Compare commits

...
20 Commits
Author SHA1 Message Date
pukkandan aa837ddf06 Release 2021.02.15 2021-02-16 04:04:27 +05:30
pukkandan a718ef84c8 [youtube] Fix for new accounts
Cookies for some new accounts doesn't work with age-gated videos without `has_verified=1`
2021-02-16 03:20:06 +05:30
shirt-devandGitHub 44f705d001 #88 Implement SHA256 checking for autoupdater
* Also fix bugs from e5813e53f0

Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com>

:ci skip dl
2021-02-16 02:36:42 +05:30
shirt-devandGitHub 47930b73a5 Fix build.yml hashing and crypto support (#87)
Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com>
2021-02-16 00:46:23 +05:30
pukkandan 1de75fa129 [ExtractAudio] Don't re-encode when file is already in a common audio format (Closes #58)
Fixes: https://github.com/blackjack4494/youtube-dlc/issues/214
Fixes: https://github.com/ytdl-org/youtube-dl/issues/28006
2021-02-15 23:22:11 +05:30
pukkandan 6285297795 [rumble] Add support for video page (Closes #80) 2021-02-15 20:08:27 +05:30
pukkandan e5813e53f0 Improve build/updater
* Fix `get_executable_path` in UNIX
* Update `x86.exe` correctly
* Exit immediately in windows once the update process starts so that the file handle is released correctly
* Show `exe`/`zip`/`source` and 32/64bit in verbose message
* Look for both `yt-dlp` and `youtube-dlc` in releases. This ensures that the updater will keep working when the binary name is changed to yt-dlp
* Disable pycryptodome in win_x86 since it causes `distutils.errors.DistutilsPlatformError: Microsoft Visual C++ 10.0 is required`
2021-02-15 15:41:40 +05:30
siikamiikaandGitHub 273762c8d0 #86 [youtube_live_chat] Use POST API (Closes #82)
YouTube has removed support for the old GET based live chat API, and it's now returning 404

Authored by siikamiika
2021-02-15 15:27:21 +05:30
shirt-devandGitHub 7620cd46c3 #79 Fix HLS AES-128 with multiple keys in external downloaders
Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com>
2021-02-13 21:45:41 +05:30
pukkandan 068693675e Cleanup some code and fix typos
:ci skip dl
2021-02-12 20:32:49 +05:30
pukkandan 1ea2412927 Minor bugfixes
* `__real_download` should be false when ffmpeg unavailable and no download
* Mistakes in #70
* `allow_playlist_files` was not correctly pass through
2021-02-12 20:29:29 +05:30
63ad4d43eb #70 Allow downloading of unplayable video formats
Video postprocessors are also turned off when this option is used

Co-authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com>
Co-authored-by: pukkandan <pukkandan@gmail.com>
2021-02-12 09:21:59 +05:30
pukkandan 584bab3766 [sponskrub] Print ffmpeg output and errors to terminal
The ffmpeg run can be long when using `--sponskrub-cut`. So progress needs to be printed

:ci skip dl
2021-02-12 01:40:08 +05:30
shirt-devandGitHub fc2119f210 #76 Fix for empty HTTP head requests
Related: https://github.com/ytdl-org/youtube-dl/issues/7181

Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com> (shirt-dev)
2021-02-11 21:31:34 +05:30
shirt-devandGitHub 5d25607a3a #75 Change optional dependency from Crypto to pycryptodome (Closes #74)
Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com> (shirt-dev)

pycryptodome is an in-place replacement for Crypto and is more actively developed
2021-02-11 17:16:02 +05:30
pukkandan a96c6d154a [youtube] Fix search continuations 2021-02-11 17:10:38 +05:30
pukkandan cc2db87805 Update to ytdl-2021.02.10
Except: [archiveorg] Fix and improve extraction (5fc53690cbe6abb11941a3f4846b566a7472753e)
2021-02-11 03:03:39 +05:30
shirt-devandGitHub 539d158c50 #72 Fix issue with unicode filenames in aria2c (Closes #71)
Authored-by: shirtjs <2660574+shirtjs@users.noreply.github.com> (shirt-dev)
2021-02-11 02:27:18 +05:30
fb198a8a9c #49 [niconico] Improved extraction and support encrypted/SMILE movies
Co-authored-by: tsukumijima <tsukumijima@users.noreply.github.com>
Co-authored-by: tsukumi <39271166+tsukumijima@users.noreply.github.com>
Co-authored-by: Bepis <36346617+bbepis@users.noreply.github.com>
Co-authored-by: pukkandan <pukkandan@gmail.com>
2021-02-10 12:15:20 +05:30
pukkandan 8d801631cf [version] update
:ci skip all
2021-02-10 02:06:49 +05:30
61 changed files with 1127 additions and 618 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 youtube-dlc:
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.02.04. If it's not, see https://github.com/pukkandan/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 `youtube-dlc --version` and ensure your version is 2021.02.09. If it's not, see https://github.com/pukkandan/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/pukkandan/yt-dlp.
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running yt-dlp version **2021.02.04**
- [ ] I've verified that I'm running yt-dlp version **2021.02.09**
- [ ] 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 youtube-dlc with (`youtube-dlc -v
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] yt-dlp version 2021.02.04
[debug] yt-dlp version 2021.02.09
[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 youtube-dlc:
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.02.04. If it's not, see https://github.com/pukkandan/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 `youtube-dlc --version` and ensure your version is 2021.02.09. If it's not, see https://github.com/pukkandan/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/pukkandan/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/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running yt-dlp version **2021.02.04**
- [ ] I've verified that I'm running yt-dlp version **2021.02.09**
- [ ] 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 youtube-dlc:
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.02.04. If it's not, see https://github.com/pukkandan/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 `youtube-dlc --version` and ensure your version is 2021.02.09. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running yt-dlp version **2021.02.04**
- [ ] I've verified that I'm running yt-dlp version **2021.02.09**
- [ ] 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 youtube-dlc:
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.02.04. If it's not, see https://github.com/pukkandan/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 `youtube-dlc --version` and ensure your version is 2021.02.09. If it's not, see https://github.com/pukkandan/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/pukkandan/yt-dlp.
- Search the bugtracker for similar issues: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
@@ -30,7 +30,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running yt-dlp version **2021.02.04**
- [ ] I've verified that I'm running yt-dlp version **2021.02.09**
- [ ] 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 youtube-dlc with (`youtube-dlc -v
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] yt-dlp version 2021.02.04
[debug] yt-dlp version 2021.02.09
[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 youtube-dlc:
- First of, make sure you are using the latest version of yt-dlp. Run `youtube-dlc --version` and ensure your version is 2021.02.04. If it's not, see https://github.com/pukkandan/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 `youtube-dlc --version` and ensure your version is 2021.02.09. If it's not, see https://github.com/pukkandan/yt-dlp on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: https://github.com/pukkandan/yt-dlp. DO NOT post duplicates.
- Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running yt-dlp version **2021.02.04**
- [ ] I've verified that I'm running yt-dlp version **2021.02.09**
- [ ] I've searched the bugtracker for similar feature requests including closed ones
+13 -11
View File
@@ -55,9 +55,7 @@ jobs:
asset_content_type: application/octet-stream
- name: Get SHA2-256SUMS for youtube-dlc
id: sha2_file
env:
SHA2: ${{ hashFiles('youtube-dlc') }}
run: echo "::set-output name=sha2_unix::$SHA2"
run: echo "::set-output name=sha2_unix::$(sha256sum youtube-dlc)"
- name: Install dependencies for pypi
run: |
python -m pip install --upgrade pip
@@ -75,6 +73,9 @@ jobs:
runs-on: windows-latest
outputs:
sha2_windows: ${{ steps.sha2_file_win.outputs.sha2_windows }}
needs: build_unix
steps:
@@ -84,7 +85,7 @@ jobs:
with:
python-version: '3.8'
- name: Install Requirements
run: pip install pyinstaller mutagen Crypto
run: pip install pyinstaller mutagen pycryptodome
- name: Bump version
id: bump_version
run: python devscripts/update-version.py
@@ -104,14 +105,15 @@ jobs:
asset_content_type: application/vnd.microsoft.portable-executable
- name: Get SHA2-256SUMS for youtube-dlc.exe
id: sha2_file_win
env:
SHA2_win: ${{ hashFiles('dist/youtube-dlc.exe') }}
run: echo "::set-output name=sha2_windows::$SHA2_win"
run: echo "::set-output name=sha2_windows::$(certUtil -hashfile dist\youtube-dlc.exe SHA256 | findstr -v :)"
build_windows32:
runs-on: windows-latest
outputs:
sha2_windows32: ${{ steps.sha2_file_win32.outputs.sha2_windows32 }}
needs: [build_unix, build_windows]
steps:
@@ -121,8 +123,10 @@ jobs:
with:
python-version: '3.4.4'
architecture: 'x86'
- name: Install VS libs
run: choco install vcexpress2010
- name: Install Requirements for 32 Bit
run: pip install pyinstaller==3.5 mutagen Crypto
run: pip install pyinstaller==3.5 mutagen pycryptodome
- name: Bump version
id: bump_version
run: python devscripts/update-version.py
@@ -142,9 +146,7 @@ jobs:
asset_content_type: application/vnd.microsoft.portable-executable
- name: Get SHA2-256SUMS for youtube-dlc_x86.exe
id: sha2_file_win32
env:
SHA2_win32: ${{ hashFiles('dist/youtube-dlc_x86.exe') }}
run: echo "::set-output name=sha2_windows32::$SHA2_win32"
run: echo "::set-output name=sha2_windows32::$(certUtil -hashfile dist\youtube-dlc_x86.exe SHA256 | findstr -v :)"
- name: Make SHA2-256SUMS file
env:
SHA2_WINDOWS: ${{ needs.build_windows.outputs.sha2_windows }}
+3
View File
@@ -55,6 +55,9 @@ youtube-dlc
*.swf
*.part
*.ytdl
*.frag
*.frag.urls
*.aria2
*.swp
*.ogg
*.opus
+26 -1
View File
@@ -17,6 +17,31 @@
-->
### 2021.02.15
* **Merge youtube-dl:** Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
* [niconico] Improved extraction and support encrypted/SMILE movies
* Fix HLS AES-128 with multiple keys in external downloaders
* [youtube_live_chat] Fix by using POST API
* [rumble] Add support for video page
* Option to allow downloading unplayable video formats (`--allow-unplayable-formats`)
* [ExtractAudio] Don't re-encode when file is already in a common audio format
* Change optional dependency to `pycryptodome`
* [youtube] Fix search continuations
* [youtube] Fix for new accounts
* Improve build/updater:
* Fix SHA256 calculation in build and implement hash checking for updater
* Exit immediately in windows once the update process starts
* Fix updater for `x86.exe`
* Updater looks for both `yt-dlp` and `youtube-dlc` in releases for future-proofing
* Fix issue with unicode filenames in aria2c
* Fix `allow_playlist_files` not being correctly passed through
* Fix for empty HTTP head requests
* Fix `get_executable_path` in UNIX
* [sponskrub] Print ffmpeg output and errors to terminal
* `__real_download` should be false when ffmpeg unavailable and no download
* Show `exe`/`zip`/`source` and 32/64bit in verbose message
### 2021.02.09
* **aria2c support for DASH/HLS**: by [shirt](https://github.com/shirt-dev)
* **Implement Updater** (`-U`) by [shirt](https://github.com/shirt-dev)
@@ -205,7 +230,7 @@
* Changed video format sorting to show video only files and video+audio files together.
* Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
* Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options]README.md(#internet-shortcut-options) for details
* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
* **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-options-sponsorblock) for details
* Added `--force-download-archive` (`--force-write-archive`) by [h-h-h-h](https://github.com/h-h-h-h)
* Added `--list-formats-as-table`, `--list-formats-old`
+1 -1
View File
@@ -4,7 +4,7 @@ man: README.txt youtube-dlc.1 youtube-dlc.bash-completion youtube-dlc.zsh youtub
clean:
rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
rm -rf youtube-dlc.1.temp.md youtube-dlc.1 youtube-dlc.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dlc.tar.gz youtube-dlc.zsh youtube-dlc.fish youtube_dlc/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec *.frag *.frag.urls *.frag.aria2 CONTRIBUTING.md.tmp youtube-dlc youtube-dlc.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete
+21 -15
View File
@@ -56,18 +56,20 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
* **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
* **Merged with youtube-dl v2021.02.04.1**: 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 v2021.02.10**: 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/pukkandan/yt-dlp/pull/31) for details.
