Release 2021.04.03

[youtube] prioritize information from YoutubeIE for playlist entries
https://github.com/ytdl-org/youtube-dl/commit/654b4f4ff2718f38b3182c1188c5d569c14cc70a

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.24. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.03.24.1. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/yt-dlp/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running yt-dlp version **2021.02.24**
+- [ ] I've verified that I'm running yt-dlp version **2021.03.24.1**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -44,7 +44,7 @@ Add the `-v` flag to your command line you run yt-dlp with (`yt-dlp -v <your com
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.02.24
+ [debug] yt-dlp version 2021.03.24.1
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.24. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.03.24.1. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/yt-dlp/yt-dlp. yt-dlp does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.24**
+- [ ] I've verified that I'm running yt-dlp version **2021.03.24.1**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.24. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.03.24.1. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.24**
+- [ ] I've verified that I'm running yt-dlp version **2021.03.24.1**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.24. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.03.24.1. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/yt-dlp/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -30,7 +30,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running yt-dlp version **2021.02.24**
+- [ ] I've verified that I'm running yt-dlp version **2021.03.24.1**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -46,7 +46,7 @@ Add the `-v` flag to your command line you run yt-dlp with (`yt-dlp -v <your com
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.02.24
+ [debug] yt-dlp version 2021.03.24.1
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.24. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.03.24.1. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.24**
+- [ ] I've verified that I'm running yt-dlp version **2021.03.24.1**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

.gitignore

@@ -25,7 +25,9 @@ updates_key.pem
 *.class
 
 # Generated
+AUTHORS
 README.txt
+.mailmap
 *.1
 *.bash-completion
 *.fish
@@ -58,6 +60,7 @@ yt-dlp.zip
 *.mkv
 *.swf
 *.part
+*.part-*
 *.ytdl
 *.dump
 *.frag

CONTRIBUTORS

@@ -1,5 +1,6 @@
 pukkandan (owner)
 shirt-dev (collaborator)
+colethedj (collaborator)
 h-h-h-h
 pauldubois98
 nixxo
@@ -21,7 +22,16 @@ nao20010128nao
 kurumigi
 tsukumi
 bbepis
+animelover1984
 Pccode66
-Ashish
+Ashish0804
 RobinD42
-hseg
+hseg
+DennyDai
+codeasashu
+teesid
+kevinoconnor7
+damianoamatruda
+2ShedsJackson
+CXwudi
+xtkoba

Changelog.md

@@ -7,7 +7,8 @@
 * Update Changelog.md and CONTRIBUTORS
 * Change "Merged with ytdl" version in Readme.md if needed
 * Commit to master as `Release <version>`
-* Push to origin/release - build task will now run
+* Push to origin/release using `git push origin master:release`
+    build task will now run
 * Update version.py using devscripts\update-version.py
 * Run `make issuetemplates`
 * Commit to master as `[version] update :ci skip all`
@@ -17,21 +18,133 @@
 -->
 
 
+### 2021.04.03
+* Merge youtube-dl: Upto 2021.04.01 ([commit/654b4f4](https://github.com/ytdl-org/youtube-dl/commit/654b4f4ff2718f38b3182c1188c5d569c14cc70a))
+* Ability to set a specific field in the file's metadata using `--parse-metadata`
+* Ability to select n'th best format like `-f bv*.2`
+* [DiscoveryPlus] Add discoveryplus.in
+* [la7] Add podcasts and podcast playlists by [nixxo](https://github.com/nixxo)
+* [mildom] Update extractor with current proxy by [nao20010128nao](https://github.com/nao20010128nao)
+* [ard:mediathek] Fix video id extraction
+* [generic] Detect Invidious' link element
+* [youtube] Show premium state in `availability` by [colethedj](https://github.com/colethedj)
+* [viewsource] Add extractor to handle `view-source:`
+* [sponskrub] Run before embedding thumbnail
+* [documentation] Improve `--parse-metadata` documentation
+
+
+### 2021.03.24.1
+* Revert [commit/8562218](https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf)
+
+### 2021.03.24
+* Merge youtube-dl: Upto 2021.03.25 ([commit/8562218](https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf))
+* Parse metadata from multiple fields using `--parse-metadata`
+* Ability to load playlist infojson using `--load-info-json`
+* Write current epoch to infojson when using `--no-clean-infojson`
+* [youtube_live_chat] fix bug when trying to set cookies
+* [niconico] Fix for when logged in by [CXwudi](https://github.com/CXwudi) and [xtkoba](https://github.com/xtkoba)
+* [linuxacadamy] Fix login
+
+
+### 2021.03.21
+* Merge youtube-dl: Upto [commit/7e79ba7](https://github.com/ytdl-org/youtube-dl/commit/7e79ba7dd6e6649dd2ce3a74004b2044f2182881)
+* Option `--no-clean-infojson` to keep private keys in the infojson
+* [aria2c] Support retry/abort unavailable fragments by [damianoamatruda](https://github.com/damianoamatruda)
+* [aria2c] Better default arguments
+* [movefiles] Fix bugs and make more robust
+* [formatSort] Fix `quality` being ignored
+* [splitchapters] Fix for older ffmpeg
+* [sponskrub] Pass proxy to sponskrub
+* Make sure `post_hook` gets the final filename
+* Recursively remove any private keys from infojson
+* Embed video URL metadata inside `mp4` by [damianoamatruda](https://github.com/damianoamatruda) and [pukkandan](https://github.com/pukkandan)
+* Merge `webm` formats into `mkv` if thumbnails are to be embedded by [damianoamatruda](https://github.com/damianoamatruda)
+* Use headers and cookies when downloading subtitles by [damianoamatruda](https://github.com/damianoamatruda)
+* Parse resolution in info dictionary by [damianoamatruda](https://github.com/damianoamatruda)
+* More consistent warning messages by [damianoamatruda](https://github.com/damianoamatruda) and [pukkandan](https://github.com/pukkandan)
+* [documentation] Add deprecated options and aliases in readme
+* [documentation] Fix some minor mistakes
+
+* [niconico] Partial fix adapted from [animelover1984/youtube-dl@b5eff52](https://github.com/animelover1984/youtube-dl/commit/b5eff52dd9ed5565672ea1694b38c9296db3fade) (login and smile formats still don't work)
+* [niconico] Add user extractor by [animelover1984](https://github.com/animelover1984)
+* [bilibili] Add anthology support by [animelover1984](https://github.com/animelover1984)
+* [amcnetworks] Fix extractor by [2ShedsJackson](https://github.com/2ShedsJackson)
+* [stitcher] Merge from youtube-dl by [nixxo](https://github.com/nixxo)
+* [rcs] Improved extraction by [nixxo](https://github.com/nixxo)
+* [linuxacadamy] Improve regex
+* [youtube] Show if video is `private`, `unlisted` etc in info (`availability`) by [colethedj](https://github.com/colethedj) and [pukkandan](https://github.com/pukkandan)
+* [youtube] bugfix for channel playlist extraction
+* [nbc] Improve metadata extraction by [2ShedsJackson](https://github.com/2ShedsJackson)
+
+
+### 2021.03.15
+* **Split video by chapters**: using option `--split-chapters`
+    * The output file of the split files can be set with `-o`/`-P` using the prefix `chapter:`
+    * Additional keys `section_title`, `section_number`, `section_start`, `section_end` are available in the output template
+* **Parallel fragment downloads** by [shirt](https://github.com/shirt-dev)
+    * Use option `--concurrent-fragments` (`-N`) to set the number of threads (default 1)
+* Merge youtube-dl: Upto [commit/3be0980](https://github.com/ytdl-org/youtube-dl/commit/3be098010f667b14075e3dfad1e74e5e2becc8ea)
+* [zee5] Add Show Extractor by [Ashish0804](https://github.com/Ashish0804) and [pukkandan](https://github.com/pukkandan)
+* [rai] fix drm check [nixxo](https://github.com/nixxo)
+* [wimtv] Add extractor by [nixxo](https://github.com/nixxo)
+* [mtv] Add mtv.it and extract series metadata by [nixxo](https://github.com/nixxo)
+* [pluto.tv] Add extractor by [kevinoconnor7](https://github.com/kevinoconnor7)
+* [youtube] Rewrite comment extraction by [colethedj](https://github.com/colethedj)
+* [embedthumbnail] Set mtime correctly
+* Refactor some postprocessor/downloader code by [pukkandan](https://github.com/pukkandan) and [shirt](https://github.com/shirt-dev)
+
+
+### 2021.03.07
+* [youtube] Fix history, mixes, community pages and trending by [pukkandan](https://github.com/pukkandan) and [colethedj](https://github.com/colethedj)
+* [youtube] Fix private feeds/playlists on multi-channel accounts by [colethedj](https://github.com/colethedj)
+* [youtube] Extract alerts from continuation by [colethedj](https://github.com/colethedj)
+* [cbs] Add support for ParamountPlus by [shirt](https://github.com/shirt-dev)
+* [mxplayer] Rewrite extractor with show support by [pukkandan](https://github.com/pukkandan) and [Ashish0804](https://github.com/Ashish0804)
+* [gedi] Improvements from youtube-dl by [nixxo](https://github.com/nixxo)
+* [vimeo] Fix videos with password by [teesid](https://github.com/teesid)
+* [lbry] Support `lbry://` url by [nixxo](https://github.com/nixxo)
+* [bilibili] Change `Accept` header by [pukkandan](https://github.com/pukkandan) and [animelover1984](https://github.com/animelover1984)
+* [trovo] Pass origin header
+* [rai] Check for DRM by [nixxo](https://github.com/nixxo)
+* [downloader] Fix bug for `ffmpeg`/`httpie`
+* [update] Fix updater removing the executable bit on some UNIX distros
+* [update] Fix current build hash for UNIX
+* [documentation] Include wget/curl/aria2c install instructions for Unix by [Ashish0804](https://github.com/Ashish0804)
+* Fix some videos downloading with `m3u8` extension
+* Remove "fixup is ignored" warning when fixup wasn't passed by user
+
+
+### 2021.03.03.2
+* [build] Fix bug
+
+### 2021.03.03
+* [youtube] Use new browse API for continuation page extraction by [colethedj](https://github.com/colethedj) and [pukkandan](https://github.com/pukkandan)
+* Fix HLS playlist downloading by [shirt](https://github.com/shirt-dev)
+* Merge youtube-dl: Upto [2021.03.03](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.03.03)
+* [mtv] Fix extractor
+* [nick] Fix extractor by [DennyDai](https://github.com/DennyDai)
+* [mxplayer] Add new extractor by [codeasashu](https://github.com/codeasashu)
+* [youtube] Throw error when `--extractor-retries` are exhausted
+* Reduce default of `--extractor-retries` to 3
+* Fix packaging bugs by [hseg](https://github.com/hseg)
+
+
 ### 2021.03.01
 * Allow specifying path in `--external-downloader`
 * Add option `--sleep-requests` to sleep b/w requests
 * Add option `--extractor-retries` to retry on known extractor errors
 * Extract comments only when needed
 * `--get-comments` doesn't imply `--write-info-json` if `-J`, `-j` or `--print-json` are used
+* Fix `get_executable_path` by [shirt](https://github.com/shirt-dev)
 * [youtube] Retry on more known errors than just HTTP-5xx
+* [youtube] Fix inconsistent `webpage_url`
 * [tennistv] Fix format sorting
-* [readthedocs] Improvements by [shirt](https://github.com/shirt-dev)
-* [hls] Fix bug with m3u8 format extraction
 * [bilibiliaudio] Recognize the file as audio-only
 * [hrfensehen] Fix wrong import
-* [youtube] Fix inconsistent `webpage_url`
-* [hls] Enable `--hls-use-mpegts` by default when downloading live-streams
 * [viki] Fix viki play pass authentication by [RobinD42](https://github.com/RobinD42)
+* [readthedocs] Improvements by [shirt](https://github.com/shirt-dev)
+* [hls] Fix bug with m3u8 format extraction
+* [hls] Enable `--hls-use-mpegts` by default when downloading live-streams
 * [embedthumbnail] Fix bug with deleting original thumbnail
 * [build] Fix completion paths, zsh pip completion install by [hseg](https://github.com/hseg)
 * [ci] Disable download tests unless specifically invoked
@@ -42,10 +155,10 @@
 * Moved project to an organization [yt-dlp](https://github.com/yt-dlp)
 * **Completely changed project name to yt-dlp** by [Pccode66](https://github.com/Pccode66) and [pukkandan](https://github.com/pukkandan)
     * Also, `youtube-dlc` config files are no longer loaded
-* **Merge youtube-dl:** Upto [commit/4460329](https://github.com/ytdl-org/youtube-dl/commit/44603290e5002153f3ebad6230cc73aef42cc2cd) (except tmz, gedi)
+* Merge youtube-dl: Upto [commit/4460329](https://github.com/ytdl-org/youtube-dl/commit/44603290e5002153f3ebad6230cc73aef42cc2cd) (except tmz, gedi)
 * [Readthedocs](https://yt-dlp.readthedocs.io) support by [shirt](https://github.com/shirt-dev)
 * [youtube] Show if video was a live stream in info (`was_live`)
-* [Zee5] Add new extractor by [Ashish](https://github.com/Ashish) and [pukkandan](https://github.com/pukkandan)
+* [Zee5] Add new extractor by [Ashish0804](https://github.com/Ashish0804) and [pukkandan](https://github.com/pukkandan)
 * [jwplatform] Add support for `hyland.com`
 * [tennistv] Fix extractor
 * [hls] Support media initialization by [shirt](https://github.com/shirt-dev)
@@ -60,7 +173,7 @@
 
 
 ### 2021.02.19
-* **Merge youtube-dl:** Upto [commit/cf2dbec](https://github.com/ytdl-org/youtube-dl/commit/cf2dbec6301177a1fddf72862de05fa912d9869d) (except kakao)
+* Merge youtube-dl: Upto [commit/cf2dbec](https://github.com/ytdl-org/youtube-dl/commit/cf2dbec6301177a1fddf72862de05fa912d9869d) (except kakao)
 * [viki] Fix extractor
 * [niconico] Extract `channel` and `channel_id` by [kurumigi](https://github.com/kurumigi)
 * [youtube] Multiple page support for hashtag URLs
@@ -85,7 +198,7 @@
 
 
 ### 2021.02.15
-* **Merge youtube-dl:** Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
+* Merge youtube-dl: Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
 * [niconico] Improved extraction and support encrypted/SMILE movies by [kurumigi](https://github.com/kurumigi), [tsukumi](https://github.com/tsukumi), [bbepis](https://github.com/bbepis), [pukkandan](https://github.com/pukkandan)
 * Fix HLS AES-128 with multiple keys in external downloaders by [shirt](https://github.com/shirt-dev)
 * [youtube_live_chat] Fix by using POST API by [siikamiika](https://github.com/siikamiika)
@@ -128,7 +241,7 @@
 
 
 ### 2021.02.04
-* **Merge youtube-dl:** Upto [2021.02.04.1](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.04.1)
+* Merge youtube-dl: Upto [2021.02.04.1](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.04.1)
 * **Date/time formatting in output template:**
     * You can use [`strftime`](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) to format date/time fields. Example: `%(upload_date>%Y-%m-%d)s`
 * **Multiple output templates:**
@@ -182,7 +295,7 @@
 
 
 ### 2021.01.24
-* **Merge youtube-dl:** Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
+* Merge youtube-dl: Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
 * Plugin support ([documentation](https://github.com/yt-dlp/yt-dlp#plugins))
 * **Multiple paths**: New option `-P`/`--paths` to give different paths for different types of files
     * The syntax is `-P "type:path" -P "type:path"` ([documentation](https://github.com/yt-dlp/yt-dlp#:~:text=-P,%20--paths%20TYPE:PATH))
@@ -211,7 +324,7 @@
 
 
 ### 2021.01.16
-* **Merge youtube-dl:** Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
+* Merge youtube-dl: Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
 * **Configuration files:**
     * Portable configuration file: `./yt-dlp.conf`
     * Allow the configuration files to be named `yt-dlp` instead of `youtube-dlc`. See [this](https://github.com/yt-dlp/yt-dlp#configuration) for details
@@ -241,7 +354,7 @@
 * [archive.org] Fix extractor and add support for audio and playlists by [wporr](https://github.com/wporr)
 * [Animelab] Added by [mariuszskon](https://github.com/mariuszskon)
 * [youtube:search] Fix view_count by [ohnonot](https://github.com/ohnonot)
-* [youtube] Show if video is embeddable in info
+* [youtube] Show if video is embeddable in info (`playable_in_embed`)
 * Update version badge automatically in README
 * Enable `test_youtube_search_matching`
 * Create `to_screen` and similar functions in postprocessor/common
@@ -257,9 +370,8 @@
 
 
 ### 2021.01.08
-* **Merge youtube-dl:** Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.08)
+* Merge youtube-dl: Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.08) except stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f))
-    * Extractor stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f)) have not been merged
+* Moved changelog to separate file
-* Moved changelog to seperate file
 
 
 ### 2021.01.07-1
@@ -297,7 +409,7 @@
     * Changed video format sorting to show video only files and video+audio files together.
     * Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
     * Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
-* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
+* Shortcut Options: Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
 * **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-sponsorblock-options) for details
 * Added `--force-download-archive` (`--force-write-archive`) by [h-h-h-h](https://github.com/h-h-h-h)
 * Added `--list-formats-as-table`,  `--list-formats-old`
@@ -307,36 +419,38 @@
 * Relaxed validation for format filters so that any arbitrary field can be used
 * Fix for embedding thumbnail in mp3 by [pauldubois98](https://github.com/pauldubois98) ([ytdl-org/youtube-dl#21569](https://github.com/ytdl-org/youtube-dl/pull/21569))
 * Make Twitch Video ID output from Playlist and VOD extractor same. This is only a temporary fix
-* **Merge youtube-dl:** Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
+* Merge youtube-dl: Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
     * Extractors [tiktok](https://github.com/ytdl-org/youtube-dl/commit/fb626c05867deab04425bad0c0b16b55473841a2) and [hotstar](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc) have not been merged
 * Cleaned up the fork for public use
 
 
+**PS**: All uncredited changes above this point are authored by [pukkandan](https://github.com/pukkandan)
+
 ### Unreleased changes in [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc)
-* Updated to youtube-dl release 2020.11.26
+* Updated to youtube-dl release 2020.11.26 by [pukkandan](https://github.com/pukkandan)
-* [youtube]
+* Youtube improvements by [pukkandan](https://github.com/pukkandan)
     * Implemented all Youtube Feeds (ytfav, ytwatchlater, ytsubs, ythistory, ytrec) and SearchURL
-    * Fix ytsearch not returning results sometimes due to promoted content
-    * Temporary fix for automatic captions - disable json3
     * Fix some improper Youtube URLs
     * Redirect channel home to /video
     * Print youtube's warning message
-    * Multiple pages are handled better for feeds
+    * Handle Multiple pages for feeds better
+* [youtube] Fix ytsearch not returning results sometimes due to promoted content by [colethedj](https://github.com/colethedj)
+* [youtube] Temporary fix for automatic captions - disable json3 by [blackjack4494](https://github.com/blackjack4494)
 * Add --break-on-existing by [gergesh](https://github.com/gergesh)
-* Pre-check video IDs in the archive before downloading
+* Pre-check video IDs in the archive before downloading by [pukkandan](https://github.com/pukkandan)
-* [bitwave.tv] New extractor
+* [bitwave.tv] New extractor by [lorpus](https://github.com/lorpus)
-* [Gedi] Add extractor
+* [Gedi] Add extractor by [nixxo](https://github.com/nixxo)
-* [Rcs] Add new extractor
+* [Rcs] Add new extractor by [nixxo](https://github.com/nixxo)
-* [skyit] Add support for multiple Sky Italia website and removed old skyitalia extractor
+* [skyit] New skyitalia extractor by [nixxo](https://github.com/nixxo)
-* [france.tv] Fix thumbnail URL
+* [france.tv] Fix thumbnail URL by [renalid](https://github.com/renalid)
-* [ina] support mobile links
+* [ina] support mobile links by [B0pol](https://github.com/B0pol)
-* [instagram] Fix extractor
+* [instagram] Fix thumbnail extractor by [nao20010128nao](https://github.com/nao20010128nao)
-* [itv] BTCC new pages' URL update (articles instead of races)
+* [SouthparkDe] Support for English URLs by [xypwn](https://github.com/xypwn)
-* [SouthparkDe] Support for English URLs
+* [spreaker] fix SpreakerShowIE test URL by [pukkandan](https://github.com/pukkandan)
-* [spreaker] fix SpreakerShowIE test URL
+* [Vlive] Fix playlist handling when downloading a channel by [kyuyeunk](https://github.com/kyuyeunk)
-* [Vlive] Fix playlist handling when downloading a channel
+* [tmz] Fix extractor by [diegorodriguezv](https://github.com/diegorodriguezv)
-* [generic] Detect embedded bitchute videos
+* [generic] Detect embedded bitchute videos by [pukkandan](https://github.com/pukkandan)
-* [generic] Extract embedded youtube and twitter videos
+* [generic] Extract embedded youtube and twitter videos by [diegorodriguezv](https://github.com/diegorodriguezv)
-* [ffmpeg] Ensure all streams are copied
+* [ffmpeg] Ensure all streams are copied by [pukkandan](https://github.com/pukkandan)
-* Fix for os.rename error when embedding thumbnail to video in a different drive
+* [embedthumbnail] Fix for os.rename error by [pukkandan](https://github.com/pukkandan)
-* make_win.bat: don't use UPX to pack vcruntime140.dll
+* make_win.bat: don't use UPX to pack vcruntime140.dll by [jbruchon](https://github.com/jbruchon)

MANIFEST.in

@@ -1,9 +1,9 @@
-include README.md
-include LICENSE
 include AUTHORS
-include ChangeLog
+include Changelog.md
-include yt-dlp.bash-completion
+include LICENSE
-include yt-dlp.fish
+include README.md
+include completions/*/*
+include supportedsites.md
 include yt-dlp.1
-recursive-include docs Makefile conf.py *.rst
+recursive-include devscripts *
 recursive-include test *

Makefile

@@ -1,12 +1,28 @@
-all: yt-dlp doc man
+all: yt-dlp doc pypi-files
+clean: clean-test clean-dist clean-cache
+completions: completion-bash completion-fish completion-zsh
 doc: README.md CONTRIBUTING.md issuetemplates supportedsites
-man: README.txt yt-dlp.1 bash-completion zsh-completion fish-completion
+ot: offlinetest
+tar: yt-dlp.tar.gz
 
+# Keep this list in sync with MANIFEST.in
+# intended use: when building a source distribution,
+# make pypi-files && python setup.py sdist
+pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites completions yt-dlp.1 devscripts/* test/*
 
-clean:
+.PHONY: all clean install test tar pypi-files completions ot offlinetest codetest supportedsites
-	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ yt_dlp/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec *.frag *.frag.urls *.frag.aria2 CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe
+
-	find . -name "*.pyc" -delete
+clean-test:
-	find . -name "*.class" -delete
+	rm -rf *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.frag *.frag.urls *.frag.aria2
+clean-dist:
+	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS .mailmap
+clean-cache:
+	find . -name "*.pyc" -o -name "*.class" -delete
+
+completion-bash: completions/bash/yt-dlp
+completion-fish: completions/fish/yt-dlp.fish
+completion-zsh: completions/zsh/_yt-dlp
+lazy-extractors: yt_dlp/extractor/lazy_extractors.py
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin
@@ -21,7 +37,7 @@ SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then ech
 # set markdown input format to "markdown-smart" for pandoc version 2 and to "markdown" for pandoc prior to version 2
 MARKDOWN = $(shell if [ `pandoc -v | head -n1 | cut -d" " -f2 | head -c1` = "2" ]; then echo markdown-smart; else echo markdown; fi)
 
-install: yt-dlp yt-dlp.1 bash-completion zsh-completion fish-completion
+install: yt-dlp yt-dlp.1 completions
 	install -Dm755 yt-dlp $(DESTDIR)$(BINDIR)
 	install -Dm644 yt-dlp.1 $(DESTDIR)$(MANDIR)/man1
 	install -Dm644 completions/bash/yt-dlp $(DESTDIR)$(SHAREDIR)/bash-completion/completions/yt-dlp
@@ -36,8 +52,6 @@ test:
 	nosetests --verbose test
 	$(MAKE) codetest
 
-ot: offlinetest
-
 # Keep this list in sync with devscripts/run_tests.sh
 offlinetest: codetest
 	$(PYTHON) -m nose --verbose test \
@@ -52,12 +66,6 @@ offlinetest: codetest
 		--exclude test_youtube_signature.py \
 		--exclude test_post_hooks.py
 
-tar: yt-dlp.tar.gz
-
-.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
-
-pypi-files: README.txt yt-dlp.1 bash-completion zsh-completion fish-completion
-
 yt-dlp: yt_dlp/*.py yt_dlp/*/*.py
 	mkdir -p zip
 	for d in yt_dlp yt_dlp/downloader yt_dlp/extractor yt_dlp/postprocessor ; do \
@@ -101,28 +109,20 @@ completions/bash/yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/bash-completion.in
 	mkdir -p completions/bash
 	$(PYTHON) devscripts/bash-completion.py
 
-bash-completion: completions/bash/yt-dlp
-
 completions/zsh/_yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/zsh-completion.in
 	mkdir -p completions/zsh
 	$(PYTHON) devscripts/zsh-completion.py
 
-zsh-completion: completions/zsh/_yt-dlp
-
 completions/fish/yt-dlp.fish: yt_dlp/*.py yt_dlp/*/*.py devscripts/fish-completion.in
 	mkdir -p completions/fish
 	$(PYTHON) devscripts/fish-completion.py
 
-fish-completion: completions/fish/yt-dlp.fish
-
-lazy-extractors: yt_dlp/extractor/lazy_extractors.py
-
 _EXTRACTOR_FILES = $(shell find yt_dlp/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
 yt_dlp/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 
-yt-dlp.tar.gz: yt-dlp README.md README.txt yt-dlp.1 bash-completion zsh-completion fish-completion ChangeLog AUTHORS
+yt-dlp.tar.gz: README.md yt-dlp.1 completions Changelog.md AUTHORS
-	@tar -czf yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
+	@tar -czf $(DESTDIR)/yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
 		--exclude '*.pyc' \
@@ -132,7 +132,13 @@ yt-dlp.tar.gz: yt-dlp README.md README.txt yt-dlp.1 bash-completion zsh-completi
 		--exclude '.git' \
 		--exclude 'docs/_build' \
 		-- \
-		bin devscripts test yt_dlp docs \
+		devscripts test \
-		ChangeLog AUTHORS LICENSE README.md supportedsites.md README.txt \
+		Changelog.md AUTHORS LICENSE README.md supportedsites.md \
 		Makefile MANIFEST.in yt-dlp.1 completions \
 		setup.py setup.cfg yt-dlp
+
+AUTHORS: .mailmap
+	git shortlog -s -n | cut -f2 | sort > AUTHORS
+
+.mailmap:
+	git shortlog -s -e -n | awk '!(out[$$NF]++) { $$1="";sub(/^[ \t]+/,""); print}' > .mailmap

README.md

@@ -3,7 +3,7 @@
 [![Release version](https://img.shields.io/github/v/release/yt-dlp/yt-dlp?color=brightgreen&label=Release)](https://github.com/yt-dlp/yt-dlp/releases/latest)
 [![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](LICENSE)
 [![CI Status](https://github.com/yt-dlp/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/yt-dlp/yt-dlp/actions)
-[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&label=discord&logo=discord)](https://discord.gg/S75JaBna)  
+[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&label=discord&logo=discord)](https://discord.gg/H5MNcFW63r)  
 
 [![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits)](https://github.com/yt-dlp/yt-dlp/commits)
 [![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master)](https://github.com/yt-dlp/yt-dlp/commits)
@@ -13,7 +13,7 @@
 
 A command-line program to download videos from youtube.com and many other [video platforms](supportedsites.md)
 
-This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which is inturn a fork of [youtube-dl](https://github.com/ytdl-org/youtube-dl)
+This is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on the now inactive [youtube-dlc](https://github.com/blackjack4494/yt-dlc). The main focus of this project is adding new features and patches while also keeping up to date with the original project
 
 * [NEW FEATURES](#new-features)
 * [INSTALLATION](#installation)
@@ -46,7 +46,10 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
     * [Filtering Formats](#filtering-formats)
     * [Sorting Formats](#sorting-formats)
     * [Format Selection examples](#format-selection-examples)
+* [MODIFYING METADATA](#modifying-metadata)
+    * [Modifying metadata examples](#modifying-metadata-examples)
 * [PLUGINS](#plugins)
+* [DEPRECATED OPTIONS](#deprecated-options)
 * [MORE](#more)
 
 
@@ -57,7 +60,7 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
 
 * **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
 
-* **Merged with youtube-dl v2021.02.22**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
+* **Merged with youtube-dl v2021.04.01**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
 
 * **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--get-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, Playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
 
@@ -66,17 +69,19 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
     * Youtube search (`ytsearch:`, `ytsearchdate:`) along with Search URLs works correctly
     * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
 
+* **Split video by chapters**: Videos can be split into multiple files based on chapters using `--split-chapters`
+
+* **Multithreaded fragment downloads**: Fragment downloads can be natively multi-threaded. Use `--concurrent-fragments` (`-N`) option to set the number of threads used
+
 * **Aria2c with HLS/DASH**: You can use aria2c as the external downloader for DASH(mpd) and HLS(m3u8) formats. No more slow ffmpeg/native downloads
 
-* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5
+* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv
 
-* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina, rumble, tennistv
+* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina, rumble, tennistv, amcnetworks
 
-* **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
+* **Plugin extractors**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
 
-* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to. See [`--paths`](https://github.com/yt-dlp/yt-dlp/#:~:text=-P,%20--paths%20TYPE:PATH) for details
+* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to using `--paths` (`-P`)
-
-<!-- Relative link doesn't work for "#:~:text=" -->
 
 * **Portable Configuration**: Configuration files are automatically loaded from the home and root directories. See [configuration](#configuration) for details
 
@@ -103,6 +108,23 @@ You can install yt-dlp using one of the following methods:
 * Use pip+git: `python -m pip install --upgrade git+https://github.com/yt-dlp/yt-dlp.git@release`
 * Install master branch: `python -m pip install --upgrade git+https://github.com/yt-dlp/yt-dlp`
 
+UNIX users (Linux, macOS, BSD) can also install the [latest release](https://github.com/yt-dlp/yt-dlp/releases/latest) one of the following ways:
+
+```
+sudo curl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
+```
+sudo wget https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -O /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
+```
+sudo aria2c https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
 ### UPDATE
 Starting from version `2021.02.09`, you can use `yt-dlp -U` to update if you are using the provided release.
 If you are using `pip`, simply re-run the same command that was used to install the program.
@@ -177,7 +199,7 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
                                      only list them
     --no-flat-playlist               Extract the videos of a playlist
     --mark-watched                   Mark videos watched (YouTube only)
-    --no-mark-watched                Do not mark videos watched
+    --no-mark-watched                Do not mark videos watched (default)
     --no-colors                      Do not emit color codes in output
 
 ## Network Options:
@@ -280,6 +302,8 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --no-include-ads                 Do not download advertisements (default)
 
 ## Download Options:
+    -N, --concurrent-fragments N     Number of fragments to download
+                                     concurrently (default is 1)
     -r, --limit-rate RATE            Maximum download rate in bytes per second
                                      (e.g. 50K or 4.2M)
     -R, --retries RETRIES            Number of retries (default is 10), or
@@ -402,6 +426,11 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
                                      --write-description etc. (default)
     --no-write-playlist-metafiles    Do not write playlist metadata when using
                                      --write-info-json, --write-description etc.
+    --clean-infojson                 Remove some private fields such as
+                                     filenames from the infojson. Note that it
+                                     could still contain some personal
+                                     information (default)
+    --no-clean-infojson              Write all fields to the infojson
     --get-comments                   Retrieve video comments to be placed in the
                                      .info.json file. The comments are fetched
                                      even without this option if the extraction
@@ -445,7 +474,8 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --no-warnings                    Ignore warnings
     -s, --simulate                   Do not download the video and do not write
                                      anything to disk
-    --skip-download                  Do not download the video
+    --skip-download                  Do not download the video but write all
+                                     related files (Alias: --no-download)
     -g, --get-url                    Simulate, quiet but print URL
     -e, --get-title                  Simulate, quiet but print title
     --get-id                         Simulate, quiet but print id
@@ -482,7 +512,7 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --encoding ENCODING              Force the specified encoding (experimental)
     --no-check-certificate           Suppress HTTPS certificate validation
     --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
+                                     information about the video (Currently
                                      supported only for YouTube)
     --user-agent UA                  Specify a custom user agent
     --referer URL                    Specify a custom referer, use if the video
@@ -496,15 +526,11 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --sleep-requests SECONDS         Number of seconds to sleep between requests
                                      during data extraction
     --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download when used alone or a lower bound
+                                     download. This is the minimum time to sleep
-                                     of a range for randomized sleep before each
+                                     when used along with --max-sleep-interval
-                                     download (minimum possible number of
+                                     (Alias: --min-sleep-interval)
-                                     seconds to sleep) when used along with
+    --max-sleep-interval SECONDS     Maximum number of seconds to sleep. Can
-                                     --max-sleep-interval
+                                     only be used along with --min-sleep-interval
-    --max-sleep-interval SECONDS     Upper bound of a range for randomized sleep
-                                     before each download (maximum possible
-                                     number of seconds to sleep). Must only be
-                                     used along with --min-sleep-interval
     --sleep-subtitles SECONDS        Number of seconds to sleep before each
                                      subtitle download
 
@@ -554,16 +580,16 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --write-subs                     Write subtitle file
     --no-write-subs                  Do not write subtitle file (default)
     --write-auto-subs                Write automatically generated subtitle file
-                                     (YouTube only)
+                                     (Alias: --write-automatic-subs)
-    --no-write-auto-subs             Do not write automatically generated
+    --no-write-auto-subs             Do not write auto-generated subtitles
-                                     subtitle file (default)
+                                     (default) (Alias: --no-write-automatic-subs)
     --all-subs                       Download all the available subtitles of the
                                      video
     --list-subs                      List all available subtitles for the video
     --sub-format FORMAT              Subtitle format, accepts formats
                                      preference, for example: "srt" or
                                      "ass/srt/best"
-    --sub-lang LANGS                 Languages of the subtitles to download
+    --sub-langs LANGS                Languages of the subtitles to download
                                      (optional) separated by commas, use --list-
                                      subs for available language tags
 
@@ -617,18 +643,19 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
                                      ExtractAudio, VideoRemuxer, VideoConvertor,
                                      EmbedSubtitle, Metadata, Merger,
                                      FixupStretched, FixupM4a, FixupM3u8,
-                                     SubtitlesConvertor and EmbedThumbnail. The
+                                     SubtitlesConvertor, EmbedThumbnail and
-                                     supported executables are: SponSkrub,
+                                     SplitChapters. The supported executables
-                                     FFmpeg, FFprobe, and AtomicParsley. You can
+                                     are: SponSkrub, FFmpeg, FFprobe, and
-                                     also specify "PP+EXE:ARGS" to give the
+                                     AtomicParsley. You can also specify
-                                     arguments to the specified executable only
+                                     "PP+EXE:ARGS" to give the arguments to the
-                                     when being used by the specified
+                                     specified executable only when being used
-                                     postprocessor. Additionally, for
+                                     by the specified postprocessor.
-                                     ffmpeg/ffprobe, a number can be appended to
+                                     Additionally, for ffmpeg/ffprobe, "_i"/"_o"
-                                     the exe name seperated by "_i" to pass the
+                                     can be appended to the prefix optionally
-                                     argument before the specified input file.
+                                     followed by a number to pass the argument
-                                     Eg: --ppa "Merger+ffmpeg_i1:-v quiet". You
+                                     before the specified input/output file. Eg:
-                                     can use this option multiple times to give
+                                     --ppa "Merger+ffmpeg_i1:-v quiet". You can
+                                     use this option multiple times to give
                                      different arguments to different
                                      postprocessors. (Alias: --ppa)
     -k, --keep-video                 Keep the intermediate video file on disk
@@ -644,20 +671,9 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
     --no-embed-thumbnail             Do not embed thumbnail (default)
     --add-metadata                   Write metadata to the video file
     --no-add-metadata                Do not write metadata (default)
-    --parse-metadata FIELD:FORMAT    Parse additional metadata like title/artist
+    --parse-metadata FROM:TO         Parse additional metadata like title/artist
-                                     from other fields. Give field name to
+                                     from other fields; see "MODIFYING METADATA"
-                                     extract data from, and format of the field
+                                     for details
-                                     seperated by a ":". Either regular
-                                     expression with named capture groups or a
-                                     similar syntax to the output template can
-                                     also be used. The parsed parameters replace
-                                     any existing values and can be use in
-                                     output template. This option can be used
-                                     multiple times. Example: --parse-metadata
-                                     "title:%(artist)s - %(title)s" matches a
-                                     title like "Coldplay - Paradise". Example
-                                     (regex): --parse-metadata
-                                     "description:Artist - (?P<artist>.+?)"
     --xattrs                         Write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the
@@ -672,8 +688,16 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
                                      downloading and post-processing, similar to
                                      find's -exec syntax. Example: --exec 'adb
                                      push {} /sdcard/Music/ && rm {}'
-    --convert-subs FORMAT            Convert the subtitles to other format
+    --convert-subs FORMAT            Convert the subtitles to another format
                                      (currently supported: srt|ass|vtt|lrc)
+                                     (Alias: --convert-subtitles)
+    --split-chapters                 Split video into multiple files based on
+                                     internal chapters. The "chapter:" prefix
+                                     can be used with "--paths" and "--output"
+                                     to set the output filename for the split
+                                     files. See "OUTPUT TEMPLATE" for details
+    --no-split-chapters              Do not split video based on chapters
+                                     (default)
 
 ## SponSkrub (SponsorBlock) Options:
 [SponSkrub](https://github.com/yt-dlp/SponSkrub) is a utility to
@@ -698,7 +722,7 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
 
 ## Extractor Options:
     --extractor-retries RETRIES      Number of retries for known extractor
-                                     errors (default is 10), or "infinite"
+                                     errors (default is 3), or "infinite"
     --allow-dynamic-mpd              Process dynamic DASH manifests (default)
                                      (Alias: --no-ignore-dynamic-mpd)
     --ignore-dynamic-mpd             Do not process dynamic DASH manifests
@@ -789,9 +813,9 @@ The `-o` option is used to indicate a template for the output file names while `
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `yt-dlp -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Date/time fields can also be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses seperated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
+The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `yt-dlp -o funny_video.flv "https://some/video"` (hard-coding file extension like this is not recommended). However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Date/time fields can also be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses separated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
 
-Additionally, you can set different output templates for the various metadata files seperately from the general output template by specifying the type of file followed by the template seperated by a colon ":". The different filetypes supported are `subtitle|thumbnail|description|annotation|infojson|pl_description|pl_infojson`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'`  will put the thumbnails in a folder with the same name as the video.
+Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon ":". The different filetypes supported are `subtitle`, `thumbnail`, `description`, `annotation`, `infojson`, `pl_description`, `pl_infojson`, `chapter`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'`  will put the thumbnails in a folder with the same name as the video.
 
 The available fields are:
 
@@ -800,6 +824,7 @@ The available fields are:
  - `url` (string): Video URL
  - `ext` (string): Video filename extension
  - `alt_title` (string): A secondary title of the video
+ - `description` (string): The description of the video
  - `display_id` (string): An alternative identifier for the video
  - `uploader` (string): Full name of the video uploader
  - `license` (string): License name the video is licensed under
@@ -823,6 +848,7 @@ The available fields are:
  - `is_live` (boolean): Whether this video is a live stream or a fixed-length video
  - `was_live` (boolean): Whether this video was originally a live stream
  - `playable_in_embed` (string): Whether this video is allowed to play in embedded players on other sites
+ - `availability` (string): Whether the video is 'private', 'premium_only', 'subscriber_only', 'needs_auth', 'unlisted' or 'public'
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
  - `format` (string): A human-readable description of the format
@@ -882,6 +908,13 @@ Available for the media that is a track or a part of a music album:
  - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
  - `release_year` (numeric): Year (YYYY) when the album was released
 
+Available for `chapter:` prefix when using `--split-chapters` for videos with internal chapters:
+
+ - `section_title` (string): Title of the chapter
+ - `section_number` (numeric): Number of the chapter within the file
+ - `section_start` (numeric): Start time of the chapter in seconds
+ - `section_end` (numeric): End time of the chapter in seconds
+
 Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
 
 For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKcj`, this will result in a `yt-dlp test video-BaW_jenozKcj.mp4` file created in the current directory.
@@ -914,7 +947,7 @@ youtube-dl_test_video_.mp4          # A simple file name
 # Download YouTube playlist videos in separate directory indexed by video order in a playlist
 $ yt-dlp -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
 
-# Download YouTube playlist videos in seperate directories according to their uploaded year
+# Download YouTube playlist videos in separate directories according to their uploaded year
 $ yt-dlp -o '%(upload_date>%Y)s/%(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
 
 # Download all playlists of YouTube channel/user keeping each playlist in separate directory:
@@ -935,7 +968,7 @@ $ yt-dlp -o - BaW_jenozKc
 By default, yt-dlp tries to download the best available quality if you **don't** pass any options.
 This is generally equivalent to using `-f bestvideo*+bestaudio/best`. However, if multiple audiostreams is enabled (`--audio-multistreams`), the default format changes to `-f bestvideo+bestaudio/best`. Similarly, if ffmpeg is unavailable, or if you use yt-dlp to stream to `stdout` (`-o -`), the default becomes `-f best/bestvideo+bestaudio`.
 
-The general syntax for format selection is `--f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
+The general syntax for format selection is `-f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
 
 **tl;dr:** [navigate me to examples](#format-selection-examples).
 
@@ -959,7 +992,9 @@ You can also use special names to select particular edge case formats:
  - `ba*`, `bestaudio*`: Select the best quality format that contains audio. It may also contain video. Equivalent to `best*[acodec!=none]`
  - `wa*`, `worstaudio*`: Select the worst quality format that contains audio. It may also contain video. Equivalent to `worst*[acodec!=none]`
 
-For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recomended to never actually use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps` instead of `-f worst`. See [sorting formats](#sorting-formats) for more details.
+For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recomended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps` instead of `-f worst`. See [sorting formats](#sorting-formats) for more details.
+
+You can select the n'th best format of a type by using `best<type>.<n>`. For example, `best.2` will select the 2nd best combined format. Similarly, `bv*.3` will select the 3rd best format that contains a video stream.
 
 If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download.
 
@@ -1030,7 +1065,7 @@ You can change the criteria for being considered the `best` by using `-S` (`--fo
  - `br`: Equivalent to using `tbr,vbr,abr`
  - `asr`: Audio sample rate in Hz
 
-Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, seperated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
+Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, separated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
 
 The fields `hasvid`, `ie_pref`, `lang` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `quality,res,fps,codec:vp9.2,size,br,asr,proto,ext,hasaud,source,id`. Note that the extractors may override this default order, but they cannot override the user-provided order.
 
