mirror of
https://github.com/ytdl-org/youtube-dl
synced 2025-10-18 14:18:37 +09:00
Compare commits
116 Commits
015e19b350
...
2021.03.02
Author | SHA1 | Date | |
---|---|---|---|
![]() |
7c06216abf | ||
![]() |
0002888627 | ||
![]() |
3fb14cd214 | ||
![]() |
bee6182680 | ||
![]() |
38fe5e239a | ||
![]() |
678d46f6bb | ||
![]() |
3c58f9e0b9 | ||
![]() |
ef28e33249 | ||
![]() |
9662e4964b | ||
![]() |
44603290e5 | ||
![]() |
1631fca1ee | ||
![]() |
295860ff00 | ||
![]() |
8cb4b71909 | ||
![]() |
d81421af4b | ||
![]() |
7422a2194f | ||
![]() |
2090dbdc8c | ||
![]() |
0a04e03a02 | ||
![]() |
44b2d5f5fc | ||
![]() |
aa9118a373 | ||
![]() |
36abc16c3c | ||
![]() |
919d764600 | ||
![]() |
696183e133 | ||
![]() |
f90d825a6b | ||
![]() |
3037ab00c7 | ||
![]() |
21e872b19a | ||
![]() |
cf2dbec630 | ||
![]() |
b92bb0e02a | ||
![]() |
40edffae3d | ||
![]() |
9fc5eafb8e | ||
![]() |
08c2fbb844 | ||
![]() |
3997efb65e | ||
![]() |
a7356dffe9 | ||
![]() |
e20ec43094 | ||
![]() |
70baa7bfae | ||
![]() |
8980f53b42 | ||
![]() |
a363fb5d28 | ||
![]() |
646052e416 | ||
![]() |
844e4cbc54 | ||
![]() |
56c63c8c02 | ||
![]() |
07eb8f1916 | ||
![]() |
4b5410c5c8 | ||
![]() |
be2e9b76ee | ||
![]() |
d8085580f6 | ||
![]() |
6d32c6c6d3 | ||
![]() |
f94d764993 | ||
![]() |
f28f1b4d6e | ||
![]() |
360d5f0daa | ||
![]() |
cd493c5adc | ||
![]() |
a4c7ed6b1e | ||
![]() |
7f8b8bc418 | ||
![]() |
311ebdd9a5 | ||
![]() |
99c68db0a8 | ||
![]() |
5fc53690cb | ||
![]() |
7a9161578e | ||
![]() |
2405854705 | ||
![]() |
0cf09c2b41 | ||
![]() |
0156ce95c5 | ||
![]() |
1641b13232 | ||
![]() |
a4bdc3112b | ||
![]() |
c7d407bca2 | ||
![]() |
7215691ab7 | ||
![]() |
fc88e8f0e3 | ||
![]() |
cfefb7d854 | ||
![]() |
3c07d007ca | ||
![]() |
89c5a7d5aa | ||
![]() |
2adc0c51cd | ||
![]() |
1f0910bc27 | ||
![]() |
e22ff4e356 | ||
![]() |
83031d749b | ||
![]() |
1b731ebcaa | ||
![]() |
ab25f3f431 | ||
![]() |
07f7aad81c | ||
![]() |
1e2575df87 | ||
![]() |
b111a64135 | ||
![]() |
0e3a968479 | ||
![]() |
c11f7cf9bd | ||
![]() |
8fa7cc387d | ||
![]() |
65eee5a745 | ||
![]() |
efef4ddf51 | ||
![]() |
159a3d48df | ||
![]() |
b46483a6ec | ||
![]() |
9c724601ba | ||
![]() |
67299f23d8 | ||
![]() |
8bf9591a70 | ||
![]() |
a800838f5a | ||
![]() |
ba15b2fee6 | ||
![]() |
56a7ee9033 | ||
![]() |
0b4f03a563 | ||
![]() |
7b8fa658f8 | ||
![]() |
fd95fc33b1 | ||
![]() |
c669554ef5 | ||
![]() |
11b68df7a4 | ||
![]() |
d18f4419a7 | ||
![]() |
0f7d413d5b | ||
![]() |
286e5d6724 | ||
![]() |
395981288b | ||
![]() |
55bb3556c8 | ||
![]() |
57f2488bbe | ||
![]() |
ea399a53eb | ||
![]() |
811a183eb6 | ||
![]() |
b63981e850 | ||
![]() |
186cbaffb9 | ||
![]() |
dbf3fa8af6 | ||
![]() |
f08c31cf33 | ||
![]() |
d8dab85419 | ||
![]() |
5519bba3e1 | ||
![]() |
142c584063 | ||
![]() |
4542e3e555 | ||
![]() |
fa8f6d8580 | ||
![]() |
3bb7769c40 | ||
![]() |
8d286bd5b6 | ||
![]() |
cff72b4cc0 | ||
![]() |
657221c81d | ||
![]() |
62acf5fa2c | ||
![]() |
b79977fb6b | ||
![]() |
bc7c8f3d4e |
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
@@ -18,7 +18,7 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update 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 http://yt-dl.org/escape.
|
||||
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@@ -26,7 +26,7 @@ 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 youtube-dl version **2021.01.16**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
|
||||
- [ ] 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
|
||||
@@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -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] youtube-dl version 2021.01.16
|
||||
[debug] youtube-dl version 2021.03.02
|
||||
[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: {}
|
||||
|
@@ -19,7 +19,7 @@ labels: 'site-support-request'
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update 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://yt-dl.org/copyright-infringement. youtube-dl 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: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@@ -27,7 +27,7 @@ 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 youtube-dl version **2021.01.16**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
|
||||
- [ ] 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
|
||||
|
@@ -18,13 +18,13 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes (like this [x])
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a site feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.01.16**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
|
||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||
|
||||
|
||||
|
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
@@ -18,7 +18,7 @@ title: ''
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update 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 http://yt-dl.org/escape.
|
||||
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
@@ -27,7 +27,7 @@ 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 youtube-dl version **2021.01.16**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
|
||||
- [ ] 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
|
||||
@@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -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] youtube-dl version 2021.01.16
|
||||
[debug] youtube-dl version 2021.03.02
|
||||
[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: {}
|
||||
|
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
@@ -19,13 +19,13 @@ labels: 'request'
|
||||
|
||||
<!--
|
||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.01.16. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.03.02. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
|
||||
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
|
||||
- Finally, put x into all relevant boxes (like this [x])
|
||||
-->
|
||||
|
||||
- [ ] I'm reporting a feature request
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.01.16**
|
||||
- [ ] I've verified that I'm running youtube-dl version **2021.03.02**
|
||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||
|
||||
|
||||
|
1
AUTHORS
1
AUTHORS
@@ -246,3 +246,4 @@ Enes Solak
|
||||
Nathan Rossi
|
||||
Thomas van der Berg
|
||||
Luca Cherubin
|
||||
Adrian Heine
|
152
ChangeLog
152
ChangeLog
@@ -1,3 +1,155 @@
|
||||
version 2021.03.02
|
||||
|
||||
Extractors
|
||||
* [zdf] Rework extractors (#11606, #13473, #17354, #21185, #26711, #27068,
|
||||
#27930, #28198, #28199, #28274)
|
||||
* Generalize cross-extractor video ids for zdf based extractors
|
||||
* Improve extraction
|
||||
* Fix 3sat and phoenix
|
||||
* [stretchinternet] Fix extraction (#28297)
|
||||
* [urplay] Fix episode data extraction (#28292)
|
||||
+ [bandaichannel] Add support for b-ch.com (#21404)
|
||||
* [srgssr] Improve extraction (#14717, #14725, #27231, #28238)
|
||||
+ Extract subtitle
|
||||
* Fix extraction for new videos
|
||||
* Update srf download domains
|
||||
* [vvvvid] Reduce season request payload size
|
||||
+ [vvvvid] Extract series sublists playlist title (#27601, #27618)
|
||||
+ [dplay] Extract Ad-Free uplynk URLs (#28160)
|
||||
+ [wat] Detect DRM protected videos (#27958)
|
||||
* [tf1] Improve extraction (#27980, #28040)
|
||||
* [tmz] Fix and improve extraction (#24603, #24687, 28211)
|
||||
+ [gedidigital] Add support for Gedi group sites (#7347, #26946)
|
||||
* [youtube] Fix get_video_info request
|
||||
|
||||
|
||||
version 2021.02.22
|
||||
|
||||
Core
|
||||
+ [postprocessor/embedthumbnail] Recognize atomicparsley binary in lowercase
|
||||
(#28112)
|
||||
|
||||
Extractors
|
||||
* [apa] Fix and improve extraction (#27750)
|
||||
+ [youporn] Extract duration (#28019)
|
||||
+ [peertube] Add support for canard.tube (#28190)
|
||||
* [youtube] Fixup m4a_dash formats (#28165)
|
||||
+ [samplefocus] Add support for samplefocus.com (#27763)
|
||||
+ [vimeo] Add support for unlisted video source format extraction
|
||||
* [viki] Improve extraction (#26522, #28203)
|
||||
* Extract uploader URL and episode number
|
||||
* Report login required error
|
||||
+ Extract 480p formats
|
||||
* Fix API v4 calls
|
||||
* [ninegag] Unescape title (#28201)
|
||||
* [youtube] Improve URL regular expression (#28193)
|
||||
+ [youtube] Add support for redirect.invidious.io (#28193)
|
||||
+ [dplay] Add support for de.hgtv.com (#28182)
|
||||
+ [dplay] Add support for discoveryplus.com (#24698)
|
||||
+ [simplecast] Add support for simplecast.com (#24107)
|
||||
* [youtube] Fix uploader extraction in flat playlist mode (#28045)
|
||||
* [yandexmusic:playlist] Request missing tracks in chunks (#27355, #28184)
|
||||
+ [storyfire] Add support for storyfire.com (#25628, #26349)
|
||||
+ [zhihu] Add support for zhihu.com (#28177)
|
||||
* [youtube] Fix controversial videos when authenticated with cookies (#28174)
|
||||
* [ccma] Fix timestamp parsing in python 2
|
||||
+ [videopress] Add support for video.wordpress.com
|
||||
* [kakao] Improve info extraction and detect geo restriction (#26577)
|
||||
* [xboxclips] Fix extraction (#27151)
|
||||
* [ard] Improve formats extraction (#28155)
|
||||
+ [canvas] Add support for dagelijksekost.een.be (#28119)
|
||||
|
||||
|
||||
version 2021.02.10
|
||||
|
||||
Extractors
|
||||
* [youtube:tab] Improve grid continuation extraction (#28130)
|
||||
* [ign] Fix extraction (#24771)
|
||||
+ [xhamster] Extract format filesize
|
||||
+ [xhamster] Extract formats from xplayer settings (#28114)
|
||||
+ [youtube] Add support phone/tablet JS player (#26424)
|
||||
* [archiveorg] Fix and improve extraction (#21330, #23586, #25277, #26780,
|
||||
#27109, #27236, #28063)
|
||||
+ [cda] Detect geo restricted videos (#28106)
|
||||
* [urplay] Fix extraction (#28073, #28074)
|
||||
* [youtube] Fix release date extraction (#28094)
|
||||
+ [youtube] Extract abr and vbr (#28100)
|
||||
* [youtube] Skip OTF formats (#28070)
|
||||
|
||||
|
||||
version 2021.02.04.1
|
||||
|
||||
Extractors
|
||||
* [youtube] Prefer DASH formats (#28070)
|
||||
* [azmedien] Fix extraction (#28064)
|
||||
|
||||
|
||||
version 2021.02.04
|
||||
|
||||
Extractors
|
||||
* [pornhub] Implement lazy playlist extraction
|
||||
* [svtplay] Fix video id extraction (#28058)
|
||||
+ [pornhub] Add support for authentication (#18797, #21416, #24294)
|
||||
* [pornhub:user] Improve paging
|
||||
+ [pornhub:user] Add support for URLs unavailable via /videos page (#27853)
|
||||
+ [bravotv] Add support for oxygen.com (#13357, #22500)
|
||||
+ [youtube] Pass embed URL to get_video_info request
|
||||
* [ccma] Improve metadata extraction (#27994)
|
||||
+ Extract age limit, alt title, categories, series and episode number
|
||||
* Fix timestamp multiple subtitles extraction
|
||||
* [egghead] Update API domain (#28038)
|
||||
- [vidzi] Remove extractor (#12629)
|
||||
* [vidio] Improve metadata extraction
|
||||
* [youtube] Improve subtitles extraction
|
||||
* [youtube] Fix chapter extraction fallback
|
||||
* [youtube] Rewrite extractor
|
||||
* Improve format sorting
|
||||
* Remove unused code
|
||||
* Fix series metadata extraction
|
||||
* Fix trailer video extraction
|
||||
* Improve error reporting
|
||||
+ Extract video location
|
||||
+ [vvvvid] Add support for youtube embeds (#27825)
|
||||
* [googledrive] Report download page errors (#28005)
|
||||
* [vlive] Fix error message decoding for python 2 (#28004)
|
||||
* [youtube] Improve DASH formats file size extraction
|
||||
* [cda] Improve birth validation detection (#14022, #27929)
|
||||
+ [awaan] Extract uploader id (#27963)
|
||||
+ [medialaan] Add support DPG Media MyChannels based websites (#14871, #15597,
|
||||
#16106, #16489)
|
||||
* [abcnews] Fix extraction (#12394, #27920)
|
||||
* [AMP] Fix upload date and timestamp extraction (#27970)
|
||||
* [tv4] Relax URL regular expression (#27964)
|
||||
+ [tv2] Add support for mtvuutiset.fi (#27744)
|
||||
* [adn] Improve login warning reporting
|
||||
* [zype] Fix uplynk id extraction (#27956)
|
||||
+ [adn] Add support for authentication (#17091, #27841, #27937)
|
||||
|
||||
|
||||
version 2021.01.24.1
|
||||
|
||||
Core
|
||||
* Introduce --output-na-placeholder (#27896)
|
||||
|
||||
Extractors
|
||||
* [franceculture] Make thumbnail optional (#18807)
|
||||
* [franceculture] Fix extraction (#27891, #27903)
|
||||
* [njpwworld] Fix extraction (#27890)
|
||||
* [comedycentral] Fix extraction (#27905)
|
||||
* [wat] Fix format extraction (#27901)
|
||||
+ [americastestkitchen:season] Add support for seasons (#27861)
|
||||
+ [trovo] Add support for trovo.live (#26125)
|
||||
+ [aol] Add support for yahoo videos (#26650)
|
||||
* [yahoo] Fix single video extraction
|
||||
* [lbry] Unescape lbry URI (#27872)
|
||||
* [9gag] Fix and improve extraction (#23022)
|
||||
* [americastestkitchen] Improve metadata extraction for ATK episodes (#27860)
|
||||
* [aljazeera] Fix extraction (#20911, #27779)
|
||||
+ [minds] Add support for minds.com (#17934)
|
||||
* [ard] Fix title and description extraction (#27761)
|
||||
+ [spotify] Add support for Spotify Podcasts (#27443)
|
||||
|
||||
|
||||
version 2021.01.16
|
||||
|
||||
Core
|
||||
|
763
README.md
763
README.md
@@ -52,394 +52,431 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
|
||||
youtube-dl [OPTIONS] URL [URL...]
|
||||
|
||||
# OPTIONS
|
||||
-h, --help Print this help text and exit
|
||||
--version Print program version and exit
|
||||
-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
|
||||
--abort-on-error Abort downloading of further videos (in the
|
||||
playlist or the command line) if an error
|
||||
occurs
|
||||
--dump-user-agent Display the current browser identification
|
||||
--list-extractors List all supported extractors
|
||||
--extractor-descriptions Output descriptions of all supported
|
||||
extractors
|
||||
--force-generic-extractor Force extraction to use the generic
|
||||
extractor
|
||||
--default-search PREFIX Use this prefix for unqualified URLs. For
|
||||
example "gvsearch2:" downloads two videos
|
||||
from google videos for youtube-dl "large
|
||||
apple". Use the value "auto" to let
|
||||
youtube-dl guess ("auto_warning" to emit a
|
||||
warning when guessing). "error" just throws
|
||||
an error. The default value "fixup_error"
|
||||
repairs broken URLs, but emits an error if
|
||||
this is not possible instead of searching.
|
||||
--ignore-config Do not read configuration files. When given
|
||||
in the global configuration file
|
||||
/etc/youtube-dl.conf: Do not read the user
|
||||
configuration in ~/.config/youtube-
|
||||
dl/config (%APPDATA%/youtube-dl/config.txt
|
||||
on Windows)
|
||||
--config-location PATH Location of the configuration file; either
|
||||
the path to the config or its containing
|
||||
directory.
|
||||
--flat-playlist Do not extract the videos of a playlist,
|
||||
only list them.
|
||||
--mark-watched Mark videos watched (YouTube only)
|
||||
--no-mark-watched Do not mark videos watched (YouTube only)
|
||||
--no-color Do not emit color codes in output
|
||||
-h, --help Print this help text and exit
|
||||
--version Print program version and exit
|
||||
-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
|
||||
--abort-on-error Abort downloading of further videos (in
|
||||
the playlist or the command line) if an
|
||||
error occurs
|
||||
--dump-user-agent Display the current browser
|
||||
identification
|
||||
--list-extractors List all supported extractors
|
||||
--extractor-descriptions Output descriptions of all supported
|
||||
extractors
|
||||
--force-generic-extractor Force extraction to use the generic
|
||||
extractor
|
||||
--default-search PREFIX Use this prefix for unqualified URLs.
|
||||
For example "gvsearch2:" downloads two
|
||||
videos from google videos for youtube-
|
||||
dl "large apple". Use the value "auto"
|
||||
to let youtube-dl guess ("auto_warning"
|
||||
to emit a warning when guessing).
|
||||
"error" just throws an error. The
|
||||
default value "fixup_error" repairs
|
||||
broken URLs, but emits an error if this
|
||||
is not possible instead of searching.
|
||||
--ignore-config Do not read configuration files. When
|
||||
given in the global configuration file
|
||||
/etc/youtube-dl.conf: Do not read the
|
||||
user configuration in
|
||||
~/.config/youtube-dl/config
|
||||
(%APPDATA%/youtube-dl/config.txt on
|
||||
Windows)
|
||||
--config-location PATH Location of the configuration file;
|
||||
either the path to the config or its
|
||||
containing directory.
|
||||
--flat-playlist Do not extract the videos of a
|
||||
playlist, only list them.
|
||||
--mark-watched Mark videos watched (YouTube only)
|
||||
--no-mark-watched Do not mark videos watched (YouTube
|
||||
only)
|
||||
--no-color Do not emit color codes in output
|
||||
|
||||
## Network Options:
|
||||
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
|
||||
To enable SOCKS proxy, specify a proper
|
||||
scheme. For example
|
||||
socks5://127.0.0.1:1080/. Pass in an empty
|
||||
string (--proxy "") for direct connection
|
||||
--socket-timeout SECONDS Time to wait before giving up, in seconds
|
||||
--source-address IP Client-side IP address to bind to
|
||||
-4, --force-ipv4 Make all connections via IPv4
|
||||
-6, --force-ipv6 Make all connections via IPv6
|
||||
--proxy URL Use the specified HTTP/HTTPS/SOCKS
|
||||
proxy. To enable SOCKS proxy, specify a
|
||||
proper scheme. For example
|
||||
socks5://127.0.0.1:1080/. Pass in an
|
||||
empty string (--proxy "") for direct
|
||||
connection
|
||||
--socket-timeout SECONDS Time to wait before giving up, in
|
||||
seconds
|
||||
--source-address IP Client-side IP address to bind to
|
||||
-4, --force-ipv4 Make all connections via IPv4
|
||||
-6, --force-ipv6 Make all connections via IPv6
|
||||
|
||||
## Geo Restriction:
|
||||
--geo-verification-proxy URL Use this proxy to verify the IP address for
|
||||
some geo-restricted sites. The default
|
||||
proxy specified by --proxy (or none, if the
|
||||
option is not present) is used for the
|
||||
actual downloading.
|
||||
--geo-bypass Bypass geographic restriction via faking
|
||||
X-Forwarded-For HTTP header
|
||||
--no-geo-bypass Do not bypass geographic restriction via
|
||||
faking X-Forwarded-For HTTP header
|
||||
--geo-bypass-country CODE Force bypass geographic restriction with
|
||||
explicitly provided two-letter ISO 3166-2
|
||||
country code
|
||||
--geo-bypass-ip-block IP_BLOCK Force bypass geographic restriction with
|
||||
explicitly provided IP block in CIDR
|
||||
notation
|
||||
--geo-verification-proxy URL Use this proxy to verify the IP address
|
||||
for some geo-restricted sites. The
|
||||
default proxy specified by --proxy (or
|
||||
none, if the option is not present) is
|
||||
used for the actual downloading.
|
||||
--geo-bypass Bypass geographic restriction via
|
||||
faking X-Forwarded-For HTTP header
|
||||
--no-geo-bypass Do not bypass geographic restriction
|
||||
via faking X-Forwarded-For HTTP header
|
||||
--geo-bypass-country CODE Force bypass geographic restriction
|
||||
with explicitly provided two-letter ISO
|
||||
3166-2 country code
|
||||
--geo-bypass-ip-block IP_BLOCK Force bypass geographic restriction
|
||||
with explicitly provided IP block in
|
||||
CIDR notation
|
||||
|
||||
## Video Selection:
|
||||
--playlist-start NUMBER Playlist video to start at (default is 1)
|
||||
--playlist-end NUMBER Playlist video to end at (default is last)
|
||||
--playlist-items ITEM_SPEC Playlist video items to download. Specify
|
||||
indices of the videos in the playlist
|
||||
separated by commas like: "--playlist-items
|
||||
1,2,5,8" if you want to download videos
|
||||
indexed 1, 2, 5, 8 in the playlist. You can
|
||||
specify range: "--playlist-items
|
||||
1-3,7,10-13", it will download the videos
|
||||
at index 1, 2, 3, 7, 10, 11, 12 and 13.
|
||||
--match-title REGEX Download only matching titles (regex or
|
||||
caseless sub-string)
|
||||
--reject-title REGEX Skip download for matching titles (regex or
|
||||
caseless sub-string)
|
||||
--max-downloads NUMBER Abort after downloading NUMBER files
|
||||
--min-filesize SIZE Do not download any videos smaller than
|
||||
SIZE (e.g. 50k or 44.6m)
|
||||
--max-filesize SIZE Do not download any videos larger than SIZE
|
||||
(e.g. 50k or 44.6m)
|
||||
--date DATE Download only videos uploaded in this date
|
||||
--datebefore DATE Download only videos uploaded on or before
|
||||
this date (i.e. inclusive)
|
||||
--dateafter DATE Download only videos uploaded on or after
|
||||
this date (i.e. inclusive)
|
||||
--min-views COUNT Do not download any videos with less than
|
||||
COUNT views
|
||||
--max-views COUNT Do not download any videos with more than
|
||||
COUNT views
|
||||
--match-filter FILTER Generic video filter. Specify any key (see
|
||||
the "OUTPUT TEMPLATE" for a list of
|
||||
available keys) to match if the key is
|
||||
present, !key to check if the key is not
|
||||
present, key > NUMBER (like "comment_count
|
||||
> 12", also works with >=, <, <=, !=, =) to
|
||||
compare against a number, key = 'LITERAL'
|
||||
(like "uploader = 'Mike Smith'", also works
|
||||
with !=) to match against a string literal
|
||||
and & to require multiple matches. Values
|
||||
which are not known are excluded unless you
|
||||
put a question mark (?) after the operator.
|
||||
For example, to only match videos that have
|
||||
been liked more than 100 times and disliked
|
||||
less than 50 times (or the dislike
|
||||
functionality is not available at the given
|
||||
service), but who also have a description,
|
||||
use --match-filter "like_count > 100 &
|
||||
dislike_count <? 50 & description" .
|
||||
--no-playlist Download only the video, if the URL refers
|
||||
to a video and a playlist.
|
||||
--yes-playlist Download the playlist, if the URL refers to
|
||||
a video and a playlist.
|
||||
--age-limit YEARS Download only videos suitable for the given
|
||||
age
|
||||
--download-archive FILE Download only videos not listed in the
|
||||
archive file. Record the IDs of all
|
||||
downloaded videos in it.
|
||||
--include-ads Download advertisements as well
|
||||
(experimental)
|
||||
--playlist-start NUMBER Playlist video to start at (default is
|
||||
1)
|
||||
--playlist-end NUMBER Playlist video to end at (default is
|
||||
last)
|
||||
--playlist-items ITEM_SPEC Playlist video items to download.
|
||||
Specify indices of the videos in the
|
||||
playlist separated by commas like: "--
|
||||
playlist-items 1,2,5,8" if you want to
|
||||
download videos indexed 1, 2, 5, 8 in
|
||||
the playlist. You can specify range: "
|
||||
--playlist-items 1-3,7,10-13", it will
|
||||
download the videos at index 1, 2, 3,
|
||||
7, 10, 11, 12 and 13.
|
||||
--match-title REGEX Download only matching titles (regex or
|
||||
caseless sub-string)
|
||||
--reject-title REGEX Skip download for matching titles
|
||||
(regex or caseless sub-string)
|
||||
--max-downloads NUMBER Abort after downloading NUMBER files
|
||||
--min-filesize SIZE Do not download any videos smaller than
|
||||
SIZE (e.g. 50k or 44.6m)
|
||||
--max-filesize SIZE Do not download any videos larger than
|
||||
SIZE (e.g. 50k or 44.6m)
|
||||
--date DATE Download only videos uploaded in this
|
||||
date
|
||||
--datebefore DATE Download only videos uploaded on or
|
||||
before this date (i.e. inclusive)
|
||||
--dateafter DATE Download only videos uploaded on or
|
||||
after this date (i.e. inclusive)
|
||||
--min-views COUNT Do not download any videos with less
|
||||
than COUNT views
|
||||
--max-views COUNT Do not download any videos with more
|
||||
than COUNT views
|
||||
--match-filter FILTER Generic video filter. Specify any key
|
||||
(see the "OUTPUT TEMPLATE" for a list
|
||||
of available keys) to match if the key
|
||||
is present, !key to check if the key is
|
||||
not present, key > NUMBER (like
|
||||
"comment_count > 12", also works with
|
||||
>=, <, <=, !=, =) to compare against a
|
||||
number, key = 'LITERAL' (like "uploader
|
||||
= 'Mike Smith'", also works with !=) to
|
||||
match against a string literal and & to
|
||||
require multiple matches. Values which
|
||||
are not known are excluded unless you
|
||||
put a question mark (?) after the
|
||||
operator. For example, to only match
|
||||
videos that have been liked more than
|
||||
100 times and disliked less than 50
|
||||
times (or the dislike functionality is
|
||||
not available at the given service),
|
||||
but who also have a description, use
|
||||
--match-filter "like_count > 100 &
|
||||
dislike_count <? 50 & description" .
|
||||
--no-playlist Download only the video, if the URL
|
||||
refers to a video and a playlist.
|
||||
--yes-playlist Download the playlist, if the URL
|
||||
refers to a video and a playlist.
|
||||
--age-limit YEARS Download only videos suitable for the
|
||||
given age
|
||||
--download-archive FILE Download only videos not listed in the
|
||||
archive file. Record the IDs of all
|
||||
downloaded videos in it.
|
||||
--include-ads Download advertisements as well
|
||||
(experimental)
|
||||
|
||||
## Download Options:
|
||||
-r, --limit-rate RATE Maximum download rate in bytes per second
|
||||
(e.g. 50K or 4.2M)
|
||||
-R, --retries RETRIES Number of retries (default is 10), or
|
||||
"infinite".
|
||||
--fragment-retries RETRIES Number of retries for a fragment (default
|
||||
is 10), or "infinite" (DASH, hlsnative and
|
||||
ISM)
|
||||
--skip-unavailable-fragments Skip unavailable fragments (DASH, hlsnative
|
||||
and ISM)
|
||||
--abort-on-unavailable-fragment Abort downloading when some fragment is not
|
||||
available
|
||||
--keep-fragments Keep downloaded fragments on disk after
|
||||
downloading is finished; fragments are
|
||||
erased by default
|
||||
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
|
||||
(default is 1024)
|
||||
--no-resize-buffer Do not automatically adjust the buffer
|
||||
size. By default, the buffer size is
|
||||
automatically resized from an initial value
|
||||
of SIZE.
|
||||
--http-chunk-size SIZE Size of a chunk for chunk-based HTTP
|
||||
downloading (e.g. 10485760 or 10M) (default
|
||||
is disabled). May be useful for bypassing
|
||||
bandwidth throttling imposed by a webserver
|
||||
(experimental)
|
||||
--playlist-reverse Download playlist videos in reverse order
|
||||
--playlist-random Download playlist videos in random order
|
||||
--xattr-set-filesize Set file xattribute ytdl.filesize with
|
||||
expected file size
|
||||
--hls-prefer-native Use the native HLS downloader instead of
|
||||
ffmpeg
|
||||
--hls-prefer-ffmpeg Use ffmpeg instead of the native HLS
|
||||
downloader
|
||||
--hls-use-mpegts Use the mpegts container for HLS videos,
|
||||
allowing to play the video while
|
||||
downloading (some players may not be able
|
||||
to play it)
|
||||
--external-downloader COMMAND Use the specified external downloader.
|
||||
Currently supports
|
||||
aria2c,avconv,axel,curl,ffmpeg,httpie,wget
|
||||
--external-downloader-args ARGS Give these arguments to the external
|
||||
downloader
|
||||
-r, --limit-rate RATE Maximum download rate in bytes per
|
||||
second (e.g. 50K or 4.2M)
|
||||
-R, --retries RETRIES Number of retries (default is 10), or
|
||||
"infinite".
|
||||
--fragment-retries RETRIES Number of retries for a fragment
|
||||
(default is 10), or "infinite" (DASH,
|
||||
hlsnative and ISM)
|
||||
--skip-unavailable-fragments Skip unavailable fragments (DASH,
|
||||
hlsnative and ISM)
|
||||
--abort-on-unavailable-fragment Abort downloading when some fragment is
|
||||
not available
|
||||
--keep-fragments Keep downloaded fragments on disk after
|
||||
downloading is finished; fragments are
|
||||
erased by default
|
||||
--buffer-size SIZE Size of download buffer (e.g. 1024 or
|
||||
16K) (default is 1024)
|
||||
--no-resize-buffer Do not automatically adjust the buffer
|
||||
size. By default, the buffer size is
|
||||
automatically resized from an initial
|
||||
value of SIZE.
|
||||
--http-chunk-size SIZE Size of a chunk for chunk-based HTTP
|
||||
downloading (e.g. 10485760 or 10M)
|
||||
(default is disabled). May be useful
|
||||
for bypassing bandwidth throttling
|
||||
imposed by a webserver (experimental)
|
||||
--playlist-reverse Download playlist videos in reverse
|
||||
order
|
||||
--playlist-random Download playlist videos in random
|
||||
order
|
||||
--xattr-set-filesize Set file xattribute ytdl.filesize with
|
||||
expected file size
|
||||
--hls-prefer-native Use the native HLS downloader instead
|
||||
of ffmpeg
|
||||
--hls-prefer-ffmpeg Use ffmpeg instead of the native HLS
|
||||
downloader
|
||||
--hls-use-mpegts Use the mpegts container for HLS
|
||||
videos, allowing to play the video
|
||||
while downloading (some players may not
|
||||
be able to play it)
|
||||
--external-downloader COMMAND Use the specified external downloader.
|
||||
Currently supports aria2c,avconv,axel,c
|
||||
url,ffmpeg,httpie,wget
|
||||
--external-downloader-args ARGS Give these arguments to the external
|
||||
downloader
|
||||
|
||||
## Filesystem Options:
|
||||
-a, --batch-file FILE File containing URLs to download ('-' for
|
||||
stdin), one URL per line. Lines starting
|
||||
with '#', ';' or ']' are considered as
|
||||
comments and ignored.
|
||||
--id Use only video ID in file name
|
||||
-o, --output TEMPLATE Output filename template, see the "OUTPUT
|
||||
TEMPLATE" for all the info
|
||||
--autonumber-start NUMBER Specify the start value for %(autonumber)s
|
||||
(default is 1)
|
||||
--restrict-filenames Restrict filenames to only ASCII
|
||||
characters, and avoid "&" and spaces in
|
||||
filenames
|
||||
-w, --no-overwrites Do not overwrite files
|
||||
-c, --continue Force resume of partially downloaded files.
|
||||
By default, youtube-dl will resume
|
||||
downloads if possible.
|
||||
--no-continue Do not resume partially downloaded files
|
||||
(restart from beginning)
|
||||
--no-part Do not use .part files - write directly
|
||||
into output file
|
||||
--no-mtime Do not use the Last-modified header to set
|
||||
the file modification time
|
||||
--write-description Write video description to a .description
|
||||
file
|
||||
--write-info-json Write video metadata to a .info.json file
|
||||
--write-annotations Write video annotations to a
|
||||
.annotations.xml file
|
||||
--load-info-json FILE JSON file containing the video information
|
||||
(created with the "--write-info-json"
|
||||
option)
|
||||
--cookies FILE File to read cookies from and dump cookie
|
||||
jar in
|
||||
--cache-dir DIR Location in the filesystem where youtube-dl
|
||||
can store some downloaded information
|
||||
permanently. By default
|
||||
$XDG_CACHE_HOME/youtube-dl or
|
||||
~/.cache/youtube-dl . At the moment, only
|
||||
YouTube player files (for videos with
|
||||
obfuscated signatures) are cached, but that
|
||||
may change.
|
||||
--no-cache-dir Disable filesystem caching
|
||||
--rm-cache-dir Delete all filesystem cache files
|
||||
-a, --batch-file FILE File containing URLs to download ('-'
|
||||
for stdin), one URL per line. Lines
|
||||
starting with '#', ';' or ']' are
|
||||
considered as comments and ignored.
|
||||
--id Use only video ID in file name
|
||||
-o, --output TEMPLATE Output filename template, see the
|
||||
"OUTPUT TEMPLATE" for all the info
|
||||
--output-na-placeholder PLACEHOLDER Placeholder value for unavailable meta
|
||||
fields in output filename template
|
||||
(default is "NA")
|
||||
--autonumber-start NUMBER Specify the start value for
|
||||
%(autonumber)s (default is 1)
|
||||
--restrict-filenames Restrict filenames to only ASCII
|
||||
characters, and avoid "&" and spaces in
|
||||
filenames
|
||||
-w, --no-overwrites Do not overwrite files
|
||||
-c, --continue Force resume of partially downloaded
|
||||
files. By default, youtube-dl will
|
||||
resume downloads if possible.