* **Youtube improvements**:
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and support downloading multiple pages of content
* Youtube search works correctly (`ytsearch:`, `ytsearchdate:`) along with Search URLs
* All Youtube Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`) works correctly and supports downloading multiple pages of content
* Youtube search (`ytsearch:`, `ytsearchdate:`) along with Search URLs works correctly
* Redirect channel's home URL automatically to `/video` to preserve the old behaviour
* **Aria2c with HLS/DASH**: You can use aria2c as the external downloader for DASH(mpd) and HLS(m3u8) formats. No more slow ffmpeg/native downloads
* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina
* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina, rumble
* **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
@@ -81,6 +83,8 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
* **Improvements**: Multiple `--postprocessor-args` and `--external-downloader-args`, Date/time formatting in `-o`, faster archive checking, more [format selection options](#format-selection) etc
* **Self-updater**: The releases can be updated using `youtube-dlc -U`
See [changelog](Changelog.md) or [commits](https://github.com/pukkandan/yt-dlp/commits) for the full list of changes
@@ -93,20 +97,21 @@ If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the
# INSTALLATION
You can install yt-dlp using one of the following methods:
* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest) (recommended method)
* Use [PyPI package](https://pypi.org/project/yt-dlp): `python -m pip install --upgrade yt-dlp`
* Download the binary from the [latest release](https://github.com/pukkandan/yt-dlp/releases/latest)
* Use pip+git: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp.git@release`
* Install master branch: `python -m pip install --upgrade git+https://github.com/pukkandan/yt-dlp`
### UPDATE
`-U` does not work. Simply repeat the install process to update.
Starting from version `2021.02.09`, you can use `youtube-dlc -U` to update if you are using the provided release.
If you are using `pip`, simply re-run the same command that was used to install the program.
### COMPILE
**For Windows**:
To build the Windows executable, you must have pyinstaller (and optionally mutagen and Crypto)
To build the Windows executable, you must have pyinstaller (and optionally mutagen and pycryptodome)
python -m pip install --upgrade pyinstaller mutagen Crypto
python -m pip install --upgrade pyinstaller mutagen pycryptodome
Once you have all the necessary dependancies installed, just run `py pyinst.py`. The executable will be built for the same architecture (32/64 bit) as the python used to build it. It is strongly reccomended to use python3 although python2.6+ is supported.
@@ -136,9 +141,9 @@ Then simply type this
## General Options:
-h, --help Print this help text and exit
--version Print program version and exit
-U, --update [BROKEN] Update this program to latest
version. Make sure that you have sufficient
permissions (run with sudo if needed)
-U, --update Update this program to latest version. Make
sure that you have sufficient permissions
(run with sudo if needed)
-i, --ignore-errors Continue on download errors, for example to
skip unavailable videos in a playlist
(default) (Alias: --no-abort-on-error)
@@ -463,10 +468,6 @@ Then simply type this
files in the current directory to debug
problems
--print-traffic Display sent and read HTTP traffic
-C, --call-home [Broken] Contact the youtube-dlc server for
debugging
--no-call-home Do not contact the youtube-dlc server for
debugging (default)
## Workarounds:
--encoding ENCODING Force the specified encoding (experimental)
@@ -539,6 +540,11 @@ Then simply type this
bestvideo+bestaudio), output to given
container format. One of mkv, mp4, ogg,
webm, flv. Ignored if no merge is required
--allow-unplayable-formats Allow unplayable formats to be listed and
downloaded. All video postprocessing will
also be turned off
--no-allow-unplayable-formats Do not allow unplayable formats to be
listed or downloaded (default)
## Subtitle Options:
--write-subs Write subtitle file
+2 -2
View File
@@ -1,6 +1,5 @@
# Supported sites
- **1tv**: Первый канал
- **1up.com**
- **20min**
- **220.ro**
- **23video**
@@ -394,6 +393,8 @@
- **HungamaSong**
- **Hypem**
- **ign.com**
- **IGNArticle**
- **IGNVideo**
- **IHeartRadio**
- **iheartradio:podcast**
- **imdb**: Internet Movie Database trailers
@@ -701,7 +702,6 @@
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
- **pcmag**
- **PearVideo**
- **PeerTube**
- **People**
+1 -1
View File
@@ -1,2 +1,2 @@
mutagen
Crypto
pycryptodome
+1 -1
View File
@@ -20,7 +20,7 @@ LONG_DESCRIPTION = '\n\n'.join((
'**PS**: Many links in this document will not work since this is a copy of the README.md from Github',
open("README.md", "r", encoding="utf-8").read()))
REQUIREMENTS = ['mutagen', 'Crypto']
REQUIREMENTS = ['mutagen', 'pycryptodome']
if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
+10 -21
View File
@@ -19,55 +19,46 @@ from youtube_dlc.compat import compat_str, compat_urlretrieve
_TESTS = [
(
'https://s.ytimg.com/yts/jsbin/html5player-vflHOr_nV.js',
'js',
86,
'>=<;:/.-[+*)(\'&%$#"!ZYX0VUTSRQPONMLKJIHGFEDCBA\\yxwvutsrqponmlkjihgfedcba987654321',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfldJ8xgI.js',
'js',
85,
'3456789a0cdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRS[UVWXYZ!"#$%&\'()*+,-./:;<=>?@',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-vfle-mVwz.js',
'js',
90,
']\\[@?>=<;:/.-,+*)(\'&%$#"hZYXWVUTSRQPONMLKJIHGFEDCBAzyxwvutsrqponmlkjiagfedcb39876',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl0Cbn9e.js',
'js',
84,
'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVW@YZ!"#$%&\'()*+,-./:;<=',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js',
'js',
'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
'js',
84,
'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
'js',
83,
'123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
)
@@ -78,6 +69,10 @@ class TestPlayerInfo(unittest.TestCase):
def test_youtube_extract_player_info(self):
PLAYER_URLS = (
('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
# obsolete
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
@@ -100,13 +95,13 @@ class TestSignature(unittest.TestCase):
os.mkdir(self.TESTDATA_DIR)
def make_tfunc(url, stype, sig_input, expected_sig):
def make_tfunc(url, sig_input, expected_sig):
m = re.match(r'.*-([a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.[a-z]+$', url)
assert m, '%r should follow URL format' % url
test_id = m.group(1)
def test_func(self):
basename = 'player-%s.%s' % (test_id, stype)
basename = 'player-%s.js' % test_id
fn = os.path.join(self.TESTDATA_DIR, basename)
if not os.path.exists(fn):
@@ -114,22 +109,16 @@ def make_tfunc(url, stype, sig_input, expected_sig):
ydl = FakeYDL()
ie = YoutubeIE(ydl)
if stype == 'js':
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()
func = ie._parse_sig_js(jscode)
else:
assert stype == 'swf'
with open(fn, 'rb') as testf:
swfcode = testf.read()
func = ie._parse_sig_swf(swfcode)
with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read()
func = ie._parse_sig_js(jscode)
src_sig = (
compat_str(string.printable[:sig_input])
if isinstance(sig_input, int) else sig_input)
got_sig = func(src_sig)
self.assertEqual(got_sig, expected_sig)
test_func.__name__ = str('test_signature_' + stype + '_' + test_id)
test_func.__name__ = str('test_signature_js_' + test_id)
setattr(TestSignature, test_func.__name__, test_func)
+28 -12
View File
@@ -27,6 +27,7 @@ import traceback
import random
from string import ascii_letters
from zipimport import zipimporter
from .compat import (
compat_basestring,
@@ -179,6 +180,7 @@ class YoutubeDL(object):
of 'skip_download' or 'simulate'.
simulate: Do not download the video files.
format: Video format code. see "FORMAT SELECTION" for more details.
allow_unplayable_formats: Allow unplayable formats to be extracted and downloaded.
format_sort: How to sort the video formats. see "Sorting Formats"
for more details.
format_sort_force: Force the given format_sort. see "Sorting Formats"
@@ -2291,10 +2293,15 @@ class YoutubeDL(object):
if info_dict.get('requested_formats') is not None:
downloaded = []
merger = FFmpegMergerPP(self)
if not merger.available:
self.report_warning('You have requested multiple '
'formats but ffmpeg is not installed.'
' The formats won\'t be merged.')
if self.params.get('allow_unplayable_formats'):
self.report_warning(
'You have requested merging of multiple formats '
'while also allowing unplayable formats to be downloaded. '
'The formats won\'t be merged to prevent data corruption.')
elif not merger.available:
self.report_warning(
'You have requested merging of multiple formats but ffmpeg is not installed. '
'The formats won\'t be merged.')
def compatible_formats(formats):
# TODO: some formats actually allow this (mkv, webm, ogg, mp4), but not all of them.
@@ -2334,6 +2341,7 @@ class YoutubeDL(object):
full_filename = correct_ext(full_filename)
temp_filename = correct_ext(temp_filename)
dl_filename = existing_file(full_filename, temp_filename)
info_dict['__real_download'] = False
if dl_filename is None:
for f in requested_formats:
new_info = dict(info_dict)
@@ -2345,12 +2353,13 @@ class YoutubeDL(object):
return
downloaded.append(fname)
partial_success, real_download = dl(fname, new_info)
info_dict['__real_download'] = info_dict['__real_download'] or real_download
success = success and partial_success
if merger.available:
if merger.available and not self.params.get('allow_unplayable_formats'):
info_dict['__postprocessors'].append(merger)
info_dict['__files_to_merge'] = downloaded
# Even if there were no downloads, it is being merged only now
info_dict['__real_download'] = True
info_dict['__files_to_merge'] = downloaded
# Even if there were no downloads, it is being merged only now
info_dict['__real_download'] = True
else:
# Just a single file
dl_filename = existing_file(full_filename, temp_filename)
@@ -2681,7 +2690,7 @@ class YoutubeDL(object):
'|',
format_field(f, 'filesize', ' %s', func=format_bytes) + format_field(f, 'filesize_approx', '~%s', func=format_bytes),
format_field(f, 'tbr', '%4dk'),
f.get('protocol').replace('http_dash_segments', 'dash').replace("native", "n"),
f.get('protocol').replace('http_dash_segments', 'dash').replace("native", "n").replace('niconico_', ''),
'|',
format_field(f, 'vcodec', default='unknown').replace('none', ''),
format_field(f, 'vbr', '%4dk'),
@@ -2762,7 +2771,12 @@ class YoutubeDL(object):
self.get_encoding()))
write_string(encoding_str, encoding=None)
self._write_string('[debug] yt-dlp version %s\n' % __version__)
source = (
'(exe)' if hasattr(sys, 'frozen')
else '(zip)' if isinstance(globals().get('__loader__'), zipimporter)
else '(source)' if os.path.basename(sys.argv[0]) == '__main__.py'
else '')
self._write_string('[debug] yt-dlp version %s %s\n' % (__version__, source))
if _LAZY_LOADER:
self._write_string('[debug] Lazy loading extractors enabled\n')
if _PLUGIN_CLASSES:
@@ -2789,8 +2803,10 @@ class YoutubeDL(object):
return impl_name + ' version %d.%d.%d' % sys.pypy_version_info[:3]
return impl_name
self._write_string('[debug] Python version %s (%s) - %s\n' % (
platform.python_version(), python_implementation(),
self._write_string('[debug] Python version %s (%s %s) - %s\n' % (
platform.python_version(),
python_implementation(),
platform.architecture()[0],
platform_name()))
exe_versions = FFmpegPostProcessor.get_versions(self)
+52 -10
View File
@@ -212,9 +212,6 @@ def _real_main(argv=None):
if opts.recodevideo is not None:
if opts.recodevideo not in REMUX_EXTENSIONS:
parser.error('invalid video recode format specified')
if opts.remuxvideo and opts.recodevideo:
opts.remuxvideo = None
write_string('WARNING: --remux-video is ignored since --recode-video was given\n', out=sys.stderr)
if opts.remuxvideo is not None:
opts.remuxvideo = opts.remuxvideo.replace(' ', '')
remux_regex = r'{0}(?:/{0})*$'.format(r'(?:\w+>)?(?:%s)' % '|'.join(REMUX_EXTENSIONS))
@@ -265,6 +262,40 @@ def _real_main(argv=None):
any_printing = opts.print_json
download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
def report_conflict(arg1, arg2):
write_string('WARNING: %s is ignored since %s was given\n' % (arg2, arg1), out=sys.stderr)
if opts.remuxvideo and opts.recodevideo:
report_conflict('--recode-video', '--remux-video')
opts.remuxvideo = False
if opts.allow_unplayable_formats:
if opts.extractaudio:
report_conflict('--allow-unplayable-formats', '--extract-audio')