@@ -1155,11 +1190,72 @@ $ yt-dlp -S 'res:720,fps'
 $ yt-dlp -S '+res:480,codec,br'
 ```
 
+# MODIFYING METADATA
+
+The metadata obtained the the extractors can be modified by using `--parse-metadata FROM:TO`. The general syntax is to give the name of a field or a template (with similar syntax to [output template](#output-template)) to extract data from, and the format to interpret it as, separated by a colon ":". Either a [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax) with named capture groups or a similar syntax to the [output template](#output-template) (only `%(field)s` formatting is supported) can be used for `TO`. The option can be used multiple times to parse and modify various fields.
+
+Note that any field created by this can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--add-metadata`.
+
+You can also use this to change only the metadata that is embedded in the media file. To do this, set the value of the corresponding field with a `meta_` prefix. For example, any value you set to `meta_description` field will be added to the `description` field in the file. You can use this to set a different "description" and "synopsis", for example.
+
+## Modifying metadata examples
+
+Note that on Windows you may need to use double quotes instead of single.
+
+```bash
+# Interpret the title as "Artist - Title"
+$ yt-dlp --parse-metadata 'title:%(artist)s - %(title)s'
+
+# Regex example
+$ yt-dlp --parse-metadata 'description:Artist - (?P<artist>.+)'
+
+# Set title as "Series name S01E05"
+$ yt-dlp --parse-metadata '%(series)s S%(season_number)02dE%(episode_number)02d:%(title)s'
+
+# Set "comment" field in video metadata using description instead of webpage_url
+$ yt-dlp --parse-metadata 'description:(?s)(?P<meta_comment>.+)' --add-metadata
+
+```
+
 # PLUGINS
 
 Plugins are loaded from `<root-dir>/ytdlp_plugins/<type>/__init__.py`. Currently only `extractor` plugins are supported. Support for `downloader` and `postprocessor` plugins may be added in the future. See [ytdlp_plugins](ytdlp_plugins) for example.
 
 **Note**: `<root-dir>` is the directory of the binary (`<root-dir>/yt-dlp`), or the root directory of the module if you are running directly from source-code (`<root dir>/yt_dlp/__main__.py`)
 
+# DEPRECATED OPTIONS
+
+These are all the deprecated options and the current alternative to achieve the same effect
+
+    --cn-verification-proxy URL      --geo-verification-proxy URL
+    --id                             -o "%(id)s.%(ext)s"
+    -A, --auto-number                -o "%(autonumber)s-%(id)s.%(ext)s"
+    -t, --title                      -o "%(title)s-%(id)s.%(ext)s"
+    -l, --literal                    -o accepts literal names
+    --autonumber-size NUMBER         Use string formatting. Eg: %(autonumber)03d
+    --metadata-from-title FORMAT     --parse-metadata "%(title)s:FORMAT"
+    --prefer-avconv                  avconv is no longer officially supported (Alias: --no-prefer-ffmpeg)
+    --prefer-ffmpeg                  Default (Alias: --no-prefer-avconv)
+    --avconv-location                avconv is no longer officially supported
+    -C, --call-home                  Not implemented
+    --no-call-home                   Default
+    --write-srt                      --write-subs
+    --no-write-srt                   --no-write-subs
+    --srt-lang LANGS                 --sub-langs LANGS
+    --prefer-unsecure                --prefer-insecure
+    --rate-limit RATE                --limit-rate RATE
+    --force-write-download-archive   --force-write-archive
+    --dump-intermediate-pages        --dump-pages
+    --dump-headers                   --print-traffic
+    --youtube-print-sig-code         No longer supported
+    --trim-file-names LENGTH         --trim-filenames LENGTH
+    --yes-overwrites                 --force-overwrites
+    --load-info                      --load-info-json
+    --split-tracks                   --split-chapters
+    --no-split-tracks                --no-split-chapters
+    --sponskrub-args ARGS            --ppa "sponskrub:ARGS"
+    --test                           Only used for testing extractors
+
+
 # MORE
 For FAQ, Developer Instructions etc., see the [original README](https://github.com/ytdl-org/youtube-dl#faq)

devscripts/release.sh

@@ -61,7 +61,7 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
 if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
-read -p "Is ChangeLog up to date? (y/n) " -n 1
+read -p "Is Changelog up to date? (y/n) " -n 1
 if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
@@ -75,12 +75,12 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" yt_dlp/version.py
 
-/bin/echo -e "\n### Changing version in ChangeLog..."
+/bin/echo -e "\n### Changing version in Changelog..."
-sed -i "s/<unreleased>/$version/" ChangeLog
+sed -i "s/<unreleased>/$version/" Changelog.md
 
 /bin/echo -e "\n### Committing documentation, templates and yt_dlp/version.py..."
 make README.md CONTRIBUTING.md issuetemplates supportedsites
-git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE/1_broken_site.md .github/ISSUE_TEMPLATE/2_site_support_request.md .github/ISSUE_TEMPLATE/3_site_feature_request.md .github/ISSUE_TEMPLATE/4_bug_report.md .github/ISSUE_TEMPLATE/5_feature_request.md .github/ISSUE_TEMPLATE/6_question.md docs/supportedsites.md yt_dlp/version.py ChangeLog
+git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE/1_broken_site.md .github/ISSUE_TEMPLATE/2_site_support_request.md .github/ISSUE_TEMPLATE/3_site_feature_request.md .github/ISSUE_TEMPLATE/4_bug_report.md .github/ISSUE_TEMPLATE/5_feature_request.md .github/ISSUE_TEMPLATE/6_question.md docs/supportedsites.md yt_dlp/version.py Changelog.md
 git commit $gpg_sign_commits -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
@@ -111,7 +111,7 @@ RELEASE_FILES="yt-dlp yt-dlp.exe yt-dlp-$version.tar.gz"
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 
 ROOT=$(pwd)
-python devscripts/create-github-release.py ChangeLog $version "$ROOT/build/$version"
+python devscripts/create-github-release.py Changelog.md $version "$ROOT/build/$version"
 
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 

setup.py

@@ -27,9 +27,9 @@ if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     print("inv")
 else:
     files_spec = [
-        ('share/bash-completion/completions', ['completions/bash/*']),
+        ('share/bash-completion/completions', ['completions/bash/yt-dlp']),
-        ('share/zsh/site-functions', ['completions/zsh/*']),
+        ('share/zsh/site-functions', ['completions/zsh/_yt-dlp']),
-        ('share/fish/vendor_completions.d', ['completions/fish/*']),
+        ('share/fish/vendor_completions.d', ['completions/fish/yt-dlp.fish']),
         ('share/doc/yt_dlp', ['README.txt']),
         ('share/man/man1', ['yt-dlp.1'])
     ]
@@ -39,7 +39,7 @@ else:
         resfiles = []
         for fn in files:
             if not os.path.exists(fn):
-                warnings.warn('Skipping file %s since it is not present. Type  make  to build all automatically generated files.' % fn)
+                warnings.warn('Skipping file %s since it is not present. Try running `make pypi-files` first.' % fn)
             else:
                 resfiles.append(fn)
         data_files.append((dirname, resfiles))

supportedsites.md

@@ -89,6 +89,7 @@
  - **awaan:video**
  - **AZMedien**: AZ Medien videos
  - **BaiduVideo**: 百度视频
+ - **bandaichannel**
  - **Bandcamp**
  - **Bandcamp:album**
  - **Bandcamp:weekly**
@@ -96,7 +97,8 @@
  - **bbc**: BBC
  - **bbc.co.uk**: BBC iPlayer
  - **bbc.co.uk:article**: BBC articles
- - **bbc.co.uk:iplayer:playlist**
+ - **bbc.co.uk:iplayer:episodes**
+ - **bbc.co.uk:iplayer:group**
  - **bbc.co.uk:playlist**
  - **BBVTV**
  - **Beatport**
@@ -247,6 +249,7 @@
  - **DiscoveryGoPlaylist**
  - **DiscoveryNetworksDe**
  - **DiscoveryPlus**
+ - **DiscoveryPlusIndia**
  - **DiscoveryVR**
  - **Disney**
  - **dlive:stream**
@@ -346,8 +349,7 @@
  - **Gaskrank**
  - **Gazeta**
  - **GDCVault**
- - **Gedi**
+ - **GediDigital**
- - **GediEmbeds**
  - **generic**: Generic downloader that works on some sites
  - **Gfycat**
  - **GiantBomb**
@@ -456,6 +458,8 @@
  - **kuwo:singer**: 酷我音乐 - 歌手
  - **kuwo:song**: 酷我音乐
  - **la7.it**
+ - **la7.it:pod:episode**
+ - **la7.it:podcast**
  - **laola1tv**
  - **laola1tv:embed**
  - **lbry**
@@ -543,6 +547,7 @@
  - **mixcloud:playlist**
  - **mixcloud:user**
  - **MLB**
+ - **MLBVideo**
  - **Mnet**
  - **MNetTV**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@@ -561,6 +566,8 @@
  - **mtg**: MTG services
  - **mtv**
  - **mtv.de**
+ - **mtv.it**
+ - **mtv.it:programma**
  - **mtv:video**
  - **mtvjapan**
  - **mtvservices:embedded**
@@ -570,6 +577,7 @@
  - **mva:course**: Microsoft Virtual Academy courses
  - **Mwave**
  - **MwaveMeetGreet**
+ - **Mxplayer**
  - **MyChannels**
  - **MySpace**
  - **MySpace:album**
@@ -631,6 +639,7 @@
  - **nicknight**
  - **niconico**: ニコニコ動画
  - **NiconicoPlaylist**
+ - **NiconicoUser**
  - **Nintendo**
  - **Nitter**
  - **njoy**: N-JOY
@@ -701,6 +710,9 @@
  - **OutsideTV**
  - **PacktPub**
  - **PacktPubCourse**
+ - **PalcoMP3:artist**
+ - **PalcoMP3:song**
+ - **PalcoMP3:video**
  - **pandora.tv**: 판도라TV
  - **ParamountNetwork**
  - **parliamentlive.tv**: UK parliament videos
@@ -733,6 +745,7 @@
  - **Playwire**
  - **pluralsight**
  - **pluralsight:course**
+ - **PlutoTV**
  - **podomatic**
  - **Pokemon**
  - **PokemonWatch**
@@ -913,6 +926,7 @@
  - **stanfordoc**: Stanford Open ClassRoom
  - **Steam**
  - **Stitcher**
+ - **StitcherShow**
  - **StoryFire**
  - **StoryFireSeries**
  - **StoryFireUser**
@@ -1085,6 +1099,7 @@
  - **Vidbit**
  - **Viddler**
  - **Videa**
+ - **video.arnes.si**: Arnes Video
  - **video.google:search**: Google Video search
  - **video.sky.it**
  - **video.sky.it:live**
@@ -1170,6 +1185,7 @@
  - **Weibo**
  - **WeiboMobile**
  - **WeiqiTV**: WQTV
+ - **WimTV**
  - **Wistia**
  - **WistiaPlaylist**
  - **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
@@ -1223,7 +1239,7 @@
  - **YourUpload**
  - **youtube**: YouTube.com
  - **youtube:favorites**: YouTube.com liked videos, ":ytfav" for short (requires authentication)
- - **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
+ - **youtube:history**: Youtube watch history, ":ythis" for short (requires authentication)
  - **youtube:playlist**: YouTube.com playlists
  - **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
  - **youtube:search**: YouTube.com searches, "ytsearch" keyword
@@ -1237,10 +1253,12 @@
  - **Zapiks**
  - **Zattoo**
  - **ZattooLive**
- - **ZDF-3sat**
+ - **ZDF**
  - **ZDFChannel**
  - **Zee5**
+ - **zee5:series**
  - **Zhihu**
  - **zingmp3**: mp3.zing.vn
+ - **zingmp3:album**
  - **zoom**
  - **Zype**

test/test_all_urls.py

@@ -37,7 +37,6 @@ class TestAllURLsMatching(unittest.TestCase):
         assertPlaylist('PL63F0C78739B09958')
         assertTab('https://www.youtube.com/AsapSCIENCE')
         assertTab('https://www.youtube.com/embedded')
-        assertTab('https://www.youtube.com/feed')  # Own channel's home page
         assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
         assertTab('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')

test/test_postprocessors.py

@@ -14,10 +14,10 @@ from yt_dlp.postprocessor import MetadataFromFieldPP, MetadataFromTitlePP
 class TestMetadataFromField(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromFieldPP(None, ['title:%(title)s - %(artist)s'])
-        self.assertEqual(pp._data[0]['regex'], r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')
+        self.assertEqual(pp._data[0]['regex'], r'(?P<title>.+)\ \-\ (?P<artist>.+)')
 
 
 class TestMetadataFromTitle(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
-        self.assertEqual(pp._titleregex, r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')
+        self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)')

yt_dlp/YoutubeDL.py

@@ -60,12 +60,14 @@ from .utils import (
     encode_compat_str,
     encodeFilename,
     error_to_compat_str,
+    EntryNotInPlaylist,
     ExistingVideoReached,
     expand_path,
     ExtractorError,
     float_or_none,
     format_bytes,
     format_field,
+    FORMAT_RE,
     formatSeconds,
     GeoRestrictedError,
     int_or_none,
@@ -216,6 +218,7 @@ class YoutubeDL(object):
     logtostderr:       Log messages to stderr instead of stdout.
     writedescription:  Write the video description to a .description file
     writeinfojson:     Write the video description to a .info.json file
+    clean_infojson:    Remove private fields from the infojson
     writecomments:     Extract video comments. This will not be written to disk
                        unless writeinfojson is also given
     writeannotations:  Write the video annotations to a .annotations.xml file
@@ -770,95 +773,93 @@ class YoutubeDL(object):
                     'Put  from __future__ import unicode_literals  at the top of your code file or consider switching to Python 3.x.')
         return outtmpl_dict
 
+    def prepare_outtmpl(self, outtmpl, info_dict, sanitize=None):
+        """ Make the template and info_dict suitable for substitution (outtmpl % info_dict)"""
+        template_dict = dict(info_dict)
+
+        # duration_string
+        template_dict['duration_string'] = (  # %(duration>%H-%M-%S)s is wrong if duration > 24hrs
+            formatSeconds(info_dict['duration'], '-')
+            if info_dict.get('duration', None) is not None
+            else None)
+
+        # epoch
+        template_dict['epoch'] = int(time.time())
+
+        # autonumber
+        autonumber_size = self.params.get('autonumber_size')
+        if autonumber_size is None:
+            autonumber_size = 5
+        template_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
+
+        # resolution if not defined
+        if template_dict.get('resolution') is None:
+            if template_dict.get('width') and template_dict.get('height'):
+                template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
+            elif template_dict.get('height'):
+                template_dict['resolution'] = '%sp' % template_dict['height']
+            elif template_dict.get('width'):
+                template_dict['resolution'] = '%dx?' % template_dict['width']
+
+        if sanitize is None:
+            sanitize = lambda k, v: v
+        template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
+                             for k, v in template_dict.items()
+                             if v is not None and not isinstance(v, (list, tuple, dict)))
+        na = self.params.get('outtmpl_na_placeholder', 'NA')
+        template_dict = collections.defaultdict(lambda: na, template_dict)
+
+        # For fields playlist_index and autonumber convert all occurrences
+        # of %(field)s to %(field)0Nd for backward compatibility
+        field_size_compat_map = {
+            'playlist_index': len(str(template_dict['n_entries'])),
+            'autonumber': autonumber_size,
+        }
+        FIELD_SIZE_COMPAT_RE = r'(?<!%)%\((?P<field>autonumber|playlist_index)\)s'
+        mobj = re.search(FIELD_SIZE_COMPAT_RE, outtmpl)
+        if mobj:
+            outtmpl = re.sub(
+                FIELD_SIZE_COMPAT_RE,
+                r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
+                outtmpl)
+
+        numeric_fields = list(self._NUMERIC_FIELDS)
+
+        # Format date
+        FORMAT_DATE_RE = FORMAT_RE.format(r'(?P<key>(?P<field>\w+)>(?P<format>.+?))')
+        for mobj in re.finditer(FORMAT_DATE_RE, outtmpl):
+            conv_type, field, frmt, key = mobj.group('type', 'field', 'format', 'key')
+            if key in template_dict:
+                continue
+            value = strftime_or_none(template_dict.get(field), frmt, na)
+            if conv_type in 'crs':  # string
+                value = sanitize(field, value)
+            else:  # number
+                numeric_fields.append(key)
+                value = float_or_none(value, default=None)
+            if value is not None:
+                template_dict[key] = value
+
+        # Missing numeric fields used together with integer presentation types
+        # in format specification will break the argument substitution since
+        # string NA placeholder is returned for missing fields. We will patch
+        # output template for missing fields to meet string presentation type.
+        for numeric_field in numeric_fields:
+            if numeric_field not in template_dict:
+                outtmpl = re.sub(
+                    FORMAT_RE.format(re.escape(numeric_field)),
+                    r'%({0})s'.format(numeric_field), outtmpl)
+
+        return outtmpl, template_dict
+
     def _prepare_filename(self, info_dict, tmpl_type='default'):
         try:
-            template_dict = dict(info_dict)
-
-            template_dict['duration_string'] = (  # %(duration>%H-%M-%S)s is wrong if duration > 24hrs
-                formatSeconds(info_dict['duration'], '-')
-                if info_dict.get('duration', None) is not None
-                else None)
-
-            template_dict['epoch'] = int(time.time())
-            autonumber_size = self.params.get('autonumber_size')
-            if autonumber_size is None:
-                autonumber_size = 5
-            template_dict['autonumber'] = self.params.get('autonumber_start', 1) - 1 + self._num_downloads
-            if template_dict.get('resolution') is None:
-                if template_dict.get('width') and template_dict.get('height'):
-                    template_dict['resolution'] = '%dx%d' % (template_dict['width'], template_dict['height'])
-                elif template_dict.get('height'):
-                    template_dict['resolution'] = '%sp' % template_dict['height']
-                elif template_dict.get('width'):
-                    template_dict['resolution'] = '%dx?' % template_dict['width']
-
             sanitize = lambda k, v: sanitize_filename(
                 compat_str(v),
                 restricted=self.params.get('restrictfilenames'),
                 is_id=(k == 'id' or k.endswith('_id')))
-            template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
-                                 for k, v in template_dict.items()
-                                 if v is not None and not isinstance(v, (list, tuple, dict)))
-            na = self.params.get('outtmpl_na_placeholder', 'NA')
-            template_dict = collections.defaultdict(lambda: na, template_dict)
-
             outtmpl = self.outtmpl_dict.get(tmpl_type, self.outtmpl_dict['default'])
-            force_ext = OUTTMPL_TYPES.get(tmpl_type)
+            outtmpl, template_dict = self.prepare_outtmpl(outtmpl, info_dict, sanitize)
-
-            # For fields playlist_index and autonumber convert all occurrences
-            # of %(field)s to %(field)0Nd for backward compatibility
-            field_size_compat_map = {
-                'playlist_index': len(str(template_dict['n_entries'])),
-                'autonumber': autonumber_size,
-            }
-            FIELD_SIZE_COMPAT_RE = r'(?<!%)%\((?P<field>autonumber|playlist_index)\)s'
-            mobj = re.search(FIELD_SIZE_COMPAT_RE, outtmpl)
-            if mobj:
-                outtmpl = re.sub(
-                    FIELD_SIZE_COMPAT_RE,
-                    r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
-                    outtmpl)
-
-            # As of [1] format syntax is:
-            #  %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
-            # 1. https://docs.python.org/2/library/stdtypes.html#string-formatting
-            FORMAT_RE = r'''(?x)
-                (?<!%)
-                %
-                \({0}\)  # mapping key
-                (?:[#0\-+ ]+)?  # conversion flags (optional)
-                (?:\d+)?  # minimum field width (optional)
-                (?:\.\d+)?  # precision (optional)
-                [hlL]?  # length modifier (optional)
-                (?P<type>[diouxXeEfFgGcrs%])  # conversion type
-            '''
-
-            numeric_fields = list(self._NUMERIC_FIELDS)
-
-            # Format date
-            FORMAT_DATE_RE = FORMAT_RE.format(r'(?P<key>(?P<field>\w+)>(?P<format>.+?))')
-            for mobj in re.finditer(FORMAT_DATE_RE, outtmpl):
-                conv_type, field, frmt, key = mobj.group('type', 'field', 'format', 'key')
-                if key in template_dict:
-                    continue
-                value = strftime_or_none(template_dict.get(field), frmt, na)
-                if conv_type in 'crs':  # string
-                    value = sanitize(field, value)
-                else:  # number
-                    numeric_fields.append(key)
-                    value = float_or_none(value, default=None)
-                if value is not None:
-                    template_dict[key] = value
-
-            # Missing numeric fields used together with integer presentation types
-            # in format specification will break the argument substitution since
-            # string NA placeholder is returned for missing fields. We will patch
-            # output template for missing fields to meet string presentation type.
-            for numeric_field in numeric_fields:
-                if numeric_field not in template_dict:
-                    outtmpl = re.sub(
-                        FORMAT_RE.format(re.escape(numeric_field)),
-                        r'%({0})s'.format(numeric_field), outtmpl)
 
             # expand_path translates '%%' into '%' and '$$' into '$'
             # correspondingly that is not what we want since we need to keep
@@ -873,6 +874,7 @@ class YoutubeDL(object):
             # title "Hello $PATH", we don't want `$PATH` to be expanded.
             filename = expand_path(outtmpl).replace(sep, '') % template_dict
 
+            force_ext = OUTTMPL_TYPES.get(tmpl_type)
             if force_ext is not None:
                 filename = replace_extension(filename, force_ext, template_dict.get('ext'))
 
@@ -1171,57 +1173,24 @@ class YoutubeDL(object):
         else:
             raise Exception('Invalid result type: %s' % result_type)
 
+    def _ensure_dir_exists(self, path):
+        return make_dir(path, self.report_error)
+
     def __process_playlist(self, ie_result, download):
         # We process each entry in the playlist
         playlist = ie_result.get('title') or ie_result.get('id')
         self.to_screen('[download] Downloading playlist: %s' % playlist)
 
-        if self.params.get('allow_playlist_files', True):
+        if 'entries' not in ie_result:
-            ie_copy = {
+            raise EntryNotInPlaylist()
-                'playlist': playlist,
+        incomplete_entries = bool(ie_result.get('requested_entries'))
-                'playlist_id': ie_result.get('id'),
+        if incomplete_entries:
-                'playlist_title': ie_result.get('title'),
+            def fill_missing_entries(entries, indexes):
-                'playlist_uploader': ie_result.get('uploader'),
+                ret = [None] * max(*indexes)
-                'playlist_uploader_id': ie_result.get('uploader_id'),
+                for i, entry in zip(indexes, entries):
-                'playlist_index': 0
+                    ret[i - 1] = entry
-            }
+                return ret
-            ie_copy.update(dict(ie_result))
+            ie_result['entries'] = fill_missing_entries(ie_result['entries'], ie_result['requested_entries'])
-
-            def ensure_dir_exists(path):
-                return make_dir(path, self.report_error)
-
-            if self.params.get('writeinfojson', False):
-                infofn = self.prepare_filename(ie_copy, 'pl_infojson')
-                if not ensure_dir_exists(encodeFilename(infofn)):
-                    return
-                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
-                    self.to_screen('[info] Playlist metadata is already present')
-                else:
-                    playlist_info = dict(ie_result)
-                    # playlist_info['entries'] = list(playlist_info['entries'])  # Entries is a generator which shouldnot be resolved here
-                    del playlist_info['entries']
-                    self.to_screen('[info] Writing playlist metadata as JSON to: ' + infofn)
-                    try:
-                        write_json_file(self.filter_requested_info(playlist_info), infofn)
-                    except (OSError, IOError):
-                        self.report_error('Cannot write playlist metadata to JSON file ' + infofn)
-
-            if self.params.get('writedescription', False):
-                descfn = self.prepare_filename(ie_copy, 'pl_description')
-                if not ensure_dir_exists(encodeFilename(descfn)):
-                    return
-                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
-                    self.to_screen('[info] Playlist description is already present')
-                elif ie_result.get('description') is None:
-                    self.report_warning('There\'s no playlist description to write.')
-                else:
-                    try:
-                        self.to_screen('[info] Writing playlist description to: ' + descfn)
-                        with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
-                            descfile.write(ie_result['description'])
-                    except (OSError, IOError):
-                        self.report_error('Cannot write playlist description file ' + descfn)
-                        return
 
         playlist_results = []
 
@@ -1248,25 +1217,20 @@ class YoutubeDL(object):
 
         def make_playlistitems_entries(list_ie_entries):
             num_entries = len(list_ie_entries)
-            return [
+            for i in playlistitems:
-                list_ie_entries[i - 1] for i in playlistitems
+                if -num_entries < i <= num_entries:
-                if -num_entries <= i - 1 < num_entries]
+                    yield list_ie_entries[i - 1]
-
+                elif incomplete_entries:
-        def report_download(num_entries):
+                    raise EntryNotInPlaylist()
-            self.to_screen(
-                '[%s] playlist %s: Downloading %d videos' %
-                (ie_result['extractor'], playlist, num_entries))
 
         if isinstance(ie_entries, list):
             n_all_entries = len(ie_entries)
             if playlistitems:
-                entries = make_playlistitems_entries(ie_entries)
+                entries = list(make_playlistitems_entries(ie_entries))
             else:
                 entries = ie_entries[playliststart:playlistend]
             n_entries = len(entries)
-            self.to_screen(
+            msg = 'Collected %d videos; downloading %d of them' % (n_all_entries, n_entries)
-                '[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
-                (ie_result['extractor'], playlist, n_all_entries, n_entries))
         elif isinstance(ie_entries, PagedList):
             if playlistitems:
                 entries = []
@@ -1278,25 +1242,73 @@ class YoutubeDL(object):
                 entries = ie_entries.getslice(
                     playliststart, playlistend)
             n_entries = len(entries)
-            report_download(n_entries)
+            msg = 'Downloading %d videos' % n_entries
         else:  # iterable
             if playlistitems:
-                entries = make_playlistitems_entries(list(itertools.islice(
+                entries = list(make_playlistitems_entries(list(itertools.islice(
-                    ie_entries, 0, max(playlistitems))))
+                    ie_entries, 0, max(playlistitems)))))
             else:
                 entries = list(itertools.islice(
                     ie_entries, playliststart, playlistend))
             n_entries = len(entries)
-            report_download(n_entries)
+            msg = 'Downloading %d videos' % n_entries
+
+        if any((entry is None for entry in entries)):
+            raise EntryNotInPlaylist()
+        if not playlistitems and (playliststart or playlistend):
+            playlistitems = list(range(1 + playliststart, 1 + playliststart + len(entries)))
+        ie_result['entries'] = entries
+        ie_result['requested_entries'] = playlistitems
+
+        if self.params.get('allow_playlist_files', True):
+            ie_copy = {
+                'playlist': playlist,
+                'playlist_id': ie_result.get('id'),
+                'playlist_title': ie_result.get('title'),
+                'playlist_uploader': ie_result.get('uploader'),
+                'playlist_uploader_id': ie_result.get('uploader_id'),
+                'playlist_index': 0
+            }
+            ie_copy.update(dict(ie_result))
+
+            if self.params.get('writeinfojson', False):
+                infofn = self.prepare_filename(ie_copy, 'pl_infojson')
+                if not self._ensure_dir_exists(encodeFilename(infofn)):
+                    return
+                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
+                    self.to_screen('[info] Playlist metadata is already present')
+                else:
+                    self.to_screen('[info] Writing playlist metadata as JSON to: ' + infofn)
+                    try:
+                        write_json_file(self.filter_requested_info(ie_result, self.params.get('clean_infojson', True)), infofn)
+                    except (OSError, IOError):
+                        self.report_error('Cannot write playlist metadata to JSON file ' + infofn)
+
+            if self.params.get('writedescription', False):
+                descfn = self.prepare_filename(ie_copy, 'pl_description')
+                if not self._ensure_dir_exists(encodeFilename(descfn)):
+                    return
+                if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
+                    self.to_screen('[info] Playlist description is already present')
+                elif ie_result.get('description') is None:
+                    self.report_warning('There\'s no playlist description to write.')
+                else:
+                    try:
+                        self.to_screen('[info] Writing playlist description to: ' + descfn)
+                        with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
+                            descfile.write(ie_result['description'])
+                    except (OSError, IOError):
+                        self.report_error('Cannot write playlist description file ' + descfn)
+                        return
 
         if self.params.get('playlistreverse', False):
             entries = entries[::-1]
-
         if self.params.get('playlistrandom', False):
             random.shuffle(entries)
 
         x_forwarded_for = ie_result.get('__x_forwarded_for_ip')
 
+        self.to_screen('[%s] playlist %s: %s' % (ie_result['extractor'], playlist, msg))
         for i, entry in enumerate(entries, 1):
             self.to_screen('[download] Downloading video %s of %s' % (i, n_entries))
             # This __x_forwarded_for_ip thing is a bit ugly but requires
@@ -1310,7 +1322,7 @@ class YoutubeDL(object):
                 'playlist_title': ie_result.get('title'),
                 'playlist_uploader': ie_result.get('uploader'),
                 'playlist_uploader_id': ie_result.get('uploader_id'),
-                'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
+                'playlist_index': playlistitems[i - 1] if playlistitems else i,
                 'extractor': ie_result['extractor'],
                 'webpage_url': ie_result['webpage_url'],
                 'webpage_url_basename': url_basename(ie_result['webpage_url']),
@@ -1564,21 +1576,25 @@ class YoutubeDL(object):
 
                 else:
                     format_fallback = False
-                    format_spec_obj = re.match(r'(best|worst|b|w)(video|audio|v|a)?(\*)?$', format_spec)
+                    mobj = re.match(
-                    if format_spec_obj is not None:
+                        r'(?P<bw>best|worst|b|w)(?P<type>video|audio|v|a)?(?P<mod>\*)?(?:\.(?P<n>[1-9]\d*))?$',
-                        format_idx = 0 if format_spec_obj.group(1)[0] == 'w' else -1
+                        format_spec)
-                        format_type = format_spec_obj.group(2)[0] if format_spec_obj.group(2) else False
+                    if mobj is not None:
-                        not_format_type = 'v' if format_type == 'a' else 'a'
+                        format_idx = int_or_none(mobj.group('n'), default=1)
-                        format_modified = format_spec_obj.group(3) is not None
+                        format_idx = format_idx - 1 if mobj.group('bw')[0] == 'w' else -format_idx
+                        format_type = (mobj.group('type') or [None])[0]
+                        not_format_type = {'v': 'a', 'a': 'v'}.get(format_type)
+                        format_modified = mobj.group('mod') is not None
 
                         format_fallback = not format_type and not format_modified  # for b, w
-                        filter_f = ((lambda f: f.get(format_type + 'codec') != 'none')
+                        filter_f = (
-                                    if format_type and format_modified  # bv*, ba*, wv*, wa*
+                            (lambda f: f.get('%scodec' % format_type) != 'none')
-                                    else (lambda f: f.get(not_format_type + 'codec') == 'none')
+                            if format_type and format_modified  # bv*, ba*, wv*, wa*
-                                    if format_type  # bv, ba, wv, wa
+                            else (lambda f: f.get('%scodec' % not_format_type) == 'none')
-                                    else (lambda f: f.get('vcodec') != 'none' and f.get('acodec') != 'none')
+                            if format_type  # bv, ba, wv, wa
-                                    if not format_modified  # b, w
+                            else (lambda f: f.get('vcodec') != 'none' and f.get('acodec') != 'none')
-                                    else None)  # b*, w*
+                            if not format_modified  # b, w
+                            else None)  # b*, w*
                     else:
                         format_idx = -1
                         filter_f = ((lambda f: f.get('ext') == format_spec)
@@ -1590,13 +1606,16 @@ class YoutubeDL(object):
                         if not formats:
                             return
                         matches = list(filter(filter_f, formats)) if filter_f is not None else formats
-                        if matches:
+                        n = len(matches)
+                        if -n <= format_idx < n:
                             yield matches[format_idx]
-                        elif format_fallback == 'force' or (format_fallback and ctx['incomplete_formats']):
+                        elif format_fallback and ctx['incomplete_formats']:
                             # for extractors with incomplete formats (audio only (soundcloud)
                             # or video only (imgur)) best/worst will fallback to
                             # best/worst {video,audio}-only format
-                            yield formats[format_idx]
+                            n = len(formats)
+                            if -n <= format_idx < n:
+                                yield formats[format_idx]
 
             elif selector.type == MERGE:        # +
                 def _merge(formats_pair):
@@ -1644,7 +1663,7 @@ class YoutubeDL(object):
                         new_dict.update({
                             'width': the_only_video.get('width'),
                             'height': the_only_video.get('height'),
-                            'resolution': the_only_video.get('resolution'),
+                            'resolution': the_only_video.get('resolution') or self.format_resolution(the_only_video),
                             'fps': the_only_video.get('fps'),
                             'vcodec': the_only_video.get('vcodec'),
                             'vbr': the_only_video.get('vbr'),
@@ -1794,14 +1813,18 @@ class YoutubeDL(object):
         if 'display_id' not in info_dict and 'id' in info_dict:
             info_dict['display_id'] = info_dict['id']
 
-        if info_dict.get('upload_date') is None and info_dict.get('timestamp') is not None:
+        for ts_key, date_key in (
-            # Working around out-of-range timestamp values (e.g. negative ones on Windows,
+                ('timestamp', 'upload_date'),
-            # see http://bugs.python.org/issue1646728)
+                ('release_timestamp', 'release_date'),
-            try:
+        ):
-                upload_date = datetime.datetime.utcfromtimestamp(info_dict['timestamp'])
+            if info_dict.get(date_key) is None and info_dict.get(ts_key) is not None:
-                info_dict['upload_date'] = upload_date.strftime('%Y%m%d')
+                # Working around out-of-range timestamp values (e.g. negative ones on Windows,
-            except (ValueError, OverflowError, OSError):
+                # see http://bugs.python.org/issue1646728)
-                pass
+                try:
+                    upload_date = datetime.datetime.utcfromtimestamp(info_dict[ts_key])
+                    info_dict[date_key] = upload_date.strftime('%Y%m%d')
+                except (ValueError, OverflowError, OSError):
+                    pass
 
         # Auto generate title fields corresponding to the *_number fields when missing
         # in order to always have clean titles. This is very common for TV series.
@@ -2043,7 +2066,7 @@ class YoutubeDL(object):
         print_mandatory('format')
         if self.params.get('forcejson', False):
             self.post_extract(info_dict)
-            self.to_stdout(json.dumps(info_dict))
+            self.to_stdout(json.dumps(info_dict, default=repr))
 
     def process_info(self, info_dict):
         """Process a single resolved IE result."""
@@ -2071,6 +2094,7 @@ class YoutubeDL(object):
 
         info_dict = self.pre_process(info_dict)
 
+        # info_dict['_filename'] needs to be set for backward compatibility
         info_dict['_filename'] = full_filename = self.prepare_filename(info_dict, warn=True)
         temp_filename = self.prepare_filename(info_dict, 'temp')
         files_to_move = {}
@@ -2089,17 +2113,14 @@ class YoutubeDL(object):
         if full_filename is None:
             return
 
-        def ensure_dir_exists(path):
+        if not self._ensure_dir_exists(encodeFilename(full_filename)):
-            return make_dir(path, self.report_error)
-
-        if not ensure_dir_exists(encodeFilename(full_filename)):
             return
-        if not ensure_dir_exists(encodeFilename(temp_filename)):
+        if not self._ensure_dir_exists(encodeFilename(temp_filename)):
             return
 
         if self.params.get('writedescription', False):
             descfn = self.prepare_filename(info_dict, 'description')
-            if not ensure_dir_exists(encodeFilename(descfn)):
+            if not self._ensure_dir_exists(encodeFilename(descfn)):
                 return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(descfn)):
                 self.to_screen('[info] Video description is already present')
@@ -2116,7 +2137,7 @@ class YoutubeDL(object):
 
         if self.params.get('writeannotations', False):
             annofn = self.prepare_filename(info_dict, 'annotation')
-            if not ensure_dir_exists(encodeFilename(annofn)):
+            if not self._ensure_dir_exists(encodeFilename(annofn)):
                 return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(annofn)):
                 self.to_screen('[info] Video annotations are already present')
@@ -2139,7 +2160,10 @@ class YoutubeDL(object):
                 fd.add_progress_hook(ph)
             if self.params.get('verbose'):
                 self.to_screen('[debug] Invoking downloader on %r' % info.get('url'))
-            return fd.download(name, info, subtitle)
+            new_info = dict(info)
+            if new_info.get('http_headers') is None:
+                new_info['http_headers'] = self._calc_headers(new_info)
+            return fd.download(name, new_info, subtitle)
 
         subtitles_are_requested = any([self.params.get('writesubtitles', False),
                                        self.params.get('writeautomaticsub')])
@@ -2158,6 +2182,7 @@ class YoutubeDL(object):
                 sub_filename_final = subtitles_filename(sub_fn, sub_lang, sub_format, info_dict.get('ext'))
                 if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(sub_filename)):
                     self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
+                    sub_info['filepath'] = sub_filename
                     files_to_move[sub_filename] = sub_filename_final
                 else:
                     self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
@@ -2167,13 +2192,15 @@ class YoutubeDL(object):
                             # See https://github.com/ytdl-org/youtube-dl/issues/10268
                             with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
                                 subfile.write(sub_info['data'])
+                            sub_info['filepath'] = sub_filename
                             files_to_move[sub_filename] = sub_filename_final
                         except (OSError, IOError):
                             self.report_error('Cannot write subtitles file ' + sub_filename)
                             return
                     else:
                         try:
-                            dl(sub_filename, sub_info, subtitle=True)
+                            dl(sub_filename, sub_info.copy(), subtitle=True)
+                            sub_info['filepath'] = sub_filename
                             files_to_move[sub_filename] = sub_filename_final
                         except (ExtractorError, IOError, OSError, ValueError, compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
                             self.report_warning('Unable to download subtitle for "%s": %s' %
@@ -2204,14 +2231,14 @@ class YoutubeDL(object):
 
         if self.params.get('writeinfojson', False):
             infofn = self.prepare_filename(info_dict, 'infojson')
-            if not ensure_dir_exists(encodeFilename(infofn)):
+            if not self._ensure_dir_exists(encodeFilename(infofn)):
                 return
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(infofn)):
                 self.to_screen('[info] Video metadata is already present')
             else:
                 self.to_screen('[info] Writing video metadata as JSON to: ' + infofn)
                 try:
-                    write_json_file(self.filter_requested_info(info_dict), infofn)
+                    write_json_file(self.filter_requested_info(info_dict, self.params.get('clean_infojson', True)), infofn)
                 except (OSError, IOError):
                     self.report_error('Cannot write video metadata to JSON file ' + infofn)
                     return
@@ -2222,7 +2249,7 @@ class YoutubeDL(object):
         for thumb_ext in self._write_thumbnails(info_dict, thumb_fn_temp):
             thumb_filename_temp = replace_extension(thumb_fn_temp, thumb_ext, info_dict.get('ext'))
             thumb_filename = replace_extension(thumbfn, thumb_ext, info_dict.get('ext'))
-            files_to_move[thumb_filename_temp] = info_dict['__thumbnail_filename'] = thumb_filename
+            files_to_move[thumb_filename_temp] = thumb_filename
 
         # Write internet shortcut files
         url_link = webloc_link = desktop_link = False
@@ -2335,10 +2362,17 @@ class YoutubeDL(object):
 
                     requested_formats = info_dict['requested_formats']
                     old_ext = info_dict['ext']
-                    if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
+                    if self.params.get('merge_output_format') is None:
-                        info_dict['ext'] = 'mkv'
+                        if not compatible_formats(requested_formats):
-                        self.report_warning(
+                            info_dict['ext'] = 'mkv'
-                            'Requested formats are incompatible for merge and will be merged into mkv.')
+                            self.report_warning(
+                                'Requested formats are incompatible for merge and will be merged into mkv.')
+                        if (info_dict['ext'] == 'webm'
+                                and self.params.get('writethumbnail', False)
+                                and info_dict.get('thumbnails')):
+                            info_dict['ext'] = 'mkv'
+                            self.report_warning(
+                                'webm doesn\'t support embedding a thumbnail, mkv will be used.')
 
                     def correct_ext(filename):
                         filename_real_ext = os.path.splitext(filename)[1][1:]
@@ -2360,7 +2394,7 @@ class YoutubeDL(object):
                             fname = prepend_extension(
                                 self.prepare_filename(new_info, 'temp'),
                                 'f%s' % f['format_id'], new_info['ext'])
-                            if not ensure_dir_exists(fname):
+                            if not self._ensure_dir_exists(fname):
                                 return
                             downloaded.append(fname)
                             partial_success, real_download = dl(fname, new_info)
@@ -2437,9 +2471,8 @@ class YoutubeDL(object):
                     else:
                         assert fixup_policy in ('ignore', 'never')
 
-                if (info_dict.get('protocol') == 'm3u8_native'
+                if ('protocol' in info_dict
-                        or info_dict.get('protocol') == 'm3u8'
+                        and get_suitable_downloader(info_dict, self.params).__name__ == 'HlsFD'):
-                        and self.params.get('hls_prefer_native')):
                     if fixup_policy == 'warn':
                         self.report_warning('%s: malformed AAC bitstream detected.' % (
                             info_dict['id']))
@@ -2455,13 +2488,13 @@ class YoutubeDL(object):
                         assert fixup_policy in ('ignore', 'never')
 
                 try:
-                    self.post_process(dl_filename, info_dict, files_to_move)
+                    info_dict = self.post_process(dl_filename, info_dict, files_to_move)
                 except PostProcessingError as err:
                     self.report_error('Postprocessing: %s' % str(err))
                     return
                 try:
                     for ph in self._post_hooks:
-                        ph(full_filename)
+                        ph(info_dict['filepath'])
                 except Exception as err:
                     self.report_error('post hooks: %s' % str(err))
                     return
@@ -2501,7 +2534,7 @@ class YoutubeDL(object):
             else:
                 if self.params.get('dump_single_json', False):
                     self.post_extract(res)
-                    self.to_stdout(json.dumps(res))
+                    self.to_stdout(json.dumps(res, default=repr))
 
         return self._download_retcode
 
@@ -2510,10 +2543,10 @@ class YoutubeDL(object):
                 [info_filename], mode='r',
                 openhook=fileinput.hook_encoded('utf-8'))) as f:
             # FileInput doesn't have a read method, we can't call json.load
-            info = self.filter_requested_info(json.loads('\n'.join(f)))
+            info = self.filter_requested_info(json.loads('\n'.join(f)), self.params.get('clean_infojson', True))
         try:
             self.process_ie_result(info, download=True)
-        except DownloadError:
+        except (DownloadError, EntryNotInPlaylist):
             webpage_url = info.get('webpage_url')
             if webpage_url is not None:
                 self.report_warning('The info failed to download, trying with "%s"' % webpage_url)
@@ -2523,21 +2556,32 @@ class YoutubeDL(object):
         return self._download_retcode
 
     @staticmethod
-    def filter_requested_info(info_dict):
+    def filter_requested_info(info_dict, actually_filter=True):
-        fields_to_remove = ('requested_formats', 'requested_subtitles')
+        if not actually_filter:
-        return dict(
+            info_dict['epoch'] = int(time.time())
-            (k, v) for k, v in info_dict.items()
+            return info_dict
-            if (k[0] != '_' or k == '_type') and k not in fields_to_remove)
+        exceptions = {
+            'remove': ['requested_formats', 'requested_subtitles', 'requested_entries', 'filepath', 'entries'],
+            'keep': ['_type'],
+        }
+        keep_key = lambda k: k in exceptions['keep'] or not (k.startswith('_') or k in exceptions['remove'])
+        filter_fn = lambda obj: (
+            list(map(filter_fn, obj)) if isinstance(obj, (list, tuple))
+            else obj if not isinstance(obj, dict)
+            else dict((k, filter_fn(v)) for k, v in obj.items() if keep_key(k)))
+        return filter_fn(info_dict)
 
-    def run_pp(self, pp, infodict, files_to_move={}):
+    def run_pp(self, pp, infodict):
         files_to_delete = []
+        if '__files_to_move' not in infodict:
+            infodict['__files_to_move'] = {}
         files_to_delete, infodict = pp.run(infodict)
         if not files_to_delete:
-            return files_to_move, infodict
+            return infodict
 
         if self.params.get('keepvideo', False):
             for f in files_to_delete:
-                files_to_move.setdefault(f, '')
+                infodict['__files_to_move'].setdefault(f, '')
         else:
             for old_filename in set(files_to_delete):
                 self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
@@ -2545,16 +2589,16 @@ class YoutubeDL(object):
                     os.remove(encodeFilename(old_filename))
                 except (IOError, OSError):
                     self.report_warning('Unable to remove downloaded original file')
-                if old_filename in files_to_move:
+                if old_filename in infodict['__files_to_move']:
-                    del files_to_move[old_filename]
+                    del infodict['__files_to_move'][old_filename]
-        return files_to_move, infodict
+        return infodict
 
     @staticmethod
     def post_extract(info_dict):
         def actual_post_extract(info_dict):
             if info_dict.get('_type') in ('playlist', 'multi_video'):
                 for video_dict in info_dict.get('entries', {}):
-                    actual_post_extract(video_dict)
+                    actual_post_extract(video_dict or {})
                 return
 
             if '__post_extractor' not in info_dict:
@@ -2565,25 +2609,27 @@ class YoutubeDL(object):
             del info_dict['__post_extractor']
             return
 
-        actual_post_extract(info_dict)
+        actual_post_extract(info_dict or {})
 
     def pre_process(self, ie_info):
         info = dict(ie_info)
         for pp in self._pps['beforedl']:
-            info = self.run_pp(pp, info)[1]
+            info = self.run_pp(pp, info)
         return info
 
-    def post_process(self, filename, ie_info, files_to_move={}):
+    def post_process(self, filename, ie_info, files_to_move=None):
         """Run all the postprocessors on the given file."""
         info = dict(ie_info)
         info['filepath'] = filename
-        info['__files_to_move'] = {}
+        info['__files_to_move'] = files_to_move or {}
 
         for pp in ie_info.get('__postprocessors', []) + self._pps['normal']:
-            files_to_move, info = self.run_pp(pp, info, files_to_move)
+            info = self.run_pp(pp, info)
-        info = self.run_pp(MoveFilesAfterDownloadPP(self, files_to_move), info)[1]
+        info = self.run_pp(MoveFilesAfterDownloadPP(self), info)
+        del info['__files_to_move']
         for pp in self._pps['aftermove']:
-            info = self.run_pp(pp, info, {})[1]
+            info = self.run_pp(pp, info)
+        return info
 
     def _make_archive_id(self, info_dict):
         video_id = info_dict.get('id')
@@ -2632,12 +2678,11 @@ class YoutubeDL(object):
             return 'audio only'
         if format.get('resolution') is not None:
             return format['resolution']
-        if format.get('height') is not None:
+        if format.get('width') and format.get('height'):
-            if format.get('width') is not None:
+            res = '%dx%d' % (format['width'], format['height'])
-                res = '%sx%s' % (format['width'], format['height'])
+        elif format.get('height'):
-            else:
+            res = '%sp' % format['height']
-                res = '%sp' % format['height']
+        elif format.get('width'):
-        elif format.get('width') is not None:
             res = '%dx?' % format['width']
         else:
             res = default
@@ -2951,7 +2996,7 @@ class YoutubeDL(object):
             thumb_ext = determine_ext(t['url'], 'jpg')
             suffix = '%s.' % t['id'] if multiple else ''
             thumb_display_id = '%s ' % t['id'] if multiple else ''
-            t['filename'] = thumb_filename = replace_extension(filename, suffix + thumb_ext, info_dict.get('ext'))
+            t['filepath'] = thumb_filename = replace_extension(filename, suffix + thumb_ext, info_dict.get('ext'))
 
             if not self.params.get('overwrites', True) and os.path.exists(encodeFilename(thumb_filename)):
                 ret.append(suffix + thumb_ext)

yt_dlp/__init__.py

@@ -180,6 +180,8 @@ def _real_main(argv=None):
     if opts.overwrites:
         # --yes-overwrites implies --no-continue
         opts.continue_dl = False
+    if opts.concurrent_fragment_downloads <= 0:
+        raise ValueError('Concurrent fragments must be positive')
 
     def parse_retries(retries, name=''):
         if retries in ('inf', 'infinite'):
@@ -277,9 +279,14 @@ def _real_main(argv=None):
 
     def report_conflict(arg1, arg2):
         write_string('WARNING: %s is ignored since %s was given\n' % (arg2, arg1), out=sys.stderr)
+
     if opts.remuxvideo and opts.recodevideo:
         report_conflict('--recode-video', '--remux-video')
         opts.remuxvideo = False
+    if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
+        report_conflict('--split-chapter', '--sponskrub-cut')
+        opts.sponskrub_cut = False
+
     if opts.allow_unplayable_formats:
         if opts.extractaudio:
             report_conflict('--allow-unplayable-formats', '--extract-audio')
@@ -361,19 +368,9 @@ def _real_main(argv=None):
     # this was the old behaviour if only --all-sub was given.
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
-    if opts.embedthumbnail:
+    # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
-        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+    # but must be below EmbedSubtitle and FFmpegMetadata
-        postprocessors.append({
+    # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
-            'key': 'EmbedThumbnail',
-            'already_have_thumbnail': already_have_thumbnail
-        })
-        if not already_have_thumbnail:
-            opts.writethumbnail = True
-    # XAttrMetadataPP should be run after post-processors that may change file
-    # contents
-    if opts.xattrs:
-        postprocessors.append({'key': 'XAttrMetadata'})
-    # This should be below all ffmpeg PP because it may cut parts out from the video
     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
     if opts.sponskrub is not False:
         postprocessors.append({
@@ -384,6 +381,19 @@ def _real_main(argv=None):
             'force': opts.sponskrub_force,
             'ignoreerror': opts.sponskrub is None,
         })
+    if opts.embedthumbnail:
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
+    if opts.split_chapters:
+        postprocessors.append({'key': 'FFmpegSplitChapters'})
+    # XAttrMetadataPP should be run after post-processors that may change file contents
+    if opts.xattrs:
+        postprocessors.append({'key': 'XAttrMetadata'})
     # ExecAfterDownload must be the last PP
     if opts.exec_cmd:
         postprocessors.append({
@@ -463,6 +473,7 @@ def _real_main(argv=None):
         'extractor_retries': opts.extractor_retries,
         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
         'keep_fragments': opts.keep_fragments,
+        'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'http_chunk_size': opts.http_chunk_size,
@@ -482,6 +493,7 @@ def _real_main(argv=None):
         'writeannotations': opts.writeannotations,
         'writeinfojson': opts.writeinfojson,
         'allow_playlist_files': opts.allow_playlist_files,
+        'clean_infojson': opts.clean_infojson,
         'getcomments': opts.getcomments,
         'writethumbnail': opts.writethumbnail,
         'write_all_thumbnails': opts.write_all_thumbnails,

yt_dlp/downloader/common.py

@@ -326,6 +326,12 @@ class FileDownloader(object):
         """Report it was impossible to resume download."""
         self.to_screen('[download] Unable to resume')
 
+    @staticmethod
+    def supports_manifest(manifest):
+        """ Whether the downloader can download the fragments from the manifest.
+        Redefine in subclasses if needed. """
+        pass
+
     def download(self, filename, info_dict, subtitle=False):
         """Download to a filename using the info from info_dict
         Return True on success and False otherwise

yt_dlp/downloader/dash.py

@@ -1,18 +1,26 @@
 from __future__ import unicode_literals
 
+try:
+    import concurrent.futures
+    can_threaded_download = True
+except ImportError:
+    can_threaded_download = False
+
 from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
 
 from ..compat import compat_urllib_error
