Compare commits

..
Author SHA1 Message Date
pukkandan a2f0b0c672 Release 2021.03.24.1 2021-03-25 04:33:34 +05:30
pukkandan b704fc1a68 Revert commit 8562218
[ard] improve clip id extraction
https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf

This was merged incorrectly
2021-03-25 04:31:32 +05:30
pukkandan a3affbe6a0 Release 2021.03.24 2021-03-25 04:18:37 +05:30
pukkandan 1418a0437f Update to ytdl-commit-8562218
[ard] improve clip id extraction
https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf
2021-03-25 04:09:21 +05:30
pukkandan 143db31d48 Parse metadata from multiple fields
Closes #196
2021-03-25 03:32:15 +05:30
pukkandan 3700c7ef10 [linuxacadamy] Fix login 2021-03-24 04:06:26 +05:30
pukkandan 498f560638 Ability to load playlist infojson
* If `--no-clean-infojson` is given, the video ids are saved/loaded from in the infojson along with their playlist index
* If a video entry that was not saved is requested, we fallback to using `webpage_url` to re-extract the entries

Related: https://github.com/yt-dlp/yt-dlp/issues/190#issuecomment-804921024
2021-03-24 01:57:50 +05:30
pukkandan 394dcd4486 Write current epoch to infojson when using --no-clean-infojson
Closes #191
2021-03-24 00:34:33 +05:30
pukkandan 83b20a970d [youtube_live_chat] fix bug when trying to set cookies
Closes #194
2021-03-23 17:53:36 +05:30
pukkandan e1feb88fdf [niconico] Fix for when logged in
Related: https://github.com/yt-dlp/yt-dlp/issues/171#issuecomment-803692716
Co-authored by: CXwudi, xtkoba
2021-03-23 14:03:07 +05:30
pukkandan 389b9dbbcc [version] update 2021-03-22 03:03:06 +05:30
pukkandan a7f347d9c9 Release 2021.03.21 2021-03-22 02:58:41 +05:30
pukkandan 421a459573 Update to ytdl-commit-7e79ba7
https://github.com/ytdl-org/youtube-dl/commit/7e79ba7dd6e6649dd2ce3a74004b2044f2182881
[vimeo:album] Fix extraction for albums with number of videos multiple to page size
2021-03-22 02:58:41 +05:30
Matthewandpukkandan c224251aad [youtube] Show if video is private, unlisted etc in new field availability (#188)
Closes: #185, https://github.com/ytdl-org/youtube-dl/issues/25631

Authored by: colethedj, pukkandan
2021-03-22 02:58:41 +05:30
pukkandan 037cc66ec8 [linuxacadamy] Improve regex
TODO: We need to make a more robust standard regex for fetching js objects from html
2021-03-21 21:27:33 +05:30
Two Sheds" JacksonandGitHub 9160a0c6a2 [nbc] Improve metadata extraction (#187)
Authored by: 2ShedsJackson
2021-03-21 21:26:31 +05:30
2ShedsJacksonandGitHub 5c5fae6d2f [amcnetworks] Fix extractor (#179)
* Prefer use of manifest based on `releasePid` since the one based on `videoPid` may have Fairplay
* Additional thumbnail images were added
* Don't add `season_number` and `series` to `title`
* `series` is now set to `None` rather than "_" when empty
* fix bug with age limit

Authored by: 2ShedsJackson
2021-03-20 16:11:11 +05:30
pukkandan c1d3a4a8f0 [niconico] Add user extractor
Co-authored by: animelover1984
2021-03-20 14:59:39 +05:30
pukkandan adc74b3c6d [bilibili] Add anthology support
Closes: #118

Co-authored by: animelover1984
2021-03-20 14:56:42 +05:30
pukkandan beb4b92a66 More consistent warning messages (#173)
Co-authored by: Damiano Amatruda <damiano.amatruda@outlook.com>
2021-03-20 09:34:52 +05:30
pukkandan cd9b384cc3 Embed video URL metadata inside MP4 (#173)
`mp4` has `comment` and `synopsis`; the synopsis is expected to have the long description
So we save the `webpage_url` to `comment` and `description` to `synopsis`

Related: https://github.com/ytdl-org/youtube-dl/issues/28478

Co-authored by: Damiano Amatruda <damiano.amatruda@outlook.com>
2021-03-20 09:34:52 +05:30
pukkandan 4d971a16b8 Merge webm formats into mkv if thumbnails are to be embedded (#173)
Co-authored by: Damiano Amatruda <damiano.amatruda@outlook.com>
2021-03-20 09:34:52 +05:30
Damiano Amatrudaandpukkandan 3561530776 Parse resolution in info dictionary (#173) 2021-03-20 09:34:52 +05:30
Damiano Amatrudaandpukkandan 4690688658 Use headers and cookies when downloading subtitles (#173) 2021-03-20 09:34:52 +05:30
pukkandan fe845284c4 [aria2c] Support retry/abort unavailable fragments (#173)
Co-authored by: Damiano Amatruda <damiano.amatruda@outlook.com>
2021-03-20 09:33:33 +05:30
pukkandan 2b3bf01c90 [aria2c] Better default arguments 2021-03-20 09:31:53 +05:30
pukkandan 23c1a66730 Make sure post_hook gets the final filename 2021-03-20 09:31:53 +05:30
pukkandan dd18a58cb1 [documentation] Add SplitChapters to --ppa 2021-03-20 09:31:53 +05:30
pukkandan a94bfd6cfe [splitchapters] Fix for older ffmpeg
Older versions of ffmpeg doesn't allow `-to` as an input option
Closes #180
2021-03-20 09:31:53 +05:30
pukkandan a515a78dd3 fix some typos and linter 2021-03-18 22:19:31 +05:30
pukkandan e167860ce7 [documentation] Add deprecated options and aliases in readme 2021-03-18 22:07:50 +05:30
pukkandan 75d43ca080 Option to keep private keys in the infojson
Options: --clean-infojson, --no-clean-infojson

Related: https://github.com/yt-dlp/yt-dlp/issues/42#issuecomment-800778391
2021-03-18 21:00:45 +05:30
pukkandan 5226731e2d Recursively remove private keys from infojson
Related: https://github.com/yt-dlp/yt-dlp/issues/42
2021-03-18 21:00:45 +05:30
pukkandan dcf64d43e0 [movefiles] Fix bugs and make more robust 2021-03-18 20:54:53 +05:30
pukkandan e3c076970e [youtube] bugfix for channel playlist extraction
Bug introduced in cd7c66cf01
2021-03-17 17:35:02 +05:30
pukkandan 7978e172f3 [niconico] Partial fix
TODO:
Smile formats don't work
Extraction code that no longer works needs to be removed

Adapted from:
https://github.com/animelover1984/youtube-dl/commit/b5eff52dd9ed5565672ea1694b38c9296db3fade
by animelover1984

Related:
https://github.com/yt-dlp/yt-dlp/issues/171
https://github.com/animelover1984/youtube-dl/issues/29
https://github.com/ytdl-org/youtube-dl/issues/28470
2021-03-17 15:38:24 +05:30
nixxoandGitHub 605d299f83 [stitcher] Merge from youtube-dl (#175)
This cherry-picks the commits:
https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f#diff-cc37718b18689c1c0588c4c74518853ef43ab020bbd674f3c04d4eae037798d2
https://github.com/ytdl-org/youtube-dl/commit/8522bcd97c4173407261a3fa0283dd7800c39601#diff-cc37718b18689c1c0588c4c74518853ef43ab020bbd674f3c04d4eae037798d2

Authored by: nixxo
2021-03-16 15:32:10 +05:30
nixxoandGitHub 18c1f04362 [rcs] Improved extraction (See desc) (#170)
* improved `video_data` extraction
* added an extra fallback value for `description`
* improved regex in `RCSVariousIE`

Authored by: nixxo
2021-03-16 00:26:29 +05:30
pukkandan e4beae703d [formatSort] Fix quality being ignored
Closes #172
2021-03-15 23:55:53 +05:30