opts.extractaudio = False
if opts.remuxvideo:
report_conflict('--allow-unplayable-formats', '--remux-video')
opts.remuxvideo = False
if opts.recodevideo:
report_conflict('--allow-unplayable-formats', '--recode-video')
opts.recodevideo = False
if opts.addmetadata:
report_conflict('--allow-unplayable-formats', '--add-metadata')
opts.addmetadata = False
if opts.embedsubtitles:
report_conflict('--allow-unplayable-formats', '--embed-subs')
opts.embedsubtitles = False
if opts.embedthumbnail:
report_conflict('--allow-unplayable-formats', '--embed-thumbnail')
opts.embedthumbnail = False
if opts.xattrs:
report_conflict('--allow-unplayable-formats', '--xattrs')
opts.xattrs = False
if opts.fixup and opts.fixup.lower() not in ('never', 'ignore'):
report_conflict('--allow-unplayable-formats', '--fixup')
opts.fixup = 'never'
if opts.sponskrub:
report_conflict('--allow-unplayable-formats', '--sponskrub')
opts.sponskrub = False
# PostProcessors
postprocessors = []
if opts.metafromfield:
@@ -348,12 +379,15 @@ def _real_main(argv=None):
'when': 'aftermove'
})
_args_compat_warning = 'WARNING: %s given without specifying name. The arguments will be given to all %s\n'
def report_args_compat(arg, name):
write_string(
'WARNING: %s given without specifying name. The arguments will be given to all %s\n' % (arg, name),
out=sys.stderr)
if 'default' in opts.external_downloader_args:
write_string(_args_compat_warning % ('--external-downloader-args', 'external downloaders'), out=sys.stderr),
report_args_compat('--external-downloader-args', 'external downloaders')
if 'default-compat' in opts.postprocessor_args and 'default' not in opts.postprocessor_args:
write_string(_args_compat_warning % ('--post-processor-args', 'post-processors'), out=sys.stderr),
report_args_compat('--post-processor-args', 'post-processors')
opts.postprocessor_args.setdefault('sponskrub', [])
opts.postprocessor_args['default'] = opts.postprocessor_args['default-compat']
@@ -393,6 +427,7 @@ def _real_main(argv=None):
'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format,
'allow_unplayable_formats': opts.allow_unplayable_formats,
'format_sort': opts.format_sort,
'format_sort_force': opts.format_sort_force,
'allow_multiple_video_streams': opts.allow_multiple_video_streams,
@@ -431,6 +466,7 @@ def _real_main(argv=None):
'writedescription': opts.writedescription,
'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson or opts.getcomments,
'allow_playlist_files': opts.allow_playlist_files,
'getcomments': opts.getcomments,
'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
@@ -513,16 +549,22 @@ def _real_main(argv=None):
}
with YoutubeDL(ydl_opts) as ydl:
# Update version
if opts.update_self:
update_self(ydl.to_screen, opts.verbose, ydl._opener)
actual_use = len(all_urls) or opts.load_info_filename
# Remove cache dir
if opts.rm_cachedir:
ydl.cache.remove()
# Update version
if opts.update_self:
# If updater returns True, exit. Required for windows
if update_self(ydl.to_screen, opts.verbose, ydl._opener):
if actual_use:
parser.error('The program must exit for the update to complete')
sys.exit()
# Maybe do nothing
if (len(all_urls) < 1) and (opts.load_info_filename is None):
if not actual_use:
if opts.update_self or opts.rm_cachedir:
sys.exit()
+2
View File
@@ -21,6 +21,7 @@ from .http import HttpFD
from .rtmp import RtmpFD
from .rtsp import RtspFD
from .ism import IsmFD
from .niconico import NiconicoDmcFD
from .youtube_live_chat import YoutubeLiveChatReplayFD
from .external import (
get_external_downloader,
@@ -36,6 +37,7 @@ PROTOCOL_MAP = {
'f4m': F4mFD,
'http_dash_segments': DashSegmentsFD,
'ism': IsmFD,
'niconico_dmc': NiconicoDmcFD,
'youtube_live_chat_replay': YoutubeLiveChatReplayFD,
}
+26 -19
View File
@@ -5,7 +5,6 @@ import re
import subprocess
import sys
import time
import shutil
try:
from Crypto.Cipher import AES
@@ -32,6 +31,7 @@ from ..utils import (
is_outdated_version,
process_communicate_or_kill,
sanitized_Request,
sanitize_open,
)
@@ -126,23 +126,29 @@ class ExternalFD(FileDownloader):
for [i, url] in enumerate(info_dict['url_list']):
tmpsegmentname = '%s_%s.frag' % (tmpfilename, i)
file_list.append(tmpsegmentname)
with open(tmpfilename, 'wb') as dest:
for i in file_list:
if 'decrypt_info' in info_dict:
decrypt_info = info_dict['decrypt_info']
with open(i, 'rb') as src:
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV')
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
encrypted_data = src.read()
decrypted_data = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(encrypted_data)
dest.write(decrypted_data)
else:
shutil.copyfileobj(open(i, 'rb'), dest)
key_list = info_dict.get('key_list')
decrypt_info = None
dest, _ = sanitize_open(tmpfilename, 'wb')
for i, file in enumerate(file_list):
src, _ = sanitize_open(file, 'rb')
if key_list:
decrypt_info = next((x for x in key_list if x['INDEX'] == i), decrypt_info)
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV')
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
encrypted_data = src.read()
decrypted_data = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(encrypted_data)
dest.write(decrypted_data)
else:
shutil.copyfileobj(open(i, 'rb'), dest)
fragment_data = src.read()
dest.write(fragment_data)
else:
fragment_data = src.read()
dest.write(fragment_data)
src.close()
dest.close()
if not self.params.get('keep_fragments', False):
for file_path in file_list:
try:
@@ -263,8 +269,9 @@ class Aria2cFD(ExternalFD):
for [i, url] in enumerate(info_dict['url_list']):
tmpsegmentname = '%s_%s.frag' % (os.path.basename(tmpfilename), i)
url_list.append('%s\n\tout=%s' % (url, tmpsegmentname))
with open(url_list_file, 'w') as f:
f.write('\n'.join(url_list))
stream, _ = sanitize_open(url_list_file, 'wb')
stream.write('\n'.join(url_list).encode('utf-8'))
stream.close()
cmd += ['-i', url_list_file]
else:
+8 -7
View File
@@ -267,13 +267,14 @@ class F4mFD(FragmentFD):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+ doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = remove_encrypted_media(media)
if not self.params.get('allow_unplayable_formats'):
for e in (doc.findall(_add_ns('drmAdditionalHeader'))
+ doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = remove_encrypted_media(media)
if not media:
self.report_error('Unsupported DRM')
return media
+2 -1
View File
@@ -95,11 +95,12 @@ class FragmentFD(FileDownloader):
frag_index_stream.write(json.dumps({'downloader': downloader}))
frag_index_stream.close()
def _download_fragment(self, ctx, frag_url, info_dict, headers=None):
def _download_fragment(self, ctx, frag_url, info_dict, headers=None, request_data=None):
fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
fragment_info_dict = {
'url': frag_url,
'http_headers': headers or info_dict.get('http_headers'),
'request_data': request_data,
}
success = ctx['dl'].download(fragment_filename, fragment_info_dict)
if not success:
+14 -6
View File
@@ -29,9 +29,8 @@ class HlsFD(FragmentFD):
FD_NAME = 'hlsnative'
@staticmethod
def can_download(manifest, info_dict):
UNSUPPORTED_FEATURES = (
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
def can_download(manifest, info_dict, allow_unplayable_formats=False):
UNSUPPORTED_FEATURES = [
# r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
# Live streams heuristic does not always work (e.g. geo restricted to Germany
@@ -50,7 +49,11 @@ class HlsFD(FragmentFD):
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.2
# 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
# 5. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.5
)
]
if not allow_unplayable_formats:
UNSUPPORTED_FEATURES += [
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
]
check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
check_results.append(can_decrypt_frag or not is_aes128_enc)
@@ -66,7 +69,7 @@ class HlsFD(FragmentFD):
man_url = urlh.geturl()
s = urlh.read().decode('utf-8', 'ignore')
if not self.can_download(s, info_dict):
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('pycrypto not found. Please install it.')
return False
@@ -131,6 +134,7 @@ class HlsFD(FragmentFD):
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
key_list = []
byte_range = {}
frag_index = 0
ad_frag_next = False
@@ -212,6 +216,10 @@ class HlsFD(FragmentFD):
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
key_data = decrypt_info.copy()
key_data['INDEX'] = frag_index
key_list.append(key_data)
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
elif line.startswith('#EXT-X-BYTERANGE'):
@@ -229,7 +237,7 @@ class HlsFD(FragmentFD):
if real_downloader:
info_copy = info_dict.copy()
info_copy['url_list'] = fragment_urls
info_copy['decrypt_info'] = decrypt_info
info_copy['key_list'] = key_list
fd = real_downloader(self.ydl, self.params)
# TODO: Make progress updates work without hooking twice
# for ph in self._progress_hooks:
+3 -2
View File
@@ -27,6 +27,7 @@ from ..utils import (
class HttpFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
request_data = info_dict.get('request_data', None)
class DownloadContext(dict):
__getattr__ = dict.get
@@ -101,7 +102,7 @@ class HttpFD(FileDownloader):
range_end = ctx.data_len - 1
has_range = range_start is not None
ctx.has_range = has_range
request = sanitized_Request(url, None, headers)
request = sanitized_Request(url, request_data, headers)
if has_range:
set_range(request, range_start, range_end)
# Establish connection
@@ -152,7 +153,7 @@ class HttpFD(FileDownloader):
try:
# Open the connection again without the range header
ctx.data = self.ydl.urlopen(
sanitized_Request(url, None, headers))
sanitized_Request(url, request_data, headers))
content_length = ctx.data.info()['Content-Length']
except (compat_urllib_error.HTTPError, ) as err:
if err.code < 500 or err.code >= 600:
+54
View File
@@ -0,0 +1,54 @@
# coding: utf-8
from __future__ import unicode_literals
import threading
from .common import FileDownloader
from ..downloader import _get_real_downloader
from ..extractor.niconico import NiconicoIE
from ..compat import compat_urllib_request
class NiconicoDmcFD(FileDownloader):
""" Downloading niconico douga from DMC with heartbeat """
FD_NAME = 'niconico_dmc'
def real_download(self, filename, info_dict):
self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
ie = NiconicoIE(self.ydl)
info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
fd = _get_real_downloader(info_dict, params=self.params)(self.ydl, self.params)
success = download_complete = False
timer = [None]
heartbeat_lock = threading.Lock()
heartbeat_url = heartbeat_info_dict['url']
heartbeat_data = heartbeat_info_dict['data']
heartbeat_interval = heartbeat_info_dict.get('interval', 30)
self.to_screen('[%s] Heartbeat with %s second interval...' % (self.FD_NAME, heartbeat_interval))
def heartbeat():
try:
compat_urllib_request.urlopen(url=heartbeat_url, data=heartbeat_data.encode())
except Exception:
self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
with heartbeat_lock:
if not download_complete:
timer[0] = threading.Timer(heartbeat_interval, heartbeat)
timer[0].start()
try:
heartbeat()
success = fd.real_download(filename, info_dict)
finally:
if heartbeat_lock:
with heartbeat_lock:
timer[0].cancel()
download_complete = True
return success
+40 -35
View File
@@ -1,11 +1,13 @@
from __future__ import division, unicode_literals
import re
import json
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import try_get
from ..utils import (
try_get,
RegexNotFoundError,
)
from ..extractor.youtube import YoutubeBaseInfoExtractor as YT_BaseIE
@@ -27,40 +29,28 @@ class YoutubeLiveChatReplayFD(FragmentFD):
'total_frags': None,
}
def dl_fragment(url):
headers = info_dict.get('http_headers', {})
return self._download_fragment(ctx, url, info_dict, headers)
ie = YT_BaseIE(self.ydl)
def parse_yt_initial_data(data):
patterns = (
r'%s\\s*%s' % (YT_BaseIE._YT_INITIAL_DATA_RE, YT_BaseIE._YT_INITIAL_BOUNDARY_RE),
r'%s' % YT_BaseIE._YT_INITIAL_DATA_RE)
data = data.decode('utf-8', 'replace')
for patt in patterns:
try:
raw_json = re.search(patt, data).group(1)
return json.loads(raw_json)
except AttributeError:
continue
def dl_fragment(url, data=None, headers=None):
http_headers = info_dict.get('http_headers', {})
if headers:
http_headers = http_headers.copy()
http_headers.update(headers)
return self._download_fragment(ctx, url, info_dict, http_headers, data)
def download_and_parse_fragment(url, frag_index):
def download_and_parse_fragment(url, frag_index, request_data):
count = 0
while count <= fragment_retries:
try:
success, raw_fragment = dl_fragment(url)
success, raw_fragment = dl_fragment(url, request_data, {'content-type': 'application/json'})