 from ..utils import (
     DownloadError,
+    sanitize_open,
     urljoin,
 )
 
 
 class DashSegmentsFD(FragmentFD):
     """
-    Download segments in a DASH manifest
+    Download segments in a DASH manifest. External downloaders can take over
+    the fragment downloads by supporting the 'frag_urls' protocol
     """
 
     FD_NAME = 'dashsegments'
@@ -37,7 +45,7 @@ class DashSegmentsFD(FragmentFD):
         fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        fragment_urls = []
+        fragments_to_download = []
         frag_index = 0
         for i, fragment in enumerate(fragments):
             frag_index += 1
@@ -48,49 +56,17 @@ class DashSegmentsFD(FragmentFD):
                 assert fragment_base_url
                 fragment_url = urljoin(fragment_base_url, fragment['path'])
 
-            if real_downloader:
+            fragments_to_download.append({
-                fragment_urls.append(fragment_url)
+                'frag_index': frag_index,
-                continue
+                'index': i,
-
+                'url': fragment_url,
-            # In DASH, the first segment contains necessary headers to
+            })
-            # generate a valid MP4 file, so always abort for the first segment
-            fatal = i == 0 or not skip_unavailable_fragments
-            count = 0
-            while count <= fragment_retries:
-                try:
-                    success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
-                    if not success:
-                        return False
-                    self._append_fragment(ctx, frag_content)
-                    break
-                except compat_urllib_error.HTTPError as err:
-                    # YouTube may often return 404 HTTP error for a fragment causing the
-                    # whole download to fail. However if the same fragment is immediately
-                    # retried with the same request data this usually succeeds (1-2 attempts
-                    # is usually enough) thus allowing to download the whole file successfully.
-                    # To be future-proof we will retry all fragments that fail with any
-                    # HTTP error.
-                    count += 1
-                    if count <= fragment_retries:
-                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
-                except DownloadError:
-                    # Don't retry fragment if error occurred during HTTP downloading
-                    # itself since it has own retry settings
-                    if not fatal:
-                        self.report_skip_fragment(frag_index)
-                        break
-                    raise
-
-            if count > fragment_retries:
-                if not fatal:
-                    self.report_skip_fragment(frag_index)
-                    continue
-                self.report_error('giving up after %s fragment retries' % fragment_retries)
-                return False
 
         if real_downloader:
+            self.to_screen(
+                '[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
             info_copy = info_dict.copy()
-            info_copy['url_list'] = fragment_urls
+            info_copy['fragments'] = fragments_to_download
             fd = real_downloader(self.ydl, self.params)
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
@@ -99,5 +75,104 @@ class DashSegmentsFD(FragmentFD):
             if not success:
                 return False
         else:
+            def download_fragment(fragment):
+                i = fragment['index']
+                frag_index = fragment['frag_index']
+                fragment_url = fragment['url']
+
+                ctx['fragment_index'] = frag_index
+
+                # In DASH, the first segment contains necessary headers to
+                # generate a valid MP4 file, so always abort for the first segment
+                fatal = i == 0 or not skip_unavailable_fragments
+                count = 0
+                while count <= fragment_retries:
+                    try:
+                        success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
+                        if not success:
+                            return False, frag_index
+                        break
+                    except compat_urllib_error.HTTPError as err:
+                        # YouTube may often return 404 HTTP error for a fragment causing the
+                        # whole download to fail. However if the same fragment is immediately
+                        # retried with the same request data this usually succeeds (1-2 attempts
+                        # is usually enough) thus allowing to download the whole file successfully.
+                        # To be future-proof we will retry all fragments that fail with any
+                        # HTTP error.
+                        count += 1
+                        if count <= fragment_retries:
+                            self.report_retry_fragment(err, frag_index, count, fragment_retries)
+                    except DownloadError:
+                        # Don't retry fragment if error occurred during HTTP downloading
+                        # itself since it has own retry settings
+                        if not fatal:
+                            break
+                        raise
+
+                if count > fragment_retries:
+                    if not fatal:
+                        return False, frag_index
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return False, frag_index
+
+                return frag_content, frag_index
+
+            def append_fragment(frag_content, frag_index):
+                if frag_content:
+                    fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], frag_index)
+                    try:
+                        file, frag_sanitized = sanitize_open(fragment_filename, 'rb')
+                        ctx['fragment_filename_sanitized'] = frag_sanitized
+                        file.close()
+                        self._append_fragment(ctx, frag_content)
+                        return True
+                    except FileNotFoundError:
+                        if skip_unavailable_fragments:
+                            self.report_skip_fragment(frag_index)
+                            return True
+                        else:
+                            self.report_error(
+                                'fragment %s not found, unable to continue' % frag_index)
+                            return False
+                else:
+                    if skip_unavailable_fragments:
+                        self.report_skip_fragment(frag_index)
+                        return True
+                    else:
+                        self.report_error(
+                            'fragment %s not found, unable to continue' % frag_index)
+                        return False
+
+            max_workers = self.params.get('concurrent_fragment_downloads', 1)
+            if can_threaded_download and max_workers > 1:
+                self.report_warning('The download speed shown is only of one thread. This is a known issue')
+                with concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
+                    futures = [pool.submit(download_fragment, fragment) for fragment in fragments_to_download]
+                    # timeout must be 0 to return instantly
+                    done, not_done = concurrent.futures.wait(futures, timeout=0)
+                    try:
+                        while not_done:
+                            # Check every 1 second for KeyboardInterrupt
+                            freshly_done, not_done = concurrent.futures.wait(not_done, timeout=1)
+                            done |= freshly_done
+                    except KeyboardInterrupt:
+                        for future in not_done:
+                            future.cancel()
+                        # timeout must be none to cancel
+                        concurrent.futures.wait(not_done, timeout=None)
+                        raise KeyboardInterrupt
+                results = [future.result() for future in futures]
+
+                for frag_content, frag_index in results:
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+            else:
+                for fragment in fragments_to_download:
+                    frag_content, frag_index = download_fragment(fragment)
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+
             self._finish_frag_download(ctx)
         return True

yt_dlp/downloader/external.py

@@ -24,7 +24,6 @@ from ..utils import (
     cli_bool_option,
     cli_configuration_args,
     encodeFilename,
-    error_to_compat_str,
     encodeArgument,
     handle_youtubedl_headers,
     check_executable,
@@ -108,7 +107,8 @@ class ExternalFD(FileDownloader):
     def _configuration_args(self, *args, **kwargs):
         return cli_configuration_args(
             self.params.get('external_downloader_args'),
-            self.get_basename(), *args, **kwargs)
+            [self.get_basename(), 'default'],
+            *args, **kwargs)
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
@@ -116,24 +116,43 @@ class ExternalFD(FileDownloader):
 
         self._debug_cmd(cmd)
 
-        p = subprocess.Popen(
+        if 'fragments' in info_dict:
-            cmd, stderr=subprocess.PIPE)
+            fragment_retries = self.params.get('fragment_retries', 0)
-        _, stderr = process_communicate_or_kill(p)
+            skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
-        if p.returncode != 0:
+
-            self.to_stderr(stderr.decode('utf-8', 'replace'))
+            count = 0
+            while count <= fragment_retries:
+                p = subprocess.Popen(
+                    cmd, stderr=subprocess.PIPE)
+                _, stderr = process_communicate_or_kill(p)
+                if p.returncode == 0:
+                    break
+                # TODO: Decide whether to retry based on error code
+                # https://aria2.github.io/manual/en/html/aria2c.html#exit-status
+                self.to_stderr(stderr.decode('utf-8', 'replace'))
+                count += 1
+                if count <= fragment_retries:
+                    self.to_screen(
+                        '[%s] Got error. Retrying fragments (attempt %d of %s)...'
+                        % (self.get_basename(), count, self.format_retries(fragment_retries)))
+            if count > fragment_retries:
+                if not skip_unavailable_fragments:
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return -1
 
-        if 'url_list' in info_dict:
-            file_list = []
-            for [i, url] in enumerate(info_dict['url_list']):
-                tmpsegmentname = '%s_%s.frag' % (tmpfilename, i)
-                file_list.append(tmpsegmentname)
-            key_list = info_dict.get('key_list')
-            decrypt_info = None
             dest, _ = sanitize_open(tmpfilename, 'wb')
-            for i, file in enumerate(file_list):
+            for frag_index, fragment in enumerate(info_dict['fragments']):
-                src, _ = sanitize_open(file, 'rb')
+                fragment_filename = '%s-Frag%d' % (tmpfilename, frag_index)
-                if key_list:
+                try:
-                    decrypt_info = next((x for x in key_list if x['INDEX'] == i), decrypt_info)
+                    src, _ = sanitize_open(fragment_filename, 'rb')
+                except IOError:
+                    if skip_unavailable_fragments and frag_index > 1:
+                        self.to_screen('[%s] Skipping fragment %d ...' % (self.get_basename(), frag_index))
+                        continue
+                    self.report_error('Unable to open fragment %d' % frag_index)
+                    return -1
+                decrypt_info = fragment.get('decrypt_info')
+                if decrypt_info:
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV')
                         decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
@@ -149,19 +168,16 @@ class ExternalFD(FileDownloader):
                     fragment_data = src.read()
                     dest.write(fragment_data)
                 src.close()
+                if not self.params.get('keep_fragments', False):
+                    os.remove(encodeFilename(fragment_filename))
             dest.close()
-            if not self.params.get('keep_fragments', False):
+            os.remove(encodeFilename('%s.frag.urls' % tmpfilename))
-                for file_path in file_list:
+        else:
-                    try:
+            p = subprocess.Popen(
-                        os.remove(file_path)
+                cmd, stderr=subprocess.PIPE)
-                    except OSError as ose:
+            _, stderr = process_communicate_or_kill(p)
-                        self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
+            if p.returncode != 0:
-                try:
+                self.to_stderr(stderr.decode('utf-8', 'replace'))
-                    file_path = '%s.frag.urls' % tmpfilename
-                    os.remove(file_path)
-                except OSError as ose:
-                    self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
-
         return p.returncode
 
     def _prepare_url(self, info_dict, url):
@@ -245,15 +261,22 @@ class Aria2cFD(ExternalFD):
     AVAILABLE_OPT = '-v'
     SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'frag_urls')
 
+    @staticmethod
+    def supports_manifest(manifest):
+        UNSUPPORTED_FEATURES = [
+            r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [1]
+            # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
+        ]
+        check_results = (not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
+        return all(check_results)
+
     def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '-c']
+        cmd = [self.exe, '-c',
-        dn = os.path.dirname(tmpfilename)
+               '--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
-        if 'url_list' not in info_dict:
+               '--file-allocation=none', '-x16', '-j16', '-s16']
-            cmd += ['--out', os.path.basename(tmpfilename)]
+        if 'fragments' in info_dict:
-        verbose_level_args = ['--console-log-level=warn', '--summary-interval=0']
+            cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
-        cmd += self._configuration_args(['--file-allocation=none', '-x16', '-j16', '-s16'] + verbose_level_args)
+
-        if dn:
-            cmd += ['--dir', dn]
         if info_dict.get('http_headers') is not None:
             for key, val in info_dict['http_headers'].items():
                 cmd += ['--header', '%s: %s' % (key, val)]
@@ -261,19 +284,25 @@ class Aria2cFD(ExternalFD):
         cmd += self._option('--all-proxy', 'proxy')
         cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
         cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
+        cmd += self._configuration_args()
+
+        dn = os.path.dirname(tmpfilename)
+        if dn:
+            cmd += ['--dir', dn]
+        if 'fragments' not in info_dict:
+            cmd += ['--out', os.path.basename(tmpfilename)]
         cmd += ['--auto-file-renaming=false']
-        if 'url_list' in info_dict:
+
-            cmd += verbose_level_args
+        if 'fragments' in info_dict:
-            cmd += ['--uri-selector', 'inorder', '--download-result=hide']
+            cmd += ['--file-allocation=none', '--uri-selector=inorder']
             url_list_file = '%s.frag.urls' % tmpfilename
             url_list = []
-            for [i, url] in enumerate(info_dict['url_list']):
+            for frag_index, fragment in enumerate(info_dict['fragments']):
-                tmpsegmentname = '%s_%s.frag' % (os.path.basename(tmpfilename), i)
+                fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
-                url_list.append('%s\n\tout=%s' % (url, tmpsegmentname))
+                url_list.append('%s\n\tout=%s' % (fragment['url'], fragment_filename))
             stream, _ = sanitize_open(url_list_file, 'wb')
             stream.write('\n'.join(url_list).encode('utf-8'))
             stream.close()
-
             cmd += ['-i', url_list_file]
         else:
             cmd += ['--', info_dict['url']]
@@ -282,8 +311,8 @@ class Aria2cFD(ExternalFD):
 
 class HttpieFD(ExternalFD):
     @classmethod
-    def available(cls):
+    def available(cls, path=None):
-        return check_executable('http', ['--version'])
+        return check_executable(path or 'http', ['--version'])
 
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
@@ -298,7 +327,7 @@ class FFmpegFD(ExternalFD):
     SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
 
     @classmethod
-    def available(cls):
+    def available(cls, path=None):  # path is ignored for ffmpeg
         return FFmpegPostProcessor().available
 
     def _call_downloader(self, tmpfilename, info_dict):

yt_dlp/downloader/hls.py

@@ -7,6 +7,11 @@ try:
     can_decrypt_frag = True
 except ImportError:
     can_decrypt_frag = False
+try:
+    import concurrent.futures
+    can_threaded_download = True
+except ImportError:
+    can_threaded_download = False
 
 from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
@@ -19,12 +24,17 @@ from ..compat import (
 )
 from ..utils import (
     parse_m3u8_attributes,
+    sanitize_open,
     update_url_query,
 )
 
 
 class HlsFD(FragmentFD):
-    """ A limited implementation that does not require ffmpeg """
+    """
+    Download segments in a m3u8 manifest. External downloaders can take over
+    the fragment downloads by supporting the 'frag_urls' protocol and
+    re-defining 'supports_manifest' function
+    """
 
     FD_NAME = 'hlsnative'
 
@@ -53,12 +63,15 @@ class HlsFD(FragmentFD):
             UNSUPPORTED_FEATURES += [
                 r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             ]
-        check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
+
-        is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
+        def check_results():
-        check_results.append(with_crypto or not is_aes128_enc)
+            yield not info_dict.get('is_live')
-        check_results.append(not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest))
+            is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
-        check_results.append(not info_dict.get('is_live'))
+            yield with_crypto or not is_aes128_enc
-        return all(check_results)
+            yield not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest)
+            for feature in UNSUPPORTED_FEATURES:
+                yield not re.search(feature, manifest)
+        return all(check_results())
 
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
@@ -70,20 +83,24 @@ class HlsFD(FragmentFD):
 
         if not self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')):
             if info_dict.get('extra_param_to_segment_url') or info_dict.get('_decryption_key_url'):
-                self.report_error('pycryptodome not found. Please install it.')
+                self.report_error('pycryptodome not found. Please install')
                 return False
             if self.can_download(s, info_dict, with_crypto=True):
-                self.report_warning('pycryptodome is needed to download this file with hlsnative')
+                self.report_warning('pycryptodome is needed to download this file natively')
-            self.report_warning(
-                'hlsnative has detected features it does not support, '
-                'extraction will be delegated to ffmpeg')
             fd = FFmpegFD(self.ydl, self.params)
+            self.report_warning(
+                '%s detected unsupported features; extraction will be delegated to %s' % (self.FD_NAME, fd.get_basename()))
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
             #     fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
         real_downloader = _get_real_downloader(info_dict, 'frag_urls', self.params, None)
+        if real_downloader and not real_downloader.supports_manifest(s):
+            real_downloader = None
+        if real_downloader:
+            self.to_screen(
+                '[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
 
         def is_ad_fragment_start(s):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
@@ -93,7 +110,7 @@ class HlsFD(FragmentFD):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
                     or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
 
-        fragment_urls = []
+        fragments = []
 
         media_frags = 0
         ad_frags = 0
@@ -136,14 +153,12 @@ class HlsFD(FragmentFD):
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
-        key_list = []
         byte_range = {}
         discontinuity_count = 0
         frag_index = 0
         ad_frag_next = False
         for line in s.splitlines():
             line = line.strip()
-            download_frag = False
             if line:
                 if not line.startswith('#'):
                     if format_index and discontinuity_count != format_index:
@@ -160,17 +175,20 @@ class HlsFD(FragmentFD):
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
 
-                    if real_downloader:
+                    fragments.append({
-                        fragment_urls.append(frag_url)
+                        'frag_index': frag_index,
-                        continue
+                        'url': frag_url,
-                    download_frag = True
+                        'decrypt_info': decrypt_info,
+                        'byte_range': byte_range,
+                        'media_sequence': media_sequence,
+                    })
 
                 elif line.startswith('#EXT-X-MAP'):
                     if format_index and discontinuity_count != format_index:
                         continue
                     if frag_index > 0:
                         self.report_error(
-                            'initialization fragment found after media fragments, unable to download')
+                            'Initialization fragment found after media fragments, unable to download')
                         return False
                     frag_index += 1
                     map_info = parse_m3u8_attributes(line[11:])
@@ -180,9 +198,14 @@ class HlsFD(FragmentFD):
                         else compat_urlparse.urljoin(man_url, map_info.get('URI')))
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
-                    if real_downloader:
+
-                        fragment_urls.append(frag_url)
+                    fragments.append({
-                        continue
+                        'frag_index': frag_index,
+                        'url': frag_url,
+                        'decrypt_info': decrypt_info,
+                        'byte_range': byte_range,
+                        'media_sequence': media_sequence
+                    })
 
                     if map_info.get('BYTERANGE'):
                         splitted_byte_range = map_info.get('BYTERANGE').split('@')
@@ -191,7 +214,6 @@ class HlsFD(FragmentFD):
                             'start': sub_range_start,
                             'end': sub_range_start + int(splitted_byte_range[0]),
                         }
-                    download_frag = True
 
                 elif line.startswith('#EXT-X-KEY'):
                     decrypt_url = decrypt_info.get('URI')
@@ -206,9 +228,6 @@ class HlsFD(FragmentFD):
                             decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
                         if decrypt_url != decrypt_info['URI']:
                             decrypt_info['KEY'] = None
-                    key_data = decrypt_info.copy()
-                    key_data['INDEX'] = frag_index
-                    key_list.append(key_data)
 
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])
@@ -225,58 +244,16 @@ class HlsFD(FragmentFD):
                     ad_frag_next = False
                 elif line.startswith('#EXT-X-DISCONTINUITY'):
                     discontinuity_count += 1
+                i += 1
+                media_sequence += 1
 
-                if download_frag:
+        # We only download the first fragment during the test
-                    count = 0
+        if test:
-                    headers = info_dict.get('http_headers', {})
+            fragments = [fragments[0] if fragments else None]
-                    if byte_range:
-                        headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
-                    while count <= fragment_retries:
-                        try:
-                            success, frag_content = self._download_fragment(
-                                ctx, frag_url, info_dict, headers)
-                            if not success:
-                                return False
-                            break
-                        except compat_urllib_error.HTTPError as err:
-                            # Unavailable (possibly temporary) fragments may be served.
-                            # First we try to retry then either skip or abort.
-                            # See https://github.com/ytdl-org/youtube-dl/issues/10165,
-                            # https://github.com/ytdl-org/youtube-dl/issues/10448).
-                            count += 1
-                            if count <= fragment_retries:
-                                self.report_retry_fragment(err, frag_index, count, fragment_retries)
-                    if count > fragment_retries:
-                        if skip_unavailable_fragments:
-                            i += 1
-                            media_sequence += 1
-                            self.report_skip_fragment(frag_index)
-                            continue
-                        self.report_error(
-                            'giving up after %s fragment retries' % fragment_retries)
-                        return False
-
-                    if decrypt_info['METHOD'] == 'AES-128':
-                        iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
-                        decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
-                            self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
-                        # Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
-                        # size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
-                        # not what it decrypts to.
-                        if not test:
-                            frag_content = AES.new(
-                                decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
-                    self._append_fragment(ctx, frag_content)
-                    # We only download the first fragment during the test
-                    if test:
-                        break
-                    i += 1
-                    media_sequence += 1
 
         if real_downloader:
             info_copy = info_dict.copy()
-            info_copy['url_list'] = fragment_urls
+            info_copy['fragments'] = fragments
-            info_copy['key_list'] = key_list
             fd = real_downloader(self.ydl, self.params)
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
@@ -285,5 +262,107 @@ class HlsFD(FragmentFD):
             if not success:
                 return False
         else:
+            def download_fragment(fragment):
+                frag_index = fragment['frag_index']
+                frag_url = fragment['url']
+                decrypt_info = fragment['decrypt_info']
+                byte_range = fragment['byte_range']
+                media_sequence = fragment['media_sequence']
+
+                ctx['fragment_index'] = frag_index
+
+                count = 0
+                headers = info_dict.get('http_headers', {})
+                if byte_range:
+                    headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
+                while count <= fragment_retries:
+                    try:
+                        success, frag_content = self._download_fragment(
+                            ctx, frag_url, info_dict, headers)
+                        if not success:
+                            return False, frag_index
+                        break
+                    except compat_urllib_error.HTTPError as err:
+                        # Unavailable (possibly temporary) fragments may be served.
+                        # First we try to retry then either skip or abort.
+                        # See https://github.com/ytdl-org/youtube-dl/issues/10165,
+                        # https://github.com/ytdl-org/youtube-dl/issues/10448).
+                        count += 1
+                        if count <= fragment_retries:
+                            self.report_retry_fragment(err, frag_index, count, fragment_retries)
+                if count > fragment_retries:
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return False, frag_index
+
+                if decrypt_info['METHOD'] == 'AES-128':
+                    iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
+                    decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
+                        self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
+                    # Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
+                    # size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
+                    # not what it decrypts to.
+                    if not test:
+                        frag_content = AES.new(
+                            decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
+
+                return frag_content, frag_index
+
+            def append_fragment(frag_content, frag_index):
+                if frag_content:
+                    fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], frag_index)
+                    try:
+                        file, frag_sanitized = sanitize_open(fragment_filename, 'rb')
+                        ctx['fragment_filename_sanitized'] = frag_sanitized
+                        file.close()
+                        self._append_fragment(ctx, frag_content)
+                        return True
+                    except FileNotFoundError:
+                        if skip_unavailable_fragments:
+                            self.report_skip_fragment(frag_index)
+                            return True
+                        else:
+                            self.report_error(
+                                'fragment %s not found, unable to continue' % frag_index)
+                            return False
+                else:
+                    if skip_unavailable_fragments:
+                        self.report_skip_fragment(frag_index)
+                        return True
+                    else:
+                        self.report_error(
+                            'fragment %s not found, unable to continue' % frag_index)
+                        return False
+
+            max_workers = self.params.get('concurrent_fragment_downloads', 1)
+            if can_threaded_download and max_workers > 1:
+                self.report_warning('The download speed shown is only of one thread. This is a known issue')
+                with concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
+                    futures = [pool.submit(download_fragment, fragment) for fragment in fragments]
+                    # timeout must be 0 to return instantly
+                    done, not_done = concurrent.futures.wait(futures, timeout=0)
+                    try:
+                        while not_done:
+                            # Check every 1 second for KeyboardInterrupt
+                            freshly_done, not_done = concurrent.futures.wait(not_done, timeout=1)
+                            done |= freshly_done
+                    except KeyboardInterrupt:
+                        for future in not_done:
+                            future.cancel()
+                        # timeout must be none to cancel
+                        concurrent.futures.wait(not_done, timeout=None)
+                        raise KeyboardInterrupt
+                results = [future.result() for future in futures]
+
+                for frag_content, frag_index in results:
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+            else:
+                for fragment in fragments:
+                    frag_content, frag_index = download_fragment(fragment)
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+
             self._finish_frag_download(ctx)
         return True

yt_dlp/downloader/rtmp.py

@@ -117,7 +117,7 @@ class RtmpFD(FileDownloader):
 
         # Check for rtmpdump first
         if not check_executable('rtmpdump', ['-h']):
-            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when

yt_dlp/downloader/rtsp.py

@@ -24,7 +24,7 @@ class RtspFD(FileDownloader):
             args = [
                 'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
         else:
-            self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
+            self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install one')
             return False
 
         self._debug_cmd(args)

yt_dlp/downloader/youtube_live_chat.py

@@ -79,8 +79,7 @@ class YoutubeLiveChatReplayFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
-        success, raw_fragment = dl_fragment(
+        success, raw_fragment = dl_fragment(info_dict['url'])
-            'https://www.youtube.com/watch?v={}'.format(video_id))
         if not success:
             return False
         try:

yt_dlp/extractor/amcnetworks.py

@@ -65,15 +65,35 @@ class AMCNetworksIE(ThePlatformIE):
     def _real_extract(self, url):
         site, display_id = re.match(self._VALID_URL, url).groups()
         requestor_id = self._REQUESTOR_ID_MAP[site]
-        properties = self._download_json(
+        page_data = self._download_json(
-            'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
+            'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
-            display_id)['data']['properties']
+            % (requestor_id.lower(), display_id), display_id)['data']
+        properties = page_data.get('properties') or {}
         query = {
             'mbr': 'true',
             'manifest': 'm3u',
         }
-        tp_path = 'M_UwQC/media/' + properties['videoPid']
+
-        media_url = 'https://link.theplatform.com/s/' + tp_path
+        video_player_count = 0
+        try:
+            for v in page_data['children']:
+                if v.get('type') == 'video-player':
+                    releasePid = v['properties']['currentVideo']['meta']['releasePid']
+                    tp_path = 'M_UwQC/' + releasePid
+                    media_url = 'https://link.theplatform.com/s/' + tp_path
+                    video_player_count += 1
+        except KeyError:
+            pass
+        if video_player_count > 1:
+            self.report_warning(
+                'The JSON data has %d video players. Only one will be extracted' % video_player_count)
+
+        # Fall back to videoPid if releasePid not found.
+        # TODO: Fall back to videoPid if releasePid manifest uses DRM.
+        if not video_player_count:
+            tp_path = 'M_UwQC/media/' + properties['videoPid']
+            media_url = 'https://link.theplatform.com/s/' + tp_path
+
         theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
         video_id = theplatform_metadata['pid']
@@ -90,30 +110,41 @@ class AMCNetworksIE(ThePlatformIE):
         formats, subtitles = self._extract_theplatform_smil(
             media_url, video_id)
         self._sort_formats(formats)
+
+        thumbnails = []
+        thumbnail_urls = [properties.get('imageDesktop')]
+        if 'thumbnail' in info:
+            thumbnail_urls.append(info.pop('thumbnail'))
+        for thumbnail_url in thumbnail_urls:
+            if not thumbnail_url:
+                continue
+            mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int(mobj.group(1)) if mobj else None,
+                'height': int(mobj.group(2)) if mobj else None,
+            })
+
         info.update({
+            'age_limit': parse_age_limit(rating),
+            'formats': formats,
             'id': video_id,
             'subtitles': subtitles,
-            'formats': formats,
+            'thumbnails': thumbnails,
-            'age_limit': parse_age_limit(parse_age_limit(rating)),
         })
         ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
         if ns_keys:
             ns = list(ns_keys)[0]
-            series = theplatform_metadata.get(ns + '$show')
+            episode = theplatform_metadata.get(ns + '$episodeTitle') or None
-            season_number = int_or_none(
-                theplatform_metadata.get(ns + '$season'))
-            episode = theplatform_metadata.get(ns + '$episodeTitle')
             episode_number = int_or_none(
                 theplatform_metadata.get(ns + '$episode'))
-            if season_number:
+            season_number = int_or_none(
-                title = 'Season %d - %s' % (season_number, title)
+                theplatform_metadata.get(ns + '$season'))
-            if series:
+            series = theplatform_metadata.get(ns + '$show') or None
-                title = '%s - %s' % (series, title)
             info.update({
-                'title': title,
-                'series': series,
-                'season_number': season_number,
                 'episode': episode,
                 'episode_number': episode_number,
+                'season_number': season_number,
+                'series': series,
             })
         return info

yt_dlp/extractor/applepodcasts.py

@@ -42,6 +42,7 @@ class ApplePodcastsIE(InfoExtractor):
         ember_data = self._parse_json(self._search_regex(
             r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
             webpage, 'ember data'), episode_id)
+        ember_data = ember_data.get(episode_id) or ember_data
         episode = ember_data['data']['attributes']
         description = episode.get('description') or {}
 

yt_dlp/extractor/ard.py

@@ -272,7 +272,8 @@ class ARDMediathekIE(ARDMediathekBaseIE):
         else:  # request JSON file
             if not document_id:
                 video_id = self._search_regex(
-                    r'/play/(?:config|media)/(\d+)', webpage, 'media id')
+                    (r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
+                    webpage, 'media id', default=None)
             info = self._extract_media_info(
                 'http://www.ardmediathek.de/play/media/%s' % video_id,
                 webpage, video_id)

yt_dlp/extractor/arnes.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    remove_start,
+)
+
+
+class ArnesIE(InfoExtractor):
+    IE_NAME = 'video.arnes.si'
+    IE_DESC = 'Arnes Video'
+    _VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
+    _TESTS = [{
+        'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
+        'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
+        'info_dict': {
+            'id': 'a1qrWTOQfVoU',
+            'ext': 'mp4',
+            'title': 'Linearna neodvisnost, definicija',
+            'description': 'Linearna neodvisnost, definicija',
+            'license': 'PRIVATE',
+            'creator': 'Polona Oblak',
+            'timestamp': 1585063725,
+            'upload_date': '20200324',
+            'channel': 'Polona Oblak',
+            'channel_id': 'q6pc04hw24cj',
+            'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
+            'duration': 596.75,
+            'view_count': int,
+            'tags': ['linearna_algebra'],
+            'start_time': 10,
+        }
+    }, {
+        'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
+        'only_matching': True,
+    }]
+    _BASE_URL = 'https://video.arnes.si'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
+        title = video['title']
+
+        formats = []
+        for media in (video.get('media') or []):
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            formats.append({
+                'url': self._BASE_URL + media_url,
+                'format_id': remove_start(media.get('format'), 'FORMAT_'),
+                'format_note': media.get('formatTranslation'),
+                'width': int_or_none(media.get('width')),
+                'height': int_or_none(media.get('height')),
+            })
+        self._sort_formats(formats)
+
+        channel = video.get('channel') or {}
+        channel_id = channel.get('url')
+        thumbnail = video.get('thumbnailUrl')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._BASE_URL + thumbnail,
+            'description': video.get('description'),
+            'license': video.get('license'),
+            'creator': video.get('author'),
+            'timestamp': parse_iso8601(video.get('creationTime')),
+            'channel': channel.get('name'),
+            'channel_id': channel_id,
+            'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None,
+            'duration': float_or_none(video.get('duration'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'tags': video.get('hashtags'),
+            'start_time': int_or_none(compat_parse_qs(
+                compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
+        }

yt_dlp/extractor/bandaichannel.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .brightcove import BrightcoveNewIE
+from ..utils import extract_attributes
+
+
+class BandaiChannelIE(BrightcoveNewIE):
+    IE_NAME = 'bandaichannel'
+    _VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
+    _TESTS = [{
+        'url': 'https://www.b-ch.com/titles/514/001',
+        'md5': 'a0f2d787baa5729bed71108257f613a4',
+        'info_dict': {
+            'id': '6128044564001',
+            'ext': 'mp4',
+            'title': 'メタルファイターMIKU 第1話',
+            'timestamp': 1580354056,
+            'uploader_id': '5797077852001',
+            'upload_date': '20200130',
+            'duration': 1387.733,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        attrs = extract_attributes(self._search_regex(
+            r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
+        bc = self._download_json(
+            'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
+            video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
+        return self._parse_brightcove_metadata(bc, bc['id'])

yt_dlp/extractor/bandcamp.py

@@ -49,6 +49,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Ben Prunty',
             'timestamp': 1396508491,
             'upload_date': '20140403',
+            'release_timestamp': 1396483200,
             'release_date': '20140403',
             'duration': 260.877,
             'track': 'Lanius (Battle)',
@@ -69,6 +70,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Mastodon',
             'timestamp': 1322005399,
             'upload_date': '20111122',
+            'release_timestamp': 1076112000,
             'release_date': '20040207',
             'duration': 120.79,
             'track': 'Hail to Fire',
@@ -197,7 +199,7 @@ class BandcampIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': artist,
             'timestamp': timestamp,
-            'release_date': unified_strdate(tralbum.get('album_release_date')),
+            'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
             'duration': duration,
             'track': track,
             'track_number': track_number,

yt_dlp/extractor/bbc.py

@@ -1,14 +1,24 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import functools
 import itertools
+import json
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_etree_Element,
+    compat_HTTPError,
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
 from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
     clean_html,
     dict_get,
-    ExtractorError,
     float_or_none,
     get_element_by_class,
     int_or_none,
@@ -21,11 +31,6 @@ from ..utils import (
     urlencode_postdata,
     urljoin,
 )
-from ..compat import (
-    compat_etree_Element,
-    compat_HTTPError,
-    compat_urlparse,
-)
 
 
 class BBCCoUkIE(InfoExtractor):
@@ -793,11 +798,25 @@ class BBCIE(BBCCoUkIE):
             'description': 'Learn English words and phrases from this story',
         },
         'add_ie': [BBCCoUkIE.ie_key()],
+    }, {
+        # BBC Reel
+        'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
+        'info_dict': {
+            'id': 'p07c6sb9',
+            'ext': 'mp4',
+            'title': 'How positive thinking is harming your happiness',
+            'alt_title': 'The downsides of positive thinking',
+            'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
+            'duration': 235,
+            'thumbnail': r're:https?://.+/p07c9dsr.jpg',
+            'upload_date': '20190604',
+            'categories': ['Psychology'],
+        },
     }]
 
     @classmethod
     def suitable(cls, url):
-        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
+        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerEpisodesIE, BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE)
         return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
                 else super(BBCIE, cls).suitable(url))
 
@@ -929,7 +948,7 @@ class BBCIE(BBCCoUkIE):
                                     else:
                                         entry['title'] = info['title']
                                         entry['formats'].extend(info['formats'])
-                                except Exception as e:
+                                except ExtractorError as e:
                                     # Some playlist URL may fail with 500, at the same time
                                     # the other one may work fine (e.g.
                                     # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
@@ -980,6 +999,37 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
+        # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
+        initial_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)',
+            webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
+        if initial_data:
+            init_data = try_get(
+                initial_data, lambda x: x['initData']['items'][0], dict) or {}
+            smp_data = init_data.get('smpData') or {}
+            clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
+            version_id = clip_data.get('versionID')
+            if version_id:
+                title = smp_data['title']
+                formats, subtitles = self._download_media_selector(version_id)
+                self._sort_formats(formats)
+                image_url = smp_data.get('holdingImageURL')
+                display_date = init_data.get('displayDate')
+                topic_title = init_data.get('topicTitle')
+
+                return {
+                    'id': version_id,
+                    'title': title,
+                    'formats': formats,
+                    'alt_title': init_data.get('shortTitle'),
+                    'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
+                    'description': smp_data.get('summary') or init_data.get('shortSummary'),
+                    'upload_date': display_date.replace('-', '') if display_date else None,
+                    'subtitles': subtitles,
+                    'duration': int_or_none(clip_data.get('duration')),
+                    'categories': [topic_title] if topic_title else None,
+                }
+
         # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
         # There are several setPayload calls may be present but the video
         # seems to be always related to the first one
@@ -1041,7 +1091,7 @@ class BBCIE(BBCCoUkIE):
                 thumbnail = None
                 image_url = current_programme.get('image_url')
                 if image_url:
-                    thumbnail = image_url.replace('{recipe}', '1920x1920')
+                    thumbnail = image_url.replace('{recipe}', 'raw')
                 return {
                     'id': programme_id,
                     'title': title,
@@ -1293,21 +1343,149 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
             playlist_id, title, description)
 
 
-class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
+class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
-    IE_NAME = 'bbc.co.uk:iplayer:playlist'
+    _VALID_URL_TMPL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/%%s/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+
-    _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
+    @staticmethod
-    _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
+    def _get_default(episode, key, default_key='default'):
+        return try_get(episode, lambda x: x[key][default_key])
+
+    def _get_description(self, data):
+        synopsis = data.get(self._DESCRIPTION_KEY) or {}
+        return dict_get(synopsis, ('large', 'medium', 'small'))
+
+    def _fetch_page(self, programme_id, per_page, series_id, page):
+        elements = self._get_elements(self._call_api(
+            programme_id, per_page, page + 1, series_id))
+        for element in elements:
+            episode = self._get_episode(element)
+            episode_id = episode.get('id')
+            if not episode_id:
+                continue
+            thumbnail = None
+            image = self._get_episode_image(episode)
+            if image:
+                thumbnail = image.replace('{recipe}', 'raw')
+            category = self._get_default(episode, 'labels', 'category')
+            yield {
+                '_type': 'url',
+                'id': episode_id,
+                'title': self._get_episode_field(episode, 'subtitle'),
+                'url': 'https://www.bbc.co.uk/iplayer/episode/' + episode_id,
+                'thumbnail': thumbnail,
+                'description': self._get_description(episode),
+                'categories': [category] if category else None,
+                'series': self._get_episode_field(episode, 'title'),
+                'ie_key': BBCCoUkIE.ie_key(),
+            }
+
+    def _real_extract(self, url):
+        pid = self._match_id(url)
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        series_id = qs.get('seriesId', [None])[0]
+        page = qs.get('page', [None])[0]
+        per_page = 36 if page else self._PAGE_SIZE
+        fetch_page = functools.partial(self._fetch_page, pid, per_page, series_id)
+        entries = fetch_page(int(page) - 1) if page else OnDemandPagedList(fetch_page, self._PAGE_SIZE)
+        playlist_data = self._get_playlist_data(self._call_api(pid, 1))
+        return self.playlist_result(
+            entries, pid, self._get_playlist_title(playlist_data),
+            self._get_description(playlist_data))
+
+
+class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:episodes'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'episodes'
     _TESTS = [{
         'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
         'info_dict': {
             'id': 'b05rcz9v',
             'title': 'The Disappearance',
-            'description': 'French thriller serial about a missing teenager.',
+            'description': 'md5:58eb101aee3116bad4da05f91179c0cb',
         },
-        'playlist_mincount': 6,
+        'playlist_mincount': 8,
-        'skip': 'This programme is not currently available on BBC iPlayer',
     }, {
+        # all seasons
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 10,
+    }, {
+        # explicit season
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster?seriesId=b094m6nv',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 5,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 37,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove?page=2',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 1,
+    }]
+    _PAGE_SIZE = 100
+    _DESCRIPTION_KEY = 'synopsis'
+
+    def _get_episode_image(self, episode):
+        return self._get_default(episode, 'image')
+
+    def _get_episode_field(self, episode, field):
+        return self._get_default(episode, field)
+
+    @staticmethod
+    def _get_elements(data):
+        return data['entities']['results']
+
+    @staticmethod
+    def _get_episode(element):
+        return element.get('episode') or {}
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        variables = {
+            'id': pid,
+            'page': page,
+            'perPage': per_page,
+        }
+        if series_id:
+            variables['sliceId'] = series_id
+        return self._download_json(
+            'https://graph.ibl.api.bbc.co.uk/', pid, headers={
+                'Content-Type': 'application/json'
+            }, data=json.dumps({
+                'id': '5692d93d5aac8d796a0305e895e61551',
+                'variables': variables,
+            }).encode('utf-8'))['data']['programme']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data
+
+    def _get_playlist_title(self, data):
+        return self._get_default(data, 'title')
+
+
+class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:group'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'group'
+    _TESTS = [{
         # Available for over a year unlike 30 days for most other programmes
         'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
         'info_dict': {
@@ -1316,14 +1494,56 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
         },
         'playlist_mincount': 10,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 47,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7?page=2',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 11,
     }]
+    _PAGE_SIZE = 200
+    _DESCRIPTION_KEY = 'synopses'
 
-    def _extract_title_and_description(self, webpage):
+    def _get_episode_image(self, episode):
-        title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
+        return self._get_default(episode, 'images', 'standard')
-        description = self._search_regex(
+
-            r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
+    def _get_episode_field(self, episode, field):
-            webpage, 'description', fatal=False, group='value')
+        return episode.get(field)
-        return title, description
+
+    @staticmethod
+    def _get_elements(data):
+        return data['elements']
+
+    @staticmethod
+    def _get_episode(element):
+        return element
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        return self._download_json(
+            'http://ibl.api.bbc.co.uk/ibl/v1/groups/%s/episodes' % pid,
+            pid, query={
+                'page': page,
+                'per_page': per_page,
+            })['group_episodes']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data['group']
+
+    def _get_playlist_title(self, data):
+        return data.get('title')
 
 
 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):

yt_dlp/extractor/bilibili.py

@@ -7,6 +7,7 @@ import re
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..compat import (
+    compat_str,
     compat_parse_qs,
     compat_urlparse,
 )
@@ -15,6 +16,7 @@ from ..utils import (
     int_or_none,
     float_or_none,
     parse_iso8601,
+    try_get,
     smuggle_url,
     str_or_none,
     strip_jsonp,
@@ -113,6 +115,13 @@ class BiliBiliIE(InfoExtractor):
         # new BV video id format
         'url': 'https://www.bilibili.com/video/BV1JE411F741',
         'only_matching': True,
+    }, {
+        # Anthology
+        'url': 'https://www.bilibili.com/video/BV1bK411W797',
+        'info_dict': {
+            'id': 'BV1bK411W797',
+        },
+        'playlist_count': 17,
     }]
 
     _APP_KEY = 'iVGUTjsxvpLeuDCf'
@@ -139,9 +148,19 @@ class BiliBiliIE(InfoExtractor):
         page_id = mobj.group('page')
         webpage = self._download_webpage(url, video_id)
 
+        # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself.
+        # If the video has no page argument, check to see if it's an anthology
+        if page_id is None:
+            if not self._downloader.params.get('noplaylist'):
+                r = self._extract_anthology_entries(bv_id, video_id, webpage)
+                if r is not None:
+                    self.to_screen('Downloading anthology %s - add --no-playlist to just download video' % video_id)
+                    return r
+            self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
+
         if 'anime/' not in url:
             cid = self._search_regex(
-                r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + str(page_id), webpage, 'cid',
+                r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + compat_str(page_id), webpage, 'cid',
                 default=None
             ) or self._search_regex(
                 r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
@@ -170,6 +189,7 @@ class BiliBiliIE(InfoExtractor):
             cid = js['result']['cid']
 
         headers = {
+            'Accept': 'application/json',
             'Referer': url
         }
         headers.update(self.geo_verification_headers())
@@ -223,7 +243,18 @@ class BiliBiliIE(InfoExtractor):
         title = self._html_search_regex(
             (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
              r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
-            group='title') + ('_p' + str(page_id) if page_id is not None else '')
+            group='title')
+
+        # Get part title for anthologies
+        if page_id is not None:
+            # TODO: The json is already downloaded by _extract_anthology_entries. Don't redownload for each video
+            part_title = try_get(
+                self._download_json(