pukkandan d034ab669c [sponskrub] Pass proxy to sponskrub
Needs atleast sponskrub version:
    faissaloo/sponskrub 3.7.0
    OR yt-dlp/sponskrub 2021.03.15
2021-03-15 06:27:21 +05:30
pukkandan 5aeefbd633 [version] update
:ci skip all
2021-03-15 06:03:59 +05:30
47 changed files with 1613 additions and 779 deletions
+3 -3
View File
@@ -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 2021.03.07. 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. 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 **2021.03.07**
- [ ] I've verified that I'm running yt-dlp version **2021.03.24**
- [ ] 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 2021.03.07
[debug] yt-dlp version 2021.03.24
[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: {}
@@ -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 2021.03.07. 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. 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 **2021.03.07**
- [ ] I've verified that I'm running yt-dlp version **2021.03.24**
- [ ] 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
@@ -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 2021.03.07. 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. 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 **2021.03.07**
- [ ] I've verified that I'm running yt-dlp version **2021.03.24**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
+3 -3
View File
@@ -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 2021.03.07. 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. 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 **2021.03.07**
- [ ] I've verified that I'm running yt-dlp version **2021.03.24**
- [ ] 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 2021.03.07
[debug] yt-dlp version 2021.03.24
[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: {}
+2 -2
View File
@@ -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 2021.03.07. 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. 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 **2021.03.07**
- [ ] I've verified that I'm running yt-dlp version **2021.03.24**
- [ ] I've searched the bugtracker for similar feature requests including closed ones
+7 -2
View File
@@ -1,5 +1,6 @@
pukkandan (owner)
shirt-dev (collaborator)
colethedj (collaborator)
h-h-h-h
pauldubois98
nixxo
@@ -23,10 +24,14 @@ tsukumi
bbepis
animelover1984
Pccode66
Ashish
Ashish0804
RobinD42
hseg
colethedj
DennyDai
codeasashu
teesid
kevinoconnor7
damianoamatruda
2ShedsJackson
CXwudi
xtkoba
+51 -7
View File
@@ -17,6 +17,51 @@
-->
### 2021.03.24.1
* Revert [commit/8562218](https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf)
### 2021.03.24
* Merge youtube-dl: Upto [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 and @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:`
@@ -24,13 +69,12 @@
* **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 [Ashish](https://github.com/Ashish) and [pukkandan](https://github.com/pukkandan)
* [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)
* [zee5] Support zee5originals
* [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)
* [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)
@@ -40,7 +84,7 @@
* [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 [Ashish](https://github.com/Ashish)
* [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)
@@ -50,7 +94,7 @@
* [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 [Ashish](https://github.com/Ashish)
* [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
@@ -100,7 +144,7 @@
* 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)
@@ -296,7 +340,7 @@
* [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
+91 -46
View File
@@ -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)
@@ -47,6 +47,7 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
* [Sorting Formats](#sorting-formats)
* [Format Selection examples](#format-selection-examples)
* [PLUGINS](#plugins)
* [DEPRECATED OPTIONS](#deprecated-options)
* [MORE](#more)
@@ -57,7 +58,7 @@ 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 v2021.03.14**: 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 v2021.03.25**: 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.
@@ -74,9 +75,9 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
* **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 using `--paths` (`-P`)
@@ -423,6 +424,11 @@ 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
@@ -466,7 +472,8 @@ 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
@@ -503,7 +510,7 @@ 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
@@ -517,15 +524,11 @@ 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
of a range for randomized sleep before each
download (minimum possible number of
seconds to sleep) when used along with
--max-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
download. This is the minimum time to sleep
when used along with --max-sleep-interval
(Alias: --min-sleep-interval)
--max-sleep-interval SECONDS Maximum number of seconds to sleep. Can
only be used along with --min-sleep-interval
--sleep-subtitles SECONDS Number of seconds to sleep before each
subtitle download
@@ -575,16 +578,16 @@ 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)
--no-write-auto-subs Do not write automatically generated
subtitle file (default)
(Alias: --write-automatic-subs)
--no-write-auto-subs Do not write auto-generated subtitles
(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
@@ -638,19 +641,19 @@ 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
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, "_i"/"_o" can be appended
to the prefix optionally followed by a
number to pass the argument before the
specified input/output file. Eg: --ppa
"Merger+ffmpeg_i1:-v quiet". You can use
this option multiple times to give
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, "_i"/"_o"
can be appended to the prefix optionally
followed by a number to pass the argument
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)
-k, --keep-video Keep the intermediate video file on disk
@@ -667,18 +670,24 @@ Then simply run `make`. You can also run `make yt-dlp` instead to compile only t
--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
from other fields. Give field name to
extract data from, and format of the field
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
from other fields. Give a template or field
name to extract data from and the format to
interpret it as, seperated by a ":". Either
regular expression with named capture
groups or a similar syntax to the output
template can be used for the FORMAT.