|
||||
--no-continue Do not resume partially downloaded
|
||||
files (restart from beginning)
|
||||
--no-part Do not use .part files - write directly
|
||||
into output file
|
||||
--no-mtime Do not use the Last-modified header to
|
||||
set the file modification time
|
||||
--write-description Write video description to a
|
||||
.description file
|
||||
--write-info-json Write video metadata to a .info.json
|
||||
file
|
||||
--write-annotations Write video annotations to a
|
||||
.annotations.xml file
|
||||
--load-info-json FILE JSON file containing the video
|
||||
information (created with the "--write-
|
||||
info-json" option)
|
||||
--cookies FILE File to read cookies from and dump
|
||||
cookie jar in
|
||||
--cache-dir DIR Location in the filesystem where
|
||||
youtube-dl can store some downloaded
|
||||
information permanently. By default
|
||||
$XDG_CACHE_HOME/youtube-dl or
|
||||
~/.cache/youtube-dl . At the moment,
|
||||
only YouTube player files (for videos
|
||||
with obfuscated signatures) are cached,
|
||||
but that may change.
|
||||
--no-cache-dir Disable filesystem caching
|
||||
--rm-cache-dir Delete all filesystem cache files
|
||||
|
||||
## Thumbnail images:
|
||||
--write-thumbnail Write thumbnail image to disk
|
||||
--write-all-thumbnails Write all thumbnail image formats to disk
|
||||
--list-thumbnails Simulate and list all available thumbnail
|
||||
formats
|
||||
--write-thumbnail Write thumbnail image to disk
|
||||
--write-all-thumbnails Write all thumbnail image formats to
|
||||
disk
|
||||
--list-thumbnails Simulate and list all available
|
||||
thumbnail formats
|
||||
|
||||
## Verbosity / Simulation Options:
|
||||
-q, --quiet Activate quiet mode
|
||||
--no-warnings Ignore warnings
|
||||
-s, --simulate Do not download the video and do not write
|
||||
anything to disk
|
||||
--skip-download Do not download the video
|
||||
-g, --get-url Simulate, quiet but print URL
|
||||
-e, --get-title Simulate, quiet but print title
|
||||
--get-id Simulate, quiet but print id
|
||||
--get-thumbnail Simulate, quiet but print thumbnail URL
|
||||
--get-description Simulate, quiet but print video description
|
||||
--get-duration Simulate, quiet but print video length
|
||||
--get-filename Simulate, quiet but print output filename
|
||||
--get-format Simulate, quiet but print output format
|
||||
-j, --dump-json Simulate, quiet but print JSON information.
|
||||
See the "OUTPUT TEMPLATE" for a description
|
||||
of available keys.
|
||||
-J, --dump-single-json Simulate, quiet but print JSON information
|
||||
for each command-line argument. If the URL
|
||||
refers to a playlist, dump the whole
|
||||
playlist information in a single line.
|
||||
--print-json Be quiet and print the video information as
|
||||
JSON (video is still being downloaded).
|
||||
--newline Output progress bar as new lines
|
||||
--no-progress Do not print progress bar
|
||||
--console-title Display progress in console titlebar
|
||||
-v, --verbose Print various debugging information
|
||||
--dump-pages Print downloaded pages encoded using base64
|
||||
to debug problems (very verbose)
|
||||
--write-pages Write downloaded intermediary pages to
|
||||
files in the current directory to debug
|
||||
problems
|
||||
--print-traffic Display sent and read HTTP traffic
|
||||
-C, --call-home Contact the youtube-dl server for debugging
|
||||
--no-call-home Do NOT contact the youtube-dl server for
|
||||
debugging
|
||||
-q, --quiet Activate quiet mode
|
||||
--no-warnings Ignore warnings
|
||||
-s, --simulate Do not download the video and do not
|
||||
write anything to disk
|
||||
--skip-download Do not download the video
|
||||
-g, --get-url Simulate, quiet but print URL
|
||||
-e, --get-title Simulate, quiet but print title
|
||||
--get-id Simulate, quiet but print id
|
||||
--get-thumbnail Simulate, quiet but print thumbnail URL
|
||||
--get-description Simulate, quiet but print video
|
||||
description
|
||||
--get-duration Simulate, quiet but print video length
|
||||
--get-filename Simulate, quiet but print output
|
||||
filename
|
||||
--get-format Simulate, quiet but print output format
|
||||
-j, --dump-json Simulate, quiet but print JSON
|
||||
information. See the "OUTPUT TEMPLATE"
|
||||
for a description of available keys.
|
||||
-J, --dump-single-json Simulate, quiet but print JSON
|
||||
information for each command-line
|
||||
argument. If the URL refers to a
|
||||
playlist, dump the whole playlist
|
||||
information in a single line.
|
||||
--print-json Be quiet and print the video
|
||||
information as JSON (video is still
|
||||
being downloaded).
|
||||
--newline Output progress bar as new lines
|
||||
--no-progress Do not print progress bar
|
||||
--console-title Display progress in console titlebar
|
||||
-v, --verbose Print various debugging information
|
||||
--dump-pages Print downloaded pages encoded using
|
||||
base64 to debug problems (very verbose)
|
||||
--write-pages Write downloaded intermediary pages to
|
||||
files in the current directory to debug
|
||||
problems
|
||||
--print-traffic Display sent and read HTTP traffic
|
||||
-C, --call-home Contact the youtube-dl server for
|
||||
debugging
|
||||
--no-call-home Do NOT contact the youtube-dl server
|
||||
for debugging
|
||||
|
||||
## Workarounds:
|
||||
--encoding ENCODING Force the specified encoding (experimental)
|
||||
--no-check-certificate Suppress HTTPS certificate validation
|
||||
--prefer-insecure Use an unencrypted connection to retrieve
|
||||
information about the video. (Currently
|
||||
supported only for YouTube)
|
||||
--user-agent UA Specify a custom user agent
|
||||
--referer URL Specify a custom referer, use if the video
|
||||
access is restricted to one domain
|
||||
--add-header FIELD:VALUE Specify a custom HTTP header and its value,
|
||||
separated by a colon ':'. You can use this
|
||||
option multiple times
|
||||
--bidi-workaround Work around terminals that lack
|
||||
bidirectional text support. Requires bidiv
|
||||
or fribidi executable in PATH
|
||||
--sleep-interval SECONDS Number of seconds to sleep before each
|
||||
download when used alone or a lower bound
|
||||
of a range for randomized sleep before each
|
||||
download (minimum possible number of
|
||||
seconds to sleep) when used along with
|
||||
--max-sleep-interval.
|
||||
--max-sleep-interval SECONDS Upper bound of a range for randomized sleep
|
||||
before each download (maximum possible
|
||||
number of seconds to sleep). Must only be
|
||||
used along with --min-sleep-interval.
|
||||
--encoding ENCODING Force the specified encoding
|
||||
(experimental)
|
||||
--no-check-certificate Suppress HTTPS certificate validation
|
||||
--prefer-insecure Use an unencrypted connection to
|
||||
retrieve information about the video.
|
||||
(Currently supported only for YouTube)
|
||||
--user-agent UA Specify a custom user agent
|
||||
--referer URL Specify a custom referer, use if the
|
||||
video access is restricted to one
|
||||
domain
|
||||
--add-header FIELD:VALUE Specify a custom HTTP header and its
|
||||
value, separated by a colon ':'. You
|
||||
can use this option multiple times
|
||||
--bidi-workaround Work around terminals that lack
|
||||
bidirectional text support. Requires
|
||||
bidiv or fribidi executable in PATH
|
||||
--sleep-interval SECONDS Number of seconds to sleep before each
|
||||
download when used alone or a lower
|
||||
bound of a range for randomized sleep
|
||||
before each download (minimum possible
|
||||
number of seconds to sleep) when used
|
||||
along with --max-sleep-interval.
|
||||
--max-sleep-interval SECONDS Upper bound of a range for randomized
|
||||
sleep before each download (maximum
|
||||
possible number of seconds to sleep).
|
||||
Must only be used along with --min-
|
||||
sleep-interval.
|
||||
|
||||
## Video Format Options:
|
||||
-f, --format FORMAT Video format code, see the "FORMAT
|
||||
SELECTION" for all the info
|
||||
--all-formats Download all available video formats
|
||||
--prefer-free-formats Prefer free video formats unless a specific
|
||||
one is requested
|
||||
-F, --list-formats List all available formats of requested
|
||||
videos
|
||||
--youtube-skip-dash-manifest Do not download the DASH manifests and
|
||||
related data on YouTube videos
|
||||
--merge-output-format FORMAT 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
|
||||
-f, --format FORMAT Video format code, see the "FORMAT
|
||||
SELECTION" for all the info
|
||||
--all-formats Download all available video formats
|
||||
--prefer-free-formats Prefer free video formats unless a
|
||||
specific one is requested
|
||||
-F, --list-formats List all available formats of requested
|
||||
videos
|
||||
--youtube-skip-dash-manifest Do not download the DASH manifests and
|
||||
related data on YouTube videos
|
||||
--merge-output-format FORMAT 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
|
||||
|
||||
## Subtitle Options:
|
||||
--write-sub Write subtitle file
|
||||
--write-auto-sub Write automatically generated subtitle file
|
||||
(YouTube only)
|
||||
--all-subs Download all the available subtitles of the
|
||||
video
|
||||
--list-subs List all available subtitles for the video
|
||||
--sub-format FORMAT Subtitle format, accepts formats
|
||||
preference, for example: "srt" or
|
||||
"ass/srt/best"
|
||||
--sub-lang LANGS Languages of the subtitles to download
|
||||
(optional) separated by commas, use --list-
|
||||
subs for available language tags
|
||||
--write-sub Write subtitle file
|
||||
--write-auto-sub Write automatically generated subtitle
|
||||
file (YouTube only)
|
||||
--all-subs Download all the available subtitles of
|
||||
the video
|
||||
--list-subs List all available subtitles for the
|
||||
video
|
||||
--sub-format FORMAT Subtitle format, accepts formats
|
||||
preference, for example: "srt" or
|
||||
"ass/srt/best"
|
||||
--sub-lang LANGS Languages of the subtitles to download
|
||||
(optional) separated by commas, use
|
||||
--list-subs for available language tags
|
||||
|
||||
## Authentication Options:
|
||||
-u, --username USERNAME Login with this account ID
|
||||
-p, --password PASSWORD Account password. If this option is left
|
||||
out, youtube-dl will ask interactively.
|
||||
-2, --twofactor TWOFACTOR Two-factor authentication code
|
||||
-n, --netrc Use .netrc authentication data
|
||||
--video-password PASSWORD Video password (vimeo, youku)
|
||||
-u, --username USERNAME Login with this account ID
|
||||
-p, --password PASSWORD Account password. If this option is
|
||||
left out, youtube-dl will ask
|
||||
interactively.
|
||||
-2, --twofactor TWOFACTOR Two-factor authentication code
|
||||
-n, --netrc Use .netrc authentication data
|
||||
--video-password PASSWORD Video password (vimeo, youku)
|
||||
|
||||
## Adobe Pass Options:
|
||||
--ap-mso MSO Adobe Pass multiple-system operator (TV
|
||||
provider) identifier, use --ap-list-mso for
|
||||
a list of available MSOs
|
||||
--ap-username USERNAME Multiple-system operator account login
|
||||
--ap-password PASSWORD Multiple-system operator account password.
|
||||
If this option is left out, youtube-dl will
|
||||
ask interactively.
|
||||
--ap-list-mso List all supported multiple-system
|
||||
operators
|
||||
--ap-mso MSO Adobe Pass multiple-system operator (TV
|
||||
provider) identifier, use --ap-list-mso
|
||||
for a list of available MSOs
|
||||
--ap-username USERNAME Multiple-system operator account login
|
||||
--ap-password PASSWORD Multiple-system operator account
|
||||
password. If this option is left out,
|
||||
youtube-dl will ask interactively.
|
||||
--ap-list-mso List all supported multiple-system
|
||||
operators
|
||||
|
||||
## Post-processing Options:
|
||||
-x, --extract-audio Convert video files to audio-only files
|
||||
(requires ffmpeg or avconv and ffprobe or
|
||||
avprobe)
|
||||
--audio-format FORMAT Specify audio format: "best", "aac",
|
||||
"flac", "mp3", "m4a", "opus", "vorbis", or
|
||||
"wav"; "best" by default; No effect without
|
||||
-x
|
||||
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert
|
||||
a value between 0 (better) and 9 (worse)
|
||||
for VBR or a specific bitrate like 128K
|
||||
(default 5)
|
||||
--recode-video FORMAT Encode the video to another format if
|
||||
necessary (currently supported:
|
||||
mp4|flv|ogg|webm|mkv|avi)
|
||||
--postprocessor-args ARGS Give these arguments to the postprocessor
|
||||
-k, --keep-video Keep the video file on disk after the post-
|
||||
processing; the video is erased by default
|
||||
--no-post-overwrites Do not overwrite post-processed files; the
|
||||
post-processed files are overwritten by
|
||||
default
|
||||
--embed-subs Embed subtitles in the video (only for mp4,
|
||||
webm and mkv videos)
|
||||
--embed-thumbnail Embed thumbnail in the audio as cover art
|
||||
--add-metadata Write metadata to the video file
|
||||
--metadata-from-title FORMAT Parse additional metadata like song title /
|
||||
artist from the video title. The format
|
||||
syntax is the same as --output. Regular
|
||||
expression with named capture groups may
|
||||
also be used. The parsed parameters replace
|
||||
existing values. Example: --metadata-from-
|
||||
title "%(artist)s - %(title)s" matches a
|
||||
title like "Coldplay - Paradise". Example
|
||||
(regex): --metadata-from-title
|
||||
"(?P<artist>.+?) - (?P<title>.+)"
|
||||
--xattrs Write metadata to the video file's xattrs
|
||||
(using dublin core and xdg standards)
|
||||
--fixup POLICY Automatically correct known faults of the
|
||||
file. One of never (do nothing), warn (only
|
||||
emit a warning), detect_or_warn (the
|
||||
default; fix file if we can, warn
|
||||
otherwise)
|
||||
--prefer-avconv Prefer avconv over ffmpeg for running the
|
||||
postprocessors
|
||||
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
|
||||
postprocessors (default)
|
||||
--ffmpeg-location PATH Location of the ffmpeg/avconv binary;
|
||||
either the path to the binary or its
|
||||
containing directory.
|
||||
--exec CMD Execute a command on the file after
|
||||
downloading and post-processing, similar to
|
||||
find's -exec syntax. Example: --exec 'adb
|
||||
push {} /sdcard/Music/ && rm {}'
|
||||
--convert-subs FORMAT Convert the subtitles to other format
|
||||
(currently supported: srt|ass|vtt|lrc)
|
||||
-x, --extract-audio Convert video files to audio-only files
|
||||
(requires ffmpeg/avconv and
|
||||
ffprobe/avprobe)
|
||||
--audio-format FORMAT Specify audio format: "best", "aac",
|
||||
"flac", "mp3", "m4a", "opus", "vorbis",
|
||||
or "wav"; "best" by default; No effect
|
||||
without -x
|
||||
--audio-quality QUALITY Specify ffmpeg/avconv audio quality,
|
||||
insert a value between 0 (better) and 9
|
||||
(worse) for VBR or a specific bitrate
|
||||
like 128K (default 5)
|
||||
--recode-video FORMAT Encode the video to another format if
|
||||
necessary (currently supported:
|
||||
mp4|flv|ogg|webm|mkv|avi)
|
||||
--postprocessor-args ARGS Give these arguments to the
|
||||
postprocessor
|
||||
-k, --keep-video Keep the video file on disk after the
|
||||
post-processing; the video is erased by
|
||||
default
|
||||
--no-post-overwrites Do not overwrite post-processed files;
|
||||
the post-processed files are
|
||||
overwritten by default
|
||||
--embed-subs Embed subtitles in the video (only for
|
||||
mp4, webm and mkv videos)
|
||||
--embed-thumbnail Embed thumbnail in the audio as cover
|
||||
art
|
||||
--add-metadata Write metadata to the video file
|
||||
--metadata-from-title FORMAT Parse additional metadata like song
|
||||
title / artist from the video title.
|
||||
The format syntax is the same as
|
||||
--output. Regular expression with named
|
||||
capture groups may also be used. The
|
||||
parsed parameters replace existing
|
||||
values. Example: --metadata-from-title
|
||||
"%(artist)s - %(title)s" matches a
|
||||
title like "Coldplay - Paradise".
|
||||
Example (regex): --metadata-from-title
|
||||
"(?P<artist>.+?) - (?P<title>.+)"
|
||||
--xattrs Write metadata to the video file's
|
||||
xattrs (using dublin core and xdg
|
||||
standards)
|
||||
--fixup POLICY Automatically correct known faults of
|
||||
the file. One of never (do nothing),
|
||||
warn (only emit a warning),
|
||||
detect_or_warn (the default; fix file
|
||||
if we can, warn otherwise)
|
||||
--prefer-avconv Prefer avconv over ffmpeg for running
|
||||
the postprocessors
|
||||
--prefer-ffmpeg Prefer ffmpeg over avconv for running
|
||||
the postprocessors (default)
|
||||
--ffmpeg-location PATH Location of the ffmpeg/avconv binary;
|
||||
either the path to the binary or its
|
||||
containing directory.
|
||||
--exec CMD Execute a command on the file after
|
||||
downloading and post-processing,
|
||||
similar to find's -exec syntax.
|
||||
Example: --exec 'adb push {}
|
||||
/sdcard/Music/ && rm {}'
|
||||
--convert-subs FORMAT Convert the subtitles to other format
|
||||
(currently supported: srt|ass|vtt|lrc)
|
||||
|
||||
# CONFIGURATION
|
||||
|
||||
@@ -583,7 +620,7 @@ Available for the media that is a track or a part of a music album:
|
||||
- `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
|
||||
- `release_year` (numeric): Year (YYYY) when the album was released
|
||||
|
||||
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with `NA`.
|
||||
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
|
||||
|
||||
For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `youtube-dl test video` and id `BaW_jenozKcj`, this will result in a `youtube-dl test video-BaW_jenozKcj.mp4` file created in the current directory.
|
||||
|
||||
|
@@ -1,6 +1,5 @@
|
||||
# Supported sites
|
||||
- **1tv**: Первый канал
|
||||
- **1up.com**
|
||||
- **20min**
|
||||
- **220.ro**
|
||||
- **23video**
|
||||
@@ -46,10 +45,11 @@
|
||||
- **Amara**
|
||||
- **AMCNetworks**
|
||||
- **AmericasTestKitchen**
|
||||
- **AmericasTestKitchenSeason**
|
||||
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
|
||||
- **AnimeOnDemand**
|
||||
- **Anvato**
|
||||
- **aol.com**
|
||||
- **aol.com**: Yahoo screen and movies
|
||||
- **APA**
|
||||
- **Aparat**
|
||||
- **AppleConnect**
|
||||
@@ -82,6 +82,7 @@
|
||||
- **awaan:video**
|
||||
- **AZMedien**: AZ Medien videos
|
||||
- **BaiduVideo**: 百度视频
|
||||
- **bandaichannel**
|
||||
- **Bandcamp**
|
||||
- **Bandcamp:album**
|
||||
- **Bandcamp:weekly**
|
||||
@@ -192,8 +193,6 @@
|
||||
- **CNNArticle**
|
||||
- **CNNBlogs**
|
||||
- **ComedyCentral**
|
||||
- **ComedyCentralFullEpisodes**
|
||||
- **ComedyCentralShortname**
|
||||
- **ComedyCentralTV**
|
||||
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
|
||||
- **CONtv**
|
||||
@@ -214,6 +213,7 @@
|
||||
- **curiositystream**
|
||||
- **curiositystream:collection**
|
||||
- **CWTV**
|
||||
- **DagelijkseKost**: dagelijksekost.een.be
|
||||
- **DailyMail**
|
||||
- **dailymotion**
|
||||
- **dailymotion:playlist**
|
||||
@@ -235,6 +235,7 @@
|
||||
- **DiscoveryGo**
|
||||
- **DiscoveryGoPlaylist**
|
||||
- **DiscoveryNetworksDe**
|
||||
- **DiscoveryPlus**
|
||||
- **DiscoveryVR**
|
||||
- **Disney**
|
||||
- **dlive:stream**
|
||||
@@ -330,6 +331,7 @@
|
||||
- **Gaskrank**
|
||||
- **Gazeta**
|
||||
- **GDCVault**
|
||||
- **GediDigital**
|
||||
- **generic**: Generic downloader that works on some sites
|
||||
- **Gfycat**
|
||||
- **GiantBomb**
|
||||
@@ -355,6 +357,7 @@
|
||||
- **HentaiStigma**
|
||||
- **hetklokhuis**
|
||||
- **hgtv.com:show**
|
||||
- **HGTVDe**
|
||||
- **HiDive**
|
||||
- **HistoricFilms**
|
||||
- **history:player**
|
||||
@@ -377,6 +380,8 @@
|
||||
- **HungamaSong**
|
||||
- **Hypem**
|
||||
- **ign.com**
|
||||
- **IGNArticle**
|
||||
- **IGNVideo**
|
||||
- **IHeartRadio**
|
||||
- **iheartradio:podcast**
|
||||
- **imdb**: Internet Movie Database trailers
|
||||
@@ -506,6 +511,9 @@
|
||||
- **Mgoon**
|
||||
- **MGTV**: 芒果TV
|
||||
- **MiaoPai**
|
||||
- **minds**
|
||||
- **minds:channel**
|
||||
- **minds:group**
|
||||
- **MinistryGrid**
|
||||
- **Minoto**
|
||||
- **miomio.tv**
|
||||
@@ -535,6 +543,7 @@
|
||||
- **mtv:video**
|
||||
- **mtvjapan**
|
||||
- **mtvservices:embedded**
|
||||
- **MTVUutisetArticle**
|
||||
- **MuenchenTV**: münchen.tv
|
||||
- **mva**: Microsoft Virtual Academy videos
|
||||
- **mva:course**: Microsoft Virtual Academy courses
|
||||
@@ -673,7 +682,6 @@
|
||||
- **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**
|
||||
@@ -800,6 +808,7 @@
|
||||
- **safari:course**: safaribooksonline.com online courses
|
||||
- **SAKTV**
|
||||
- **SaltTV**
|
||||
- **SampleFocus**
|
||||
- **Sapo**: SAPO Vídeos
|
||||
- **savefrom.net**
|
||||
- **SBS**: sbs.com.au
|
||||
@@ -822,6 +831,9 @@
|
||||
- **ShahidShow**
|
||||
- **Shared**: shared.sx
|
||||
- **ShowRoomLive**
|
||||
- **simplecast**
|
||||
- **simplecast:episode**
|
||||
- **simplecast:podcast**
|
||||
- **Sina**
|
||||
- **sky.it**
|
||||
- **sky:news**
|
||||
@@ -859,6 +871,8 @@
|
||||
- **Sport5**
|
||||
- **SportBox**
|
||||
- **SportDeutschland**
|
||||
- **spotify**
|
||||
- **spotify:show**
|
||||
- **Spreaker**
|
||||
- **SpreakerPage**
|
||||
- **SpreakerShow**
|
||||
@@ -872,6 +886,9 @@
|
||||
- **Steam**
|
||||
- **Stitcher**
|
||||
- **StitcherShow**
|
||||
- **StoryFire**
|
||||
- **StoryFireSeries**
|
||||
- **StoryFireUser**
|
||||
- **Streamable**
|
||||
- **streamcloud.eu**
|
||||
- **StreamCZ**
|
||||
@@ -940,12 +957,13 @@
|
||||
- **TNAFlixNetworkEmbed**
|
||||
- **toggle**
|
||||
- **ToonGoggles**
|
||||
- **Tosh**: Tosh.0
|
||||
- **tou.tv**
|
||||
- **Toypics**: Toypics video
|
||||
- **ToypicsUser**: Toypics user profile
|
||||
- **TrailerAddict** (Currently broken)
|
||||
- **Trilulilu**
|
||||
- **Trovo**
|
||||
- **TrovoVod**
|
||||
- **TruNews**
|
||||
- **TruTV**
|
||||
- **Tube8**
|
||||
@@ -1053,7 +1071,6 @@
|
||||
- **vidme**
|
||||
- **vidme:user**
|
||||
- **vidme:user:likes**
|
||||
- **Vidzi**
|
||||
- **vier**: vier.be and vijf.be
|
||||
- **vier:videos**
|
||||
- **viewlift**
|
||||
@@ -1098,6 +1115,7 @@
|
||||
- **vrv**
|
||||
- **vrv:series**
|
||||
- **VShare**
|
||||
- **VTM**
|
||||
- **VTXTV**
|
||||
- **vube**: Vube.com
|
||||
- **VuClip**
|
||||
@@ -1192,5 +1210,6 @@
|
||||
- **ZattooLive**
|
||||
- **ZDF**
|
||||
- **ZDFChannel**
|
||||
- **Zhihu**
|
||||
- **zingmp3**: mp3.zing.vn
|
||||
- **Zype**
|
||||
|
@@ -633,13 +633,20 @@ class TestYoutubeDL(unittest.TestCase):
|
||||
'title2': '%PATH%',
|
||||
}
|
||||
|
||||
def fname(templ):
|
||||
ydl = YoutubeDL({'outtmpl': templ})
|
||||
def fname(templ, na_placeholder='NA'):
|
||||
params = {'outtmpl': templ}
|
||||
if na_placeholder != 'NA':
|
||||
params['outtmpl_na_placeholder'] = na_placeholder
|
||||
ydl = YoutubeDL(params)
|
||||
return ydl.prepare_filename(info)
|
||||
self.assertEqual(fname('%(id)s.%(ext)s'), '1234.mp4')
|
||||
self.assertEqual(fname('%(id)s-%(width)s.%(ext)s'), '1234-NA.mp4')
|
||||
# Replace missing fields with 'NA'
|
||||
self.assertEqual(fname('%(uploader_date)s-%(id)s.%(ext)s'), 'NA-1234.mp4')
|
||||
NA_TEST_OUTTMPL = '%(uploader_date)s-%(width)d-%(id)s.%(ext)s'
|
||||
# Replace missing fields with 'NA' by default
|
||||
self.assertEqual(fname(NA_TEST_OUTTMPL), 'NA-NA-1234.mp4')
|
||||
# Or by provided placeholder
|
||||
self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder='none'), 'none-none-1234.mp4')
|
||||
self.assertEqual(fname(NA_TEST_OUTTMPL, na_placeholder=''), '--1234.mp4')
|
||||
self.assertEqual(fname('%(height)d.%(ext)s'), '1080.mp4')
|
||||
self.assertEqual(fname('%(height)6d.%(ext)s'), ' 1080.mp4')
|
||||
self.assertEqual(fname('%(height)-6d.%(ext)s'), '1080 .mp4')
|
||||
|
@@ -1,275 +0,0 @@
|
||||
#!/usr/bin/env python
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
# Allow direct execution
|
||||
import os
|
||||
import sys
|
||||
import unittest
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
from test.helper import expect_value
|
||||
from youtube_dl.extractor import YoutubeIE
|
||||
|
||||
|
||||
class TestYoutubeChapters(unittest.TestCase):
|
||||
|
||||
_TEST_CASES = [
|
||||
(
|
||||
# https://www.youtube.com/watch?v=A22oy8dFjqc
|
||||
# pattern: 00:00 - <title>
|
||||
'''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
|
||||
1477,
|
||||
[{
|
||||
'start_time': 36,
|
||||
'end_time': 162,
|
||||
'title': 'Bohemian Rhapsody',
|
||||
}, {
|
||||
'start_time': 162,
|
||||
'end_time': 413,
|
||||
'title': 'Radio Ga Ga',
|
||||
}, {
|
||||
'start_time': 413,
|
||||
'end_time': 454,
|
||||
'title': 'Ay Oh!',
|
||||
}, {
|
||||
'start_time': 454,
|
||||
'end_time': 728,
|
||||
'title': 'Hammer To Fall',
|
||||
}, {
|
||||
'start_time': 728,
|
||||
'end_time': 963,
|
||||
'title': 'Crazy Little Thing Called Love',
|
||||
}, {
|
||||
'start_time': 963,
|
||||
'end_time': 1038,
|
||||
'title': 'We Will Rock You',
|
||||
}, {
|
||||
'start_time': 1038,
|
||||
'end_time': 1272,
|
||||
'title': 'We Are The Champions',
|
||||
}, {
|
||||
'start_time': 1272,
|
||||
'end_time': 1477,
|
||||
'title': 'Is This The World We Created...?',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=ekYlRhALiRQ
|
||||
# pattern: <num>. <title> 0:00
|
||||
'1. Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2. Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3. Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4. The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5. Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6. Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
|
||||
4009,
|
||||
[{
|
||||
'start_time': 0,
|
||||
'end_time': 707,
|
||||
'title': '1. Those Beaten Paths of Confusion',
|
||||
}, {
|
||||
'start_time': 707,
|
||||
'end_time': 1590,
|
||||
'title': '2. Beyond the Shadows of Emptiness & Nothingness',
|
||||
}, {
|
||||
'start_time': 1590,
|
||||
'end_time': 2157,
|
||||
'title': '3. Poison Yourself...With Thought',
|
||||
}, {
|
||||
'start_time': 2157,
|
||||
'end_time': 2672,
|
||||
'title': '4. The Agents of Transformation',
|
||||
}, {
|
||||
'start_time': 2672,
|
||||
'end_time': 3187,
|
||||
'title': '5. Drowning in the Pain of Consciousness',
|
||||
}, {
|
||||
'start_time': 3187,
|
||||
'end_time': 4009,
|
||||
'title': '6. Deny the Disease of Life',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=WjL4pSzog9w
|
||||
# pattern: 00:00 <title>
|
||||
'<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
|
||||
2705,
|
||||
[{
|
||||
'start_time': 0,
|
||||
'end_time': 428,
|
||||
'title': 'Christening Unborn Deformities',
|
||||
}, {
|
||||
'start_time': 428,
|
||||
'end_time': 976,
|
||||
'title': 'Taste of Purity',
|
||||
}, {
|
||||
'start_time': 976,
|
||||
'end_time': 1485,
|
||||
'title': 'Sculpting Sins of a Universal Tongue',
|
||||
}, {
|
||||
'start_time': 1485,
|
||||
'end_time': 1884,
|
||||
'title': 'Birth',
|
||||
}, {
|
||||
'start_time': 1884,
|
||||
'end_time': 2275,
|
||||
'title': 'Neves',
|
||||
}, {
|
||||
'start_time': 2275,
|
||||
'end_time': 2705,
|
||||
'title': 'Libations in Limbo',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=o3r1sn-t3is
|
||||
# pattern: <title> 00:00 <note>
|
||||
'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a> (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
|
||||
5640,
|
||||
[{
|
||||
'start_time': 45,
|
||||
'end_time': 266,
|
||||
'title': 'I-E-A-I-A-I-O',
|
||||
}, {
|
||||
'start_time': 266,
|
||||
'end_time': 331,
|
||||
'title': 'Suite-Pee (Incomplete)',
|
||||
}, {
|
||||
'start_time': 331,
|
||||
'end_time': 522,
|
||||
'title': 'Attack (First live performance since 2011)',
|
||||
}, {
|
||||
'start_time': 522,
|
||||
'end_time': 752,
|
||||
'title': 'Prison Song',
|
||||
}, {
|
||||
'start_time': 752,
|
||||
'end_time': 932,
|
||||
'title': 'Know (First live performance since 2011)',
|
||||
}, {
|
||||
'start_time': 932,
|
||||
'end_time': 1153,
|
||||
'title': 'Aerials',
|
||||
}, {
|
||||
'start_time': 1153,
|
||||
'end_time': 1209,
|
||||
'title': 'Soldier Side - Intro',
|
||||
}, {
|
||||
'start_time': 1209,
|
||||
'end_time': 1472,
|
||||
'title': 'B.Y.O.B.',
|
||||
}, {
|
||||
'start_time': 1472,
|
||||
'end_time': 1668,
|
||||
'title': 'Soil',
|
||||
}, {
|
||||
'start_time': 1668,
|
||||
'end_time': 1838,
|
||||
'title': 'Darts',
|
||||
}, {
|
||||
'start_time': 1838,
|
||||
'end_time': 2105,
|
||||
'title': 'Radio/Video',
|
||||
}, {
|
||||
'start_time': 2105,
|
||||
'end_time': 2288,
|
||||
'title': 'Hypnotize',
|
||||
}, {
|
||||
'start_time': 2288,
|
||||
'end_time': 2460,
|
||||
'title': 'Temper (First live performance since 1999)',
|
||||
}, {
|
||||
'start_time': 2460,
|
||||
'end_time': 2577,
|
||||
'title': 'CUBErt',
|
||||
}, {
|
||||
'start_time': 2577,
|
||||
'end_time': 2787,
|
||||
'title': 'Needles',
|
||||
}, {
|
||||
'start_time': 2787,
|
||||
'end_time': 2978,
|
||||
'title': 'Deer Dance',
|
||||
}, {
|
||||
'start_time': 2978,
|
||||
'end_time': 3085,
|
||||
'title': 'Bounce',
|
||||
}, {
|
||||
'start_time': 3085,
|
||||
'end_time': 3232,
|
||||
'title': 'Suggestions',
|
||||
}, {
|
||||
'start_time': 3232,
|
||||
'end_time': 3493,
|
||||
'title': 'Psycho',
|
||||
}, {
|
||||
'start_time': 3493,
|
||||
'end_time': 3675,
|
||||
'title': 'Chop Suey!',
|
||||
}, {
|
||||
'start_time': 3675,
|
||||
'end_time': 3854,
|
||||
'title': 'Lonely Day',
|
||||
}, {
|
||||
'start_time': 3854,
|
||||
'end_time': 4090,
|
||||
'title': 'Question!',
|
||||
}, {
|
||||
'start_time': 4090,
|
||||
'end_time': 4420,
|
||||
'title': 'Lost in Hollywood',
|
||||
}, {
|
||||
'start_time': 4420,
|
||||
'end_time': 4577,
|
||||
'title': 'Vicinity of Obscenity (First live performance since 2012)',
|
||||
}, {
|
||||
'start_time': 4577,
|
||||
'end_time': 4802,
|
||||
'title': 'Forest',
|
||||
}, {
|
||||
'start_time': 4802,
|
||||
'end_time': 5037,
|
||||
'title': 'Cigaro',
|
||||
}, {
|
||||
'start_time': 5037,
|
||||
'end_time': 5273,
|
||||
'title': 'Toxicity (with Chino Moreno)',
|
||||
}, {
|
||||
'start_time': 5273,
|
||||
'end_time': 5640,
|
||||
'title': 'Sugar',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=PkYLQbsqCE8
|
||||
# pattern: <num> - <title> [<latinized title>] 0:00:00
|
||||
'''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
|
||||
1138,
|
||||
[{
|
||||
'start_time': 0,
|
||||
'end_time': 490,
|
||||
'title': '1 - Во прах [Vo prakh]',
|
||||
}, {
|
||||
'start_time': 490,
|
||||
'end_time': 870,
|
||||
'title': '2 - Искупление [Iskupleniye]',
|
||||
}, {
|
||||
'start_time': 870,
|
||||
'end_time': 1138,
|
||||
'title': '3 - Из серпов луны...[Iz serpov luny]',
|
||||
}]
|
||||
),
|
||||
(
|
||||
# https://www.youtube.com/watch?v=xZW70zEasOk
|
||||
# time point more than duration
|
||||
'''● LCS Spring finals: Saturday and Sunday from <a href="#" onclick="yt.www.watch.player.seekTo(13*60+30);return false;">13:30</a> outside the venue! <br />● PAX East: Fri, Sat & Sun - more info in tomorrows video on the main channel!''',
|
||||
283,
|
||||
[]
|
||||
),
|
||||
]
|
||||
|
||||
def test_youtube_chapters(self):
|
||||
for description, duration, expected_chapters in self._TEST_CASES:
|
||||
ie = YoutubeIE()
|
||||
expect_value(
|
||||
self, ie._extract_chapters_from_description(description, duration),
|
||||
expected_chapters, None)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
@@ -12,6 +12,7 @@ from test.helper import FakeYDL
|
||||
|
||||
from youtube_dl.extractor import (
|
||||
YoutubePlaylistIE,
|
||||
YoutubeTabIE,
|
||||
YoutubeIE,
|
||||
)
|
||||
|
||||
@@ -57,14 +58,22 @@ class TestYoutubeLists(unittest.TestCase):
|
||||
entries = result['entries']
|
||||
self.assertEqual(len(entries), 100)
|
||||
|
||||
def test_youtube_flat_playlist_titles(self):
|
||||
def test_youtube_flat_playlist_extraction(self):
|
||||
dl = FakeYDL()
|
||||
dl.params['extract_flat'] = True
|
||||
ie = YoutubePlaylistIE(dl)
|
||||
result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
|
||||
ie = YoutubeTabIE(dl)
|
||||
result = ie.extract('https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc')
|
||||
self.assertIsPlaylist(result)
|
||||
for entry in result['entries']:
|
||||
self.assertTrue(entry.get('title'))
|
||||
entries = list(result['entries'])
|
||||
self.assertTrue(len(entries) == 1)
|
||||
video = entries[0]
|
||||
self.assertEqual(video['_type'], 'url_transparent')
|
||||
self.assertEqual(video['ie_key'], 'Youtube')
|
||||
self.assertEqual(video['id'], 'BaW_jenozKc')
|
||||
self.assertEqual(video['url'], 'BaW_jenozKc')
|
||||
self.assertEqual(video['title'], 'youtube-dl test video "\'/\\ä↭𝕐')
|
||||
self.assertEqual(video['duration'], 10)
|
||||
self.assertEqual(video['uploader'], 'Philipp Hagemeister')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
@@ -19,55 +19,46 @@ from youtube_dl.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'),
|
||||
@@ -86,13 +81,9 @@ class TestPlayerInfo(unittest.TestCase):
|
||||
('https://www.youtube.com/yts/jsbin/player-en_US-vflaxXRn1/base.js', 'vflaxXRn1'),
|
||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
|
||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
|
||||
('http://s.ytimg.com/yt/swfbin/watch_as3-vflrEm9Nq.swf', 'vflrEm9Nq'),
|
||||
('https://s.ytimg.com/yts/swfbin/player-vflenCdZL/watch_as3.swf', 'vflenCdZL'),
|
||||
)
|
||||
for player_url, expected_player_id in PLAYER_URLS:
|
||||
expected_player_type = player_url.split('.')[-1]
|
||||
player_type, player_id = YoutubeIE._extract_player_info(player_url)
|
||||
self.assertEqual(player_type, expected_player_type)
|
||||
player_id = YoutubeIE._extract_player_info(player_url)
|
||||
self.assertEqual(player_id, expected_player_id)
|
||||
|
||||
|
||||
@@ -104,13 +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):
|
||||
@@ -118,22 +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)
|
||||
|
||||
|
||||
|
@@ -163,6 +163,7 @@ class YoutubeDL(object):
|
||||
simulate: Do not download the video files.