+                    "https://api.bilibili.com/x/player/pagelist?bvid=%s&jsonp=jsonp" % bv_id,
+                    video_id, note='Extracting videos in anthology'),
+                lambda x: x['data'][int(page_id) - 1]['part'])
+            title = part_title or title
+
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time',
@@ -233,7 +264,7 @@ class BiliBiliIE(InfoExtractor):
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
-            'id': str(video_id) if page_id is None else '%s_p%s' % (video_id, page_id),
+            'id': compat_str(video_id) if page_id is None else '%s_p%s' % (video_id, page_id),
             'cid': cid,
             'title': title,
             'description': description,
@@ -299,7 +330,7 @@ class BiliBiliIE(InfoExtractor):
 
             global_info = {
                 '_type': 'multi_video',
-                'id': video_id,
+                'id': compat_str(video_id),
                 'bv_id': bv_id,
                 'title': title,
                 'description': description,
@@ -311,6 +342,20 @@ class BiliBiliIE(InfoExtractor):
 
             return global_info
 
+    def _extract_anthology_entries(self, bv_id, video_id, webpage):
+        title = self._html_search_regex(
+            (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
+            group='title')
+        json_data = self._download_json(
+            "https://api.bilibili.com/x/player/pagelist?bvid=%s&jsonp=jsonp" % bv_id,
+            video_id, note='Extracting videos in anthology')
+
+        if len(json_data['data']) > 1:
+            return self.playlist_from_matches(
+                json_data['data'], bv_id, title, ie=BiliBiliIE.ie_key(),
+                getter=lambda entry: 'https://www.bilibili.com/video/%s?p=%d' % (bv_id, entry['page']))
+
     def _get_video_id_set(self, id, is_bv):
         query = {'bvid': id} if is_bv else {'aid': id}
         response = self._download_json(
@@ -505,7 +550,7 @@ class BiliBiliSearchIE(SearchInfoExtractor):
 
             videos = data['result']
             for video in videos:
-                e = self.url_result(video['arcurl'], 'BiliBili', str(video['aid']))
+                e = self.url_result(video['arcurl'], 'BiliBili', compat_str(video['aid']))
                 entries.append(e)
 
             if(len(entries) >= n or len(videos) >= BiliBiliSearchIE.MAX_NUMBER_OF_RESULTS):

yt_dlp/extractor/cbs.py

@@ -27,10 +27,10 @@ class CBSBaseIE(ThePlatformFeedIE):
 
 
 class CBSIE(CBSBaseIE):
-    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
+    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
 
     _TESTS = [{
-        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
             'ext': 'mp4',
@@ -52,16 +52,19 @@ class CBSIE(CBSBaseIE):
     }, {
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
+        'only_matching': True,
     }]
 
     def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
         items_data = self._download_xml(
-            'http://can.cbs.com/thunder/player/videoPlayerService.php',
+            'https://can.cbs.com/thunder/player/videoPlayerService.php',
             content_id, query={'partner': site, 'contentId': content_id})
         video_data = xpath_element(items_data, './/item')
         title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
         tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
-        tp_release_url = 'http://link.theplatform.com/s/' + tp_path
+        tp_release_url = 'https://link.theplatform.com/s/' + tp_path
 
         asset_types = []
         subtitles = {}

yt_dlp/extractor/common.py

@@ -231,8 +231,9 @@ class InfoExtractor(object):
     uploader:       Full name of the video uploader.
     license:        License name the video is licensed under.
     creator:        The creator of the video.
+    release_timestamp: UNIX timestamp of the moment the video was released.
     release_date:   The date (YYYYMMDD) when the video was released.
-    timestamp:      UNIX timestamp of the moment the video became available.
+    timestamp:      UNIX timestamp of the moment the video was uploaded
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
@@ -251,8 +252,8 @@ class InfoExtractor(object):
                         * "data": The subtitles file contents
                         * "url": A URL pointing to the subtitles file
                     "ext" will be calculated from URL if missing
-    automatic_captions: Like 'subtitles', used by the YoutubeIE for
+    automatic_captions: Like 'subtitles'; contains automatically generated
-                    automatically generated captions
+                    captions instead of normal subtitles
     duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
@@ -264,6 +265,7 @@ class InfoExtractor(object):
                     properties (all but one of text or html optional):
                         * "author" - human-readable name of the comment author
                         * "author_id" - user ID of the comment author
+                        * "author_thumbnail" - The thumbnail of the comment author
                         * "id" - Comment ID
                         * "html" - Comment as HTML
                         * "text" - Plain text of the comment
@@ -271,6 +273,12 @@ class InfoExtractor(object):
                         * "parent" - ID of the comment this one is replying to.
                                      Set to "root" to indicate that this is a
                                      comment to the original video.
+                        * "like_count" - Number of positive ratings of the comment
+                        * "dislike_count" - Number of negative ratings of the comment
+                        * "is_favorited" - Whether the comment is marked as
+                                           favorite by the video uploader
+                        * "author_is_uploader" - Whether the comment is made by
+                                                 the video uploader
     age_limit:      Age restriction for the video, as an integer (years)
     webpage_url:    The URL to the video webpage, if given to yt-dlp it
                     should allow to get the same result again. (It will be set
@@ -293,7 +301,11 @@ class InfoExtractor(object):
     playable_in_embed: Whether this video is allowed to play in embedded
                     players on other sites. Can be True (=always allowed),
                     False (=never allowed), None (=unknown), or a string
-                    specifying the criteria for embedability (Eg: 'whitelist').
+                    specifying the criteria for embedability (Eg: 'whitelist')
+    availability:   Under what condition the video is available. One of
+                    'private', 'premium_only', 'subscriber_only', 'needs_auth',
+                    'unlisted' or 'public'. Use 'InfoExtractor._availability'
+                    to set it
     __post_extractor: A function to be called just before the metadata is
                     written to either disk, logger or console. The function
                     must return a dict which will be added to the info_dict.
@@ -1386,7 +1398,7 @@ class InfoExtractor(object):
         return self._hidden_inputs(form)
 
     class FormatSort:
-        regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<seperator>[~:])(?P<limit>.*?))?)? *$'
+        regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'
 
         default = ('hidden', 'hasvid', 'ie_pref', 'lang', 'quality',
                    'res', 'fps', 'codec:vp9.2', 'size', 'br', 'asr',
@@ -1409,8 +1421,8 @@ class InfoExtractor(object):
             'ie_pref': {'priority': True, 'type': 'extractor'},
             'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
             'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'lang': {'priority': True, 'convert': 'ignore', 'type': 'extractor', 'field': 'language_preference'},
+            'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
-            'quality': {'convert': 'float_none', 'type': 'extractor'},
+            'quality': {'convert': 'float_none'},
             'filesize': {'convert': 'bytes'},
             'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
             'id': {'convert': 'string', 'field': 'format_id'},
@@ -1421,7 +1433,7 @@ class InfoExtractor(object):
             'vbr': {'convert': 'float_none'},
             'abr': {'convert': 'float_none'},
             'asr': {'convert': 'float_none'},
-            'source': {'convert': 'ignore', 'type': 'extractor', 'field': 'source_preference'},
+            'source': {'convert': 'ignore', 'field': 'source_preference'},
 
             'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
             'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
@@ -1546,7 +1558,7 @@ class InfoExtractor(object):
                 if self._get_field_setting(field, 'type') == 'alias':
                     field = self._get_field_setting(field, 'field')
                 reverse = match.group('reverse') is not None
-                closest = match.group('seperator') == '~'
+                closest = match.group('separator') == '~'
                 limit_text = match.group('limit')
 
                 has_limit = limit_text is not None
@@ -1849,8 +1861,9 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None, quality=None,
-                              m3u8_id=None, live=False, note=None, errnote=None,
+                              m3u8_id=None, note=None, errnote=None,
-                              fatal=True, data=None, headers={}, query={}):
+                              fatal=True, live=False, data=None, headers={},
+                              query={}):
         res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
@@ -1904,15 +1917,16 @@ class InfoExtractor(object):
         # media playlist and MUST NOT appear in master playlist thus we can
         # clearly detect media playlist with this criterion.
 
-        def _extract_m3u8_playlist_formats(format_url=None, m3u8_doc=None):
+        def _extract_m3u8_playlist_formats(format_url=None, m3u8_doc=None, video_id=None,
+                                           fatal=True, data=None, headers={}):
             if not m3u8_doc:
                 if not format_url:
                     return []
                 res = self._download_webpage_handle(
                     format_url, video_id,
                     note=False,
-                    errnote=errnote or 'Failed to download m3u8 playlist information',
+                    errnote='Failed to download m3u8 playlist information',
-                    fatal=fatal, data=data, headers=headers, query=query)
+                    fatal=fatal, data=data, headers=headers)
 
                 if res is False:
                     return []
@@ -1984,7 +1998,8 @@ class InfoExtractor(object):
             if media_url:
                 manifest_url = format_url(media_url)
                 format_id = []
-                playlist_formats = _extract_m3u8_playlist_formats(manifest_url)
+                playlist_formats = _extract_m3u8_playlist_formats(manifest_url, video_id=video_id,
+                                                                  fatal=fatal, data=data, headers=headers)
 
                 for format in playlist_formats:
                     format_index = format.get('index')
@@ -2045,13 +2060,14 @@ class InfoExtractor(object):
                     or last_stream_inf.get('BANDWIDTH'), scale=1000)
                 manifest_url = format_url(line.strip())
 
-                playlist_formats = _extract_m3u8_playlist_formats(manifest_url)
+                playlist_formats = _extract_m3u8_playlist_formats(manifest_url, video_id=video_id,
+                                                                  fatal=fatal, data=data, headers=headers)
 
-                for format in playlist_formats:
+                for frmt in playlist_formats:
                     format_id = []
                     if m3u8_id:
                         format_id.append(m3u8_id)
-                    format_index = format.get('index')
+                    format_index = frmt.get('index')
                     stream_name = build_stream_name()
                     # Bandwidth of live streams may differ over time thus making
                     # format_id unpredictable. So it's better to keep provided
@@ -2106,6 +2122,8 @@ class InfoExtractor(object):
                             # TODO: update acodec for audio only formats with
                             # the same GROUP-ID
                             f['acodec'] = 'none'
+                    if not f.get('ext'):
+                        f['ext'] = 'm4a' if f.get('vcodec') == 'none' else 'mp4'
                     formats.append(f)
 
                     # for DailyMotion
@@ -3203,7 +3221,10 @@ class InfoExtractor(object):
         """ Return a compat_cookies.SimpleCookie with the cookies for the url """
         req = sanitized_Request(url)
         self._downloader.cookiejar.add_cookie_header(req)
-        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+        cookie = req.get_header('Cookie')
+        if cookie and sys.version_info[0] == 2:
+            cookie = str(cookie)
+        return compat_cookies.SimpleCookie(cookie)
 
     def _apply_first_set_cookie_header(self, url_handle, cookie):
         """
@@ -3318,6 +3339,20 @@ class InfoExtractor(object):
     def _generic_title(self, url):
         return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
 
+    @staticmethod
+    def _availability(is_private, needs_premium, needs_subscription, needs_auth, is_unlisted):
+        all_known = all(map(
+            lambda x: x is not None,
+            (is_private, needs_premium, needs_subscription, needs_auth, is_unlisted)))
+        return (
+            'private' if is_private
+            else 'premium_only' if needs_premium
+            else 'subscriber_only' if needs_subscription
+            else 'needs_auth' if needs_auth
+            else 'unlisted' if is_unlisted
+            else 'public' if all_known
+            else None)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

yt_dlp/extractor/commonprotocols.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urlparse,
@@ -58,3 +60,16 @@ class MmsIE(InfoExtractor):
             'title': title,
             'url': url,
         }
+
+
+class ViewSourceIE(InfoExtractor):
+    IE_DESC = False
+    _VALID_URL = r'view-source:(?P<url>.+)'
+
+    _TEST = {
+        'url': 'view-source:https://www.youtube.com/watch?v=BaW_jenozKc',
+        'only_matching': True
+    }
+
+    def _real_extract(self, url):
+        return self.url_result(re.match(self._VALID_URL, url).group('url'))

yt_dlp/extractor/dplay.py

@@ -296,6 +296,51 @@ class DPlayIE(InfoExtractor):
             url, display_id, host, 'dplay' + country, country)
 
 
+class DiscoveryPlusIndiaIE(DPlayIE):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/videos?' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.in/videos/how-do-they-do-it/fugu-and-more?seasonId=8&type=EPISODE',
+        'info_dict': {
+            'id': '27104',
+            'ext': 'mp4',
+            'display_id': 'how-do-they-do-it/fugu-and-more',
+            'title': 'Fugu and More',
+            'description': 'The Japanese catch, prepare and eat the deadliest fish on the planet.',
+            'duration': 1319,
+            'timestamp': 1582309800,
+            'upload_date': '20200221',
+            'series': 'How Do They Do It?',
+            'season_number': 8,
+            'episode_number': 2,
+            'creator': 'Discovery Channel',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+        'skip': 'Cookies (not necessarily logged in) are needed'
+    }]
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['x-disco-params'] = 'realm=%s' % realm
+        headers['x-disco-client'] = 'WEB:UNKNOWN:dplus-india:17.0.0'
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        return self._download_json(
+            disco_base + 'playback/v3/videoPlaybackInfo',
+            video_id, headers=headers, data=json.dumps({
+                'deviceInfo': {
+                    'adBlocker': False,
+                },
+                'videoId': video_id,
+            }).encode('utf-8'))['data']['attributes']['streaming']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'ap2-prod-direct.discoveryplus.in', 'dplusindia', 'in')
+
+
 class DiscoveryPlusIE(DPlayIE):
     _VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
     _TESTS = [{

yt_dlp/extractor/dreisat.py

@@ -1,193 +1,43 @@
 from __future__ import unicode_literals
 
-import re
+from .zdf import ZDFIE
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    xpath_text,
-    determine_ext,
-    float_or_none,
-    ExtractorError,
-)
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
-    _GEO_COUNTRIES = ['DE']
+    _VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
-    _VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
+    _TESTS = [{
-    _TESTS = [
+        # Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
-        {
+        'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
-            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
-            'md5': 'be37228896d30a88f315b638900a026e',
+        'info_dict': {
-            'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
-                'id': '45918',
+            'ext': 'mp4',
-                'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
-                'title': 'Waidmannsheil',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
-                'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+            'duration': 2660,
-                'uploader': 'SCHWEIZWEIT',
+            'timestamp': 1608604200,
-                'uploader_id': '100000210',
+            'upload_date': '20201222',
-                'upload_date': '20140913'
-            },
-            'params': {
-                'skip_download': True,  # m3u8 downloads
-            }
         },
-        {
+    }, {
-            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
+        'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
-            'only_matching': True,
+        'info_dict': {
+            'id': '140913_sendung_schweizweit',
+            'ext': 'mp4',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+            'timestamp': 1410623100,
+            'upload_date': '20140913'
         },
-    ]
+        'params': {
-
+            'skip_download': True,
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        param_groups = {}
-        for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
-            group_id = param_group.get(self._xpath_ns(
-                'id', 'http://www.w3.org/XML/1998/namespace'))
-            params = {}
-            for param in param_group:
-                params[param.get('name')] = param.get('value')
-            param_groups[group_id] = params
-
-        formats = []
-        for video in smil.findall(self._xpath_ns('.//video', namespace)):
-            src = video.get('src')
-            if not src:
-                continue
-            bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-            group_id = video.get('paramGroup')
-            param_group = param_groups[group_id]
-            for proto in param_group['protocols'].split(','):
-                formats.append({
-                    'url': '%s://%s' % (proto, param_group['host']),
-                    'app': param_group['app'],
-                    'play_path': src,
-                    'ext': 'flv',
-                    'format_id': '%s-%d' % (proto, bitrate),
-                    'tbr': bitrate,
-                })
-        self._sort_formats(formats)
-        return formats
-
-    def extract_from_xml_url(self, video_id, xml_url):
-        doc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        status_code = xpath_text(doc, './status/statuscode')
-        if status_code and status_code != 'ok':
-            if status_code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, status_code)
-            raise ExtractorError(message, expected=True)
-
-        title = xpath_text(doc, './/information/title', 'title', True)
-
-        urls = []
-        formats = []
-        for fnode in doc.findall('.//formitaeten/formitaet'):
-            video_url = xpath_text(fnode, 'url')
-            if not video_url or video_url in urls:
-                continue
-            urls.append(video_url)
-
-            is_available = 'http://www.metafilegenerator' not in video_url
-            geoloced = 'static_geoloced_online' in video_url
-            if not is_available or geoloced:
-                continue
-
-            format_id = fnode.attrib['basetype']
-            format_m = re.match(r'''(?x)
-                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
-                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
-            ''', format_id)
-
-            ext = determine_ext(video_url, None) or format_m.group('container')
-
-            if ext == 'meta':
-                continue
-            elif ext == 'smil':
-                formats.extend(self._extract_smil_formats(
-                    video_url, video_id, fatal=False))
-            elif ext == 'm3u8':
-                # the certificates are misconfigured (see
-                # https://github.com/ytdl-org/youtube-dl/issues/8665)
-                if video_url.startswith('https://'):
-                    continue
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    video_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                quality = xpath_text(fnode, './quality')
-                if quality:
-                    format_id += '-' + quality
-
-                abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
-                vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
-
-                tbr = int_or_none(self._search_regex(
-                    r'_(\d+)k', video_url, 'bitrate', None))
-                if tbr and vbr and not abr:
-                    abr = tbr - vbr
-
-                formats.append({
-                    'format_id': format_id,
-                    'url': video_url,
-                    'ext': ext,
-                    'acodec': format_m.group('acodec'),
-                    'vcodec': format_m.group('vcodec'),
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(xpath_text(fnode, './width')),
-                    'height': int_or_none(xpath_text(fnode, './height')),
-                    'filesize': int_or_none(xpath_text(fnode, './filesize')),
-                    'protocol': format_m.group('proto').lower(),
-                })
-
-        geolocation = xpath_text(doc, './/details/geolocation')
-        if not formats and geolocation and geolocation != 'none':
-            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-
-        self._sort_formats(formats)
-
-        thumbnails = []
-        for node in doc.findall('.//teaserimages/teaserimage'):
-            thumbnail_url = node.text
-            if not thumbnail_url:
-                continue
-            thumbnail = {
-                'url': thumbnail_url,
-            }
-            thumbnail_key = node.get('key')
-            if thumbnail_key:
-                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
-                if m:
-                    thumbnail['width'] = int(m.group(1))
-                    thumbnail['height'] = int(m.group(2))
-            thumbnails.append(thumbnail)
-
-        upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': xpath_text(doc, './/information/detail'),
-            'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
-            'thumbnails': thumbnails,
-            'uploader': xpath_text(doc, './/details/originChannelTitle'),
-            'uploader_id': xpath_text(doc, './/details/originChannelId'),
-            'upload_date': upload_date,
-            'formats': formats,
         }
-
+    }, {
-    def _real_extract(self, url):
+        # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
-        video_id = self._match_id(url)
+        'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
-        details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
+        'only_matching': True,
-        return self.extract_from_xml_url(video_id, details_url)
+    }, {
+        # Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }]

yt_dlp/extractor/extractors.py

@@ -80,6 +80,7 @@ from .arte import (
     ArteTVEmbedIE,
     ArteTVPlaylistIE,
 )
+from .arnes import ArnesIE
 from .asiancrush import (
     AsianCrushIE,
     AsianCrushPlaylistIE,
@@ -103,11 +104,13 @@ from .awaan import (
 )
 from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
+from .bandaichannel import BandaiChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
 from .bbc import (
     BBCCoUkIE,
     BBCCoUkArticleIE,
-    BBCCoUkIPlayerPlaylistIE,
+    BBCCoUkIPlayerEpisodesIE,
+    BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
     BBCIE,
 )
@@ -262,6 +265,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import (
     MmsIE,
     RtmpIE,
+    ViewSourceIE,
 )
 from .condenast import CondeNastIE
 from .contv import CONtvIE
@@ -313,6 +317,7 @@ from .douyutv import (
 from .dplay import (
     DPlayIE,
     DiscoveryPlusIE,
+    DiscoveryPlusIndiaIE,
     HGTVDeIE,
 )
 from .dreisat import DreiSatIE
@@ -449,10 +454,7 @@ from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
-from .gedi import (
+from .gedidigital import GediDigitalIE
-    GediIE,
-    GediEmbedsIE,
-)
 from .generic import GenericIE
 from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
@@ -583,7 +585,11 @@ from .kuwo import (
     KuwoCategoryIE,
     KuwoMvIE,
 )
-from .la7 import LA7IE
+from .la7 import (
+    LA7IE,
+    LA7PodcastEpisodeIE,
+    LA7PodcastIE,
+)
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
@@ -710,7 +716,10 @@ from .mixcloud import (
     MixcloudUserIE,
     MixcloudPlaylistIE,
 )
-from .mlb import MLBIE
+from .mlb import (
+    MLBIE,
+    MLBVideoIE,
+)
 from .mnet import MnetIE
 from .moevideo import MoeVideoIE
 from .mofosex import (
@@ -734,9 +743,12 @@ from .mtv import (
     MTVServicesEmbeddedIE,
     MTVDEIE,
     MTVJapanIE,
+    MTVItaliaIE,
+    MTVItaliaProgrammaIE,
 )
 from .muenchentv import MuenchenTVIE
 from .mwave import MwaveIE, MwaveMeetGreetIE
+from .mxplayer import MxplayerIE
 from .mychannels import MyChannelsIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
@@ -821,7 +833,7 @@ from .nick import (
     NickNightIE,
     NickRuIE,
 )
-from .niconico import NiconicoIE, NiconicoPlaylistIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE, NiconicoUserIE
 from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
@@ -916,6 +928,11 @@ from .packtpub import (
     PacktPubIE,
     PacktPubCourseIE,
 )
+from .palcomp3 import (
+    PalcoMP3IE,
+    PalcoMP3ArtistIE,
+    PalcoMP3VideoIE,
+)
 from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
@@ -952,6 +969,7 @@ from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
+from .plutotv import PlutoTVIE
 from .pluralsight import (
     PluralsightIE,
     PluralsightCourseIE,
@@ -1177,7 +1195,10 @@ from .spike import (
     BellatorIE,
     ParamountNetworkIE,
 )
-from .stitcher import StitcherIE
+from .stitcher import (
+    StitcherIE,
+    StitcherShowIE,
+)
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
@@ -1558,6 +1579,7 @@ from .weibo import (
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
+from .wimtv import WimTVIE
 from .wistia import (
     WistiaIE,
     WistiaPlaylistIE,
@@ -1664,8 +1686,14 @@ from .zattoo import (
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
+from .zee5 import (
+    Zee5IE,
+    Zee5SeriesIE,
+)
 from .zhihu import ZhihuIE
-from .zingmp3 import ZingMp3IE
+from .zingmp3 import (
-from .zee5 import Zee5IE
+    ZingMp3IE,
+    ZingMp3AlbumIE,
+)
 from .zoom import ZoomIE
 from .zype import ZypeIE

yt_dlp/extractor/francetv.py

@@ -401,7 +401,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
             (r'player\.load[^;]+src:\s*["\']([^"\']+)',
              r'id-video=([^@]+@[^"]+)',
              r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
-             r'data-id="([^"]+)"'),
+             r'data-id=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
             webpage, 'video id')
 
         return self._make_url_result(video_id)

yt_dlp/extractor/fujitv.py

@@ -17,7 +17,7 @@ class FujiTVFODPlus7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         formats = self._extract_m3u8_formats(
-            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id)
+            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id, 'mp4')
         for f in formats:
             wh = self._BITRATE_MAP.get(f.get('tbr'))
             if wh:

yt_dlp/extractor/gedi.py

@@ -1,266 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    base_url,
-    url_basename,
-    urljoin,
-)
-
-
-class GediBaseIE(InfoExtractor):
-    @staticmethod
-    def _clean_audio_fmts(formats):
-        unique_formats = []
-        for f in formats:
-            if 'acodec' in f:
-                unique_formats.append(f)
-        formats[:] = unique_formats
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        player_data = re.findall(
-            r'PlayerFactory\.setParam\(\'(?P<type>.+?)\',\s*\'(?P<name>.+?)\',\s*\'(?P<val>.+?)\'\);',
-            webpage)
-
-        formats = []
-        audio_fmts = []
-        hls_fmts = []
-        http_fmts = []
-        title = ''
-        thumb = ''
-
-        fmt_reg = r'(?P<t>video|audio)-(?P<p>rrtv|hls)-(?P<h>[\w\d]+)(?:-(?P<br>[\w\d]+))?$'
-        br_reg = r'video-rrtv-(?P<br>\d+)-'
-
-        for t, n, v in player_data:
-            if t == 'format':
-                m = re.match(fmt_reg, n)
-                if m:
-                    # audio formats
-                    if m.group('t') == 'audio':
-                        if m.group('p') == 'hls':
-                            audio_fmts.extend(self._extract_m3u8_formats(
-                                v, video_id, 'm4a', m3u8_id='hls', fatal=False))
-                        elif m.group('p') == 'rrtv':
-                            audio_fmts.append({
-                                'format_id': 'mp3',
-                                'url': v,
-                                'tbr': 128,
-                                'ext': 'mp3',
-                                'vcodec': 'none',
-                                'acodec': 'mp3',
-                            })
-
-                    # video formats
-                    elif m.group('t') == 'video':
-                        # hls manifest video
-                        if m.group('p') == 'hls':
-                            hls_fmts.extend(self._extract_m3u8_formats(
-                                v, video_id, 'mp4', m3u8_id='hls', fatal=False))
-                        # direct mp4 video
-                        elif m.group('p') == 'rrtv':
-                            if not m.group('br'):
-                                mm = re.search(br_reg, v)
-                            http_fmts.append({
-                                'format_id': 'https-' + m.group('h'),
-                                'protocol': 'https',
-                                'url': v,
-                                'tbr': int(m.group('br')) if m.group('br') else
-                                (int(mm.group('br')) if mm.group('br') else 0),
-                                'height': int(m.group('h'))
-                            })
-
-            elif t == 'param':
-                if n == 'videotitle':
-                    title = v
-                if n == 'image_full_play':
-                    thumb = v
-
-        title = self._og_search_title(webpage) if title == '' else title
-
-        # clean weird char
-        title = compat_str(title).encode('utf8', 'replace').replace(b'\xc3\x82', b'').decode('utf8', 'replace')
-
-        if audio_fmts:
-            self._clean_audio_fmts(audio_fmts)
-            self._sort_formats(audio_fmts)
-        if hls_fmts:
-            self._sort_formats(hls_fmts)
-        if http_fmts:
-            self._sort_formats(http_fmts)
-
-        formats.extend(audio_fmts)
-        formats.extend(hls_fmts)
-        formats.extend(http_fmts)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': self._html_search_meta('twitter:description', webpage),
-            'thumbnail': thumb,
-            'formats': formats,
-        }
-
-
-class GediIE(GediBaseIE):
-    _VALID_URL = r'''(?x)https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/(?!embed/).+?/(?P<id>[\d/]+)(?:\?|\&|$)'''
-    _TESTS = [{
-        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
-        'md5': '84658d7fb9e55a6e57ecc77b73137494',
-        'info_dict': {
-            'id': '121559/121683',
-            'ext': 'mp4',
-            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
-            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
-        'md5': 'e763b94b7920799a0e0e23ffefa2d157',
-        'info_dict': {
-            'id': '367415/367963',
-            'ext': 'mp4',
-            'title': 'Record della pista a Spa Francorchamps, la Pagani Huayra Roadster BC stupisce',
-            'description': 'md5:5deb503cefe734a3eb3f07ed74303920',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
-        'md5': 'e48108e97b1af137d22a8469f2019057',
-        'info_dict': {
-            'id': '66184/66267',
-            'ext': 'mp4',
-            'title': 'Cassani e i brividi azzurri ai Mondiali di Imola: \\"Qui mi sono innamorato del ciclismo da ragazzino, incredibile tornarci da ct\\"',
-            'description': 'md5:fc9c50894f70a2469bb9b54d3d0a3d3b',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
-        'md5': 'a6e39f3bdc1842bbd92abbbbef230817',
-        'info_dict': {
-            'id': '141059/142723',
-            'ext': 'mp4',
-            'title': 'Dentro la notizia - Ferrari, cosa succede a Maranello',
-            'description': 'md5:9907d65b53765681fa3a0b3122617c1f',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }]
-
-
-class GediEmbedsIE(GediBaseIE):
-    _VALID_URL = r'''(?x)https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/embed/.+?/(?P<id>[\d/]+)(?:\?|\&|$)'''
-    _TESTS = [{
-        'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
-        'md5': 'f4ac23cadfea7fef89bea536583fa7ed',
-        'info_dict': {
-            'id': '29312/29276',
-            'ext': 'mp4',
-            'title': 'Cotticelli: \\"Non so cosa mi sia successo. Sto cercando di capire se ho avuto un malore\\"',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
-        'md5': '0391c2c83c6506581003aaf0255889c0',
-        'info_dict': {
-            'id': '14772/14870',
-            'ext': 'mp4',
-            'title': 'Festival EMERGENCY, Villa: «La buona informazione aiuta la salute» (14772-14870)',
-            'description': 'md5:2bce954d278248f3c950be355b7c2226',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }]
-
-    @staticmethod
-    def _sanitize_urls(urls):
-        # add protocol if missing
-        for i, e in enumerate(urls):
-            if e.startswith('//'):
-                urls[i] = 'https:%s' % e
-        # clean iframes urls
-        for i, e in enumerate(urls):
-            urls[i] = urljoin(base_url(e), url_basename(e))
-        return urls
-
-    @staticmethod
-    def _extract_urls(webpage):
-        entries = [
-            mobj.group('url')
-            for mobj in re.finditer(r'''(?x)
-            (?:
-                data-frame-src=|
-                <iframe[^\n]+src=
-            )
-            (["'])
-                (?P<url>https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/embed/.+?)
-            \1''', webpage)]
-        return GediEmbedsIE._sanitize_urls(entries)
-
-    @staticmethod
-    def _extract_url(webpage):
-        urls = GediEmbedsIE._extract_urls(webpage)
-        return urls[0] if urls else None

yt_dlp/extractor/gedidigital.py

@@ -0,0 +1,210 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    base_url,
+    determine_ext,
+    int_or_none,
+    url_basename,
+    urljoin,
+)
+
+
+class GediDigitalIE(InfoExtractor):
+    _VALID_URL = r'''(?x)(?P<url>(?:https?:)//video\.
+        (?:
+            (?:
+                (?:espresso\.)?repubblica
+                |lastampa
+                |ilsecoloxix
+                |huffingtonpost
+            )|
+            (?:
+                iltirreno
+                |messaggeroveneto
+                |ilpiccolo
+                |gazzettadimantova
+                |mattinopadova
+                |laprovinciapavese
+                |tribunatreviso
+                |nuovavenezia
+                |gazzettadimodena
+                |lanuovaferrara
+                |corrierealpi
+                |lasentinella
+            )\.gelocal
+        )\.it(?:/[^/]+){2,4}/(?P<id>\d+))(?:$|[?&].*)'''
+    _TESTS = [{
+        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
+        'md5': '84658d7fb9e55a6e57ecc77b73137494',
+        'info_dict': {
+            'id': '121683',
+            'ext': 'mp4',
+            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
+            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
+            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
+            'duration': 125,
+        },
+    }, {
+        'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _sanitize_urls(urls):
+        # add protocol if missing
+        for i, e in enumerate(urls):
+            if e.startswith('//'):
+                urls[i] = 'https:%s' % e
+        # clean iframes urls
+        for i, e in enumerate(urls):
+            urls[i] = urljoin(base_url(e), url_basename(e))
+        return urls
+
+    @staticmethod
+    def _extract_urls(webpage):
+        entries = [
+            mobj.group('eurl')
+            for mobj in re.finditer(r'''(?x)
+            (?:
+                data-frame-src=|
+                <iframe[^\n]+src=
+            )
+            (["'])(?P<eurl>%s)\1''' % GediDigitalIE._VALID_URL, webpage)]
+        return GediDigitalIE._sanitize_urls(entries)
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = GediDigitalIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
+    @staticmethod
+    def _clean_formats(formats):
+        format_urls = set()
+        clean_formats = []
+        for f in formats:
+            if f['url'] not in format_urls:
+                if f.get('audio_ext') != 'none' and not f.get('acodec'):
+                    continue
+                format_urls.add(f['url'])
+                clean_formats.append(f)
+        formats[:] = clean_formats
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = re.match(self._VALID_URL, url).group('url')
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            ['twitter:title', 'og:title'], webpage, fatal=True)
+        player_data = re.findall(
+            r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
+            webpage)
+
+        formats = []
+        duration = thumb = None
+        for t, n, v in player_data:
+            if t == 'format':
+                if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
+                    continue
+                elif n.endswith('-vod-ak'):
+                    formats.extend(self._extract_akamai_formats(
+                        v, video_id, {'http': 'media.gedidigital.it'}))
+                else:
+                    ext = determine_ext(v)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
+                        continue
+                    f = {
+                        'format_id': n,
+                        'url': v,
+                    }
+                    if ext == 'mp3':
+                        abr = int_or_none(self._search_regex(
+                            r'-mp3-audio-(\d+)', v, 'abr', default=None))
+                        f.update({
+                            'abr': abr,
+                            'tbr': abr,
+                            'acodec': ext,
+                            'vcodec': 'none'
+                        })
+                    else:
+                        mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
+                        if mobj:
+                            f.update({
+                                'height': int(mobj.group(1)),
+                                'vbr': int_or_none(mobj.group(2)),
+                            })
+                        if not f.get('vbr'):
+                            f['vbr'] = int_or_none(self._search_regex(
+                                r'-video-rrtv-(\d+)', v, 'abr', default=None))
+                    formats.append(f)
+            elif t == 'param':
+                if n in ['image_full', 'image']:
+                    thumb = v
+                elif n == 'videoDuration':
+                    duration = int_or_none(v)
+
+        self._clean_formats(formats)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                ['twitter:description', 'og:description', 'description'], webpage),
+            'thumbnail': thumb or self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'duration': duration,
+        }

yt_dlp/extractor/generic.py

@@ -127,13 +127,14 @@ from .expressen import ExpressenIE
 from .zype import ZypeIE
 from .odnoklassniki import OdnoklassnikiIE
 from .kinja import KinjaEmbedIE
-from .gedi import GediEmbedsIE
+from .gedidigital import GediDigitalIE
 from .rcs import RCSEmbedsIE
 from .bitchute import BitChuteIE
 from .rumble import RumbleEmbedIE
 from .arcpublishing import ArcPublishingIE
 from .medialaan import MedialaanIE
 from .simplecast import SimplecastIE
+from .wimtv import WimTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -2250,6 +2251,15 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 52,
         },
+        {
+            # WimTv embed player
+            'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
+            'info_dict': {
+                'id': 'wearefmi-pt-2-2021',
+                'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
+            },
+            'playlist_count': 1,
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2649,6 +2659,15 @@ class GenericIE(InfoExtractor):
         if vid_me_embed_url is not None:
             return self.url_result(vid_me_embed_url, 'Vidme')
 
+        # Invidious Instances
+        # https://github.com/yt-dlp/yt-dlp/issues/195
+        # https://github.com/iv-org/invidious/pull/1730
+        youtube_url = self._search_regex(
+            r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
+            webpage, 'youtube link', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, YoutubeIE.ie_key())
+
         # Look for YouTube embeds
         youtube_urls = YoutubeIE._extract_urls(webpage)
         if youtube_urls:
@@ -2955,7 +2974,7 @@ class GenericIE(InfoExtractor):
             webpage)
         if not mobj:
             mobj = re.search(
-                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
                 webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
@@ -3339,17 +3358,22 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
 
-        # Look for RCS media group embeds
+        gedi_urls = GediDigitalIE._extract_urls(webpage)
-        gedi_urls = GediEmbedsIE._extract_urls(webpage)
         if gedi_urls:
             return self.playlist_from_matches(
-                gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
+                gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
 
+        # Look for RCS media group embeds
         rcs_urls = RCSEmbedsIE._extract_urls(webpage)
         if rcs_urls:
             return self.playlist_from_matches(
                 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
 
+        wimtv_urls = WimTVIE._extract_urls(webpage)
+        if wimtv_urls:
+            return self.playlist_from_matches(
+                wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
+
         bitchute_urls = BitChuteIE._extract_urls(webpage)
         if bitchute_urls:
             return self.playlist_from_matches(

yt_dlp/extractor/instagram.py

@@ -12,6 +12,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
     get_element_by_attribute,
     int_or_none,
     lowercase_escape,
@@ -32,6 +33,7 @@ class InstagramIE(InfoExtractor):
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
             'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 0,
             'timestamp': 1371748545,
             'upload_date': '20130620',
             'uploader_id': 'naomipq',
@@ -48,6 +50,7 @@ class InstagramIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Video by britneyspears',
             'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 0,
             'timestamp': 1453760977,
             'upload_date': '20160125',
             'uploader_id': 'britneyspears',
@@ -86,6 +89,24 @@ class InstagramIE(InfoExtractor):
             'title': 'Post by instagram',
             'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957',
         },
+    }, {
+        # IGTV
+        'url': 'https://www.instagram.com/tv/BkfuX9UB-eK/',
+        'info_dict': {
+            'id': 'BkfuX9UB-eK',
+            'ext': 'mp4',
+            'title': 'Fingerboarding Tricks with @cass.fb',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 53.83,
+            'timestamp': 1530032919,
+            'upload_date': '20180626',
+            'uploader_id': 'instagram',
+            'uploader': 'Instagram',
+            'like_count': int,
+            'comment_count': int,
+            'comments': list,
+            'description': 'Meet Cass Hirst (@cass.fb), a fingerboarding pro who can perform tiny ollies and kickflips while blindfolded.',
+        }
     }, {
         'url': 'https://instagram.com/p/-Cmh1cukG2/',
         'only_matching': True,
@@ -159,7 +180,9 @@ class InstagramIE(InfoExtractor):
             description = try_get(
                 media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
                 compat_str) or media.get('caption')
+            title = media.get('title')
             thumbnail = media.get('display_src') or media.get('display_url')
+            duration = float_or_none(media.get('video_duration'))
             timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
             uploader = media.get('owner', {}).get('full_name')
             uploader_id = media.get('owner', {}).get('username')
@@ -200,9 +223,10 @@ class InstagramIE(InfoExtractor):
                             continue
                         entries.append({
                             'id': node.get('shortcode') or node['id'],
-                            'title': 'Video %d' % edge_num,
+                            'title': node.get('title') or 'Video %d' % edge_num,
                             'url': node_video_url,
                             'thumbnail': node.get('display_url'),
+                            'duration': float_or_none(node.get('video_duration')),
                             'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
                             'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
                             'view_count': int_or_none(node.get('video_view_count')),
@@ -239,8 +263,9 @@ class InstagramIE(InfoExtractor):
             'id': video_id,
             'formats': formats,
             'ext': 'mp4',
-            'title': 'Video by %s' % uploader_id,
+            'title': title or 'Video by %s' % uploader_id,
             'description': description,
+            'duration': duration,
             'thumbnail': thumbnail,
             'timestamp': timestamp,
             'uploader_id': uploader_id,

yt_dlp/extractor/ivi.py

@@ -146,7 +146,7 @@ class IviIE(InfoExtractor):
                         expected=True)
                 elif not pycryptodomex_found:
                     raise ExtractorError(
-                        'pycryptodomex not found. Please install it.',
+                        'pycryptodomex not found. Please install',
                         expected=True)
                 elif message:
                     extractor_msg += ': ' + message

yt_dlp/extractor/la7.py

@@ -1,9 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
+    float_or_none,
+    parse_duration,
     smuggle_url,
+    unified_strdate,
 )
 
 
@@ -57,3 +63,141 @@ class LA7IE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'ie_key': 'Kaltura',
         }
+
+
+class LA7PodcastEpisodeIE(InfoExtractor):
+    IE_NAME = 'la7.it:pod:episode'
+    _VALID_URL = r'''(?x)(https?://)?
+        (?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)'''
+
+    _TESTS = [{
+        'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497',
+        'md5': '7737d4d79b3c1a34b3de3e16297119ed',
+        'info_dict': {
+            'id': '371497',
+            'ext': 'mp3',
+            'title': '"La carezza delle memoria" di Carlo Verdone',
+            'description': 'md5:5abf07c3c551a687db80af3f9ceb7d52',
+            'thumbnail': 'https://www.la7.it/sites/default/files/podcast/371497.jpg',
+            'upload_date': '20210323',
+        },
+    }, {
+        # embed url
+        'url': 'https://www.la7.it/embed/podcast/371497',
+        'only_matching': True,
+    }, {
+        # date already in the title
+        'url': 'https://www.la7.it/propagandalive/podcast/lintervista-di-diego-bianchi-ad-annalisa-cuzzocrea-puntata-del-1932021-20-03-2021-371130',
+        'only_matching': True,
+    }, {
+        # title same as show_title
+        'url': 'https://www.la7.it/otto-e-mezzo/podcast/otto-e-mezzo-26-03-2021-372340',
+        'only_matching': True,
+    }]
+
+    def _extract_info(self, webpage, video_id=None, ppn=None):
+        if not video_id:
+            video_id = self._search_regex(
+                r'data-nid=([\'"])(?P<vid>\d+)\1',
+                webpage, 'video_id', group='vid')
+
+        media_url = self._search_regex(
+            (r'src:\s*([\'"])(?P<url>.+?mp3.+?)\1',
+             r'data-podcast=([\'"])(?P<url>.+?mp3.+?)\1'),
+            webpage, 'media_url', group='url')
+        ext = determine_ext(media_url)
+        formats = [{
+            'url': media_url,
+            'format_id': ext,
+            'ext': ext,
+        }]
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            (r'<div class="title">(?P<title>.+?)</',
+             r'<title>(?P<title>[^<]+)</title>',
+             r'title:\s*([\'"])(?P<title>.+?)\1'),
+            webpage, 'title', group='title')
+
+        description = (
+            self._html_search_regex(
+                (r'<div class="description">(.+?)</div>',
+                 r'<div class="description-mobile">(.+?)</div>',
+                 r'<div class="box-txt">([^<]+?)</div>',
+                 r'<div class="field-content"><p>(.+?)</p></div>'),
+                webpage, 'description', default=None)
+            or self._html_search_meta('description', webpage))
+
+        thumb = self._html_search_regex(
+            (r'<div class="podcast-image"><img src="(.+?)"></div>',
+             r'<div class="container-embed"[^<]+url\((.+?)\);">',
+             r'<div class="field-content"><img src="(.+?)"'),
+            webpage, 'thumbnail', fatal=False, default=None)
+
+        duration = parse_duration(self._html_search_regex(
+            r'<span class="(?:durata|duration)">([\d:]+)</span>',
+            webpage, 'duration', fatal=False, default=None))
+
+        date = self._html_search_regex(
+            r'class="data">\s*(?:<span>)?([\d\.]+)\s*</',
+            webpage, 'date', default=None)
+
+        date_alt = self._search_regex(
+            r'(\d+[\./]\d+[\./]\d+)', title, 'date_alt', default=None)
+        ppn = ppn or self._search_regex(
+            r'ppN:\s*([\'"])(?P<ppn>.+?)\1',
+            webpage, 'ppn', group='ppn', default=None)
+        # if the date is not in the title
+        # and title is the same as the show_title
+        # add the date to the title
+        if date and not date_alt and ppn and ppn.lower() == title.lower():
+            title += ' del %s' % date
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': float_or_none(duration),
+            'formats': formats,
+            'thumbnail': thumb,
+            'upload_date': unified_strdate(date),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        return self._extract_info(webpage, video_id)
+
+
+class LA7PodcastIE(LA7PodcastEpisodeIE):
+    IE_NAME = 'la7.it:podcast'
+    _VALID_URL = r'(https?://)?(www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])'
+
+    _TESTS = [{
+        'url': 'https://www.la7.it/propagandalive/podcast',
+        'info_dict': {
+            'id': 'propagandalive',
+            'title': "Propaganda Live",
+        },
+        'playlist_count': 10,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = (
+            self._html_search_regex(
+                r'<h1.*?>(.+?)</h1>', webpage, 'title', fatal=False, default=None)
+            or self._og_search_title(webpage))
+        ppn = self._search_regex(
+            r'window\.ppN\s*=\s*([\'"])(?P<ppn>.+?)\1',
+            webpage, 'ppn', group='ppn', default=None)
+
+        entries = []
+        for episode in re.finditer(
+                r'<div class="container-podcast-property">([\s\S]+?)(?:</div>\s*){3}',
+                webpage):
+            entries.append(self._extract_info(episode.group(1), ppn=ppn))
+
+        return self.playlist_result(entries, playlist_id, title)

yt_dlp/extractor/lbry.py

@@ -6,8 +6,10 @@ import json
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_parse_qs,
     compat_str,
     compat_urllib_parse_unquote,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     determine_ext,
@@ -21,9 +23,9 @@ from ..utils import (
 
 
 class LBRYBaseIE(InfoExtractor):
-    _BASE_URL_REGEX = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/'
+    _BASE_URL_REGEX = r'(?:https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/|lbry://)'
     _CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
-    _OPT_CLAIM_ID = '[^:/?#&]+(?::%s)?' % _CLAIM_ID_REGEX
+    _OPT_CLAIM_ID = '[^:/?#&]+(?:[:#]%s)?' % _CLAIM_ID_REGEX
     _SUPPORTED_STREAM_TYPES = ['video', 'audio']
 
     def _call_api_proxy(self, method, display_id, params, resource):
@@ -41,7 +43,9 @@ class LBRYBaseIE(InfoExtractor):
             'resolve', display_id, {'urls': url}, resource)[url]
 
     def _permanent_url(self, url, claim_name, claim_id):
-        return urljoin(url, '/%s:%s' % (claim_name, claim_id))
+        return urljoin(
+            url.replace('lbry://', 'https://lbry.tv/'),
+            '/%s:%s' % (claim_name, claim_id))
 
     def _parse_stream(self, stream, url):
         stream_value = stream.get('value') or {}
@@ -60,6 +64,7 @@ class LBRYBaseIE(InfoExtractor):
             'description': stream_value.get('description'),
             'license': stream_value.get('license'),
             'timestamp': int_or_none(stream.get('timestamp')),
+            'release_timestamp': int_or_none(stream_value.get('release_time')),
             'tags': stream_value.get('tags'),
             'duration': int_or_none(media.get('duration')),
             'channel': try_get(signing_channel, lambda x: x['value']['title']),
@@ -92,6 +97,8 @@ class LBRYIE(LBRYBaseIE):
             'description': 'md5:f6cb5c704b332d37f5119313c2c98f51',
             'timestamp': 1595694354,
             'upload_date': '20200725',
+            'release_timestamp': 1595340697,
+            'release_date': '20200721',
             'width': 1280,
             'height': 720,
         }
@@ -106,6 +113,8 @@ class LBRYIE(LBRYBaseIE):
             'description': 'md5:661ac4f1db09f31728931d7b88807a61',
             'timestamp': 1591312601,
             'upload_date': '20200604',
+            'release_timestamp': 1591312421,
+            'release_date': '20200604',
             'tags': list,
             'duration': 2570,
             'channel': 'The LBRY Foundation',
@@ -137,6 +146,9 @@ class LBRYIE(LBRYBaseIE):
     }, {
         'url': 'https://lbry.tv/@lacajadepandora:a/TRUMP-EST%C3%81-BIEN-PUESTO-con-Pilar-Baselga,-Carlos-Senra,-Luis-Palacios-(720p_30fps_H264-192kbit_AAC):1',
         'only_matching': True,
+    }, {
+        'url': 'lbry://@lbry#3f/odysee#7',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -166,7 +178,7 @@ class LBRYIE(LBRYBaseIE):
 
 class LBRYChannelIE(LBRYBaseIE):
     IE_NAME = 'lbry:channel'
-    _VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?#&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
+    _VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
     _TESTS = [{
         'url': 'https://lbry.tv/@LBRYFoundation:0',
         'info_dict': {
@@ -178,20 +190,24 @@ class LBRYChannelIE(LBRYBaseIE):
     }, {
         'url': 'https://lbry.tv/@LBRYFoundation',
         'only_matching': True,
+    }, {
+        'url': 'lbry://@lbry#3f',
+        'only_matching': True,
     }]
     _PAGE_SIZE = 50
 
-    def _fetch_page(self, claim_id, url, page):
+    def _fetch_page(self, claim_id, url, params, page):
         page += 1
+        page_params = {
+            'channel_ids': [claim_id],
+            'claim_type': 'stream',
+            'no_totals': True,
+            'page': page,
+            'page_size': self._PAGE_SIZE,
+        }
+        page_params.update(params)
         result = self._call_api_proxy(
-            'claim_search', claim_id, {
+            'claim_search', claim_id, page_params, 'page %d' % page)
-                'channel_ids': [claim_id],
-                'claim_type': 'stream',
-                'no_totals': True,
-                'page': page,
-                'page_size': self._PAGE_SIZE,
-                'stream_types': self._SUPPORTED_STREAM_TYPES,
-            }, 'page %d' % page)
         for item in (result.get('items') or []):
             stream_claim_name = item.get('name')
             stream_claim_id = item.get('claim_id')