if not success:
return False, None, None
data = parse_yt_initial_data(raw_fragment)
try:
data = ie._extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
except RegexNotFoundError:
data = None
if not data:
raw_data = json.loads(raw_fragment)
# sometimes youtube replies with a list
if not isinstance(raw_data, list):
raw_data = [raw_data]
try:
data = next(item['response'] for item in raw_data if 'response' in item)
except StopIteration:
data = {}
data = json.loads(raw_fragment)
live_chat_continuation = try_get(
data,
lambda x: x['continuationContents']['liveChatContinuation'], dict) or {}
@@ -93,22 +83,37 @@ class YoutubeLiveChatReplayFD(FragmentFD):
'https://www.youtube.com/watch?v={}'.format(video_id))
if not success:
return False
data = parse_yt_initial_data(raw_fragment)
try:
data = ie._extract_yt_initial_data(video_id, raw_fragment.decode('utf-8', 'replace'))
except RegexNotFoundError:
return False
continuation_id = try_get(
data,
lambda x: x['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'])
# no data yet but required to call _append_fragment
self._append_fragment(ctx, b'')
ytcfg = ie._extract_ytcfg(video_id, raw_fragment.decode('utf-8', 'replace'))
if not ytcfg:
return False
api_key = try_get(ytcfg, lambda x: x['INNERTUBE_API_KEY'])
innertube_context = try_get(ytcfg, lambda x: x['INNERTUBE_CONTEXT'])
if not api_key or not innertube_context:
return False
url = 'https://www.youtube.com/youtubei/v1/live_chat/get_live_chat_replay?key=' + api_key
frag_index = offset = 0
while continuation_id is not None:
frag_index += 1
url = ''.join((
'https://www.youtube.com/live_chat_replay',
'/get_live_chat_replay' if frag_index > 1 else '',
'?continuation=%s' % continuation_id,
'&playerOffsetMs=%d&hidden=false&pbj=1' % max(offset - 5000, 0) if frag_index > 1 else ''))
success, continuation_id, offset = download_and_parse_fragment(url, frag_index)
request_data = {
'context': innertube_context,
'continuation': continuation_id,
}
if frag_index > 1:
request_data['currentPlayerState'] = {'playerOffsetMs': str(max(offset - 5000, 0))}
success, continuation_id, offset = download_and_parse_fragment(
url, frag_index, json.dumps(request_data, ensure_ascii=False).encode('utf-8') + b'\n')
if not success:
return False
if test:
+5 -3
View File
@@ -478,11 +478,12 @@ class BrightcoveNewIE(AdobePassIE):
container = source.get('container')
ext = mimetype2ext(source.get('type'))
src = source.get('src')
skip_unplayable = not self._downloader.params.get('allow_unplayable_formats')
# https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
if container == 'WVM' or source.get('key_systems'):
if skip_unplayable and (container == 'WVM' or source.get('key_systems')):
num_drm_sources += 1
continue
elif ext == 'ism':
elif ext == 'ism' and skip_unplayable:
continue
elif ext == 'm3u8' or container == 'M2TS':
if not src:
@@ -546,7 +547,8 @@ class BrightcoveNewIE(AdobePassIE):
error = errors[0]
raise ExtractorError(
error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
if sources and num_drm_sources == len(sources):
if (not self._downloader.params.get('allow_unplayable_formats')
and sources and num_drm_sources == len(sources)):
raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
+3
View File
@@ -95,6 +95,9 @@ class CDAIE(InfoExtractor):
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
raise ExtractorError('This video is only available for premium users.', expected=True)
if re.search(r'niedostępn[ey] w(?:&nbsp;|\s+)Twoim kraju\s*<', webpage):
self.raise_geo_restricted()
need_confirm_age = False
if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
webpage, 'birthday validate form', default=None):
+2 -1
View File
@@ -147,7 +147,8 @@ class CeskaTelevizeIE(InfoExtractor):
is_live = item.get('type') == 'LIVE'
formats = []
for format_id, stream_url in item.get('streamUrls', {}).items():
if 'drmOnly=true' in stream_url:
if (not self._downloader.params.get('allow_unplayable_formats')
and 'drmOnly=true' in stream_url):
continue
if 'playerType=flash' in stream_url:
stream_formats = self._extract_m3u8_formats(
+8 -3
View File
@@ -2358,6 +2358,8 @@ class InfoExtractor(object):
extract_Initialization(segment_template)
return ms_info
skip_unplayable = not self._downloader.params.get('allow_unplayable_formats')
mpd_duration = parse_duration(mpd_doc.get('mediaPresentationDuration'))
formats = []
for period in mpd_doc.findall(_add_ns('Period')):
@@ -2367,11 +2369,11 @@ class InfoExtractor(object):
'timescale': 1,
})
for adaptation_set in period.findall(_add_ns('AdaptationSet')):
if is_drm_protected(adaptation_set):
if skip_unplayable and is_drm_protected(adaptation_set):
continue
adaption_set_ms_info = extract_multisegment_info(adaptation_set, period_ms_info)
for representation in adaptation_set.findall(_add_ns('Representation')):
if is_drm_protected(representation):
if skip_unplayable and is_drm_protected(representation):
continue
representation_attrib = adaptation_set.attrib.copy()
representation_attrib.update(representation.attrib)
@@ -2585,7 +2587,10 @@ class InfoExtractor(object):
1. [MS-SSTR]: Smooth Streaming Protocol,
https://msdn.microsoft.com/en-us/library/ff469518.aspx
"""
if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
if ism_doc.get('IsLive') == 'TRUE':
return []
if (not self._downloader.params.get('allow_unplayable_formats')
and ism_doc.find('Protection') is not None):
return []
duration = int(ism_doc.attrib['Duration'])
+1 -1
View File
@@ -103,7 +103,7 @@ class CrackleIE(InfoExtractor):
formats = []
for e in media['MediaURLs']:
if e.get('UseDRM') is True:
if not self._downloader.params.get('allow_unplayable_formats') and e.get('UseDRM') is True:
continue
format_url = url_or_none(e.get('Path'))
if not format_url:
+2 -2
View File
@@ -502,8 +502,8 @@ from .hungama import (
from .hypem import HypemIE
from .ign import (
IGNIE,
OneUPIE,
PCMagIE,
IGNVideoIE,
IGNArticleIE,
)
from .iheart import (
IHeartRadioIE,
+8
View File
@@ -130,6 +130,7 @@ from .kinja import KinjaEmbedIE
from .gedi import GediEmbedsIE
from .rcs import RCSEmbedsIE
from .bitchute import BitChuteIE
from .rumble import RumbleEmbedIE
from .arcpublishing import ArcPublishingIE
from .medialaan import MedialaanIE
@@ -3338,6 +3339,13 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
bitchute_urls, video_id, video_title, ie=BitChuteIE.ie_key())
rumble_urls = RumbleEmbedIE._extract_urls(webpage)
if len(rumble_urls) == 1:
return self.url_result(rumble_urls[0], RumbleEmbedIE.ie_key())
if rumble_urls:
return self.playlist_from_matches(
rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key())
# Look for HTML5 media
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls')
if entries:
+1 -1
View File
@@ -96,7 +96,7 @@ class GloboIE(InfoExtractor):
video = self._download_json(
'http://api.globovideos.com/videos/%s/playlist' % video_id,
video_id)['videos'][0]
if video.get('encrypted') is True:
if not self._downloader.params.get('allow_unplayable_formats') and video.get('encrypted') is True:
raise ExtractorError('This video is DRM protected.', expected=True)
title = video['title']
+1 -1
View File
@@ -141,7 +141,7 @@ class HotStarIE(HotStarBaseIE):
title = video_data['title']
if video_data.get('drmProtected'):
if not self._downloader.params.get('allow_unplayable_formats') and video_data.get('drmProtected'):
raise ExtractorError('This video is DRM protected.', expected=True)
headers = {'Referer': url}
+198 -173
View File
@@ -3,230 +3,255 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
HEADRequest,
determine_ext,
int_or_none,
parse_iso8601,
strip_or_none,
try_get,
)
class IGNIE(InfoExtractor):
class IGNBaseIE(InfoExtractor):
def _call_api(self, slug):
return self._download_json(
'http://apis.ign.com/{0}/v3/{0}s/slug/{1}'.format(self._PAGE_TYPE, slug), slug)
class IGNIE(IGNBaseIE):
"""
Extractor for some of the IGN sites, like www.ign.com, es.ign.com de.ign.com.
Some videos of it.ign.com are also supported
"""
_VALID_URL = r'https?://.+?\.ign\.com/(?:[^/]+/)?(?P<type>videos|show_videos|articles|feature|(?:[^/]+/\d+/video))(/.+)?/(?P<name_or_id>.+)'
_VALID_URL = r'https?://(?:.+?\.ign|www\.pcmag)\.com/videos/(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[^/?&#]+)'
IE_NAME = 'ign.com'
_PAGE_TYPE = 'video'
_API_URL_TEMPLATE = 'http://apis.ign.com/video/v3/videos/%s'
_EMBED_RE = r'<iframe[^>]+?["\']((?:https?:)?//.+?\.ign\.com.+?/embed.+?)["\']'
_TESTS = [
{
'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
'md5': 'febda82c4bafecd2d44b6e1a18a595f8',
'info_dict': {
'id': '8f862beef863986b2785559b9e1aa599',
'ext': 'mp4',
'title': 'The Last of Us Review',
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
'uploader_id': 'cberidon@ign.com',
}
},
{
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': '100-little-things-in-gta-5-that-will-blow-your-mind',
},
'playlist': [
{
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
'uploader_id': 'danieljkrupa@gmail.com',
},
},
{
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
'uploader_id': 'togilvie@ign.com',
},
},
],
'params': {
'skip_download': True,
},
},
{
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'md5': '618fedb9c901fd086f6f093564ef8558',
'info_dict': {
'id': '078fdd005f6d3c02f63d795faa1b984f',
'ext': 'mp4',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
'description': 'Brian and Jared explore Michel Ancel\'s captivating new preview.',
'timestamp': 1408047180,
'upload_date': '20140814',
'uploader_id': 'jamesduggan1990@gmail.com',
},
},
{
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
'only_matching': True,
},
{
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
},
{
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
'only_matching': True,
},
]
def _find_video_id(self, webpage):
res_id = [
r'"video_id"\s*:\s*"(.*?)"',
r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
r'videoId&quot;\s*:\s*&quot;(.+?)&quot;',
r'videoId["\']\s*:\s*["\']([^"\']+?)["\']',
]
return self._search_regex(res_id, webpage, 'video id', default=None)
_TESTS = [{
'url': 'http://www.ign.com/videos/2013/06/05/the-last-of-us-review',
'md5': 'd2e1586d9987d40fad7867bf96a018ea',
'info_dict': {
'id': '8f862beef863986b2785559b9e1aa599',
'ext': 'mp4',
'title': 'The Last of Us Review',
'description': 'md5:c8946d4260a4d43a00d5ae8ed998870c',
'timestamp': 1370440800,
'upload_date': '20130605',
'tags': 'count:9',
}
}, {
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': 'f1581a6fe8c5121be5b807684aeac3f6',
'info_dict': {
'id': 'ee10d774b508c9b8ec07e763b9125b91',
'ext': 'mp4',
'title': 'What\'s New Now: Is GoGo Snooping on Your Data?',
'description': 'md5:817a20299de610bd56f13175386da6fa',
'timestamp': 1420571160,
'upload_date': '20150106',
'tags': 'count:4',
}
}, {
'url': 'https://www.ign.com/videos/is-a-resident-evil-4-remake-on-the-way-ign-daily-fix',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name_or_id = mobj.group('name_or_id')
page_type = mobj.group('type')
webpage = self._download_webpage(url, name_or_id)
if page_type != 'video':
multiple_urls = re.findall(
r'<param name="flashvars"[^>]*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]',
webpage)
if multiple_urls:
entries = [self.url_result(u, ie='IGN') for u in multiple_urls]
return {
'_type': 'playlist',
'id': name_or_id,
'entries': entries,
}
video_id = self._find_video_id(webpage)
if not video_id:
return self.url_result(self._search_regex(
self._EMBED_RE, webpage, 'embed url'))
return self._get_video_info(video_id)
def _get_video_info(self, video_id):
api_data = self._download_json(
self._API_URL_TEMPLATE % video_id, video_id)
display_id = self._match_id(url)
video = self._call_api(display_id)
video_id = video['videoId']
metadata = video['metadata']
title = metadata.get('longTitle') or metadata.get('title') or metadata['name']
formats = []
m3u8_url = api_data['refs'].get('m3uUrl')
refs = video.get('refs') or {}
m3u8_url = refs.get('m3uUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = api_data['refs'].get('f4mUrl')
f4m_url = refs.get('f4mUrl')
if f4m_url:
formats.extend(self._extract_f4m_formats(
f4m_url, video_id, f4m_id='hds', fatal=False))
for asset in api_data['assets']:
for asset in (video.get('assets') or []):
asset_url = asset.get('url')
if not asset_url:
continue
formats.append({
'url': asset['url'],
'tbr': asset.get('actual_bitrate_kbps'),
'fps': asset.get('frame_rate'),
'url': asset_url,
'tbr': int_or_none(asset.get('bitrate'), 1000),
'fps': int_or_none(asset.get('frame_rate')),
'height': int_or_none(asset.get('height')),
'width': int_or_none(asset.get('width')),
})
mezzanine_url = try_get(video, lambda x: x['system']['mezzanineUrl'])