Similarly, the syntax for output template
can be used for FIELD to parse the data
from multiple fields. The parsed parameters
replace any existing values and can be used
in output templates. This option can be
used multiple times. Example: --parse-
metadata "title:%(artist)s - %(title)s"
matches a title like "Coldplay - Paradise".
Example: --parse-metadata "%(series)s
%(episode_number)s:%(title)s" sets the
title using series and episode number.
Example (regex): --parse-metadata
"description:Artist - (?P<artist>.+?)"
--xattrs Write metadata to the video file's xattrs
(using dublin core and xdg standards)
@@ -694,8 +703,9 @@ 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"
@@ -853,6 +863,7 @@ 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
@@ -1198,5 +1209,39 @@ Plugins are loaded from `<root-dir>/ytdlp_plugins/<type>/__init__.py`. Currently
**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: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)
+6 -1
View File
@@ -97,7 +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**
@@ -543,6 +544,7 @@
- **mixcloud:playlist**
- **mixcloud:user**
- **MLB**
- **MLBVideo**
- **Mnet**
- **MNetTV**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@@ -634,6 +636,7 @@
- **nicknight**
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **NiconicoUser**
- **Nintendo**
- **Nitter**
- **njoy**: N-JOY
@@ -917,6 +920,7 @@
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
- **StitcherShow**
- **StoryFire**
- **StoryFireSeries**
- **StoryFireUser**
@@ -1248,5 +1252,6 @@
- **zee5:series**
- **Zhihu**
- **zingmp3**: mp3.zing.vn
- **zingmp3:album**
- **zoom**
- **Zype**
+220 -182
View File
@@ -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)
# 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)
outtmpl, template_dict = self.prepare_outtmpl(outtmpl, info_dict, sanitize)
# 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'))
@@ -1179,49 +1181,16 @@ class YoutubeDL(object):
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):
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:
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 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 'entries' not in ie_result:
raise EntryNotInPlaylist()
incomplete_entries = bool(ie_result.get('requested_entries'))
if incomplete_entries:
def fill_missing_entries(entries, indexes):
ret = [None] * max(*indexes)
for i, entry in zip(indexes, entries):
ret[i - 1] = entry
return ret
ie_result['entries'] = fill_missing_entries(ie_result['entries'], ie_result['requested_entries'])
playlist_results = []
@@ -1248,25 +1217,20 @@ class YoutubeDL(object):
def make_playlistitems_entries(list_ie_entries):
num_entries = len(list_ie_entries)
return [
list_ie_entries[i - 1] for i in playlistitems
if -num_entries <= i - 1 < num_entries]
def report_download(num_entries):
self.to_screen(
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, num_entries))
for i in playlistitems:
if -num_entries < i <= num_entries:
yield list_ie_entries[i - 1]
elif incomplete_entries:
raise EntryNotInPlaylist()
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(
'[%s] playlist %s: Collected %d video ids (downloading %d of them)' %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
msg = 'Collected %d videos; downloading %d of them' % (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(
ie_entries, 0, max(playlistitems))))
entries = list(make_playlistitems_entries(list(itertools.islice(
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']),
@@ -1644,7 +1656,7 @@ 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'),
@@ -2047,7 +2059,7 @@ 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."""
@@ -2075,6 +2087,7 @@ 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 = {}
@@ -2140,7 +2153,10 @@ 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')])
@@ -2159,6 +2175,7 @@ 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)
@@ -2168,13 +2185,15 @@ 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' %
@@ -2212,7 +2231,7 @@ class YoutubeDL(object):
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
@@ -2223,7 +2242,7 @@ 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
@@ -2336,10 +2355,17 @@ 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):
info_dict['ext'] = 'mkv'
self.report_warning(
'Requested formats are incompatible for merge and will be merged into mkv.')
if self.params.get('merge_output_format') is None:
if not compatible_formats(requested_formats):
info_dict['ext'] = '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:]
@@ -2455,13 +2481,13 @@ 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 +2527,7 @@ 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 +2536,10 @@ 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 +2549,32 @@ class YoutubeDL(object):
return self._download_retcode
@staticmethod
def filter_requested_info(info_dict):
fields_to_remove = ('requested_formats', 'requested_subtitles')
return dict(
(k, v) for k, v in info_dict.items()
if (k[0] != '_' or k == '_type') and k not in fields_to_remove)
def filter_requested_info(info_dict, actually_filter=True):
if not actually_filter:
info_dict['epoch'] = int(time.time())
return info_dict
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)
@@ -2545,9 +2582,9 @@ 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:
del files_to_move[old_filename]
return files_to_move, infodict
if old_filename in infodict['__files_to_move']:
del infodict['__files_to_move'][old_filename]
return infodict
@staticmethod
def post_extract(info_dict):
@@ -2570,20 +2607,22 @@ class YoutubeDL(object):
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(MoveFilesAfterDownloadPP(self, files_to_move), info)[1]
info = self.run_pp(pp, info)
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 +2671,11 @@ 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') is not None:
res = '%sx%s' % (format['width'], format['height'])
else:
res = '%sp' % format['height']
elif format.get('width') is not None:
if format.get('width') and format.get('height'):
res = '%dx%d' % (format['width'], format['height'])
elif format.get('height'):
res = '%sp' % format['height']
elif format.get('width'):
res = '%dx?' % format['width']
else:
res = default
@@ -2951,7 +2989,7 @@ 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)
+1
View File
@@ -491,6 +491,7 @@ 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,
+3 -1
View File
@@ -63,6 +63,8 @@ class DashSegmentsFD(FragmentFD):
})
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['fragments'] = fragments_to_download
fd = real_downloader(self.ydl, self.params)
@@ -110,7 +112,7 @@ class DashSegmentsFD(FragmentFD):
if count > fragment_retries:
if not fatal:
return False, frag_index
self.report_error('giving up after %s fragment retries' % fragment_retries)
self.report_error('Giving up after %s fragment retries' % fragment_retries)
return False, frag_index
return frag_content, frag_index
+60 -38
View File
@@ -24,7 +24,6 @@ from ..utils import (
cli_bool_option,
cli_configuration_args,