|
||||
format: Video format code. See options.py for more information.
|
||||
outtmpl: Template for output names.
|
||||
outtmpl_na_placeholder: Placeholder for unavailable meta fields.
|
||||
restrictfilenames: Do not allow "&" and spaces in file names
|
||||
ignoreerrors: Do not stop on download errors.
|
||||
force_generic_extractor: Force downloader to use the generic extractor
|
||||
@@ -658,7 +659,7 @@ class YoutubeDL(object):
|
||||
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
|
||||
for k, v in template_dict.items()
|
||||
if v is not None and not isinstance(v, (list, tuple, dict)))
|
||||
template_dict = collections.defaultdict(lambda: 'NA', template_dict)
|
||||
template_dict = collections.defaultdict(lambda: self.params.get('outtmpl_na_placeholder', 'NA'), template_dict)
|
||||
|
||||
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
|
||||
|
||||
@@ -678,8 +679,8 @@ class YoutubeDL(object):
|
||||
|
||||
# Missing numeric fields used together with integer presentation types
|
||||
# in format specification will break the argument substitution since
|
||||
# string 'NA' is returned for missing fields. We will patch output
|
||||
# template for missing fields to meet string presentation type.
|
||||
# string NA placeholder is returned for missing fields. We will patch
|
||||
# output template for missing fields to meet string presentation type.
|
||||
for numeric_field in self._NUMERIC_FIELDS:
|
||||
if numeric_field not in template_dict:
|
||||
# As of [1] format syntax is:
|
||||
|
@@ -340,6 +340,7 @@ def _real_main(argv=None):
|
||||
'format': opts.format,
|
||||
'listformats': opts.listformats,
|
||||
'outtmpl': outtmpl,
|
||||
'outtmpl_na_placeholder': opts.outtmpl_na_placeholder,
|
||||
'autonumber_size': opts.autonumber_size,
|
||||
'autonumber_start': opts.autonumber_start,
|
||||
'restrictfilenames': opts.restrictfilenames,
|
||||
|
@@ -1,14 +1,15 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import calendar
|
||||
import re
|
||||
import time
|
||||
|
||||
from .amp import AMPIE
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class AbcNewsVideoIE(AMPIE):
|
||||
@@ -18,8 +19,8 @@ class AbcNewsVideoIE(AMPIE):
|
||||
(?:
|
||||
abcnews\.go\.com/
|
||||
(?:
|
||||
[^/]+/video/(?P<display_id>[0-9a-z-]+)-|
|
||||
video/embed\?.*?\bid=
|
||||
(?:[^/]+/)*video/(?P<display_id>[0-9a-z-]+)-|
|
||||
video/(?:embed|itemfeed)\?.*?\bid=
|
||||
)|
|
||||
fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
|
||||
)
|
||||
@@ -36,6 +37,8 @@ class AbcNewsVideoIE(AMPIE):
|
||||
'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
|
||||
'duration': 180,
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'timestamp': 1380454200,
|
||||
'upload_date': '20130929',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
@@ -47,6 +50,12 @@ class AbcNewsVideoIE(AMPIE):
|
||||
}, {
|
||||
'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://abcnews.go.com/video/itemfeed?id=46979033',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -67,28 +76,23 @@ class AbcNewsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
|
||||
# Youtube Embeds
|
||||
'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501',
|
||||
'info_dict': {
|
||||
'id': '10505354',
|
||||
'ext': 'flv',
|
||||
'display_id': 'dramatic-video-rare-death-job-america',
|
||||
'title': 'Occupational Hazards',
|
||||
'description': 'Nightline investigates the dangers that lurk at various jobs.',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'upload_date': '20100428',
|
||||
'timestamp': 1272412800,
|
||||
'id': '51286501',
|
||||
'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player",
|
||||
'description': 'Billingsley went from a child actor to Hollywood power player.',
|
||||
},
|
||||
'add_ie': ['AbcNewsVideo'],
|
||||
'playlist_count': 5,
|
||||
}, {
|
||||
'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
|
||||
'info_dict': {
|
||||
'id': '38897857',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
|
||||
'title': 'Justin Timberlake Drops Hints For Secret Single',
|
||||
'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
|
||||
'upload_date': '20160515',
|
||||
'timestamp': 1463329500,
|
||||
'upload_date': '20160505',
|
||||
'timestamp': 1462442280,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
@@ -100,49 +104,55 @@ class AbcNewsIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# inline.type == 'video'
|
||||
'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
display_id = mobj.group('display_id')
|
||||
video_id = mobj.group('id')
|
||||
story_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, story_id)
|
||||
story = self._parse_json(self._search_regex(
|
||||
r"window\['__abcnews__'\]\s*=\s*({.+?});",
|
||||
webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0]
|
||||
article_contents = story.get('articleContents') or {}
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_url = self._search_regex(
|
||||
r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
|
||||
full_video_url = compat_urlparse.urljoin(url, video_url)
|
||||
def entries():
|
||||
featured_video = story.get('featuredVideo') or {}
|
||||
feed = try_get(featured_video, lambda x: x['video']['feed'])
|
||||
if feed:
|
||||
yield {
|
||||
'_type': 'url',
|
||||
'id': featured_video.get('id'),
|
||||
'title': featured_video.get('name'),
|
||||
'url': feed,
|
||||
'thumbnail': featured_video.get('images'),
|
||||
'description': featured_video.get('description'),
|
||||
'timestamp': parse_iso8601(featured_video.get('uploadDate')),
|
||||
'duration': parse_duration(featured_video.get('duration')),
|
||||
'ie_key': AbcNewsVideoIE.ie_key(),
|
||||
}
|
||||
|
||||
youtube_url = YoutubeIE._extract_url(webpage)
|
||||
for inline in (article_contents.get('inlines') or []):
|
||||
inline_type = inline.get('type')
|
||||
if inline_type == 'iframe':
|
||||
iframe_url = try_get(inline, lambda x: x['attrs']['src'])
|
||||
if iframe_url:
|
||||
yield self.url_result(iframe_url)
|
||||
elif inline_type == 'video':
|
||||
video_id = inline.get('id')
|
||||
if video_id:
|
||||
yield {
|
||||
'_type': 'url',
|
||||
'id': video_id,
|
||||
'url': 'http://abcnews.go.com/video/embed?id=' + video_id,
|
||||
'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'),
|
||||
'description': inline.get('description'),
|
||||
'duration': parse_duration(inline.get('duration')),
|
||||
'ie_key': AbcNewsVideoIE.ie_key(),
|
||||
}
|
||||
|
||||
timestamp = None
|
||||
date_str = self._html_search_regex(
|
||||
r'<span[^>]+class="timestamp">([^<]+)</span>',
|
||||
webpage, 'timestamp', fatal=False)
|
||||
if date_str:
|
||||
tz_offset = 0
|
||||
if date_str.endswith(' ET'): # Eastern Time
|
||||
tz_offset = -5
|
||||
date_str = date_str[:-3]
|
||||
date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
|
||||
for date_format in date_formats:
|
||||
try:
|
||||
timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
|
||||
except ValueError:
|
||||
continue
|
||||
if timestamp is not None:
|
||||
timestamp -= tz_offset * 3600
|
||||
|
||||
entry = {
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': AbcNewsVideoIE.ie_key(),
|
||||
'url': full_video_url,
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'timestamp': timestamp,
|
||||
}
|
||||
|
||||
if youtube_url:
|
||||
entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())]
|
||||
return self.playlist_result(entries)
|
||||
|
||||
return entry
|
||||
return self.playlist_result(
|
||||
entries(), story_id, article_contents.get('headline'),
|
||||
article_contents.get('subHead'))
|
||||
|
@@ -26,6 +26,7 @@ from ..utils import (
|
||||
strip_or_none,
|
||||
try_get,
|
||||
unified_strdate,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
@@ -51,9 +52,12 @@ class ADNIE(InfoExtractor):
|
||||
}
|
||||
}
|
||||
|
||||
_NETRC_MACHINE = 'animedigitalnetwork'
|
||||
_BASE_URL = 'http://animedigitalnetwork.fr'
|
||||
_API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/'
|
||||
_PLAYER_BASE_URL = _API_BASE_URL + 'player/'
|
||||
_HEADERS = {}
|
||||
_LOGIN_ERR_MESSAGE = 'Unable to log in'
|
||||
_RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537)
|
||||
_POS_ALIGN_MAP = {
|
||||
'start': 1,
|
||||
@@ -129,19 +133,42 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
|
||||
}])
|
||||
return subtitles
|
||||
|
||||
def _real_initialize(self):
|
||||
username, password = self._get_login_info()
|
||||
if not username:
|
||||
return
|
||||
try:
|
||||
access_token = (self._download_json(
|
||||
self._API_BASE_URL + 'authentication/login', None,
|
||||
'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False,
|
||||
data=urlencode_postdata({
|
||||
'password': password,
|
||||
'rememberMe': False,
|
||||
'source': 'Web',
|
||||
'username': username,
|
||||
})) or {}).get('accessToken')
|
||||
if access_token:
|
||||
self._HEADERS = {'authorization': 'Bearer ' + access_token}
|
||||
except ExtractorError as e:
|
||||
message = None
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
|
||||
resp = self._parse_json(
|
||||
e.cause.read().decode(), None, fatal=False) or {}
|
||||
message = resp.get('message') or resp.get('code')
|
||||
self.report_warning(message or self._LOGIN_ERR_MESSAGE)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
|
||||
player = self._download_json(
|
||||
video_base_url + 'configuration', video_id,
|
||||
'Downloading player config JSON metadata')['player']
|
||||
'Downloading player config JSON metadata',
|
||||
headers=self._HEADERS)['player']
|
||||
options = player['options']
|
||||
|
||||
user = options['user']
|
||||
if not user.get('hasAccess'):
|
||||
raise ExtractorError(
|
||||
'This video is only available for paying users', expected=True)
|
||||
# self.raise_login_required() # FIXME: Login is not implemented
|
||||
self.raise_login_required()
|
||||
|
||||
token = self._download_json(
|
||||
user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'),
|
||||
@@ -188,8 +215,7 @@ Format: Marked,Start,End,Style,Name,MarginL,MarginR,MarginV,Effect,Text'''
|
||||
message = error.get('message')
|
||||
if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country':
|
||||
self.raise_geo_restricted(msg=message)
|
||||
else:
|
||||
raise ExtractorError(message)
|
||||
raise ExtractorError(message)
|
||||
else:
|
||||
raise ExtractorError('Giving up retrying')
|
||||
|
||||
|
@@ -252,7 +252,7 @@ class AENetworksShowIE(AENetworksListBaseIE):
|
||||
_TESTS = [{
|
||||
'url': 'http://www.history.com/shows/ancient-aliens',
|
||||
'info_dict': {
|
||||
'id': 'SH012427480000',
|
||||
'id': 'SERIES1574',
|
||||
'title': 'Ancient Aliens',
|
||||
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
|
||||
},
|
||||
|
@@ -1,6 +1,7 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
@@ -90,3 +91,69 @@ class AmericasTestKitchenIE(InfoExtractor):
|
||||
'series': try_get(episode, lambda x: x['show']['title']),
|
||||
'episode': episode.get('title'),
|
||||
}
|
||||
|
||||
|
||||
class AmericasTestKitchenSeasonIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<show>americastestkitchen|cookscountry)\.com/episodes/browse/season_(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
# ATK Season
|
||||
'url': 'https://www.americastestkitchen.com/episodes/browse/season_1',
|
||||
'info_dict': {
|
||||
'id': 'season_1',
|
||||
'title': 'Season 1',
|
||||
},
|
||||
'playlist_count': 13,
|
||||
}, {
|
||||
# Cooks Country Season
|
||||
'url': 'https://www.cookscountry.com/episodes/browse/season_12',
|
||||
'info_dict': {
|
||||
'id': 'season_12',
|
||||
'title': 'Season 12',
|
||||
},
|
||||
'playlist_count': 13,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
show_name, season_number = re.match(self._VALID_URL, url).groups()
|
||||
season_number = int(season_number)
|
||||
|
||||
slug = 'atk' if show_name == 'americastestkitchen' else 'cco'
|
||||
|
||||
season = 'Season %d' % season_number
|
||||
|
||||
season_search = self._download_json(
|
||||
'https://y1fnzxui30-dsn.algolia.net/1/indexes/everest_search_%s_season_desc_production' % slug,
|
||||
season, headers={
|
||||
'Origin': 'https://www.%s.com' % show_name,
|
||||
'X-Algolia-API-Key': '8d504d0099ed27c1b73708d22871d805',
|
||||
'X-Algolia-Application-Id': 'Y1FNZXUI30',
|
||||
}, query={
|
||||
'facetFilters': json.dumps([
|
||||
'search_season_list:' + season,
|
||||
'search_document_klass:episode',
|
||||
'search_show_slug:' + slug,
|
||||
]),
|
||||
'attributesToRetrieve': 'description,search_%s_episode_number,search_document_date,search_url,title' % slug,
|
||||
'attributesToHighlight': '',
|
||||
'hitsPerPage': 1000,
|
||||
})
|
||||
|
||||
def entries():
|
||||
for episode in (season_search.get('hits') or []):
|
||||
search_url = episode.get('search_url')
|
||||
if not search_url:
|
||||
continue
|
||||
yield {
|
||||
'_type': 'url',
|
||||
'url': 'https://www.%s.com%s' % (show_name, search_url),
|
||||
'id': try_get(episode, lambda e: e['objectID'].split('_')[-1]),
|
||||
'title': episode.get('title'),
|
||||
'description': episode.get('description'),
|
||||
'timestamp': unified_timestamp(episode.get('search_document_date')),
|
||||
'season_number': season_number,
|
||||
'episode_number': int_or_none(episode.get('search_%s_episode_number' % slug)),
|
||||
'ie_key': AmericasTestKitchenIE.ie_key(),
|
||||
}
|
||||
|
||||
return self.playlist_result(
|
||||
entries(), 'season_%d' % season_number, season)
|
||||
|
@@ -8,6 +8,7 @@ from ..utils import (
|
||||
int_or_none,
|
||||
mimetype2ext,
|
||||
parse_iso8601,
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
@@ -88,7 +89,7 @@ class AMPIE(InfoExtractor):
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
|
||||
timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
|
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .yahoo import YahooIE
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse,
|
||||
@@ -15,9 +15,9 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class AolIE(InfoExtractor):
|
||||
class AolIE(YahooIE):
|
||||
IE_NAME = 'aol.com'
|
||||
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>[0-9a-f]+)'
|
||||
_VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
|
||||
|
||||
_TESTS = [{
|
||||
# video with 5min ID
|
||||
@@ -76,10 +76,16 @@ class AolIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Yahoo video
|
||||
'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
if '-' in video_id:
|
||||
return self._extract_yahoo_video(video_id, 'us')
|
||||
|
||||
response = self._download_json(
|
||||
'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
|
||||
|
@@ -6,25 +6,21 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
js_to_json,
|
||||
int_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class APAIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
|
||||
_VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
|
||||
_TESTS = [{
|
||||
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
|
||||
'info_dict': {
|
||||
'id': 'jjv85FdZ',
|
||||
'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'ext': 'mp4',
|
||||
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
|
||||
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
|
||||
'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 254,
|
||||
'timestamp': 1519211149,
|
||||
'upload_date': '20180221',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
|
||||
@@ -46,9 +42,11 @@ class APAIE(InfoExtractor):
|
||||
webpage)]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, base_url = mobj.group('id', 'base_url')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
webpage = self._download_webpage(
|
||||
'%s/player/%s' % (base_url, video_id), video_id)
|
||||
|
||||
jwplatform_id = self._search_regex(
|
||||
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
|
||||
@@ -59,16 +57,18 @@ class APAIE(InfoExtractor):
|
||||
'jwplatform:' + jwplatform_id, ie='JWPlatform',
|
||||
video_id=video_id)
|
||||
|
||||
sources = self._parse_json(
|
||||
self._search_regex(
|
||||
r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
|
||||
video_id, transform_source=js_to_json)
|
||||
def extract(field, name=None):
|
||||
return self._search_regex(
|
||||
r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
|
||||
webpage, name or field, default=None, group='value')
|
||||
|
||||
title = extract('title') or video_id
|
||||
description = extract('description')
|
||||
thumbnail = extract('poster', 'thumbnail')
|
||||
|
||||
formats = []
|
||||
for source in sources:
|
||||
if not isinstance(source, dict):
|
||||
continue
|
||||
source_url = url_or_none(source.get('file'))
|
||||
for format_id in ('hls', 'progressive'):
|
||||
source_url = url_or_none(extract(format_id))
|
||||
if not source_url:
|
||||
continue
|
||||
ext = determine_ext(source_url)
|
||||
@@ -77,18 +77,19 @@ class APAIE(InfoExtractor):
|
||||
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
height = int_or_none(self._search_regex(
|
||||
r'(\d+)\.mp4', source_url, 'height', default=None))
|
||||
formats.append({
|
||||
'url': source_url,
|
||||
'format_id': format_id,
|
||||
'height': height,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._search_regex(
|
||||
r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
|
||||
'thumbnail', fatal=False, group='url')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'formats': formats,
|
||||
}
|
||||
|
@@ -2,15 +2,17 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
unified_strdate,
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
unified_strdate,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class ArchiveOrgIE(InfoExtractor):
|
||||
IE_NAME = 'archive.org'
|
||||
IE_DESC = 'archive.org videos'
|
||||
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
|
||||
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
'md5': '8af1d4cf447933ed3c7f4871162602db',
|
||||
@@ -19,8 +21,11 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'ext': 'ogg',
|
||||
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
|
||||
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
|
||||
'upload_date': '19681210',
|
||||
'uploader': 'SRI International'
|
||||
'creator': 'SRI International',
|
||||
'release_date': '19681210',
|
||||
'uploader': 'SRI International',
|
||||
'timestamp': 1268695290,
|
||||
'upload_date': '20100315',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://archive.org/details/Cops1922',
|
||||
@@ -29,22 +34,43 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'id': 'Cops1922',
|
||||
'ext': 'mp4',
|
||||
'title': 'Buster Keaton\'s "Cops" (1922)',
|
||||
'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
|
||||
'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
|
||||
'timestamp': 1387699629,
|
||||
'upload_date': '20131222',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://archive.org/details/MSNBCW_20131125_040000_To_Catch_a_Predator/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(
|
||||
'http://archive.org/embed/' + video_id, video_id)
|
||||
jwplayer_playlist = self._parse_json(self._search_regex(
|
||||
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
|
||||
webpage, 'jwplayer playlist'), video_id)
|
||||
info = self._parse_jwplayer_data(
|
||||
{'playlist': jwplayer_playlist}, video_id, base_url=url)
|
||||
|
||||
playlist = None
|
||||
play8 = self._search_regex(
|
||||
r'(<[^>]+\bclass=["\']js-play8-playlist[^>]+>)', webpage,
|
||||
'playlist', default=None)
|
||||
if play8:
|
||||
attrs = extract_attributes(play8)
|
||||
playlist = attrs.get('value')
|
||||
if not playlist:
|
||||
# Old jwplayer fallback
|
||||
playlist = self._search_regex(
|
||||
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
|
||||
webpage, 'jwplayer playlist', default='[]')
|
||||
jwplayer_playlist = self._parse_json(playlist, video_id, fatal=False)
|
||||
if jwplayer_playlist:
|
||||
info = self._parse_jwplayer_data(
|
||||
{'playlist': jwplayer_playlist}, video_id, base_url=url)
|
||||
else:
|
||||
# HTML5 media fallback
|
||||
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
|
||||
info['id'] = video_id
|
||||
|
||||
def get_optional(metadata, field):
|
||||
return metadata.get(field, [None])[0]
|
||||
@@ -58,8 +84,12 @@ class ArchiveOrgIE(InfoExtractor):
|
||||
'description': clean_html(get_optional(metadata, 'description')),
|
||||
})
|
||||
if info.get('_type') != 'playlist':
|
||||
creator = get_optional(metadata, 'creator')
|
||||
info.update({
|
||||
'uploader': get_optional(metadata, 'creator'),
|
||||
'upload_date': unified_strdate(get_optional(metadata, 'date')),
|
||||
'creator': creator,
|
||||
'release_date': unified_strdate(get_optional(metadata, 'date')),
|
||||
'uploader': get_optional(metadata, 'publisher') or creator,
|
||||
'timestamp': unified_timestamp(get_optional(metadata, 'publicdate')),
|
||||
'language': get_optional(metadata, 'language'),
|
||||
})
|
||||
return info
|
||||
|
@@ -284,20 +284,42 @@ class ARDIE(InfoExtractor):
|
||||
|
||||
formats = []
|
||||
for a in video_node.findall('.//asset'):
|
||||
file_name = xpath_text(a, './fileName', default=None)
|
||||
if not file_name:
|
||||
continue
|
||||
format_type = a.attrib.get('type')
|
||||
format_url = url_or_none(file_name)
|
||||
if format_url:
|
||||
ext = determine_ext(file_name)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, display_id, 'mp4', entry_protocol='m3u8_native',
|
||||
m3u8_id=format_type or 'hls', fatal=False))
|
||||
continue
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
update_url_query(format_url, {'hdcore': '3.7.0'}),
|
||||
display_id, f4m_id=format_type or 'hds', fatal=False))
|
||||
continue
|
||||
f = {
|
||||
'format_id': a.attrib['type'],
|
||||
'width': int_or_none(a.find('./frameWidth').text),
|
||||
'height': int_or_none(a.find('./frameHeight').text),
|
||||
'vbr': int_or_none(a.find('./bitrateVideo').text),
|
||||
'abr': int_or_none(a.find('./bitrateAudio').text),
|
||||
'vcodec': a.find('./codecVideo').text,
|
||||
'tbr': int_or_none(a.find('./totalBitrate').text),
|
||||
'format_id': format_type,
|
||||
'width': int_or_none(xpath_text(a, './frameWidth')),
|
||||
'height': int_or_none(xpath_text(a, './frameHeight')),
|
||||
'vbr': int_or_none(xpath_text(a, './bitrateVideo')),
|
||||
'abr': int_or_none(xpath_text(a, './bitrateAudio')),
|
||||
'vcodec': xpath_text(a, './codecVideo'),
|
||||
'tbr': int_or_none(xpath_text(a, './totalBitrate')),
|
||||
}
|
||||
if a.find('./serverPrefix').text:
|
||||
f['url'] = a.find('./serverPrefix').text
|
||||
f['playpath'] = a.find('./fileName').text
|
||||
server_prefix = xpath_text(a, './serverPrefix', default=None)
|
||||
if server_prefix:
|
||||
f.update({
|
||||
'url': server_prefix,
|
||||
'playpath': file_name,
|
||||
})
|
||||
else:
|
||||
f['url'] = a.find('./fileName').text
|
||||
if not format_url:
|
||||
continue
|
||||
f['url'] = format_url
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
@@ -48,6 +48,7 @@ class AWAANBaseIE(InfoExtractor):
|
||||
'duration': int_or_none(video_data.get('duration')),
|
||||
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
|
||||
'is_live': is_live,
|
||||
'uploader_id': video_data.get('user_id'),
|
||||
}
|
||||
|
||||
|
||||
@@ -107,6 +108,7 @@ class AWAANLiveIE(AWAANBaseIE):
|
||||
'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
|
||||
'upload_date': '20150107',
|
||||
'timestamp': 1420588800,
|
||||
'uploader_id': '71',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
|
@@ -47,7 +47,7 @@ class AZMedienIE(InfoExtractor):
|
||||
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
|
||||
'only_matching': True
|
||||
}]
|
||||
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
|
||||
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be'
|
||||
_PARTNER_ID = '1719221'
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
37
youtube_dl/extractor/bandaichannel.py
Normal file
37
youtube_dl/extractor/bandaichannel.py
Normal file
@@ -0,0 +1,37 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .brightcove import BrightcoveNewIE
|
||||
from ..utils import extract_attributes
|
||||
|
||||
|
||||
class BandaiChannelIE(BrightcoveNewIE):
|
||||
IE_NAME = 'bandaichannel'
|
||||
_VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.b-ch.com/titles/514/001',
|
||||
'md5': 'a0f2d787baa5729bed71108257f613a4',
|
||||
'info_dict': {
|
||||
'id': '6128044564001',
|
||||
'ext': 'mp4',
|
||||
'title': 'メタルファイターMIKU 第1話',
|
||||
'timestamp': 1580354056,
|
||||
'uploader_id': '5797077852001',
|
||||
'upload_date': '20200130',
|
||||
'duration': 1387.733,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
attrs = extract_attributes(self._search_regex(
|
||||
r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
|
||||
bc = self._download_json(
|
||||
'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
|
||||
video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
|
||||
return self._parse_brightcove_metadata(bc, bc['id'])
|
@@ -90,13 +90,19 @@ class BleacherReportCMSIE(AMPIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
|
||||
_TESTS = [{
|
||||
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
|
||||
'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
|
||||
'md5': '670b2d73f48549da032861130488c681',
|
||||
'info_dict': {
|
||||
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
|
||||
'ext': 'flv',
|
||||
'ext': 'mp4',
|
||||
'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
|
||||
'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
|
||||
'upload_date': '20150723',
|
||||
'timestamp': 1437679032,
|
||||
|
||||
},
|
||||
'expected_warnings': [
|
||||
'Unable to download f4m manifest'
|
||||
]
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
@@ -12,7 +12,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class BravoTVIE(AdobePassIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<req_id>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
|
||||
'md5': 'e34684cfea2a96cd2ee1ef3a60909de9',
|
||||
@@ -28,10 +28,13 @@ class BravoTVIE(AdobePassIE):
|
||||
}, {
|
||||
'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
site, display_id = re.match(self._VALID_URL, url).groups()
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
settings = self._parse_json(self._search_regex(
|
||||
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})</script>', webpage, 'drupal settings'),
|
||||
@@ -53,11 +56,14 @@ class BravoTVIE(AdobePassIE):
|
||||
tp_path = release_pid = tve['release_pid']
|
||||
if tve.get('entitlement') == 'auth':
|
||||
adobe_pass = settings.get('tve_adobe_auth', {})
|
||||
if site == 'bravotv':
|
||||
site = 'bravo'
|
||||
resource = self._get_mvpd_resource(
|
||||
adobe_pass.get('adobePassResourceId', 'bravo'),
|
||||
adobe_pass.get('adobePassResourceId') or site,
|
||||
tve['title'], release_pid, tve.get('rating'))
|
||||
query['auth'] = self._extract_mvpd_auth(
|
||||
url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
|
||||
url, release_pid,
|
||||
adobe_pass.get('adobePassRequestorId') or site, resource)
|
||||
else:
|
||||
shared_playlist = settings['ls_playlist']
|
||||
account_pid = shared_playlist['account_pid']
|
||||
|
@@ -7,19 +7,21 @@ from .common import InfoExtractor
|
||||
from .gigya import GigyaBaseIE
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
ExtractorError,
|
||||
strip_or_none,
|
||||
clean_html,
|
||||
extract_attributes,
|
||||
float_or_none,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
str_or_none,
|
||||
strip_or_none,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class CanvasIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza|dako)/assets/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||
'md5': '68993eda72ef62386a15ea2cf3c93107',
|
||||
@@ -332,3 +334,51 @@ class VrtNUIE(GigyaBaseIE):
|
||||
'display_id': display_id,
|
||||
'season_number': int_or_none(page.get('episode_season')),
|
||||
})
|
||||
|
||||
|
||||
class DagelijkseKostIE(InfoExtractor):
|
||||
IE_DESC = 'dagelijksekost.een.be'
|
||||
_VALID_URL = r'https?://dagelijksekost\.een\.be/gerechten/(?P<id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
'url': 'https://dagelijksekost.een.be/gerechten/hachis-parmentier-met-witloof',
|
||||
'md5': '30bfffc323009a3e5f689bef6efa2365',
|
||||
'info_dict': {
|
||||
'id': 'md-ast-27a4d1ff-7d7b-425e-b84f-a4d227f592fa',
|
||||
'display_id': 'hachis-parmentier-met-witloof',
|
||||
'ext': 'mp4',
|
||||
'title': 'Hachis parmentier met witloof',
|
||||
'description': 'md5:9960478392d87f63567b5b117688cdc5',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 283.02,
|
||||
},
|
||||
'expected_warnings': ['is not a supported codec'],
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
title = strip_or_none(get_element_by_class(
|
||||
'dish-metadata__title', webpage
|
||||
) or self._html_search_meta(
|
||||
'twitter:title', webpage))
|
||||
|
||||
description = clean_html(get_element_by_class(
|
||||
'dish-description', webpage)
|
||||
) or self._html_search_meta(
|
||||
('description', 'twitter:description', 'og:description'),
|
||||
webpage)
|
||||
|
||||
video_id = self._html_search_regex(
|
||||
r'data-url=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
|
||||
group='id')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'https://mediazone.vrt.be/api/v1/dako/assets/%s' % video_id,
|
||||
'ie_key': CanvasIE.ie_key(),
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
}
|
||||
|
@@ -1,15 +1,18 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import calendar
|
||||
import datetime
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
extract_timezone,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
parse_resolution,
|
||||
try_get,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
@@ -24,8 +27,9 @@ class CCMAIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'L\'espot de La Marató de TV3',
|
||||
'description': 'md5:f12987f320e2f6e988e9908e4fe97765',
|
||||
'timestamp': 1470918540,
|
||||
'upload_date': '20160811',
|
||||
'timestamp': 1478608140,
|
||||
'upload_date': '20161108',
|
||||
'age_limit': 0,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/',
|
||||
@@ -35,8 +39,24 @@ class CCMAIE(InfoExtractor):
|
||||
'ext': 'mp3',
|
||||
'title': 'El Consell de Savis analitza el derbi',
|
||||
'description': 'md5:e2a3648145f3241cb9c6b4b624033e53',
|
||||
'upload_date': '20171205',
|
||||
'timestamp': 1512507300,
|
||||
'upload_date': '20170512',
|
||||
'timestamp': 1494622500,
|
||||
'vcodec': 'none',
|
||||
'categories': ['Esports'],
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/',
|
||||
'md5': 'b43c3d3486f430f3032b5b160d80cbc3',
|
||||
'info_dict': {
|
||||
'id': '6031387',
|
||||
'ext': 'mp4',
|
||||
'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)',
|
||||
'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60',
|
||||
'timestamp': 1582577700,
|
||||
'upload_date': '20200224',
|
||||
'subtitles': 'mincount:4',
|
||||
'age_limit': 16,
|
||||
'series': 'Crims',
|
||||
}
|
||||
}]
|
||||
|
||||
@@ -72,17 +92,28 @@ class CCMAIE(InfoExtractor):
|
||||
|
||||
informacio = media['informacio']
|
||||
title = informacio['titol']
|
||||
durada = informacio.get('durada', {})
|
||||
durada = informacio.get('durada') or {}
|
||||
duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
|
||||
timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
|
||||
tematica = try_get(informacio, lambda x: x['tematica']['text'])
|
||||
|
||||
timestamp = None
|
||||
data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
|
||||
try:
|
||||
timezone, data_utc = extract_timezone(data_utc)
|
||||
timestamp = calendar.timegm((datetime.datetime.strptime(
|
||||
data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
|
||||
except TypeError:
|
||||
pass
|
||||
|
||||
subtitles = {}
|
||||
subtitols = media.get('subtitols', {})
|
||||
if subtitols:
|
||||
sub_url = subtitols.get('url')
|
||||
subtitols = media.get('subtitols') or []
|
||||
if isinstance(subtitols, dict):
|
||||
subtitols = [subtitols]
|
||||
for st in subtitols:
|
||||
sub_url = st.get('url')
|
||||
if sub_url:
|
||||
subtitles.setdefault(
|
||||
subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({
|
||||
st.get('iso') or st.get('text') or 'ca', []).append({
|
||||
'url': sub_url,
|
||||
})
|
||||
|
||||
@@ -97,6 +128,16 @@ class CCMAIE(InfoExtractor):
|
||||
'height': int_or_none(imatges.get('alcada')),
|
||||
}]
|
||||
|
||||
age_limit = None
|
||||
codi_etic = try_get(informacio, lambda x: x['codi_etic']['id'])
|
||||
if codi_etic:
|
||||
codi_etic_s = codi_etic.split('_')
|
||||
if len(codi_etic_s) == 2:
|
||||
if codi_etic_s[1] == 'TP':
|
||||
age_limit = 0
|
||||
else:
|
||||
age_limit = int_or_none(codi_etic_s[1])
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
@@ -106,4 +147,9 @@ class CCMAIE(InfoExtractor):
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
'age_limit': age_limit,
|
||||
'alt_title': informacio.get('titol_complet'),
|
||||
'episode_number': int_or_none(informacio.get('capitol')),
|
||||
'categories': [tematica] if tematica else None,
|
||||
'series': informacio.get('programa'),
|
||||
}
|
||||
|
@@ -95,8 +95,11 @@ 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(?: |\s+)Twoim kraju\s*<', webpage):
|
||||
self.raise_geo_restricted()
|
||||
|
||||
need_confirm_age = False
|
||||
if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
|
||||
if self._html_search_regex(r'(<form[^>]+action="[^"]*/a/validatebirth[^"]*")',
|
||||
webpage, 'birthday validate form', default=None):
|
||||
webpage = self._download_age_confirm_page(
|
||||
url, video_id, note='Confirming age')
|
||||
|
@@ -1,142 +1,51 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .mtv import MTVServicesInfoExtractor
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class ComedyCentralIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
|
||||
(video-clips|episodes|cc-studios|video-collections|shows(?=/[^/]+/(?!full-episodes)))
|
||||
/(?P<title>.*)'''
|
||||
_VALID_URL = r'https?://(?:www\.)?cc\.com/(?:episodes|video(?:-clips)?)/(?P<id>[0-9a-z]{6})'
|
||||
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
|
||||
'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
|
||||
'url': 'http://www.cc.com/video-clips/5ke9v2/the-daily-show-with-trevor-noah-doc-rivers-and-steve-ballmer---the-nba-player-strike',
|
||||
'md5': 'b8acb347177c680ff18a292aa2166f80',
|
||||
'info_dict': {
|
||||
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
|
||||
'id': '89ccc86e-1b02-4f83-b0c9-1d9592ecd025',
|
||||
'ext': 'mp4',
|
||||
'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
|
||||
'description': 'After a certain point, breastfeeding becomes c**kblocking.',
|
||||
'timestamp': 1376798400,
|
||||
'upload_date': '20130818',
|
||||
'title': 'The Daily Show with Trevor Noah|August 28, 2020|25|25149|Doc Rivers and Steve Ballmer - The NBA Player Strike',
|
||||
'description': 'md5:5334307c433892b85f4f5e5ac9ef7498',
|
||||
'timestamp': 1598670000,
|
||||
'upload_date': '20200829',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
|
||||
'url': 'http://www.cc.com/episodes/pnzzci/drawn-together--american-idol--parody-clip-show-season-3-ep-314',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
|
||||
(?:full-episodes|shows(?=/[^/]+/full-episodes))
|
||||
/(?P<id>[^?]+)'''
|
||||
_FEED_URL = 'http://comedycentral.com/feeds/mrss/'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
|
||||
'info_dict': {
|
||||
'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
|
||||
'title': 'November 28, 2016 - Ryan Speedo Green',
|
||||
},
|
||||
'playlist_count': 4,
|
||||
}, {
|
||||
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
mgid = self._extract_triforce_mgid(webpage, data_zone='t2_lc_promo1')
|
||||
videos_info = self._get_videos_info(mgid)
|
||||
return videos_info
|
||||
|
||||
|
||||
class ToshIE(MTVServicesInfoExtractor):
|
||||
IE_DESC = 'Tosh.0'
|
||||
_VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
|
||||
_FEED_URL = 'http://tosh.cc.com/feeds/mrss'
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
|
||||
'info_dict': {
|
||||
'description': 'Tosh asked fans to share their summer plans.',
|
||||
'title': 'Twitter Users Share Summer Plans',
|
||||
},
|
||||
'playlist': [{
|
||||
'md5': 'f269e88114c1805bb6d7653fecea9e06',
|
||||
'info_dict': {
|
||||
'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
|
||||
'ext': 'mp4',
|
||||
'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
|
||||
'description': 'Tosh asked fans to share their summer plans.',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
# It's really reported to be published on year 2077
|
||||
'upload_date': '20770610',
|
||||
'timestamp': 3390510600,
|
||||
'subtitles': {
|
||||
'en': 'mincount:3',
|
||||
},
|
||||
},
|
||||
}]
|
||||
}, {
|
||||
'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
|
||||
'url': 'https://www.cc.com/video/k3sdvm/the-daily-show-with-jon-stewart-exclusive-the-fourth-estate',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
|
||||
class ComedyCentralTVIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/folgen/(?P<id>[0-9a-z]{6})'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
|
||||
'url': 'https://www.comedycentral.tv/folgen/pxdpec/josh-investigates-klimawandel-staffel-1-ep-1',
|
||||
'info_dict': {
|
||||
'id': 'local_playlist-f99b626bdfe13568579a',
|
||||
'ext': 'flv',
|
||||
'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
|
||||
'id': '15907dc3-ec3c-11e8-a442-0e40cf2fc285',
|
||||
'ext': 'mp4',
|
||||
'title': 'Josh Investigates',
|
||||
'description': 'Steht uns das Ende der Welt bevor?',
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
mrss_url = self._search_regex(
|
||||
r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'mrss url', group='url')
|
||||
|
||||
return self._get_videos_info_from_url(mrss_url, video_id)
|
||||
|
||||
|
||||
class ComedyCentralShortnameIE(InfoExtractor):
|
||||
_VALID_URL = r'^:(?P<id>tds|thedailyshow|theopposition)$'
|
||||
_TESTS = [{
|
||||
'url': ':tds',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': ':thedailyshow',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': ':theopposition',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
shortcut_map = {
|
||||
'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
|
||||
'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
|
||||
'theopposition': 'http://www.cc.com/shows/the-opposition-with-jordan-klepper/full-episodes',
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'accountOverride': 'intl.mtvi.com',
|
||||
'arcEp': 'web.cc.tv',
|
||||
'ep': 'b9032c3a',
|
||||
'imageEp': 'web.cc.tv',
|
||||
'mgid': uri,
|
||||
}
|
||||
return self.url_result(shortcut_map[video_id])
|
||||
|
@@ -2064,7 +2064,7 @@ class InfoExtractor(object):
|
||||
})
|
||||
return entries
|
||||
|
||||
def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}):
|
||||
def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
|
||||
res = self._download_xml_handle(
|
||||
mpd_url, video_id,
|
||||
note=note or 'Downloading MPD manifest',
|
||||
@@ -2078,10 +2078,9 @@ class InfoExtractor(object):
|
||||
mpd_base_url = base_url(urlh.geturl())
|
||||
|
||||
return self._parse_mpd_formats(
|
||||
mpd_doc, mpd_id=mpd_id, mpd_base_url=mpd_base_url,
|
||||
formats_dict=formats_dict, mpd_url=mpd_url)
|
||||
mpd_doc, mpd_id, mpd_base_url, mpd_url)
|
||||
|
||||
def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}, mpd_url=None):
|
||||
def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', mpd_url=None):
|
||||
"""
|
||||
Parse formats from MPD manifest.