if mezzanine_url:
formats.append({
'ext': determine_ext(mezzanine_url, 'mp4'),
'format_id': 'mezzanine',
'preference': 1,
'url': mezzanine_url,
})
self._sort_formats(formats)
thumbnails = [{
'url': thumbnail['url']
} for thumbnail in api_data.get('thumbnails', [])]
thumbnails = []
for thumbnail in (video.get('thumbnails') or []):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
})
metadata = api_data['metadata']
tags = []
for tag in (video.get('tags') or []):
display_name = tag.get('displayName')
if not display_name:
continue
tags.append(display_name)
return {
'id': api_data.get('videoId') or video_id,
'title': metadata.get('longTitle') or metadata.get('name') or metadata.get['title'],
'description': metadata.get('description'),
'id': video_id,
'title': title,
'description': strip_or_none(metadata.get('description')),
'timestamp': parse_iso8601(metadata.get('publishDate')),
'duration': int_or_none(metadata.get('duration')),
'display_id': metadata.get('slug') or video_id,
'uploader_id': metadata.get('creator'),
'display_id': display_id,
'thumbnails': thumbnails,
'formats': formats,
'tags': tags,
}
class OneUPIE(IGNIE):
_VALID_URL = r'https?://gamevideos\.1up\.com/(?P<type>video)/id/(?P<name_or_id>.+)\.html'
IE_NAME = '1up.com'
class IGNVideoIE(InfoExtractor):
_VALID_URL = r'https?://.+?\.ign\.com/(?:[a-z]{2}/)?[^/]+/(?P<id>\d+)/(?:video|trailer)/'
_TESTS = [{
'url': 'http://gamevideos.1up.com/video/id/34976.html',
'md5': 'c9cc69e07acb675c31a16719f909e347',
'url': 'http://me.ign.com/en/videos/112203/video/how-hitman-aims-to-be-different-than-every-other-s',
'md5': 'dd9aca7ed2657c4e118d8b261e5e9de1',
'info_dict': {
'id': '34976',
'id': 'e9be7ea899a9bbfc0674accc22a36cc8',
'ext': 'mp4',
'title': 'Sniper Elite V2 - Trailer',
'description': 'md5:bf0516c5ee32a3217aa703e9b1bc7826',
'timestamp': 1313099220,
'upload_date': '20110811',
'uploader_id': 'IGN',
'title': 'How Hitman Aims to Be Different Than Every Other Stealth Game - NYCC 2015',
'description': 'Taking out assassination targets in Hitman has never been more stylish.',
'timestamp': 1444665600,
'upload_date': '20151012',
}
}, {
'url': 'http://me.ign.com/ar/angry-birds-2/106533/video/lrd-ldyy-lwl-lfylm-angry-birds',
'only_matching': True,
}, {
# Youtube embed
'url': 'https://me.ign.com/ar/ratchet-clank-rift-apart/144327/trailer/embed',
'only_matching': True,
}, {
# Twitter embed
'url': 'http://adria.ign.com/sherlock-season-4/9687/trailer/embed',
'only_matching': True,
}, {
# Vimeo embed
'url': 'https://kr.ign.com/bic-2018/3307/trailer/embed',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
result = super(OneUPIE, self)._real_extract(url)
result['id'] = mobj.group('name_or_id')
return result
video_id = self._match_id(url)
req = HEADRequest(url.rsplit('/', 1)[0] + '/embed')
url = self._request_webpage(req, video_id).geturl()
ign_url = compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('url', [None])[0]
if ign_url:
return self.url_result(ign_url, IGNIE.ie_key())
return self.url_result(url)
class PCMagIE(IGNIE):
_VALID_URL = r'https?://(?:www\.)?pcmag\.com/(?P<type>videos|article2)(/.+)?/(?P<name_or_id>.+)'
IE_NAME = 'pcmag'
_EMBED_RE = r'iframe\.setAttribute\("src",\s*__util.objToUrlString\("http://widgets\.ign\.com/video/embed/content\.html?[^"]*url=([^"]+)["&]'
class IGNArticleIE(IGNBaseIE):
_VALID_URL = r'https?://.+?\.ign\.com/(?:articles(?:/\d{4}/\d{2}/\d{2})?|(?:[a-z]{2}/)?feature/\d+)/(?P<id>[^/?&#]+)'
_PAGE_TYPE = 'article'
_TESTS = [{
'url': 'http://www.pcmag.com/videos/2015/01/06/010615-whats-new-now-is-gogo-snooping-on-your-data',
'md5': '212d6154fd0361a2781075f1febbe9ad',
'url': 'http://me.ign.com/en/feature/15775/100-little-things-in-gta-5-that-will-blow-your-mind',
'info_dict': {
'id': 'ee10d774b508c9b8ec07e763b9125b91',
'ext': 'mp4',
'title': '010615_What\'s New Now: Is GoGo Snooping on Your Data?',
'description': 'md5:a7071ae64d2f68cc821c729d4ded6bb3',
'timestamp': 1420571160,
'upload_date': '20150106',
'uploader_id': 'cozzipix@gmail.com',
}
'id': '524497489e4e8ff5848ece34',
'title': '100 Little Things in GTA 5 That Will Blow Your Mind',
},
'playlist': [
{
'info_dict': {
'id': '5ebbd138523268b93c9141af17bec937',
'ext': 'mp4',
'title': 'GTA 5 Video Review',
'description': 'Rockstar drops the mic on this generation of games. Watch our review of the masterly Grand Theft Auto V.',
'timestamp': 1379339880,
'upload_date': '20130916',
},
},
{
'info_dict': {
'id': '638672ee848ae4ff108df2a296418ee2',
'ext': 'mp4',
'title': '26 Twisted Moments from GTA 5 in Slow Motion',
'description': 'The twisted beauty of GTA 5 in stunning slow motion.',
'timestamp': 1386878820,
'upload_date': '20131212',
},
},
],
'params': {
'playlist_items': '2-3',
'skip_download': True,
},
}, {
'url': 'http://www.pcmag.com/article2/0,2817,2470156,00.asp',
'md5': '94130c1ca07ba0adb6088350681f16c1',
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'info_dict': {
'id': '042e560ba94823d43afcb12ddf7142ca',
'ext': 'mp4',
'title': 'HTC\'s Weird New Re Camera - What\'s New Now',
'description': 'md5:53433c45df96d2ea5d0fda18be2ca908',
'timestamp': 1412953920,
'upload_date': '20141010',
'uploader_id': 'chris_snyder@pcmag.com',
}
'id': '53ee806780a81ec46e0790f8',
'title': 'Rewind Theater - Wild Trailer Gamescom 2014',
},
'playlist_count': 2,
}, {
# videoId pattern
'url': 'http://www.ign.com/articles/2017/06/08/new-ducktales-short-donalds-birthday-doesnt-go-as-planned',
'only_matching': True,
}, {
# Youtube embed
'url': 'https://www.ign.com/articles/2021-mvp-named-in-puppy-bowl-xvii',
'only_matching': True,
}, {
# IMDB embed
'url': 'https://www.ign.com/articles/2014/08/07/sons-of-anarchy-final-season-trailer',
'only_matching': True,
}, {
# Facebook embed
'url': 'https://www.ign.com/articles/2017/09/20/marvels-the-punisher-watch-the-new-trailer-for-the-netflix-series',
'only_matching': True,
}, {
# Brightcove embed
'url': 'https://www.ign.com/articles/2016/01/16/supergirl-goes-flying-with-martian-manhunter-in-new-clip',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
article = self._call_api(display_id)
def entries():
media_url = try_get(article, lambda x: x['mediaRelations'][0]['media']['metadata']['url'])
if media_url:
yield self.url_result(media_url, IGNIE.ie_key())
for content in (article.get('content') or []):
for video_url in re.findall(r'(?:\[(?:ignvideo\s+url|youtube\s+clip_id)|<iframe[^>]+src)="([^"]+)"', content):
yield self.url_result(video_url)
return self.playlist_result(
entries(), article.get('articleId'),
strip_or_none(try_get(article, lambda x: x['metadata']['headline'])))
+4 -1
View File
@@ -163,7 +163,10 @@ class IviIE(InfoExtractor):
for f in result.get('files', []):
f_url = f.get('url')
content_format = f.get('content_format')
if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format:
if not f_url:
continue
if (not self._downloader.params.get('allow_unplayable_formats')
and ('-MDRM-' in content_format or '-FPS-' in content_format)):
continue
formats.append({
'url': f_url,
+1 -1
View File
@@ -309,7 +309,7 @@ class KalturaIE(InfoExtractor):
if f.get('fileExt') == 'chun':
continue
# DRM-protected video, cannot be decrypted
if f.get('fileExt') == 'wvm':
if not self._downloader.params.get('allow_unplayable_formats') and f.get('fileExt') == 'wvm':
continue
if not f.get('fileExt'):
# QT indicates QuickTime; some videos have broken fileExt
+3 -1
View File
@@ -96,7 +96,9 @@ class LimelightBaseIE(InfoExtractor):
urls = []
for stream in pc_item.get('streams', []):
stream_url = stream.get('url')
if not stream_url or stream.get('drmProtected') or stream_url in urls:
if not stream_url or stream_url in urls:
continue
if not self._downloader.params.get('allow_unplayable_formats') and stream.get('drmProtected'):
continue
urls.append(stream_url)
ext = determine_ext(stream_url)
+281 -167
View File
@@ -1,25 +1,25 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import functools
import re
import json
import math
import datetime
from .common import InfoExtractor
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
determine_ext,
dict_get,
ExtractorError,
float_or_none,
InAdvancePagedList,
int_or_none,
float_or_none,
OnDemandPagedList,
parse_duration,
parse_iso8601,
PostProcessingError,
remove_start,
try_get,
unified_timestamp,
@@ -191,37 +191,87 @@ class NiconicoIE(InfoExtractor):
self._downloader.report_warning('unable to log in: bad username or password')
return login_ok
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
def yesno(boolean):
return 'yes' if boolean else 'no'
def _get_heartbeat_info(self, info_dict):
session_api_data = api_data['video']['dmcInfo']['session_api']
session_api_endpoint = session_api_data['urls'][0]
video_id, video_src_id, audio_src_id = info_dict['url'].split(':')[1].split('/')
format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
# Get video webpage for API data.
webpage, handle = self._download_webpage_handle(
'http://www.nicovideo.jp/watch/' + video_id, video_id)
api_data = self._parse_json(self._html_search_regex(
'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_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
# ping
self._download_json(
'https://nvapi.nicovideo.jp/v1/2ab0cbaa/watch', video_id,
query={'t': try_get(api_data, lambda x: x['video']['dmcInfo']['tracking_id'])},
headers={
'Origin': 'https://www.nicovideo.jp',
'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
'X-Frontend-Id': '6',
'X-Frontend-Version': '0'
})
yesno = lambda x: 'yes' if x else 'no'
# m3u8 (encryption)
if 'encryption' in try_get(api_data, lambda x: x['video']['dmcInfo']) or {}:
protocol = 'm3u8'
session_api_http_parameters = {
'parameters': {
'hls_parameters': {
'encryption': {
'hls_encryption_v1': {
'encrypted_key': try_get(api_data, lambda x: x['video']['dmcInfo']['encryption']['hls_encryption_v1']['encrypted_key']),
'key_uri': try_get(api_data, lambda x: x['video']['dmcInfo']['encryption']['hls_encryption_v1']['key_uri'])
}
},
'transfer_preset': '',
'use_ssl': yesno(session_api_endpoint['is_ssl']),
'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
'segment_duration': 6000
}
}
}
# http
else:
protocol = 'http'
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']),
}
}
}
session_response = self._download_json(
session_api_endpoint['url'], video_id,
query={'_format': 'json'},
headers={'Content-Type': 'application/json'},
note='Downloading JSON metadata for %s' % format_id,
note='Downloading JSON metadata for %s' % info_dict['format_id'],
data=json.dumps({
'session': {
'client_info': {
'player_id': session_api_data['player_id'],
'player_id': session_api_data.get('player_id'),
},
'content_auth': {
'auth_type': session_api_data['auth_types'][session_api_data['protocols'][0]],
'content_key_timeout': session_api_data['content_key_timeout'],
'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'),
'service_id': 'nicovideo',
'service_user_id': session_api_data['service_user_id']
'service_user_id': session_api_data.get('service_user_id')
},
'content_id': session_api_data['content_id'],
'content_id': session_api_data.get('content_id'),
'content_src_id_sets': [{
'content_src_ids': [{
'src_id_to_mux': {
'audio_src_ids': [audio_quality['id']],
'video_src_ids': [video_quality['id']],
'audio_src_ids': [audio_src_id],
'video_src_ids': [video_src_id],
}
}]
}],
@@ -229,52 +279,78 @@ class NiconicoIE(InfoExtractor):
'content_uri': '',
'keep_method': {
'heartbeat': {
'lifetime': session_api_data['heartbeat_lifetime']
'lifetime': session_api_data.get('heartbeat_lifetime')
}
},
'priority': session_api_data['priority'],
'priority': session_api_data.get('priority'),
'protocol': {
'name': 'http',
'parameters': {
'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']),
}
}
}
'http_parameters': session_api_http_parameters
}
},
'recipe_id': session_api_data['recipe_id'],
'recipe_id': session_api_data.get('recipe_id'),
'session_operation_auth': {
'session_operation_auth_by_signature': {
'signature': session_api_data['signature'],
'token': session_api_data['token'],
'signature': session_api_data.get('signature'),
'token': session_api_data.get('token'),
}
},
'timing_constraint': 'unlimited'
}
}).encode())
resolution = video_quality.get('resolution', {})
info_dict['url'] = session_response['data']['session']['content_uri']
info_dict['protocol'] = protocol
# get heartbeat info
heartbeat_info_dict = {
'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),
}
return info_dict, heartbeat_info_dict
def _extract_format_for_quality(self, api_data, video_id, audio_quality, video_quality):
def parse_format_id(id_code):
mobj = re.match(r'''(?x)
(?:archive_)?