encodeFilename,
error_to_compat_str,
encodeArgument,
handle_youtubedl_headers,
check_executable,
@@ -117,19 +116,42 @@ class ExternalFD(FileDownloader):
self._debug_cmd(cmd)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
if 'fragments' in info_dict:
file_list = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
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
dest, _ = sanitize_open(tmpfilename, 'wb')
for i, fragment in enumerate(info_dict['fragments']):
file = '%s-Frag%d' % (tmpfilename, i)
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (tmpfilename, frag_index)
try:
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')
src, _ = sanitize_open(file, 'rb')
if decrypt_info:
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV')
@@ -146,20 +168,16 @@ class ExternalFD(FileDownloader):
fragment_data = src.read()
dest.write(fragment_data)
src.close()
file_list.append(file)
if not self.params.get('keep_fragments', False):
os.remove(encodeFilename(fragment_filename))
dest.close()
if not self.params.get('keep_fragments', False):
for file_path in file_list:
try:
os.remove(file_path)
except OSError as ose:
self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
try:
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)))
os.remove(encodeFilename('%s.frag.urls' % tmpfilename))
else:
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
self.to_stderr(stderr.decode('utf-8', 'replace'))
return p.returncode
def _prepare_url(self, info_dict, url):
@@ -253,14 +271,12 @@ class Aria2cFD(ExternalFD):
return all(check_results)
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c']
dn = os.path.dirname(tmpfilename)
if 'fragments' not in info_dict:
cmd += ['--out', os.path.basename(tmpfilename)]
verbose_level_args = ['--console-log-level=warn', '--summary-interval=0']
cmd += self._configuration_args(['--file-allocation=none', '-x16', '-j16', '-s16'] + verbose_level_args)
if dn:
cmd += ['--dir', dn]
cmd = [self.exe, '-c',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
'--file-allocation=none', '-x16', '-j16', '-s16']
if 'fragments' in info_dict:
cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
if info_dict.get('http_headers') is not None:
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
@@ -268,19 +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 'fragments' in info_dict:
cmd += verbose_level_args
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, fragment in enumerate(info_dict['fragments']):
tmpsegmentname = '%s-Frag%d' % (os.path.basename(tmpfilename), i)
url_list.append('%s\n\tout=%s' % (fragment['url'], tmpsegmentname))
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
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']]
+9 -6
View File
@@ -83,14 +83,13 @@ 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(
'hlsnative has detected features it does not support, '
'extraction will be delegated to ffmpeg')
self.report_warning('pycryptodome is needed to download this file natively')
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)
@@ -99,6 +98,9 @@ class HlsFD(FragmentFD):
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
@@ -186,7 +188,7 @@ class HlsFD(FragmentFD):
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:])
@@ -289,6 +291,7 @@ class HlsFD(FragmentFD):
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':
+1 -1
View File
@@ -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
+1 -1
View File
@@ -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)
+1 -2
View File
@@ -79,8 +79,7 @@ class YoutubeLiveChatReplayFD(FragmentFD):
self._prepare_and_start_frag_download(ctx)
success, raw_fragment = dl_fragment(
'https://www.youtube.com/watch?v={}'.format(video_id))
success, raw_fragment = dl_fragment(info_dict['url'])
if not success:
return False
try:
+49 -18
View File
@@ -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(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
display_id)['data']['properties']
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), 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,
'age_limit': parse_age_limit(parse_age_limit(rating)),
'thumbnails': thumbnails,
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
series = theplatform_metadata.get(ns + '$show')
season_number = int_or_none(
theplatform_metadata.get(ns + '$season'))
episode = theplatform_metadata.get(ns + '$episodeTitle')
episode = theplatform_metadata.get(ns + '$episodeTitle') or None
episode_number = int_or_none(
theplatform_metadata.get(ns + '$episode'))
if season_number:
title = 'Season %d - %s' % (season_number, title)
if series:
title = '%s - %s' % (series, title)
season_number = int_or_none(
theplatform_metadata.get(ns + '$season'))
series = theplatform_metadata.get(ns + '$show') or None
info.update({
'title': title,
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'season_number': season_number,
'series': series,
})
return info
+190 -15
View File
@@ -1,17 +1,22 @@
# 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,
float_or_none,
@@ -811,7 +816,7 @@ class BBCIE(BBCCoUkIE):
@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))
@@ -1338,21 +1343,149 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
playlist_id, title, description)
class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
IE_NAME = 'bbc.co.uk:iplayer:playlist'
_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'
_VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
_VALID_URL_TMPL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/%%s/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
@staticmethod
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,
'skip': 'This programme is not currently available on BBC iPlayer',
'playlist_mincount': 8,
}, {
# 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': {
@@ -1361,14 +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):
title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
description = self._search_regex(
r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
webpage, 'description', fatal=False, group='value')
return title, description
def _get_episode_image(self, episode):
return self._get_default(episode, 'images', 'standard')
def _get_episode_field(self, episode, field):
return episode.get(field)
@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):
+49 -5
View File
@@ -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',
@@ -224,7 +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',
@@ -234,7 +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,
@@ -300,7 +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,
@@ -312,6 +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(
@@ -506,7 +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):
+24 -6
View File
@@ -252,8 +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
automatically generated captions
automatic_captions: Like 'subtitles'; contains automatically generated
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
@@ -301,7 +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.