@@ -212,8 +228,31 @@ class LBRYChannelIE(LBRYBaseIE):
         result = self._resolve_url(
             'lbry://' + display_id, display_id, 'channel')
         claim_id = result['claim_id']
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        content = qs.get('content', [None])[0]
+        params = {
+            'fee_amount': qs.get('fee_amount', ['>=0'])[0],
+            'order_by': {
+                'new': ['release_time'],
+                'top': ['effective_amount'],
+                'trending': ['trending_group', 'trending_mixed'],
+            }[qs.get('order', ['new'])[0]],
+            'stream_types': [content] if content in ['audio', 'video'] else self._SUPPORTED_STREAM_TYPES,
+        }
+        duration = qs.get('duration', [None])[0]
+        if duration:
+            params['duration'] = {
+                'long': '>=1200',
+                'short': '<=240',
+            }[duration]
+        language = qs.get('language', ['all'])[0]
+        if language != 'all':
+            languages = [language]
+            if language == 'en':
+                languages.append('none')
+            params['any_languages'] = languages
         entries = OnDemandPagedList(
-            functools.partial(self._fetch_page, claim_id, url),
+            functools.partial(self._fetch_page, claim_id, url, params),
             self._PAGE_SIZE)
         result_value = result.get('value') or {}
         return self.playlist_result(

yt_dlp/extractor/linuxacademy.py

@@ -38,8 +38,8 @@ class LinuxAcademyIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'What Is Data Science',
             'description': 'md5:c574a3c20607144fb36cb65bdde76c99',
-            'timestamp': 1607387907,
+            'timestamp': int,  # The timestamp and upload date changes
-            'upload_date': '20201208',
+            'upload_date': r're:\d+',
             'duration': 304,
         },
         'params': {
@@ -59,6 +59,16 @@ class LinuxAcademyIE(InfoExtractor):
         },
         'playlist_count': 41,
         'skip': 'Requires Linux Academy account credentials',
+    }, {
+        'url': 'https://linuxacademy.com/cp/modules/view/id/39',
+        'info_dict': {
+            'id': '39',
+            'title': 'Red Hat Certified Systems Administrator - RHCSA (EX200) Exam Prep  (legacy)',
+            'description': 'md5:0f1d3369e90c3fb14a79813b863c902f',
+            'duration': 89280,
+        },
+        'playlist_count': 73,
+        'skip': 'Requires Linux Academy account credentials',
     }]
 
     _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
@@ -102,7 +112,7 @@ class LinuxAcademyIE(InfoExtractor):
             'client_id': self._CLIENT_ID,
             'redirect_uri': self._ORIGIN_URL,
             'tenant': 'lacausers',
-            'connection': 'Username-Password-Authentication',
+            'connection': 'Username-Password-ACG-Proxy',
             'username': username,
             'password': password,
             'sso': 'true',
@@ -162,7 +172,7 @@ class LinuxAcademyIE(InfoExtractor):
         if course_id:
             module = self._parse_json(
                 self._search_regex(
-                    r'window\.module\s*=\s*({.+?})\s*;', webpage, 'module'),
+                    r'window\.module\s*=\s*({(?:(?!};)[^"]|"([^"]|\\")*")+})\s*;', webpage, 'module'),
                 item_id)
             entries = []
             chapter_number = None

yt_dlp/extractor/mildom.py

@@ -5,6 +5,7 @@ from datetime import datetime
 import itertools
 import json
 import base64
+import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -68,7 +69,7 @@ class MildomBaseIE(InfoExtractor):
                 self._DISPATCHER_CONFIG = self._parse_json(base64.b64decode(tmp['data']), 'initialization')
             except ExtractorError:
                 self._DISPATCHER_CONFIG = self._download_json(
-                    'https://bookish-octo-barnacle.vercel.app/api/dispatcher_config', 'initialization',
+                    'https://bookish-octo-barnacle.vercel.app/api/mildom/dispatcher_config', 'initialization',
                     note='Downloading dispatcher_config fallback')
         return self._DISPATCHER_CONFIG
 
@@ -110,6 +111,7 @@ class MildomIE(MildomBaseIE):
         enterstudio = self._call_api(
             'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
             note='Downloading live metadata', query={'user_id': video_id})
+        result_video_id = enterstudio.get('log_id', video_id)
 
         title = try_get(
             enterstudio, (
@@ -128,7 +130,7 @@ class MildomIE(MildomBaseIE):
             ), compat_str)
 
         servers = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', video_id,
+            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
             note='Downloading live server list', query={
                 'user_id': video_id,
                 'live_server_type': 'hls',
@@ -139,7 +141,7 @@ class MildomIE(MildomBaseIE):
             'is_lhls': '0',
         })
         m3u8_url = update_url_query(servers['stream_server'] + '/%s_master.m3u8' % video_id, stream_query)
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={
+        formats = self._extract_m3u8_formats(m3u8_url, result_video_id, 'mp4', headers={
             'Referer': 'https://www.mildom.com/',
             'Origin': 'https://www.mildom.com',
         }, note='Downloading m3u8 information')
@@ -150,13 +152,13 @@ class MildomIE(MildomBaseIE):
             parsed = parsed._replace(
                 netloc='bookish-octo-barnacle.vercel.app',
                 query=compat_urllib_parse_urlencode(stream_query, True),
-                path='/api' + parsed.path)
+                path='/api/mildom' + parsed.path)
             fmt['url'] = compat_urlparse.urlunparse(parsed)
 
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
+            'id': result_video_id,
             'title': title,
             'description': description,
             'uploader': uploader,
@@ -172,9 +174,8 @@ class MildomVodIE(MildomBaseIE):
     _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+)'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        m = re.match(self._VALID_URL, url)
-        m = self._VALID_URL_RE.match(url)
+        user_id, video_id = m.group('user_id'), m.group('id')
-        user_id = m.group('user_id')
         url = 'https://www.mildom.com/playback/%s/%s' % (user_id, video_id)
 
         webpage = self._download_webpage(url, video_id)
@@ -230,7 +231,7 @@ class MildomVodIE(MildomBaseIE):
             parsed = parsed._replace(
                 netloc='bookish-octo-barnacle.vercel.app',
                 query=compat_urllib_parse_urlencode(stream_query, True),
-                path='/api/vod2/proxy')
+                path='/api/mildom/vod2/proxy')
             fmt['url'] = compat_urlparse.urlunparse(parsed)
 
         self._sort_formats(formats)

yt_dlp/extractor/mlb.py

@@ -1,15 +1,91 @@
 from __future__ import unicode_literals
 
-from .nhl import NHLBaseIE
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    try_get,
+)
 
 
-class MLBIE(NHLBaseIE):
+class MLBBaseIE(InfoExtractor):
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        video = self._download_video_data(display_id)
+        video_id = video['id']
+        title = video['title']
+        feed = self._get_feed(video)
+
+        formats = []
+        for playback in (feed.get('playbacks') or []):
+            playback_url = playback.get('url')
+            if not playback_url:
+                continue
+            name = playback.get('name')
+            ext = determine_ext(playback_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    playback_url, video_id, 'mp4',
+                    'm3u8_native', m3u8_id=name, fatal=False))
+            else:
+                f = {
+                    'format_id': name,
+                    'url': playback_url,
+                }
+                mobj = re.search(r'_(\d+)K_(\d+)X(\d+)', name)
+                if mobj:
+                    f.update({
+                        'height': int(mobj.group(3)),
+                        'tbr': int(mobj.group(1)),
+                        'width': int(mobj.group(2)),
+                    })
+                mobj = re.search(r'_(\d+)x(\d+)_(\d+)_(\d+)K\.mp4', playback_url)
+                if mobj:
+                    f.update({
+                        'fps': int(mobj.group(3)),
+                        'height': int(mobj.group(2)),
+                        'tbr': int(mobj.group(4)),
+                        'width': int(mobj.group(1)),
+                    })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for cut in (try_get(feed, lambda x: x['image']['cuts'], list) or []):
+            src = cut.get('src')
+            if not src:
+                continue
+            thumbnails.append({
+                'height': int_or_none(cut.get('height')),
+                'url': src,
+                'width': int_or_none(cut.get('width')),
+            })
+
+        language = (video.get('language') or 'EN').lower()
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': video.get('description'),
+            'duration': parse_duration(feed.get('duration')),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(video.get(self._TIMESTAMP_KEY)),
+            'subtitles': self._extract_mlb_subtitles(feed, language),
+        }
+
+
+class MLBIE(MLBBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:[\da-z_-]+\.)*(?P<site>mlb)\.com/
+                        (?:[\da-z_-]+\.)*mlb\.com/
                         (?:
                             (?:
-                                (?:[^/]+/)*c-|
+                                (?:[^/]+/)*video/[^/]+/c-|
                                 (?:
                                     shared/video/embed/(?:embed|m-internal-embed)\.html|
                                     (?:[^/]+/)+(?:play|index)\.jsp|
@@ -18,7 +94,6 @@ class MLBIE(NHLBaseIE):
                             (?P<id>\d+)
                         )
                     '''
-    _CONTENT_DOMAIN = 'content.mlb.com'
     _TESTS = [
         {
             'url': 'https://www.mlb.com/mariners/video/ackleys-spectacular-catch/c-34698933',
@@ -76,18 +151,6 @@ class MLBIE(NHLBaseIE):
                 'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
-        {
-            'url': 'https://www.mlb.com/news/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer/c-118550098',
-            'md5': 'e09e37b552351fddbf4d9e699c924d68',
-            'info_dict': {
-                'id': '75609783',
-                'ext': 'mp4',
-                'title': 'Must C: Pillar climbs for catch',
-                'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run',
-                'timestamp': 1429139220,
-                'upload_date': '20150415',
-            }
-        },
         {
             'url': 'https://www.mlb.com/video/hargrove-homers-off-caldwell/c-1352023483?tid=67793694',
             'only_matching': True,
@@ -113,8 +176,92 @@ class MLBIE(NHLBaseIE):
             'url': 'http://mlb.mlb.com/shared/video/embed/m-internal-embed.html?content_id=75609783&property=mlb&autoplay=true&hashmode=false&siteSection=mlb/multimedia/article_118550098/article_embed&club=mlb',
             'only_matching': True,
         },
-        {
-            'url': 'https://www.mlb.com/cut4/carlos-gomez-borrowed-sunglasses-from-an-as-fan/c-278912842',
-            'only_matching': True,
-        }
     ]
+    _TIMESTAMP_KEY = 'date'
+
+    @staticmethod
+    def _get_feed(video):
+        return video
+
+    @staticmethod
+    def _extract_mlb_subtitles(feed, language):
+        subtitles = {}
+        for keyword in (feed.get('keywordsAll') or []):
+            keyword_type = keyword.get('type')
+            if keyword_type and keyword_type.startswith('closed_captions_location_'):
+                cc_location = keyword.get('value')
+                if cc_location:
+                    subtitles.setdefault(language, []).append({
+                        'url': cc_location,
+                    })
+        return subtitles
+
+    def _download_video_data(self, display_id):
+        return self._download_json(
+            'http://content.mlb.com/mlb/item/id/v1/%s/details/web-v1.json' % display_id,
+            display_id)
+
+
+class MLBVideoIE(MLBBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?mlb\.com/(?:[^/]+/)*video/(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://www.mlb.com/mariners/video/ackley-s-spectacular-catch-c34698933',
+        'md5': '632358dacfceec06bad823b83d21df2d',
+        'info_dict': {
+            'id': 'c04a8863-f569-42e6-9f87-992393657614',
+            'ext': 'mp4',
+            'title': "Ackley's spectacular catch",
+            'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
+            'duration': 66,
+            'timestamp': 1405995000,
+            'upload_date': '20140722',
+            'thumbnail': r're:^https?://.+',
+        },
+    }
+    _TIMESTAMP_KEY = 'timestamp'
+
+    @classmethod
+    def suitable(cls, url):
+        return False if MLBIE.suitable(url) else super(MLBVideoIE, cls).suitable(url)
+
+    @staticmethod
+    def _get_feed(video):
+        return video['feeds'][0]
+
+    @staticmethod
+    def _extract_mlb_subtitles(feed, language):
+        subtitles = {}
+        for cc_location in (feed.get('closedCaptions') or []):
+            subtitles.setdefault(language, []).append({
+                'url': cc_location,
+            })
+
+    def _download_video_data(self, display_id):
+        # https://www.mlb.com/data-service/en/videos/[SLUG]
+        return self._download_json(
+            'https://fastball-gateway.mlb.com/graphql',
+            display_id, query={
+                'query': '''{
+  mediaPlayback(ids: "%s") {
+    description
+    feeds(types: CMS) {
+      closedCaptions
+      duration
+      image {
+        cuts {
+          width
+          height
+          src
+        }
+      }
+      playbacks {
+        name
+        url
+      }
+    }
+    id
+    timestamp
+    title
+  }
+}''' % display_id,
+            })['data']['mediaPlayback'][0]

yt_dlp/extractor/mtv.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_xpath,
-    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
@@ -15,6 +14,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
+    int_or_none,
     RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
@@ -23,7 +23,6 @@ from ..utils import (
     unescapeHTML,
     update_url_query,
     url_basename,
-    get_domain,
     xpath_text,
 )
 
@@ -45,7 +44,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         # Remove the templates, like &device={device}
         return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
 
-    def _get_feed_url(self, uri, url=None):
+    def _get_feed_url(self, uri):
         return self._FEED_URL
 
     def _get_thumbnail_url(self, uri, itemdoc):
@@ -178,6 +177,22 @@ class MTVServicesInfoExtractor(InfoExtractor):
             raise ExtractorError('Could not find video title')
         title = title.strip()
 
+        series = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:franchise')
+        season = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:seasonN')
+        episode = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:episodeN')
+        series = series.text if series is not None else None
+        season = season.text if season is not None else None
+        episode = episode.text if episode is not None else None
+        if season and episode:
+            # episode number includes season, so remove it
+            episode = re.sub(r'^%s' % season, '', episode)
+
         # This a short id that's used in the webpage urls
         mtvn_id = None
         mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
@@ -203,6 +218,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             'description': description,
             'duration': float_or_none(content_el.attrib.get('duration')),
             'timestamp': timestamp,
+            'series': series,
+            'season_number': int_or_none(season),
+            'episode_number': int_or_none(episode),
         }
 
     def _get_feed_query(self, uri):
@@ -211,9 +229,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             data['lang'] = self._LANG
         return data
 
-    def _get_videos_info(self, uri, use_hls=True, url=None):
+    def _get_videos_info(self, uri, use_hls=True):
         video_id = self._id_from_uri(uri)
-        feed_url = self._get_feed_url(uri, url)
+        feed_url = self._get_feed_url(uri)
         info_url = update_url_query(feed_url, self._get_feed_query(uri))
         return self._get_videos_info_from_url(info_url, video_id, use_hls)
 
@@ -259,41 +277,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
     def _extract_child_with_type(parent, t):
         return next(c for c in parent['children'] if c.get('type') == t)
 
-    def _extract_new_triforce_mgid(self, webpage, url='', video_id=None):
+    def _extract_mgid(self, webpage):
-        if url == '':
-            return
-        domain = get_domain(url)
-        if domain is None:
-            raise ExtractorError(
-                '[%s] could not get domain' % self.IE_NAME,
-                expected=True)
-        url = url.replace("https://", "http://")
-        enc_url = compat_urlparse.quote(url, safe='')
-        _TRIFORCE_V8_TEMPLATE = 'https://%s/feeds/triforce/manifest/v8?url=%s'
-        triforce_manifest_url = _TRIFORCE_V8_TEMPLATE % (domain, enc_url)
-
-        manifest = self._download_json(triforce_manifest_url, video_id, fatal=False)
-        if manifest:
-            if manifest.get('manifest').get('type') == 'redirect':
-                self.to_screen('Found a redirect. Downloading manifest from new location')
-                new_loc = manifest.get('manifest').get('newLocation')
-                new_loc = new_loc.replace("https://", "http://")
-                enc_new_loc = compat_urlparse.quote(new_loc, safe='')
-                triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc)
-                manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False)
-
-        item_id = try_get(manifest, lambda x: x['manifest']['reporting']['itemId'], compat_str)
-        if not item_id:
-            self.to_screen('No id found!')
-            return
-
-        # 'episode' can be anything. 'content' is used often as well
-        _MGID_TEMPLATE = 'mgid:arc:episode:%s:%s'
-        mgid = _MGID_TEMPLATE % (domain, item_id)
-
-        return mgid
-
-    def _extract_mgid(self, webpage, url, title=None, data_zone=None):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -304,21 +288,6 @@ class MTVServicesInfoExtractor(InfoExtractor):
         except RegexNotFoundError:
             mgid = None
 
-        if not title:
-            title = url_basename(url)
-
-        try:
-            window_data = self._parse_json(self._search_regex(
-                r'(?s)window.__DATA__ = (?P<json>{.+});', webpage,
-                'JSON Window Data', default=None, fatal=False, group='json'), title, fatal=False)
-            main_container = None
-            for i in range(len(window_data['children'])):
-                if window_data['children'][i]['type'] == 'MainContainer':
-                    main_container = window_data['children'][i]
-            mgid = main_container['children'][0]['props']['media']['video']['config']['uri']
-        except (KeyError, IndexError, TypeError):
-            pass
-
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
@@ -331,10 +300,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
 
         if not mgid:
-            mgid = self._extract_new_triforce_mgid(webpage, url)
+            mgid = self._extract_triforce_mgid(webpage)
-
-        if not mgid:
-            mgid = self._extract_triforce_mgid(webpage, data_zone)
 
         if not mgid:
             data = self._parse_json(self._search_regex(
@@ -348,8 +314,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
     def _real_extract(self, url):
         title = url_basename(url)
         webpage = self._download_webpage(url, title)
-        mgid = self._extract_mgid(webpage, url, title=title)
+        mgid = self._extract_mgid(webpage)
-        videos_info = self._get_videos_info(mgid, url=url)
+        videos_info = self._get_videos_info(mgid)
         return videos_info
 
 
@@ -374,7 +340,7 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage)
         if mobj:
             return mobj.group('url')
 
@@ -537,3 +503,152 @@ class MTVDEIE(MTVServicesInfoExtractor):
             'arcEp': 'mtv.de',
             'mgid': uri,
         }
+
+
+class MTVItaliaIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtv.it'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1',
+        'info_dict': {
+            'id': '0f0fc78e-45fc-4cce-8f24-971c25477530',
+            'ext': 'mp4',
+            'title': 'Cavoli amario (episodio completo)',
+            'description': 'md5:4962bccea8fed5b7c03b295ae1340660',
+            'series': 'Mario - Una Serie Di Maccio Capatonda',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    _GEO_COUNTRIES = ['IT']
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+
+    def _get_feed_query(self, uri):
+        return {
+            'arcEp': 'mtv.it',
+            'mgid': uri,
+        }
+
+
+class MTVItaliaProgrammaIE(MTVItaliaIE):
+    IE_NAME = 'mtv.it:programma'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        # program page: general
+        'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda',
+        'info_dict': {
+            'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d',
+            'title': 'Mario - Una Serie Di Maccio Capatonda',
+            'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153',
+        },
+        'playlist_count': 2,
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # program page: specific season
+        'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2',
+        'info_dict': {
+            'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1',
+            'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2',
+        },
+        'playlist_count': 34,
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # playlist page + redirect
+        'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal',
+        'info_dict': {
+            'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359',
+            'title': 'Sexy Videos',
+        },
+        'playlist_mincount': 145,
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    _GEO_COUNTRIES = ['IT']
+    _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8'
+
+    def _get_entries(self, title, url):
+        while True:
+            pg = self._search_regex(r'/(\d+)$', url, 'entries', '1')
+            entries = self._download_json(url, title, 'page %s' % pg)
+            url = try_get(
+                entries, lambda x: x['result']['nextPageURL'], compat_str)
+            entries = try_get(
+                entries, (
+                    lambda x: x['result']['data']['items'],
+                    lambda x: x['result']['data']['seasons']),
+                list)
+            for entry in entries or []:
+                if entry.get('canonicalURL'):
+                    yield self.url_result(entry['canonicalURL'])
+            if not url:
+                break
+
+    def _real_extract(self, url):
+        query = {'url': url}
+        info_url = update_url_query(self._FEED_URL, query)
+        video_id = self._match_id(url)
+        info = self._download_json(info_url, video_id).get('manifest')
+
+        redirect = try_get(
+            info, lambda x: x['newLocation']['url'], compat_str)
+        if redirect:
+            return self.url_result(redirect)
+
+        title = info.get('title')
+        video_id = try_get(
+            info, lambda x: x['reporting']['itemId'], compat_str)
+        parent_id = try_get(
+            info, lambda x: x['reporting']['parentId'], compat_str)
+
+        playlist_url = current_url = None
+        for z in (info.get('zones') or {}).values():
+            if z.get('moduleName') in ('INTL_M304', 'INTL_M209'):
+                info_url = z.get('feed')
+            if z.get('moduleName') in ('INTL_M308', 'INTL_M317'):
+                playlist_url = playlist_url or z.get('feed')
+            if z.get('moduleName') in ('INTL_M300',):
+                current_url = current_url or z.get('feed')
+
+        if not info_url:
+            raise ExtractorError('No info found')
+
+        if video_id == parent_id:
+            video_id = self._search_regex(
+                r'([^\/]+)/[^\/]+$', info_url, 'video_id')
+
+        info = self._download_json(info_url, video_id, 'Show infos')
+        info = try_get(info, lambda x: x['result']['data'], dict)
+        title = title or try_get(
+            info, (
+                lambda x: x['title'],
+                lambda x: x['headline']),
+            compat_str)
+        description = try_get(info, lambda x: x['content'], compat_str)
+
+        if current_url:
+            season = try_get(
+                self._download_json(playlist_url, video_id, 'Seasons info'),
+                lambda x: x['result']['data'], dict)
+            current = try_get(
+                season, lambda x: x['currentSeason'], compat_str)
+            seasons = try_get(
+                season, lambda x: x['seasons'], list) or []
+
+            if current in [s.get('eTitle') for s in seasons]:
+                playlist_url = current_url
+
+        title = re.sub(
+            r'[-|]\s*(?:mtv\s*italia|programma|playlist)',
+            '', title, flags=re.IGNORECASE).strip()
+
+        return self.playlist_result(
+            self._get_entries(title, playlist_url),
+            video_id, title, description)

yt_dlp/extractor/mxplayer.py

@@ -0,0 +1,127 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    js_to_json,
+    qualities,
+    try_get,
+    url_or_none,
+    urljoin,
+)
+
+
+class MxplayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mxplayer\.in/(?:show|movie)/(?:(?P<display_id>[-/a-z0-9]+)-)?(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.mxplayer.in/movie/watch-knock-knock-hindi-dubbed-movie-online-b9fa28df3bfb8758874735bbd7d2655a?watch=true',
+        'info_dict': {
+            'id': 'b9fa28df3bfb8758874735bbd7d2655a',
+            'ext': 'mp4',
+            'title': 'Knock Knock (Hindi Dubbed)',
+            'description': 'md5:b195ba93ff1987309cfa58e2839d2a5b'
+        },
+        'params': {
+            'skip_download': True,
+            'format': 'bestvideo'
+        }
+    }, {
+        'url': 'https://www.mxplayer.in/show/watch-shaitaan/season-1/the-infamous-taxi-gang-of-meerut-online-45055d5bcff169ad48f2ad7552a83d6c',
+        'info_dict': {
+            'id': '45055d5bcff169ad48f2ad7552a83d6c',
+            'ext': 'm3u8',
+            'title': 'The infamous taxi gang of Meerut',
+            'description': 'md5:033a0a7e3fd147be4fb7e07a01a3dc28',
+            'season': 'Season 1',
+            'series': 'Shaitaan'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.mxplayer.in/show/watch-aashram/chapter-1/duh-swapna-online-d445579792b0135598ba1bc9088a84cb',
+        'info_dict': {
+            'id': 'd445579792b0135598ba1bc9088a84cb',
+            'ext': 'mp4',
+            'title': 'Duh Swapna',
+            'description': 'md5:35ff39c4bdac403c53be1e16a04192d8',
+            'season': 'Chapter 1',
+            'series': 'Aashram'
+        },
+        'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
+        'params': {
+            'skip_download': True,
+            'format': 'bestvideo'
+        }
+    }]
+
+    def _get_stream_urls(self, video_dict):
+        stream_provider_dict = try_get(
+            video_dict,
+            lambda x: x['stream'][x['stream']['provider']])
+        if not stream_provider_dict:
+            raise ExtractorError('No stream provider found', expected=True)
+
+        for stream_name, stream in stream_provider_dict.items():
+            if stream_name in ('hls', 'dash', 'hlsUrl', 'dashUrl'):
+                stream_type = stream_name.replace('Url', '')
+                if isinstance(stream, dict):
+                    for quality, stream_url in stream.items():
+                        if stream_url:
+                            yield stream_type, quality, stream_url
+                else:
+                    yield stream_type, 'base', stream
+
+    def _real_extract(self, url):
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, video_id)
+
+        source = self._parse_json(
+            js_to_json(self._html_search_regex(
+                r'(?s)<script>window\.state\s*[:=]\s(\{.+\})\n(\w+).*(</script>).*',
+                webpage, 'WindowState')),
+            video_id)
+        if not source:
+            raise ExtractorError('Cannot find source', expected=True)
+
+        config_dict = source['config']
+        video_dict = source['entities'][video_id]
+
+        thumbnails = []
+        for i in video_dict.get('imageInfo') or []:
+            thumbnails.append({
+                'url': urljoin(config_dict['imageBaseUrl'], i['url']),
+                'width': i['width'],
+                'height': i['height'],
+            })
+
+        formats = []
+        get_quality = qualities(['main', 'base', 'high'])
+        for stream_type, quality, stream_url in self._get_stream_urls(video_dict):
+            format_url = url_or_none(urljoin(config_dict['videoCdnBaseUrl'], stream_url))
+            if not format_url:
+                continue
+            if stream_type == 'dash':
+                dash_formats = self._extract_mpd_formats(
+                    format_url, video_id, mpd_id='dash-%s' % quality, headers={'Referer': url})
+                for frmt in dash_formats:
+                    frmt['quality'] = get_quality(quality)
+                formats.extend(dash_formats)
+            elif stream_type == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, fatal=False,
+                    m3u8_id='hls-%s' % quality, quality=get_quality(quality)))
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'display_id': display_id.replace('/', '-'),
+            'title': video_dict['title'] or self._og_search_title(webpage),
+            'formats': formats,
+            'description': video_dict.get('description'),
+            'season': try_get(video_dict, lambda x: x['container']['title']),
+            'series': try_get(video_dict, lambda x: x['container']['container']['title']),
+            'thumbnails': thumbnails,
+        }

yt_dlp/extractor/nbc.py

@@ -10,6 +10,7 @@ from .adobepass import AdobePassIE
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     int_or_none,
+    parse_age_limit,
     parse_duration,
     smuggle_url,
     try_get,
@@ -18,7 +19,7 @@ from ..utils import (
 )
 
 
-class NBCIE(AdobePassIE):
+class NBCIE(ThePlatformIE):
     _VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
 
     _TESTS = [
@@ -132,7 +133,9 @@ class NBCIE(AdobePassIE):
             'manifest': 'm3u',
         }
         video_id = video_data['mpxGuid']
-        title = video_data['secondaryTitle']
+        tp_path = 'NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id)
+        tpm = self._download_theplatform_metadata(tp_path, video_id)
+        title = tpm.get('title') or video_data.get('secondaryTitle')
         if video_data.get('locked'):
             resource = self._get_mvpd_resource(
                 video_data.get('resourceId') or 'nbcentertainment',
@@ -142,18 +145,40 @@ class NBCIE(AdobePassIE):
         theplatform_url = smuggle_url(update_url_query(
             'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
             query), {'force_smil_url': True})
+
+        # Empty string or 0 can be valid values for these. So the check must be `is None`
+        description = video_data.get('description')
+        if description is None:
+            description = tpm.get('description')
+        episode_number = int_or_none(video_data.get('episodeNumber'))
+        if episode_number is None:
+            episode_number = int_or_none(tpm.get('nbcu$airOrder'))
+        rating = video_data.get('rating')
+        if rating is None:
+            try_get(tpm, lambda x: x['ratings'][0]['rating'])
+        season_number = int_or_none(video_data.get('seasonNumber'))
+        if season_number is None:
+            season_number = int_or_none(tpm.get('nbcu$seasonNumber'))
+        series = video_data.get('seriesShortTitle')
+        if series is None:
+            series = tpm.get('nbcu$seriesShortTitle')
+        tags = video_data.get('keywords')
+        if tags is None or len(tags) == 0:
+            tags = tpm.get('keywords')
+
         return {
             '_type': 'url_transparent',
+            'age_limit': parse_age_limit(rating),
+            'description': description,
+            'episode': title,
+            'episode_number': episode_number,
             'id': video_id,
+            'ie_key': 'ThePlatform',
+            'season_number': season_number,
+            'series': series,
+            'tags': tags,
             'title': title,
             'url': theplatform_url,
-            'description': video_data.get('description'),
-            'tags': video_data.get('keywords'),
-            'season_number': int_or_none(video_data.get('seasonNumber')),
-            'episode_number': int_or_none(video_data.get('episodeNumber')),
-            'episode': title,
-            'series': video_data.get('seriesShortTitle'),
-            'ie_key': 'ThePlatform',
         }
 
 

yt_dlp/extractor/nick.py

@@ -8,59 +8,66 @@ from ..utils import update_url_query
 
 
 class NickIE(MTVServicesInfoExtractor):
-    # None of videos on the website are still alive?
     IE_NAME = 'nick.com'
-    _VALID_URL = r'https?://(?P<domain>(?:(?:www|beta)\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?P<domain>(?:www\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?P<type>videos/clip|[^/]+/videos|episodes/[^/]+)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
     _GEO_COUNTRIES = ['US']
     _TESTS = [{
-        'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
+        'url': 'https://www.nick.com/episodes/sq47rw/spongebob-squarepants-a-place-for-pets-lockdown-for-love-season-13-ep-1',
+        'info_dict': {
+            'description': 'md5:0650a9eb88955609d5c1d1c79292e234',
+            'title': 'A Place for Pets/Lockdown for Love',
+        },
         'playlist': [
             {
-                'md5': '6e5adc1e28253bbb1b28ab05403dd4d4',
+                'md5': 'cb8a2afeafb7ae154aca5a64815ec9d6',
                 'info_dict': {
-                    'id': 'be6a17b0-412d-11e5-8ff7-0026b9414f30',
+                    'id': '85ee8177-d6ce-48f8-9eee-a65364f8a6df',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S1',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S1',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
 
                 }
             },
             {
-                'md5': 'd7be441fc53a1d4882fa9508a1e5b3ce',
+                'md5': '839a04f49900a1fcbf517020d94e0737',
                 'info_dict': {
-                    'id': 'be6b8f96-412d-11e5-8ff7-0026b9414f30',
+                    'id': '2e2a9960-8fd4-411d-868b-28eb1beb7fae',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S2',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S2',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
 
                 }
             },
             {
-                'md5': 'efffe1728a234b2b0d2f2b343dd1946f',
+                'md5': 'f1145699f199770e2919ee8646955d46',
                 'info_dict': {
-                    'id': 'be6cf7e6-412d-11e5-8ff7-0026b9414f30',
+                    'id': 'dc91c304-6876-40f7-84a6-7aece7baa9d0',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S3',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S3',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
+
                 }
             },
             {
-                'md5': '1ec6690733ab9f41709e274a1d5c7556',
+                'md5': 'd463116875aee2585ee58de3b12caebd',
                 'info_dict': {
-                    'id': 'be6e3354-412d-11e5-8ff7-0026b9414f30',
+                    'id': '5d929486-cf4c-42a1-889a-6e0d183a101a',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S4',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S4',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
+
                 }
             },
         ],
     }, {
-        'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
+        'url': 'http://www.nickjr.com/blues-clues-and-you/videos/blues-clues-and-you-original-209-imagination-station/',
-        'only_matching': True,
+        'info_dict': {
-    }, {
+            'id': '31631529-2fc5-430b-b2ef-6a74b4609abd',
-        'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/',
+            'ext': 'mp4',
-        'only_matching': True,
+            'description': 'md5:9d65a66df38e02254852794b2809d1cf',
+            'title': 'Blue\'s Imagination Station',
+        },
     }]
 
     def _get_feed_query(self, uri):
@@ -69,8 +76,14 @@ class NickIE(MTVServicesInfoExtractor):
             'mgid': uri,
         }
 
+    def _extract_mgid(self, webpage):
+        mgid = self._search_regex(r'"media":{"video":{"config":{"uri":"(mgid:.*?)"', webpage, 'mgid', default=None)
+        return mgid
+
     def _real_extract(self, url):
-        domain, display_id = re.match(self._VALID_URL, url).groups()
+        domain, video_type, display_id = re.match(self._VALID_URL, url).groups()
+        if video_type.startswith("episodes"):
+            return super()._real_extract(url)
         video_data = self._download_json(
             'http://%s/data/video.endLevel.json' % domain,
             display_id, query={

yt_dlp/extractor/niconico.py

@@ -8,6 +8,7 @@ import datetime
 from .common import InfoExtractor
 from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..compat import (
+    compat_str,
     compat_parse_qs,
     compat_urllib_parse_urlparse,
 )
@@ -20,6 +21,7 @@ from ..utils import (
     parse_duration,
     parse_iso8601,
     PostProcessingError,
+    str_or_none,
     remove_start,
     try_get,
     unified_timestamp,
@@ -34,7 +36,7 @@ class NiconicoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
-        'md5': 'd1a75c0823e2f629128c43e1212760f9',
+        'md5': 'a5bad06f1347452102953f323c69da34s',
         'info_dict': {
             'id': 'sm22312215',
             'ext': 'mp4',
@@ -203,7 +205,7 @@ class NiconicoIE(InfoExtractor):
             'data-api-data="([^"]+)"', webpage,
             'API data', default='{}'), video_id)
 
-        session_api_data = try_get(api_data, lambda x: x['video']['dmcInfo']['session_api'])
+        session_api_data = try_get(api_data, lambda x: x['media']['delivery']['movie']['session'])
         session_api_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
 
         # ping
@@ -220,7 +222,7 @@ class NiconicoIE(InfoExtractor):
         yesno = lambda x: 'yes' if x else 'no'
 
         # m3u8 (encryption)
-        if 'encryption' in try_get(api_data, lambda x: x['video']['dmcInfo']) or {}:
+        if 'encryption' in (try_get(api_data, lambda x: x['media']['delivery']['movie']) or {}):
             protocol = 'm3u8'
             session_api_http_parameters = {
                 'parameters': {
@@ -244,8 +246,8 @@ class NiconicoIE(InfoExtractor):
             session_api_http_parameters = {
                 'parameters': {
                     'http_output_download_parameters': {
-                        'use_ssl': yesno(session_api_endpoint['is_ssl']),
+                        'use_ssl': yesno(session_api_endpoint['isSsl']),
-                        'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
+                        'use_well_known_port': yesno(session_api_endpoint['isWellKnownPort']),
                     }
                 }
             }
@@ -258,15 +260,15 @@ class NiconicoIE(InfoExtractor):
             data=json.dumps({
                 'session': {
                     'client_info': {
-                        'player_id': session_api_data.get('player_id'),
+                        'player_id': session_api_data.get('playerId'),
                     },
                     'content_auth': {
-                        'auth_type': try_get(session_api_data, lambda x: x['auth_types'][session_api_data['protocols'][0]]),
+                        'auth_type': try_get(session_api_data, lambda x: x['authTypes'][session_api_data['protocols'][0]]),
-                        'content_key_timeout': session_api_data.get('content_key_timeout'),
+                        'content_key_timeout': session_api_data.get('contentKeyTimeout'),
                         'service_id': 'nicovideo',
-                        'service_user_id': session_api_data.get('service_user_id')
+                        'service_user_id': session_api_data.get('serviceUserId')
                     },
-                    'content_id': session_api_data.get('content_id'),
+                    'content_id': session_api_data.get('contentId'),
                     'content_src_id_sets': [{
                         'content_src_ids': [{
                             'src_id_to_mux': {
@@ -279,7 +281,7 @@ class NiconicoIE(InfoExtractor):
                     'content_uri': '',
                     'keep_method': {
                         'heartbeat': {
-                            'lifetime': session_api_data.get('heartbeat_lifetime')
+                            'lifetime': session_api_data.get('heartbeatLifetime')
                         }
                     },
                     'priority': session_api_data.get('priority'),
@@ -289,7 +291,7 @@ class NiconicoIE(InfoExtractor):
                             'http_parameters': session_api_http_parameters
                         }
                     },
-                    'recipe_id': session_api_data.get('recipe_id'),
+                    'recipe_id': session_api_data.get('recipeId'),
                     'session_operation_auth': {
                         'session_operation_auth_by_signature': {
                             'signature': session_api_data.get('signature'),
@@ -308,7 +310,7 @@ class NiconicoIE(InfoExtractor):
             'url': session_api_endpoint['url'] + '/' + session_response['data']['session']['id'] + '?_format=json&_method=PUT',
             'data': json.dumps(session_response['data']),
             # interval, convert milliseconds to seconds, then halve to make a buffer.
-            'interval': float_or_none(session_api_data.get('heartbeat_lifetime'), scale=2000),
+            'interval': float_or_none(session_api_data.get('heartbeatLifetime'), scale=2000),
         }
 
         return info_dict, heartbeat_info_dict
@@ -327,15 +329,17 @@ class NiconicoIE(InfoExtractor):
         format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
         vdict = parse_format_id(video_quality['id'])
         adict = parse_format_id(audio_quality['id'])
-        resolution = video_quality.get('resolution', {'height': vdict.get('res')})
+        resolution = try_get(video_quality, lambda x: x['metadata']['resolution'], dict) or {'height': vdict.get('res')}
+        vbr = try_get(video_quality, lambda x: x['metadata']['bitrate'], float)
 
         return {
             'url': '%s:%s/%s/%s' % (protocol, video_id, video_quality['id'], audio_quality['id']),
             'format_id': format_id,
+            'format_note': 'DMC %s' % try_get(video_quality, lambda x: x['metadata']['label'], compat_str),
             'ext': 'mp4',  # Session API are used in HTML5, which always serves mp4
             'vcodec': vdict.get('codec'),
             'acodec': adict.get('codec'),
-            'vbr': float_or_none(video_quality.get('bitrate'), 1000) or float_or_none(vdict.get('br')),
+            'vbr': float_or_none(vbr, 1000) or float_or_none(vdict.get('br')),
             'abr': float_or_none(audio_quality.get('bitrate'), 1000) or float_or_none(adict.get('br')),
             'height': int_or_none(resolution.get('height', vdict.get('res'))),
             'width': int_or_none(resolution.get('width')),
@@ -394,92 +398,93 @@ class NiconicoIE(InfoExtractor):
         formats = []
 
         # Get HTML5 videos info
-        try:
+        quality_info = try_get(api_data, lambda x: x['media']['delivery']['movie'])
-            dmc_info = api_data['video']['dmcInfo']
+        if not quality_info:
-        except KeyError:
+            raise ExtractorError('The video can\'t downloaded.', expected=True)
-            raise ExtractorError('The video can\'t downloaded.',
-                                 expected=True)
 
-        quality_info = dmc_info.get('quality')
         for audio_quality in quality_info.get('audios') or {}:
             for video_quality in quality_info.get('videos') or {}:
-                if not audio_quality.get('available') or not video_quality.get('available'):
+                if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'):
                     continue
                 formats.append(self._extract_format_for_quality(
                     api_data, video_id, audio_quality, video_quality))
 
         # Get flv/swf info
+        timestamp = None
         video_real_url = try_get(api_data, lambda x: x['video']['smileInfo']['url'])
-        is_economy = video_real_url.endswith('low')
+        if not video_real_url:
+            self.report_warning('Unable to obtain smile video information')
+        else:
+            is_economy = video_real_url.endswith('low')
 
-        if is_economy:
+            if is_economy:
-            self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
+                self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
 
-        # Invoking ffprobe to determine resolution
+            # Invoking ffprobe to determine resolution
-        pp = FFmpegPostProcessor(self._downloader)
+            pp = FFmpegPostProcessor(self._downloader)
-        cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
+            cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
 
-        self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
+            self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
 
-        try:
+            try:
-            metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
+                metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
-        except PostProcessingError as err:
+            except PostProcessingError as err:
-            raise ExtractorError(err.msg, expected=True)
+                raise ExtractorError(err.msg, expected=True)
 
-        v_stream = a_stream = {}
+            v_stream = a_stream = {}
 
-        # Some complex swf files doesn't have video stream (e.g. nm4809023)
+            # Some complex swf files doesn't have video stream (e.g. nm4809023)
-        for stream in metadata['streams']:
+            for stream in metadata['streams']:
-            if stream['codec_type'] == 'video':
+                if stream['codec_type'] == 'video':
-                v_stream = stream
+                    v_stream = stream
-            elif stream['codec_type'] == 'audio':
+                elif stream['codec_type'] == 'audio':
-                a_stream = stream
+                    a_stream = stream
 
-        # Community restricted videos seem to have issues with the thumb API not returning anything at all
+            # Community restricted videos seem to have issues with the thumb API not returning anything at all
-        filesize = int(
+            filesize = int(
-            (get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
+                (get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
-            or metadata['format']['size']
+                or metadata['format']['size']
-        )
+            )
-        extension = (
+            extension = (
-            get_video_info_xml('movie_type')
+                get_video_info_xml('movie_type')
-            or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
+                or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
-        )
+            )
 
-        # 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
+            # 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
-        timestamp = (
+            timestamp = (
-            parse_iso8601(get_video_info_web('first_retrieve'))
+                parse_iso8601(get_video_info_web('first_retrieve'))
-            or unified_timestamp(get_video_info_web('postedDateTime'))
+                or unified_timestamp(get_video_info_web('postedDateTime'))
-        )
+            )
-        metadata_timestamp = (
+            metadata_timestamp = (
-            parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
+                parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
-            or timestamp if extension != 'mp4' else 0
+                or timestamp if extension != 'mp4' else 0
-        )
+            )
 
-        # According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
+            # According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
-        smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
+            smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
 
-        is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
+            is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
 
-        # If movie file size is unstable, old server movie is not source movie.
+            # If movie file size is unstable, old server movie is not source movie.
-        if filesize > 1:
+            if filesize > 1:
-            formats.append({
+                formats.append({
-                'url': video_real_url,
+                    'url': video_real_url,
-                'format_id': 'smile' if not is_economy else 'smile_low',
+                    'format_id': 'smile' if not is_economy else 'smile_low',
-                'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
+                    'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
-                'ext': extension,
+                    'ext': extension,
-                'container': extension,
+                    'container': extension,
-                'vcodec': v_stream.get('codec_name'),
+                    'vcodec': v_stream.get('codec_name'),
-                'acodec': a_stream.get('codec_name'),
+                    'acodec': a_stream.get('codec_name'),
-                # Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
+                    # Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
-                'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
+                    'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
-                'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
+                    'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
-                'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
+                    'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
-                'height': int_or_none(v_stream.get('height')),
+                    'height': int_or_none(v_stream.get('height')),
-                'width': int_or_none(v_stream.get('width')),
+                    'width': int_or_none(v_stream.get('width')),
-                'source_preference': 5 if not is_economy else -2,
+                    'source_preference': 5 if not is_economy else -2,
-                'quality': 5 if is_source and not is_economy else None,
+                    'quality': 5 if is_source and not is_economy else None,
-                'filesize': filesize
+                    'filesize': filesize
-            })
+                })
 
         if len(formats) == 0:
             raise ExtractorError('Unable to find video info.')
@@ -487,13 +492,12 @@ class NiconicoIE(InfoExtractor):
         self._sort_formats(formats)
 
         # Start extracting information
-        title = get_video_info_web('originalTitle')
+        title = (
-        if not title:
+            get_video_info_web(['originalTitle', 'title'])
-            title = self._og_search_title(webpage, default=None)
+            or self._og_search_title(webpage, default=None)
-        if not title:
+            or self._html_search_regex(
-            title = self._html_search_regex(
                 r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
-                webpage, 'video title')
+                webpage, 'video title'))
 
         watch_api_data_string = self._html_search_regex(
             r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
@@ -517,6 +521,7 @@ class NiconicoIE(InfoExtractor):
             timestamp = parse_iso8601(
                 video_detail['postedAt'].replace('/', '-'),
                 delimiter=' ', timezone=datetime.timedelta(hours=9))
+        timestamp = timestamp or try_get(api_data, lambda x: parse_iso8601(x['video']['registeredAt']))
 
         view_count = int_or_none(get_video_info_web(['view_counter', 'viewCount']))
         if not view_count:
@@ -525,11 +530,16 @@ class NiconicoIE(InfoExtractor):
                 webpage, 'view count', default=None)
             if match:
                 view_count = int_or_none(match.replace(',', ''))
-        view_count = view_count or video_detail.get('viewCount')
+        view_count = (
+            view_count
+            or video_detail.get('viewCount')
+            or try_get(api_data, lambda x: x['video']['count']['view']))
+
+        comment_count = (
+            int_or_none(get_video_info_web('comment_num'))
+            or video_detail.get('commentCount')
+            or try_get(api_data, lambda x: x['video']['count']['comment']))
 
-        comment_count = (int_or_none(get_video_info_web('comment_num'))
-                         or video_detail.get('commentCount')
-                         or try_get(api_data, lambda x: x['thread']['commentCount']))
         if not comment_count:
             match = self._html_search_regex(
                 r'>Comments: <strong[^>]*>([^<]+)</strong>',
@@ -559,7 +569,7 @@ class NiconicoIE(InfoExtractor):
         # Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
         # in the JSON, which will cause None to be returned instead of {}.
         owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
-        uploader_id = (
+        uploader_id = str_or_none(
             get_video_info_web(['ch_id', 'user_id'])
             or owner.get('id')
             or channel_id
@@ -589,7 +599,7 @@ class NiconicoIE(InfoExtractor):
 
 
 class NiconicoPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/)?mylist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/|my/)?mylist/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/mylist/27411728',
@@ -647,3 +657,40 @@ class NiconicoPlaylistIE(InfoExtractor):
             'uploader_id': uploader_id,
             'entries': OnDemandPagedList(pagefunc, 25),
         }
+
+
+class NiconicoUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
+    _TEST = {
+        'url': 'https://www.nicovideo.jp/user/419948',
+        'info_dict': {
+            'id': '419948',
+        },
+        'playlist_mincount': 101,
+    }
+    _API_URL = "https://nvapi.nicovideo.jp/v1/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s"
+    _api_headers = {
+        'X-Frontend-ID': '6',
+        'X-Frontend-Version': '0',
+        'X-Niconico-Language': 'en-us'
+    }
+    _PAGE_SIZE = 100
+
+    def _entries(self, list_id, ):
+        total_count = 1
+        count = page_num = 0
+        while count < total_count:
+            json_parsed = self._download_json(
+                self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
+                headers=self._api_headers,
+                note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
+            if not page_num:
+                total_count = int_or_none(json_parsed['data'].get('totalCount'))
+            for entry in json_parsed["data"]["items"]:
+                count += 1
+                yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
+            page_num += 1
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())

yt_dlp/extractor/ninecninemedia.py

@@ -23,11 +23,9 @@ class NineCNineMediaIE(InfoExtractor):
         destination_code, content_id = re.match(self._VALID_URL, url).groups()
         api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
         content = self._download_json(api_base_url, content_id, query={
-            '$include': '[Media,Season,ContentPackages]',
+            '$include': '[Media.Name,Season,ContentPackages.Duration,ContentPackages.Id]',
         })
         title = content['Name']
-        if len(content['ContentPackages']) > 1:
-            raise ExtractorError('multiple content packages')
         content_package = content['ContentPackages'][0]
         package_id = content_package['Id']
         content_package_url = api_base_url + 'contentpackages/%s/' % package_id

yt_dlp/extractor/palcomp3.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class PalcoMP3BaseIE(InfoExtractor):
+    _GQL_QUERY_TMPL = '''{
+  artist(slug: "%s") {
+    %s
+  }
+}'''
+    _ARTIST_FIELDS_TMPL = '''music(slug: "%%s") {
+      %s
+    }'''
+    _MUSIC_FIELDS = '''duration
+      hls
+      mp3File
+      musicID
+      plays
+      title'''
+
+    def _call_api(self, artist_slug, artist_fields):
+        return self._download_json(
+            'https://www.palcomp3.com.br/graphql/', artist_slug, query={
+                'query': self._GQL_QUERY_TMPL % (artist_slug, artist_fields),
+            })['data']
+
+    def _parse_music(self, music):
+        music_id = compat_str(music['musicID'])
+        title = music['title']
+
+        formats = []
+        hls_url = music.get('hls')
+        if hls_url:
+            formats.append({
+                'url': hls_url,
+                'protocol': 'm3u8_native',
+                'ext': 'mp4',