(?:(?P<codec>[^_]+)_)?
(?:(?P<br>[\d]+)kbps_)?
(?:(?P<res>[\d+]+)p_)?
''', '%s_' % id_code)
return mobj.groupdict() if mobj else {}
protocol = 'niconico_dmc'
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')})
return {
'url': session_response['data']['session']['content_uri'],
'url': '%s:%s/%s/%s' % (protocol, video_id, video_quality['id'], audio_quality['id']),
'format_id': format_id,
'ext': 'mp4', # Session API are used in HTML5, which always serves mp4
'abr': float_or_none(audio_quality.get('bitrate'), 1000),
'vbr': float_or_none(video_quality.get('bitrate'), 1000),
'height': resolution.get('height'),
'width': resolution.get('width'),
'vcodec': vdict.get('codec'),
'acodec': adict.get('codec'),
'vbr': float_or_none(video_quality.get('bitrate'), 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')),
'quality': -2 if 'low' in format_id else -1, # Default quality value is -1
'protocol': protocol,
'http_headers': {
'Origin': 'https://www.nicovideo.jp',
'Referer': 'https://www.nicovideo.jp/watch/' + video_id,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
# Get video webpage. We are not actually interested in it for normal
# cases, but need the cookies in order to be able to download the
# info webpage
# Get video webpage for API data.
webpage, handle = self._download_webpage_handle(
'http://www.nicovideo.jp/watch/' + video_id, video_id)
if video_id.startswith('so'):
@@ -284,80 +360,134 @@ class NiconicoIE(InfoExtractor):
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
def _format_id_from_url(video_url):
return 'economy' if video_real_url.endswith('low') else 'normal'
def get_video_info_web(items):
return dict_get(api_data['video'], items)
# Get video info
video_info_xml = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
video_id, note='Downloading video info page')
def get_video_info_xml(items):
if not isinstance(items, list):
items = [items]
for item in items:
ret = xpath_text(video_info_xml, './/' + item)
if ret:
return ret
if get_video_info_xml('error'):
error_code = get_video_info_xml('code')
if error_code == 'DELETED':
raise ExtractorError('The video has been deleted.',
expected=True)
elif error_code == 'NOT_FOUND':
raise ExtractorError('The video is not found.',
expected=True)
elif error_code == 'COMMUNITY':
self.to_screen('%s: The video is community members only.' % video_id)
else:
raise ExtractorError('%s reports error: %s' % (self.IE_NAME, error_code))
# Start extracting video formats
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 = 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'):
continue
formats.append(self._extract_format_for_quality(
api_data, video_id, audio_quality, video_quality))
# Get flv/swf info
video_real_url = try_get(api_data, lambda x: x['video']['smileInfo']['url'])
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')
# 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'))
try:
video_real_url = api_data['video']['smileInfo']['url']
except KeyError: # Flash videos
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
except PostProcessingError as err:
raise ExtractorError(err.msg, expected=True)
flv_info = compat_parse_qs(flv_info_webpage)
if 'url' not in flv_info:
if 'deleted' in flv_info:
raise ExtractorError('The video has been deleted.',
expected=True)
elif 'closed' in flv_info:
raise ExtractorError('Niconico videos now require logging in',
expected=True)
elif 'error' in flv_info:
raise ExtractorError('%s reports error: %s' % (
self.IE_NAME, flv_info['error'][0]), expected=True)
else:
raise ExtractorError('Unable to find video URL')
v_stream = a_stream = {}
video_info_xml = self._download_xml(
'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id,
video_id, note='Downloading video info page')
# 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
def get_video_info(items):
if not isinstance(items, list):
items = [items]
for item in items:
ret = xpath_text(video_info_xml, './/' + item)
if ret:
return ret
# 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']
)
video_real_url = flv_info['url'][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
)
extension = get_video_info('movie_type')
if not extension:
extension = determine_ext(video_real_url)
# 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')
formats = [{
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,
'format_id': _format_id_from_url(video_real_url),
}]
else:
formats = []
'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
})
dmc_info = api_data['video'].get('dmcInfo')
if dmc_info: # "New" HTML5 videos
quality_info = dmc_info['quality']
for audio_quality in quality_info['audios']:
for video_quality in quality_info['videos']:
if not audio_quality['available'] or not video_quality['available']:
continue
formats.append(self._extract_format_for_quality(
api_data, video_id, audio_quality, video_quality))
if len(formats) == 0:
raise ExtractorError('Unable to find video info.')
self._sort_formats(formats)
else: # "Old" HTML5 videos
formats = [{
'url': video_real_url,
'ext': 'mp4',
'format_id': _format_id_from_url(video_real_url),
}]
def get_video_info(items):
return dict_get(api_data['video'], items)
self._sort_formats(formats)
# Start extracting information
title = get_video_info('title')
title = get_video_info_web('originalTitle')
if not title:
title = self._og_search_title(webpage, default=None)
if not title:
@@ -372,14 +502,13 @@ class NiconicoIE(InfoExtractor):
video_detail = watch_api_data.get('videoDetail', {})
thumbnail = (
get_video_info(['thumbnail_url', 'thumbnailURL'])
self._html_search_regex(r'<meta property="og:image" content="([^"]+)">', webpage, 'thumbnail data', default=None)
or get_video_info_web(['thumbnail_url', 'largeThumbnailURL', 'thumbnailURL'])
or self._html_search_meta('image', webpage, 'thumbnail', default=None)
or video_detail.get('thumbnail'))
description = get_video_info('description')
description = get_video_info_web('description')
timestamp = (parse_iso8601(get_video_info('first_retrieve'))
or unified_timestamp(get_video_info('postedDateTime')))
if not timestamp:
match = self._html_search_meta('datePublished', webpage, 'date published', default=None)
if match:
@@ -389,7 +518,7 @@ class NiconicoIE(InfoExtractor):
video_detail['postedAt'].replace('/', '-'),
delimiter=' ', timezone=datetime.timedelta(hours=9))
view_count = int_or_none(get_video_info(['view_counter', 'viewCount']))
view_count = int_or_none(get_video_info_web(['view_counter', 'viewCount']))
if not view_count:
match = self._html_search_regex(
r'>Views: <strong[^>]*>([^<]+)</strong>',
@@ -398,7 +527,7 @@ class NiconicoIE(InfoExtractor):
view_count = int_or_none(match.replace(',', ''))
view_count = view_count or video_detail.get('viewCount')
comment_count = (int_or_none(get_video_info('comment_num'))
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:
@@ -409,19 +538,19 @@ class NiconicoIE(InfoExtractor):
comment_count = int_or_none(match.replace(',', ''))
duration = (parse_duration(
get_video_info('length')
get_video_info_web('length')
or self._html_search_meta(
'video:duration', webpage, 'video duration', default=None))
or video_detail.get('length')
or get_video_info('duration'))
or get_video_info_web('duration'))
webpage_url = get_video_info('watch_url') or url
webpage_url = get_video_info_web('watch_url') or url
# 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 = get_video_info(['ch_id', 'user_id']) or owner.get('id')
uploader = get_video_info(['ch_name', 'user_nickname']) or owner.get('nickname')
uploader_id = get_video_info_web(['ch_id', 'user_id']) or owner.get('id')
uploader = get_video_info_web(['ch_name', 'user_nickname']) or owner.get('nickname')
return {
'id': video_id,
@@ -456,60 +585,45 @@ class NiconicoPlaylistIE(InfoExtractor):
'url': 'https://www.nicovideo.jp/user/805442/mylist/27411728',
'only_matching': True,
}]
_PAGE_SIZE = 100
def _call_api(self, list_id, resource, query):
return self._download_json(
'https://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
'Downloading %s JSON metatdata' % resource, query=query,
headers={'X-Frontend-Id': 6})['data']['mylist']
def _parse_owner(self, item):
owner = item.get('owner') or {}
if owner:
return {
'uploader': owner.get('name'),
'uploader_id': owner.get('id'),
}
return {}
def _fetch_page(self, list_id, page):
page += 1
items = self._call_api(list_id, 'page %d' % page, {
'page': page,
'pageSize': self._PAGE_SIZE,
})['items']
for item in items:
video = item.get('video') or {}
video_id = video.get('id')
if not video_id:
continue
count = video.get('count') or {}
get_count = lambda x: int_or_none(count.get(x))
info = {
'_type': 'url',
'id': video_id,
'title': video.get('title'),
'url': 'https://www.nicovideo.jp/watch/' + video_id,
'description': video.get('shortDescription'),
'duration': int_or_none(video.get('duration')),
'view_count': get_count('view'),
'comment_count': get_count('comment'),
'ie_key': NiconicoIE.ie_key(),
}
info.update(self._parse_owner(video))
yield info
def _real_extract(self, url):
list_id = self._match_id(url)
mylist = self._call_api(list_id, 'list', {
'pageSize': 1,
})
entries = InAdvancePagedList(
functools.partial(self._fetch_page, list_id),
math.ceil(mylist['totalItemCount'] / self._PAGE_SIZE),
self._PAGE_SIZE)
result = self.playlist_result(
entries, list_id, mylist.get('name'), mylist.get('description'))
result.update(self._parse_owner(mylist))
return result
webpage = self._download_webpage(url, list_id)
header = self._parse_json(self._html_search_regex(
r'data-common-header="([^"]+)"', webpage,
'webpage header'), list_id)
frontendId = header.get('initConfig').get('frontendId')
frontendVersion = header.get('initConfig').get('frontendVersion')
def get_page_data(pagenum, pagesize):
return self._download_json(
'http://nvapi.nicovideo.jp/v2/mylists/' + list_id, list_id,
query={'page': 1 + pagenum, 'pageSize': pagesize},
headers={
'X-Frontend-Id': frontendId,
'X-Frontend-Version': frontendVersion,
}).get('data').get('mylist')
data = get_page_data(0, 1)
title = data.get('name')
description = data.get('description')
uploader = data.get('owner').get('name')
uploader_id = data.get('owner').get('id')
def pagefunc(pagenum):
data = get_page_data(pagenum, 25)
return ({
'_type': 'url',
'url': 'http://www.nicovideo.jp/watch/' + item.get('watchId'),
} for item in data.get('items'))
return {
'_type': 'playlist',
'id': list_id,
'title': title,
'description': description,
'uploader': uploader,
'uploader_id': uploader_id,
'entries': OnDemandPagedList(pagefunc, 25),
}
+2 -1
View File
@@ -36,7 +36,8 @@ class NineCNineMediaIE(InfoExtractor):
'$include': '[HasClosedCaptions]',
})
if try_get(content_package, lambda x: x['Constraints']['Security']['Type']):
if (not self._downloader.params.get('allow_unplayable_formats')
and try_get(content_package, lambda x: x['Constraints']['Security']['Type'])):
raise ExtractorError('This video is DRM protected.', expected=True)
manifest_base_url = content_package_url + 'manifest.'