@@ -1417,8 +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'},
'quality': {'convert': 'float_none', 'type': 'extractor'},
'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
'quality': {'convert': 'float_none'},
'filesize': {'convert': 'bytes'},
'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
'id': {'convert': 'string', 'field': 'format_id'},
@@ -1429,7 +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},
@@ -3332,6 +3336,20 @@ 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):
"""
+19 -7
View File
@@ -108,7 +108,8 @@ from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
from .bbc import (
BBCCoUkIE,
BBCCoUkArticleIE,
BBCCoUkIPlayerPlaylistIE,
BBCCoUkIPlayerEpisodesIE,
BBCCoUkIPlayerGroupIE,
BBCCoUkPlaylistIE,
BBCIE,
)
@@ -708,7 +709,10 @@ 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 (
@@ -822,7 +826,7 @@ 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
@@ -1179,7 +1183,10 @@ 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
@@ -1667,9 +1674,14 @@ from .zattoo import (
ZattooLiveIE,
)
from .zdf import ZDFIE, ZDFChannelIE
from .zee5 import (
Zee5IE,
Zee5SeriesIE,
)
from .zhihu import ZhihuIE
from .zingmp3 import ZingMp3IE
from .zee5 import Zee5IE
from .zee5 import Zee5SeriesIE
from .zingmp3 import (
ZingMp3IE,
ZingMp3AlbumIE,
)
from .zoom import ZoomIE
from .zype import ZypeIE
+1 -1
View File
@@ -2965,7 +2965,7 @@ 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')
+1 -1
View File
@@ -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
+14 -4
View File
@@ -38,8 +38,8 @@ class LinuxAcademyIE(InfoExtractor):
'ext': 'mp4',
'title': 'What Is Data Science',
'description': 'md5:c574a3c20607144fb36cb65bdde76c99',
'timestamp': 1607387907,
'upload_date': '20201208',
'timestamp': int, # The timestamp and upload date changes
'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
+168 -21
View File
@@ -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]
+1 -1
View File
@@ -340,7 +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')
+34 -9
View File
@@ -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',
}
+140 -93
View File
@@ -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_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
'use_ssl': yesno(session_api_endpoint['isSsl']),
'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]]),
'content_key_timeout': session_api_data.get('content_key_timeout'),
'auth_type': try_get(session_api_data, lambda x: x['authTypes'][session_api_data['protocols'][0]]),
'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:
dmc_info = api_data['video']['dmcInfo']
except KeyError:
raise ExtractorError('The video can\'t downloaded.',
expected=True)
quality_info = try_get(api_data, lambda x: x['media']['delivery']['movie'])
if not quality_info:
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:
self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
if is_economy:
self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
# Invoking ffprobe to determine resolution
pp = FFmpegPostProcessor(self._downloader)
cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
# Invoking ffprobe to determine resolution
pp = FFmpegPostProcessor(self._downloader)
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:
metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
except PostProcessingError as err:
raise ExtractorError(err.msg, expected=True)
try:
metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
except PostProcessingError as err:
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)
for stream in metadata['streams']:
if stream['codec_type'] == 'video':
v_stream = stream
elif stream['codec_type'] == 'audio':
a_stream = stream
# Some complex swf files doesn't have video stream (e.g. nm4809023)
for stream in metadata['streams']:
if stream['codec_type'] == 'video':
v_stream = stream
elif stream['codec_type'] == 'audio':
a_stream = stream
# Community restricted videos seem to have issues with the thumb API not returning anything at all
filesize = int(
(get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
or metadata['format']['size']
)
extension = (
get_video_info_xml('movie_type')
or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
)
# Community restricted videos seem to have issues with the thumb API not returning anything at all
filesize = int(
(get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
or metadata['format']['size']
)
extension = (
get_video_info_xml('movie_type')
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'.
timestamp = (
parse_iso8601(get_video_info_web('first_retrieve'))
or unified_timestamp(get_video_info_web('postedDateTime'))
)
metadata_timestamp = (
parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
or timestamp if extension != 'mp4' else 0
)
# 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
timestamp = (
parse_iso8601(get_video_info_web('first_retrieve'))
or unified_timestamp(get_video_info_web('postedDateTime'))
)
metadata_timestamp = (
parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
or timestamp if extension != 'mp4' else 0
)
# 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')
# 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')
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 filesize > 1:
formats.append({
'url': video_real_url,
'format_id': 'smile' if not is_economy else 'smile_low',
'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
'ext': extension,
'container': extension,
'vcodec': v_stream.get('codec_name'),
'acodec': a_stream.get('codec_name'),
# 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),
'vbr': int_or_none(v_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')),
'width': int_or_none(v_stream.get('width')),
'source_preference': 5 if not is_economy else -2,
'quality': 5 if is_source and not is_economy else None,
'filesize': filesize
})
# If movie file size is unstable, old server movie is not source movie.
if filesize > 1:
formats.append({
'url': video_real_url,
'format_id': 'smile' if not is_economy else 'smile_low',
'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
'ext': extension,
'container': extension,
'vcodec': v_stream.get('codec_name'),
'acodec': a_stream.get('codec_name'),
# 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),
'vbr': int_or_none(v_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')),
'width': int_or_none(v_stream.get('width')),
'source_preference': 5 if not is_economy else -2,
'quality': 5 if is_source and not is_economy else None,
'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')
if not title:
title = self._og_search_title(webpage, default=None)
if not title:
title = self._html_search_regex(
title = (
get_video_info_web(['originalTitle', 'title'])
or self._og_search_title(webpage, default=None)
or 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())
+31 -17
View File
@@ -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?:)?