+            })
+        mp3_file = music.get('mp3File')
+        if mp3_file:
+            formats.append({
+                'url': mp3_file,
+            })
+
+        return {
+            'id': music_id,
+            'title': title,
+            'formats': formats,
+            'duration': int_or_none(music.get('duration')),
+            'view_count': int_or_none(music.get('plays')),
+        }
+
+    def _real_initialize(self):
+        self._ARTIST_FIELDS_TMPL = self._ARTIST_FIELDS_TMPL % self._MUSIC_FIELDS
+
+    def _real_extract(self, url):
+        artist_slug, music_slug = re.match(self._VALID_URL, url).groups()
+        artist_fields = self._ARTIST_FIELDS_TMPL % music_slug
+        music = self._call_api(artist_slug, artist_fields)['artist']['music']
+        return self._parse_music(music)
+
+
+class PalcoMP3IE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:song'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/',
+        'md5': '99fd6405b2d8fd589670f6db1ba3b358',
+        'info_dict': {
+            'id': '3162927',
+            'ext': 'mp3',
+            'title': 'Nossas Composições - CUIDA BEM DELA',
+            'duration': 210,
+            'view_count': int,
+        }
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PalcoMP3VideoIE.suitable(url) else super(PalcoMP3IE, cls).suitable(url)
+
+
+class PalcoMP3ArtistIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:artist'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com.br/condedoforro/',
+        'info_dict': {
+            'id': '358396',
+            'title': 'Conde do Forró',
+        },
+        'playlist_mincount': 188,
+    }]
+    _ARTIST_FIELDS_TMPL = '''artistID
+    musics {
+      nodes {
+        %s
+      }
+    }
+    name'''
+
+    @ classmethod
+    def suitable(cls, url):
+        return False if re.match(PalcoMP3IE._VALID_URL, url) else super(PalcoMP3ArtistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        artist_slug = self._match_id(url)
+        artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
+
+        def entries():
+            for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
+                yield self._parse_music(music)
+
+        return self.playlist_result(
+            entries(), str_or_none(artist.get('artistID')), artist.get('name'))
+
+
+class PalcoMP3VideoIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:video'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)/?#clipe'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/maiara-e-maraisa-voce-faz-falta-aqui-ao-vivo-em-vicosa-mg/#clipe',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': '_pD1nR2qqPg',
+            'ext': 'mp4',
+            'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
+            'description': 'md5:7043342c09a224598e93546e98e49282',
+            'upload_date': '20161107',
+            'uploader_id': 'maiaramaraisaoficial',
+            'uploader': 'Maiara e Maraisa',
+        }
+    }]
+    _MUSIC_FIELDS = 'youtubeID'
+
+    def _parse_music(self, music):
+        youtube_id = music['youtubeID']
+        return self.url_result(youtube_id, 'Youtube', youtube_id)

yt_dlp/extractor/peertube.py

@@ -599,11 +599,13 @@ class PeerTubeIE(InfoExtractor):
         else:
             age_limit = None
 
+        webpage_url = 'https://%s/videos/watch/%s' % (host, video_id)
+
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': urljoin(url, video.get('thumbnailPath')),
+            'thumbnail': urljoin(webpage_url, video.get('thumbnailPath')),
             'timestamp': unified_timestamp(video.get('publishedAt')),
             'uploader': account_data('displayName', compat_str),
             'uploader_id': str_or_none(account_data('id', int)),
@@ -621,5 +623,6 @@ class PeerTubeIE(InfoExtractor):
             'tags': try_get(video, lambda x: x['tags'], list),
             'categories': categories,
             'formats': formats,
-            'subtitles': subtitles
+            'subtitles': subtitles,
+            'webpage_url': webpage_url,
         }

yt_dlp/extractor/phoenix.py

@@ -1,52 +1,128 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
+import re
-from ..utils import ExtractorError
+
+from .youtube import YoutubeIE
+from .zdf import ZDFBaseIE
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    merge_dicts,
+    unified_timestamp,
+    xpath_text,
+)
 
 
-class PhoenixIE(InfoExtractor):
+class PhoenixIE(ZDFBaseIE):
     IE_NAME = 'phoenix.de'
-    _VALID_URL = r'''https?://(?:www\.)?phoenix.de/\D+(?P<id>\d+)\.html'''
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
-    _TESTS = [
+    _TESTS = [{
-        {
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
-            'url': 'https://www.phoenix.de/sendungen/dokumentationen/unsere-welt-in-zukunft---stadt-a-1283620.html',
+        'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
-            'md5': '5e765e838aa3531c745a4f5b249ee3e3',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
-            'info_dict': {
+        'info_dict': {
-                'id': '0OB4HFc43Ns',
+            'id': '210222_phx_nachgehakt_corona_protest',
-                'ext': 'mp4',
+            'ext': 'mp4',
-                'title': 'Unsere Welt in Zukunft - Stadt',
+            'title': 'Wohin führt der Protest in der Pandemie?',
-                'description': 'md5:9bfb6fd498814538f953b2dcad7ce044',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
-                'upload_date': '20190912',
+            'duration': 1691,
-                'uploader': 'phoenix',
+            'timestamp': 1613906100,
-                'uploader_id': 'phoenix',
+            'upload_date': '20210221',
-            }
+            'uploader': 'Phoenix',
+            'channel': 'corona nachgehakt',
         },
-        {
+    }, {
-            'url': 'https://www.phoenix.de/drohnenangriffe-in-saudi-arabien-a-1286995.html?ref=aktuelles',
+        # Youtube embed
-            'only_matching': True,
+        'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
+        'info_dict': {
+            'id': 'hMQtqFYjomk',
+            'ext': 'mp4',
+            'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
+            'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
+            'duration': 3509,
+            'upload_date': '20201219',
+            'uploader': 'phoenix',
+            'uploader_id': 'phoenix',
         },
-        # an older page: https://www.phoenix.de/sendungen/gespraeche/phoenix-persoenlich/im-dialog-a-177727.html
+        'params': {
-        # seems to not have an embedded video, even though it's uploaded on youtube: https://www.youtube.com/watch?v=4GxnoUHvOkM
+            'skip_download': True,
-    ]
+        },
-
+    }, {
-    def extract_from_json_api(self, video_id, api_url):
+        'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
-        doc = self._download_json(
+        'only_matching': True,
-            api_url, video_id,
+    }, {
-            note="Downloading webpage metadata",
+        # no media
-            errnote="Failed to load webpage metadata")
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
-
+        'only_matching': True,
-        for a in doc["absaetze"]:
+    }, {
-            if a["typ"] == "video-youtube":
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
-                return {
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
-                    '_type': 'url_transparent',
+        'only_matching': True,
-                    'id': a["id"],
+    }]
-                    'title': doc["titel"],
-                    'url': "https://www.youtube.com/watch?v=%s" % a["id"],
-                    'ie_key': 'Youtube',
-                }
-        raise ExtractorError("No downloadable video found", expected=True)
 
     def _real_extract(self, url):
-        page_id = self._match_id(url)
+        article_id = self._match_id(url)
-        api_url = 'https://www.phoenix.de/response/id/%s' % page_id
+
-        return self.extract_from_json_api(page_id, api_url)
+        article = self._download_json(
+            'https://www.phoenix.de/response/id/%s' % article_id, article_id,
+            'Downloading article JSON')
+
+        video = article['absaetze'][0]
+        title = video.get('titel') or article.get('subtitel')
+
+        if video.get('typ') == 'video-youtube':
+            video_id = video['id']
+            return self.url_result(
+                video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
+                video_title=title)
+
+        video_id = compat_str(video.get('basename') or video.get('content'))
+
+        details = self._download_xml(
+            'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
+            video_id, 'Downloading details XML', query={
+                'ak': 'web',
+                'ptmd': 'true',
+                'id': video_id,
+                'profile': 'player2',
+            })
+
+        title = title or xpath_text(
+            details, './/information/title', 'title', fatal=True)
+        content_id = xpath_text(
+            details, './/video/details/basename', 'content id', fatal=True)
+
+        info = self._extract_ptmd(
+            'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
+            content_id, None, url)
+
+        timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
+
+        thumbnails = []
+        for node in details.findall('.//teaserimages/teaserimage'):
+            thumbnail_url = node.text
+            if not thumbnail_url:
+                continue
+            thumbnail = {
+                'url': thumbnail_url,
+            }
+            thumbnail_key = node.get('key')
+            if thumbnail_key:
+                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
+                if m:
+                    thumbnail['width'] = int(m.group(1))
+                    thumbnail['height'] = int(m.group(2))
+            thumbnails.append(thumbnail)
+
+        return merge_dicts(info, {
+            'id': content_id,
+            'title': title,
+            'description': xpath_text(details, './/information/detail'),
+            'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': xpath_text(details, './/details/channel'),
+            'uploader_id': xpath_text(details, './/details/originChannelId'),
+            'channel': xpath_text(details, './/details/originChannelTitle'),
+        })

yt_dlp/extractor/picarto.py

@@ -1,22 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import time
-
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     js_to_json,
-    try_get,
-    update_url_query,
-    urlencode_postdata,
 )
 
 
 class PicartoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?'
+    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
     _TEST = {
         'url': 'https://picarto.tv/Setz',
         'info_dict': {
@@ -34,65 +27,46 @@ class PicartoIE(InfoExtractor):
         return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        channel_id = self._match_id(url)
-        channel_id = mobj.group('id')
 
-        metadata = self._download_json(
+        data = self._download_json(
-            'https://api.picarto.tv/v1/channel/name/' + channel_id,
+            'https://ptvintern.picarto.tv/ptvapi', channel_id, query={
-            channel_id)
+                'query': '''{
+  channel(name: "%s") {
+    adult
+    id
+    online
+    stream_name
+    title
+  }
+  getLoadBalancerUrl(channel_name: "%s") {
+    url
+  }
+}''' % (channel_id, channel_id),
+            })['data']
+        metadata = data['channel']
 
-        if metadata.get('online') is False:
+        if metadata.get('online') == 0:
             raise ExtractorError('Stream is offline', expected=True)
+        title = metadata['title']
 
         cdn_data = self._download_json(
-            'https://picarto.tv/process/channel', channel_id,
+            data['getLoadBalancerUrl']['url'] + '/stream/json_' + metadata['stream_name'] + '.js',
-            data=urlencode_postdata({'loadbalancinginfo': channel_id}),
+            channel_id, 'Downloading load balancing info')
-            note='Downloading load balancing info')
 
-        token = mobj.group('token') or 'public'
-        params = {
-            'con': int(time.time() * 1000),
-            'token': token,
-        }
-
-        prefered_edge = cdn_data.get('preferedEdge')
         formats = []
-
+        for source in (cdn_data.get('source') or []):
-        for edge in cdn_data['edges']:
+            source_url = source.get('url')
-            edge_ep = edge.get('ep')
+            if not source_url:
-            if not edge_ep or not isinstance(edge_ep, compat_str):
                 continue
-            edge_id = edge.get('id')
+            source_type = source.get('type')
-            for tech in cdn_data['techs']:
+            if source_type == 'html5/application/vnd.apple.mpegurl':
-                tech_label = tech.get('label')
+                formats.extend(self._extract_m3u8_formats(
-                tech_type = tech.get('type')
+                    source_url, channel_id, 'mp4', m3u8_id='hls', fatal=False))
-                preference = 0
+            elif source_type == 'html5/video/mp4':
-                if edge_id == prefered_edge:
+                formats.append({
-                    preference += 1
+                    'url': source_url,
-                format_id = []
+                })
-                if edge_id:
-                    format_id.append(edge_id)
-                if tech_type == 'application/x-mpegurl' or tech_label == 'HLS':
-                    format_id.append('hls')
-                    formats.extend(self._extract_m3u8_formats(
-                        update_url_query(
-                            'https://%s/hls/%s/index.m3u8'
-                            % (edge_ep, channel_id), params),
-                        channel_id, 'mp4', quality=preference,
-                        m3u8_id='-'.join(format_id), fatal=False))
-                    continue
-                elif tech_type == 'video/mp4' or tech_label == 'MP4':
-                    format_id.append('mp4')
-                    formats.append({
-                        'url': update_url_query(
-                            'https://%s/mp4/%s.mp4' % (edge_ep, channel_id),
-                            params),
-                        'format_id': '-'.join(format_id),
-                        'quality': preference,
-                    })
-                else:
-                    # rtmp format does not seem to work
-                    continue
         self._sort_formats(formats)
 
         mature = metadata.get('adult')
@@ -103,10 +77,10 @@ class PicartoIE(InfoExtractor):
 
         return {
             'id': channel_id,
-            'title': self._live_title(metadata.get('title') or channel_id),
+            'title': self._live_title(title.strip()),
             'is_live': True,
-            'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']),
             'channel': channel_id,
+            'channel_id': metadata.get('id'),
             'channel_url': 'https://picarto.tv/%s' % channel_id,
             'age_limit': age_limit,
             'formats': formats,

yt_dlp/extractor/pinterest.py

@@ -31,6 +31,7 @@ class PinterestBaseIE(InfoExtractor):
 
         title = (data.get('title') or data.get('grid_title') or video_id).strip()
 
+        urls = []
         formats = []
         duration = None
         if extract_formats:
@@ -38,8 +39,9 @@ class PinterestBaseIE(InfoExtractor):
                 if not isinstance(format_dict, dict):
                     continue
                 format_url = url_or_none(format_dict.get('url'))
-                if not format_url:
+                if not format_url or format_url in urls:
                     continue
+                urls.append(format_url)
                 duration = float_or_none(format_dict.get('duration'), scale=1000)
                 ext = determine_ext(format_url)
                 if 'hls' in format_id.lower() or ext == 'm3u8':

yt_dlp/extractor/plutotv.py

@@ -0,0 +1,164 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import uuid
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    try_get,
+    url_or_none,
+)
+
+
+class PlutoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pluto\.tv/on-demand/(?P<video_type>movies|series)/(?P<slug>.*)/?$'
+    _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
+    _INFO_QUERY_PARAMS = {
+        'appName': 'web',
+        'appVersion': 'na',
+        'clientID': compat_str(uuid.uuid1()),
+        'clientModelNumber': 'na',
+        'serverSideAds': 'false',
+        'deviceMake': 'unknown',
+        'deviceModel': 'web',
+        'deviceType': 'web',
+        'deviceVersion': 'unknown',
+        'sid': compat_str(uuid.uuid1()),
+    }
+    _TESTS = [
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
+            'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
+            'info_dict': {
+                'id': '5de6c598e9379ae4912df0a8',
+                'ext': 'mp4',
+                'title': 'It\'s In The Cards',
+                'episode': 'It\'s In The Cards',
+                'description': 'The teams face off against each other in a 3-on-2 soccer showdown.  Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.',
+                'series': 'I Love Money',
+                'season_number': 2,
+                'episode_number': 3,
+                'duration': 3600,
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
+            'playlist_count': 11,
+            'info_dict': {
+                'id': '5de6c582e9379ae4912dedbd',
+                'title': 'I Love Money - Season 1',
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/',
+            'playlist_count': 26,
+            'info_dict': {
+                'id': '5de6c582e9379ae4912dedbd',
+                'title': 'I Love Money',
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
+            'md5': '3cead001d317a018bf856a896dee1762',
+            'info_dict': {
+                'id': '5e83ac701fa6a9001bb9df24',
+                'ext': 'mp4',
+                'title': 'Arrival',
+                'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.',
+                'duration': 9000,
+            }
+        },
+    ]
+
+    def _to_ad_free_formats(self, video_id, formats):
+        ad_free_formats = []
+        m3u8_urls = set()
+        for format in formats:
+            res = self._download_webpage(
+                format.get('url'), video_id, note='Downloading m3u8 playlist',
+                fatal=False)
+            if not res:
+                continue
+            first_segment_url = re.search(
+                r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res,
+                re.MULTILINE)
+            if not first_segment_url:
+                continue
+            m3u8_urls.add(
+                compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
+
+        for m3u8_url in m3u8_urls:
+            ad_free_formats.extend(
+                self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+        self._sort_formats(ad_free_formats)
+        return ad_free_formats
+
+    def _get_video_info(self, video_json, slug, series_name=None):
+        video_id = video_json.get('_id', slug)
+        formats = []
+        for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
+            if video_url.get('type') != 'hls':
+                continue
+            url = url_or_none(video_url.get('url'))
+            formats.extend(
+                self._extract_m3u8_formats(
+                    url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+        info = {
+            'id': video_id,
+            'formats': self._to_ad_free_formats(video_id, formats),
+            'title': video_json.get('name'),
+            'description': video_json.get('description'),
+            'duration': float_or_none(video_json.get('duration'), scale=1000),
+        }
+        if series_name:
+            info.update({
+                'series': series_name,
+                'episode': video_json.get('name'),
+                'season_number': int_or_none(video_json.get('season')),
+                'episode_number': int_or_none(video_json.get('number')),
+            })
+        return info
+
+    def _real_extract(self, url):
+        path = compat_urlparse.urlparse(url).path
+        path_components = path.split('/')
+        video_type = path_components[2]
+        info_slug = path_components[3]
+        video_json = self._download_json(self._INFO_URL + info_slug, info_slug,
+                                         query=self._INFO_QUERY_PARAMS)
+
+        if video_type == 'series':
+            series_name = video_json.get('name', info_slug)
+            season_number = int_or_none(try_get(path_components, lambda x: x[5]))
+            episode_slug = try_get(path_components, lambda x: x[7])
+
+            videos = []
+            for season in video_json['seasons']:
+                if season_number is not None and season_number != int_or_none(season.get('number')):
+                    continue
+                for episode in season['episodes']:
+                    if episode_slug is not None and episode_slug != episode.get('slug'):
+                        continue
+                    videos.append(self._get_video_info(episode, episode_slug, series_name))
+            if not videos:
+                raise ExtractorError('Failed to find any videos to extract')
+            if episode_slug is not None and len(videos) == 1:
+                return videos[0]
+            playlist_title = series_name
+            if season_number is not None:
+                playlist_title += ' - Season %d' % season_number
+            return self.playlist_result(videos,
+                                        playlist_id=video_json.get('_id', info_slug),
+                                        playlist_title=playlist_title)
+        return self._get_video_info(video_json, info_slug)

yt_dlp/extractor/pornhub.py

@@ -167,6 +167,7 @@ class PornHubIE(PornHubBaseIE):
         'params': {
             'skip_download': True,
         },
+        'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
     }, {
         # subtitles
         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
@@ -265,7 +266,8 @@ class PornHubIE(PornHubBaseIE):
         webpage = dl_webpage('pc')
 
         error_msg = self._html_search_regex(
-            r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+            (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+             r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
             webpage, 'error message', default=None, group='error')
         if error_msg:
             error_msg = re.sub(r'\s+', ' ', error_msg)
@@ -394,6 +396,21 @@ class PornHubIE(PornHubBaseIE):
 
         upload_date = None
         formats = []
+
+        def add_format(format_url, height=None):
+            tbr = None
+            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
+            if mobj:
+                if not height:
+                    height = int(mobj.group('height'))
+                tbr = int(mobj.group('tbr'))
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
         for video_url, height in video_urls:
             if not upload_date:
                 upload_date = self._search_regex(
@@ -410,18 +427,19 @@ class PornHubIE(PornHubBaseIE):
                     video_url, video_id, 'mp4', entry_protocol='m3u8_native',
                     m3u8_id='hls', fatal=False))
                 continue
-            tbr = None
+            if '/video/get_media' in video_url:
-            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
+                medias = self._download_json(video_url, video_id, fatal=False)
-            if mobj:
+                if isinstance(medias, list):
-                if not height:
+                    for media in medias:
-                    height = int(mobj.group('height'))
+                        if not isinstance(media, dict):
-                tbr = int(mobj.group('tbr'))
+                            continue
-            formats.append({
+                        video_url = url_or_none(media.get('videoUrl'))
-                'url': video_url,
+                        if not video_url:
-                'format_id': '%dp' % height if height else None,
+                            continue
-                'height': height,
+                        height = int_or_none(media.get('quality'))
-                'tbr': tbr,
+                        add_format(video_url, height)
-            })
+                continue
+            add_format(video_url)
         self._sort_formats(formats)
 
         video_uploader = self._html_search_regex(

yt_dlp/extractor/rai.py

@@ -158,6 +158,10 @@ class RaiPlayIE(RaiBaseIE):
         # subtitles at 'subtitlesArray' key (see #27698)
         'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
         'only_matching': True,
+    }, {
+        # DRM protected
+        'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -166,6 +170,14 @@ class RaiPlayIE(RaiBaseIE):
         media = self._download_json(
             base + '.json', video_id, 'Downloading video JSON')
 
+        if not self._downloader.params.get('allow_unplayable_formats'):
+            if try_get(
+                    media,
+                    (lambda x: x['rights_management']['rights']['drm'],
+                     lambda x: x['program_info']['rights_management']['rights']['drm']),
+                    dict):
+                raise ExtractorError('This video is DRM protected.', expected=True)
+
         title = media['name']
         video = media['video']
 

yt_dlp/extractor/rcs.py

@@ -15,6 +15,9 @@ from ..utils import (
 
 
 class RCSBaseIE(InfoExtractor):
+    # based on VideoPlayerLoader.prototype.getVideoSrc
+    # and VideoPlayerLoader.prototype.transformSrc from
+    # https://js2.corriereobjects.it/includes2013/LIBS/js/corriere_video.sjs
     _ALL_REPLACE = {
         'media2vam.corriere.it.edgesuite.net':
             'media2vam-corriere-it.akamaized.net',
@@ -191,10 +194,10 @@ class RCSBaseIE(InfoExtractor):
             urls.get('m3u8'), video_id, 'mp4', entry_protocol='m3u8_native',
             m3u8_id='hls', fatal=False)
 
-        if not formats:
+        if urls.get('mp4'):
             formats.append({
                 'format_id': 'http-mp4',
-                'url': urls.get('mp4')
+                'url': urls['mp4']
             })
         self._sort_formats(formats)
         return formats
@@ -216,10 +219,12 @@ class RCSBaseIE(InfoExtractor):
         video_data = None
         # look for json video data url
         json = self._search_regex(
-            r'''(?x)var url\s*=\s*["']((?:https?:)?
+            r'''(?x)url\s*=\s*(["'])
-                //video\.rcs\.it
+            (?P<url>
-                /fragment-includes/video-includes/.+?\.json)["'];''',
+                (?:https?:)?//video\.rcs\.it
-            page, video_id, default=None)
+                /fragment-includes/video-includes/.+?\.json
+            )\1;''',
+            page, video_id, group='url', default=None)
         if json:
             if json.startswith('//'):
                 json = 'https:%s' % json
@@ -227,13 +232,16 @@ class RCSBaseIE(InfoExtractor):
 
         # if json url not found, look for json video data directly in the page
         else:
+            # RCS normal pages and most of the embeds
             json = self._search_regex(
                 r'[\s;]video\s*=\s*({[\s\S]+?})(?:;|,playlist=)',
                 page, video_id, default=None)
-            if json:
+            if not json and 'video-embed' in url:
-                video_data = self._parse_json(
+                page = self._download_webpage(url.replace('video-embed', 'video-json'), video_id)
-                    json, video_id, transform_source=js_to_json)
+                json = self._search_regex(
-            else:
+                    r'##start-video##({[\s\S]+?})##end-video##',
+                    page, video_id, default=None)
+            if not json:
                 # if no video data found try search for iframes
                 emb = RCSEmbedsIE._extract_url(page)
                 if emb:
@@ -242,6 +250,9 @@ class RCSBaseIE(InfoExtractor):
                         'url': emb,
                         'ie_key': RCSEmbedsIE.ie_key()
                     }
+            if json:
+                video_data = self._parse_json(
+                    json, video_id, transform_source=js_to_json)
 
         if not video_data:
             raise ExtractorError('Video data not found in the page')
@@ -250,7 +261,8 @@ class RCSBaseIE(InfoExtractor):
             self._get_video_src(video_data), video_id)
 
         description = (video_data.get('description')
-                       or clean_html(video_data.get('htmlDescription')))
+                       or clean_html(video_data.get('htmlDescription'))
+                       or self._html_search_meta('description', page))
         uploader = video_data.get('provider') or mobj.group('cdn')
 
         return {
@@ -283,6 +295,7 @@ class RCSEmbedsIE(RCSBaseIE):
             'uploader': 'rcs.it',
         }
     }, {
+        # redownload the page changing 'video-embed' in 'video-json'
         'url': 'https://video.gazzanet.gazzetta.it/video-embed/gazzanet-mo05-0000260789',
         'md5': 'a043e3fecbe4d9ed7fc5d888652a5440',
         'info_dict': {
@@ -359,6 +372,7 @@ class RCSIE(RCSBaseIE):
             'uploader': 'Corriere Tv',
         }
     }, {
+        # video data inside iframe
         'url': 'https://viaggi.corriere.it/video/norvegia-il-nuovo-ponte-spettacolare-sopra-la-cascata-di-voringsfossen/',
         'md5': 'da378e4918d2afbf7d61c35abb948d4c',
         'info_dict': {
@@ -389,15 +403,15 @@ class RCSVariousIE(RCSBaseIE):
                     (?P<cdn>
                         leitv\.it|
                         youreporter\.it
-                    )/(?:video/)?(?P<id>[^/]+?)(?:$|\?|/)'''
+                    )/(?:[^/]+/)?(?P<id>[^/]+?)(?:$|\?|/)'''
     _TESTS = [{
-        'url': 'https://www.leitv.it/video/marmellata-di-ciliegie-fatta-in-casa/',
+        'url': 'https://www.leitv.it/benessere/mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa/',
-        'md5': '618aaabac32152199c1af86784d4d554',
+        'md5': '92b4e63667b8f95acb0a04da25ae28a1',
         'info_dict': {
-            'id': 'marmellata-di-ciliegie-fatta-in-casa',
+            'id': 'mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa',
             'ext': 'mp4',
-            'title': 'Marmellata di ciliegie fatta in casa',
+            'title': 'Cervicalgia e mal di testa, il video con i suggerimenti dell\'esperto',
-            'description': 'md5:89133864d6aad456dbcf6e7a29f86263',
+            'description': 'md5:ae21418f34cee0b8d02a487f55bcabb5',
             'uploader': 'leitv.it',
         }
     }, {

yt_dlp/extractor/rds.py

@@ -15,17 +15,17 @@ class RDSIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+'
 
     _TESTS = [{
-        'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799',
+        # has two 9c9media ContentPackages, the web player selects the first ContentPackage
+        'url': 'https://www.rds.ca/videos/Hockey/NationalHockeyLeague/teams/9/forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande-3.1377606',
         'info_dict': {
-            'id': '604333',
+            'id': '2083309',
-            'display_id': 'fowler-jr-prend-la-direction-de-jacksonville',
+            'display_id': 'forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande',
             'ext': 'flv',
-            'title': 'Fowler Jr. prend la direction de Jacksonville',
+            'title': 'Forum du 5 à 7 : Kotkaniemi de retour de Finlande',
-            'description': 'Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ',
+            'description': 'md5:83fa38ecc4a79b19e433433254077f25',
-            'timestamp': 1430397346,
+            'timestamp': 1606129030,
-            'upload_date': '20150430',
+            'upload_date': '20201123',
-            'duration': 154.354,
+            'duration': 773.039,
-            'age_limit': 0,
         }
     }, {
         'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',

yt_dlp/extractor/rts.py

@@ -6,11 +6,12 @@ import re
 from .srgssr import SRGSSRIE
 from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    determine_ext,
+    urljoin,
 )
 
 
@@ -21,7 +22,7 @@ class RTSIE(SRGSSRIE):
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
+            'md5': '753b877968ad8afaeddccc374d4256a5',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
@@ -35,6 +36,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
@@ -63,11 +65,12 @@ class RTSIE(SRGSSRIE):
                 # m3u8 download
                 'skip_download': True,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
-            'md5': '1bae984fe7b1f78e94abc74e802ed99f',
+            'md5': '9bb06503773c07ce83d3cbd793cebb91',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
@@ -81,6 +84,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
@@ -160,7 +164,7 @@ class RTSIE(SRGSSRIE):
         media_type = 'video' if 'video' in all_info else 'audio'
 
         # check for errors
-        self.get_media_data('rts', media_type, media_id)
+        self._get_media_data('rts', media_type, media_id)
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
@@ -194,6 +198,7 @@ class RTSIE(SRGSSRIE):
                     'tbr': extract_bitrate(format_url),
                 })
 
+        download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
         for media in info.get('media', []):
             media_url = media.get('url')
             if not media_url or re.match(r'https?://', media_url):
@@ -205,7 +210,7 @@ class RTSIE(SRGSSRIE):
                 format_id += '-%dk' % rate
             formats.append({
                 'format_id': format_id,
-                'url': 'http://download-video.rts.ch/' + media_url,
+                'url': urljoin(download_base, media_url),
                 'tbr': rate or extract_bitrate(media_url),
             })
 

yt_dlp/extractor/rtve.py

@@ -2,8 +2,9 @@
 from __future__ import unicode_literals
 
 import base64
+import io
 import re
-import time
+import sys
 
 from .common import InfoExtractor
 from ..compat import (
@@ -14,56 +15,13 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
+    qualities,
     remove_end,
     remove_start,
-    sanitized_Request,
     std_headers,
 )
 
-
+_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
-def _decrypt_url(png):
-    encrypted_data = compat_b64decode(png)
-    text_index = encrypted_data.find(b'tEXt')
-    text_chunk = encrypted_data[text_index - 4:]
-    length = compat_struct_unpack('!I', text_chunk[:4])[0]
-    # Use bytearray to get integers when iterating in both python 2.x and 3.x
-    data = bytearray(text_chunk[8:8 + length])
-    data = [chr(b) for b in data if b != 0]
-    hash_index = data.index('#')
-    alphabet_data = data[:hash_index]
-    url_data = data[hash_index + 1:]
-    if url_data[0] == 'H' and url_data[3] == '%':
-        # remove useless HQ%% at the start
-        url_data = url_data[4:]
-
-    alphabet = []
-    e = 0
-    d = 0
-    for l in alphabet_data:
-        if d == 0:
-            alphabet.append(l)
-            d = e = (e + 1) % 4
-        else:
-            d -= 1
-    url = ''
-    f = 0
-    e = 3
-    b = 1
-    for letter in url_data:
-        if f == 0:
-            l = int(letter) * 10
-            f = 1
-        else:
-            if e == 0:
-                l += int(letter)
-                url += alphabet[l]
-                e = (b + 3) % 4
-                f = 0
-                b += 1
-            else:
-                e -= 1
-
-    return url
 
 
 class RTVEALaCartaIE(InfoExtractor):
@@ -79,28 +37,31 @@ class RTVEALaCartaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
             'duration': 5024.566,
+            'series': 'Balonmano',
         },
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
     }, {
         'note': 'Live stream',
         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
         'info_dict': {
             'id': '1694255',
-            'ext': 'flv',
+            'ext': 'mp4',
-            'title': 'TODO',
+            'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': 'live stream',
         },
-        'skip': 'The f4m manifest can\'t be used yet',
     }, {
         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
-        'md5': 'e55e162379ad587e9640eda4f7353c0f',
+        'md5': 'd850f3c8731ea53952ebab489cf81cbf',
         'info_dict': {
             'id': '4236788',
             'ext': 'mp4',
-            'title': 'Servir y proteger - Capítulo 104 ',
+            'title': 'Servir y proteger - Capítulo 104',
             'duration': 3222.0,
         },
-        'params': {
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
-            'skip_download': True,  # requires ffmpeg
-        },
     }, {
         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
         'only_matching': True,
@@ -111,58 +72,102 @@ class RTVEALaCartaIE(InfoExtractor):
 
     def _real_initialize(self):
         user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
-        manager_info = self._download_json(
+        self._manager = self._download_json(
             'http://www.rtve.es/odin/loki/' + user_agent_b64,
-            None, 'Fetching manager info')
+            None, 'Fetching manager info')['manager']
-        self._manager = manager_info['manager']
+
+    @staticmethod
+    def _decrypt_url(png):
+        encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
+        while True:
+            length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
+            chunk_type = encrypted_data.read(4)
+            if chunk_type == b'IEND':
+                break
+            data = encrypted_data.read(length)
+            if chunk_type == b'tEXt':
+                alphabet_data, text = data.split(b'\0')
+                quality, url_data = text.split(b'%%')
+                alphabet = []
+                e = 0
+                d = 0
+                for l in _bytes_to_chr(alphabet_data):
+                    if d == 0:
+                        alphabet.append(l)
+                        d = e = (e + 1) % 4
+                    else:
+                        d -= 1
+                url = ''
+                f = 0
+                e = 3
+                b = 1
+                for letter in _bytes_to_chr(url_data):
+                    if f == 0:
+                        l = int(letter) * 10
+                        f = 1
+                    else:
+                        if e == 0:
+                            l += int(letter)
+                            url += alphabet[l]
+                            e = (b + 3) % 4
+                            f = 0
+                            b += 1
+                        else:
+                            e -= 1
+
+                yield quality.decode(), url
+            encrypted_data.read(4)  # CRC
+
+    def _extract_png_formats(self, video_id):
+        png = self._download_webpage(
+            'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
+            video_id, 'Downloading url information', query={'q': 'v2'})
+        q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
+        formats = []
+        for quality, video_url in self._decrypt_url(png):
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, 'dash', fatal=False))
+            else:
+                formats.append({
+                    'format_id': quality,
+                    'quality': q(quality),
+                    'url': video_url,
+                })
+        self._sort_formats(formats)
+        return formats
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        video_id = self._match_id(url)
-        video_id = mobj.group('id')
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
         if info['state'] == 'DESPU':
             raise ExtractorError('The video is no longer available', expected=True)
-        title = info['title']
+        title = info['title'].strip()
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
+        formats = self._extract_png_formats(video_id)
-        png_request = sanitized_Request(png_url)
-        png_request.add_header('Referer', url)
-        png = self._download_webpage(png_request, video_id, 'Downloading url information')
-        video_url = _decrypt_url(png)
-        ext = determine_ext(video_url)
-
-        formats = []
-        if not video_url.endswith('.f4m') and ext != 'm3u8':
-            if '?' not in video_url:
-                video_url = video_url.replace('resources/', 'auth/resources/')
-            video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
-
-        if ext == 'm3u8':
-            formats.extend(self._extract_m3u8_formats(
-                video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
-                m3u8_id='hls', fatal=False))
-        elif ext == 'f4m':
-            formats.extend(self._extract_f4m_formats(
-                video_url, video_id, f4m_id='hds', fatal=False))
-        else:
-            formats.append({
-                'url': video_url,
-            })
-        self._sort_formats(formats)
 
         subtitles = None
-        if info.get('sbtFile') is not None:
+        sbt_file = info.get('sbtFile')
-            subtitles = self.extract_subtitles(video_id, info['sbtFile'])
+        if sbt_file:
+            subtitles = self.extract_subtitles(video_id, sbt_file)
+
+        is_live = info.get('live') is True
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'formats': formats,
             'thumbnail': info.get('image'),
-            'page_url': url,
             'subtitles': subtitles,
-            'duration': float_or_none(info.get('duration'), scale=1000),
+            'duration': float_or_none(info.get('duration'), 1000),
+            'is_live': is_live,
+            'series': info.get('programTitle'),
         }
 
     def _get_subtitles(self, video_id, sub_file):
@@ -174,48 +179,26 @@ class RTVEALaCartaIE(InfoExtractor):
             for s in subs)
 
 
-class RTVEInfantilIE(InfoExtractor):
+class RTVEInfantilIE(RTVEALaCartaIE):
     IE_NAME = 'rtve.es:infantil'
     IE_DESC = 'RTVE infantil'
-    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
-        'md5': '915319587b33720b8e0357caaa6617e6',
+        'md5': '5747454717aedf9f9fdf212d1bcfc48d',
         'info_dict': {
             'id': '3040283',
             'ext': 'mp4',
             'title': 'Maneras de vivir',
-            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
+            'thumbnail': r're:https?://.+/1426182947956\.JPG',
             'duration': 357.958,
         },
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        info = self._download_json(
-            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
-            video_id)['page']['items'][0]
 
-        webpage = self._download_webpage(url, video_id)
+class RTVELiveIE(RTVEALaCartaIE):
-        vidplayer_id = self._search_regex(
-            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
-
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
-        png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        video_url = _decrypt_url(png)
-
-        return {
-            'id': video_id,
-            'ext': 'mp4',
-            'title': info['title'],
-            'url': video_url,
-            'thumbnail': info.get('image'),
-            'duration': float_or_none(info.get('duration'), scale=1000),
-        }
-
-
-class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
@@ -225,7 +208,7 @@ class RTVELiveIE(InfoExtractor):
         'info_dict': {
             'id': 'la-1',
             'ext': 'mp4',
-            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
+            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
         },
         'params': {
             'skip_download': 'live stream',
@@ -234,29 +217,22 @@ class RTVELiveIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        start_time = time.gmtime()
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
         title = remove_start(title, 'Estoy viendo ')
-        title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
             (r'playerId=player([0-9]+)',
              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
              r'data-id=["\'](\d+)'),
             webpage, 'internal video ID')
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
-        png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        m3u8_url = _decrypt_url(png)
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
-        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title),
-            'formats': formats,
+            'formats': self._extract_png_formats(vidplayer_id),
             'is_live': True,
         }
 

yt_dlp/extractor/sbs.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
-    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=|/watch/)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
@@ -43,6 +43,9 @@ class SBSIE(InfoExtractor):
     }, {
         'url': 'https://www.sbs.com.au/news/embeds/video/1840778819866',
         'only_matching': True,
+    }, {
+        'url': 'https://www.sbs.com.au/ondemand/watch/1698704451971',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/screencastomatic.py

@@ -2,12 +2,18 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import js_to_json
+from ..utils import (
+    get_element_by_class,
+    int_or_none,
+    remove_start,
+    strip_or_none,
+    unified_strdate,
+)
 
 
 class ScreencastOMaticIE(InfoExtractor):
-    _VALID_URL = r'https?://screencast-o-matic\.com/watch/(?P<id>[0-9a-zA-Z]+)'
+    _VALID_URL = r'https?://screencast-o-matic\.com/(?:(?:watch|player)/|embed\?.*?\bsc=)(?P<id>[0-9a-zA-Z]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://screencast-o-matic.com/watch/c2lD3BeOPl',
         'md5': '483583cb80d92588f15ccbedd90f0c18',
         'info_dict': {
@@ -16,22 +22,30 @@ class ScreencastOMaticIE(InfoExtractor):
             'title': 'Welcome to 3-4 Philosophy @ DECV!',
             'thumbnail': r're:^https?://.*\.jpg$',
             'description': 'as the title says! also: some general info re 1) VCE philosophy and 2) distance learning.',
-            'duration': 369.163,
+            'duration': 369,
+            'upload_date': '20141216',
         }
-    }
+    }, {
+        'url': 'http://screencast-o-matic.com/player/c2lD3BeOPl',
+        'only_matching': True,
+    }, {
+        'url': 'http://screencast-o-matic.com/embed?ff=true&sc=cbV2r4Q5TL&fromPH=true&a=1',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
-
+            'https://screencast-o-matic.com/player/' + video_id, video_id)
-        jwplayer_data = self._parse_json(
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
-            self._search_regex(
+        info.update({
-                r"(?s)jwplayer\('mp4Player'\).setup\((\{.*?\})\);", webpage, 'setup code'),
+            'id': video_id,
-            video_id, transform_source=js_to_json)
+            'title': get_element_by_class('overlayTitle', webpage),
-
+            'description': strip_or_none(get_element_by_class('overlayDescription', webpage)) or None,
-        info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
+            'duration': int_or_none(self._search_regex(
-        info_dict.update({
+                r'player\.duration\s*=\s*function\(\)\s*{\s*return\s+(\d+);\s*};',
-            'title': self._og_search_title(webpage),
+                webpage, 'duration', default=None)),
-            'description': self._og_search_description(webpage),
+            'upload_date': unified_strdate(remove_start(
+                get_element_by_class('overlayPublished', webpage), 'Published: ')),
         })
-        return info_dict
+        return info

yt_dlp/extractor/shahid.py

@@ -51,13 +51,16 @@ class ShahidIE(ShahidBaseIE):
     _NETRC_MACHINE = 'shahid'
     _VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
     _TESTS = [{
-        'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286',
+        'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AA%D8%AD%D9%81-%D8%A7%D9%84%D8%AF%D8%AD%D9%8A%D8%AD-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-816924',
         'info_dict': {
-            'id': '275286',
+            'id': '816924',
             'ext': 'mp4',
-            'title': 'مجلس الشباب الموسم 1 كليب 1',
+            'title': 'متحف الدحيح الموسم 1 كليب 1',
-            'timestamp': 1506988800,
+            'timestamp': 1602806400,
-            'upload_date': '20171003',
+            'upload_date': '20201016',
+            'description': 'برومو',
+            'duration': 22,
+            'categories': ['كوميديا'],
         },
         'params': {
             # m3u8 download
@@ -109,12 +112,15 @@ class ShahidIE(ShahidBaseIE):
             page_type = 'episode'
 
         playout = self._call_api(
-            'playout/url/' + video_id, video_id)['playout']
+            'playout/new/url/' + video_id, video_id)['playout']
 
         if not self._downloader.params.get('allow_unplayable_formats') and playout.get('drm'):
             raise ExtractorError('This video is DRM protected.', expected=True)
 
-        formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
+        formats = self._extract_m3u8_formats(re.sub(
+            # https://docs.aws.amazon.com/mediapackage/latest/ug/manifest-filtering.html
+            r'aws\.manifestfilter=[\w:;,-]+&?',
+            '', playout['url']), video_id, 'mp4')
         self._sort_formats(formats)
 
         # video = self._call_api(

yt_dlp/extractor/southpark.py

@@ -6,9 +6,9 @@ from .mtv import MTVServicesInfoExtractor
 
 class SouthParkIE(MTVServicesInfoExtractor):
     IE_NAME = 'southpark.cc.com'
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
 
-    _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
 
     _TESTS = [{
         'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured',
@@ -23,8 +23,20 @@ class SouthParkIE(MTVServicesInfoExtractor):
     }, {
         'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
         'only_matching': True,
+    }, {
+        'url': 'https://www.southparkstudios.com/episodes/h4o269/south-park-stunning-and-brave-season-19-ep-1',
+        'only_matching': True,
     }]
 
+    def _get_feed_query(self, uri):
+        return {
+            'accountOverride': 'intl.mtvi.com',
+            'arcEp': 'shared.southpark.global',
+            'ep': '90877963',
+            'imageEp': 'shared.southpark.global',
+            'mgid': uri,
+        }
+
 
 class SouthParkEsIE(SouthParkIE):
     IE_NAME = 'southpark.cc.com:español'

yt_dlp/extractor/sportdeutschland.py

@@ -1,82 +1,105 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
+    clean_html,
+    float_or_none,
+    int_or_none,
     parse_iso8601,
-    sanitized_Request,
+    strip_or_none,
+    try_get,
 )
 
 
 class SportDeutschlandIE(InfoExtractor):
-    _VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
+    _VALID_URL = r'https?://sportdeutschland\.tv/(?P<id>(?:[^/]+/)?[^?#/&]+)'
     _TESTS = [{
         'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
         'info_dict': {
-            'id': 're-live-deutsche-meisterschaften-2020-halbfinals',
+            'id': '5318cac0275701382770543d7edaf0a0',
             'ext': 'mp4',
-            'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals',
+            'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals - Teil 1',
-            'categories': ['Badminton-Deutschland'],
+            'duration': 16106.36,
-            'view_count': int,
-            'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
-            'timestamp': int,
-            'upload_date': '20200201',
-            'description': 're:.*',  # meaningless description for THIS video
         },
+        'params': {
+            'noplaylist': True,
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
+        'info_dict': {
+            'id': 'c6e2fdd01f63013854c47054d2ab776f',
+            'title': 'Re-live: Deutsche Meisterschaften 2020 - Halbfinals',
+            'description': 'md5:5263ff4c31c04bb780c9f91130b48530',
+            'duration': 31397,
+        },
+        'playlist_count': 2,
+    }, {
+        'url': 'https://sportdeutschland.tv/freeride-world-tour-2021-fieberbrunn-oesterreich',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
+        display_id = self._match_id(url)
-        video_id = mobj.group('id')
+        data = self._download_json(
-        sport_id = mobj.group('sport')
+            'https://backend.sportdeutschland.tv/api/permalinks/' + display_id,
-
+            display_id, query={'access_token': 'true'})
-        api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
-            sport_id, video_id)
-        req = sanitized_Request(api_url, headers={
-            'Accept': 'application/vnd.vidibus.v2.html+json',
-            'Referer': url,
-        })
-        data = self._download_json(req, video_id)
-
         asset = data['asset']
-        categories = [data['section']['title']]
+        title = (asset.get('title') or asset['label']).strip()
-
+        asset_id = asset.get('id') or asset.get('uuid')
-        formats = []
+        info = {
-        smil_url = asset['video']
+            'id': asset_id,
-        if '.smil' in smil_url:
+            'title': title,
-            m3u8_url = smil_url.replace('.smil', '.m3u8')
+            'description': clean_html(asset.get('body') or asset.get('description')) or asset.get('teaser'),
-            formats.extend(
+            'duration': int_or_none(asset.get('seconds')),
-                self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4'))
-
-            smil_doc = self._download_xml(
-                smil_url, video_id, note='Downloading SMIL metadata')
-            base_url_el = smil_doc.find('./head/meta')
-            if base_url_el:
-                base_url = base_url_el.attrib['base']
-            formats.extend([{
-                'format_id': 'rmtp',
-                'url': base_url if base_url_el else n.attrib['src'],
-                'play_path': n.attrib['src'],
-                'ext': 'flv',
-                'preference': -100,
-                'format_note': 'Seems to fail at example stream',
-            } for n in smil_doc.findall('./body/video')])
-        else:
-            formats.append({'url': smil_url})
-
-        self._sort_formats(formats)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'title': asset['title'],
-            'thumbnail': asset.get('image'),
-            'description': asset.get('teaser'),
-            'duration': asset.get('duration'),
-            'categories': categories,
-            'view_count': asset.get('views'),
-            'rtmp_live': asset.get('live'),
-            'timestamp': parse_iso8601(asset.get('date')),
         }
+        videos = asset.get('videos') or []
+        if len(videos) > 1:
+            playlist_id = compat_parse_qs(compat_urllib_parse_urlparse(url).query).get('playlistId', [None])[0]
+            if playlist_id:
+                if self._downloader.params.get('noplaylist'):
+                    videos = [videos[int(playlist_id)]]
+                    self.to_screen('Downloading just a single video because of --no-playlist')
+                else:
+                    self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % asset_id)
+
+            def entries():
+                for i, video in enumerate(videos, 1):
+                    video_id = video.get('uuid')
+                    video_url = video.get('url')
+                    if not (video_id and video_url):
+                        continue
+                    formats = self._extract_m3u8_formats(
+                        video_url.replace('.smil', '.m3u8'), video_id, 'mp4', fatal=False)
+                    if not formats:
+                        continue
+                    yield {
+                        'id': video_id,
+                        'formats': formats,
+                        'title': title + ' - ' + (video.get('label') or 'Teil %d' % i),
+                        'duration': float_or_none(video.get('duration')),
+                    }
+            info.update({
+                '_type': 'multi_video',
+                'entries': entries(),
+            })
+        else:
+            formats = self._extract_m3u8_formats(
+                videos[0]['url'].replace('.smil', '.m3u8'), asset_id, 'mp4')
+            section_title = strip_or_none(try_get(data, lambda x: x['section']['title']))
+            info.update({
+                'formats': formats,
+                'display_id': asset.get('permalink'),
+                'thumbnail': try_get(asset, lambda x: x['images'][0]),
+                'categories': [section_title] if section_title else None,
+                'view_count': int_or_none(asset.get('views')),
+                'is_live': asset.get('is_live') is True,
+                'timestamp': parse_iso8601(asset.get('date') or asset.get('published_at')),
+            })
+        return info

yt_dlp/extractor/srgssr.py

@@ -4,16 +4,32 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     ExtractorError,
+    float_or_none,
+    int_or_none,
     parse_iso8601,
     qualities,
+    try_get,
 )
 
 
 class SRGSSRIE(InfoExtractor):
-    _VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
+    _VALID_URL = r'''(?x)
+                    (?:
+                        https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|
+                        srgssr
+                    ):
+                    (?P<bu>
+                        srf|rts|rsi|rtr|swi
+                    ):(?:[^:]+:)?
+                    (?P<type>
+                        video|audio
+                    ):