+1 -1
View File
@@ -66,7 +66,7 @@ class NineNowIE(InfoExtractor):
video_data = common_data['video']
if video_data.get('drm'):
if not self._downloader.params.get('allow_unplayable_formats') and video_data.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
brightcove_id = video_data.get('brightcoveId') or 'ref:' + video_data['referenceId']
+1 -1
View File
@@ -246,7 +246,7 @@ class NPOIE(NPOBaseIE):
})
if not formats:
if drm:
if not self._downloader.params.get('allow_unplayable_formats') and drm:
raise ExtractorError('This video is DRM protected.', expected=True)
return
+1 -1
View File
@@ -34,7 +34,7 @@ class ProSiebenSat1BaseIE(InfoExtractor):
'ids': clip_id,
})[0]
if video.get('is_protected') is True:
if not self._downloader.params.get('allow_unplayable_formats') and video.get('is_protected') is True:
raise ExtractorError('This video is DRM protected.', expected=True)
formats = []
+1 -1
View File
@@ -125,7 +125,7 @@ class RTBFIE(InfoExtractor):
})
mpd_url = data.get('urlDash')
if not data.get('drm') and mpd_url:
if mpd_url and (self._downloader.params.get('allow_unplayable_formats') or not data.get('drm')):
formats.extend(self._extract_mpd_formats(
mpd_url, media_id, mpd_id='dash', fatal=False))
+10
View File
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
@@ -28,6 +30,14 @@ class RumbleEmbedIE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'(?:<(?:script|iframe)[^>]+\bsrc=|["\']embedUrl["\']\s*:\s*)["\'](?P<url>%s)' % RumbleEmbedIE._VALID_URL,
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
+2 -2
View File
@@ -200,8 +200,8 @@ class RuutuIE(InfoExtractor):
return node.get('value')
if not formats:
drm = xpath_text(video_xml, './Clip/DRM', default=None)
if drm:
if (not self._downloader.params.get('allow_unplayable_formats')
and xpath_text(video_xml, './Clip/DRM', default=None)):
raise ExtractorError('This video is DRM protected.', expected=True)
ns_st_cds = pv('ns_st_cds')
if ns_st_cds != 'free':
+1 -1
View File
@@ -111,7 +111,7 @@ class ShahidIE(ShahidBaseIE):
playout = self._call_api(
'playout/url/' + video_id, video_id)['playout']
if playout.get('drm'):
if not self._downloader.params.get('allow_unplayable_formats') and playout.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
+1 -1
View File
@@ -75,7 +75,7 @@ class SonyLIVIE(InfoExtractor):
video_id = self._match_id(url)
content = self._call_api(
'1.5', 'IN/CONTENT/VIDEOURL/VOD/' + video_id, video_id)
if content.get('isEncrypted'):
if not self._downloader.params.get('allow_unplayable_formats') and content.get('isEncrypted'):
raise ExtractorError('This video is DRM protected.', expected=True)
dash_url = content['videoURL']
headers = {
+2 -1
View File
@@ -154,7 +154,8 @@ class ToggleIE(InfoExtractor):
})
if not formats:
for meta in (info.get('Metas') or []):
if meta.get('Key') == 'Encryption' and meta.get('Value') == '1':
if (not self._downloader.params.get('allow_unplayable_formats')
and meta.get('Key') == 'Encryption' and meta.get('Value') == '1'):
raise ExtractorError(
'This video is DRM protected.', expected=True)
# Most likely because geo-blocked
+1 -1
View File
@@ -74,7 +74,7 @@ class TouTvIE(RadioCanadaIE):
})
# IsDrm does not necessarily mean the video is DRM protected (see
# https://github.com/ytdl-org/youtube-dl/issues/13994).
if metadata.get('IsDrm'):
if not self._downloader.params.get('allow_unplayable_formats') and metadata.get('IsDrm'):
self.report_warning('This video is probably DRM protected.', path)
video_id = metadata['IdMedia']
details = metadata['Details']
+1 -1
View File
@@ -69,7 +69,7 @@ class TVNowBaseIE(InfoExtractor):
if formats:
break
else:
if info.get('isDrm'):
if not self._downloader.params.get('allow_unplayable_formats') and info.get('isDrm'):
raise ExtractorError(
'Video %s is DRM protected' % video_id, expected=True)
if info.get('geoblocked'):
+2 -2
View File
@@ -42,8 +42,8 @@ class URPlayIE(InfoExtractor):
url = url.replace('skola.se/Produkter', 'play.se/program')
webpage = self._download_webpage(url, video_id)
urplayer_data = self._parse_json(self._html_search_regex(
r'data-react-class="components/Player/Player"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['currentProduct']
r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0]
episode = urplayer_data['title']
host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
+1 -1
View File
@@ -315,7 +315,7 @@ class VikiIE(VikiBaseIE):
# Despite CODECS metadata in m3u8 all video-only formats
# are actually video+audio
for f in m3u8_formats:
if '_drm/index_' in f['url']:
if not self._downloader.params.get('allow_unplayable_formats') and '_drm/index_' in f['url']:
continue
if f.get('acodec') == 'none' and f.get('vcodec') != 'none':
f['acodec'] = None
+7 -6
View File
@@ -41,12 +41,13 @@ class WakanimIE(InfoExtractor):
m3u8_url = urljoin(url, self._search_regex(
r'file\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'm3u8 url',
group='url'))
# https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls
encryption = self._search_regex(
r'encryption%3D(c(?:enc|bc(?:s-aapl)?))',
m3u8_url, 'encryption', default=None)
if encryption and encryption in ('cenc', 'cbcs-aapl'):
raise ExtractorError('This video is DRM protected.', expected=True)
if not self._downloader.params.get('allow_unplayable_formats'):
# https://docs.microsoft.com/en-us/azure/media-services/previous/media-services-content-protection-overview#streaming-urls
encryption = self._search_regex(
r'encryption%3D(c(?:enc|bc(?:s-aapl)?))',
m3u8_url, 'encryption', default=None)
if encryption in ('cenc', 'cbcs-aapl'):
raise ExtractorError('This video is DRM protected.', expected=True)
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
+68 -12
View File
@@ -11,11 +11,14 @@ from ..utils import (
dict_get,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
parse_duration,
str_or_none,
try_get,
unified_strdate,
url_or_none,
urljoin,
)
@@ -146,36 +149,89 @@ class XHamsterIE(InfoExtractor):
video = initials['videoModel']
title = video['title']
formats = []
for format_id, formats_dict in video['sources'].items():
format_urls = set()
format_sizes = {}
sources = try_get(video, lambda x: x['sources'], dict) or {}
for format_id, formats_dict in sources.items():
if not isinstance(formats_dict, dict):
continue
download_sources = try_get(sources, lambda x: x['download'], dict) or {}
for quality, format_dict in download_sources.items():
if not isinstance(format_dict, dict):
continue
format_sizes[quality] = float_or_none(format_dict.get('size'))
for quality, format_item in formats_dict.items():
if format_id == 'download':
# Download link takes some time to be generated,
# skipping for now
continue
if not isinstance(format_item, dict):
continue
format_url = format_item.get('link')
filesize = int_or_none(
format_item.get('size'), invscale=1000000)
else:
format_url = format_item
filesize = None
format_url = format_item
format_url = url_or_none(format_url)
if not format_url:
if not format_url or format_url in format_urls:
continue
format_urls.add(format_url)
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'url': format_url,
'ext': determine_ext(format_url, 'mp4'),
'height': get_height(quality),
'filesize': filesize,
'filesize': format_sizes.get(quality),
'http_headers': {
'Referer': urlh.geturl(),
},
})
self._sort_formats(formats)
xplayer_sources = try_get(
initials, lambda x: x['xplayerSettings']['sources'], dict)
if xplayer_sources:
hls_sources = xplayer_sources.get('hls')
if isinstance(hls_sources, dict):
for hls_format_key in ('url', 'fallback'):
hls_url = hls_sources.get(hls_format_key)
if not hls_url:
continue
hls_url = urljoin(url, hls_url)
if not hls_url or hls_url in format_urls:
continue
format_urls.add(hls_url)
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
standard_sources = xplayer_sources.get('standard')
if isinstance(standard_sources, dict):
for format_id, formats_list in standard_sources.items():
if not isinstance(formats_list, list):
continue
for standard_format in formats_list:
if not isinstance(standard_format, dict):
continue
for standard_format_key in ('url', 'fallback'):
standard_url = standard_format.get(standard_format_key)
if not standard_url:
continue
standard_url = urljoin(url, standard_url)
if not standard_url or standard_url in format_urls:
continue
format_urls.add(standard_url)
ext = determine_ext(standard_url, 'mp4')
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
standard_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
quality = (str_or_none(standard_format.get('quality'))
or str_or_none(standard_format.get('label'))
or '')
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'url': standard_url,
'ext': ext,
'height': get_height(quality),
'filesize': format_sizes.get(quality),
'http_headers': {
'Referer': standard_url,
},
})
self._sort_formats(formats, field_preference=('height', 'width', 'tbr', 'format_id'))
categories_list = video.get('categories')
if isinstance(categories_list, list):
+68 -33
View File
@@ -32,7 +32,7 @@ from ..utils import (
mimetype2ext,
parse_codecs,
parse_duration,
# qualities,
# qualities, # TODO: Enable this after fixing formatSort
remove_start,
smuggle_url,
str_or_none,
@@ -414,7 +414,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
(?(1).+)? # if we found the ID, everything can follow
$""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_PLAYER_INFO_RE = (
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.js$',
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
)
_formats = {
@@ -621,6 +622,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'uploader': 'AfrojackVEVO',
'uploader_id': 'AfrojackVEVO',
'upload_date': '20131011',
'abr': 129.495,
},
'params': {
'youtube_include_dash_manifest': True,
@@ -1134,10 +1136,26 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'only_matching': True,
},
{
# Age-gated video only available with authentication (unavailable
# via embed page workaround)
'url': 'XgnwCQzjau8',
'only_matching': True,
# https://github.com/ytdl-org/youtube-dl/pull/28094
'url': 'OtqTfy26tG0',
'info_dict': {
'id': 'OtqTfy26tG0',
'ext': 'mp4',
'title': 'Burn Out',
'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
'upload_date': '20141120',
'uploader': 'The Cinematic Orchestra - Topic',
'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
'artist': 'The Cinematic Orchestra',
'track': 'Burn Out',
'album': 'Every Day',
'release_data': None,
'release_year': None,
},
'params': {
'skip_download': True,
},
},
]
@@ -1230,6 +1248,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
funcname = self._search_regex(
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
r'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
# Obsolete patterns
@@ -1393,7 +1414,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
base_url = self.http_scheme() + '//www.youtube.com/'
webpage_url = base_url + 'watch?v=' + video_id
webpage_url = base_url + 'watch?v=' + video_id + '&has_verified=1'
webpage = self._download_webpage(webpage_url, video_id, fatal=False)
player_response = None
@@ -1493,7 +1514,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
formats = []
itags = []
itag_qualities = {}
player_url = None
# TODO: Enable this after fixing formatSort
# q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
streaming_data = player_response.get('streamingData') or {}
streaming_formats = streaming_data.get('formats') or []
@@ -1502,6 +1525,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
continue
itag = str_or_none(fmt.get('itag'))
quality = fmt.get('quality')
if itag and quality:
itag_qualities[itag] = quality
# FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
# (adding `&sq=0` to the URL) and parsing emsg box to determine the
# number of fragment that would subsequently requested with (`&sq=N`)
if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
continue
fmt_url = fmt.get('url')
if not fmt_url:
sc = compat_parse_qs(fmt.get('signatureCipher'))
@@ -1521,10 +1554,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
fmt_url += '&' + sp + '=' + signature
itag = str_or_none(fmt.get('itag'))
if itag:
itags.append(itag)
quality = fmt.get('quality')
tbr = float_or_none(
fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
dct = {
'asr': int_or_none(fmt.get('audioSampleRate')),
'filesize': int_or_none(fmt.get('contentLength')),
@@ -1532,9 +1565,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'format_note': fmt.get('qualityLabel') or quality,
'fps': int_or_none(fmt.get('fps')),
'height': int_or_none(fmt.get('height')),
# 'quality': q(quality), # This does not correctly reflect the overall quality of the format
'tbr': float_or_none(fmt.get(
'averageBitrate') or fmt.get('bitrate'), 1000),
# 'quality': q(quality), # TODO: Enable this after fixing formatSort
'tbr': tbr,
'url': fmt_url,
'width': fmt.get('width'),
}
@@ -1545,7 +1577,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if mobj:
dct['ext'] = mimetype2ext(mobj.group(1))
dct.update(parse_codecs(mobj.group(2)))
if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
no_audio = dct.get('acodec') == 'none'
no_video = dct.get('vcodec') == 'none'
if no_audio:
dct['vbr'] = tbr
if no_video:
dct['abr'] = tbr
if no_audio or no_video:
dct['downloader_options'] = {
# Youtube throttles chunks >~10M
'http_chunk_size': 10485760,
@@ -1565,25 +1603,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if self._downloader.params.get('youtube_include_dash_manifest'):
dash_manifest_url = streaming_data.get('dashManifestUrl')
if dash_manifest_url:
dash_formats = []
for f in self._extract_mpd_formats(
dash_manifest_url, video_id, fatal=False):
itag = f['format_id']
if itag in itags:
continue
# if itag in itag_qualities: # TODO: Enable this after fixing formatSort
# f['quality'] = q(itag_qualities[itag])
filesize = int_or_none(self._search_regex(
r'/clen/(\d+)', f.get('fragment_base_url')
or f['url'], 'file size', default=None))
if filesize:
f['filesize'] = filesize
dash_formats.append(f)
# Until further investigation prefer DASH formats as non-DASH
# may not be available (see [1])
# 1. https://github.com/ytdl-org/youtube-dl/issues/28070
if dash_formats:
dash_formats_keys = [f['format_id'] for f in dash_formats]
formats = [f for f in formats if f['format_id'] not in dash_formats_keys]
formats.extend(dash_formats)
formats.append(f)
if not formats:
if streaming_data.get('licenseInfos'):
if not self._downloader.params.get('allow_unplayable_formats') and streaming_data.get('licenseInfos'):
raise ExtractorError(
'This video is DRM protected.', expected=True)
pemr = try_get(
@@ -1747,7 +1782,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
'track': mobj.group('track').strip(),
'release_date': release_date,
'release_year': int(release_year),
'release_year': int_or_none(release_year),
})
initial_data = None
@@ -2597,9 +2632,9 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
next_continuation = cls._extract_next_continuation_data(renderer)
if next_continuation:
return next_continuation
contents = renderer.get('contents') or renderer.get('items')
if not isinstance(contents, list):
return
contents = []
for key in ('contents', 'items'):
contents.extend(try_get(renderer, lambda x: x[key], list) or [])
for content in contents:
if not isinstance(content, dict):