|
||||
References:
|
||||
@@ -2359,15 +2358,7 @@ class InfoExtractor(object):
|
||||
else:
|
||||
# Assuming direct URL to unfragmented media.
|
||||
f['url'] = base_url
|
||||
|
||||
# According to [1, 5.3.5.2, Table 7, page 35] @id of Representation
|
||||
# is not necessarily unique within a Period thus formats with
|
||||
# the same `format_id` are quite possible. There are numerous examples
|
||||
# of such manifests (see https://github.com/ytdl-org/youtube-dl/issues/15111,
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/13919)
|
||||
full_info = formats_dict.get(representation_id, {}).copy()
|
||||
full_info.update(f)
|
||||
formats.append(full_info)
|
||||
formats.append(f)
|
||||
else:
|
||||
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
|
||||
return formats
|
||||
|
@@ -1,6 +1,7 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
@@ -10,11 +11,13 @@ from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
strip_or_none,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class DPlayIE(InfoExtractor):
|
||||
_PATH_REGEX = r'/(?P<id>[^/]+/[^/?#]+)'
|
||||
_VALID_URL = r'''(?x)https?://
|
||||
(?P<domain>
|
||||
(?:www\.)?(?P<host>d
|
||||
@@ -24,7 +27,7 @@ class DPlayIE(InfoExtractor):
|
||||
)
|
||||
)|
|
||||
(?P<subdomain_country>es|it)\.dplay\.com
|
||||
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
|
||||
)/[^/]+''' + _PATH_REGEX
|
||||
|
||||
_TESTS = [{
|
||||
# non geo restricted, via secure api, unsigned download hls URL
|
||||
@@ -151,56 +154,79 @@ class DPlayIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _process_errors(self, e, geo_countries):
|
||||
info = self._parse_json(e.cause.read().decode('utf-8'), None)
|
||||
error = info['errors'][0]
|
||||
error_code = error.get('code')
|
||||
if error_code == 'access.denied.geoblocked':
|
||||
self.raise_geo_restricted(countries=geo_countries)
|
||||
elif error_code in ('access.denied.missingpackage', 'invalid.token'):
|
||||
raise ExtractorError(
|
||||
'This video is only available for registered users. You may want to use --cookies.', expected=True)
|
||||
raise ExtractorError(info['errors'][0]['detail'], expected=True)
|
||||
|
||||
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
|
||||
headers['Authorization'] = 'Bearer ' + self._download_json(
|
||||
disco_base + 'token', display_id, 'Downloading token',
|
||||
query={
|
||||
'realm': realm,
|
||||
})['data']['attributes']['token']
|
||||
|
||||
def _download_video_playback_info(self, disco_base, video_id, headers):
|
||||
streaming = self._download_json(
|
||||
disco_base + 'playback/videoPlaybackInfo/' + video_id,
|
||||
video_id, headers=headers)['data']['attributes']['streaming']
|
||||
streaming_list = []
|
||||
for format_id, format_dict in streaming.items():
|
||||
streaming_list.append({
|
||||
'type': format_id,
|
||||
'url': format_dict.get('url'),
|
||||
})
|
||||
return streaming_list
|
||||
|
||||
def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
|
||||
geo_countries = [country.upper()]
|
||||
self._initialize_geo_bypass({
|
||||
'countries': geo_countries,
|
||||
})
|
||||
disco_base = 'https://%s/' % disco_host
|
||||
token = self._download_json(
|
||||
disco_base + 'token', display_id, 'Downloading token',
|
||||
query={
|
||||
'realm': realm,
|
||||
})['data']['attributes']['token']
|
||||
headers = {
|
||||
'Referer': url,
|
||||
'Authorization': 'Bearer ' + token,
|
||||
}
|
||||
video = self._download_json(
|
||||
disco_base + 'content/videos/' + display_id, display_id,
|
||||
headers=headers, query={
|
||||
'fields[channel]': 'name',
|
||||
'fields[image]': 'height,src,width',
|
||||
'fields[show]': 'name',
|
||||
'fields[tag]': 'name',
|
||||
'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
|
||||
'include': 'images,primaryChannel,show,tags'
|
||||
})
|
||||
self._update_disco_api_headers(headers, disco_base, display_id, realm)
|
||||
try:
|
||||
video = self._download_json(
|
||||
disco_base + 'content/videos/' + display_id, display_id,
|
||||
headers=headers, query={
|
||||
'fields[channel]': 'name',
|
||||
'fields[image]': 'height,src,width',
|
||||
'fields[show]': 'name',
|
||||
'fields[tag]': 'name',
|
||||
'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
|
||||
'include': 'images,primaryChannel,show,tags'
|
||||
})
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
|
||||
self._process_errors(e, geo_countries)
|
||||
raise
|
||||
video_id = video['data']['id']
|
||||
info = video['data']['attributes']
|
||||
title = info['name'].strip()
|
||||
formats = []
|
||||
try:
|
||||
streaming = self._download_json(
|
||||
disco_base + 'playback/videoPlaybackInfo/' + video_id,
|
||||
display_id, headers=headers)['data']['attributes']['streaming']
|
||||
streaming = self._download_video_playback_info(
|
||||
disco_base, video_id, headers)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
|
||||
error = info['errors'][0]
|
||||
error_code = error.get('code')
|
||||
if error_code == 'access.denied.geoblocked':
|
||||
self.raise_geo_restricted(countries=geo_countries)
|
||||
elif error_code == 'access.denied.missingpackage':
|
||||
self.raise_login_required()
|
||||
raise ExtractorError(info['errors'][0]['detail'], expected=True)
|
||||
self._process_errors(e, geo_countries)
|
||||
raise
|
||||
for format_id, format_dict in streaming.items():
|
||||
for format_dict in streaming:
|
||||
if not isinstance(format_dict, dict):
|
||||
continue
|
||||
format_url = format_dict.get('url')
|
||||
if not format_url:
|
||||
continue
|
||||
format_id = format_dict.get('type')
|
||||
ext = determine_ext(format_url)
|
||||
if format_id == 'dash' or ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
@@ -248,7 +274,7 @@ class DPlayIE(InfoExtractor):
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': info.get('description'),
|
||||
'description': strip_or_none(info.get('description')),
|
||||
'duration': float_or_none(info.get('videoDuration'), 1000),
|
||||
'timestamp': unified_timestamp(info.get('publishStart')),
|
||||
'series': series,
|
||||
@@ -268,3 +294,76 @@ class DPlayIE(InfoExtractor):
|
||||
host = 'disco-api.' + domain if domain[0] == 'd' else 'eu2-prod.disco-api.com'
|
||||
return self._get_disco_api_info(
|
||||
url, display_id, host, 'dplay' + country, country)
|
||||
|
||||
|
||||
class DiscoveryPlusIE(DPlayIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/video' + DPlayIE._PATH_REGEX
|
||||
_TESTS = [{
|
||||
'url': 'https://www.discoveryplus.com/video/property-brothers-forever-home/food-and-family',
|
||||
'info_dict': {
|
||||
'id': '1140794',
|
||||
'display_id': 'property-brothers-forever-home/food-and-family',
|
||||
'ext': 'mp4',
|
||||
'title': 'Food and Family',
|
||||
'description': 'The brothers help a Richmond family expand their single-level home.',
|
||||
'duration': 2583.113,
|
||||
'timestamp': 1609304400,
|
||||
'upload_date': '20201230',
|
||||
'creator': 'HGTV',
|
||||
'series': 'Property Brothers: Forever Home',
|
||||
'season_number': 1,
|
||||
'episode_number': 1,
|
||||
},
|
||||
'skip': 'Available for Premium users',
|
||||
}]
|
||||
|
||||
def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
|
||||
headers['x-disco-client'] = 'WEB:UNKNOWN:dplus_us:15.0.0'
|
||||
|
||||
def _download_video_playback_info(self, disco_base, video_id, headers):
|
||||
return self._download_json(
|
||||
disco_base + 'playback/v3/videoPlaybackInfo',
|
||||
video_id, headers=headers, data=json.dumps({
|
||||
'deviceInfo': {
|
||||
'adBlocker': False,
|
||||
},
|
||||
'videoId': video_id,
|
||||
'wisteriaProperties': {
|
||||
'platform': 'desktop',
|
||||
'product': 'dplus_us',
|
||||
},
|
||||
}).encode('utf-8'))['data']['attributes']['streaming']
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
return self._get_disco_api_info(
|
||||
url, display_id, 'us1-prod-direct.discoveryplus.com', 'go', 'us')
|
||||
|
||||
|
||||
class HGTVDeIE(DPlayIE):
|
||||
_VALID_URL = r'https?://de\.hgtv\.com/sendungen' + DPlayIE._PATH_REGEX
|
||||
_TESTS = [{
|
||||
'url': 'https://de.hgtv.com/sendungen/tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette/',
|
||||
'info_dict': {
|
||||
'id': '151205',
|
||||
'display_id': 'tiny-house-klein-aber-oho/wer-braucht-schon-eine-toilette',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wer braucht schon eine Toilette',
|
||||
'description': 'md5:05b40a27e7aed2c9172de34d459134e2',
|
||||
'duration': 1177.024,
|
||||
'timestamp': 1595705400,
|
||||
'upload_date': '20200725',
|
||||
'creator': 'HGTV',
|
||||
'series': 'Tiny House - klein, aber oho',
|
||||
'season_number': 3,
|
||||
'episode_number': 3,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
return self._get_disco_api_info(
|
||||
url, display_id, 'eu1-prod.disco-api.com', 'hgtv', 'de')
|
||||
|
@@ -1,193 +1,43 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_strdate,
|
||||
xpath_text,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
ExtractorError,
|
||||
)
|
||||
from .zdf import ZDFIE
|
||||
|
||||
|
||||
class DreiSatIE(InfoExtractor):
|
||||
class DreiSatIE(ZDFIE):
|
||||
IE_NAME = '3sat'
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
_VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
|
||||
'md5': 'be37228896d30a88f315b638900a026e',
|
||||
'info_dict': {
|
||||
'id': '45918',
|
||||
'ext': 'mp4',
|
||||
'title': 'Waidmannsheil',
|
||||
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
|
||||
'uploader': 'SCHWEIZWEIT',
|
||||
'uploader_id': '100000210',
|
||||
'upload_date': '20140913'
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # m3u8 downloads
|
||||
}
|
||||
_VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
|
||||
_TESTS = [{
|
||||
# Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
|
||||
'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
|
||||
'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
|
||||
'info_dict': {
|
||||
'id': '141007_ab18_10wochensommer_film',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ab 18! - 10 Wochen Sommer',
|
||||
'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
|
||||
'duration': 2660,
|
||||
'timestamp': 1608604200,
|
||||
'upload_date': '20201222',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
|
||||
'info_dict': {
|
||||
'id': '140913_sendung_schweizweit',
|
||||
'ext': 'mp4',
|
||||
'title': 'Waidmannsheil',
|
||||
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
|
||||
'timestamp': 1410623100,
|
||||
'upload_date': '20140913'
|
||||
},
|
||||
]
|
||||
|
||||
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
|
||||
param_groups = {}
|
||||
for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
|
||||
group_id = param_group.get(self._xpath_ns(
|
||||
'id', 'http://www.w3.org/XML/1998/namespace'))
|
||||
params = {}
|
||||
for param in param_group:
|
||||
params[param.get('name')] = param.get('value')
|
||||
param_groups[group_id] = params
|
||||
|
||||
formats = []
|
||||
for video in smil.findall(self._xpath_ns('.//video', namespace)):
|
||||
src = video.get('src')
|
||||
if not src:
|
||||
continue
|
||||
bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
|
||||
group_id = video.get('paramGroup')
|
||||
param_group = param_groups[group_id]
|
||||
for proto in param_group['protocols'].split(','):
|
||||
formats.append({
|
||||
'url': '%s://%s' % (proto, param_group['host']),
|
||||
'app': param_group['app'],
|
||||
'play_path': src,
|
||||
'ext': 'flv',
|
||||
'format_id': '%s-%d' % (proto, bitrate),
|
||||
'tbr': bitrate,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
return formats
|
||||
|
||||
def extract_from_xml_url(self, video_id, xml_url):
|
||||
doc = self._download_xml(
|
||||
xml_url, video_id,
|
||||
note='Downloading video info',
|
||||
errnote='Failed to download video info')
|
||||
|
||||
status_code = xpath_text(doc, './status/statuscode')
|
||||
if status_code and status_code != 'ok':
|
||||
if status_code == 'notVisibleAnymore':
|
||||
message = 'Video %s is not available' % video_id
|
||||
else:
|
||||
message = '%s returned error: %s' % (self.IE_NAME, status_code)
|
||||
raise ExtractorError(message, expected=True)
|
||||
|
||||
title = xpath_text(doc, './/information/title', 'title', True)
|
||||
|
||||
urls = []
|
||||
formats = []
|
||||
for fnode in doc.findall('.//formitaeten/formitaet'):
|
||||
video_url = xpath_text(fnode, 'url')
|
||||
if not video_url or video_url in urls:
|
||||
continue
|
||||
urls.append(video_url)
|
||||
|
||||
is_available = 'http://www.metafilegenerator' not in video_url
|
||||
geoloced = 'static_geoloced_online' in video_url
|
||||
if not is_available or geoloced:
|
||||
continue
|
||||
|
||||
format_id = fnode.attrib['basetype']
|
||||
format_m = re.match(r'''(?x)
|
||||
(?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
|
||||
(?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
|
||||
''', format_id)
|
||||
|
||||
ext = determine_ext(video_url, None) or format_m.group('container')
|
||||
|
||||
if ext == 'meta':
|
||||
continue
|
||||
elif ext == 'smil':
|
||||
formats.extend(self._extract_smil_formats(
|
||||
video_url, video_id, fatal=False))
|
||||
elif ext == 'm3u8':
|
||||
# the certificates are misconfigured (see
|
||||
# https://github.com/ytdl-org/youtube-dl/issues/8665)
|
||||
if video_url.startswith('https://'):
|
||||
continue
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
elif ext == 'f4m':
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
video_url, video_id, f4m_id=format_id, fatal=False))
|
||||
else:
|
||||
quality = xpath_text(fnode, './quality')
|
||||
if quality:
|
||||
format_id += '-' + quality
|
||||
|
||||
abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
|
||||
vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
|
||||
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'_(\d+)k', video_url, 'bitrate', None))
|
||||
if tbr and vbr and not abr:
|
||||
abr = tbr - vbr
|
||||
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': video_url,
|
||||
'ext': ext,
|
||||
'acodec': format_m.group('acodec'),
|
||||
'vcodec': format_m.group('vcodec'),
|
||||
'abr': abr,
|
||||
'vbr': vbr,
|
||||
'tbr': tbr,
|
||||
'width': int_or_none(xpath_text(fnode, './width')),
|
||||
'height': int_or_none(xpath_text(fnode, './height')),
|
||||
'filesize': int_or_none(xpath_text(fnode, './filesize')),
|
||||
'protocol': format_m.group('proto').lower(),
|
||||
})
|
||||
|
||||
geolocation = xpath_text(doc, './/details/geolocation')
|
||||
if not formats and geolocation and geolocation != 'none':
|
||||
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnails = []
|
||||
for node in doc.findall('.//teaserimages/teaserimage'):
|
||||
thumbnail_url = node.text
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
thumbnail_key = node.get('key')
|
||||
if thumbnail_key:
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': xpath_text(doc, './/information/detail'),
|
||||
'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
|
||||
'thumbnails': thumbnails,
|
||||
'uploader': xpath_text(doc, './/details/originChannelTitle'),
|
||||
'uploader_id': xpath_text(doc, './/details/originChannelId'),
|
||||
'upload_date': upload_date,
|
||||
'formats': formats,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
|
||||
return self.extract_from_xml_url(video_id, details_url)
|
||||
}, {
|
||||
# Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
|
||||
'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
|
||||
'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
@@ -12,7 +12,14 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class EggheadCourseIE(InfoExtractor):
|
||||
class EggheadBaseIE(InfoExtractor):
|
||||
def _call_api(self, path, video_id, resource, fatal=True):
|
||||
return self._download_json(
|
||||
'https://app.egghead.io/api/v1/' + path,
|
||||
video_id, 'Downloading %s JSON' % resource, fatal=fatal)
|
||||
|
||||
|
||||
class EggheadCourseIE(EggheadBaseIE):
|
||||
IE_DESC = 'egghead.io course'
|
||||
IE_NAME = 'egghead:course'
|
||||
_VALID_URL = r'https://egghead\.io/courses/(?P<id>[^/?#&]+)'
|
||||
@@ -28,10 +35,9 @@ class EggheadCourseIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
playlist_id = self._match_id(url)
|
||||
|
||||
lessons = self._download_json(
|
||||
'https://egghead.io/api/v1/series/%s/lessons' % playlist_id,
|
||||
playlist_id, 'Downloading course lessons JSON')
|
||||
series_path = 'series/' + playlist_id
|
||||
lessons = self._call_api(
|
||||
series_path + '/lessons', playlist_id, 'course lessons')
|
||||
|
||||
entries = []
|
||||
for lesson in lessons:
|
||||
@@ -44,9 +50,8 @@ class EggheadCourseIE(InfoExtractor):
|
||||
entries.append(self.url_result(
|
||||
lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
|
||||
|
||||
course = self._download_json(
|
||||
'https://egghead.io/api/v1/series/%s' % playlist_id,
|
||||
playlist_id, 'Downloading course JSON', fatal=False) or {}
|
||||
course = self._call_api(
|
||||
series_path, playlist_id, 'course', False) or {}
|
||||
|
||||
playlist_id = course.get('id')
|
||||
if playlist_id:
|
||||
@@ -57,7 +62,7 @@ class EggheadCourseIE(InfoExtractor):
|
||||
course.get('description'))
|
||||
|
||||
|
||||
class EggheadLessonIE(InfoExtractor):
|
||||
class EggheadLessonIE(EggheadBaseIE):
|
||||
IE_DESC = 'egghead.io lesson'
|
||||
IE_NAME = 'egghead:lesson'
|
||||
_VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
|
||||
@@ -74,7 +79,7 @@ class EggheadLessonIE(InfoExtractor):
|
||||
'upload_date': '20161209',
|
||||
'duration': 304,
|
||||
'view_count': 0,
|
||||
'tags': ['javascript', 'free'],
|
||||
'tags': 'count:2',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
@@ -88,8 +93,8 @@ class EggheadLessonIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
|
||||
lesson = self._download_json(
|
||||
'https://egghead.io/api/v1/lessons/%s' % display_id, display_id)
|
||||
lesson = self._call_api(
|
||||
'lessons/' + display_id, display_id, 'lesson')
|
||||
|
||||
lesson_id = compat_str(lesson['id'])
|
||||
title = lesson['title']
|
||||
|
@@ -42,7 +42,10 @@ from .aljazeera import AlJazeeraIE
|
||||
from .alphaporno import AlphaPornoIE
|
||||
from .amara import AmaraIE
|
||||
from .amcnetworks import AMCNetworksIE
|
||||
from .americastestkitchen import AmericasTestKitchenIE
|
||||
from .americastestkitchen import (
|
||||
AmericasTestKitchenIE,
|
||||
AmericasTestKitchenSeasonIE,
|
||||
)
|
||||
from .animeondemand import AnimeOnDemandIE
|
||||
from .anvato import AnvatoIE
|
||||
from .aol import AolIE
|
||||
@@ -87,6 +90,7 @@ from .awaan import (
|
||||
)
|
||||
from .azmedien import AZMedienIE
|
||||
from .baidu import BaiduVideoIE
|
||||
from .bandaichannel import BandaiChannelIE
|
||||
from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
|
||||
from .bbc import (
|
||||
BBCCoUkIE,
|
||||
@@ -160,6 +164,7 @@ from .canvas import (
|
||||
CanvasIE,
|
||||
CanvasEenIE,
|
||||
VrtNUIE,
|
||||
DagelijkseKostIE,
|
||||
)
|
||||
from .carambatv import (
|
||||
CarambaTVIE,
|
||||
@@ -232,11 +237,8 @@ from .cnn import (
|
||||
)
|
||||
from .coub import CoubIE
|
||||
from .comedycentral import (
|
||||
ComedyCentralFullEpisodesIE,
|
||||
ComedyCentralIE,
|
||||
ComedyCentralShortnameIE,
|
||||
ComedyCentralTVIE,
|
||||
ToshIE,
|
||||
)
|
||||
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
|
||||
from .commonprotocols import (
|
||||
@@ -287,7 +289,11 @@ from .douyutv import (
|
||||
DouyuShowIE,
|
||||
DouyuTVIE,
|
||||
)
|
||||
from .dplay import DPlayIE
|
||||
from .dplay import (
|
||||
DPlayIE,
|
||||
DiscoveryPlusIE,
|
||||
HGTVDeIE,
|
||||
)
|
||||
from .dreisat import DreiSatIE
|
||||
from .drbonanza import DRBonanzaIE
|
||||
from .drtuber import DrTuberIE
|
||||
@@ -416,6 +422,7 @@ from .gamestar import GameStarIE
|
||||
from .gaskrank import GaskrankIE
|
||||
from .gazeta import GazetaIE
|
||||
from .gdcvault import GDCVaultIE
|
||||
from .gedidigital import GediDigitalIE
|
||||
from .generic import GenericIE
|
||||
from .gfycat import GfycatIE
|
||||
from .giantbomb import GiantBombIE
|
||||
@@ -470,8 +477,8 @@ from .hungama import (
|
||||
from .hypem import HypemIE
|
||||
from .ign import (
|
||||
IGNIE,
|
||||
OneUPIE,
|
||||
PCMagIE,
|
||||
IGNVideoIE,
|
||||
IGNArticleIE,
|
||||
)
|
||||
from .iheart import (
|
||||
IHeartRadioIE,
|
||||
@@ -1024,6 +1031,7 @@ from .safari import (
|
||||
SafariApiIE,
|
||||
SafariCourseIE,
|
||||
)
|
||||
from .samplefocus import SampleFocusIE
|
||||
from .sapo import SapoIE
|
||||
from .savefrom import SaveFromIE
|
||||
from .sbs import SBSIE
|
||||
@@ -1056,6 +1064,11 @@ from .shared import (
|
||||
VivoIE,
|
||||
)
|
||||
from .showroomlive import ShowRoomLiveIE
|
||||
from .simplecast import (
|
||||
SimplecastIE,
|
||||
SimplecastEpisodeIE,
|
||||
SimplecastPodcastIE,
|
||||
)
|
||||
from .sina import SinaIE
|
||||
from .sixplay import SixPlayIE
|
||||
from .skyit import (
|
||||
@@ -1140,6 +1153,11 @@ from .srgssr import (
|
||||
from .srmediathek import SRMediathekIE
|
||||
from .stanfordoc import StanfordOpenClassroomIE
|
||||
from .steam import SteamIE
|
||||
from .storyfire import (
|
||||
StoryFireIE,
|
||||
StoryFireUserIE,
|
||||
StoryFireSeriesIE,
|
||||
)
|
||||
from .streamable import StreamableIE
|
||||
from .streamcloud import StreamcloudIE
|
||||
from .streamcz import StreamCZIE
|
||||
@@ -1238,6 +1256,10 @@ from .toutv import TouTvIE
|
||||
from .toypics import ToypicsUserIE, ToypicsIE
|
||||
from .traileraddict import TrailerAddictIE
|
||||
from .trilulilu import TriluliluIE
|
||||
from .trovo import (
|
||||
TrovoIE,
|
||||
TrovoVodIE,
|
||||
)
|
||||
from .trunews import TruNewsIE
|
||||
from .trutv import TruTVIE
|
||||
from .tube8 import Tube8IE
|
||||
@@ -1256,6 +1278,7 @@ from .tv2 import (
|
||||
TV2IE,
|
||||
TV2ArticleIE,
|
||||
KatsomoIE,
|
||||
MTVUutisetArticleIE,
|
||||
)
|
||||
from .tv2dk import (
|
||||
TV2DKIE,
|
||||
@@ -1394,7 +1417,6 @@ from .vidme import (
|
||||
VidmeUserIE,
|
||||
VidmeUserLikesIE,
|
||||
)
|
||||
from .vidzi import VidziIE
|
||||
from .vier import VierIE, VierVideosIE
|
||||
from .viewlift import (
|
||||
ViewLiftIE,
|
||||
@@ -1454,6 +1476,7 @@ from .vrv import (
|
||||
VRVSeriesIE,
|
||||
)
|
||||
from .vshare import VShareIE
|
||||
from .vtm import VTMIE
|
||||
from .medialaan import MedialaanIE
|
||||
from .vube import VubeIE
|
||||
from .vuclip import VuClipIE
|
||||
@@ -1597,5 +1620,6 @@ from .zattoo import (
|
||||
ZattooLiveIE,
|
||||
)
|
||||
from .zdf import ZDFIE, ZDFChannelIE
|
||||
from .zhihu import ZhihuIE
|
||||
from .zingmp3 import ZingMp3IE
|
||||
from .zype import ZypeIE
|
||||
|
@@ -11,7 +11,7 @@ from ..utils import (
|
||||
|
||||
class FranceCultureIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
|
||||
'info_dict': {
|
||||
'id': 'rendez-vous-au-pays-des-geeks',
|
||||
@@ -20,10 +20,14 @@ class FranceCultureIE(InfoExtractor):
|
||||
'title': 'Rendez-vous au pays des geeks',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'upload_date': '20140301',
|
||||
'timestamp': 1393642916,
|
||||
'timestamp': 1393700400,
|
||||
'vcodec': 'none',
|
||||
}
|
||||
}
|
||||
}, {
|
||||
# no thumbnail
|
||||
'url': 'https://www.franceculture.fr/emissions/la-recherche-montre-en-main/la-recherche-montre-en-main-du-mercredi-10-octobre-2018',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
@@ -36,19 +40,19 @@ class FranceCultureIE(InfoExtractor):
|
||||
</h1>|
|
||||
<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
|
||||
).*?
|
||||
(<button[^>]+data-asset-source="[^"]+"[^>]+>)
|
||||
(<button[^>]+data-(?:url|asset-source)="[^"]+"[^>]+>)
|
||||
''',
|
||||
webpage, 'video data'))
|
||||
|
||||
video_url = video_data['data-asset-source']
|
||||
title = video_data.get('data-asset-title') or self._og_search_title(webpage)
|
||||
video_url = video_data.get('data-url') or video_data['data-asset-source']
|
||||
title = video_data.get('data-asset-title') or video_data.get('data-diffusion-title') or self._og_search_title(webpage)
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
|
||||
webpage, 'description', default=None)
|
||||
thumbnail = self._search_regex(
|
||||
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
|
||||
webpage, 'thumbnail', fatal=False)
|
||||
webpage, 'thumbnail', default=None)
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<span class="author">(.*?)</span>',
|
||||
webpage, 'uploader', default=None)
|
||||
@@ -64,6 +68,6 @@ class FranceCultureIE(InfoExtractor):
|
||||
'ext': ext,
|
||||
'vcodec': 'none' if ext == 'mp3' else None,
|
||||
'uploader': uploader,
|
||||
'timestamp': int_or_none(video_data.get('data-asset-created-date')),
|
||||
'timestamp': int_or_none(video_data.get('data-start-time')) or int_or_none(video_data.get('data-asset-created-date')),
|
||||
'duration': int_or_none(video_data.get('data-duration')),
|
||||
}
|
||||
|
161
youtube_dl/extractor/gedidigital.py
Normal file
161
youtube_dl/extractor/gedidigital.py
Normal file
@@ -0,0 +1,161 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class GediDigitalIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://video\.