+                    (?P<id>
+                        [0-9a-f\-]{36}|\d+
+                    )
+                    '''
     _GEO_BYPASS = False
     _GEO_COUNTRIES = ['CH']
 
@@ -25,25 +41,39 @@ class SRGSSRIE(InfoExtractor):
         'LEGAL': 'The video cannot be transmitted for legal reasons.',
         'STARTDATE': 'This video is not yet available. Please try again later.',
     }
+    _DEFAULT_LANGUAGE_CODES = {
+        'srf': 'de',
+        'rts': 'fr',
+        'rsi': 'it',
+        'rtr': 'rm',
+        'swi': 'en',
+    }
 
     def _get_tokenized_src(self, url, video_id, format_id):
-        sp = compat_urllib_parse_urlparse(url).path.split('/')
         token = self._download_json(
-            'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
+            'http://tp.srgssr.ch/akahd/token?acl=*',
             video_id, 'Downloading %s token' % format_id, fatal=False) or {}
-        auth_params = token.get('token', {}).get('authparams')
+        auth_params = try_get(token, lambda x: x['token']['authparams'])
         if auth_params:
-            url += '?' + auth_params
+            url += ('?' if '?' not in url else '&') + auth_params
         return url
 
-    def get_media_data(self, bu, media_type, media_id):
+    def _get_media_data(self, bu, media_type, media_id):
-        media_data = self._download_json(
+        query = {'onlyChapters': True} if media_type == 'video' else {}
-            'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
+        full_media_data = self._download_json(
-            media_id)[media_type.capitalize()]
+            'https://il.srgssr.ch/integrationlayer/2.0/%s/mediaComposition/%s/%s.json'
+            % (bu, media_type, media_id),
+            media_id, query=query)['chapterList']
+        try:
+            media_data = next(
+                x for x in full_media_data if x.get('id') == media_id)
+        except StopIteration:
+            raise ExtractorError('No media information found')
 
-        if media_data.get('block') and media_data['block'] in self._ERRORS:
+        block_reason = media_data.get('blockReason')
-            message = self._ERRORS[media_data['block']]
+        if block_reason and block_reason in self._ERRORS:
-            if media_data['block'] == 'GEOBLOCK':
+            message = self._ERRORS[block_reason]
+            if block_reason == 'GEOBLOCK':
                 self.raise_geo_restricted(
                     msg=message, countries=self._GEO_COUNTRIES)
             raise ExtractorError(
@@ -53,53 +83,75 @@ class SRGSSRIE(InfoExtractor):
 
     def _real_extract(self, url):
         bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
+        media_data = self._get_media_data(bu, media_type, media_id)
+        title = media_data['title']
 
-        media_data = self.get_media_data(bu, media_type, media_id)
-
-        metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
-        title = metadata['title']
-        description = metadata.get('description')
-        created_date = media_data.get('createdDate') or metadata.get('createdDate')
-        timestamp = parse_iso8601(created_date)
-
-        thumbnails = [{
-            'id': image.get('id'),
-            'url': image['url'],
-        } for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
-
-        preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
         formats = []
-        for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
+        q = qualities(['SD', 'HD'])
-            protocol = source.get('@protocol')
+        for source in (media_data.get('resourceList') or []):
-            for asset in source['url']:
+            format_url = source.get('url')
-                asset_url = asset['text']
+            if not format_url:
-                quality = asset['@quality']
+                continue
-                format_id = '%s-%s' % (protocol, quality)
+            protocol = source.get('protocol')
-                if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
+            quality = source.get('quality')
-                    asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
+            format_id = []
-                    if protocol.startswith('HTTP-HDS'):
+            for e in (protocol, source.get('encoding'), quality):
-                        formats.extend(self._extract_f4m_formats(
+                if e:
-                            asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
+                    format_id.append(e)
-                            media_id, f4m_id=format_id, fatal=False))
+            format_id = '-'.join(format_id)
-                    elif protocol.startswith('HTTP-HLS'):
+
-                        formats.extend(self._extract_m3u8_formats(
+            if protocol in ('HDS', 'HLS'):
-                            asset_url, media_id, 'mp4', 'm3u8_native',
+                if source.get('tokenType') == 'AKAMAI':
-                            m3u8_id=format_id, fatal=False))
+                    format_url = self._get_tokenized_src(
-                else:
+                        format_url, media_id, format_id)
-                    formats.append({
+                    formats.extend(self._extract_akamai_formats(
-                        'format_id': format_id,
+                        format_url, media_id))
-                        'url': asset_url,
+                elif protocol == 'HLS':
-                        'quality': preference(quality),
+                    formats.extend(self._extract_m3u8_formats(
-                        'ext': 'flv' if protocol == 'RTMP' else None,
+                        format_url, media_id, 'mp4', 'm3u8_native',
-                    })
+                        m3u8_id=format_id, fatal=False))
+            elif protocol in ('HTTP', 'HTTPS'):
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'quality': q(quality),
+                })
+
+        # This is needed because for audio medias the podcast url is usually
+        # always included, even if is only an audio segment and not the
+        # whole episode.
+        if int_or_none(media_data.get('position')) == 0:
+            for p in ('S', 'H'):
+                podcast_url = media_data.get('podcast%sdUrl' % p)
+                if not podcast_url:
+                    continue
+                quality = p + 'D'
+                formats.append({
+                    'format_id': 'PODCAST-' + quality,
+                    'url': podcast_url,
+                    'quality': q(quality),
+                })
         self._sort_formats(formats)
 
+        subtitles = {}
+        if media_type == 'video':
+            for sub in (media_data.get('subtitleList') or []):
+                sub_url = sub.get('url')
+                if not sub_url:
+                    continue
+                lang = sub.get('locale') or self._DEFAULT_LANGUAGE_CODES[bu]
+                subtitles.setdefault(lang, []).append({
+                    'url': sub_url,
+                })
+
         return {
             'id': media_id,
             'title': title,
-            'description': description,
+            'description': media_data.get('description'),
-            'timestamp': timestamp,
+            'timestamp': parse_iso8601(media_data.get('date')),
-            'thumbnails': thumbnails,
+            'thumbnail': media_data.get('imageUrl'),
+            'duration': float_or_none(media_data.get('duration'), 1000),
+            'subtitles': subtitles,
             'formats': formats,
         }
 
@@ -119,26 +171,17 @@ class SRGSSRPlayIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
-        'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
+        'md5': '6db2226ba97f62ad42ce09783680046c',
         'info_dict': {
             'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
             'ext': 'mp4',
             'upload_date': '20130701',
             'title': 'Snowden beantragt Asyl in Russland',
-            'timestamp': 1372713995,
+            'timestamp': 1372708215,
-        }
+            'duration': 113.827,
-    }, {
+            'thumbnail': r're:^https?://.*1383719781\.png$',
-        # No Speichern (Save) button
-        'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
-        'md5': '0a274ce38fda48c53c01890651985bc6',
-        'info_dict': {
-            'id': '677f5829-e473-4823-ac83-a1087fe97faa',
-            'ext': 'flv',
-            'upload_date': '20130710',
-            'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
-            'description': 'md5:88604432b60d5a38787f152dec89cd56',
-            'timestamp': 1373493600,
         },
+        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
         'info_dict': {
@@ -146,7 +189,8 @@ class SRGSSRPlayIE(InfoExtractor):
             'ext': 'mp3',
             'upload_date': '20151013',
             'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
-            'timestamp': 1444750398,
+            'timestamp': 1444709160,
+            'duration': 336.816,
         },
         'params': {
             # rtmp download
@@ -159,19 +203,32 @@ class SRGSSRPlayIE(InfoExtractor):
             'id': '6348260',
             'display_id': '6348260',
             'ext': 'mp4',
-            'duration': 1796,
+            'duration': 1796.76,
             'title': 'Le 19h30',
-            'description': '',
-            'uploader': '19h30',
             'upload_date': '20141201',
             'timestamp': 1417458600,
             'thumbnail': r're:^https?://.*\.image',
-            'view_count': int,
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         }
+    }, {
+        'url': 'http://play.swissinfo.ch/play/tv/business/video/why-people-were-against-tax-reforms?id=42960270',
+        'info_dict': {
+            'id': '42960270',
+            'ext': 'mp4',
+            'title': 'Why people were against tax reforms',
+            'description': 'md5:7ac442c558e9630e947427469c4b824d',
+            'duration': 94.0,
+            'upload_date': '20170215',
+            'timestamp': 1487173560,
+            'thumbnail': r're:https?://www\.swissinfo\.ch/srgscalableimage/42961964',
+            'subtitles': 'count:9',
+        },
+        'params': {
+            'skip_download': True,
+        }
     }, {
         'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
         'only_matching': True,
@@ -181,6 +238,10 @@ class SRGSSRPlayIE(InfoExtractor):
     }, {
         'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
         'only_matching': True,
+    }, {
+        # audio segment, has podcastSdUrl of the full episode
+        'url': 'https://www.srf.ch/play/radio/popupaudioplayer?id=50b20dc8-f05b-4972-bf03-e438ff2833eb',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -188,5 +249,4 @@ class SRGSSRPlayIE(InfoExtractor):
         bu = mobj.group('bu')
         media_type = mobj.group('type') or mobj.group('type_2')
         media_id = mobj.group('id')
-        # other info can be extracted from url + '&layout=json'
         return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')

yt_dlp/extractor/stitcher.py

@@ -1,19 +1,61 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     clean_html,
+    clean_podcast_url,
     ExtractorError,
     int_or_none,
     str_or_none,
     try_get,
+    url_or_none,
 )
 
 
-class StitcherIE(InfoExtractor):
+class StitcherBaseIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?stitcher\.com/(?:podcast|show)/(?:[^/]+/)+e(?:pisode)?/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
+    _VALID_URL_BASE = r'https?://(?:www\.)?stitcher\.com/(?:podcast|show)/'
+
+    def _call_api(self, path, video_id, query):
+        resp = self._download_json(
+            'https://api.prod.stitcher.com/' + path,
+            video_id, query=query)
+        error_massage = try_get(resp, lambda x: x['errors'][0]['message'])
+        if error_massage:
+            raise ExtractorError(error_massage, expected=True)
+        return resp['data']
+
+    def _extract_description(self, data):
+        return clean_html(data.get('html_description') or data.get('description'))
+
+    def _extract_audio_url(self, episode):
+        return url_or_none(episode.get('audio_url') or episode.get('guid'))
+
+    def _extract_show_info(self, show):
+        return {
+            'thumbnail': show.get('image_base_url'),
+            'series': show.get('title'),
+        }
+
+    def _extract_episode(self, episode, audio_url, show_info):
+        info = {
+            'id': compat_str(episode['id']),
+            'display_id': episode.get('slug'),
+            'title': episode['title'].strip(),
+            'description': self._extract_description(episode),
+            'duration': int_or_none(episode.get('duration')),
+            'url': clean_podcast_url(audio_url),
+            'vcodec': 'none',
+            'timestamp': int_or_none(episode.get('date_published')),
+            'season_number': int_or_none(episode.get('season')),
+            'season_id': str_or_none(episode.get('season_id')),
+        }
+        info.update(show_info)
+        return info
+
+
+class StitcherIE(StitcherBaseIE):
+    _VALID_URL = StitcherBaseIE._VALID_URL_BASE + r'(?:[^/]+/)+e(?:pisode)?/(?:[^/#?&]+-)?(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
         'md5': 'e9635098e0da10b21a0e2b85585530f6',
@@ -24,8 +66,9 @@ class StitcherIE(InfoExtractor):
             'description': 'md5:547adb4081864be114ae3831b4c2b42f',
             'duration': 1604,
             'thumbnail': r're:^https?://.*\.jpg',
-            'upload_date': '20180126',
+            'upload_date': '20151008',
-            'timestamp': 1516989316,
+            'timestamp': 1444285800,
+            'series': 'Talking Machines',
         },
     }, {
         'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
@@ -55,33 +98,47 @@ class StitcherIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        display_id, audio_id = re.match(self._VALID_URL, url).groups()
+        audio_id = self._match_id(url)
+        data = self._call_api(
+            'shows/episodes', audio_id, {'episode_ids': audio_id})
+        episode = data['episodes'][0]
+        audio_url = self._extract_audio_url(episode)
+        if not audio_url:
+            self.raise_login_required()
+        show = try_get(data, lambda x: x['shows'][0], dict) or {}
+        return self._extract_episode(
+            episode, audio_url, self._extract_show_info(show))
 
-        resp = self._download_json(
-            'https://api.prod.stitcher.com/episode/' + audio_id,
-            display_id or audio_id)
-        episode = try_get(resp, lambda x: x['data']['episodes'][0], dict)
-        if not episode:
-            raise ExtractorError(resp['errors'][0]['message'], expected=True)
 
-        title = episode['title'].strip()
+class StitcherShowIE(StitcherBaseIE):
-        audio_url = episode['audio_url']
+    _VALID_URL = StitcherBaseIE._VALID_URL_BASE + r'(?P<id>[^/#?&]+)/?(?:[?#&]|$)'
+    _TESTS = [{
+        'url': 'http://www.stitcher.com/podcast/the-talking-machines',
+        'info_dict': {
+            'id': 'the-talking-machines',
+            'title': 'Talking Machines',
+            'description': 'md5:831f0995e40f26c10231af39cf1ebf0b',
+        },
+        'playlist_mincount': 106,
+    }, {
+        'url': 'https://www.stitcher.com/show/the-talking-machines',
+        'only_matching': True,
+    }]
 
-        thumbnail = None
+    def _real_extract(self, url):
-        show_id = episode.get('show_id')
+        show_slug = self._match_id(url)
-        if show_id and episode.get('classic_id') != -1:
+        data = self._call_api(
-            thumbnail = 'https://stitcher-classic.imgix.net/feedimages/%s.jpg' % show_id
+            'search/show/%s/allEpisodes' % show_slug, show_slug, {'count': 10000})
+        show = try_get(data, lambda x: x['shows'][0], dict) or {}
+        show_info = self._extract_show_info(show)
 
-        return {
+        entries = []
-            'id': audio_id,
+        for episode in (data.get('episodes') or []):
-            'display_id': display_id,
+            audio_url = self._extract_audio_url(episode)
-            'title': title,
+            if not audio_url:
-            'description': clean_html(episode.get('html_description') or episode.get('description')),
+                continue
-            'duration': int_or_none(episode.get('duration')),
+            entries.append(self._extract_episode(episode, audio_url, show_info))
-            'thumbnail': thumbnail,
+
-            'url': audio_url,
+        return self.playlist_result(
-            'vcodec': 'none',
+            entries, show_slug, show.get('title'),
-            'timestamp': int_or_none(episode.get('date_created')),
+            self._extract_description(show))
-            'season_number': int_or_none(episode.get('season')),
-            'season_id': str_or_none(episode.get('season_id')),
-        }

yt_dlp/extractor/stretchinternet.py

@@ -1,7 +1,6 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import int_or_none
 
 
 class StretchInternetIE(InfoExtractor):
@@ -11,22 +10,28 @@ class StretchInternetIE(InfoExtractor):
         'info_dict': {
             'id': '573272',
             'ext': 'mp4',
-            'title': 'University of Mary Wrestling vs. Upper Iowa',
+            'title': 'UNIVERSITY OF MARY WRESTLING VS UPPER IOWA',
-            'timestamp': 1575668361,
+            # 'timestamp': 1575668361,
-            'upload_date': '20191206',
+            # 'upload_date': '20191206',
+            'uploader_id': '99997',
         }
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        media_url = self._download_json(
+            'https://core.stretchlive.com/trinity/event/tcg/' + video_id,
+            video_id)[0]['media'][0]['url']
         event = self._download_json(
-            'https://api.stretchinternet.com/trinity/event/tcg/' + video_id,
+            'https://neo-client.stretchinternet.com/portal-ws/getEvent.json',
-            video_id)[0]
+            video_id, query={'eventID': video_id, 'token': 'asdf'})['event']
 
         return {
             'id': video_id,
             'title': event['title'],
-            'timestamp': int_or_none(event.get('dateCreated'), 1000),
+            # TODO: parse US timezone abbreviations
-            'url': 'https://' + event['media'][0]['url'],
+            # 'timestamp': event.get('dateTimeString'),
+            'url': 'https://' + media_url,
+            'uploader_id': event.get('ownerID'),
         }

yt_dlp/extractor/svt.py

@@ -146,18 +146,19 @@ class SVTPlayIE(SVTPlayBaseIE):
                         )
                         (?P<svt_id>[^/?#&]+)|
                         https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
+                        (?:.*?modalId=(?P<modal_id>[\da-zA-Z-]+))?
                     )
                     '''
     _TESTS = [{
-        'url': 'https://www.svtplay.se/video/26194546/det-har-ar-himlen',
+        'url': 'https://www.svtplay.se/video/30479064',
         'md5': '2382036fd6f8c994856c323fe51c426e',
         'info_dict': {
-            'id': 'jNwpV9P',
+            'id': '8zVbDPA',
             'ext': 'mp4',
-            'title': 'Det här är himlen',
+            'title': 'Designdrömmar i Stenungsund',
-            'timestamp': 1586044800,
+            'timestamp': 1615770000,
-            'upload_date': '20200405',
+            'upload_date': '20210315',
-            'duration': 3515,
+            'duration': 3519,
             'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
             'age_limit': 0,
             'subtitles': {
@@ -173,6 +174,9 @@ class SVTPlayIE(SVTPlayBaseIE):
             # AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.svtplay.se/video/30479064/husdrommar/husdrommar-sasong-8-designdrommar-i-stenungsund?modalId=8zVbDPA',
+        'only_matching': True,
     }, {
         # geo restricted to Sweden
         'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
@@ -219,7 +223,8 @@ class SVTPlayIE(SVTPlayBaseIE):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id, svt_id = mobj.group('id', 'svt_id')
+        video_id = mobj.group('id')
+        svt_id = mobj.group('svt_id') or mobj.group('modal_id')
 
         if svt_id:
             return self._extract_by_video_id(svt_id)
@@ -254,6 +259,7 @@ class SVTPlayIE(SVTPlayBaseIE):
         if not svt_id:
             svt_id = self._search_regex(
                 (r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
+                 r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/%s/[^"\']*\bmodalId=([\da-zA-Z-]+)' % re.escape(video_id),
                  r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
                  r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
                  r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',

yt_dlp/extractor/tiktok.py

@@ -143,7 +143,10 @@ class TikTokIE(TikTokBaseIE):
         props_data = try_get(json_data, lambda x: x['props'], expected_type=dict)
 
         # Chech statusCode for success
-        if props_data.get('pageProps').get('statusCode') == 0:
+        status = props_data.get('pageProps').get('statusCode')
+        if status == 0:
             return self._extract_aweme(props_data, webpage, url)
+        elif status == 10216:
+            raise ExtractorError('This video is private', expected=True)
 
         raise ExtractorError('Video not available', video_id=video_id)

yt_dlp/extractor/trovo.py

@@ -14,6 +14,7 @@ from ..utils import (
 
 class TrovoBaseIE(InfoExtractor):
     _VALID_URL_BASE = r'https?://(?:www\.)?trovo\.live/'
+    _HEADERS = {'Origin': 'https://trovo.live'}
 
     def _extract_streamer_info(self, data):
         streamer_info = data.get('streamerInfo') or {}
@@ -68,6 +69,7 @@ class TrovoIE(TrovoBaseIE):
                 'format_id': format_id,
                 'height': int_or_none(format_id[:-1]) if format_id else None,
                 'url': play_url,
+                'http_headers': self._HEADERS,
             })
         self._sort_formats(formats)
 
@@ -153,6 +155,7 @@ class TrovoVodIE(TrovoBaseIE):
                 'protocol': 'm3u8_native',
                 'tbr': int_or_none(play_info.get('bitrate')),
                 'url': play_url,
+                'http_headers': self._HEADERS,
             })
         self._sort_formats(formats)
 

yt_dlp/extractor/tver.py

@@ -9,6 +9,7 @@ from ..utils import (
     int_or_none,
     remove_start,
     smuggle_url,
+    strip_or_none,
     try_get,
 )
 
@@ -25,6 +26,10 @@ class TVerIE(InfoExtractor):
     }, {
         'url': 'https://tver.jp/episode/79622438',
         'only_matching': True,
+    }, {
+        # subtitle = ' '
+        'url': 'https://tver.jp/corner/f0068870',
+        'only_matching': True,
     }]
     _TOKEN = None
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
@@ -47,8 +52,12 @@ class TVerIE(InfoExtractor):
         }
 
         if service == 'cx':
+            title = main['title']
+            subtitle = strip_or_none(main.get('subtitle'))
+            if subtitle:
+                title += ' - ' + subtitle
             info.update({
-                'title': main.get('subtitle') or main['title'],
+                'title': title,
                 'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
                 'ie_key': 'FujiTVFODPlus7',
             })

yt_dlp/extractor/urplay.py

@@ -21,6 +21,11 @@ class URPlayIE(InfoExtractor):
             'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
             'timestamp': 1513292400,
             'upload_date': '20171214',
+            'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
+            'duration': 2269,
+            'categories': ['Kultur & historia'],
+            'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
+            'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
         },
     }, {
         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
@@ -31,6 +36,10 @@ class URPlayIE(InfoExtractor):
             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
             'timestamp': 1440086400,
             'upload_date': '20150820',
+            'series': 'Tripp, Trapp, Träd',
+            'duration': 865,
+            'tags': ['Sova'],
+            'episode': 'Sovkudde',
         },
     }, {
         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
@@ -41,9 +50,11 @@ class URPlayIE(InfoExtractor):
         video_id = self._match_id(url)
         url = url.replace('skola.se/Produkter', 'play.se/program')
         webpage = self._download_webpage(url, video_id)
-        urplayer_data = self._parse_json(self._html_search_regex(
+        vid = int(video_id)
+        accessible_episodes = self._parse_json(self._html_search_regex(
             r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
-            webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0]
+            webpage, 'urplayer data'), video_id)['accessibleEpisodes']
+        urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid)
         episode = urplayer_data['title']
 
         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']

yt_dlp/extractor/vgtv.py

@@ -23,6 +23,8 @@ class VGTVIE(XstreamIE):
         'fvn.no/fvntv': 'fvntv',
         'aftenposten.no/webtv': 'aptv',
         'ap.vgtv.no/webtv': 'aptv',
+        'tv.aftonbladet.se': 'abtv',
+        # obsolete URL schemas, kept in order to save one HTTP redirect
         'tv.aftonbladet.se/abtv': 'abtv',
         'www.aftonbladet.se/tv': 'abtv',
     }
@@ -140,6 +142,10 @@ class VGTVIE(XstreamIE):
             'url': 'http://www.vgtv.no/#!/video/127205/inside-the-mind-of-favela-funk',
             'only_matching': True,
         },
+        {
+            'url': 'https://tv.aftonbladet.se/video/36015/vulkanutbrott-i-rymden-nu-slapper-nasa-bilderna',
+            'only_matching': True,
+        },
         {
             'url': 'http://tv.aftonbladet.se/abtv/articles/36015',
             'only_matching': True,

yt_dlp/extractor/vimeo.py

@@ -24,6 +24,7 @@ from ..utils import (
     merge_dicts,
     OnDemandPagedList,
     parse_filesize,
+    parse_iso8601,
     RegexNotFoundError,
     sanitized_Request,
     smuggle_url,
@@ -74,25 +75,28 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                     expected=True)
             raise ExtractorError('Unable to log in')
 
-    def _verify_video_password(self, url, video_id, webpage):
+    def _get_video_password(self):
         password = self._downloader.params.get('videopassword')
         if password is None:
-            raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
+            raise ExtractorError(
-        token, vuid = self._extract_xsrft_and_vuid(webpage)
+                'This video is protected by a password, use the --video-password option',
-        data = urlencode_postdata({
+                expected=True)
-            'password': password,
+        return password
-            'token': token,
+
-        })
+    def _verify_video_password(self, url, video_id, password, token, vuid):
         if url.startswith('http://'):
             # vimeo only supports https now, but the user can give an http url
             url = url.replace('http://', 'https://')
-        password_request = sanitized_Request(url + '/password', data)
-        password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
-        password_request.add_header('Referer', url)
         self._set_vimeo_cookie('vuid', vuid)
         return self._download_webpage(
-            password_request, video_id,
+            url + '/password', video_id, 'Verifying the password',
-            'Verifying the password', 'Wrong password')
+            'Wrong password', data=urlencode_postdata({
+                'password': password,
+                'token': token,
+            }), headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Referer': url,
+            })
 
     def _extract_xsrft_and_vuid(self, webpage):
         xsrft = self._search_regex(
@@ -273,7 +277,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                             )?
                         (?:videos?/)?
                         (?P<id>[0-9]+)
-                        (?:/[\da-f]+)?
+                        (?:/(?P<unlisted_hash>[\da-f]{10}))?
                         /?(?:[?&].*)?(?:[#].*)?$
                     '''
     IE_NAME = 'vimeo'
@@ -326,9 +330,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'id': '54469442',
                 'ext': 'mp4',
                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
-                'uploader': 'The BLN & Business of Software',
+                'uploader': 'Business of Software',
-                'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
+                'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
-                'uploader_id': 'theblnbusinessofsoftware',
+                'uploader_id': 'businessofsoftware',
                 'duration': 3610,
                 'description': None,
             },
@@ -463,6 +467,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 'skip_download': True,
             },
             'expected_warnings': ['Unable to download JSON metadata'],
+            'skip': 'this page is no longer available.',
         },
         {
             'url': 'http://player.vimeo.com/video/68375962',
@@ -498,6 +503,24 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'url': 'https://vimeo.com/album/2632481/video/79010983',
             'only_matching': True,
         },
+        {
+            'url': 'https://vimeo.com/showcase/3253534/video/119195465',
+            'note': 'A video in a password protected album (showcase)',
+            'info_dict': {
+                'id': '119195465',
+                'ext': 'mp4',
+                'title': 'youtube-dl test video \'ä"BaW_jenozKc',
+                'uploader': 'Philipp Hagemeister',
+                'uploader_id': 'user20132939',
+                'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
+                'upload_date': '20150209',
+                'timestamp': 1423518307,
+            },
+            'params': {
+                'format': 'best[protocol=https]',
+                'videopassword': 'youtube-dl',
+            },
+        },
         {
             # source file returns 403: Forbidden
             'url': 'https://vimeo.com/7809605',
@@ -545,9 +568,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         return urls[0] if urls else None
 
     def _verify_player_video_password(self, url, video_id, headers):
-        password = self._downloader.params.get('videopassword')
+        password = self._get_video_password()
-        if password is None:
-            raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
         data = urlencode_postdata({
             'password': base64.b64encode(password.encode()),
         })
@@ -564,6 +585,44 @@ class VimeoIE(VimeoBaseInfoExtractor):
     def _real_initialize(self):
         self._login()
 
+    def _try_album_password(self, url):
+        album_id = self._search_regex(
+            r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
+        if not album_id:
+            return
+        viewer = self._download_json(
+            'https://vimeo.com/_rv/viewer', album_id, fatal=False)
+        if not viewer:
+            webpage = self._download_webpage(url, album_id)
+            viewer = self._parse_json(self._search_regex(
+                r'bootstrap_data\s*=\s*({.+?})</script>',
+                webpage, 'bootstrap data'), album_id)['viewer']
+        jwt = viewer['jwt']
+        album = self._download_json(
+            'https://api.vimeo.com/albums/' + album_id,
+            album_id, headers={'Authorization': 'jwt ' + jwt},
+            query={'fields': 'description,name,privacy'})
+        if try_get(album, lambda x: x['privacy']['view']) == 'password':
+            password = self._downloader.params.get('videopassword')
+            if not password:
+                raise ExtractorError(
+                    'This album is protected by a password, use the --video-password option',
+                    expected=True)
+            self._set_vimeo_cookie('vuid', viewer['vuid'])
+            try:
+                self._download_json(
+                    'https://vimeo.com/showcase/%s/auth' % album_id,
+                    album_id, 'Verifying the password', data=urlencode_postdata({
+                        'password': password,
+                        'token': viewer['xsrft'],
+                    }), headers={
+                        'X-Requested-With': 'XMLHttpRequest',
+                    })
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                    raise ExtractorError('Wrong password', expected=True)
+                raise
+
     def _real_extract(self, url):
         url, data = unsmuggle_url(url, {})
         headers = std_headers.copy()
@@ -572,11 +631,37 @@ class VimeoIE(VimeoBaseInfoExtractor):
         if 'Referer' not in headers:
             headers['Referer'] = url
 
-        channel_id = self._search_regex(
-            r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
-
         # Extract ID from URL
-        video_id = self._match_id(url)
+        video_id, unlisted_hash = re.match(self._VALID_URL, url).groups()
+        if unlisted_hash:
+            token = self._download_json(
+                'https://vimeo.com/_rv/jwt', video_id, headers={
+                    'X-Requested-With': 'XMLHttpRequest'
+                })['token']
+            video = self._download_json(
+                'https://api.vimeo.com/videos/%s:%s' % (video_id, unlisted_hash),
+                video_id, headers={
+                    'Authorization': 'jwt ' + token,
+                }, query={
+                    'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
+                })
+            info = self._parse_config(self._download_json(
+                video['config_url'], video_id), video_id)
+            self._vimeo_sort_formats(info['formats'])
+            get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
+            info.update({
+                'description': video.get('description'),
+                'license': video.get('license'),
+                'release_timestamp': get_timestamp('release'),
+                'timestamp': get_timestamp('created'),
+                'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
+            })
+            connections = try_get(
+                video, lambda x: x['metadata']['connections'], dict) or {}
+            for k in ('comment', 'like'):
+                info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
+            return info
+
         orig_url = url
         is_pro = 'vimeopro.com/' in url
         is_player = '://player.vimeo.com/video/' in url
@@ -591,6 +676,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
             url = 'https://vimeo.com/' + video_id
 
+        self._try_album_password(url)
         try:
             # Retrieve video webpage to extract further information
             webpage, urlh = self._download_webpage_handle(
@@ -665,7 +751,10 @@ class VimeoIE(VimeoBaseInfoExtractor):
             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
                 if '_video_password_verified' in data:
                     raise ExtractorError('video password verification failed!')
-                self._verify_video_password(redirect_url, video_id, webpage)
+                video_password = self._get_video_password()
+                token, vuid = self._extract_xsrft_and_vuid(webpage)
+                self._verify_video_password(
+                    redirect_url, video_id, video_password, token, vuid)
                 return self._real_extract(
                     smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
             else:
@@ -751,6 +840,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
                 webpage, 'license', default=None, group='license')
 
+        channel_id = self._search_regex(
+            r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 
         info_dict = {
@@ -934,11 +1025,15 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
         }
         if hashed_pass:
             query['_hashed_pass'] = hashed_pass
-        videos = self._download_json(
+        try:
-            'https://api.vimeo.com/albums/%s/videos' % album_id,
+            videos = self._download_json(
-            album_id, 'Downloading page %d' % api_page, query=query, headers={
+                'https://api.vimeo.com/albums/%s/videos' % album_id,
-                'Authorization': 'jwt ' + authorization,
+                album_id, 'Downloading page %d' % api_page, query=query, headers={
-            })['data']
+                    'Authorization': 'jwt ' + authorization,
+                })['data']
+        except ExtractorError as e:
+            if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+                return
         for video in videos:
             link = video.get('link')
             if not link:
@@ -1053,10 +1148,23 @@ class VimeoReviewIE(VimeoBaseInfoExtractor):
 
     def _real_extract(self, url):
         page_url, video_id = re.match(self._VALID_URL, url).groups()
-        clip_data = self._download_json(
+        data = self._download_json(
-            page_url.replace('/review/', '/review/data/'),
+            page_url.replace('/review/', '/review/data/'), video_id)
-            video_id)['clipData']
+        if data.get('isLocked') is True:
-        config_url = clip_data['configUrl']
+            video_password = self._get_video_password()
+            viewer = self._download_json(
+                'https://vimeo.com/_rv/viewer', video_id)
+            webpage = self._verify_video_password(
+                'https://vimeo.com/' + video_id, video_id,
+                video_password, viewer['xsrft'], viewer['vuid'])
+            clip_page_config = self._parse_json(self._search_regex(
+                r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
+                webpage, 'clip page config'), video_id)
+            config_url = clip_page_config['player']['config_url']
+            clip_data = clip_page_config.get('clip') or {}
+        else:
+            clip_data = data['clipData']
+            config_url = clip_data['configUrl']
         config = self._download_json(config_url, video_id)
         info_dict = self._parse_config(config, video_id)
         source_format = self._extract_original_format(

yt_dlp/extractor/vlive.py

@@ -113,7 +113,7 @@ class VLiveIE(VLiveBaseIE):
             raise ExtractorError('Unable to log in', expected=True)
 
     def _call_api(self, path_template, video_id, fields=None, limit=None):
-        query = {'appId': self._APP_ID, 'gcc': 'KR'}
+        query = {'appId': self._APP_ID, 'gcc': 'KR', 'platformType': 'PC'}
         if fields:
             query['fields'] = fields
         if limit:

yt_dlp/extractor/voxmedia.py

@@ -7,6 +7,8 @@ from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     ExtractorError,
     int_or_none,
+    try_get,
+    unified_timestamp,
 )
 
 
@@ -19,14 +21,17 @@ class VoxMediaVolumeIE(OnceIE):
 
         setup = self._parse_json(self._search_regex(
             r'setup\s*=\s*({.+});', webpage, 'setup'), video_id)
-        video_data = setup.get('video') or {}
+        player_setup = setup.get('player_setup') or setup
+        video_data = player_setup.get('video') or {}
+        formatted_metadata = video_data.get('formatted_metadata') or {}
         info = {
             'id': video_id,
-            'title': video_data.get('title_short'),
+            'title': player_setup.get('title') or video_data.get('title_short'),
             'description': video_data.get('description_long') or video_data.get('description_short'),
-            'thumbnail': video_data.get('brightcove_thumbnail')
+            'thumbnail': formatted_metadata.get('thumbnail') or video_data.get('brightcove_thumbnail'),
+            'timestamp': unified_timestamp(formatted_metadata.get('video_publish_date')),
         }
-        asset = setup.get('asset') or setup.get('params') or {}
+        asset = try_get(setup, lambda x: x['embed_assets']['chorus'], dict) or {}
 
         formats = []
         hls_url = asset.get('hls_url')
@@ -47,6 +52,7 @@ class VoxMediaVolumeIE(OnceIE):
         if formats:
             self._sort_formats(formats)
             info['formats'] = formats
+            info['duration'] = int_or_none(asset.get('duration'))
             return info
 
         for provider_video_type in ('ooyala', 'youtube', 'brightcove'):
@@ -84,7 +90,7 @@ class VoxMediaIE(InfoExtractor):
     }, {
         # Volume embed, Youtube
         'url': 'http://www.theverge.com/2014/10/21/7025853/google-nexus-6-hands-on-photos-video-android-phablet',
-        'md5': '4c8f4a0937752b437c3ebc0ed24802b5',
+        'md5': 'fd19aa0cf3a0eea515d4fd5c8c0e9d68',
         'info_dict': {
             'id': 'Gy8Md3Eky38',
             'ext': 'mp4',
@@ -93,6 +99,7 @@ class VoxMediaIE(InfoExtractor):
             'uploader_id': 'TheVerge',
             'upload_date': '20141021',
             'uploader': 'The Verge',
+            'timestamp': 1413907200,
         },
         'add_ie': ['Youtube'],
         'skip': 'similar to the previous test',
@@ -100,13 +107,13 @@ class VoxMediaIE(InfoExtractor):
         # Volume embed, Youtube
         'url': 'http://www.vox.com/2016/3/31/11336640/mississippi-lgbt-religious-freedom-bill',
         'info_dict': {
-            'id': 'YCjDnX-Xzhg',
+            'id': '22986359b',
             'ext': 'mp4',
             'title': "Mississippi's laws are so bad that its anti-LGBTQ law isn't needed to allow discrimination",
             'description': 'md5:fc1317922057de31cd74bce91eb1c66c',
-            'uploader_id': 'voxdotcom',
             'upload_date': '20150915',
-            'uploader': 'Vox',
+            'timestamp': 1442332800,
+            'duration': 285,
         },
         'add_ie': ['Youtube'],
         'skip': 'similar to the previous test',
@@ -160,6 +167,9 @@ class VoxMediaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella',
             'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.',
+            'timestamp': 1402938000,
+            'upload_date': '20140616',
+            'duration': 4114,
         },
         'add_ie': ['VoxMediaVolume'],
     }]

yt_dlp/extractor/vvvvid.py

@@ -75,12 +75,15 @@ class VVVVIDIE(InfoExtractor):
             'https://www.vvvvid.it/user/login',
             None, headers=self.geo_verification_headers())['data']['conn_id']
 
-    def _download_info(self, show_id, path, video_id, fatal=True):
+    def _download_info(self, show_id, path, video_id, fatal=True, query=None):
+        q = {
+            'conn_id': self._conn_id,
+        }
+        if query:
+            q.update(query)
         response = self._download_json(
             'https://www.vvvvid.it/vvvvid/ondemand/%s/%s' % (show_id, path),
-            video_id, headers=self.geo_verification_headers(), query={
+            video_id, headers=self.geo_verification_headers(), query=q, fatal=fatal)
-                'conn_id': self._conn_id,
-            }, fatal=fatal)
         if not (response or fatal):
             return
         if response.get('result') == 'error':
@@ -98,7 +101,8 @@ class VVVVIDIE(InfoExtractor):
         show_id, season_id, video_id = re.match(self._VALID_URL, url).groups()
 
         response = self._download_info(
-            show_id, 'season/%s' % season_id, video_id)
+            show_id, 'season/%s' % season_id,
+            video_id, query={'video_id': video_id})
 
         vid = int(video_id)
         video_data = list(filter(
@@ -178,17 +182,20 @@ class VVVVIDIE(InfoExtractor):
             if not embed_code:
                 continue
             embed_code = ds(embed_code)
-            if video_type in ('video/rcs', 'video/kenc'):
+            if video_type == 'video/kenc':
-                if video_type == 'video/kenc':
+                embed_code = re.sub(r'https?(://[^/]+)/z/', r'https\1/i/', embed_code).replace('/manifest.f4m', '/master.m3u8')
-                    kenc = self._download_json(
+                kenc = self._download_json(
-                        'https://www.vvvvid.it/kenc', video_id, query={
+                    'https://www.vvvvid.it/kenc', video_id, query={
-                            'action': 'kt',
+                        'action': 'kt',
-                            'conn_id': self._conn_id,
+                        'conn_id': self._conn_id,
-                            'url': embed_code,
+                        'url': embed_code,
-                        }, fatal=False) or {}
+                    }, fatal=False) or {}
-                    kenc_message = kenc.get('message')
+                kenc_message = kenc.get('message')
-                    if kenc_message:
+                if kenc_message:
-                        embed_code += '?' + ds(kenc_message)
+                    embed_code += '?' + ds(kenc_message)
+                formats.extend(self._extract_m3u8_formats(
+                    embed_code, video_id, 'mp4', m3u8_id='hls', fatal=False))
+            elif video_type == 'video/rcs':
                 formats.extend(self._extract_akamai_formats(embed_code, video_id))
             elif video_type == 'video/youtube':
                 info.update({
@@ -247,9 +254,13 @@ class VVVVIDShowIE(VVVVIDIE):
         show_info = self._download_info(
             show_id, 'info/', show_title, fatal=False)
 
+        if not show_title:
+            base_url += "/title"
+
         entries = []
         for season in (seasons or []):
             episodes = season.get('episodes') or []
+            playlist_title = season.get('name') or show_info.get('title')
             for episode in episodes:
                 if episode.get('playable') is False:
                     continue
@@ -259,12 +270,13 @@ class VVVVIDShowIE(VVVVIDIE):
                     continue
                 info = self._extract_common_video_info(episode)
                 info.update({
-                    '_type': 'url',
+                    '_type': 'url_transparent',
                     'ie_key': VVVVIDIE.ie_key(),
                     'url': '/'.join([base_url, season_id, video_id]),
                     'title': episode.get('title'),
                     'description': episode.get('description'),
                     'season_id': season_id,
+                    'playlist_title': playlist_title,
                 })
                 entries.append(info)
 

yt_dlp/extractor/wimtv.py

@@ -0,0 +1,163 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    parse_duration,
+    urlencode_postdata,
+    ExtractorError,
+)
+
+
+class WimTVIE(InfoExtractor):
+    _player = None
+    _UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
+    _VALID_URL = r'''(?x)
+        https?://platform.wim.tv/
+        (?:
+            (?:embed/)?\?
+            |\#/webtv/.+?/
+        )
+        (?P<type>vod|live|cast)[=/]
+        (?P<id>%s).*?''' % _UUID_RE
+    _TESTS = [{
+        # vod stream
+        'url': 'https://platform.wim.tv/embed/?vod=db29fb32-bade-47b6-a3a6-cb69fe80267a',
+        'md5': 'db29fb32-bade-47b6-a3a6-cb69fe80267a',
+        'info_dict': {
+            'id': 'db29fb32-bade-47b6-a3a6-cb69fe80267a',
+            'ext': 'mp4',
+            'title': 'AMA SUPERCROSS 2020 - R2 ST. LOUIS',
+            'duration': 6481,
+            'thumbnail': r're:https?://.+?/thumbnail/.+?/720$'
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # live stream
+        'url': 'https://platform.wim.tv/embed/?live=28e22c22-49db-40f3-8c37-8cbb0ff44556&autostart=true',
+        'info_dict': {
+            'id': '28e22c22-49db-40f3-8c37-8cbb0ff44556',
+            'ext': 'mp4',
+            'title': 'Streaming MSmotorTV',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://platform.wim.tv/#/webtv/automotornews/vod/422492b6-539e-474d-9c6b-68c9d5893365',
+        'only_matching': True,
+    }, {
+        'url': 'https://platform.wim.tv/#/webtv/renzoarborechannel/cast/f47e0d15-5b45-455e-bf0d-dba8ffa96365',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [
+            mobj.group('url')
+            for mobj in re.finditer(
+                r'<iframe[^>]+src=["\'](?P<url>%s)' % WimTVIE._VALID_URL,
+                webpage)]
+
+    def _real_initialize(self):
+        if not self._player:
+            self._get_player_data()
+
+    def _get_player_data(self):
+        msg_id = 'Player data'
+        self._player = {}
+
+        datas = [{
+            'url': 'https://platform.wim.tv/common/libs/player/wimtv/wim-rest.js',
+            'vars': [{
+                'regex': r'appAuth = "(.+?)"',
+                'variable': 'app_auth',
+            }]
+        }, {
+            'url': 'https://platform.wim.tv/common/config/endpointconfig.js',
+            'vars': [{
+                'regex': r'PRODUCTION_HOSTNAME_THUMB = "(.+?)"',
+                'variable': 'thumb_server',
+            }, {
+                'regex': r'PRODUCTION_HOSTNAME_THUMB\s*\+\s*"(.+?)"',
+                'variable': 'thumb_server_path',
+            }]
+        }]
+
+        for data in datas:
+            temp = self._download_webpage(data['url'], msg_id)
+            for var in data['vars']:
+                val = self._search_regex(var['regex'], temp, msg_id)
+                if not val:
+                    raise ExtractorError('%s not found' % var['variable'])
+                self._player[var['variable']] = val
+
+    def _generate_token(self):
+        json = self._download_json(
+            'https://platform.wim.tv/wimtv-server/oauth/token', 'Token generation',
+            headers={'Authorization': 'Basic %s' % self._player['app_auth']},
+            data=urlencode_postdata({'grant_type': 'client_credentials'}))
+        token = json.get('access_token')
+        if not token:
+            raise ExtractorError('access token not generated')
+        return token
+
+    def _generate_thumbnail(self, thumb_id, width='720'):
+        if not thumb_id or not self._player.get('thumb_server'):
+            return None
+        if not self._player.get('thumb_server_path'):
+            self._player['thumb_server_path'] = ''
+        return '%s%s/asset/thumbnail/%s/%s' % (
+            self._player['thumb_server'],
+            self._player['thumb_server_path'],
+            thumb_id, width)
+
+    def _real_extract(self, url):
+        urlc = re.match(self._VALID_URL, url).groupdict()
+        video_id = urlc['id']
+        stream_type = is_live = None
+        if urlc['type'] in {'live', 'cast'}:
+            stream_type = urlc['type'] + '/channel'
+            is_live = True
+        else:
+            stream_type = 'vod'
+            is_live = False
+        token = self._generate_token()
+        json = self._download_json(
+            'https://platform.wim.tv/wimtv-server/api/public/%s/%s/play' % (
+                stream_type, video_id), video_id,
+            headers={'Authorization': 'Bearer %s' % token,
+                     'Content-Type': 'application/json'},
+            data=bytes('{}', 'utf-8'))
+
+        formats = []
+        for src in json.get('srcs') or []:
+            if src.get('mimeType') == 'application/x-mpegurl':
+                formats.extend(
+                    self._extract_m3u8_formats(
+                        src.get('uniqueStreamer'), video_id, 'mp4'))
+            if src.get('mimeType') == 'video/flash':
+                formats.append({
+                    'format_id': 'rtmp',
+                    'url': src.get('uniqueStreamer'),
+                    'ext': determine_ext(src.get('uniqueStreamer'), 'flv'),
+                    'rtmp_live': is_live,
+                })
+        json = json.get('resource')
+        thumb = self._generate_thumbnail(json.get('thumbnailId'))
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': json.get('title') or json.get('name'),
+            'duration': parse_duration(json.get('duration')),
+            'formats': formats,
+            'thumbnail': thumb,
+            'is_live': is_live,
+        }

yt_dlp/extractor/zdf.py

@@ -7,7 +7,9 @@ from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
     determine_ext,
+    float_or_none,
     int_or_none,
+    merge_dicts,
     NO_DEFAULT,
     orderedSet,
     parse_codecs,
@@ -21,61 +23,17 @@ from ..utils import (
 
 
 class ZDFBaseIE(InfoExtractor):
-    def _call_api(self, url, player, referrer, video_id, item):
-        return self._download_json(
-            url, video_id, 'Downloading JSON %s' % item,
-            headers={
-                'Referer': referrer,
-                'Api-Auth': 'Bearer %s' % player['apiToken'],
-            })
-
-    def _extract_player(self, webpage, video_id, fatal=True):
-        return self._parse_json(
-            self._search_regex(
-                r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
-                'player JSON', default='{}' if not fatal else NO_DEFAULT,
-                group='json'),
-            video_id)
-
-
-class ZDFIE(ZDFBaseIE):
-    IE_NAME = "ZDF-3sat"
-    _VALID_URL = r'https?://www\.(zdf|3sat)\.de/(?:[^/]+/)*(?P<id>[^/?]+)\.html'
-    _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
     _GEO_COUNTRIES = ['DE']
+    _QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
 
-    _TESTS = [{
+    def _call_api(self, url, video_id, item, api_token=None, referrer=None):
-        'url': 'https://www.3sat.de/wissen/wissenschaftsdoku/luxusgut-lebensraum-100.html',
+        headers = {}
-        'info_dict': {
+        if api_token:
-            'id': 'luxusgut-lebensraum-100',
+            headers['Api-Auth'] = 'Bearer %s' % api_token
-            'ext': 'mp4',
+        if referrer:
-            'title': 'Luxusgut Lebensraum',
+            headers['Referer'] = referrer
-            'description': 'md5:5c09b2f45ac3bc5233d1b50fc543d061',
+        return self._download_json(
-            'duration': 2601,
+            url, video_id, 'Downloading JSON %s' % item, headers=headers)
-            'timestamp': 1566497700,
-            'upload_date': '20190822',
-        }
-    }, {
-        'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
-        'info_dict': {
-            'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
-            'ext': 'mp4',
-            'title': 'Die Magie der Farben (2/2)',
-            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
-            'duration': 2615,
-            'timestamp': 1465021200,
-            'upload_date': '20160604',
-        },
-    }, {
-        'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
-        'only_matching': True,
-    }]
 
     @staticmethod
     def _extract_subtitles(src):
@@ -121,20 +79,11 @@ class ZDFIE(ZDFBaseIE):
             })
             formats.append(f)
 
-    def _extract_entry(self, url, player, content, video_id):
+    def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
-        title = content.get('title') or content['teaserHeadline']
-
-        t = content['mainVideoContent']['http://zdf.de/rels/target']
-
-        ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
-
-        if not ptmd_path:
-            ptmd_path = t[
-                'http://zdf.de/rels/streams/ptmd-template'].replace(
-                '{playerId}', 'ngplayer_2_4')
-
         ptmd = self._call_api(
-            urljoin(url, ptmd_path), player, url, video_id, 'metadata')
+            ptmd_url, video_id, 'metadata', api_token, referrer)
+
+        content_id = ptmd.get('basename') or ptmd_url.split('/')[-1]
 
         formats = []
         track_uris = set()
@@ -152,7 +101,7 @@ class ZDFIE(ZDFBaseIE):
                         continue
                     for track in tracks:
                         self._extract_format(
-                            video_id, formats, track_uris, {
+                            content_id, formats, track_uris, {
                                 'url': track.get('uri'),
                                 'type': f.get('type'),
                                 'mimeType': f.get('mimeType'),
@@ -161,6 +110,103 @@ class ZDFIE(ZDFBaseIE):
                             })
         self._sort_formats(formats)
 
+        duration = float_or_none(try_get(
+            ptmd, lambda x: x['attributes']['duration']['value']), scale=1000)
+
+        return {
+            'extractor_key': ZDFIE.ie_key(),
+            'id': content_id,
+            'duration': duration,
+            'formats': formats,
+            'subtitles': self._extract_subtitles(ptmd),
+        }
+
+    def _extract_player(self, webpage, video_id, fatal=True):
+        return self._parse_json(
+            self._search_regex(
+                r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
+                'player JSON', default='{}' if not fatal else NO_DEFAULT,
+                group='json'),
+            video_id)
+
+
+class ZDFIE(ZDFBaseIE):
+    _VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html
+        'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
+        'info_dict': {
+            'id': '210222_phx_nachgehakt_corona_protest',
+            'ext': 'mp4',
+            'title': 'Wohin führt der Protest in der Pandemie?',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
+            'duration': 1691,
+            'timestamp': 1613948400,
+            'upload_date': '20210221',
+        },
+    }, {
+        # Same as https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html
+        'url': 'https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
+        'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
+        },
+    }, {
+        'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
+        'info_dict': {
+            'id': '151025_magie_farben2_tex',
+            'ext': 'mp4',
+            'title': 'Die Magie der Farben (2/2)',
+            'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
+            'duration': 2615,