//video\.rcs\.it
/fragment-includes/video-includes/.+?\.json)["'];''',
page, video_id, default=None)
r'''(?x)url\s*=\s*(["'])
(?P<url>
(?:https?:)?//video\.rcs\.it
/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:
video_data = self._parse_json(
json, video_id, transform_source=js_to_json)
else:
if not json and 'video-embed' in url:
page = self._download_webpage(url.replace('video-embed', 'video-json'), video_id)
json = self._search_regex(
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>[^/]+?)(?:$|\?|/)'''
_TESTS = [{
'url': 'https://www.leitv.it/video/marmellata-di-ciliegie-fatta-in-casa/',
'md5': '618aaabac32152199c1af86784d4d554',
'url': 'https://www.leitv.it/benessere/mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa/',
'md5': '92b4e63667b8f95acb0a04da25ae28a1',
'info_dict': {
'id': 'marmellata-di-ciliegie-fatta-in-casa',
'id': 'mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa',
'ext': 'mp4',
'title': 'Marmellata di ciliegie fatta in casa',
'description': 'md5:89133864d6aad456dbcf6e7a29f86263',
'title': 'Cervicalgia e mal di testa, il video con i suggerimenti dell\'esperto',
'description': 'md5:ae21418f34cee0b8d02a487f55bcabb5',
'uploader': 'leitv.it',
}
}, {
+89 -32
View File
@@ -1,19 +1,61 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
clean_podcast_url,
ExtractorError,
int_or_none,
str_or_none,
try_get,
url_or_none,
)
class StitcherIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stitcher\.com/(?:podcast|show)/(?:[^/]+/)+e(?:pisode)?/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
class StitcherBaseIE(InfoExtractor):
_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',
'timestamp': 1516989316,
'upload_date': '20151008',
'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()
audio_url = episode['audio_url']
class StitcherShowIE(StitcherBaseIE):
_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
show_id = episode.get('show_id')
if show_id and episode.get('classic_id') != -1:
thumbnail = 'https://stitcher-classic.imgix.net/feedimages/%s.jpg' % show_id
def _real_extract(self, url):
show_slug = self._match_id(url)
data = self._call_api(
'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 {
'id': audio_id,
'display_id': display_id,
'title': title,
'description': clean_html(episode.get('html_description') or episode.get('description')),
'duration': int_or_none(episode.get('duration')),
'thumbnail': thumbnail,
'url': audio_url,
'vcodec': 'none',
'timestamp': int_or_none(episode.get('date_created')),
'season_number': int_or_none(episode.get('season')),
'season_id': str_or_none(episode.get('season_id')),
}
entries = []
for episode in (data.get('episodes') or []):
audio_url = self._extract_audio_url(episode)
if not audio_url:
continue
entries.append(self._extract_episode(episode, audio_url, show_info))
return self.playlist_result(
entries, show_slug, show.get('title'),
self._extract_description(show))
+13 -7
View File
@@ -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',
'timestamp': 1586044800,
'upload_date': '20200405',
'duration': 3515,
'title': 'Designdrömmar i Stenungsund',
'timestamp': 1615770000,
'upload_date': '20210315',
'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-]+)"',
+4 -1
View File
@@ -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)
+6
View File
@@ -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,
+9 -5
View File
@@ -991,11 +991,15 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
}
if hashed_pass:
query['_hashed_pass'] = hashed_pass
videos = self._download_json(
'https://api.vimeo.com/albums/%s/videos' % album_id,
album_id, 'Downloading page %d' % api_page, query=query, headers={
'Authorization': 'jwt ' + authorization,
})['data']
try:
videos = self._download_json(
'https://api.vimeo.com/albums/%s/videos' % album_id,
album_id, 'Downloading page %d' % api_page, query=query, headers={
'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:
+14 -11
View File
@@ -182,17 +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':
kenc = self._download_json(
'https://www.vvvvid.it/kenc', video_id, query={
'action': 'kt',
'conn_id': self._conn_id,
'url': embed_code,
}, fatal=False) or {}
kenc_message = kenc.get('message')
if kenc_message:
embed_code += '?' + ds(kenc_message)
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(
'https://www.vvvvid.it/kenc', video_id, query={
'action': 'kt',
'conn_id': self._conn_id,
'url': embed_code,
}, fatal=False) or {}
kenc_message = kenc.get('message')
if 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({
+29 -3
View File
@@ -25,6 +25,7 @@ from ..compat import (
)
from ..jsinterp import JSInterpreter
from ..utils import (
bool_or_none,
clean_html,
dict_get,
ExtractorError,
@@ -1946,7 +1947,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
f['format_id'] = itag
formats.append(f)
if self._downloader.params.get('youtube_include_dash_manifest'):
if self._downloader.params.get('youtube_include_dash_manifest', True):
dash_manifest_url = streaming_data.get('dashManifestUrl')
if dash_manifest_url:
for f in self._extract_mpd_formats(
@@ -2066,7 +2067,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'tags': keywords,
'is_live': is_live,
'playable_in_embed': playability_status.get('playableInEmbed'),
'was_live': video_details.get('isLiveContent')
'was_live': video_details.get('isLiveContent'),
}
pctr = try_get(
@@ -2149,6 +2150,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# This will error if there is no livechat
initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
info['subtitles']['live_chat'] = [{
'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
'video_id': video_id,
'ext': 'json',
'protocol': 'youtube_live_chat_replay',
@@ -2283,6 +2285,30 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if v:
info[d_k] = v
is_private = bool_or_none(video_details.get('isPrivate'))
is_unlisted = bool_or_none(microformat.get('isUnlisted'))
is_membersonly = None
if initial_data and is_private is not None:
is_membersonly = False
contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list)
for content in contents or []:
badges = try_get(content, lambda x: x['videoPrimaryInfoRenderer']['badges'], list)
for badge in badges or []:
label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label']) or ''
if label.lower() == 'members only':
is_membersonly = True
break
if is_membersonly:
break
# TODO: Add this for playlists
info['availability'] = self._availability(
is_private=is_private,
needs_premium=False, # Youtube no longer have premium-only videos?