|
||||
(?:
|
||||
(?:
|
||||
(?:espresso\.)?repubblica
|
||||
|lastampa
|
||||
|ilsecoloxix
|
||||
)|
|
||||
(?:
|
||||
iltirreno
|
||||
|messaggeroveneto
|
||||
|ilpiccolo
|
||||
|gazzettadimantova
|
||||
|mattinopadova
|
||||
|laprovinciapavese
|
||||
|tribunatreviso
|
||||
|nuovavenezia
|
||||
|gazzettadimodena
|
||||
|lanuovaferrara
|
||||
|corrierealpi
|
||||
|lasentinella
|
||||
)\.gelocal
|
||||
)\.it(?:/[^/]+){2,3}?/(?P<id>\d+)(?:[/?&#]|$)'''
|
||||
_TESTS = [{
|
||||
'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
|
||||
'md5': '84658d7fb9e55a6e57ecc77b73137494',
|
||||
'info_dict': {
|
||||
'id': '121559',
|
||||
'ext': 'mp4',
|
||||
'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
|
||||
'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
|
||||
'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
|
||||
'duration': 125,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
title = self._html_search_meta(
|
||||
['twitter:title', 'og:title'], webpage, fatal=True)
|
||||
player_data = re.findall(
|
||||
r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
|
||||
webpage)
|
||||
|
||||
formats = []
|
||||
duration = thumb = None
|
||||
for t, n, v in player_data:
|
||||
if t == 'format':
|
||||
if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
|
||||
continue
|
||||
elif n.endswith('-vod-ak'):
|
||||
formats.extend(self._extract_akamai_formats(
|
||||
v, video_id, {'http': 'media.gedidigital.it'}))
|
||||
else:
|
||||
ext = determine_ext(v)
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
|
||||
continue
|
||||
f = {
|
||||
'format_id': n,
|
||||
'url': v,
|
||||
}
|
||||
if ext == 'mp3':
|
||||
abr = int_or_none(self._search_regex(
|
||||
r'-mp3-audio-(\d+)', v, 'abr', default=None))
|
||||
f.update({
|
||||
'abr': abr,
|
||||
'tbr': abr,
|
||||
'vcodec': 'none'
|
||||
})
|
||||
else:
|
||||
mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
|
||||
if mobj:
|
||||
f.update({
|
||||
'height': int(mobj.group(1)),
|
||||
'vbr': int_or_none(mobj.group(2)),
|
||||
})
|
||||
if not f.get('vbr'):
|
||||
f['vbr'] = int_or_none(self._search_regex(
|
||||
r'-video-rrtv-(\d+)', v, 'abr', default=None))
|
||||
formats.append(f)
|
||||
elif t == 'param':
|
||||
if n in ['image_full', 'image']:
|
||||
thumb = v
|
||||
elif n == 'videoDuration':
|
||||
duration = int_or_none(v)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': self._html_search_meta(
|
||||
['twitter:description', 'og:description', 'description'], webpage),
|
||||
'thumbnail': thumb or self._og_search_thumbnail(webpage),
|
||||
'formats': formats,
|
||||
'duration': duration,
|
||||
}
|
@@ -128,6 +128,8 @@ from .zype import ZypeIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .kinja import KinjaEmbedIE
|
||||
from .arcpublishing import ArcPublishingIE
|
||||
from .medialaan import MedialaanIE
|
||||
from .simplecast import SimplecastIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
@@ -2223,6 +2225,29 @@ class GenericIE(InfoExtractor):
|
||||
'duration': 1581,
|
||||
},
|
||||
},
|
||||
{
|
||||
# MyChannels SDK embed
|
||||
# https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen
|
||||
'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/',
|
||||
'md5': '90c0699c37006ef18e198c032d81739c',
|
||||
'info_dict': {
|
||||
'id': '194165',
|
||||
'ext': 'mp4',
|
||||
'title': 'Burgemeester Aboutaleb spreekt relschoppers toe',
|
||||
'timestamp': 1611740340,
|
||||
'upload_date': '20210127',
|
||||
'duration': 159,
|
||||
},
|
||||
},
|
||||
{
|
||||
# Simplecast player embed
|
||||
'url': 'https://www.bio.org/podcast',
|
||||
'info_dict': {
|
||||
'id': 'podcast',
|
||||
'title': 'I AM BIO Podcast | BIO',
|
||||
},
|
||||
'playlist_mincount': 52,
|
||||
},
|
||||
]
|
||||
|
||||
def report_following_redirect(self, new_url):
|
||||
@@ -2462,6 +2487,9 @@ class GenericIE(InfoExtractor):
|
||||
webpage = self._webpage_read_content(
|
||||
full_response, url, video_id, prefix=first_bytes)
|
||||
|
||||
if '<title>DPG Media Privacy Gate</title>' in webpage:
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
self.report_extraction(video_id)
|
||||
|
||||
# Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest?
|
||||
@@ -2593,6 +2621,11 @@ class GenericIE(InfoExtractor):
|
||||
if arc_urls:
|
||||
return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key())
|
||||
|
||||
mychannels_urls = MedialaanIE._extract_urls(webpage)
|
||||
if mychannels_urls:
|
||||
return self.playlist_from_matches(
|
||||
mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key())
|
||||
|
||||
# Look for embedded rtl.nl player
|
||||
matches = re.findall(
|
||||
r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
|
||||
@@ -2769,6 +2802,12 @@ class GenericIE(InfoExtractor):
|
||||
return self.playlist_from_matches(
|
||||
matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
|
||||
|
||||
# Look for Simplecast embeds
|
||||
simplecast_urls = SimplecastIE._extract_urls(webpage)
|
||||
if simplecast_urls:
|
||||
return self.playlist_from_matches(
|
||||
simplecast_urls, video_id, video_title)
|
||||
|
||||
# Look for BBC iPlayer embed
|
||||
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
|
||||
if matches:
|
||||
|
@@ -7,6 +7,7 @@ from ..compat import compat_parse_qs
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
get_element_by_class,
|
||||
int_or_none,
|
||||
lowercase_escape,
|
||||
try_get,
|
||||
@@ -237,7 +238,7 @@ class GoogleDriveIE(InfoExtractor):
|
||||
if confirmation_webpage:
|
||||
confirm = self._search_regex(
|
||||
r'confirm=([^&"\']+)', confirmation_webpage,
|
||||
'confirmation code', fatal=False)
|
||||
'confirmation code', default=None)
|
||||
if confirm:
|
||||
confirmed_source_url = update_url_query(source_url, {
|
||||
'confirm': confirm,
|
||||
@@ -245,6 +246,11 @@ class GoogleDriveIE(InfoExtractor):
|
||||
urlh = request_source_file(confirmed_source_url, 'confirmed source')
|
||||
if urlh and urlh.headers.get('Content-Disposition'):
|
||||
add_source_format(urlh)
|
||||
else:
|
||||
self.report_warning(
|
||||
get_element_by_class('uc-error-subcaption', confirmation_webpage)
|
||||
or get_element_by_class('uc-error-caption', confirmation_webpage)
|
||||
or 'unable to extract confirmation code')
|
||||
|
||||
if not formats and reason:
|
||||
raise ExtractorError(reason, expected=True)
|
||||
|
@@ -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"\s*:\s*"(.+?)"',
|
||||
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'])))
|
||||
|
@@ -3,10 +3,13 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..compat import compat_HTTPError
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
)
|
||||
@@ -23,7 +26,7 @@ class KakaoIE(InfoExtractor):
|
||||
'id': '301965083',
|
||||
'ext': 'mp4',
|
||||
'title': '乃木坂46 バナナマン 「3期生紹介コーナーが始動!顔高低差GPも!」 『乃木坂工事中』',
|
||||
'uploader_id': 2671005,
|
||||
'uploader_id': '2671005',
|
||||
'uploader': '그랑그랑이',
|
||||
'timestamp': 1488160199,
|
||||
'upload_date': '20170227',
|
||||
@@ -36,11 +39,15 @@ class KakaoIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
|
||||
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
|
||||
'uploader_id': 2653210,
|
||||
'uploader_id': '2653210',
|
||||
'uploader': '쇼! 음악중심',
|
||||
'timestamp': 1485684628,
|
||||
'upload_date': '20170129',
|
||||
}
|
||||
}, {
|
||||
# geo restricted
|
||||
'url': 'https://tv.kakao.com/channel/3643855/cliplink/412069491',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -68,8 +75,7 @@ class KakaoIE(InfoExtractor):
|
||||
'fields': ','.join([
|
||||
'-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
|
||||
'description', 'channelId', 'createTime', 'duration', 'playCount',
|
||||
'likeCount', 'commentCount', 'tagList', 'channel', 'name',
|
||||
'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
|
||||
'likeCount', 'commentCount', 'tagList', 'channel', 'name', 'thumbnailUrl',
|
||||
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
|
||||
}
|
||||
|
||||
@@ -82,24 +88,28 @@ class KakaoIE(InfoExtractor):
|
||||
|
||||
title = clip.get('title') or clip_link.get('displayTitle')
|
||||
|
||||
query['tid'] = impress.get('tid', '')
|
||||
query.update({
|
||||
'fields': '-*,code,message,url',
|
||||
'tid': impress.get('tid') or '',
|
||||
})
|
||||
|
||||
formats = []
|
||||
for fmt in clip.get('videoOutputList', []):
|
||||
for fmt in (clip.get('videoOutputList') or []):
|
||||
try:
|
||||
profile_name = fmt['profile']
|
||||
if profile_name == 'AUDIO':
|
||||
continue
|
||||
query.update({
|
||||
'profile': profile_name,
|
||||
'fields': '-*,url',
|
||||
})
|
||||
fmt_url_json = self._download_json(
|
||||
api_base + 'raw/videolocation', display_id,
|
||||
'Downloading video URL for profile %s' % profile_name,
|
||||
query=query, headers=player_header, fatal=False)
|
||||
|
||||
if fmt_url_json is None:
|
||||
query['profile'] = profile_name
|
||||
try:
|
||||
fmt_url_json = self._download_json(
|
||||
api_base + 'raw/videolocation', display_id,
|
||||
'Downloading video URL for profile %s' % profile_name,
|
||||
query=query, headers=player_header)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
resp = self._parse_json(e.cause.read().decode(), video_id)
|
||||
if resp.get('code') == 'GeoBlocked':
|
||||
self.raise_geo_restricted()
|
||||
continue
|
||||
|
||||
fmt_url = fmt_url_json['url']
|
||||
@@ -116,27 +126,13 @@ class KakaoIE(InfoExtractor):
|
||||
pass
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbs = []
|
||||
for thumb in clip.get('clipChapterThumbnailList', []):
|
||||
thumbs.append({
|
||||
'url': thumb.get('thumbnailUrl'),
|
||||
'id': compat_str(thumb.get('timeInSec')),
|
||||
'preference': -1 if thumb.get('isDefault') else 0
|
||||
})
|
||||
top_thumbnail = clip.get('thumbnailUrl')
|
||||
if top_thumbnail:
|
||||
thumbs.append({
|
||||
'url': top_thumbnail,
|
||||
'preference': 10,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': display_id,
|
||||
'title': title,
|
||||
'description': strip_or_none(clip.get('description')),
|
||||
'uploader': clip_link.get('channel', {}).get('name'),
|
||||
'uploader_id': clip_link.get('channelId'),
|
||||
'thumbnails': thumbs,
|
||||
'uploader': try_get(clip_link, lambda x: x['channel']['name']),
|
||||
'uploader_id': str_or_none(clip_link.get('channelId')),
|
||||
'thumbnail': clip.get('thumbnailUrl'),
|
||||
'timestamp': unified_timestamp(clip_link.get('createTime')),
|
||||
'duration': int_or_none(clip.get('duration')),
|
||||
'view_count': int_or_none(clip.get('playCount')),
|
||||
|
@@ -2,268 +2,113 @@ from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .gigya import GigyaBaseIE
|
||||
|
||||
from ..compat import compat_str
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
mimetype2ext,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
|
||||
class MedialaanIE(GigyaBaseIE):
|
||||
class MedialaanIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://
|
||||
(?:www\.|nieuws\.)?
|
||||
(?:
|
||||
(?P<site_id>vtm|q2|vtmkzoom)\.be/
|
||||
(?:
|
||||
video(?:/[^/]+/id/|/?\?.*?\baid=)|
|
||||
(?:[^/]+/)*
|
||||
)
|
||||
(?:embed\.)?mychannels.video/embed/|
|
||||
embed\.mychannels\.video/(?:s(?:dk|cript)/)?production/|
|
||||
(?:www\.)?(?:
|
||||
(?:
|
||||
7sur7|
|
||||
demorgen|
|
||||
hln|
|
||||
joe|
|
||||
qmusic
|
||||
)\.be|
|
||||
(?:
|
||||
[abe]d|
|
||||
bndestem|
|
||||
destentor|
|
||||
gelderlander|
|
||||
pzc|
|
||||
tubantia|
|
||||
volkskrant
|
||||
)\.nl
|
||||
)/video/(?:[^/]+/)*[^/?&#]+~p
|
||||
)
|
||||
(?P<id>[^/?#&]+)
|
||||
(?P<id>\d+)
|
||||
'''
|
||||
_NETRC_MACHINE = 'medialaan'
|
||||
_APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
|
||||
_SITE_TO_APP_ID = {
|
||||
'vtm': 'vtm_watch',
|
||||
'q2': 'q2',
|
||||
'vtmkzoom': 'vtmkzoom',
|
||||
}
|
||||
_TESTS = [{
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
|
||||
'url': 'https://www.bndestem.nl/video/de-terugkeer-van-ally-de-aap-en-wie-vertrekt-er-nog-bij-nac~p193993',
|
||||
'info_dict': {
|
||||
'id': 'vtm_20170219_VM0678361_vtmwatch',
|
||||
'id': '193993',
|
||||
'ext': 'mp4',
|
||||
'title': 'Allemaal Chris afl. 6',
|
||||
'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
|
||||
'timestamp': 1487533280,
|
||||
'upload_date': '20170219',
|
||||
'duration': 2562,
|
||||
'series': 'Allemaal Chris',
|
||||
'season': 'Allemaal Chris',
|
||||
'season_number': 1,
|
||||
'season_id': '256936078124527',
|
||||
'episode': 'Allemaal Chris afl. 6',
|
||||
'episode_number': 6,
|
||||
'episode_id': '256936078591527',
|
||||
'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?',
|
||||
'timestamp': 1611663540,
|
||||
'upload_date': '20210126',
|
||||
'duration': 238,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Requires account credentials',
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtm.be/video?aid=168332',
|
||||
'info_dict': {
|
||||
'id': '168332',
|
||||
'ext': 'mp4',
|
||||
'title': '"Veronique liegt!"',
|
||||
'description': 'md5:1385e2b743923afe54ba4adc38476155',
|
||||
'timestamp': 1489002029,
|
||||
'upload_date': '20170308',
|
||||
'duration': 96,
|
||||
},
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
|
||||
'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://vtm.be/video?aid=163157',
|
||||
'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# vod
|
||||
'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
|
||||
'url': 'https://embed.mychannels.video/script/production/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
|
||||
'url': 'https://embed.mychannels.video/production/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# http/s redirect
|
||||
'url': 'https://vtmkzoom.be/video?aid=45724',
|
||||
'info_dict': {
|
||||
'id': '257136373657000',
|
||||
'ext': 'mp4',
|
||||
'title': 'K3 Dansstudio Ushuaia afl.6',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'Requires account credentials',
|
||||
'url': 'https://mychannels.video/embed/193993',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# nieuws.vtm.be
|
||||
'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma',
|
||||
'url': 'https://embed.mychannels.video/embed/193993',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._logged_in = False
|
||||
|
||||
def _login(self):
|
||||
username, password = self._get_login_info()
|
||||
if username is None:
|
||||
self.raise_login_required()
|
||||
|
||||
auth_data = {
|
||||
'APIKey': self._APIKEY,
|
||||
'sdk': 'js_6.1',
|
||||
'format': 'json',
|
||||
'loginID': username,
|
||||
'password': password,
|
||||
}
|
||||
|
||||
auth_info = self._gigya_login(auth_data)
|
||||
|
||||
self._uid = auth_info['UID']
|
||||
self._uid_signature = auth_info['UIDSignature']
|
||||
self._signature_timestamp = auth_info['signatureTimestamp']
|
||||
|
||||
self._logged_in = True
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
entries = []
|
||||
for element in re.findall(r'(<div[^>]+data-mychannels-type="video"[^>]*>)', webpage):
|
||||
mychannels_id = extract_attributes(element).get('data-mychannels-id')
|
||||
if mychannels_id:
|
||||
entries.append('https://mychannels.video/embed/' + mychannels_id)
|
||||
return entries
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, site_id = mobj.group('id', 'site_id')
|
||||
production_id = self._match_id(url)
|
||||
production = self._download_json(
|
||||
'https://embed.mychannels.video/sdk/production/' + production_id,
|
||||
production_id, query={'options': 'UUUU_default'})['productions'][0]
|
||||
title = production['title']
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
config = self._parse_json(
|
||||
self._search_regex(
|
||||
r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
|
||||
webpage, 'config', default='{}'), video_id,
|
||||
transform_source=lambda s: s.replace(
|
||||
'\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
|
||||
|
||||
vod_id = config.get('vodId') or self._search_regex(
|
||||
(r'\\"vodId\\"\s*:\s*\\"(.+?)\\"',
|
||||
r'"vodId"\s*:\s*"(.+?)"',
|
||||
r'<[^>]+id=["\']vod-(\d+)'),
|
||||
webpage, 'video_id', default=None)
|
||||
|
||||
# clip, no authentication required
|
||||
if not vod_id:
|
||||
player = self._parse_json(
|
||||
self._search_regex(
|
||||
r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
|
||||
default=''),
|
||||
video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
|
||||
if player:
|
||||
video = player[-1]
|
||||
if video['videoUrl'] in ('http', 'https'):
|
||||
return self.url_result(video['url'], MedialaanIE.ie_key())
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video['videoUrl'],
|
||||
'title': video['title'],
|
||||
'thumbnail': video.get('imageUrl'),
|
||||
'timestamp': int_or_none(video.get('createdDate')),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
}
|
||||
formats = []
|
||||
for source in (production.get('sources') or []):
|
||||
src = source.get('src')
|
||||
if not src:
|
||||
continue
|
||||
ext = mimetype2ext(source.get('type'))
|
||||
if ext == 'm3u8':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
src, production_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id='hls', fatal=False))
|
||||
else:
|
||||
info = self._parse_html5_media_entries(
|
||||
url, webpage, video_id, m3u8_id='hls')[0]
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': self._html_search_meta('description', webpage),
|
||||
'duration': parse_duration(self._html_search_meta('duration', webpage)),
|
||||
formats.append({
|
||||
'ext': ext,
|
||||
'url': src,
|
||||
})
|
||||
# vod, authentication required
|
||||
else:
|
||||
if not self._logged_in:
|
||||
self._login()
|
||||
self._sort_formats(formats)
|
||||
|
||||
settings = self._parse_json(
|
||||
self._search_regex(
|
||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
||||
webpage, 'drupal settings', default='{}'),
|
||||
video_id)
|
||||
|
||||
def get(container, item):
|
||||
return try_get(
|
||||
settings, lambda x: x[container][item],
|
||||
compat_str) or self._search_regex(
|
||||
r'"%s"\s*:\s*"([^"]+)' % item, webpage, item,
|
||||
default=None)
|
||||
|
||||
app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
|
||||
sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
|
||||
|
||||
data = self._download_json(
|
||||
'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
|
||||
video_id, query={
|
||||
'app_id': app_id,
|
||||
'user_network': sso,
|
||||
'UID': self._uid,
|
||||
'UIDSignature': self._uid_signature,
|
||||
'signatureTimestamp': self._signature_timestamp,
|
||||
})
|
||||
|
||||
formats = self._extract_m3u8_formats(
|
||||
data['response']['uri'], video_id, entry_protocol='m3u8_native',
|
||||
ext='mp4', m3u8_id='hls')
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = {
|
||||
'id': vod_id,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
api_key = get('vod', 'apiKey')
|
||||
channel = get('medialaanGigya', 'channel')
|
||||
|
||||
if api_key:
|
||||
videos = self._download_json(
|
||||
'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
|
||||
query={
|
||||
'channels': channel,
|
||||
'ids': vod_id,
|
||||
'limit': 1,
|
||||
'apikey': api_key,
|
||||
})
|
||||
if videos:
|
||||
video = try_get(
|
||||
videos, lambda x: x['response']['videos'][0], dict)
|
||||
if video:
|
||||
def get(container, item, expected_type=None):
|
||||
return try_get(
|
||||
video, lambda x: x[container][item], expected_type)
|
||||
|
||||
def get_string(container, item):
|
||||
return get(container, item, compat_str)
|
||||
|
||||
info.update({
|
||||
'series': get_string('program', 'title'),
|
||||
'season': get_string('season', 'title'),
|
||||
'season_number': int_or_none(get('season', 'number')),
|
||||
'season_id': get_string('season', 'id'),
|
||||
'episode': get_string('episode', 'title'),
|
||||
'episode_number': int_or_none(get('episode', 'number')),
|
||||
'episode_id': get_string('episode', 'id'),
|
||||
'duration': int_or_none(
|
||||
video.get('duration')) or int_or_none(
|
||||
video.get('durationMillis'), scale=1000),
|
||||
'title': get_string('episode', 'title'),
|
||||
'description': get_string('episode', 'text'),
|
||||
'timestamp': unified_timestamp(get_string(
|
||||
'publication', 'begin')),
|
||||
})
|
||||
|
||||
if not info.get('title'):
|
||||
info['title'] = try_get(
|
||||
config, lambda x: x['videoConfig']['title'],
|
||||
compat_str) or self._html_search_regex(
|
||||
r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title',
|
||||
default=None) or self._og_search_title(webpage)
|
||||
|
||||
if not info.get('description'):
|
||||
info['description'] = self._html_search_regex(
|
||||
r'<div[^>]+class="field-item\s+even">\s*<p>(.+?)</p>',
|
||||
webpage, 'description', default=None)
|
||||
|
||||
return info
|
||||
return {
|
||||
'id': production_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': production.get('posterUrl'),
|
||||
'timestamp': parse_iso8601(production.get('publicationDate'), ' '),
|
||||
'duration': int_or_none(production.get('duration')) or None,
|
||||
}
|
||||
|
@@ -253,6 +253,10 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
|
||||
return try_get(feed, lambda x: x['result']['data']['id'], compat_str)
|
||||
|
||||
@staticmethod
|
||||
def _extract_child_with_type(parent, t):
|
||||
return next(c for c in parent['children'] if c.get('type') == t)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
try:
|
||||
# the url can be http://media.mtvnservices.com/fb/{mgid}.swf
|
||||
@@ -278,6 +282,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
||||
if not mgid:
|
||||
mgid = self._extract_triforce_mgid(webpage)
|
||||
|
||||
if not mgid:
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
|
||||
main_container = self._extract_child_with_type(data, 'MainContainer')
|
||||
video_player = self._extract_child_with_type(main_container, 'VideoPlayer')
|
||||
mgid = video_player['props']['media']['video']['config']['uri']
|
||||
|
||||
return mgid
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -349,18 +360,6 @@ class MTVIE(MTVServicesInfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def extract_child_with_type(parent, t):
|
||||
children = parent['children']
|
||||
return next(c for c in children if c.get('type') == t)
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
data = self._parse_json(self._search_regex(
|
||||
r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
|
||||
main_container = self.extract_child_with_type(data, 'MainContainer')
|
||||
video_player = self.extract_child_with_type(main_container, 'VideoPlayer')
|
||||
return video_player['props']['media']['video']['config']['uri']
|
||||
|
||||
|
||||
class MTVJapanIE(MTVServicesInfoExtractor):
|
||||
IE_NAME = 'mtvjapan'
|
||||
|
@@ -2,10 +2,11 @@ from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
@@ -14,7 +15,7 @@ class NineGagIE(InfoExtractor):
|
||||
IE_NAME = '9gag'
|
||||
_VALID_URL = r'https?://(?:www\.)?9gag\.com/gag/(?P<id>[^/?&#]+)'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'https://9gag.com/gag/ae5Ag7B',
|
||||
'info_dict': {
|
||||
'id': 'ae5Ag7B',
|
||||
@@ -29,7 +30,11 @@ class NineGagIE(InfoExtractor):
|
||||
'dislike_count': int,
|
||||
'comment_count': int,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
# HTML escaped title
|
||||
'url': 'https://9gag.com/gag/av5nvyb',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
post_id = self._match_id(url)
|
||||
@@ -43,7 +48,7 @@ class NineGagIE(InfoExtractor):
|
||||
'The given url does not contain a video',
|
||||
expected=True)
|
||||
|
||||
title = post['title']
|
||||
title = unescapeHTML(post['title'])
|
||||
|
||||
duration = None
|
||||
formats = []
|
||||
|
@@ -6,30 +6,40 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urlparse
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
get_element_by_class,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class NJPWWorldIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
|
||||
_VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
|
||||
IE_DESC = '新日本プロレスワールド'
|
||||
_NETRC_MACHINE = 'njpwworld'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
|
||||
'info_dict': {
|
||||
'id': 's_series_00155_1_9',
|
||||
'ext': 'mp4',
|
||||
'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
|
||||
'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー',
|
||||
'tags': list,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True, # AES-encrypted m3u8
|
||||
},
|
||||
'skip': 'Requires login',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
|
||||
'info_dict': {
|
||||
'id': 's_series_00563_16_bs',
|
||||
'ext': 'mp4',
|
||||
'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント(字幕あり)',
|
||||
'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"],
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
_LOGIN_URL = 'https://front.njpwworld.com/auth/login'
|
||||
|
||||
@@ -64,35 +74,27 @@ class NJPWWorldIE(InfoExtractor):
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
formats = []
|
||||
for mobj in re.finditer(r'<a[^>]+\bhref=(["\'])/player.+?[^>]*>', webpage):
|
||||
player = extract_attributes(mobj.group(0))
|
||||
player_path = player.get('href')
|
||||
if not player_path:
|
||||
continue
|
||||
kind = self._search_regex(
|
||||
r'(low|high)$', player.get('class') or '', 'kind',
|
||||
default='low')
|
||||
for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
|
||||
player_path = '/intent?id=%s&type=url' % vid
|
||||
player_url = compat_urlparse.urljoin(url, player_path)
|
||||
player_page = self._download_webpage(
|
||||
player_url, video_id, note='Downloading player page')
|
||||
entries = self._parse_html5_media_entries(
|
||||
player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
|
||||
m3u8_entry_protocol='m3u8_native')
|
||||
kind_formats = entries[0]['formats']
|
||||
for f in kind_formats:
|
||||
f['quality'] = 2 if kind == 'high' else 1
|
||||
formats.extend(kind_formats)
|
||||
formats.append({
|
||||
'url': player_url,
|
||||
'format_id': kind,
|
||||
'ext': 'mp4',
|
||||
'protocol': 'm3u8',
|
||||
'quality': 2 if kind == 'high' else 1,
|
||||
})
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
post_content = get_element_by_class('post-content', webpage)
|
||||
tag_block = get_element_by_class('tag-block', webpage)
|
||||
tags = re.findall(
|
||||
r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
|
||||
) if post_content else None
|
||||
r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
|
||||
) if tag_block else None
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': self._og_search_title(webpage),
|
||||
'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
|
||||
'formats': formats,
|
||||
'tags': tags,
|
||||
}
|
||||
|
@@ -413,7 +413,8 @@ class PeerTubeIE(InfoExtractor):
|
||||
peertube3\.cpy\.re|
|
||||
peertube2\.cpy\.re|
|
||||
videos\.tcit\.fr|
|
||||
peertube\.cpy\.re
|
||||
peertube\.cpy\.re|
|
||||
canard\.tube
|
||||
)'''
|
||||
_UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
|
||||
_API_BASE = 'https://%s/api/v1/videos/%s/%s'
|
||||
|
@@ -1,45 +1,128 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .dreisat import DreiSatIE
|
||||
import re
|
||||
|
||||
from .youtube import YoutubeIE
|
||||
from .zdf import ZDFBaseIE
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
unified_timestamp,
|
||||
xpath_text,
|
||||
)
|
||||
|
||||
|
||||
class PhoenixIE(DreiSatIE):
|
||||
class PhoenixIE(ZDFBaseIE):
|
||||
IE_NAME = 'phoenix.de'
|
||||
_VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
|
||||
(?:
|
||||
phoenix/die_sendungen/(?:[^/]+/)?
|
||||
)?
|
||||
(?P<id>[0-9]+)'''
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/884301',
|
||||
'md5': 'ed249f045256150c92e72dbb70eadec6',
|
||||
'info_dict': {
|
||||
'id': '884301',
|
||||
'ext': 'mp4',
|
||||
'title': 'Michael Krons mit Hans-Werner Sinn',
|
||||
'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
|
||||
'upload_date': '20141025',
|
||||
'uploader': 'Im Dialog',
|
||||
}
|
||||
_VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
|
||||
_TESTS = [{
|
||||
# Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
|
||||
'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
|
||||
'md5': '34ec321e7eb34231fd88616c65c92db0',
|
||||
'info_dict': {
|
||||
'id': '210222_phx_nachgehakt_corona_protest',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wohin führt der Protest in der Pandemie?',
|
||||
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
|
||||
'duration': 1691,
|
||||
'timestamp': 1613906100,
|
||||
'upload_date': '20210221',
|
||||
'uploader': 'Phoenix',
|
||||
'channel': 'corona nachgehakt',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Youtube embed
|
||||
'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
|
||||
'info_dict': {
|
||||
'id': 'hMQtqFYjomk',
|
||||
'ext': 'mp4',
|
||||
'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
|
||||
'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
|
||||
'duration': 3509,
|
||||
'upload_date': '20201219',
|
||||
'uploader': 'phoenix',
|
||||
'uploader_id': 'phoenix',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
|
||||
'only_matching': True,
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
]
|
||||
}, {
|
||||
'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# no media
|
||||
'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
|
||||
'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
article_id = self._match_id(url)
|
||||
|
||||
internal_id = self._search_regex(
|
||||
r'<div class="phx_vod" id="phx_vod_([0-9]+)"',
|
||||
webpage, 'internal video ID')
|
||||
article = self._download_json(
|
||||
'https://www.phoenix.de/response/id/%s' % article_id, article_id,
|
||||
'Downloading article JSON')
|
||||
|
||||
api_url = 'http://www.phoenix.de/php/mediaplayer/data/beitrags_details.php?ak=web&id=%s' % internal_id
|
||||
return self.extract_from_xml_url(video_id, api_url)
|
||||
video = article['absaetze'][0]
|
||||
title = video.get('titel') or article.get('subtitel')
|
||||
|
||||
if video.get('typ') == 'video-youtube':
|
||||
video_id = video['id']
|
||||
return self.url_result(
|
||||
video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
|
||||
video_title=title)
|
||||
|
||||
video_id = compat_str(video.get('basename') or video.get('content'))
|
||||
|
||||
details = self._download_xml(
|
||||
'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
|
||||
video_id, 'Downloading details XML', query={
|
||||
'ak': 'web',
|
||||
'ptmd': 'true',
|
||||
'id': video_id,
|
||||
'profile': 'player2',
|
||||
})
|
||||
|
||||
title = title or xpath_text(
|
||||
details, './/information/title', 'title', fatal=True)
|
||||
content_id = xpath_text(
|
||||
details, './/video/details/basename', 'content id', fatal=True)
|
||||
|
||||
info = self._extract_ptmd(
|
||||
'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
|
||||
content_id, None, url)
|
||||
|
||||
timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
|
||||
|
||||
thumbnails = []
|
||||
for node in details.findall('.//teaserimages/teaserimage'):
|
||||
thumbnail_url = node.text
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumbnail = {
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
thumbnail_key = node.get('key')
|
||||
if thumbnail_key:
|
||||
m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
|
||||
if m:
|
||||
thumbnail['width'] = int(m.group(1))
|
||||
thumbnail['height'] = int(m.group(2))
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
return merge_dicts(info, {
|
||||
'id': content_id,
|
||||
'title': title,
|
||||
'description': xpath_text(details, './/information/detail'),
|
||||
'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': timestamp,
|
||||
'uploader': xpath_text(details, './/details/channel'),
|
||||
'uploader_id': xpath_text(details, './/details/originChannelId'),
|
||||
'channel': xpath_text(details, './/details/originChannelTitle'),
|
||||
})
|
||||
|
@@ -22,11 +22,15 @@ from ..utils import (
|
||||
orderedSet,
|
||||
remove_quotes,
|
||||
str_to_int,
|
||||
update_url_query,
|
||||
urlencode_postdata,
|
||||
url_or_none,
|
||||
)
|
||||
|
||||
|
||||
class PornHubBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'pornhub'
|
||||
|
||||
def _download_webpage_handle(self, *args, **kwargs):
|
||||
def dl(*args, **kwargs):
|
||||
return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
|
||||
@@ -52,6 +56,66 @@ class PornHubBaseIE(InfoExtractor):
|
||||
|
||||
return webpage, urlh
|
||||
|
||||
def _real_initialize(self):
|
||||
self._logged_in = False
|
||||
|
||||
def _login(self, host):
|
||||
if self._logged_in:
|
||||
return
|
||||
|
||||
site = host.split('.')[0]
|
||||
|
||||
# Both sites pornhub and pornhubpremium have separate accounts
|
||||
# so there should be an option to provide credentials for both.
|
||||
# At the same time some videos are available under the same video id
|
||||
# on both sites so that we have to identify them as the same video.
|
||||
# For that purpose we have to keep both in the same extractor
|
||||
# but under different netrc machines.
|
||||
username, password = self._get_login_info(netrc_machine=site)
|
||||
if username is None:
|
||||
return
|
||||
|
||||
login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
|
||||
login_page = self._download_webpage(
|
||||
login_url, None, 'Downloading %s login page' % site)
|
||||
|
||||
def is_logged(webpage):
|
||||
return any(re.search(p, webpage) for p in (
|
||||
r'class=["\']signOut',
|
||||
r'>Sign\s+[Oo]ut\s*<'))
|
||||
|
||||
if is_logged(login_page):
|
||||
self._logged_in = True
|
||||
return
|
||||
|
||||
login_form = self._hidden_inputs(login_page)
|
||||
|
||||
login_form.update({
|
||||
'username': username,
|
||||
'password': password,
|
||||
})
|
||||
|
||||
response = self._download_json(
|
||||
'https://www.%s/front/authenticate' % host, None,
|
||||
'Logging in to %s' % site,
|
||||
data=urlencode_postdata(login_form),
|
||||
headers={
|
||||
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
|
||||
'Referer': login_url,
|
||||
'X-Requested-With': 'XMLHttpRequest',
|
||||
})
|
||||
|
||||
if response.get('success') == '1':
|
||||
self._logged_in = True
|
||||
return
|
||||
|
||||
message = response.get('message')
|
||||
if message is not None:
|
||||
raise ExtractorError(
|
||||
'Unable to login: %s' % message, expected=True)
|
||||
|
||||
raise ExtractorError('Unable to log in')
|
||||
|
||||
|
||||
class PornHubIE(PornHubBaseIE):
|
||||
IE_DESC = 'PornHub and Thumbzilla'
|
||||
@@ -163,12 +227,20 @@ class PornHubIE(PornHubBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Some videos are available with the same id on both premium
|
||||
# and non-premium sites (e.g. this and the following test)
|
||||
'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net|org)/embed/[\da-z]+)',
|
||||
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
|
||||
webpage)
|
||||
|
||||
def _extract_count(self, pattern, webpage, name):
|
||||
@@ -180,12 +252,7 @@ class PornHubIE(PornHubBaseIE):
|
||||
host = mobj.group('host') or 'pornhub.com'
|
||||
video_id = mobj.group('id')
|
||||
|
||||
if 'premium' in host:
|
||||
if not self._downloader.params.get('cookiefile'):
|
||||
raise ExtractorError(
|
||||
'PornHub Premium requires authentication.'