+            'timestamp': 1465021200,
+            'upload_date': '20160604',
+        },
+    }, {
+        # Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
+        'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.3sat.de/film/spielfilm/der-hauptmann-100.html
+        'url': 'https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
+        'only_matching': True,
+    }]
+
+    def _extract_entry(self, url, player, content, video_id):
+        title = content.get('title') or content['teaserHeadline']
+
+        t = content['mainVideoContent']['http://zdf.de/rels/target']
+
+        ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
+
+        if not ptmd_path:
+            ptmd_path = t[
+                'http://zdf.de/rels/streams/ptmd-template'].replace(
+                '{playerId}', 'ngplayer_2_4')
+
+        info = self._extract_ptmd(
+            urljoin(url, ptmd_path), video_id, player['apiToken'], url)
+
         thumbnails = []
         layouts = try_get(
             content, lambda x: x['teaserImageRef']['layouts'], dict)
@@ -181,33 +227,33 @@ class ZDFIE(ZDFBaseIE):
                     })
                 thumbnails.append(thumbnail)
 
-        return {
+        return merge_dicts(info, {
-            'id': video_id,
             'title': title,
             'description': content.get('leadParagraph') or content.get('teasertext'),
             'duration': int_or_none(t.get('duration')),
             'timestamp': unified_timestamp(content.get('editorialDate')),
             'thumbnails': thumbnails,
-            'subtitles': self._extract_subtitles(ptmd),
+        })
-            'formats': formats,
-        }
 
     def _extract_regular(self, url, player, video_id):
         content = self._call_api(
-            player['content'], player, url, video_id, 'content')
+            player['content'], video_id, 'content', player['apiToken'], url)
         return self._extract_entry(player['content'], player, content, video_id)
 
     def _extract_mobile(self, video_id):
-        document = self._download_json(
+        video = self._download_json(
             'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
-            video_id)['document']
+            video_id)
+
+        document = video['document']
 
         title = document['titel']
+        content_id = document['basename']
 
         formats = []
         format_urls = set()
         for f in document['formitaeten']:
-            self._extract_format(video_id, formats, format_urls, f)
+            self._extract_format(content_id, formats, format_urls, f)
         self._sort_formats(formats)
 
         thumbnails = []
@@ -225,12 +271,12 @@ class ZDFIE(ZDFBaseIE):
                     })
 
         return {
-            'id': video_id,
+            'id': content_id,
             'title': title,
             'description': document.get('beschreibung'),
             'duration': int_or_none(document.get('length')),
-            'timestamp': unified_timestamp(try_get(
+            'timestamp': unified_timestamp(document.get('date')) or unified_timestamp(
-                document, lambda x: x['meta']['editorialDate'], compat_str)),
+                try_get(video, lambda x: x['meta']['editorialDate'], compat_str)),
             'thumbnails': thumbnails,
             'subtitles': self._extract_subtitles(document),
             'formats': formats,

yt_dlp/extractor/zee5.py

@@ -4,6 +4,7 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_age_limit,
@@ -16,24 +17,34 @@ from ..utils import (
 
 
 class Zee5IE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?zee5\.com/[^#?]*/(?P<display_id>[-\w]+)/(?P<id>[-\d]+)'
+    _VALID_URL = r'''(?x)
+                     (?:
+                        zee5:|
+                        (?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
+                        (?:
+                            (?:tvshows|kids|zee5originals)(?:/[^#/?]+){3}
+                            |movies/[^#/?]+
+                        )/(?P<display_id>[^#/?]+)/
+                     )
+                     (?P<id>[^#/?]+)/?(?:$|[?#])
+                     '''
     _TESTS = [{
         'url': 'https://www.zee5.com/movies/details/krishna-the-birth/0-0-63098',
         'info_dict': {
-            "id": "0-0-63098",
+            'id': '0-0-63098',
-            "ext": "m3u8",
+            'ext': 'mp4',
-            "display_id": "krishna-the-birth",
+            'display_id': 'krishna-the-birth',
-            "title": "Krishna - The Birth",
+            'title': 'Krishna - The Birth',
-            "duration": 4368,
+            'duration': 4368,
-            "average_rating": 4,
+            'average_rating': 4,
-            "description": str,
+            'description': str,
-            "alt_title": "Krishna - The Birth",
+            'alt_title': 'Krishna - The Birth',
-            "uploader": "Zee Entertainment Enterprises Ltd",
+            'uploader': 'Zee Entertainment Enterprises Ltd',
-            "release_date": "20060101",
+            'release_date': '20060101',
-            "upload_date": "20060101",
+            'upload_date': '20060101',
-            "timestamp": 1136073600,
+            'timestamp': 1136073600,
-            "thumbnail": "https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg",
+            'thumbnail': 'https://akamaividz.zee5.com/resources/0-0-63098/list/270x152/0063098_list_80888170.jpg',
-            "tags": list
+            'tags': list
         },
         'params': {
             'format': 'bv',
@@ -41,37 +52,43 @@ class Zee5IE(InfoExtractor):
     }, {
         'url': 'https://zee5.com/tvshows/details/krishna-balram/0-6-1871/episode-1-the-test-of-bramha/0-1-233402',
         'info_dict': {
-            "id": "0-1-233402",
+            'id': '0-1-233402',
-            'ext': 'm3u8',
+            'ext': 'mp4',
-            "display_id": "episode-1-the-test-of-bramha",
+            'display_id': 'episode-1-the-test-of-bramha',
-            "title": "Episode 1 - The Test Of Bramha",
+            'title': 'Episode 1 - The Test Of Bramha',
-            "duration": 1336,
+            'duration': 1336,
-            "average_rating": 4,
+            'average_rating': 4,
-            "description": str,
+            'description': str,
-            "alt_title": "Episode 1 - The Test Of Bramha",
+            'alt_title': 'Episode 1 - The Test Of Bramha',
-            "uploader": "Green Gold",
+            'uploader': 'Green Gold',
-            "release_date": "20090101",
+            'release_date': '20090101',
-            "upload_date": "20090101",
+            'upload_date': '20090101',
-            "timestamp": 1230768000,
+            'timestamp': 1230768000,
-            "thumbnail": "https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg",
+            'thumbnail': 'https://akamaividz.zee5.com/resources/0-1-233402/list/270x152/01233402_list.jpg',
-            "series": "Krishna Balram",
+            'series': 'Krishna Balram',
-            "season_number": 1,
+            'season_number': 1,
-            "episode_number": 1,
+            'episode_number': 1,
-            "tags": list,
+            'tags': list,
         },
         'params': {
             'format': 'bv',
         },
+    }, {
+        'url': 'https://www.zee5.com/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730?country=IN',
+        'only_matching': True
+    }, {
+        'url': 'https://www.zee5.com/global/hi/tvshows/details/kundali-bhagya/0-6-366/kundali-bhagya-march-08-2021/0-1-manual_7g9jv1os7730',
+        'only_matching': True
     }]
 
     def _real_extract(self, url):
         video_id, display_id = re.match(self._VALID_URL, url).group('id', 'display_id')
         access_token_request = self._download_json(
             'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
-            video_id, note="Downloading access token")
+            video_id, note='Downloading access token')
         token_request = self._download_json(
             'https://useraction.zee5.com/tokennd',
-            video_id, note="Downloading video token")
+            video_id, note='Downloading video token')
         json_data = self._download_json(
             'https://gwapi.zee5.com/content/details/{}?translation=en&country=IN'.format(video_id),
             video_id, headers={'X-Access-Token': access_token_request['token']})
@@ -111,3 +128,78 @@ class Zee5IE(InfoExtractor):
             'episode_number': int_or_none(try_get(json_data, lambda x: x['index'])),
             'tags': try_get(json_data, lambda x: x['tags'], list)
         }
+
+
+class Zee5SeriesIE(InfoExtractor):
+    IE_NAME = 'zee5:series'
+    _VALID_URL = r'''(?x)
+                     (?:
+                        zee5:series:|
+                        (?:https?://)(?:www\.)?zee5\.com/(?:[^#?]+/)?
+                        (?:tvshows|kids|zee5originals)(?:/[^#/?]+){2}/
+                     )
+                     (?P<id>[^#/?]+)/?(?:$|[?#])
+                     '''
+    _TESTS = [{
+        'url': 'https://www.zee5.com/kids/kids-shows/krishna-balram/0-6-1871',
+        'playlist_mincount': 43,
+        'info_dict': {
+            'id': '0-6-1871',
+        },
+    }, {
+        'url': 'https://www.zee5.com/tvshows/details/bhabi-ji-ghar-par-hai/0-6-199',
+        'playlist_mincount': 1500,
+        'info_dict': {
+            'id': '0-6-199',
+        },
+    }, {
+        'url': 'https://www.zee5.com/tvshows/details/agent-raghav-crime-branch/0-6-965',
+        'playlist_mincount': 25,
+        'info_dict': {
+            'id': '0-6-965',
+        },
+    }, {
+        'url': 'https://www.zee5.com/ta/tvshows/details/nagabhairavi/0-6-3201',
+        'playlist_mincount': 3,
+        'info_dict': {
+            'id': '0-6-3201',
+        },
+    }, {
+        'url': 'https://www.zee5.com/global/hi/tvshows/details/khwaabon-ki-zamin-par/0-6-270',
+        'playlist_mincount': 150,
+        'info_dict': {
+            'id': '0-6-270',
+        },
+    }
+    ]
+
+    def _entries(self, show_id):
+        access_token_request = self._download_json(
+            'https://useraction.zee5.com/token/platform_tokens.php?platform_name=web_app',
+            show_id, note='Downloading access token')
+        headers = {
+            'X-Access-Token': access_token_request['token'],
+            'Referer': 'https://www.zee5.com/',
+        }
+        show_url = 'https://gwapi.zee5.com/content/tvshow/{}?translation=en&country=IN'.format(show_id)
+
+        page_num = 0
+        show_json = self._download_json(show_url, video_id=show_id, headers=headers)
+        for season in show_json.get('seasons') or []:
+            season_id = try_get(season, lambda x: x['id'], compat_str)
+            next_url = 'https://gwapi.zee5.com/content/tvshow/?season_id={}&type=episode&translation=en&country=IN&on_air=false&asset_subtype=tvshow&page=1&limit=100'.format(season_id)
+            while next_url:
+                page_num += 1
+                episodes_json = self._download_json(
+                    next_url, video_id=show_id, headers=headers,
+                    note='Downloading JSON metadata page %d' % page_num)
+                for episode in try_get(episodes_json, lambda x: x['episode'], list) or []:
+                    video_id = episode.get('id')
+                    yield self.url_result(
+                        'zee5:%s' % video_id,
+                        ie=Zee5IE.ie_key(), video_id=video_id)
+                next_url = url_or_none(episodes_json.get('next_episode_api'))
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        return self.playlist_result(self._entries(show_id), playlist_id=show_id)

yt_dlp/extractor/zingmp3.py

@@ -1,93 +1,94 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
-    update_url_query,
 )
 
 
-class ZingMp3BaseInfoExtractor(InfoExtractor):
+class ZingMp3BaseIE(InfoExtractor):
+    _VALID_URL_TMPL = r'https?://(?:mp3\.zing|zingmp3)\.vn/(?:%s)/[^/]+/(?P<id>\w+)\.html'
+    _GEO_COUNTRIES = ['VN']
 
-    def _extract_item(self, item, page_type, fatal=True):
+    def _extract_item(self, item, fatal):
-        error_message = item.get('msg')
+        item_id = item['id']
-        if error_message:
+        title = item.get('name') or item['title']
-            if not fatal:
-                return
-            raise ExtractorError(
-                '%s returned error: %s' % (self.IE_NAME, error_message),
-                expected=True)
 
         formats = []
-        for quality, source_url in zip(item.get('qualities') or item.get('quality', []), item.get('source_list') or item.get('source', [])):
+        for k, v in (item.get('source') or {}).items():
-            if not source_url or source_url == 'require vip':
+            if not v:
                 continue
-            if not re.match(r'https?://', source_url):
+            if k in ('mp4', 'hls'):
-                source_url = '//' + source_url
+                for res, video_url in v.items():
-            source_url = self._proto_relative_url(source_url, 'http:')
+                    if not video_url:
-            quality_num = int_or_none(quality)
+                        continue
-            f = {
+                    if k == 'hls':
-                'format_id': quality,
+                        formats.extend(self._extract_m3u8_formats(
-                'url': source_url,
+                            video_url, item_id, 'mp4',
-            }
+                            'm3u8_native', m3u8_id=k, fatal=False))
-            if page_type == 'video':
+                    elif k == 'mp4':
-                f.update({
+                        formats.append({
-                    'height': quality_num,
+                            'format_id': 'mp4-' + res,
-                    'ext': 'mp4',
+                            'url': video_url,
-                })
+                            'height': int_or_none(self._search_regex(
+                                r'^(\d+)p', res, 'resolution', default=None)),
+                        })
             else:
-                f.update({
+                formats.append({
-                    'abr': quality_num,
                     'ext': 'mp3',
+                    'format_id': k,
+                    'tbr': int_or_none(k),
+                    'url': self._proto_relative_url(v),
+                    'vcodec': 'none',
                 })
-            formats.append(f)
+        if not formats:
+            if not fatal:
+                return
+            msg = item['msg']
+            if msg == 'Sorry, this content is not available in your country.':
+                self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+            raise ExtractorError(msg, expected=True)
+        self._sort_formats(formats)
 
-        cover = item.get('cover')
+        subtitles = None
+        lyric = item.get('lyric')
+        if lyric:
+            subtitles = {
+                'origin': [{
+                    'url': lyric,
+                }],
+            }
+
+        album = item.get('album') or {}
 
         return {
-            'title': (item.get('name') or item.get('title')).strip(),
+            'id': item_id,
+            'title': title,
             'formats': formats,
-            'thumbnail': 'http:/' + cover if cover else None,
+            'thumbnail': item.get('thumbnail'),
-            'artist': item.get('artist'),
+            'subtitles': subtitles,
+            'duration': int_or_none(item.get('duration')),
+            'track': title,
+            'artist': item.get('artists_names'),
+            'album': album.get('name') or album.get('title'),
+            'album_artist': album.get('artists_names'),
         }
 
-    def _extract_player_json(self, player_json_url, id, page_type, playlist_title=None):
+    def _real_extract(self, url):
-        player_json = self._download_json(player_json_url, id, 'Downloading Player JSON')
+        page_id = self._match_id(url)
-        items = player_json['data']
+        webpage = self._download_webpage(
-        if 'item' in items:
+            url.replace('://zingmp3.vn/', '://mp3.zing.vn/'),
-            items = items['item']
+            page_id, query={'play_song': 1})
-
+        data_path = self._search_regex(
-        if len(items) == 1:
+            r'data-xml="([^"]+)', webpage, 'data path')
-            # one single song
+        return self._process_data(self._download_json(
-            data = self._extract_item(items[0], page_type)
+            'https://mp3.zing.vn/xhr' + data_path, page_id)['data'])
-            data['id'] = id
-
-            return data
-        else:
-            # playlist of songs
-            entries = []
-
-            for i, item in enumerate(items, 1):
-                entry = self._extract_item(item, page_type, fatal=False)
-                if not entry:
-                    continue
-                entry['id'] = '%s-%d' % (id, i)
-                entries.append(entry)
-
-            return {
-                '_type': 'playlist',
-                'id': id,
-                'title': playlist_title,
-                'entries': entries,
-            }
 
 
-class ZingMp3IE(ZingMp3BaseInfoExtractor):
+class ZingMp3IE(ZingMp3BaseIE):
-    _VALID_URL = r'https?://mp3\.zing\.vn/(?:bai-hat|album|playlist|video-clip)/[^/]+/(?P<id>\w+)\.html'
+    _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'bai-hat|video-clip'
     _TESTS = [{
         'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
         'md5': 'ead7ae13693b3205cbc89536a077daed',
@@ -95,49 +96,66 @@ class ZingMp3IE(ZingMp3BaseInfoExtractor):
             'id': 'ZWZB9WAB',
             'title': 'Xa Mãi Xa',
             'ext': 'mp3',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'subtitles': {
+                'origin': [{
+                    'ext': 'lrc',
+                }]
+            },
+            'duration': 255,
+            'track': 'Xa Mãi Xa',
+            'artist': 'Bảo Thy',
+            'album': 'Special Album',
+            'album_artist': 'Bảo Thy',
         },
     }, {
-        'url': 'http://mp3.zing.vn/video-clip/Let-It-Go-Frozen-OST-Sungha-Jung/ZW6BAEA0.html',
+        'url': 'https://mp3.zing.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
-        'md5': '870295a9cd8045c0e15663565902618d',
+        'md5': 'e9c972b693aa88301ef981c8151c4343',
         'info_dict': {
-            'id': 'ZW6BAEA0',
+            'id': 'ZO8ZF7C7',
-            'title': 'Let It Go (Frozen OST)',
+            'title': 'Sương Hoa Đưa Lối',
             'ext': 'mp4',
+            'thumbnail': r're:^https?://.+\.jpg',
+            'duration': 207,
+            'track': 'Sương Hoa Đưa Lối',
+            'artist': 'K-ICM, RYO',
         },
     }, {
-        'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
-        'info_dict': {
-            '_type': 'playlist',
-            'id': 'ZWZBWDAF',
-            'title': 'Lâu Đài Tình Ái - Bằng Kiều,Minh Tuyết | Album 320 lossless',
-        },
-        'playlist_count': 10,
-        'skip': 'removed at the request of the owner',
-    }, {
-        'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
         'only_matching': True,
     }]
     IE_NAME = 'zingmp3'
     IE_DESC = 'mp3.zing.vn'
 
-    def _real_extract(self, url):
+    def _process_data(self, data):
-        page_id = self._match_id(url)
+        return self._extract_item(data, True)
 
-        webpage = self._download_webpage(url, page_id)
 
-        player_json_url = self._search_regex([
+class ZingMp3AlbumIE(ZingMp3BaseIE):
-            r'data-xml="([^"]+)',
+    _VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
-            r'&amp;xmlURL=([^&]+)&'
+    _TESTS = [{
-        ], webpage, 'player xml url')
+        'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'info_dict': {
+            '_type': 'playlist',
+            'id': 'ZWZBWDAF',
+            'title': 'Lâu Đài Tình Ái',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
+        'only_matching': True,
+    }, {
+        'url': 'https://zingmp3.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
+        'only_matching': True,
+    }]
+    IE_NAME = 'zingmp3:album'
 
-        playlist_title = None
+    def _process_data(self, data):
-        page_type = self._search_regex(r'/(?:html5)?xml/([^/-]+)', player_json_url, 'page type')
+        def entries():
-        if page_type == 'video':
+            for item in (data.get('items') or []):
-            player_json_url = update_url_query(player_json_url, {'format': 'json'})
+                entry = self._extract_item(item, False)
-        else:
+                if entry:
-            player_json_url = player_json_url.replace('/xml/', '/html5xml/')
+                    yield entry
-            if page_type == 'album':
+        info = data.get('info') or {}
-                playlist_title = self._og_search_title(webpage)
+        return self.playlist_result(
-
+            entries(), info.get('id'), info.get('name') or info.get('title'))
-        return self._extract_player_json(player_json_url, page_id, page_type, playlist_title)

yt_dlp/extractor/zoom.py

@@ -1,82 +1,68 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
-    url_or_none,
+    js_to_json,
     parse_filesize,
-    urlencode_postdata
+    urlencode_postdata,
 )
 
 
 class ZoomIE(InfoExtractor):
     IE_NAME = 'zoom'
-    _VALID_URL = r'https://(?:.*).?zoom.us/rec(?:ording)?/(play|share)/(?P<id>[A-Za-z0-9\-_.]+)'
+    _VALID_URL = r'(?P<base_url>https?://(?:[^.]+\.)?zoom.us/)rec(?:ording)?/(?:play|share)/(?P<id>[A-Za-z0-9_.-]+)'
-
     _TEST = {
-        'url': 'https://zoom.us/recording/play/SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK',
+        'url': 'https://economist.zoom.us/rec/play/dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
+        'md5': 'ab445e8c911fddc4f9adc842c2c5d434',
         'info_dict': {
-            'md5': '031a5b379f1547a8b29c5c4c837dccf2',
+            'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
-            'title': "GAZ Transformational Tuesdays W/ Landon & Stapes",
+            'ext': 'mp4',
-            'id': "SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK",
+            'title': 'China\'s "two sessions" and the new five-year plan',
-            'ext': "mp4"
         }
     }
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        base_url, play_id = re.match(self._VALID_URL, url).groups()
-        webpage = self._download_webpage(url, display_id)
+        webpage = self._download_webpage(url, play_id)
 
-        password_protected = self._search_regex(r'<form[^>]+?id="(password_form)"', webpage, 'password field', fatal=False, default=None)
+        try:
-        if password_protected is not None:
+            form = self._form_hidden_inputs('password_form', webpage)
-            self._verify_video_password(url, display_id, webpage)
+        except ExtractorError:
-            webpage = self._download_webpage(url, display_id)
+            form = None
+        if form:
+            password = self._downloader.params.get('videopassword')
+            if not password:
+                raise ExtractorError(
+                    'This video is protected by a passcode, use the --video-password option', expected=True)
+            is_meeting = form.get('useWhichPasswd') == 'meeting'
+            validation = self._download_json(
+                base_url + 'rec/validate%s_passwd' % ('_meet' if is_meeting else ''),
+                play_id, 'Validating passcode', 'Wrong passcode', data=urlencode_postdata({
+                    'id': form[('meet' if is_meeting else 'file') + 'Id'],
+                    'passwd': password,
+                    'action': form.get('action'),
+                }))
+            if not validation.get('status'):
+                raise ExtractorError(validation['errorMessage'], expected=True)
+            webpage = self._download_webpage(url, play_id)
 
-        video_url = self._search_regex(r"viewMp4Url: \'(.*)\'", webpage, 'video url')
+        data = self._parse_json(self._search_regex(
-        title = self._html_search_regex([r"topic: \"(.*)\",", r"<title>(.*) - Zoom</title>"], webpage, 'title')
+            r'(?s)window\.__data__\s*=\s*({.+?});',
-        viewResolvtionsWidth = self._search_regex(r"viewResolvtionsWidth: (\d*)", webpage, 'res width', fatal=False)
+            webpage, 'data'), play_id, js_to_json)
-        viewResolvtionsHeight = self._search_regex(r"viewResolvtionsHeight: (\d*)", webpage, 'res height', fatal=False)
-        fileSize = parse_filesize(self._search_regex(r"fileSize: \'(.+)\'", webpage, 'fileSize', fatal=False))
-
-        urlprefix = url.split("zoom.us")[0] + "zoom.us/"
-
-        formats = []
-        formats.append({
-            'url': url_or_none(video_url),
-            'width': int_or_none(viewResolvtionsWidth),
-            'height': int_or_none(viewResolvtionsHeight),
-            'http_headers': {'Accept': 'video/webm,video/ogg,video/*;q=0.9,application/ogg;q=0.7,audio/*;q=0.6,*/*;q=0.5',
-                             'Referer': urlprefix},
-            'ext': "mp4",
-            'filesize_approx': int_or_none(fileSize)
-        })
-        self._sort_formats(formats)
 
         return {
-            'id': display_id,
+            'id': play_id,
-            'title': title,
+            'title': data['topic'],
-            'formats': formats
+            'url': data['viewMp4Url'],
+            'width': int_or_none(data.get('viewResolvtionsWidth')),
+            'height': int_or_none(data.get('viewResolvtionsHeight')),
+            'http_headers': {
+                'Referer': base_url,
+            },
+            'filesize_approx': parse_filesize(data.get('fileSize')),
         }
-
-    def _verify_video_password(self, url, video_id, webpage):
-        password = self._downloader.params.get('videopassword')
-        if password is None:
-            raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
-        meetId = self._search_regex(r'<input[^>]+?id="meetId" value="([^\"]+)"', webpage, 'meetId')
-        data = urlencode_postdata({
-            'id': meetId,
-            'passwd': password,
-            'action': "viewdetailedpage",
-            'recaptcha': ""
-        })
-        validation_url = url.split("zoom.us")[0] + "zoom.us/rec/validate_meet_passwd"
-        validation_response = self._download_json(
-            validation_url, video_id,
-            note='Validating Password...',
-            errnote='Wrong password?',
-            data=data)
-
-        if validation_response['errorCode'] != 0:
-            raise ExtractorError('Login failed, %s said: %r' % (self.IE_NAME, validation_response['errorMessage']))

yt_dlp/options.py

@@ -214,12 +214,11 @@ def parseOpts(overrideArguments=None):
         help='Mark videos watched (YouTube only)')
     general.add_option(
         '--no-mark-watched',
-        action='store_false', dest='mark_watched', default=False,
+        action='store_false', dest='mark_watched',
-        help='Do not mark videos watched')
+        help='Do not mark videos watched (default)')
     general.add_option(
         '--no-colors',
-        action='store_true', dest='no_color',
+        action='store_true', dest='no_color', default=False,
-        default=False,
         help='Do not emit color codes in output')
 
     network = optparse.OptionGroup(parser, 'Network Options')
@@ -534,11 +533,11 @@ def parseOpts(overrideArguments=None):
     subtitles.add_option(
         '--write-auto-subs', '--write-automatic-subs',
         action='store_true', dest='writeautomaticsub', default=False,
-        help='Write automatically generated subtitle file (YouTube only)')
+        help='Write automatically generated subtitle file (Alias: --write-automatic-subs)')
     subtitles.add_option(
         '--no-write-auto-subs', '--no-write-automatic-subs',
         action='store_false', dest='writeautomaticsub', default=False,
-        help='Do not write automatically generated subtitle file (default)')
+        help='Do not write auto-generated subtitles (default) (Alias: --no-write-automatic-subs)')
     subtitles.add_option(
         '--all-subs',
         action='store_true', dest='allsubtitles', default=False,
@@ -552,12 +551,16 @@ def parseOpts(overrideArguments=None):
         action='store', dest='subtitlesformat', metavar='FORMAT', default='best',
         help='Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"')
     subtitles.add_option(
-        '--sub-lang', '--sub-langs', '--srt-lang',
+        '--sub-langs', '--srt-langs',
         action='callback', dest='subtitleslangs', metavar='LANGS', type='str',
         default=[], callback=_comma_separated_values_options_callback,
         help='Languages of the subtitles to download (optional) separated by commas, use --list-subs for available language tags')
 
     downloader = optparse.OptionGroup(parser, 'Download Options')
+    downloader.add_option(
+        '-N', '--concurrent-fragments',
+        dest='concurrent_fragment_downloads', metavar='N', default=1, type=int,
+        help='Number of fragments to download concurrently (default is %default)')
     downloader.add_option(
         '-r', '--limit-rate', '--rate-limit',
         dest='ratelimit', metavar='RATE',
@@ -676,7 +679,7 @@ def parseOpts(overrideArguments=None):
     workarounds.add_option(
         '--prefer-insecure', '--prefer-unsecure',
         action='store_true', dest='prefer_insecure',
-        help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)')
+        help='Use an unencrypted connection to retrieve information about the video (Currently supported only for YouTube)')
     workarounds.add_option(
         '--user-agent',
         metavar='UA', dest='user_agent',
@@ -704,17 +707,13 @@ def parseOpts(overrideArguments=None):
         '--sleep-interval', '--min-sleep-interval', metavar='SECONDS',
         dest='sleep_interval', type=float,
         help=(
-            'Number of seconds to sleep before each download when used alone '
+            'Number of seconds to sleep before each download. '
-            'or a lower bound of a range for randomized sleep before each download '
+            'This is the minimum time to sleep when used along with --max-sleep-interval '
-            '(minimum possible number of seconds to sleep) when used along with '
+            '(Alias: --min-sleep-interval)'))
-            '--max-sleep-interval'))
     workarounds.add_option(
         '--max-sleep-interval', metavar='SECONDS',
         dest='max_sleep_interval', type=float,
-        help=(
+        help='Maximum number of seconds to sleep. Can only be used along with --min-sleep-interval')
-            'Upper bound of a range for randomized sleep before each download '
-            '(maximum possible number of seconds to sleep). Must only be used '
-            'along with --min-sleep-interval'))
     workarounds.add_option(
         '--sleep-subtitles', metavar='SECONDS',
         dest='sleep_interval_subtitles', default=0, type=int,
@@ -736,7 +735,7 @@ def parseOpts(overrideArguments=None):
     verbosity.add_option(
         '--skip-download', '--no-download',
         action='store_true', dest='skip_download', default=False,
-        help='Do not download the video')
+        help='Do not download the video but write all related files (Alias: --no-download)')
     verbosity.add_option(
         '-g', '--get-url',
         action='store_true', dest='geturl', default=False,
@@ -863,7 +862,7 @@ def parseOpts(overrideArguments=None):
         callback_kwargs={
             'allowed_keys': '|'.join(OUTTMPL_TYPES.keys()),
             'default_key': 'default', 'process': lambda x: x.strip()},
-        help='Output filename template, see "OUTPUT TEMPLATE" for details')
+        help='Output filename template; see "OUTPUT TEMPLATE" for details')
     filesystem.add_option(
         '--output-na-placeholder',
         dest='outtmpl_na_placeholder', metavar='TEXT', default='NA',
@@ -979,9 +978,17 @@ def parseOpts(overrideArguments=None):
     filesystem.add_option(
         '--no-write-playlist-metafiles',
         action='store_false', dest='allow_playlist_files',
+        help='Do not write playlist metadata when using --write-info-json, --write-description etc.')
+    filesystem.add_option(
+        '--clean-infojson',
+        action='store_true', dest='clean_infojson', default=True,
         help=(
-            'Do not write playlist metadata when using '
+            'Remove some private fields such as filenames from the infojson. '
-            '--write-info-json, --write-description etc.'))
+            'Note that it could still contain some personal information (default)'))
+    filesystem.add_option(
+        '--no-clean-infojson',
+        action='store_false', dest='clean_infojson',
+        help='Write all fields to the infojson')
     filesystem.add_option(
         '--get-comments',
         action='store_true', dest='getcomments', default=False,
@@ -1083,12 +1090,12 @@ def parseOpts(overrideArguments=None):
             'Specify the postprocessor/executable name and the arguments separated by a colon ":" '
             'to give the argument to the specified postprocessor/executable. Supported postprocessors are: '
             'SponSkrub, ExtractAudio, VideoRemuxer, VideoConvertor, EmbedSubtitle, Metadata, Merger, '
-            'FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor and EmbedThumbnail. '
+            'FixupStretched, FixupM4a, FixupM3u8, SubtitlesConvertor, EmbedThumbnail and SplitChapters. '
             'The supported executables are: SponSkrub, FFmpeg, FFprobe, and AtomicParsley. '
             'You can also specify "PP+EXE:ARGS" to give the arguments to the specified executable '
             'only when being used by the specified postprocessor. Additionally, for ffmpeg/ffprobe, '
-            'a number can be appended to the exe name seperated by "_i" to pass the argument '
+            '"_i"/"_o" can be appended to the prefix optionally followed by a number to pass the argument '
-            'before the specified input file. Eg: --ppa "Merger+ffmpeg_i1:-v quiet". '
+            'before the specified input/output file. Eg: --ppa "Merger+ffmpeg_i1:-v quiet". '
             'You can use this option multiple times to give different arguments to different '
             'postprocessors. (Alias: --ppa)'))
     postproc.add_option(
@@ -1137,24 +1144,17 @@ def parseOpts(overrideArguments=None):
         help=optparse.SUPPRESS_HELP)
     postproc.add_option(
         '--parse-metadata',
-        metavar='FIELD:FORMAT', dest='metafromfield', action='append',
+        metavar='FROM:TO', dest='metafromfield', action='append',
         help=(
-            'Parse additional metadata like title/artist from other fields. '
+            'Parse additional metadata like title/artist from other fields; '
-            'Give field name to extract data from, and format of the field seperated by a ":". '
+            'see "MODIFYING METADATA" for details'))
-            'Either regular expression with named capture groups or a '
-            'similar syntax to the output template can also be used. '
-            'The parsed parameters replace any existing values and can be use in output template. '
-            'This option can be used multiple times. '
-            'Example: --parse-metadata "title:%(artist)s - %(title)s" matches a title like '
-            '"Coldplay - Paradise". '
-            'Example (regex): --parse-metadata "description:Artist - (?P<artist>.+?)"'))
     postproc.add_option(
         '--xattrs',
         action='store_true', dest='xattrs', default=False,
         help='Write metadata to the video file\'s xattrs (using dublin core and xdg standards)')
     postproc.add_option(
         '--fixup',
-        metavar='POLICY', dest='fixup', default='detect_or_warn',
+        metavar='POLICY', dest='fixup', default=None,
         help=(
             'Automatically correct known faults of the file. '
             'One of never (do nothing), warn (only emit a warning), '
@@ -1176,9 +1176,20 @@ def parseOpts(overrideArguments=None):
         metavar='CMD', dest='exec_cmd',
         help='Execute a command on the file after downloading and post-processing, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'')
     postproc.add_option(
-        '--convert-subs', '--convert-subtitles',
+        '--convert-subs', '--convert-sub', '--convert-subtitles',
         metavar='FORMAT', dest='convertsubtitles', default=None,
-        help='Convert the subtitles to other format (currently supported: srt|ass|vtt|lrc)')
+        help='Convert the subtitles to another format (currently supported: srt|ass|vtt|lrc) (Alias: --convert-subtitles)')
+    postproc.add_option(
+        '--split-chapters', '--split-tracks',
+        dest='split_chapters', action='store_true', default=False,
+        help=(
+            'Split video into multiple files based on internal chapters. '
+            'The "chapter:" prefix can be used with "--paths" and "--output" to '
+            'set the output filename for the split files. See "OUTPUT TEMPLATE" for details'))
+    postproc.add_option(
+        '--no-split-chapters', '--no-split-tracks',
+        dest='split_chapters', action='store_false',
+        help='Do not split video based on chapters (default)')
 
     sponskrub = optparse.OptionGroup(parser, 'SponSkrub (SponsorBlock) Options', description=(
         'SponSkrub (https://github.com/yt-dlp/SponSkrub) is a utility to mark/remove sponsor segments '
@@ -1220,7 +1231,7 @@ def parseOpts(overrideArguments=None):
     extractor = optparse.OptionGroup(parser, 'Extractor Options')
     extractor.add_option(
         '--extractor-retries',
-        dest='extractor_retries', metavar='RETRIES', default=10,
+        dest='extractor_retries', metavar='RETRIES', default=3,
         help='Number of retries for known extractor errors (default is %default), or "infinite"')
     extractor.add_option(
         '--allow-dynamic-mpd', '--no-ignore-dynamic-mpd',

yt_dlp/postprocessor/__init__.py

@@ -13,6 +13,7 @@ from .ffmpeg import (
     FFmpegVideoConvertorPP,
     FFmpegVideoRemuxerPP,
     FFmpegSubtitlesConvertorPP,
+    FFmpegSplitChaptersPP,
 )
 from .xattrpp import XAttrMetadataPP
 from .execafterdownload import ExecAfterDownloadPP
@@ -31,6 +32,7 @@ __all__ = [
     'ExecAfterDownloadPP',
     'FFmpegEmbedSubtitlePP',
     'FFmpegExtractAudioPP',
+    'FFmpegSplitChaptersPP',
     'FFmpegFixupM3u8PP',
     'FFmpegFixupM4aPP',
     'FFmpegFixupStretchedPP',

yt_dlp/postprocessor/common.py

@@ -91,10 +91,18 @@ class PostProcessor(object):
         except Exception:
             self.report_warning(errnote)
 
-    def _configuration_args(self, *args, **kwargs):
+    def _configuration_args(self, exe, keys=None, default=[], use_compat=True):
+        pp_key = self.pp_key().lower()
+        exe = exe.lower()
+        root_key = exe if pp_key == exe else '%s+%s' % (pp_key, exe)
+        keys = ['%s%s' % (root_key, k) for k in (keys or [''])]
+        if root_key in keys:
+            keys += [root_key] + ([] if pp_key == exe else [(self.pp_key(), exe)]) + ['default']
+        else:
+            use_compat = False
         return cli_configuration_args(
             self._downloader.params.get('postprocessor_args'),
-            self.pp_key().lower(), *args, **kwargs)
+            keys, default, use_compat)
 
 
 class AudioConversionError(PostProcessingError):

yt_dlp/postprocessor/embedthumbnail.py

@@ -47,7 +47,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             self.to_screen('There aren\'t any thumbnails to embed')
             return [], info
 
-        original_thumbnail = thumbnail_filename = info['thumbnails'][-1]['filename']
+        initial_thumbnail = original_thumbnail = thumbnail_filename = info['thumbnails'][-1]['filepath']
 
         if not os.path.exists(encodeFilename(thumbnail_filename)):
             self.report_warning('Skipping embedding the thumbnail because the file is missing.')
@@ -65,6 +65,8 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             if thumbnail_ext != 'webp' and is_webp(thumbnail_filename):
                 self.to_screen('Correcting extension to webp and escaping path for thumbnail "%s"' % thumbnail_filename)
                 thumbnail_webp_filename = replace_extension(thumbnail_filename, 'webp')
+                if os.path.exists(thumbnail_webp_filename):
+                    os.remove(thumbnail_webp_filename)
                 os.rename(encodeFilename(thumbnail_filename), encodeFilename(thumbnail_webp_filename))
                 original_thumbnail = thumbnail_filename = thumbnail_webp_filename
                 thumbnail_ext = 'webp'
@@ -85,6 +87,8 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             thumbnail_filename = thumbnail_jpg_filename
             thumbnail_ext = 'jpg'
 
+        mtime = os.stat(encodeFilename(filename)).st_mtime
+
         success = True
         if info['ext'] == 'mp3':
             options = [
@@ -131,7 +135,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
                     x for x in ['AtomicParsley', 'atomicparsley']
                     if check_executable(x, ['-v'])), None)
                 if atomicparsley is None:
-                    raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
+                    raise EmbedThumbnailPPError('AtomicParsley was not found. Please install')
 
                 cmd = [encodeFilename(atomicparsley, True),
                        encodeFilename(filename, True),
@@ -139,7 +143,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
                        encodeFilename(thumbnail_filename, True),
                        encodeArgument('-o'),
                        encodeFilename(temp_filename, True)]
-                cmd += [encodeArgument(o) for o in self._configuration_args(exe='AtomicParsley')]
+                cmd += [encodeArgument(o) for o in self._configuration_args('AtomicParsley')]
 
                 self.to_screen('Adding thumbnail to "%s"' % filename)
                 self.write_debug('AtomicParsley command line: %s' % shell_quote(cmd))
@@ -187,10 +191,13 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
             os.remove(encodeFilename(filename))
             os.rename(encodeFilename(temp_filename), encodeFilename(filename))
 
+        self.try_utime(filename, mtime, mtime)
+
         files_to_delete = [thumbnail_filename]
         if self._already_have_thumbnail:
             info['__files_to_move'][original_thumbnail] = replace_extension(
-                info['__thumbnail_filename'], os.path.splitext(original_thumbnail)[1][1:])
+                info['__files_to_move'][initial_thumbnail],
+                os.path.splitext(original_thumbnail)[1][1:])
             if original_thumbnail == thumbnail_filename:
                 files_to_delete = []
         elif original_thumbnail != thumbnail_filename:

yt_dlp/postprocessor/ffmpeg.py

@@ -10,6 +10,7 @@ import json
 
 from .common import AudioConversionError, PostProcessor
 
+from ..compat import compat_str, compat_numeric_types
 from ..utils import (
     encodeArgument,
     encodeFilename,
@@ -18,7 +19,6 @@ from ..utils import (
     PostProcessingError,
     prepend_extension,
     shell_quote,
-    subtitles_filename,
     dfxp2srt,
     ISO639Utils,
     process_communicate_or_kill,
@@ -61,7 +61,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def check_version(self):
         if not self.available:
-            raise FFmpegPostProcessorError('ffmpeg not found. Please install')
+            raise FFmpegPostProcessorError('ffmpeg not found. Please install or provide the path using --ffmpeg-location')
 
         required_version = '10-0' if self.basename == 'avconv' else '1.0'
         if is_outdated_version(
@@ -165,7 +165,7 @@ class FFmpegPostProcessor(PostProcessor):
 
     def get_audio_codec(self, path):
         if not self.probe_available and not self.available:
-            raise PostProcessingError('ffprobe and ffmpeg not found. Please install')
+            raise PostProcessingError('ffprobe and ffmpeg not found. Please install or provide the path using --ffmpeg-location')
         try:
             if self.probe_available:
                 cmd = [
@@ -207,7 +207,7 @@ class FFmpegPostProcessor(PostProcessor):
         if self.probe_basename != 'ffprobe':
             if self.probe_available:
                 self.report_warning('Only ffprobe is supported for metadata extraction')
-            raise PostProcessingError('ffprobe not found. Please install.')
+            raise PostProcessingError('ffprobe not found. Please install or provide the path using --ffmpeg-location')
         self.check_version()
 
         cmd = [
@@ -234,25 +234,35 @@ class FFmpegPostProcessor(PostProcessor):
         return num, len(streams)
 
     def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
+        return self.real_run_ffmpeg(
+            [(path, []) for path in input_paths],
+            [(out_path, opts)])
+
+    def real_run_ffmpeg(self, input_path_opts, output_path_opts):
         self.check_version()
 
         oldest_mtime = min(
-            os.stat(encodeFilename(path)).st_mtime for path in input_paths)
+            os.stat(encodeFilename(path)).st_mtime for path, _ in input_path_opts)
 
         cmd = [encodeFilename(self.executable, True), encodeArgument('-y')]
         # avconv does not have repeat option
         if self.basename == 'ffmpeg':
             cmd += [encodeArgument('-loglevel'), encodeArgument('repeat+info')]
 
-        def make_args(file, pre=[], post=[], *args, **kwargs):
+        def make_args(file, args, name, number):
-            args = pre + self._configuration_args(*args, **kwargs) + post
+            keys = ['_%s%d' % (name, number), '_%s' % name]
+            if name == 'o' and number == 1:
+                keys.append('')
+            args += self._configuration_args(self.basename, keys)
+            if name == 'i':
+                args.append('-i')
             return (
-                [encodeArgument(o) for o in args]
+                [encodeArgument(arg) for arg in args]
                 + [encodeFilename(self._ffmpeg_filename_argument(file), True)])
 
-        for i, path in enumerate(input_paths):
+        for arg_type, path_opts in (('i', input_path_opts), ('o', output_path_opts)):
-            cmd += make_args(path, post=['-i'], exe='%s_i%d' % (self.basename, i + 1), use_default_arg=False)
+            cmd += [arg for i, o in enumerate(path_opts)
-        cmd += make_args(out_path, pre=opts, exe=self.basename)
+                    for arg in make_args(o[0], o[1], arg_type, i + 1)]
 
         self.write_debug('ffmpeg command line: %s' % shell_quote(cmd))
         p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
@@ -262,7 +272,8 @@ class FFmpegPostProcessor(PostProcessor):
             if self.get_param('verbose', False):
                 self.report_error(stderr)
             raise FFmpegPostProcessorError(stderr.split('\n')[-1])
-        self.try_utime(out_path, oldest_mtime, oldest_mtime)
+        for out_path, _ in output_path_opts:
+            self.try_utime(out_path, oldest_mtime, oldest_mtime)
         return stderr.decode('utf-8', 'replace')
 
     def run_ffmpeg(self, path, out_path, opts):
@@ -474,7 +485,7 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
                 self.report_warning('JSON subtitles cannot be embedded')
             elif ext != 'webm' or ext == 'webm' and sub_ext == 'vtt':
                 sub_langs.append(lang)
-                sub_filenames.append(subtitles_filename(filename, lang, sub_ext, ext))
+                sub_filenames.append(sub_info['filepath'])
             else:
                 if not webm_vtt_warn and ext == 'webm' and sub_ext != 'vtt':
                     webm_vtt_warn = True
@@ -519,6 +530,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         metadata = {}
 
         def add(meta_list, info_list=None):
+            if not meta_list:
+                return
             if not info_list:
                 info_list = meta_list
             if not isinstance(meta_list, (list, tuple)):
@@ -526,7 +539,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
             if not isinstance(info_list, (list, tuple)):
                 info_list = (info_list,)
             for info_f in info_list:
-                if info.get(info_f) is not None:
+                if isinstance(info.get(info_f), (compat_str, compat_numeric_types)):
                     for meta_f in meta_list:
                         metadata[meta_f] = info[info_f]
                     break
@@ -539,8 +552,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
 
         add('title', ('track', 'title'))
         add('date', 'upload_date')
-        add(('description', 'comment'), 'description')
+        add(('description', 'synopsis'), 'description')
-        add('purl', 'webpage_url')
+        add(('purl', 'comment'), 'webpage_url')
         add('track', 'track_number')
         add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
         add('genre')
@@ -552,6 +565,10 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         add('episode_id', ('episode', 'episode_id'))
         add('episode_sort', 'episode_number')
 
+        prefix = 'meta_'
+        for key in filter(lambda k: k.startswith(prefix), info.keys()):
+            add(key[len(prefix):], key)
+
         if not metadata:
             self.to_screen('There isn\'t any metadata to add')
             return [], info
@@ -566,7 +583,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
         else:
             options.extend(['-c', 'copy'])
 
-        for (name, value) in metadata.items():
+        for name, value in metadata.items():
             options.extend(['-metadata', '%s=%s' % (name, value)])
 
         chapters = info.get('chapters', [])
@@ -700,7 +717,6 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
 
     def run(self, info):
         subs = info.get('requested_subtitles')
-        filename = info['filepath']
         new_ext = self.format
         new_format = new_ext
         if new_format == 'vtt':
@@ -720,9 +736,9 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
                     'You have requested to convert json subtitles into another format, '
                     'which is currently not possible')
                 continue
-            old_file = subtitles_filename(filename, lang, ext, info.get('ext'))
+            old_file = sub['filepath']
             sub_filenames.append(old_file)
-            new_file = subtitles_filename(filename, lang, new_ext, info.get('ext'))
+            new_file = replace_extension(old_file, new_ext)
 
             if ext in ('dfxp', 'ttml', 'tt'):
                 self.report_warning(
@@ -730,7 +746,7 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
                     'which results in style information loss')
 
                 dfxp_file = old_file
-                srt_file = subtitles_filename(filename, lang, 'srt', info.get('ext'))
+                srt_file = replace_extension(old_file, 'srt')
 
                 with open(dfxp_file, 'rb') as f:
                     srt_data = dfxp2srt(f.read())
@@ -741,7 +757,8 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
 
                 subs[lang] = {
                     'ext': 'srt',
-                    'data': srt_data
+                    'data': srt_data,
+                    'filepath': srt_file,
                 }
 
                 if new_ext == 'srt':
@@ -755,6 +772,47 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
                 subs[lang] = {
                     'ext': new_ext,
                     'data': f.read(),
+                    'filepath': new_file,
                 }
 
+            info['__files_to_move'][new_file] = replace_extension(
+                info['__files_to_move'][old_file], new_ext)
+
         return sub_filenames, info
+
+
+class FFmpegSplitChaptersPP(FFmpegPostProcessor):
+
+    def _prepare_filename(self, number, chapter, info):
+        info = info.copy()
+        info.update({
+            'section_number': number,
+            'section_title': chapter.get('title'),
+            'section_start': chapter.get('start_time'),
+            'section_end': chapter.get('end_time'),
+        })
+        return self._downloader.prepare_filename(info, 'chapter')
+
+    def _ffmpeg_args_for_chapter(self, number, chapter, info):
+        destination = self._prepare_filename(number, chapter, info)
+        if not self._downloader._ensure_dir_exists(encodeFilename(destination)):
+            return
+
+        chapter['filepath'] = destination
+        self.to_screen('Chapter %03d; Destination: %s' % (number, destination))
+        return (
+            destination,
+            ['-ss', compat_str(chapter['start_time']),
+             '-t', compat_str(chapter['end_time'] - chapter['start_time'])])
+
+    def run(self, info):
+        chapters = info.get('chapters') or []
+        if not chapters:
+            self.report_warning('Chapter information is unavailable')
+            return [], info
+
+        self.to_screen('Splitting video by chapters; %d chapters found' % len(chapters))
+        for idx, chapter in enumerate(chapters):
+            destination, opts = self._ffmpeg_args_for_chapter(idx + 1, chapter, info)
+            self.real_run_ffmpeg([(info['filepath'], opts)], [(destination, ['-c', 'copy'])])
+        return [], info

yt_dlp/postprocessor/metadatafromfield.py

@@ -4,11 +4,10 @@ import re
 
 from .common import PostProcessor
 from ..compat import compat_str
-from ..utils import str_or_none
 
 
 class MetadataFromFieldPP(PostProcessor):
-    regex = r'(?P<field>\w+):(?P<format>.+)$'
+    regex = r'(?P<in>.+):(?P<out>.+)$'
 
     def __init__(self, downloader, formats):
         PostProcessor.__init__(self, downloader)
@@ -19,11 +18,20 @@ class MetadataFromFieldPP(PostProcessor):
             match = re.match(self.regex, f)
             assert match is not None
             self._data.append({
-                'field': match.group('field'),
+                'in': match.group('in'),
-                'format': match.group('format'),
+                'out': match.group('out'),
-                'regex': self.format_to_regex(match.group('format'))})
+                'tmpl': self.field_to_template(match.group('in')),
+                'regex': self.format_to_regex(match.group('out')),
+            })
 
-    def format_to_regex(self, fmt):
+    @staticmethod
+    def field_to_template(tmpl):
+        if re.match(r'\w+$', tmpl):
+            return '%%(%s)s' % tmpl
+        return tmpl
+
+    @staticmethod
+    def format_to_regex(fmt):
         r"""
         Converts a string like
            '%(title)s - %(artist)s'
@@ -37,7 +45,7 @@ class MetadataFromFieldPP(PostProcessor):
         # replace %(..)s with regex group and escape other string parts
         for match in re.finditer(r'%\((\w+)\)s', fmt):
             regex += re.escape(fmt[lastpos:match.start()])
-            regex += r'(?P<' + match.group(1) + r'>[^\r\n]+)'
+            regex += r'(?P<%s>.+)' % match.group(1)
             lastpos = match.end()
         if lastpos < len(fmt):
             regex += re.escape(fmt[lastpos:])
@@ -45,22 +53,16 @@ class MetadataFromFieldPP(PostProcessor):
 
     def run(self, info):
         for dictn in self._data:
-            field, regex = dictn['field'], dictn['regex']
+            tmpl, info_copy = self._downloader.prepare_outtmpl(dictn['tmpl'], info)
-            if field not in info:
+            data_to_parse = tmpl % info_copy
-                self.report_warning('Video doesnot have a %s' % field)
+            self.write_debug('Searching for r"%s" in %s' % (dictn['regex'], tmpl))
-                continue
+            match = re.search(dictn['regex'], data_to_parse)
-            data_to_parse = str_or_none(info[field])
-            if data_to_parse is None:
-                self.report_warning('Field %s cannot be parsed' % field)
-                continue
-            self.write_debug('Searching for r"%s" in %s' % (regex, field))
-            match = re.search(regex, data_to_parse)
             if match is None:
-                self.report_warning('Could not interpret video %s as "%s"' % (field, dictn['format']))
+                self.report_warning('Could not interpret video %s as "%s"' % (dictn['in'], dictn['out']))
                 continue
             for attribute, value in match.groupdict().items():
                 info[attribute] = value
-                self.to_screen('parsed %s from %s: %s' % (attribute, field, value if value is not None else 'NA'))
+                self.to_screen('parsed %s from "%s": %s' % (attribute, dictn['in'], value if value is not None else 'NA'))
         return [], info
 
 

yt_dlp/postprocessor/movefilesafterdownload.py

@@ -13,10 +13,6 @@ from ..utils import (
 
 class MoveFilesAfterDownloadPP(PostProcessor):
 
-    def __init__(self, downloader, files_to_move):
-        PostProcessor.__init__(self, downloader)
-        self.files_to_move = files_to_move
-
     @classmethod
     def pp_key(cls):
         return 'MoveFiles'
@@ -25,11 +21,10 @@ class MoveFilesAfterDownloadPP(PostProcessor):
         dl_path, dl_name = os.path.split(encodeFilename(info['filepath']))
         finaldir = info.get('__finaldir', dl_path)
         finalpath = os.path.join(finaldir, dl_name)
-        self.files_to_move.update(info['__files_to_move'])
+        info['__files_to_move'][info['filepath']] = decodeFilename(finalpath)
-        self.files_to_move[info['filepath']] = decodeFilename(finalpath)
 
         make_newfilename = lambda old: decodeFilename(os.path.join(finaldir, os.path.basename(encodeFilename(old))))
-        for oldfile, newfile in self.files_to_move.items():
+        for oldfile, newfile in info['__files_to_move'].items():
             if not newfile:
                 newfile = make_newfilename(oldfile)
             if os.path.abspath(encodeFilename(oldfile)) == os.path.abspath(encodeFilename(newfile)):