needs_subscription=is_membersonly,
needs_auth=info['age_limit'] >= 18,
is_unlisted=None if is_private is None else is_unlisted)
# get xsrf for annotations or comments
get_annotations = self._downloader.params.get('writeannotations', False)
get_comments = self._downloader.params.get('getcomments', False)
@@ -2666,7 +2692,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
def _extract_basic_item_renderer(item):
# Modified from _extract_grid_item_renderer
known_renderers = (
'playlistRenderer', 'videoRenderer', 'channelRenderer'
'playlistRenderer', 'videoRenderer', 'channelRenderer',
'gridPlaylistRenderer', 'gridVideoRenderer', 'gridChannelRenderer'
)
for key, renderer in item.items():
+115 -97
View File
@@ -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):
error_message = item.get('msg')
if error_message:
if not fatal:
return
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error_message),
expected=True)
def _extract_item(self, item, fatal):
item_id = item['id']
title = item.get('name') or item['title']
formats = []
for quality, source_url in zip(item.get('qualities') or item.get('quality', []), item.get('source_list') or item.get('source', [])):
if not source_url or source_url == 'require vip':
for k, v in (item.get('source') or {}).items():
if not v:
continue
if not re.match(r'https?://', source_url):
source_url = '//' + source_url
source_url = self._proto_relative_url(source_url, 'http:')
quality_num = int_or_none(quality)
f = {
'format_id': quality,
'url': source_url,
}
if page_type == 'video':
f.update({
'height': quality_num,
'ext': 'mp4',
})
if k in ('mp4', 'hls'):
for res, video_url in v.items():
if not video_url:
continue
if k == 'hls':
formats.extend(self._extract_m3u8_formats(
video_url, item_id, 'mp4',
'm3u8_native', m3u8_id=k, fatal=False))
elif k == 'mp4':
formats.append({
'format_id': 'mp4-' + res,
'url': video_url,
'height': int_or_none(self._search_regex(
r'^(\d+)p', res, 'resolution', default=None)),
})
else:
f.update({
'abr': quality_num,
formats.append({
'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,
'artist': item.get('artist'),
'thumbnail': item.get('thumbnail'),
'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):
player_json = self._download_json(player_json_url, id, 'Downloading Player JSON')
items = player_json['data']
if 'item' in items:
items = items['item']
if len(items) == 1:
# one single song
data = self._extract_item(items[0], page_type)
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,
}
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(
url.replace('://zingmp3.vn/', '://mp3.zing.vn/'),
page_id, query={'play_song': 1})
data_path = self._search_regex(
r'data-xml="([^"]+)', webpage, 'data path')
return self._process_data(self._download_json(
'https://mp3.zing.vn/xhr' + data_path, page_id)['data'])
class ZingMp3IE(ZingMp3BaseInfoExtractor):
_VALID_URL = r'https?://mp3\.zing\.vn/(?:bai-hat|album|playlist|video-clip)/[^/]+/(?P<id>\w+)\.html'
class ZingMp3IE(ZingMp3BaseIE):
_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',
'md5': '870295a9cd8045c0e15663565902618d',
'url': 'https://mp3.zing.vn/video-clip/Suong-Hoa-Dua-Loi-K-ICM-RYO/ZO8ZF7C7.html',
'md5': 'e9c972b693aa88301ef981c8151c4343',
'info_dict': {
'id': 'ZW6BAEA0',
'title': 'Let It Go (Frozen OST)',
'id': 'ZO8ZF7C7',
'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',
'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',
'url': 'https://zingmp3.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html',
'only_matching': True,
}]
IE_NAME = 'zingmp3'
IE_DESC = 'mp3.zing.vn'
def _real_extract(self, url):
page_id = self._match_id(url)
def _process_data(self, data):
return self._extract_item(data, True)
webpage = self._download_webpage(url, page_id)
player_json_url = self._search_regex([
r'data-xml="([^"]+)',
r'&amp;xmlURL=([^&]+)&'
], webpage, 'player xml url')
class ZingMp3AlbumIE(ZingMp3BaseIE):
_VALID_URL = ZingMp3BaseIE._VALID_URL_TMPL % 'album|playlist'
_TESTS = [{
'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
page_type = self._search_regex(r'/(?:html5)?xml/([^/-]+)', player_json_url, 'page type')
if page_type == 'video':
player_json_url = update_url_query(player_json_url, {'format': 'json'})
else:
player_json_url = player_json_url.replace('/xml/', '/html5xml/')
if page_type == 'album':
playlist_title = self._og_search_title(webpage)
return self._extract_player_json(player_json_url, page_id, page_type, playlist_title)
def _process_data(self, data):
def entries():
for item in (data.get('items') or []):
entry = self._extract_item(item, False)
if entry:
yield entry
info = data.get('info') or {}
return self.playlist_result(
entries(), info.get('id'), info.get('name') or info.get('title'))
+44 -58
View File
@@ -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',
'title': "GAZ Transformational Tuesdays W/ Landon & Stapes",
'id': "SILVuCL4bFtRwWTtOCFQQxAsBQsJljFtm9e4Z_bvo-A8B-nzUSYZRNuPl3qW5IGK",
'ext': "mp4"
'id': 'dUk_CNBETmZ5VA2BwEl-jjakPpJ3M1pcfVYAPRsoIbEByGsLjUZtaa4yCATQuOL3der8BlTwxQePl_j0.EImBkXzTIaPvdZO5',
'ext': 'mp4',
'title': 'China\'s "two sessions" and the new five-year plan',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
base_url, play_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, play_id)
password_protected = self._search_regex(r'<form[^>]+?id="(password_form)"', webpage, 'password field', fatal=False, default=None)
if password_protected is not None:
self._verify_video_password(url, display_id, webpage)
webpage = self._download_webpage(url, display_id)
try:
form = self._form_hidden_inputs('password_form', webpage)
except ExtractorError:
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')
title = self._html_search_regex([r"topic: \"(.*)\",", r"<title>(.*) - Zoom</title>"], webpage, 'title')
viewResolvtionsWidth = self._search_regex(r"viewResolvtionsWidth: (\d*)", webpage, 'res width', fatal=False)
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)
data = self._parse_json(self._search_regex(
r'(?s)window\.__data__\s*=\s*({.+?});',
webpage, 'data'), play_id, js_to_json)
return {
'id': display_id,
'title': title,
'formats': formats
'id': play_id,
'title': data['topic'],
'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']))
+30 -21
View File
@@ -533,11 +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,
@@ -551,7 +551,7 @@ 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')
@@ -679,7 +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',
@@ -707,17 +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 '
'or a lower bound of a range for randomized sleep before each download '
'(minimum possible number of seconds to sleep) when used along with '
'--max-sleep-interval'))
'Number of seconds to sleep before each download. '
'This is the minimum time to sleep when used along with --max-sleep-interval '
'(Alias: --min-sleep-interval)'))
workarounds.add_option(
'--max-sleep-interval', metavar='SECONDS',
dest='max_sleep_interval', type=float,
help=(
'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'))
help='Maximum number of seconds to sleep. Can only be used along with --min-sleep-interval')
workarounds.add_option(
'--sleep-subtitles', metavar='SECONDS',
dest='sleep_interval_subtitles', default=0, type=int,
@@ -739,7 +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,
@@ -982,9 +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 '
'--write-info-json, --write-description etc.'))