|
||||
' You may want to use --cookies.',
|
||||
expected=True)
|
||||
self._login(host)
|
||||
|
||||
self._set_cookie(host, 'age_verified', '1')
|
||||
|
||||
@@ -405,6 +472,10 @@ class PornHubIE(PornHubBaseIE):
|
||||
|
||||
|
||||
class PornHubPlaylistBaseIE(PornHubBaseIE):
|
||||
def _extract_page(self, url):
|
||||
return int_or_none(self._search_regex(
|
||||
r'\bpage=(\d+)', url, 'page', default=None))
|
||||
|
||||
def _extract_entries(self, webpage, host):
|
||||
# Only process container div with main playlist content skipping
|
||||
# drop-down menu that uses similar pattern for videos (see
|
||||
@@ -422,26 +493,6 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
|
||||
container))
|
||||
]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
playlist_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
entries = self._extract_entries(webpage, host)
|
||||
|
||||
playlist = self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
|
||||
'playlist', default='{}'),
|
||||
playlist_id, fatal=False)
|
||||
title = playlist.get('title') or self._search_regex(
|
||||
r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
|
||||
|
||||
return self.playlist_result(
|
||||
entries, playlist_id, title, playlist.get('description'))
|
||||
|
||||
|
||||
class PornHubUserIE(PornHubPlaylistBaseIE):
|
||||
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
|
||||
@@ -463,14 +514,27 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
|
||||
}, {
|
||||
'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Unavailable via /videos page, but available with direct pagination
|
||||
# on pornstar page (see [1]), requires premium
|
||||
# 1. https://github.com/ytdl-org/youtube-dl/issues/27853
|
||||
'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as before, multi page
|
||||
'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
user_id = mobj.group('id')
|
||||
videos_url = '%s/videos' % mobj.group('url')
|
||||
page = self._extract_page(url)
|
||||
if page:
|
||||
videos_url = update_url_query(videos_url, {'page': page})
|
||||
return self.url_result(
|
||||
'%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
|
||||
video_id=user_id)
|
||||
videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
|
||||
|
||||
|
||||
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
||||
@@ -483,32 +547,55 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
|
||||
<button[^>]+\bid=["\']moreDataBtn
|
||||
''', webpage) is not None
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
item_id = mobj.group('id')
|
||||
def _entries(self, url, host, item_id):
|
||||
page = self._extract_page(url)
|
||||
|
||||
page = int_or_none(self._search_regex(
|
||||
r'\bpage=(\d+)', url, 'page', default=None))
|
||||
VIDEOS = '/videos'
|
||||
|
||||
entries = []
|
||||
for page_num in (page, ) if page is not None else itertools.count(1):
|
||||
def download_page(base_url, num, fallback=False):
|
||||
note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
|
||||
return self._download_webpage(
|
||||
base_url, item_id, note, query={'page': num})
|
||||
|
||||
def is_404(e):
|
||||
return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
|
||||
|
||||
base_url = url
|
||||
has_page = page is not None
|
||||
first_page = page if has_page else 1
|
||||
for page_num in (first_page, ) if has_page else itertools.count(first_page):
|
||||
try:
|
||||
webpage = self._download_webpage(
|
||||
url, item_id, 'Downloading page %d' % page_num,
|
||||
query={'page': page_num})
|
||||
try:
|
||||
webpage = download_page(base_url, page_num)
|
||||
except ExtractorError as e:
|
||||
# Some sources may not be available via /videos page,
|
||||
# trying to fallback to main page pagination (see [1])
|
||||
# 1. https://github.com/ytdl-org/youtube-dl/issues/27853
|
||||
if is_404(e) and page_num == first_page and VIDEOS in base_url:
|
||||
base_url = base_url.replace(VIDEOS, '')
|
||||
webpage = download_page(base_url, page_num, fallback=True)
|
||||
else:
|
||||
raise
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
|
||||
if is_404(e) and page_num != first_page:
|
||||
break
|
||||
raise
|
||||
page_entries = self._extract_entries(webpage, host)
|
||||
if not page_entries:
|
||||
break
|
||||
entries.extend(page_entries)
|
||||
for e in page_entries:
|
||||
yield e
|
||||
if not self._has_more(webpage):
|
||||
break
|
||||
|
||||
return self.playlist_result(orderedSet(entries), item_id)
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
host = mobj.group('host')
|
||||
item_id = mobj.group('id')
|
||||
|
||||
self._login(host)
|
||||
|
||||
return self.playlist_result(self._entries(url, host, item_id), item_id)
|
||||
|
||||
|
||||
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
|
||||
|
@@ -6,11 +6,12 @@ import re
|
||||
from .srgssr import SRGSSRIE
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
parse_iso8601,
|
||||
unescapeHTML,
|
||||
determine_ext,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
@@ -21,7 +22,7 @@ class RTSIE(SRGSSRIE):
|
||||
_TESTS = [
|
||||
{
|
||||
'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
|
||||
'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
|
||||
'md5': '753b877968ad8afaeddccc374d4256a5',
|
||||
'info_dict': {
|
||||
'id': '3449373',
|
||||
'display_id': 'les-enfants-terribles',
|
||||
@@ -35,6 +36,7 @@ class RTSIE(SRGSSRIE):
|
||||
'thumbnail': r're:^https?://.*\.image',
|
||||
'view_count': int,
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
|
||||
},
|
||||
{
|
||||
'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
|
||||
@@ -63,11 +65,12 @@ class RTSIE(SRGSSRIE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
|
||||
'skip': 'Blocked outside Switzerland',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
|
||||
'md5': '1bae984fe7b1f78e94abc74e802ed99f',
|
||||
'md5': '9bb06503773c07ce83d3cbd793cebb91',
|
||||
'info_dict': {
|
||||
'id': '5745356',
|
||||
'display_id': 'londres-cachee-par-un-epais-smog',
|
||||
@@ -81,6 +84,7 @@ class RTSIE(SRGSSRIE):
|
||||
'thumbnail': r're:^https?://.*\.image',
|
||||
'view_count': int,
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
|
||||
},
|
||||
{
|
||||
'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
|
||||
@@ -160,7 +164,7 @@ class RTSIE(SRGSSRIE):
|
||||
media_type = 'video' if 'video' in all_info else 'audio'
|
||||
|
||||
# check for errors
|
||||
self.get_media_data('rts', media_type, media_id)
|
||||
self._get_media_data('rts', media_type, media_id)
|
||||
|
||||
info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
|
||||
|
||||
@@ -194,6 +198,7 @@ class RTSIE(SRGSSRIE):
|
||||
'tbr': extract_bitrate(format_url),
|
||||
})
|
||||
|
||||
download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
|
||||
for media in info.get('media', []):
|
||||
media_url = media.get('url')
|
||||
if not media_url or re.match(r'https?://', media_url):
|
||||
@@ -205,7 +210,7 @@ class RTSIE(SRGSSRIE):
|
||||
format_id += '-%dk' % rate
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': 'http://download-video.rts.ch/' + media_url,
|
||||
'url': urljoin(download_base, media_url),
|
||||
'tbr': rate or extract_bitrate(media_url),
|
||||
})
|
||||
|
||||
|
100
youtube_dl/extractor/samplefocus.py
Normal file
100
youtube_dl/extractor/samplefocus.py
Normal file
@@ -0,0 +1,100 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
extract_attributes,
|
||||
get_element_by_attribute,
|
||||
int_or_none,
|
||||
)
|
||||
|
||||
|
||||
class SampleFocusIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?samplefocus\.com/samples/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://samplefocus.com/samples/lil-peep-sad-emo-guitar',
|
||||
'md5': '48c8d62d60be467293912e0e619a5120',
|
||||
'info_dict': {
|
||||
'id': '40316',
|
||||
'display_id': 'lil-peep-sad-emo-guitar',
|
||||
'ext': 'mp3',
|
||||
'title': 'Lil Peep Sad Emo Guitar',
|
||||
'thumbnail': r're:^https?://.+\.png',
|
||||
'license': 'Standard License',
|
||||
'uploader': 'CapsCtrl',
|
||||
'uploader_id': 'capsctrl',
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'categories': ['Samples', 'Guitar', 'Electric guitar'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/dababy-style-bass-808',
|
||||
'only_matching': True
|
||||
}, {
|
||||
'url': 'https://samplefocus.com/samples/young-chop-kick',
|
||||
'only_matching': True
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
sample_id = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_id\1[^>]+value=(?:["\'])(?P<id>\d+)',
|
||||
webpage, 'sample id', group='id')
|
||||
|
||||
title = self._og_search_title(webpage, fatal=False) or self._html_search_regex(
|
||||
r'<h1>(.+?)</h1>', webpage, 'title')
|
||||
|
||||
mp3_url = self._search_regex(
|
||||
r'<input[^>]+id=(["\'])sample_mp3\1[^>]+value=(["\'])(?P<url>(?:(?!\2).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url') or extract_attributes(self._search_regex(
|
||||
r'<meta[^>]+itemprop=(["\'])contentUrl\1[^>]*>',
|
||||
webpage, 'mp3 url', group=0))['content']
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage) or self._html_search_regex(
|
||||
r'<img[^>]+class=(?:["\'])waveform responsive-img[^>]+src=(["\'])(?P<url>(?:(?!\1).)+)',
|
||||
webpage, 'mp3', fatal=False, group='url')
|
||||
|
||||
comments = []
|
||||
for author_id, author, body in re.findall(r'(?s)<p[^>]+class="comment-author"><a[^>]+href="/users/([^"]+)">([^"]+)</a>.+?<p[^>]+class="comment-body">([^>]+)</p>', webpage):
|
||||
comments.append({
|
||||
'author': author,
|
||||
'author_id': author_id,
|
||||
'text': body,
|
||||
})
|
||||
|
||||
uploader_id = uploader = None
|
||||
mobj = re.search(r'>By <a[^>]+href="/users/([^"]+)"[^>]*>([^<]+)', webpage)
|
||||
if mobj:
|
||||
uploader_id, uploader = mobj.groups()
|
||||
|
||||
breadcrumb = get_element_by_attribute('typeof', 'BreadcrumbList', webpage)
|
||||
categories = []
|
||||
if breadcrumb:
|
||||
for _, name in re.findall(r'<span[^>]+property=(["\'])name\1[^>]*>([^<]+)', breadcrumb):
|
||||
categories.append(name)
|
||||
|
||||
def extract_count(klass):
|
||||
return int_or_none(self._html_search_regex(
|
||||
r'<span[^>]+class=(?:["\'])?%s-count[^>]*>(\d+)' % klass,
|
||||
webpage, klass, fatal=False))
|
||||
|
||||
return {
|
||||
'id': sample_id,
|
||||
'title': title,
|
||||
'url': mp3_url,
|
||||
'display_id': display_id,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
'license': self._html_search_regex(
|
||||
r'<a[^>]+href=(["\'])/license\1[^>]*>(?P<license>[^<]+)<',
|
||||
webpage, 'license', fatal=False, group='license'),
|
||||
'uploader_id': uploader_id,
|
||||
'like_count': extract_count('sample-%s-favorites' % sample_id),
|
||||
'comment_count': extract_count('comments'),
|
||||
'comments': comments,
|
||||
'categories': categories,
|
||||
}
|
160
youtube_dl/extractor/simplecast.py
Normal file
160
youtube_dl/extractor/simplecast.py
Normal file
@@ -0,0 +1,160 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_podcast_url,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
urlencode_postdata,
|
||||
)
|
||||
|
||||
|
||||
class SimplecastBaseIE(InfoExtractor):
|
||||
_UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
|
||||
_API_BASE = 'https://api.simplecast.com/'
|
||||
|
||||
def _call_api(self, path_tmpl, video_id):
|
||||
return self._download_json(
|
||||
self._API_BASE + path_tmpl % video_id, video_id)
|
||||
|
||||
def _call_search_api(self, resource, resource_id, resource_url):
|
||||
return self._download_json(
|
||||
'https://api.simplecast.com/%ss/search' % resource, resource_id,
|
||||
data=urlencode_postdata({'url': resource_url}))
|
||||
|
||||
def _parse_episode(self, episode):
|
||||
episode_id = episode['id']
|
||||
title = episode['title'].strip()
|
||||
audio_file = episode.get('audio_file') or {}
|
||||
audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
|
||||
|
||||
season = episode.get('season') or {}
|
||||
season_href = season.get('href')
|
||||
season_id = None
|
||||
if season_href:
|
||||
season_id = self._search_regex(
|
||||
r'https?://api.simplecast.com/seasons/(%s)' % self._UUID_REGEX,
|
||||
season_href, 'season id', default=None)
|
||||
|
||||
webpage_url = episode.get('episode_url')
|
||||
channel_url = None
|
||||
if webpage_url:
|
||||
channel_url = self._search_regex(
|
||||
r'(https?://[^/]+\.simplecast\.com)',
|
||||
webpage_url, 'channel url', default=None)
|
||||
|
||||
return {
|
||||
'id': episode_id,
|
||||
'display_id': episode.get('slug'),
|
||||
'title': title,
|
||||
'url': clean_podcast_url(audio_file_url),
|
||||
'webpage_url': webpage_url,
|
||||
'channel_url': channel_url,
|
||||
'series': try_get(episode, lambda x: x['podcast']['title']),
|
||||
'season_number': int_or_none(season.get('number')),
|
||||
'season_id': season_id,
|
||||
'thumbnail': episode.get('image_url'),
|
||||
'episode_id': episode_id,
|
||||
'episode_number': int_or_none(episode.get('number')),
|
||||
'description': strip_or_none(episode.get('description')),
|
||||
'timestamp': parse_iso8601(episode.get('published_at')),
|
||||
'duration': int_or_none(episode.get('duration')),
|
||||
'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
|
||||
}
|
||||
|
||||
|
||||
class SimplecastIE(SimplecastBaseIE):
|
||||
IE_NAME = 'simplecast'
|
||||
_VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
|
||||
_COMMON_TEST_INFO = {
|
||||
'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
|
||||
'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
|
||||
'ext': 'mp3',
|
||||
'title': 'Errant Signal - Chris Franklin & New Wave Video Essays',
|
||||
'episode_number': 1,
|
||||
'episode_id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
|
||||
'description': 'md5:34752789d3d2702e2d2c975fbd14f357',
|
||||
'season_number': 1,
|
||||
'season_id': 'e23df0da-bae4-4531-8bbf-71364a88dc13',
|
||||
'series': 'The RE:BIND.io Podcast',
|
||||
'duration': 5343,
|
||||
'timestamp': 1580979475,
|
||||
'upload_date': '20200206',
|
||||
'webpage_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
|
||||
'channel_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com$',
|
||||
}
|
||||
_TESTS = [{
|
||||
'url': 'https://api.simplecast.com/episodes/b6dc49a2-9404-4853-9aa9-9cfc097be876',
|
||||
'md5': '8c93be7be54251bf29ee97464eabe61c',
|
||||
'info_dict': _COMMON_TEST_INFO,
|
||||
}, {
|
||||
'url': 'https://player.simplecast.com/b6dc49a2-9404-4853-9aa9-9cfc097be876',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'''(?x)<iframe[^>]+src=["\']
|
||||
(
|
||||
https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
|
||||
player\.simplecast\.com/%s
|
||||
))''' % SimplecastBaseIE._UUID_REGEX, webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
episode_id = self._match_id(url)
|
||||
episode = self._call_api('episodes/%s', episode_id)
|
||||
return self._parse_episode(episode)
|
||||
|
||||
|
||||
class SimplecastEpisodeIE(SimplecastBaseIE):
|
||||
IE_NAME = 'simplecast:episode'
|
||||
_VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
|
||||
_TEST = {
|
||||
'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
|
||||
'md5': '8c93be7be54251bf29ee97464eabe61c',
|
||||
'info_dict': SimplecastIE._COMMON_TEST_INFO,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
episode = self._call_search_api(
|
||||
'episode', mobj.group(1), mobj.group(0))
|
||||
return self._parse_episode(episode)
|
||||
|
||||
|
||||
class SimplecastPodcastIE(SimplecastBaseIE):
|
||||
IE_NAME = 'simplecast:podcast'
|
||||
_VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://the-re-bind-io-podcast.simplecast.com',
|
||||
'playlist_mincount': 33,
|
||||
'info_dict': {
|
||||
'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
|
||||
'title': 'The RE:BIND.io Podcast',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
subdomain = self._match_id(url)
|
||||
site = self._call_search_api('site', subdomain, url)
|
||||
podcast = site['podcast']
|
||||
podcast_id = podcast['id']
|
||||
podcast_title = podcast.get('title')
|
||||
|
||||
def entries():
|
||||
episodes = self._call_api('podcasts/%s/episodes', podcast_id)
|
||||
for episode in (episodes.get('collection') or []):
|
||||
info = self._parse_episode(episode)
|
||||
info['series'] = podcast_title
|
||||
yield info
|
||||
|
||||
return self.playlist_result(entries(), podcast_id, podcast_title)
|
@@ -20,9 +20,6 @@ class BellatorIE(MTVServicesInfoExtractor):
|
||||
_FEED_URL = 'http://www.bellator.com/feeds/mrss/'
|
||||
_GEO_COUNTRIES = ['US']
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
return self._extract_triforce_mgid(webpage)
|
||||
|
||||
|
||||
class ParamountNetworkIE(MTVServicesInfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?paramountnetwork\.com/[^/]+/[\da-z]{6}(?:[/?#&]|$)'
|
||||
@@ -46,16 +43,6 @@ class ParamountNetworkIE(MTVServicesInfoExtractor):
|
||||
def _get_feed_query(self, uri):
|
||||
return {
|
||||
'arcEp': 'paramountnetwork.com',
|
||||
'imageEp': 'paramountnetwork.com',
|
||||
'mgid': uri,
|
||||
}
|
||||
|
||||
def _extract_mgid(self, webpage):
|
||||
root_data = self._parse_json(self._search_regex(
|
||||
r'window\.__DATA__\s*=\s*({.+})',
|
||||
webpage, 'data'), None)
|
||||
|
||||
def find_sub_data(data, data_type):
|
||||
return next(c for c in data['children'] if c.get('type') == data_type)
|
||||
|
||||
c = find_sub_data(find_sub_data(root_data, 'MainContainer'), 'VideoPlayer')
|
||||
return c['props']['media']['video']['config']['uri']
|
||||
|
@@ -4,16 +4,32 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_urlparse
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
qualities,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class SRGSSRIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|srgssr):(?P<bu>srf|rts|rsi|rtr|swi):(?:[^:]+:)?(?P<type>video|audio):(?P<id>[0-9a-f\-]{36}|\d+)'
|
||||
_VALID_URL = r'''(?x)
|
||||
(?:
|
||||
https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|
|
||||
srgssr
|
||||
):
|
||||
(?P<bu>
|
||||
srf|rts|rsi|rtr|swi
|
||||
):(?:[^:]+:)?
|
||||
(?P<type>
|
||||
video|audio
|
||||
):
|
||||
(?P<id>
|
||||
[0-9a-f\-]{36}|\d+
|
||||
)
|
||||
'''
|
||||
_GEO_BYPASS = False
|
||||
_GEO_COUNTRIES = ['CH']
|
||||
|
||||
@@ -25,25 +41,39 @@ class SRGSSRIE(InfoExtractor):
|
||||
'LEGAL': 'The video cannot be transmitted for legal reasons.',
|
||||
'STARTDATE': 'This video is not yet available. Please try again later.',
|
||||
}
|
||||
_DEFAULT_LANGUAGE_CODES = {
|
||||
'srf': 'de',
|
||||
'rts': 'fr',
|
||||
'rsi': 'it',
|
||||
'rtr': 'rm',
|
||||
'swi': 'en',
|
||||
}
|
||||
|
||||
def _get_tokenized_src(self, url, video_id, format_id):
|
||||
sp = compat_urllib_parse_urlparse(url).path.split('/')
|
||||
token = self._download_json(
|
||||
'http://tp.srgssr.ch/akahd/token?acl=/%s/%s/*' % (sp[1], sp[2]),
|
||||
'http://tp.srgssr.ch/akahd/token?acl=*',
|
||||
video_id, 'Downloading %s token' % format_id, fatal=False) or {}
|
||||
auth_params = token.get('token', {}).get('authparams')
|
||||
auth_params = try_get(token, lambda x: x['token']['authparams'])
|
||||
if auth_params:
|
||||
url += '?' + auth_params
|
||||
url += ('?' if '?' not in url else '&') + auth_params
|
||||
return url
|
||||
|
||||
def get_media_data(self, bu, media_type, media_id):
|
||||
media_data = self._download_json(
|
||||
'http://il.srgssr.ch/integrationlayer/1.0/ue/%s/%s/play/%s.json' % (bu, media_type, media_id),
|
||||
media_id)[media_type.capitalize()]
|
||||
def _get_media_data(self, bu, media_type, media_id):
|
||||
query = {'onlyChapters': True} if media_type == 'video' else {}
|
||||
full_media_data = self._download_json(
|
||||
'https://il.srgssr.ch/integrationlayer/2.0/%s/mediaComposition/%s/%s.json'
|
||||
% (bu, media_type, media_id),
|
||||
media_id, query=query)['chapterList']
|
||||
try:
|
||||
media_data = next(
|
||||
x for x in full_media_data if x.get('id') == media_id)
|
||||
except StopIteration:
|
||||
raise ExtractorError('No media information found')
|
||||
|
||||
if media_data.get('block') and media_data['block'] in self._ERRORS:
|
||||
message = self._ERRORS[media_data['block']]
|
||||
if media_data['block'] == 'GEOBLOCK':
|
||||
block_reason = media_data.get('blockReason')
|
||||
if block_reason and block_reason in self._ERRORS:
|
||||
message = self._ERRORS[block_reason]
|
||||
if block_reason == 'GEOBLOCK':
|
||||
self.raise_geo_restricted(
|
||||
msg=message, countries=self._GEO_COUNTRIES)
|
||||
raise ExtractorError(
|
||||
@@ -53,53 +83,75 @@ class SRGSSRIE(InfoExtractor):
|
||||
|
||||
def _real_extract(self, url):
|
||||
bu, media_type, media_id = re.match(self._VALID_URL, url).groups()
|
||||
media_data = self._get_media_data(bu, media_type, media_id)
|
||||
title = media_data['title']
|
||||
|
||||
media_data = self.get_media_data(bu, media_type, media_id)
|
||||
|
||||
metadata = media_data['AssetMetadatas']['AssetMetadata'][0]
|
||||
title = metadata['title']
|
||||
description = metadata.get('description')
|
||||
created_date = media_data.get('createdDate') or metadata.get('createdDate')
|
||||
timestamp = parse_iso8601(created_date)
|
||||
|
||||
thumbnails = [{
|
||||
'id': image.get('id'),
|
||||
'url': image['url'],
|
||||
} for image in media_data.get('Image', {}).get('ImageRepresentations', {}).get('ImageRepresentation', [])]
|
||||
|
||||
preference = qualities(['LQ', 'MQ', 'SD', 'HQ', 'HD'])
|
||||
formats = []
|
||||
for source in media_data.get('Playlists', {}).get('Playlist', []) + media_data.get('Downloads', {}).get('Download', []):
|
||||
protocol = source.get('@protocol')
|
||||
for asset in source['url']:
|
||||
asset_url = asset['text']
|
||||
quality = asset['@quality']
|
||||
format_id = '%s-%s' % (protocol, quality)
|
||||
if protocol.startswith('HTTP-HDS') or protocol.startswith('HTTP-HLS'):
|
||||
asset_url = self._get_tokenized_src(asset_url, media_id, format_id)
|
||||
if protocol.startswith('HTTP-HDS'):
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
asset_url + ('?' if '?' not in asset_url else '&') + 'hdcore=3.4.0',
|
||||
media_id, f4m_id=format_id, fatal=False))
|
||||
elif protocol.startswith('HTTP-HLS'):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
asset_url, media_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
else:
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': asset_url,
|
||||
'preference': preference(quality),
|
||||
'ext': 'flv' if protocol == 'RTMP' else None,
|
||||
})
|
||||
q = qualities(['SD', 'HD'])
|
||||
for source in (media_data.get('resourceList') or []):
|
||||
format_url = source.get('url')
|
||||
if not format_url:
|
||||
continue
|
||||
protocol = source.get('protocol')
|
||||
quality = source.get('quality')
|
||||
format_id = []
|
||||
for e in (protocol, source.get('encoding'), quality):
|
||||
if e:
|
||||
format_id.append(e)
|
||||
format_id = '-'.join(format_id)
|
||||
|
||||
if protocol in ('HDS', 'HLS'):
|
||||
if source.get('tokenType') == 'AKAMAI':
|
||||
format_url = self._get_tokenized_src(
|
||||
format_url, media_id, format_id)
|
||||
formats.extend(self._extract_akamai_formats(
|
||||
format_url, media_id))
|
||||
elif protocol == 'HLS':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
format_url, media_id, 'mp4', 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
elif protocol in ('HTTP', 'HTTPS'):
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': format_url,
|
||||
'quality': q(quality),
|
||||
})
|
||||
|
||||
# This is needed because for audio medias the podcast url is usually
|
||||
# always included, even if is only an audio segment and not the
|
||||
# whole episode.
|
||||
if int_or_none(media_data.get('position')) == 0:
|
||||
for p in ('S', 'H'):
|
||||
podcast_url = media_data.get('podcast%sdUrl' % p)
|
||||
if not podcast_url:
|
||||
continue
|
||||
quality = p + 'D'
|
||||
formats.append({
|
||||
'format_id': 'PODCAST-' + quality,
|
||||
'url': podcast_url,
|
||||
'quality': q(quality),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
subtitles = {}
|
||||
if media_type == 'video':
|
||||
for sub in (media_data.get('subtitleList') or []):
|
||||
sub_url = sub.get('url')
|
||||
if not sub_url:
|
||||
continue
|
||||
lang = sub.get('locale') or self._DEFAULT_LANGUAGE_CODES[bu]
|
||||
subtitles.setdefault(lang, []).append({
|
||||
'url': sub_url,
|
||||
})
|
||||
|
||||
return {
|
||||
'id': media_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'timestamp': timestamp,
|
||||
'thumbnails': thumbnails,
|
||||
'description': media_data.get('description'),
|
||||
'timestamp': parse_iso8601(media_data.get('date')),
|
||||
'thumbnail': media_data.get('imageUrl'),
|
||||
'duration': float_or_none(media_data.get('duration'), 1000),
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@@ -119,26 +171,17 @@ class SRGSSRPlayIE(InfoExtractor):
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
|
||||
'md5': 'da6b5b3ac9fa4761a942331cef20fcb3',
|
||||
'md5': '6db2226ba97f62ad42ce09783680046c',
|
||||
'info_dict': {
|
||||
'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20130701',
|
||||
'title': 'Snowden beantragt Asyl in Russland',
|
||||
'timestamp': 1372713995,
|
||||
}
|
||||
}, {
|
||||
# No Speichern (Save) button
|
||||
'url': 'http://www.srf.ch/play/tv/top-gear/video/jaguar-xk120-shadow-und-tornado-dampflokomotive?id=677f5829-e473-4823-ac83-a1087fe97faa',
|
||||
'md5': '0a274ce38fda48c53c01890651985bc6',
|
||||
'info_dict': {
|
||||
'id': '677f5829-e473-4823-ac83-a1087fe97faa',
|
||||
'ext': 'flv',
|
||||
'upload_date': '20130710',
|
||||
'title': 'Jaguar XK120, Shadow und Tornado-Dampflokomotive',
|
||||
'description': 'md5:88604432b60d5a38787f152dec89cd56',
|
||||
'timestamp': 1373493600,
|
||||
'timestamp': 1372708215,
|
||||
'duration': 113.827,
|
||||
'thumbnail': r're:^https?://.*1383719781\.png$',
|
||||
},
|
||||
'expected_warnings': ['Unable to download f4m manifest'],
|
||||
}, {
|
||||
'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
|
||||
'info_dict': {
|
||||
@@ -146,7 +189,8 @@ class SRGSSRPlayIE(InfoExtractor):
|
||||
'ext': 'mp3',
|
||||
'upload_date': '20151013',
|
||||
'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
|
||||
'timestamp': 1444750398,
|
||||
'timestamp': 1444709160,
|
||||
'duration': 336.816,
|
||||
},
|
||||
'params': {
|
||||
# rtmp download
|
||||
@@ -159,19 +203,32 @@ class SRGSSRPlayIE(InfoExtractor):
|
||||
'id': '6348260',
|
||||
'display_id': '6348260',
|
||||
'ext': 'mp4',
|
||||
'duration': 1796,
|
||||
'duration': 1796.76,
|
||||
'title': 'Le 19h30',
|
||||
'description': '',
|
||||
'uploader': '19h30',
|
||||
'upload_date': '20141201',
|
||||
'timestamp': 1417458600,
|
||||
'thumbnail': r're:^https?://.*\.image',
|
||||
'view_count': int,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://play.swissinfo.ch/play/tv/business/video/why-people-were-against-tax-reforms?id=42960270',
|
||||
'info_dict': {
|
||||
'id': '42960270',
|
||||
'ext': 'mp4',
|
||||
'title': 'Why people were against tax reforms',
|
||||
'description': 'md5:7ac442c558e9630e947427469c4b824d',
|
||||
'duration': 94.0,
|
||||
'upload_date': '20170215',
|
||||
'timestamp': 1487173560,
|
||||
'thumbnail': r're:https?://www\.swissinfo\.ch/srgscalableimage/42961964',
|
||||
'subtitles': 'count:9',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
|
||||
'only_matching': True,
|
||||
@@ -181,6 +238,10 @@ class SRGSSRPlayIE(InfoExtractor):
|
||||
}, {
|
||||
'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# audio segment, has podcastSdUrl of the full episode
|
||||
'url': 'https://www.srf.ch/play/radio/popupaudioplayer?id=50b20dc8-f05b-4972-bf03-e438ff2833eb',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -188,5 +249,4 @@ class SRGSSRPlayIE(InfoExtractor):
|
||||
bu = mobj.group('bu')
|
||||
media_type = mobj.group('type') or mobj.group('type_2')
|
||||
media_id = mobj.group('id')
|
||||
# other info can be extracted from url + '&layout=json'
|
||||
return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')
|
||||
|
151
youtube_dl/extractor/storyfire.py
Normal file
151
youtube_dl/extractor/storyfire.py
Normal file
@@ -0,0 +1,151 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import functools
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
# HEADRequest,
|
||||
int_or_none,
|
||||
OnDemandPagedList,
|
||||
smuggle_url,
|
||||
)
|
||||
|
||||
|
||||
class StoryFireBaseIE(InfoExtractor):
|
||||
_VALID_URL_BASE = r'https?://(?:www\.)?storyfire\.com/'
|
||||
|
||||
def _call_api(self, path, video_id, resource, query=None):
|
||||
return self._download_json(
|
||||
'https://storyfire.com/app/%s/%s' % (path, video_id), video_id,
|
||||
'Downloading %s JSON metadata' % resource, query=query)
|
||||
|
||||
def _parse_video(self, video):
|
||||
title = video['title']
|
||||
vimeo_id = self._search_regex(
|
||||
r'https?://player\.vimeo\.com/external/(\d+)',
|
||||
video['vimeoVideoURL'], 'vimeo id')
|
||||
|
||||
# video_url = self._request_webpage(
|
||||
# HEADRequest(video['vimeoVideoURL']), video_id).geturl()
|
||||
# formats = []
|
||||
# for v_url, suffix in [(video_url, '_sep'), (video_url.replace('/sep/video/', '/video/'), '')]:
|
||||
# formats.extend(self._extract_m3u8_formats(
|
||||
# v_url, video_id, 'mp4', 'm3u8_native',
|
||||
# m3u8_id='hls' + suffix, fatal=False))
|
||||
# formats.extend(self._extract_mpd_formats(
|
||||
# v_url.replace('.m3u8', '.mpd'), video_id,
|
||||
# mpd_id='dash' + suffix, fatal=False))
|
||||
# self._sort_formats(formats)
|
||||
|
||||
uploader_id = video.get('hostID')
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': vimeo_id,
|
||||
'title': title,
|
||||
'description': video.get('description'),
|
||||
'url': smuggle_url(
|
||||
'https://player.vimeo.com/video/' + vimeo_id, {
|
||||
'http_headers': {
|
||||
'Referer': 'https://storyfire.com/',
|
||||
}
|
||||
}),
|
||||
# 'formats': formats,
|
||||
'thumbnail': video.get('storyImage'),
|
||||
'view_count': int_or_none(video.get('views')),
|
||||
'like_count': int_or_none(video.get('likesCount')),
|
||||
'comment_count': int_or_none(video.get('commentsCount')),
|
||||
'duration': int_or_none(video.get('videoDuration')),
|
||||
'timestamp': int_or_none(video.get('publishDate')),
|
||||
'uploader': video.get('username'),
|
||||
'uploader_id': uploader_id,
|
||||
'uploader_url': 'https://storyfire.com/user/%s/video' % uploader_id if uploader_id else None,
|
||||
'episode_number': int_or_none(video.get('episodeNumber') or video.get('episode_number')),
|
||||
}
|
||||
|
||||
|
||||
class StoryFireIE(StoryFireBaseIE):
|
||||
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'video-details/(?P<id>[0-9a-f]{24})'
|
||||
_TEST = {
|
||||
'url': 'https://storyfire.com/video-details/5df1d132b6378700117f9181',
|
||||
'md5': 'caec54b9e4621186d6079c7ec100c1eb',
|
||||
'info_dict': {
|
||||
'id': '378954662',
|
||||
'ext': 'mp4',
|
||||
'title': 'Buzzfeed Teaches You About Memes',
|
||||
'uploader_id': 'ntZAJFECERSgqHSxzonV5K2E89s1',
|
||||
'timestamp': 1576129028,
|
||||
'description': 'md5:0b4e28021548e144bed69bb7539e62ea',
|
||||
'uploader': 'whang!',
|
||||
'upload_date': '20191212',
|
||||
'duration': 418,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['Unable to download JSON metadata']
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video = self._call_api(
|
||||
'generic/video-detail', video_id, 'video')['video']
|
||||
return self._parse_video(video)
|
||||
|
||||
|
||||
class StoryFireUserIE(StoryFireBaseIE):
|
||||
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'user/(?P<id>[^/]+)/video'
|
||||
_TEST = {
|
||||
'url': 'https://storyfire.com/user/UQ986nFxmAWIgnkZQ0ftVhq4nOk2/video',
|
||||
'info_dict': {
|
||||
'id': 'UQ986nFxmAWIgnkZQ0ftVhq4nOk2',
|
||||
},
|
||||
'playlist_mincount': 151,
|
||||
}
|
||||
_PAGE_SIZE = 20
|
||||
|
||||
def _fetch_page(self, user_id, page):
|
||||
videos = self._call_api(
|
||||
'publicVideos', user_id, 'page %d' % (page + 1), {
|
||||
'skip': page * self._PAGE_SIZE,
|
||||
})['videos']
|
||||
for video in videos:
|
||||
yield self._parse_video(video)
|
||||
|
||||
def _real_extract(self, url):
|
||||
user_id = self._match_id(url)
|
||||
entries = OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, user_id), self._PAGE_SIZE)
|
||||
return self.playlist_result(entries, user_id)
|
||||
|
||||
|
||||
class StoryFireSeriesIE(StoryFireBaseIE):
|
||||
_VALID_URL = StoryFireBaseIE._VALID_URL_BASE + r'write/series/stories/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://storyfire.com/write/series/stories/-Lq6MsuIHLODO6d2dDkr/',
|
||||
'info_dict': {
|
||||
'id': '-Lq6MsuIHLODO6d2dDkr',
|
||||
},
|
||||
'playlist_mincount': 13,
|
||||
}, {
|
||||
'url': 'https://storyfire.com/write/series/stories/the_mortal_one/',
|
||||
'info_dict': {
|
||||
'id': 'the_mortal_one',
|
||||
},
|
||||
'playlist_count': 0,
|
||||
}]
|
||||
|
||||
def _extract_videos(self, stories):
|
||||
for story in stories.values():
|
||||
if story.get('hasVideo'):
|
||||
yield self._parse_video(story)
|
||||
|
||||
def _real_extract(self, url):
|
||||
series_id = self._match_id(url)
|
||||
stories = self._call_api(
|
||||
'seriesStories', series_id, 'series stories')
|
||||
return self.playlist_result(self._extract_videos(stories), series_id)
|
@@ -1,7 +1,6 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
|
||||
|
||||
class StretchInternetIE(InfoExtractor):
|
||||
@@ -11,22 +10,28 @@ class StretchInternetIE(InfoExtractor):
|
||||
'info_dict': {
|
||||
'id': '573272',
|
||||
'ext': 'mp4',
|
||||
'title': 'University of Mary Wrestling vs. Upper Iowa',
|
||||
'timestamp': 1575668361,
|
||||
'upload_date': '20191206',
|
||||
'title': 'UNIVERSITY OF MARY WRESTLING VS UPPER IOWA',
|
||||
# 'timestamp': 1575668361,
|
||||
# 'upload_date': '20191206',
|
||||
'uploader_id': '99997',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
media_url = self._download_json(
|
||||
'https://core.stretchlive.com/trinity/event/tcg/' + video_id,
|
||||
video_id)[0]['media'][0]['url']
|
||||
event = self._download_json(
|
||||
'https://api.stretchinternet.com/trinity/event/tcg/' + video_id,
|
||||
video_id)[0]
|
||||
'https://neo-client.stretchinternet.com/portal-ws/getEvent.json',
|
||||
video_id, query={'eventID': video_id, 'token': 'asdf'})['event']
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': event['title'],
|
||||
'timestamp': int_or_none(event.get('dateCreated'), 1000),
|
||||
'url': 'https://' + event['media'][0]['url'],
|
||||
# TODO: parse US timezone abbreviations
|
||||
# 'timestamp': event.get('dateTimeString'),
|
||||
'url': 'https://' + media_url,
|
||||
'uploader_id': event.get('ownerID'),
|
||||
}
|
||||
|
@@ -255,8 +255,10 @@ class SVTPlayIE(SVTPlayBaseIE):
|
||||
svt_id = self._search_regex(
|
||||
(r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
|
||||
r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
|
||||
r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)',
|
||||
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"',
|
||||
r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'),
|
||||
r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)',
|
||||
r'["\']svtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)'),
|
||||
webpage, 'video id')
|
||||
|
||||
info_dict = self._extract_by_video_id(svt_id, webpage)
|
||||
|
@@ -1,92 +1,87 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class TF1IE(InfoExtractor):
|
||||
"""TF1 uses the wat.tv player."""