continue
@@ -3146,6 +3181,12 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
# So we search through all entries till we find them.
continuation_token = None
for slr_content in slr_contents:
if continuation_token is None:
continuation_token = try_get(
slr_content,
lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
compat_str)
isr_contents = try_get(
slr_content,
lambda x: x['itemSectionRenderer']['contents'],
@@ -3167,12 +3208,6 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
if total == n:
return
if continuation_token is None:
continuation_token = try_get(
slr_content,
lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
compat_str)
if not continuation_token:
break
data['continuation'] = continuation_token
+15 -3
View File
@@ -153,7 +153,7 @@ def parseOpts(overrideArguments=None):
general.add_option(
'-U', '--update',
action='store_true', dest='update_self',
help='[BROKEN] Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
help='Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)')
general.add_option(
'-i', '--ignore-errors', '--no-abort-on-error',
action='store_true', dest='ignoreerrors', default=True,
@@ -519,6 +519,16 @@ def parseOpts(overrideArguments=None):
'If a merge is required (e.g. bestvideo+bestaudio), '
'output to given container format. One of mkv, mp4, ogg, webm, flv. '
'Ignored if no merge is required'))
video_format.add_option(
'--allow-unplayable-formats',
action='store_true', dest='allow_unplayable_formats', default=False,
help=(
'Allow unplayable formats to be listed and downloaded. '
'All video postprocessing will also be turned off'))
video_format.add_option(
'--no-allow-unplayable-formats',
action='store_false', dest='allow_unplayable_formats',
help='Do not allow unplayable formats to be listed or downloaded (default)')
subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
subtitles.add_option(
@@ -810,11 +820,13 @@ def parseOpts(overrideArguments=None):
verbosity.add_option(
'-C', '--call-home',
dest='call_home', action='store_true', default=False,
help='[Broken] Contact the youtube-dlc server for debugging')
# help='[Broken] Contact the youtube-dlc server for debugging')
help=optparse.SUPPRESS_HELP)
verbosity.add_option(
'--no-call-home',
dest='call_home', action='store_false',
help='Do not contact the youtube-dlc server for debugging (default)')
# help='Do not contact the youtube-dlc server for debugging (default)')
help=optparse.SUPPRESS_HELP)
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
filesystem.add_option(
+8 -3
View File
@@ -221,8 +221,7 @@ class FFmpegPostProcessor(PostProcessor):
cmd += opts
cmd.append(encodeFilename(self._ffmpeg_filename_argument(path), True))
if self._downloader.params.get('verbose', False):
self._downloader.to_screen('[debug] ffprobe command line: %s' % shell_quote(cmd))
self.write_debug('ffprobe command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
stdout, stderr = p.communicate()
return json.loads(stdout.decode('utf-8', 'replace'))
@@ -261,7 +260,7 @@ class FFmpegPostProcessor(PostProcessor):
stdout, stderr = process_communicate_or_kill(p)
if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace').strip()
if self._downloader.params.get('verbose', False):
if self.get_param('verbose', False):
self.report_error(stderr)
raise FFmpegPostProcessorError(stderr.split('\n')[-1])
self.try_utime(out_path, oldest_mtime, oldest_mtime)
@@ -281,6 +280,8 @@ class FFmpegPostProcessor(PostProcessor):
class FFmpegExtractAudioPP(FFmpegPostProcessor):
COMMON_AUDIO_EXTENSIONS = ('wav', 'flac', 'm4a', 'aiff', 'mp3', 'ogg', 'mka', 'opus', 'wma')
def __init__(self, downloader=None, preferredcodec=None, preferredquality=None, nopostoverwrites=False):
FFmpegPostProcessor.__init__(self, downloader)
if preferredcodec is None:
@@ -302,6 +303,10 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
def run(self, information):
path = information['filepath']
orig_ext = information['ext']
if self._preferredcodec == 'best' and orig_ext in self.COMMON_AUDIO_EXTENSIONS:
self.to_screen('Skipping audio extraction since the file is already in a common audio format')
filecodec = self.get_audio_codec(path)
if filecodec is None:
+6 -6
View File
@@ -12,6 +12,7 @@ from ..utils import (
str_or_none,
PostProcessingError,
prepend_extension,
process_communicate_or_kill,
)
@@ -75,8 +76,9 @@ class SponSkrubPP(PostProcessor):
cmd = [encodeArgument(i) for i in cmd]
self.write_debug('sponskrub command line: %s' % shell_quote(cmd))
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
stdout, stderr = p.communicate()
pipe = None if self.get_param('verbose') else subprocess.PIPE
p = subprocess.Popen(cmd, stdout=pipe)
stdout = process_communicate_or_kill(p)[0]
if p.returncode == 0:
os.remove(encodeFilename(filename))
@@ -85,9 +87,7 @@ class SponSkrubPP(PostProcessor):
elif p.returncode == 3:
self.to_screen('No segments in the SponsorBlock database')
else:
msg = stderr.decode('utf-8', 'replace').strip() or stdout.decode('utf-8', 'replace').strip()
self.write_debug(msg, prefix=False)
line = 0 if msg[:12].lower() == 'unrecognised' else -1
msg = msg.split('\n')[line]
msg = stdout.decode('utf-8', 'replace').strip() if stdout else ''
msg = msg.split('\n')[0 if msg.lower().startswith('unrecognised') else -1]
raise PostProcessingError(msg if msg else 'sponskrub failed with error code %s' % p.returncode)
return [], information
+87 -26
View File
@@ -5,6 +5,7 @@ import json
import traceback
import hashlib
import os
import platform
import subprocess
import sys
from zipimport import zipimporter
@@ -32,23 +33,26 @@ def rsa_verify(message, signature, key):
def update_self(to_screen, verbose, opener):
"""Update the program file with the latest version from the repository"""
"""
Update the program file with the latest version from the repository
Returns whether the program should terminate
"""
JSON_URL = 'https://api.github.com/repos/pukkandan/yt-dlp/releases/latest'
def sha256sum():
def calc_sha256sum(path):
h = hashlib.sha256()
b = bytearray(128 * 1024)
mv = memoryview(b)
with open(os.path.realpath(sys.executable), 'rb', buffering=0) as f:
with open(os.path.realpath(path), 'rb', buffering=0) as f:
for n in iter(lambda: f.readinto(mv), 0):
h.update(mv[:n])
return h.hexdigest()
to_screen('Current Build Hash %s' % sha256sum())
to_screen('Current Build Hash %s' % calc_sha256sum(sys.executable))
if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, 'frozen'):
to_screen('It looks like you installed youtube-dlc with a package manager, pip, setup.py or a tarball. Please use that to update.')
to_screen('It looks like you installed yt-dlp with a package manager, pip, setup.py or a tarball. Please use that to update.')
return
# Download and check versions info
@@ -59,29 +63,46 @@ def update_self(to_screen, verbose, opener):
if verbose:
to_screen(encode_compat_str(traceback.format_exc()))
to_screen('ERROR: can\'t obtain versions info. Please try again later.')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/lastest')
return
version_id = version_info['tag_name']
if version_id == __version__:
to_screen('youtube-dlc is up-to-date (' + __version__ + ')')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
return
def version_tuple(version_str):
return tuple(map(int, version_str.split('.')))
version_id = version_info['tag_name']
if version_tuple(__version__) >= version_tuple(version_id):
to_screen('youtube-dlc is up to date (%s)' % __version__)
to_screen('yt-dlp is up to date (%s)' % __version__)
return
to_screen('Updating to version ' + version_id + ' ...')
version = {
'bin': next(i for i in version_info['assets'] if i['name'] == 'youtube-dlc'),
'exe': next(i for i in version_info['assets'] if i['name'] == 'youtube-dlc.exe'),
'exe_x86': next(i for i in version_info['assets'] if i['name'] == 'youtube-dlc_x86.exe'),
version_labels = {
'zip_3': '',
'zip_2': '',
# 'zip_2': '_py2',
'exe_64': '.exe',
'exe_32': '_x86.exe',
}
def get_bin_info(bin_or_exe, version):
label = version_labels['%s_%s' % (bin_or_exe, version)]
return next(
(i for i in version_info['assets']
if i['name'] in ('yt-dlp%s' % label, 'youtube-dlc%s' % label)), {})
def get_sha256sum(bin_or_exe, version):
label = version_labels['%s_%s' % (bin_or_exe, version)]
urlh = next(
(i for i in version_info['assets']
if i['name'] in ('SHA2-256SUMS')), {}).get('browser_download_url')
if not urlh:
return None
hash_data = opener.open(urlh).read().decode('utf-8')
hashes = list(map(lambda x: x.split(':'), hash_data.splitlines()))
return next(
(i[1] for i in hashes
if i[0] in ('yt-dlp%s' % label, 'youtube-dlc%s' % label)), None)
# sys.executable is set to the full pathname of the exe-file for py2exe
# though symlinks are not followed so that we need to do this manually
# with help of realpath
@@ -100,14 +121,20 @@ def update_self(to_screen, verbose, opener):
return
try:
urlh = opener.open(version['exe']['browser_download_url'])
arch = platform.architecture()[0][:2]
url = get_bin_info('exe', arch).get('browser_download_url')
if not url:
to_screen('ERROR: unable to fetch updates')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
return
urlh = opener.open(url)
newcontent = urlh.read()
urlh.close()
except (IOError, OSError):
except (IOError, OSError, StopIteration):
if verbose:
to_screen(encode_compat_str(traceback.format_exc()))
to_screen('ERROR: unable to download latest version')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/lastest')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
return
try:
@@ -119,6 +146,18 @@ def update_self(to_screen, verbose, opener):
to_screen('ERROR: unable to write the new version')
return
expected_sum = get_sha256sum('exe', arch)
if not expected_sum:
to_screen('WARNING: no hash information found for the release')
elif calc_sha256sum(exe + '.new') != expected_sum:
to_screen('ERROR: unable to verify the new executable')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
try:
os.remove(exe + '.new')
except OSError:
to_screen('ERROR: unable to remove corrupt download')
return
try:
bat = os.path.join(directory, 'yt-dlp-updater.cmd')
with io.open(bat, 'w') as batfile:
@@ -127,13 +166,13 @@ def update_self(to_screen, verbose, opener):
echo.Waiting for file handle to be closed ...
ping 127.0.0.1 -n 5 -w 1000 > NUL
move /Y "%s.new" "%s" > NUL
echo.Updated youtube-dlc to version %s.
echo.Updated yt-dlp to version %s.
)
@start /b "" cmd /c del "%%~f0"&exit /b
''' % (exe, exe, version_id))
subprocess.Popen([bat]) # Continues to run in the background
return # Do not show premature success messages
return True # Exit app
except (IOError, OSError):
if verbose:
to_screen(encode_compat_str(traceback.format_exc()))
@@ -143,26 +182,48 @@ def update_self(to_screen, verbose, opener):
# Zip unix package
elif isinstance(globals().get('__loader__'), zipimporter):
try:
urlh = opener.open(version['bin']['browser_download_url'])
py_ver = platform.python_version()[0]
url = get_bin_info('zip', py_ver).get('browser_download_url')
if not url:
to_screen('ERROR: unable to fetch updates')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
return
urlh = opener.open(url)
newcontent = urlh.read()
urlh.close()
except (IOError, OSError):
except (IOError, OSError, StopIteration):
if verbose:
to_screen(encode_compat_str(traceback.format_exc()))
to_screen('ERROR: unable to download latest version')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/lastest')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
return
try:
with open(filename, 'wb') as outf:
with open(filename + '.new', 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError):
if verbose:
to_screen(encode_compat_str(traceback.format_exc()))
to_screen('ERROR: unable to write the new version')
return
expected_sum = get_sha256sum('zip', py_ver)
if expected_sum and calc_sha256sum(filename + '.new') != expected_sum:
to_screen('ERROR: unable to verify the new zip')
to_screen('Visit https://github.com/pukkandan/yt-dlp/releases/latest')
try:
os.remove(filename + '.new')
except OSError:
to_screen('ERROR: unable to remove corrupt zip')
return
try:
os.rename(filename + '.new', filename)
except OSError:
to_screen('ERROR: unable to overwrite current version')
return
to_screen('Updated youtube-dlc. Restart youtube-dlc to use the new version.')
to_screen('Updated yt-dlp. Restart youtube-dlc to use the new version.')
''' # UNUSED
+3 -1
View File
@@ -2609,6 +2609,8 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
@staticmethod
def deflate(data):
if not data:
return data
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
@@ -5934,7 +5936,7 @@ def make_dir(path, to_screen=None):
def get_executable_path():
path = os.path.dirname(sys.argv[0])
if os.path.abspath(sys.argv[0]) != os.path.abspath(sys.executable): # Not packaged
if os.path.basename(sys.argv[0]) == '__main__': # Running from source
path = os.path.join(path, '..')
return os.path.abspath(path)
+1 -1
View File
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2021.02.04'
__version__ = '2021.02.09'