'Remove some private fields such as filenames from the infojson. '
'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,
@@ -1086,7 +1090,7 @@ 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, '
@@ -1143,13 +1147,18 @@ def parseOpts(overrideArguments=None):
metavar='FIELD:FORMAT', dest='metafromfield', action='append',
help=(
'Parse additional metadata like title/artist from other fields. '
'Give field name to extract data from, and format of the field seperated by a ":". '
'Give a template or field name to extract data from and the '
'format to interpret it as, 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. '
'similar syntax to the output template can be used for the FORMAT. '
'Similarly, the syntax for output template can be used for FIELD '
'to parse the data from multiple fields. '
'The parsed parameters replace any existing values and can be used in output templates. '
'This option can be used multiple times. '
'Example: --parse-metadata "title:%(artist)s - %(title)s" matches a title like '
'"Coldplay - Paradise". '
'Example: --parse-metadata "%(series)s %(episode_number)s:%(title)s" '
'sets the title using series and episode number. '
'Example (regex): --parse-metadata "description:Artist - (?P<artist>.+?)"'))
postproc.add_option(
'--xattrs',
@@ -1179,9 +1188,9 @@ 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,
+6 -3
View File
@@ -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'
@@ -133,7 +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),
@@ -194,7 +196,8 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
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:
+18 -15
View File
@@ -19,7 +19,6 @@ from ..utils import (
PostProcessingError,
prepend_extension,
shell_quote,
subtitles_filename,
dfxp2srt,
ISO639Utils,
process_communicate_or_kill,
@@ -62,7 +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(
@@ -166,7 +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 = [
@@ -208,7 +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 = [
@@ -486,7 +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
@@ -551,8 +550,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor):
add('title', ('track', 'title'))
add('date', 'upload_date')
add(('description', 'comment'), 'description')
add('purl', 'webpage_url')
add(('description', 'synopsis'), 'description')
add(('purl', 'comment'), 'webpage_url')
add('track', 'track_number')
add('artist', ('artist', 'creator', 'uploader', 'uploader_id'))
add('genre')
@@ -712,7 +711,6 @@ 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':
@@ -732,9 +730,9 @@ 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(
@@ -742,7 +740,7 @@ 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())
@@ -753,7 +751,8 @@ class FFmpegSubtitlesConvertorPP(FFmpegPostProcessor):
subs[lang] = {
'ext': 'srt',
'data': srt_data
'data': srt_data,
'filepath': srt_file,
}
if new_ext == 'srt':
@@ -767,8 +766,12 @@ 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
@@ -789,17 +792,17 @@ class FFmpegSplitChaptersPP(FFmpegPostProcessor):
if not self._downloader._ensure_dir_exists(encodeFilename(destination)):
return
chapter['_filename'] = destination
chapter['filepath'] = destination
self.to_screen('Chapter %03d; Destination: %s' % (number, destination))
return (
destination,
['-ss', compat_str(chapter['start_time']),
'-to', compat_str(chapter['end_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('There are no tracks to extract')
self.report_warning('Chapter information is unavailable')
return [], info
self.to_screen('Splitting video by chapters; %d chapters found' % len(chapters))
+21 -19
View File
@@ -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>.+)$'
def __init__(self, downloader, formats):
PostProcessor.__init__(self, downloader)
@@ -19,11 +18,20 @@ class MetadataFromFieldPP(PostProcessor):
match = re.match(self.regex, f)
assert match is not None
self._data.append({
'field': match.group('field'),
'format': match.group('format'),
'regex': self.format_to_regex(match.group('format'))})
'in': match.group('in'),
'out': match.group('out'),
'tmpl': self.field_to_template(match.group('in')),
'regex': self.format_to_regex(match.group('out')),
})
def format_to_regex(self, fmt):
@staticmethod
def field_to_template(tmpl):
if re.match(r'\w+$', 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>[^\r\n]+)' % 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']
if field not in info:
self.report_warning('Video doesnot have a %s' % field)
continue
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)
tmpl, info_copy = self._downloader.prepare_outtmpl(dictn['tmpl'], info)
data_to_parse = tmpl % info_copy
self.write_debug('Searching for r"%s" in %s' % (dictn['regex'], tmpl))
match = re.search(dictn['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
@@ -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'])
self.files_to_move[info['filepath']] = decodeFilename(finalpath)
info['__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)):
+3 -1
View File
@@ -6,6 +6,7 @@ from .common import PostProcessor
from ..compat import compat_shlex_split
from ..utils import (
check_executable,
cli_option,
encodeArgument,
encodeFilename,
shell_quote,
@@ -31,7 +32,7 @@ class SponSkrubPP(PostProcessor):
if path:
raise PostProcessingError('sponskrub not found in "%s"' % path)
else:
raise PostProcessingError('sponskrub not found. Please install or provide the path using --sponskrub-path.')
raise PostProcessingError('sponskrub not found. Please install or provide the path using --sponskrub-path')
def get_exe(self, path=''):
if not path or not check_executable(path, ['-h']):
@@ -70,6 +71,7 @@ class SponSkrubPP(PostProcessor):
cmd = [self.path]
if not self.cutout:
cmd += ['-chapter']
cmd += cli_option(self._downloader.params, '-proxy', 'proxy')
cmd += compat_shlex_split(self.args) # For backward compatibility
cmd += self._configuration_args(self._exe_name, use_compat=False)
cmd += ['--', information['id'], filename, temp_filename]
+25 -1
View File
@@ -1836,7 +1836,7 @@ def write_json_file(obj, fn):
try:
with tf:
json.dump(obj, tf)
json.dump(obj, tf, default=repr)
if sys.platform == 'win32':
# Need to remove existing file on Windows, else os.rename raises
# WindowsError or FileExistsError.
@@ -2423,6 +2423,15 @@ class DownloadError(YoutubeDLError):
self.exc_info = exc_info
class EntryNotInPlaylist(YoutubeDLError):
"""Entry not in playlist exception.
This exception will be thrown by YoutubeDL when a requested entry
is not found in the playlist info_dict
"""
pass
class SameFileError(YoutubeDLError):
"""Same File exception.
@@ -4106,6 +4115,7 @@ def parse_age_limit(s):
m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
if m:
return int(m.group('age'))
s = s.upper()
if s in US_RATINGS:
return US_RATINGS[s]
m = re.match(r'^TV[_-]?(%s)$' % '|'.join(k[3:] for k in TV_PARENTAL_GUIDELINES), s)
@@ -4195,6 +4205,20 @@ OUTTMPL_TYPES = {
'pl_infojson': 'info.json',
}
# 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
'''
def limit_length(s, length):
""" Add ellipses to overly long strings """
+1 -1
View File
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2021.03.07'
__version__ = '2021.03.24'