|
||||
_VALID_URL = r'https?://(?:(?:videos|www|lci)\.tf1|(?:www\.)?(?:tfou|ushuaiatv|histoire|tvbreizh))\.fr/(?:[^/]+/)*(?P<id>[^/?#.]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?tf1\.fr/[^/]+/(?P<program_slug>[^/]+)/videos/(?P<id>[^/?&#]+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
|
||||
'info_dict': {
|
||||
'id': '10635995',
|
||||
'ext': 'mp4',
|
||||
'title': 'Citroën Grand C4 Picasso 2013 : présentation officielle',
|
||||
'description': 'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['HTTP Error 404'],
|
||||
}, {
|
||||
'url': 'http://www.tfou.fr/chuggington/videos/le-grand-mysterioso-chuggington-7085291-739.html',
|
||||
'info_dict': {
|
||||
'id': 'le-grand-mysterioso-chuggington-7085291-739',
|
||||
'ext': 'mp4',
|
||||
'title': 'Le grand Mystérioso - Chuggington',
|
||||
'description': 'Le grand Mystérioso - Emery rêve qu\'un article lui soit consacré dans le journal.',
|
||||
'upload_date': '20150103',
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': 'HTTP Error 410: Gone',
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
|
||||
'info_dict': {
|
||||
'id': '13641379',
|
||||
'ext': 'mp4',
|
||||
'title': 'md5:f392bc52245dc5ad43771650c96fb620',
|
||||
'description': 'md5:44bc54f0a21322f5b91d68e76a544eae',
|
||||
'description': 'md5:a02cdb217141fb2d469d6216339b052f',
|
||||
'upload_date': '20190611',
|
||||
'timestamp': 1560273989,
|
||||
'duration': 1738,
|
||||
'series': 'Quotidien avec Yann Barthès',
|
||||
'tags': ['intégrale', 'quotidien', 'Replay'],
|
||||
},
|
||||
'params': {
|
||||
# Sometimes wat serves the whole file with the --test option
|
||||
'skip_download': True,
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
program_slug, slug = re.match(self._VALID_URL, url).groups()
|
||||
video = self._download_json(
|
||||
'https://www.tf1.fr/graphql/web', slug, query={
|
||||
'id': '9b80783950b85247541dd1d851f9cc7fa36574af015621f853ab111a679ce26f',
|
||||
'variables': json.dumps({
|
||||
'programSlug': program_slug,
|
||||
'slug': slug,
|
||||
})
|
||||
})['data']['videoBySlug']
|
||||
wat_id = video['streamId']
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
tags = []
|
||||
for tag in (video.get('tags') or []):
|
||||
label = tag.get('label')
|
||||
if not label:
|
||||
continue
|
||||
tags.append(label)
|
||||
|
||||
wat_id = None
|
||||
decoration = video.get('decoration') or {}
|
||||
|
||||
data = self._parse_json(
|
||||
self._search_regex(
|
||||
r'__APOLLO_STATE__\s*=\s*({.+?})\s*(?:;|</script>)', webpage,
|
||||
'data', default='{}'), video_id, fatal=False)
|
||||
thumbnails = []
|
||||
for source in (try_get(decoration, lambda x: x['image']['sources'], list) or []):
|
||||
source_url = source.get('url')
|
||||
if not source_url:
|
||||
continue
|
||||
thumbnails.append({
|
||||
'url': source_url,
|
||||
'width': int_or_none(source.get('width')),
|
||||
})
|
||||
|
||||
if data:
|
||||
try:
|
||||
wat_id = next(
|
||||
video.get('streamId')
|
||||
for key, video in data.items()
|
||||
if isinstance(video, dict)
|
||||
and video.get('slug') == video_id)
|
||||
if not isinstance(wat_id, compat_str) or not wat_id.isdigit():
|
||||
wat_id = None
|
||||
except StopIteration:
|
||||
pass
|
||||
|
||||
if not wat_id:
|
||||
wat_id = self._html_search_regex(
|
||||
(r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
|
||||
r'(["\']?)streamId\1\s*:\s*(["\']?)(?P<id>\d+)\2'),
|
||||
webpage, 'wat id', group='id')
|
||||
|
||||
return self.url_result('wat:%s' % wat_id, 'Wat')
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'id': wat_id,
|
||||
'url': 'wat:' + wat_id,
|
||||
'title': video.get('title'),
|
||||
'thumbnails': thumbnails,
|
||||
'description': decoration.get('description'),
|
||||
'timestamp': parse_iso8601(video.get('date')),
|
||||
'duration': int_or_none(try_get(video, lambda x: x['publicPlayingInfos']['duration'])),
|
||||
'tags': tags,
|
||||
'series': decoration.get('programLabel'),
|
||||
'season_number': int_or_none(video.get('season')),
|
||||
'episode_number': int_or_none(video.get('episode')),
|
||||
}
|
||||
|
@@ -2,55 +2,110 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .jwplatform import JWPlatformIE
|
||||
from .kaltura import KalturaIE
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
unified_timestamp,
|
||||
)
|
||||
|
||||
|
||||
class TMZIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/?#]+)'
|
||||
_VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/?#&]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tmz.com/videos/0_okj015ty/',
|
||||
'md5': '4d22a51ef205b6c06395d8394f72d560',
|
||||
'info_dict': {
|
||||
'id': '0_okj015ty',
|
||||
'ext': 'mp4',
|
||||
'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!',
|
||||
'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie??? Or is she just showing off her amazing boobs?',
|
||||
'timestamp': 1394747163,
|
||||
'uploader_id': 'batchUser',
|
||||
'upload_date': '20140313',
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.tmz.com/videos/0-cegprt2p/',
|
||||
'md5': '31f9223e20eef55954973359afa61a20',
|
||||
'info_dict': {
|
||||
'id': 'P6YjLBLk',
|
||||
'ext': 'mp4',
|
||||
'title': "No Charges Against Hillary Clinton? Harvey Says It Ain't Over Yet",
|
||||
'description': 'md5:b714359fc18607715ebccbd2da8ff488',
|
||||
'timestamp': 1467831837,
|
||||
'upload_date': '20160706',
|
||||
},
|
||||
'add_ie': [JWPlatformIE.ie_key()],
|
||||
}, {
|
||||
'url': 'http://www.tmz.com/videos/0_okj015ty/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.tmz.com/videos/071119-chris-morgan-women-4590005-0-zcsejvcr/',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.tmz.com/videos/2021-02-19-021921-floyd-mayweather-1043872/',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url).replace('-', '_')
|
||||
return self.url_result('kaltura:591531:%s' % video_id, 'Kaltura', video_id)
|
||||
|
||||
webpage = self._download_webpage(url, video_id, fatal=False)
|
||||
if webpage:
|
||||
tmz_video_id = self._search_regex(
|
||||
r'nodeRef\s*:\s*["\']tmz:video:([\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12})',
|
||||
webpage, 'video id', default=None)
|
||||
video = self._download_json(
|
||||
'https://www.tmz.com/_/video/%s' % tmz_video_id, video_id,
|
||||
fatal=False)
|
||||
if video:
|
||||
message = video['message']
|
||||
info = {
|
||||
'_type': 'url_transparent',
|
||||
'title': message.get('title'),
|
||||
'description': message.get('description'),
|
||||
'timestamp': unified_timestamp(message.get('published_at')),
|
||||
'duration': int_or_none(message.get('duration')),
|
||||
}
|
||||
jwplatform_id = message.get('jwplayer_media_id')
|
||||
if jwplatform_id:
|
||||
info.update({
|
||||
'url': 'jwplatform:%s' % jwplatform_id,
|
||||
'ie_key': JWPlatformIE.ie_key(),
|
||||
})
|
||||
else:
|
||||
kaltura_entry_id = message.get('kaltura_entry_id') or video_id
|
||||
kaltura_partner_id = message.get('kaltura_partner_id') or '591531'
|
||||
info.update({
|
||||
'url': 'kaltura:%s:%s' % (kaltura_partner_id, kaltura_entry_id),
|
||||
'ie_key': KalturaIE.ie_key(),
|
||||
})
|
||||
return info
|
||||
|
||||
return self.url_result(
|
||||
'kaltura:591531:%s' % video_id, KalturaIE.ie_key(), video_id)
|
||||
|
||||
|
||||
class TMZArticleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/]+)/?'
|
||||
_VALID_URL = r'https?://(?:www\.)?tmz\.com/\d{4}/\d{2}/\d{2}/(?P<id>[^/?#&]+)'
|
||||
_TEST = {
|
||||
'url': 'http://www.tmz.com/2015/04/19/bobby-brown-bobbi-kristina-awake-video-concert',
|
||||
'md5': '3316ff838ae5bb7f642537825e1e90d2',
|
||||
'info_dict': {
|
||||
'id': '0_6snoelag',
|
||||
'ext': 'mov',
|
||||
'id': 'PAKZa97W',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bobby Brown Tells Crowd ... Bobbi Kristina is Awake',
|
||||
'description': 'Bobby Brown stunned his audience during a concert Saturday night, when he told the crowd, "Bobbi is awake. She\'s watching me."',
|
||||
'timestamp': 1429467813,
|
||||
'timestamp': 1429466400,
|
||||
'upload_date': '20150419',
|
||||
'uploader_id': 'batchUser',
|
||||
}
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'add_ie': [JWPlatformIE.ie_key()],
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
tmz_url = self._search_regex(
|
||||
r'clickLink\s*\(\s*["\'](?P<url>%s)' % TMZIE._VALID_URL, webpage,
|
||||
'video id', default=None, group='url')
|
||||
if tmz_url:
|
||||
return self.url_result(tmz_url, ie=TMZIE.ie_key())
|
||||
|
||||
embedded_video_info = self._parse_json(self._html_search_regex(
|
||||
r'tmzVideoEmbed\(({.+?})\);', webpage, 'embedded video info'),
|
||||
video_id)
|
||||
|
||||
return self.url_result(
|
||||
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'])
|
||||
'http://www.tmz.com/videos/%s/' % embedded_video_info['id'],
|
||||
ie=TMZIE.ie_key())
|
||||
|
193
youtube_dl/extractor/trovo.py
Normal file
193
youtube_dl/extractor/trovo.py
Normal file
@@ -0,0 +1,193 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
str_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class TrovoBaseIE(InfoExtractor):
|
||||
_VALID_URL_BASE = r'https?://(?:www\.)?trovo\.live/'
|
||||
|
||||
def _extract_streamer_info(self, data):
|
||||
streamer_info = data.get('streamerInfo') or {}
|
||||
username = streamer_info.get('userName')
|
||||
return {
|
||||
'uploader': streamer_info.get('nickName'),
|
||||
'uploader_id': str_or_none(streamer_info.get('uid')),
|
||||
'uploader_url': 'https://trovo.live/' + username if username else None,
|
||||
}
|
||||
|
||||
|
||||
class TrovoIE(TrovoBaseIE):
|
||||
_VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?!(?:clip|video)/)(?P<id>[^/?&#]+)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
username = self._match_id(url)
|
||||
live_info = self._download_json(
|
||||
'https://gql.trovo.live/', username, query={
|
||||
'query': '''{
|
||||
getLiveInfo(params: {userName: "%s"}) {
|
||||
isLive
|
||||
programInfo {
|
||||
coverUrl
|
||||
id
|
||||
streamInfo {
|
||||
desc
|
||||
playUrl
|
||||
}
|
||||
title
|
||||
}
|
||||
streamerInfo {
|
||||
nickName
|
||||
uid
|
||||
userName
|
||||
}
|
||||
}
|
||||
}''' % username,
|
||||
})['data']['getLiveInfo']
|
||||
if live_info.get('isLive') == 0:
|
||||
raise ExtractorError('%s is offline' % username, expected=True)
|
||||
program_info = live_info['programInfo']
|
||||
program_id = program_info['id']
|
||||
title = self._live_title(program_info['title'])
|
||||
|
||||
formats = []
|
||||
for stream_info in (program_info.get('streamInfo') or []):
|
||||
play_url = stream_info.get('playUrl')
|
||||
if not play_url:
|
||||
continue
|
||||
format_id = stream_info.get('desc')
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'height': int_or_none(format_id[:-1]) if format_id else None,
|
||||
'url': play_url,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
info = {
|
||||
'id': program_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': program_info.get('coverUrl'),
|
||||
'is_live': True,
|
||||
}
|
||||
info.update(self._extract_streamer_info(live_info))
|
||||
return info
|
||||
|
||||
|
||||
class TrovoVodIE(TrovoBaseIE):
|
||||
_VALID_URL = TrovoBaseIE._VALID_URL_BASE + r'(?:clip|video)/(?P<id>[^/?&#]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://trovo.live/video/ltv-100095501_100095501_1609596043',
|
||||
'info_dict': {
|
||||
'id': 'ltv-100095501_100095501_1609596043',
|
||||
'ext': 'mp4',
|
||||
'title': 'Spontaner 12 Stunden Stream! - Ok Boomer!',
|
||||
'uploader': 'Exsl',
|
||||
'timestamp': 1609640305,
|
||||
'upload_date': '20210103',
|
||||
'uploader_id': '100095501',
|
||||
'duration': 43977,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
'comments': 'mincount:8',
|
||||
'categories': ['Grand Theft Auto V'],
|
||||
},
|
||||
}, {
|
||||
'url': 'https://trovo.live/clip/lc-5285890810184026005',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
vid = self._match_id(url)
|
||||
resp = self._download_json(
|
||||
'https://gql.trovo.live/', vid, data=json.dumps([{
|
||||
'query': '''{
|
||||
batchGetVodDetailInfo(params: {vids: ["%s"]}) {
|
||||
VodDetailInfos
|
||||
}
|
||||
}''' % vid,
|
||||
}, {
|
||||
'query': '''{
|
||||
getCommentList(params: {appInfo: {postID: "%s"}, pageSize: 1000000000, preview: {}}) {
|
||||
commentList {
|
||||
author {
|
||||
nickName
|
||||
uid
|
||||
}
|
||||
commentID
|
||||
content
|
||||
createdAt
|
||||
parentID
|
||||
}
|
||||
}
|
||||
}''' % vid,
|
||||
}]).encode(), headers={
|
||||
'Content-Type': 'application/json',
|
||||
})
|
||||
vod_detail_info = resp[0]['data']['batchGetVodDetailInfo']['VodDetailInfos'][vid]
|
||||
vod_info = vod_detail_info['vodInfo']
|
||||
title = vod_info['title']
|
||||
|
||||
language = vod_info.get('languageName')
|
||||
formats = []
|
||||
for play_info in (vod_info.get('playInfos') or []):
|
||||
play_url = play_info.get('playUrl')
|
||||
if not play_url:
|
||||
continue
|
||||
format_id = play_info.get('desc')
|
||||
formats.append({
|
||||
'ext': 'mp4',
|
||||
'filesize': int_or_none(play_info.get('fileSize')),
|
||||
'format_id': format_id,
|
||||
'height': int_or_none(format_id[:-1]) if format_id else None,
|
||||
'language': language,
|
||||
'protocol': 'm3u8_native',
|
||||
'tbr': int_or_none(play_info.get('bitrate')),
|
||||
'url': play_url,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
category = vod_info.get('categoryName')
|
||||
get_count = lambda x: int_or_none(vod_info.get(x + 'Num'))
|
||||
|
||||
comment_list = try_get(resp, lambda x: x[1]['data']['getCommentList']['commentList'], list) or []
|
||||
comments = []
|
||||
for comment in comment_list:
|
||||
content = comment.get('content')
|
||||
if not content:
|
||||
continue
|
||||
author = comment.get('author') or {}
|
||||
parent = comment.get('parentID')
|
||||
comments.append({
|
||||
'author': author.get('nickName'),
|
||||
'author_id': str_or_none(author.get('uid')),
|
||||
'id': str_or_none(comment.get('commentID')),
|
||||
'text': content,
|
||||
'timestamp': int_or_none(comment.get('createdAt')),
|
||||
'parent': 'root' if parent == 0 else str_or_none(parent),
|
||||
})
|
||||
|
||||
info = {
|
||||
'id': vid,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': vod_info.get('coverUrl'),
|
||||
'timestamp': int_or_none(vod_info.get('publishTs')),
|
||||
'duration': int_or_none(vod_info.get('duration')),
|
||||
'view_count': get_count('watch'),
|
||||
'like_count': get_count('like'),
|
||||
'comment_count': get_count('comment'),
|
||||
'comments': comments,
|
||||
'categories': [category] if category else None,
|
||||
}
|
||||
info.update(self._extract_streamer_info(vod_detail_info))
|
||||
return info
|
@@ -20,7 +20,7 @@ from ..utils import (
|
||||
|
||||
class TV2IE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.tv2.no/v/916509/',
|
||||
'info_dict': {
|
||||
'id': '916509',
|
||||
@@ -33,7 +33,7 @@ class TV2IE(InfoExtractor):
|
||||
'view_count': int,
|
||||
'categories': list,
|
||||
},
|
||||
}
|
||||
}]
|
||||
_API_DOMAIN = 'sumo.tv2.no'
|
||||
_PROTOCOLS = ('HDS', 'HLS', 'DASH')
|
||||
_GEO_COUNTRIES = ['NO']
|
||||
@@ -42,6 +42,12 @@ class TV2IE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)
|
||||
|
||||
asset = self._download_json(
|
||||
api_base + '.json', video_id,
|
||||
'Downloading metadata JSON')['asset']
|
||||
title = asset.get('subtitle') or asset['title']
|
||||
is_live = asset.get('live') is True
|
||||
|
||||
formats = []
|
||||
format_urls = []
|
||||
for protocol in self._PROTOCOLS:
|
||||
@@ -81,7 +87,8 @@ class TV2IE(InfoExtractor):
|
||||
elif ext == 'm3u8':
|
||||
if not data.get('drmProtected'):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||
video_url, video_id, 'mp4',
|
||||
'm3u8' if is_live else 'm3u8_native',
|
||||
m3u8_id=format_id, fatal=False))
|
||||
elif ext == 'mpd':
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
@@ -99,11 +106,6 @@ class TV2IE(InfoExtractor):
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
self._sort_formats(formats)
|
||||
|
||||
asset = self._download_json(
|
||||
api_base + '.json', video_id,
|
||||
'Downloading metadata JSON')['asset']
|
||||
title = asset['title']
|
||||
|
||||
thumbnails = [{
|
||||
'id': thumbnail.get('@type'),
|
||||
'url': thumbnail.get('url'),
|
||||
@@ -112,7 +114,7 @@ class TV2IE(InfoExtractor):
|
||||
return {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'title': self._live_title(title) if is_live else title,
|
||||
'description': strip_or_none(asset.get('description')),
|
||||
'thumbnails': thumbnails,
|
||||
'timestamp': parse_iso8601(asset.get('createTime')),
|
||||
@@ -120,6 +122,7 @@ class TV2IE(InfoExtractor):
|
||||
'view_count': int_or_none(asset.get('views')),
|
||||
'categories': asset.get('keywords', '').split(','),
|
||||
'formats': formats,
|
||||
'is_live': is_live,
|
||||
}
|
||||
|
||||
|
||||
@@ -168,13 +171,13 @@ class TV2ArticleIE(InfoExtractor):
|
||||
|
||||
|
||||
class KatsomoIE(TV2IE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P<id>\d+)'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
|
||||
'info_dict': {
|
||||
'id': '1181321',
|
||||
'ext': 'mp4',
|
||||
'title': 'MTV Uutiset Live',
|
||||
'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle',
|
||||
'description': 'Päätöksen teki Pelicansin hallitus.',
|
||||
'timestamp': 1575116484,
|
||||
'upload_date': '20191130',
|
||||
@@ -186,7 +189,60 @@ class KatsomoIE(TV2IE):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.mtvuutiset.fi/video/prog1311159',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.katsomo.fi/#!/jakso/1311159',
|
||||
'only_matching': True,
|
||||
}]
|
||||
_API_DOMAIN = 'api.katsomo.fi'
|
||||
_PROTOCOLS = ('HLS', 'MPD')
|
||||
_GEO_COUNTRIES = ['FI']
|
||||
|
||||
|
||||
class MTVUutisetArticleIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384',
|
||||
'info_dict': {
|
||||
'id': '1311159',
|
||||
'ext': 'mp4',
|
||||
'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
|
||||
'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla',
|
||||
'timestamp': 1600608966,
|
||||
'upload_date': '20200920',
|
||||
'duration': 153.7886666,
|
||||
'view_count': int,
|
||||
'categories': list,
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# multiple Youtube embeds
|
||||
'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
article_id = self._match_id(url)
|
||||
article = self._download_json(
|
||||
'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id,
|
||||
article_id)
|
||||
|
||||
def entries():
|
||||
for video in (article.get('videos') or []):
|
||||
video_type = video.get('videotype')
|
||||
video_url = video.get('url')
|
||||
if not (video_url and video_type in ('katsomo', 'youtube')):
|
||||
continue
|
||||
yield self.url_result(
|
||||
video_url, video_type.capitalize(), video.get('video_id'))
|
||||
|
||||
return self.playlist_result(
|
||||
entries(), article_id, article.get('title'), article.get('description'))
|
||||
|
@@ -17,7 +17,7 @@ class TV4IE(InfoExtractor):
|
||||
tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
|
||||
tv4play\.se/
|
||||
(?:
|
||||
(?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)|
|
||||
(?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)|
|
||||
iframe/video/|
|
||||
film/|
|
||||
sport/|
|
||||
@@ -65,6 +65,10 @@ class TV4IE(InfoExtractor):
|
||||
{
|
||||
'url': 'http://www.tv4play.se/program/farang/3922081',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940',
|
||||
'only_matching': True,
|
||||
}
|
||||
]
|
||||
|
||||
|
@@ -21,6 +21,11 @@ class URPlayIE(InfoExtractor):
|
||||
'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
|
||||
'timestamp': 1513292400,
|
||||
'upload_date': '20171214',
|
||||
'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
|
||||
'duration': 2269,
|
||||
'categories': ['Kultur & historia'],
|
||||
'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
|
||||
'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
|
||||
@@ -31,6 +36,10 @@ class URPlayIE(InfoExtractor):
|
||||
'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
|
||||
'timestamp': 1440086400,
|
||||
'upload_date': '20150820',
|
||||
'series': 'Tripp, Trapp, Träd',
|
||||
'duration': 865,
|
||||
'tags': ['Sova'],
|
||||
'episode': 'Sovkudde',
|
||||
},
|
||||
}, {
|
||||
'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
|
||||
@@ -41,9 +50,11 @@ class URPlayIE(InfoExtractor):
|
||||
video_id = self._match_id(url)
|
||||
url = url.replace('skola.se/Produkter', 'play.se/program')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
urplayer_data = self._parse_json(self._html_search_regex(
|
||||
r'data-react-class="components/Player/Player"[^>]+data-react-props="({.+?})"',
|
||||
webpage, 'urplayer data'), video_id)['currentProduct']
|
||||
vid = int(video_id)
|
||||
accessible_episodes = self._parse_json(self._html_search_regex(
|
||||
r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
|
||||
webpage, 'urplayer data'), video_id)['accessibleEpisodes']
|
||||
urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid)
|
||||
episode = urplayer_data['title']
|
||||
raw_streaming_info = urplayer_data['streamingInfo']['raw']
|
||||
host = self._download_json(
|
||||
|
@@ -4,21 +4,22 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
parse_age_limit,
|
||||
qualities,
|
||||
random_birthday,
|
||||
try_get,
|
||||
unified_timestamp,
|
||||
urljoin,
|
||||
)
|
||||
|
||||
|
||||
class VideoPressIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://videopress\.com/embed/(?P<id>[\da-zA-Z]+)'
|
||||
_ID_REGEX = r'[\da-zA-Z]{8}'
|
||||
_PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
|
||||
_VALID_URL = r'https?://%s(?P<id>%s)' % (_PATH_REGEX, _ID_REGEX)
|
||||
_TESTS = [{
|
||||
'url': 'https://videopress.com/embed/kUJmAcSf',
|
||||
'md5': '706956a6c875873d51010921310e4bc6',
|
||||
@@ -36,35 +37,36 @@ class VideoPressIE(InfoExtractor):
|
||||
# 17+, requires birth_* params
|
||||
'url': 'https://videopress.com/embed/iH3gstfZ',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://video.wordpress.com/embed/kUJmAcSf',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _extract_urls(webpage):
|
||||
return re.findall(
|
||||
r'<iframe[^>]+src=["\']((?:https?://)?videopress\.com/embed/[\da-zA-Z]+)',
|
||||
r'<iframe[^>]+src=["\']((?:https?://)?%s%s)' % (VideoPressIE._PATH_REGEX, VideoPressIE._ID_REGEX),
|
||||
webpage)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
query = random_birthday('birth_year', 'birth_month', 'birth_day')
|
||||
query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
|
||||
video = self._download_json(
|
||||
'https://public-api.wordpress.com/rest/v1.1/videos/%s' % video_id,
|
||||
video_id, query=query)
|
||||
|
||||
title = video['title']
|
||||
|
||||
def base_url(scheme):
|
||||
return try_get(
|
||||
video, lambda x: x['file_url_base'][scheme], compat_str)
|
||||
|
||||
base_url = base_url('https') or base_url('http')
|
||||
file_url_base = video.get('file_url_base') or {}
|
||||
base_url = file_url_base.get('https') or file_url_base.get('http')
|
||||
|
||||
QUALITIES = ('std', 'dvd', 'hd')
|
||||
quality = qualities(QUALITIES)
|
||||
|
||||
formats = []
|
||||
for format_id, f in video['files'].items():
|
||||
for format_id, f in (video.get('files') or {}).items():
|
||||
if not isinstance(f, dict):
|
||||
continue
|
||||
for ext, path in f.items():
|
||||
@@ -75,12 +77,14 @@ class VideoPressIE(InfoExtractor):
|
||||
'ext': determine_ext(path, ext),
|
||||
'quality': quality(format_id),
|
||||
})
|
||||
original_url = try_get(video, lambda x: x['original'], compat_str)
|
||||
original_url = video.get('original')
|
||||
if original_url:
|
||||
formats.append({
|
||||
'url': original_url,
|
||||
'format_id': 'original',
|
||||
'quality': len(QUALITIES),
|
||||
'width': int_or_none(video.get('width')),
|
||||
'height': int_or_none(video.get('height')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
|
@@ -4,7 +4,13 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import int_or_none
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
strip_or_none,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class VidioIE(InfoExtractor):
|
||||
@@ -21,57 +27,63 @@ class VidioIE(InfoExtractor):
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 149,
|
||||
'like_count': int,
|
||||
'uploader': 'TWELVE Pic',
|
||||
'timestamp': 1444902800,
|
||||
'upload_date': '20151015',
|
||||
'uploader_id': 'twelvepictures',
|
||||
'channel': 'Cover Music Video',
|
||||
'channel_id': '280236',
|
||||
'view_count': int,
|
||||
'dislike_count': int,
|
||||
'comment_count': int,
|
||||
'tags': 'count:4',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
self._api_key = self._download_json(
|
||||
'https://www.vidio.com/auth', None, data=b'')['api_key']
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id, display_id = mobj.group('id', 'display_id')
|
||||
video_id, display_id = re.match(self._VALID_URL, url).groups()
|
||||
data = self._download_json(
|
||||
'https://api.vidio.com/videos/' + video_id, display_id, headers={
|
||||
'Content-Type': 'application/vnd.api+json',
|
||||
'X-API-KEY': self._api_key,
|
||||
})
|
||||
video = data['videos'][0]
|
||||
title = video['title'].strip()
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
|
||||
m3u8_url, duration, thumbnail = [None] * 3
|
||||
|
||||
clips = self._parse_json(
|
||||
self._html_search_regex(
|
||||
r'data-json-clips\s*=\s*(["\'])(?P<data>\[.+?\])\1',
|
||||
webpage, 'video data', default='[]', group='data'),
|
||||
display_id, fatal=False)
|
||||
if clips:
|
||||
clip = clips[0]
|
||||
m3u8_url = clip.get('sources', [{}])[0].get('file')
|
||||
duration = clip.get('clip_duration')
|
||||
thumbnail = clip.get('image')
|
||||
|
||||
m3u8_url = m3u8_url or self._search_regex(
|
||||
r'data(?:-vjs)?-clip-hls-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
||||
webpage, 'hls url', group='url')
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native')
|
||||
data['clips'][0]['hls_url'], display_id, 'mp4', 'm3u8_native')
|
||||
self._sort_formats(formats)
|
||||
|
||||
duration = int_or_none(duration or self._search_regex(
|
||||
r'data-video-duration=(["\'])(?P<duration>\d+)\1', webpage,
|
||||
'duration', fatal=False, group='duration'))
|
||||
thumbnail = thumbnail or self._og_search_thumbnail(webpage)
|
||||
|
||||
like_count = int_or_none(self._search_regex(
|
||||
(r'<span[^>]+data-comment-vote-count=["\'](\d+)',
|
||||
r'<span[^>]+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'),
|
||||
webpage, 'like count', fatal=False))
|
||||
get_first = lambda x: try_get(data, lambda y: y[x + 's'][0], dict) or {}
|
||||
channel = get_first('channel')
|
||||
user = get_first('user')
|
||||
username = user.get('username')
|
||||
get_count = lambda x: int_or_none(video.get('total_' + x))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'like_count': like_count,
|
||||
'description': strip_or_none(video.get('description')),
|
||||
'thumbnail': video.get('image_url_medium'),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'like_count': get_count('likes'),
|
||||
'formats': formats,
|
||||
'uploader': user.get('name'),
|
||||
'timestamp': parse_iso8601(video.get('created_at')),
|
||||
'uploader_id': username,
|
||||
'uploader_url': 'https://www.vidio.com/@' + username if username else None,
|
||||
'channel': channel.get('name'),
|
||||
'channel_id': str_or_none(channel.get('id')),
|
||||
'view_count': get_count('view_count'),
|
||||
'dislike_count': get_count('dislikes'),
|
||||
'comment_count': get_count('comments'),
|
||||
'tags': video.get('tag_list'),
|
||||
}
|
||||
|
@@ -1,68 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
decode_packed_codes,
|
||||
js_to_json,
|
||||
NO_DEFAULT,
|
||||
PACKED_CODES_RE,
|
||||
)
|
||||
|
||||
|
||||
class VidziIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vidzi\.(?:tv|cc|si|nu)/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
|
||||
_TESTS = [{
|
||||
'url': 'http://vidzi.tv/cghql9yq6emu.html',
|
||||
'md5': '4f16c71ca0c8c8635ab6932b5f3f1660',
|
||||
'info_dict': {
|
||||
'id': 'cghql9yq6emu',
|
||||
'ext': 'mp4',
|
||||
'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭',
|
||||
},
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'http://vidzi.tv/embed-4z2yb0rzphe9-600x338.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://vidzi.cc/cghql9yq6emu.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://vidzi.si/rph9gztxj1et.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://vidzi.nu/cghql9yq6emu.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://vidzi.tv/%s' % video_id, video_id)
|
||||
title = self._html_search_regex(
|
||||
r'(?s)<h2 class="video-title">(.*?)</h2>', webpage, 'title')
|
||||
|
||||
codes = [webpage]
|
||||
codes.extend([
|
||||
decode_packed_codes(mobj.group(0)).replace('\\\'', '\'')
|
||||
for mobj in re.finditer(PACKED_CODES_RE, webpage)])
|
||||
for num, code in enumerate(codes, 1):
|
||||
jwplayer_data = self._parse_json(
|
||||
self._search_regex(
|
||||
r'setup\(([^)]+)\)', code, 'jwplayer data',
|
||||
default=NO_DEFAULT if num == len(codes) else '{}'),
|
||||
video_id, transform_source=lambda s: js_to_json(
|
||||
re.sub(r'\s*\+\s*window\[.+?\]', '', s)))
|
||||
if jwplayer_data:
|
||||
break
|
||||
|
||||
info_dict = self._parse_jwplayer_data(jwplayer_data, video_id, require_title=False)
|
||||
info_dict['title'] = title
|
||||
|
||||
return info_dict
|
@@ -21,6 +21,7 @@ from ..utils import (
|
||||
parse_iso8601,
|
||||
sanitized_Request,
|
||||
std_headers,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
@@ -30,7 +31,7 @@ class VikiBaseIE(InfoExtractor):
|
||||
_API_URL_TEMPLATE = 'https://api.viki.io%s&sig=%s'
|
||||
|
||||
_APP = '100005a'
|
||||
_APP_VERSION = '2.2.5.1428709186'
|
||||
_APP_VERSION = '6.0.0'
|
||||
_APP_SECRET = 'MM_d*yP@`&1@]@!AVrXf_o-HVEnoTnm$O-ti4[G~$JDI/Dc-&piU&z&5.;:}95=Iad'
|
||||
|
||||
_GEO_BYPASS = False
|
||||
@@ -41,7 +42,7 @@ class VikiBaseIE(InfoExtractor):
|
||||
_ERRORS = {
|
||||
'geo': 'Sorry, this content is not available in your region.',
|
||||
'upcoming': 'Sorry, this content is not yet available.',
|
||||
# 'paywall': 'paywall',
|
||||
'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
|
||||
}
|
||||
|
||||
def _prepare_call(self, path, timestamp=None, post_data=None):
|
||||
@@ -62,7 +63,8 @@ class VikiBaseIE(InfoExtractor):
|
||||
|
||||
def _call_api(self, path, video_id, note, timestamp=None, post_data=None):
|
||||
resp = self._download_json(
|
||||
self._prepare_call(path, timestamp, post_data), video_id, note)
|
||||
self._prepare_call(path, timestamp, post_data), video_id, note,
|
||||
headers={'x-viki-app-ver': self._APP_VERSION})
|
||||
|
||||
error = resp.get('error')
|
||||
if error:
|
||||
@@ -82,11 +84,13 @@ class VikiBaseIE(InfoExtractor):
|
||||
expected=True)
|
||||
|
||||
def _check_errors(self, data):
|
||||
for reason, status in data.get('blocking', {}).items():
|
||||
for reason, status in (data.get('blocking') or {}).items():
|
||||
if status and reason in self._ERRORS:
|
||||
message = self._ERRORS[reason]
|
||||
if reason == 'geo':
|
||||
self.raise_geo_restricted(msg=message)
|
||||
elif reason == 'paywall':
|
||||
self.raise_login_required(message)
|
||||
raise ExtractorError('%s said: %s' % (
|
||||
self.IE_NAME, message), expected=True)
|
||||
|
||||
@@ -131,13 +135,19 @@ class VikiIE(VikiBaseIE):
|
||||
'info_dict': {
|
||||
'id': '1023585v',
|
||||
'ext': 'mp4',
|
||||
'title': 'Heirs Episode 14',
|
||||
'uploader': 'SBS',
|
||||
'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
|
||||
'title': 'Heirs - Episode 14',
|
||||
'uploader': 'SBS Contents Hub',
|
||||
'timestamp': 1385047627,
|
||||
'upload_date': '20131121',
|
||||
'age_limit': 13,
|
||||
'duration': 3570,
|
||||
'episode_number': 14,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'skip': 'Blocked in the US',
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}, {
|
||||
# clip
|
||||
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
|
||||
@@ -153,7 +163,8 @@ class VikiIE(VikiBaseIE):
|
||||
'uploader': 'Arirang TV',
|
||||
'like_count': int,
|
||||
'age_limit': 0,
|
||||
}
|
||||
},
|
||||
'skip': 'Sorry. There was an error loading this video',
|
||||
}, {
|
||||
'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
|
||||
'info_dict': {
|
||||
@@ -171,7 +182,7 @@ class VikiIE(VikiBaseIE):
|
||||
}, {
|
||||
# episode
|
||||
'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
|
||||
'md5': '94e0e34fd58f169f40c184f232356cfe',
|
||||
'md5': '0a53dc252e6e690feccd756861495a8c',
|
||||
'info_dict': {
|
||||
'id': '44699v',
|
||||
'ext': 'mp4',
|
||||
@@ -183,6 +194,10 @@ class VikiIE(VikiBaseIE):
|
||||
'uploader': 'group8',
|
||||
'like_count': int,
|
||||
'age_limit': 13,
|
||||
'episode_number': 1,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}, {
|
||||
@@ -209,7 +224,7 @@ class VikiIE(VikiBaseIE):
|
||||
}, {
|
||||
# non-English description
|
||||
'url': 'http://www.viki.com/videos/158036v-love-in-magic',
|
||||
'md5': 'adf9e321a0ae5d0aace349efaaff7691',
|
||||
'md5': '41faaba0de90483fb4848952af7c7d0d',
|
||||
'info_dict': {
|
||||
'id': '158036v',
|
||||
'ext': 'mp4',
|
||||
@@ -220,6 +235,10 @@ class VikiIE(VikiBaseIE):
|
||||
'title': 'Love In Magic',
|
||||
'age_limit': 13,
|
||||
},
|
||||
'params': {
|
||||
'format': 'bestvideo',
|
||||
},
|
||||
'expected_warnings': ['Unknown MIME type image/jpeg in DASH manifest'],
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -229,36 +248,33 @@ class VikiIE(VikiBaseIE):
|
||||
'https://www.viki.com/api/videos/' + video_id,
|
||||
video_id, 'Downloading video JSON', headers={
|
||||
'x-client-user-agent': std_headers['User-Agent'],
|
||||
'x-viki-app-ver': '4.0.57',
|
||||
'x-viki-app-ver': '3.0.0',
|
||||
})
|
||||
video = resp['video']
|
||||
|
||||
self._check_errors(video)
|
||||
|
||||
title = self.dict_selection(video.get('titles', {}), 'en', allow_fallback=False)
|
||||
episode_number = int_or_none(video.get('number'))
|
||||
if not title:
|
||||
title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id
|
||||
container_titles = video.get('container', {}).get('titles', {})
|
||||
title = 'Episode %d' % episode_number if video.get('type') == 'episode' else video.get('id') or video_id
|
||||
container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
|
||||
container_title = self.dict_selection(container_titles, 'en')
|
||||
title = '%s - %s' % (container_title, title)
|
||||
|
||||
description = self.dict_selection(video.get('descriptions', {}), 'en')
|
||||
|
||||
duration = int_or_none(video.get('duration'))
|
||||
timestamp = parse_iso8601(video.get('created_at'))
|
||||
uploader = video.get('author')
|
||||
like_count = int_or_none(video.get('likes', {}).get('count'))
|
||||
age_limit = parse_age_limit(video.get('rating'))
|
||||
like_count = int_or_none(try_get(video, lambda x: x['likes']['count']))
|
||||
|
||||
thumbnails = []
|
||||
for thumbnail_id, thumbnail in video.get('images', {}).items():
|
||||
for thumbnail_id, thumbnail in (video.get('images') or {}).items():
|
||||
thumbnails.append({
|
||||
'id': thumbnail_id,
|
||||
'url': thumbnail.get('url'),
|
||||
})
|
||||
|
||||
subtitles = {}
|
||||
for subtitle_lang, _ in video.get('subtitle_completions', {}).items():
|
||||
for subtitle_lang, _ in (video.get('subtitle_completions') or {}).items():
|
||||
subtitles[subtitle_lang] = [{
|
||||
'ext': subtitles_format,
|
||||
'url': self._prepare_call(
|
||||
@@ -269,13 +285,15 @@ class VikiIE(VikiBaseIE):
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'duration': duration,
|
||||
'timestamp': timestamp,
|
||||
'uploader': uploader,
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'timestamp': parse_iso8601(video.get('created_at')),
|
||||
'uploader': video.get('author'),
|
||||
'uploader_url': video.get('author_url'),
|
||||
'like_count': like_count,
|
||||
'age_limit': age_limit,
|
||||
'age_limit': parse_age_limit(video.get('rating')),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': subtitles,
|
||||
'episode_number': episode_number,
|
||||
}
|
||||
|
||||
formats = []
|
||||
@@ -360,7 +378,7 @@ class VikiChannelIE(VikiBaseIE):
|
||||
'info_dict': {
|
||||
'id': '50c',
|
||||
'title': 'Boys Over Flowers',
|
||||
'description': 'md5:ecd3cff47967fe193cff37c0bec52790',
|
||||
'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
|
||||
},
|
||||
'playlist_mincount': 71,
|
||||
}, {
|
||||
@@ -371,6 +389,7 @@ class VikiChannelIE(VikiBaseIE):
|
||||
'description': 'md5:05bf5471385aa8b21c18ad450e350525',
|
||||
},
|
||||
'playlist_count': 127,
|
||||
'skip': 'Page not found',
|
||||
}, {
|
||||
'url': 'http://www.viki.com/news/24569c-showbiz-korea',
|
||||
'only_matching': True,
|
||||
|
@@ -226,10 +226,12 @@ class VimeoBaseInfoExtractor(InfoExtractor):
|
||||
'is_live': is_live,
|
||||
}
|
||||
|
||||
def _extract_original_format(self, url, video_id):
|
||||
def _extract_original_format(self, url, video_id, unlisted_hash=None):
|
||||
query = {'action': 'load_download_config'}
|
||||
if unlisted_hash:
|
||||
query['unlisted_hash'] = unlisted_hash
|
||||
download_data = self._download_json(
|
||||
url, video_id, fatal=False,
|
||||
query={'action': 'load_download_config'},
|
||||
url, video_id, fatal=False, query=query,
|
||||
headers={'X-Requested-With': 'XMLHttpRequest'})
|
||||
if download_data:
|
||||
source_file = download_data.get('source_file')
|
||||
@@ -509,6 +511,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
{
|
||||
'url': 'https://vimeo.com/160743502/abd0e13fb4',
|
||||
'only_matching': True,
|
||||
},
|
||||
{
|
||||
# requires passing unlisted_hash(a52724358e) to load_download_config request
|
||||
'url': 'https://vimeo.com/392479337/a52724358e',
|
||||
'only_matching': True,
|
||||
}
|
||||
# https://gettingthingsdone.com/workflowmap/
|
||||
# vimeo embed with check-password page protected by Referer header
|
||||
@@ -673,7 +680,8 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
if config.get('view') == 4:
|
||||
config = self._verify_player_video_password(redirect_url, video_id, headers)
|
||||
|
||||
vod = config.get('video', {}).get('vod', {})
|
||||
video = config.get('video') or {}
|
||||
vod = video.get('vod') or {}
|
||||
|
||||
def is_rented():
|
||||
if '>You rented this title.<' in webpage:
|
||||
@@ -733,7 +741,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
|
||||
formats = []
|
||||
|
||||
source_format = self._extract_original_format(
|
||||
'https://vimeo.com/' + video_id, video_id)
|
||||
'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
|
||||
if source_format:
|
||||
formats.append(source_format)
|
||||
|
||||
|
@@ -116,7 +116,7 @@ class VLiveIE(VLiveBaseIE):
|
||||
headers={'Referer': 'https://www.vlive.tv/'}, query=query)
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||
self.raise_login_required(json.loads(e.cause.read().decode())['message'])
|
||||
self.raise_login_required(json.loads(e.cause.read().decode('utf-8'))['message'])
|
||||
raise
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
62
youtube_dl/extractor/vtm.py
Normal file
62
youtube_dl/extractor/vtm.py
Normal file
@@ -0,0 +1,62 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
parse_iso8601,
|
||||
try_get,
|
||||
)
|
||||
|
||||
|
||||
class VTMIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?vtm\.be/([^/?&#]+)~v(?P<id>[0-9a-f]{8}(?:-[0-9a-f]{4}){3}-[0-9a-f]{12})'
|
||||
_TEST = {
|
||||
'url': 'https://vtm.be/gast-vernielt-genkse-hotelkamer~ve7534523-279f-4b4d-a5c9-a33ffdbe23e1',
|
||||
'md5': '37dca85fbc3a33f2de28ceb834b071f8',
|
||||
'info_dict': {
|
||||
'id': '192445',
|
||||
'ext': 'mp4',
|
||||
'title': 'Gast vernielt Genkse hotelkamer',
|
||||
'timestamp': 1611060180,
|
||||
'upload_date': '20210119',
|
||||
'duration': 74,
|
||||
# TODO: fix url _type result processing
|
||||
# 'series': 'Op Interventie',
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
uuid = self._match_id(url)
|
||||
video = self._download_json(
|
||||
'https://omc4vm23offuhaxx6hekxtzspi.appsync-api.eu-west-1.amazonaws.com/graphql',
|
||||
uuid, query={
|
||||
'query': '''{
|
||||
getComponent(type: Video, uuid: "%s") {
|
||||
... on Video {
|
||||
description
|
||||
duration
|
||||
myChannelsVideo
|
||||
program {
|
||||
title
|
||||
}
|
||||
publishedAt
|
||||
title
|
||||
}
|
||||
}
|
||||
}''' % uuid,
|
||||
}, headers={
|
||||
'x-api-key': 'da2-lz2cab4tfnah3mve6wiye4n77e',
|
||||
})['data']['getComponent']
|
||||
|
||||
return {
|
||||
'_type': 'url',
|
||||
'id': uuid,
|
||||
'title': video.get('title'),
|
||||
'url': 'http://mychannels.video/embed/%d' % video['myChannelsVideo'],
|
||||
'description': video.get('description'),
|
||||
'timestamp': parse_iso8601(video.get('publishedAt')),
|
||||
'duration': int_or_none(video.get('duration')),
|
||||
'series': try_get(video, lambda x: x['program']['title']),
|
||||
'ie_key': 'Medialaan',
|
||||
}
|
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from .youtube import YoutubeIE
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
int_or_none,
|
||||
@@ -47,6 +48,22 @@ class VVVVIDIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# video_type == 'video/youtube'
|
||||
'url': 'https://www.vvvvid.it/show/404/one-punch-man/406/486683/trailer',
|
||||
'md5': '33e0edfba720ad73a8782157fdebc648',
|
||||
'info_dict': {
|
||||
'id': 'RzmFKUDOUgw',
|
||||
'ext': 'mp4',
|
||||
'title': 'Trailer',
|
||||
'upload_date': '20150906',
|
||||
'description': 'md5:a5e802558d35247fee285875328c0b80',
|
||||
'uploader_id': 'BandaiVisual',
|
||||
'uploader': 'BANDAI NAMCO Arts Channel',
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048',
|
||||
'only_matching': True
|
||||
@@ -58,12 +75,15 @@ class VVVVIDIE(InfoExtractor):
|
||||
'https://www.vvvvid.it/user/login',
|
||||
None, headers=self.geo_verification_headers())['data']['conn_id']
|
||||
|
||||
def _download_info(self, show_id, path, video_id, fatal=True):
|
||||
def _download_info(self, show_id, path, video_id, fatal=True, query=None):
|
||||
q = {
|
||||
'conn_id': self._conn_id,
|
||||
}
|
||||
if query:
|
||||
q.update(query)
|
||||
response = self._download_json(
|
||||
'https://www.vvvvid.it/vvvvid/ondemand/%s/%s' % (show_id, path),
|
||||
video_id, headers=self.geo_verification_headers(), query={
|
||||
'conn_id': self._conn_id,
|
||||
}, fatal=fatal)
|
||||
video_id, headers=self.geo_verification_headers(), query=q, fatal=fatal)
|
||||
if not (response or fatal):
|
||||
return
|
||||
if response.get('result') == 'error':
|
||||
@@ -81,7 +101,8 @@ class VVVVIDIE(InfoExtractor):
|
||||
show_id, season_id, video_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
response = self._download_info(
|
||||
show_id, 'season/%s' % season_id, video_id)
|
||||
show_id, 'season/%s' % season_id,
|
||||
video_id, query={'video_id': video_id})
|
||||
|
||||
vid = int(video_id)
|
||||
video_data = list(filter(
|
||||
@@ -154,12 +175,13 @@ class VVVVIDIE(InfoExtractor):
|
||||
if season_number:
|
||||
info['season_number'] = int(season_number)
|
||||
|
||||
for quality in ('_sd', ''):
|
||||
video_type = video_data.get('video_type')
|
||||
is_youtube = False
|
||||
for quality in ('', '_sd'):
|
||||
embed_code = video_data.get('embed_info' + quality)
|
||||
if not embed_code:
|
||||
continue
|
||||
embed_code = ds(embed_code)
|
||||
video_type = video_data.get('video_type')
|
||||
if video_type in ('video/rcs', 'video/kenc'):
|
||||
if video_type == 'video/kenc':
|
||||
kenc = self._download_json(
|
||||
@@ -172,19 +194,28 @@ class VVVVIDIE(InfoExtractor):
|
||||
if kenc_message:
|
||||
embed_code += '?' + ds(kenc_message)
|
||||
formats.extend(self._extract_akamai_formats(embed_code, video_id))
|
||||
elif video_type == 'video/youtube':
|
||||
info.update({
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': YoutubeIE.ie_key(),
|
||||
'url': embed_code,
|
||||
})
|
||||
is_youtube = True
|
||||
break
|
||||
else:
|
||||
formats.extend(self._extract_wowza_formats(
|
||||
'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id))
|
||||
metadata_from_url(embed_code)
|
||||
|
||||
self._sort_formats(formats)
|
||||
if not is_youtube:
|
||||
self._sort_formats(formats)
|
||||
info['formats'] = formats
|
||||
|
||||
metadata_from_url(video_data.get('thumbnail'))
|
||||
info.update(self._extract_common_video_info(video_data))
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'duration': int_or_none(video_data.get('length')),
|
||||
'series': video_data.get('show_title'),
|
||||
'season_id': season_id,
|
||||
@@ -220,9 +251,13 @@ class VVVVIDShowIE(VVVVIDIE):
|
||||
show_info = self._download_info(
|
||||
show_id, 'info/', show_title, fatal=False)
|
||||
|
||||
if not show_title:
|
||||
base_url += "/title"
|
||||
|
||||
entries = []
|
||||
for season in (seasons or []):
|
||||
episodes = season.get('episodes') or []
|
||||
playlist_title = season.get('name') or show_info.get('title')
|
||||
for episode in episodes:
|
||||
if episode.get('playable') is False:
|
||||
continue
|
||||
@@ -232,12 +267,13 @@ class VVVVIDShowIE(VVVVIDIE):
|
||||
continue
|
||||
info = self._extract_common_video_info(episode)
|
||||
info.update({
|
||||
'_type': 'url',
|
||||
'_type': 'url_transparent',
|
||||
'ie_key': VVVVIDIE.ie_key(),
|
||||
'url': '/'.join([base_url, season_id, video_id]),
|
||||
'title': episode.get('title'),
|
||||
'description': episode.get('description'),
|
||||
'season_id': season_id,
|
||||
'playlist_title': playlist_title,
|
||||
})
|
||||
entries.append(info)
|
||||
|
||||
|
@@ -1,15 +1,13 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unified_strdate,
|
||||
HEADRequest,
|
||||
int_or_none,
|
||||
try_get,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@@ -32,6 +30,7 @@ class WatIE(InfoExtractor):
|
||||
'skip_download': True,
|
||||
},
|
||||
'expected_warnings': ['HTTP Error 404'],
|
||||
'skip': 'This content is no longer available',
|
||||
},
|
||||
{
|
||||
'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
|
||||
@@ -43,17 +42,10 @@ class WatIE(InfoExtractor):
|
||||
'upload_date': '20140816',
|
||||
},
|
||||
'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
|
||||
'skip': 'This content is no longer available',
|
||||
},
|
||||
]
|
||||
|
||||
_FORMATS = (
|
||||
(200, 416, 234),
|
||||
(400, 480, 270),
|
||||
(600, 640, 360),
|
||||
(1200, 640, 360),
|
||||
(1800, 960, 540),
|
||||
(2500, 1280, 720),
|
||||
)
|
||||
_GEO_BYPASS = False
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@@ -61,97 +53,54 @@ class WatIE(InfoExtractor):
|
||||
|
||||
# 'contentv4' is used in the website, but it also returns the related
|
||||
# videos, we don't need them
|
||||
# video_data = self._download_json(
|
||||
# 'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
|
||||
video_data = self._download_json(
|
||||
'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
|
||||
'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
|
||||
video_id, query={'context': 'MYTF1'})
|
||||
video_info = video_data['media']
|
||||
|
||||
error_desc = video_info.get('error_desc')
|
||||
if error_desc:
|
||||
self.report_warning(
|
||||
'%s returned error: %s' % (self.IE_NAME, error_desc))
|
||||
if video_info.get('error_code') == 'GEOBLOCKED':
|
||||
self.raise_geo_restricted(error_desc, video_info.get('geoList'))
|
||||
raise ExtractorError(error_desc, expected=True)
|
||||
|
||||
chapters = video_info['chapters']
|
||||
if chapters:
|
||||
first_chapter = chapters[0]
|
||||
|
||||
def video_id_for_chapter(chapter):
|
||||
return chapter['tc_start'].split('-')[0]
|
||||
|
||||
if video_id_for_chapter(first_chapter) != video_id:
|
||||
self.to_screen('Multipart video detected')
|
||||
entries = [self.url_result('wat:%s' % video_id_for_chapter(chapter)) for chapter in chapters]
|
||||
return self.playlist_result(entries, video_id, video_info['title'])
|
||||
# Otherwise we can continue and extract just one part, we have to use
|
||||
# the video id for getting the video url
|
||||
else:
|
||||
first_chapter = video_info
|
||||
|
||||
title = first_chapter['title']
|
||||
|
||||
def extract_url(path_template, url_type):
|
||||
req_url = 'http://www.wat.tv/get/%s' % (path_template % video_id)
|
||||
head = self._request_webpage(HEADRequest(req_url), video_id, 'Extracting %s url' % url_type, fatal=False)
|
||||
if head:
|
||||
red_url = head.geturl()
|
||||
if req_url != red_url:
|
||||
return red_url
|
||||
return None
|
||||
|
||||
def remove_bitrate_limit(manifest_url):
|
||||
return re.sub(r'(?:max|min)_bitrate=\d+&?', '', manifest_url)
|
||||
title = video_info['title']
|
||||
|
||||
formats = []
|
||||
try:
|
||||
alt_urls = lambda manifest_url: [re.sub(r'(?:wdv|ssm)?\.ism/', repl + '.ism/', manifest_url) for repl in ('', 'ssm')]
|
||||
manifest_urls = self._download_json(
|
||||
'http://www.wat.tv/get/webhtml/' + video_id, video_id)
|
||||
m3u8_url = manifest_urls.get('hls')
|
||||
if m3u8_url:
|
||||
m3u8_url = remove_bitrate_limit(m3u8_url)
|
||||
for m3u8_alt_url in alt_urls(m3u8_url):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
m3u8_alt_url, video_id, 'mp4',
|
||||
'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
m3u8_alt_url.replace('ios', 'web').replace('.m3u8', '.f4m'),
|
||||
video_id, f4m_id='hds', fatal=False))
|
||||
mpd_url = manifest_urls.get('mpd')
|
||||
if mpd_url:
|
||||
mpd_url = remove_bitrate_limit(mpd_url)
|
||||
for mpd_alt_url in alt_urls(mpd_url):
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
mpd_alt_url, video_id, mpd_id='dash', fatal=False))
|
||||
self._sort_formats(formats)
|
||||
except ExtractorError:
|
||||
abr = 64
|
||||
for vbr, width, height in self._FORMATS:
|
||||
tbr = vbr + abr
|
||||
format_id = 'http-%s' % tbr
|
||||
fmt_url = 'http://dnl.adv.tf1.fr/2/USP-0x0/%s/%s/%s/ssm/%s-%s-64k.mp4' % (video_id[-4:-2], video_id[-2:], video_id, video_id, vbr)
|
||||
if self._is_valid_url(fmt_url, video_id, format_id):
|
||||
formats.append({
|
||||
'format_id': format_id,
|
||||
'url': fmt_url,
|
||||
'vbr': vbr,
|
||||
'abr': abr,
|
||||
'width': width,
|
||||
'height': height,
|
||||
})
|
||||
|
||||
date_diffusion = first_chapter.get('date_diffusion') or video_data.get('configv4', {}).get('estatS4')
|
||||
upload_date = unified_strdate(date_diffusion) if date_diffusion else None
|
||||
duration = None
|
||||
files = video_info['files']
|
||||
if files:
|
||||
duration = int_or_none(files[0].get('duration'))
|
||||
def extract_formats(manifest_urls):
|
||||
for f, f_url in manifest_urls.items():
|
||||
if not f_url:
|
||||
continue
|
||||
if f in ('dash', 'mpd'):
|
||||
formats.extend(self._extract_mpd_formats(
|
||||
f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
|
||||
video_id, mpd_id='dash', fatal=False))
|
||||
elif f == 'hls':
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
f_url, video_id, 'mp4',
|
||||
'm3u8_native', m3u8_id='hls', fatal=False))
|
||||
|
||||
delivery = video_data.get('delivery') or {}
|
||||
extract_formats({delivery.get('format'): delivery.get('url')})
|
||||
if not formats:
|
||||
if delivery.get('drm'):
|
||||
raise ExtractorError('This video is DRM protected.', expected=True)
|
||||
manifest_urls = self._download_json(
|
||||
'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
|
||||
if manifest_urls:
|
||||
extract_formats(manifest_urls)
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'thumbnail': first_chapter.get('preview'),
|
||||
'description': first_chapter.get('description'),
|
||||
'view_count': int_or_none(video_info.get('views')),
|
||||
'upload_date': upload_date,
|
||||
'duration': duration,
|
||||
'thumbnail': video_info.get('preview'),
|
||||
'upload_date': unified_strdate(try_get(
|
||||
video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
|
||||
'duration': int_or_none(video_info.get('duration')),
|
||||
'formats': formats,
|
||||
}
|
||||
|
@@ -1,40 +1,55 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_parse_qs,
|
||||
compat_urllib_parse_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
int_or_none,
|
||||
month_by_abbreviation,
|
||||
parse_filesize,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
class XboxClipsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?xboxclips\.com/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\w-]{36})'
|
||||
_TEST = {
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:xboxclips\.com|gameclips\.io)/(?:video\.php\?.*vid=|[^/]+/)(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
|
||||
_TESTS = [{
|
||||
'url': 'http://xboxclips.com/video.php?uid=2533274823424419&gamertag=Iabdulelah&vid=074a69a9-5faf-46aa-b93b-9909c1720325',
|
||||
'md5': 'fbe1ec805e920aeb8eced3c3e657df5d',
|
||||
'info_dict': {
|
||||
'id': '074a69a9-5faf-46aa-b93b-9909c1720325',
|
||||
'ext': 'mp4',
|
||||
'title': 'Iabdulelah playing Titanfall',
|
||||
'title': 'iAbdulElah playing Titanfall',
|
||||
'filesize_approx': 26800000,
|
||||
'upload_date': '20140807',
|
||||
'duration': 56,
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'https://gameclips.io/iAbdulElah/074a69a9-5faf-46aa-b93b-9909c1720325',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
if '/video.php' in url:
|
||||
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
|
||||
url = 'https://gameclips.io/%s/%s' % (qs['gamertag'][0], qs['vid'][0])
|
||||
|
||||
video_url = self._html_search_regex(
|
||||
r'>(?:Link|Download): <a[^>]+href="([^"]+)"', webpage, 'video URL')
|
||||
title = self._html_search_regex(
|
||||
r'<title>XboxClips \| ([^<]+)</title>', webpage, 'title')
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'>Recorded: ([^<]+)<', webpage, 'upload date', fatal=False))
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
|
||||
|
||||
title = self._html_search_meta(['og:title', 'twitter:title'], webpage)
|
||||
upload_date = None
|
||||
mobj = re.search(
|
||||
r'>Recorded: (\d{2})-(Jan|Feb|Mar|Apr|May|Ju[nl]|Aug|Sep|Oct|Nov|Dec)-(\d{4})',
|
||||
webpage)
|
||||
if mobj:
|
||||
upload_date = '%s%.2d%s' % (mobj.group(3), month_by_abbreviation(mobj.group(2)), mobj.group(1))
|
||||
filesize = parse_filesize(self._html_search_regex(
|
||||
r'>Size: ([^<]+)<', webpage, 'file size', fatal=False))
|
||||
duration = int_or_none(self._html_search_regex(
|
||||
@@ -42,12 +57,12 @@ class XboxClipsIE(InfoExtractor):
|
||||
view_count = int_or_none(self._html_search_regex(
|
||||
r'>Views: (\d+)<', webpage, 'view count', fatal=False))
|
||||
|
||||
return {
|
||||
info.update({
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
'upload_date': upload_date,
|
||||
'filesize_approx': filesize,
|
||||
'duration': duration,
|
||||
'view_count': view_count,
|
||||
}
|
||||
})
|
||||
return info
|
||||
|
@@ -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):
|
||||
|
@@ -177,46 +177,9 @@ class YahooIE(InfoExtractor):
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, country, display_id = re.match(self._VALID_URL, url).groups()
|
||||
if not country:
|
||||
country = 'us'
|
||||
else:
|
||||
country = country.split('-')[0]
|
||||
api_base = 'https://%s.yahoo.com/_td/api/resource/' % country
|
||||
|
||||
for i, uuid in enumerate(['url=' + url, 'ymedia-alias=' + display_id]):
|
||||
content = self._download_json(
|
||||
api_base + 'content;getDetailView=true;uuids=["%s"]' % uuid,
|
||||
display_id, 'Downloading content JSON metadata', fatal=i == 1)
|
||||
if content:
|
||||
item = content['items'][0]
|
||||
break
|
||||
|
||||
if item.get('type') != 'video':
|
||||
entries = []
|
||||
|
||||
cover = item.get('cover') or {}
|
||||
if cover.get('type') == 'yvideo':
|
||||
cover_url = cover.get('url')
|
||||
if cover_url:
|
||||
entries.append(self.url_result(
|
||||
cover_url, 'Yahoo', cover.get('uuid')))
|
||||
|
||||
for e in item.get('body', []):
|
||||
if e.get('type') == 'videoIframe':
|
||||
iframe_url = e.get('url')
|
||||
if not iframe_url:
|
||||
continue
|
||||
entries.append(self.url_result(iframe_url))
|
||||
|
||||
return self.playlist_result(
|
||||
entries, item.get('uuid'),
|
||||
item.get('title'), item.get('summary'))
|
||||
|
||||
video_id = item['uuid']
|
||||
def _extract_yahoo_video(self, video_id, country):
|
||||
video = self._download_json(
|
||||
api_base + 'VideoService.videos;view=full;video_ids=["%s"]' % video_id,
|
||||
'https://%s.yahoo.com/_td/api/resource/VideoService.videos;view=full;video_ids=["%s"]' % (country, video_id),
|
||||
video_id, 'Downloading video JSON metadata')[0]
|
||||
title = video['title']
|
||||
|
||||
@@ -298,7 +261,6 @@ class YahooIE(InfoExtractor):
|
||||
'id': video_id,
|
||||
'title': self._live_title(title) if is_live else title,
|
||||
'formats': formats,
|
||||
'display_id': display_id,
|
||||
'thumbnails': thumbnails,
|
||||
'description': clean_html(video.get('description')),
|
||||
'timestamp': parse_iso8601(video.get('publish_time')),
|
||||
@@ -311,6 +273,44 @@ class YahooIE(InfoExtractor):
|
||||
'episode_number': int_or_none(series_info.get('episode_number')),
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, country, display_id = re.match(self._VALID_URL, url).groups()
|
||||
if not country:
|
||||
country = 'us'
|
||||
else:
|
||||
country = country.split('-')[0]
|
||||
|
||||
item = self._download_json(
|
||||
'https://%s.yahoo.com/caas/content/article' % country, display_id,
|
||||
'Downloading content JSON metadata', query={
|
||||
'url': url
|
||||
})['items'][0]['data']['partnerData']
|
||||
|
||||
if item.get('type') != 'video':
|
||||
entries = []
|
||||
|
||||
cover = item.get('cover') or {}
|
||||
if cover.get('type') == 'yvideo':
|
||||
cover_url = cover.get('url')
|
||||
if cover_url:
|
||||
entries.append(self.url_result(
|
||||
cover_url, 'Yahoo', cover.get('uuid')))
|
||||
|
||||
for e in (item.get('body') or []):
|
||||
if e.get('type') == 'videoIframe':
|
||||
iframe_url = e.get('url')
|
||||
if not iframe_url:
|
||||
continue
|
||||
entries.append(self.url_result(iframe_url))
|
||||
|
||||
return self.playlist_result(
|
||||
entries, item.get('uuid'),
|
||||
item.get('title'), item.get('summary'))
|
||||
|
||||
info = self._extract_yahoo_video(item['uuid'], country)
|
||||
info['display_id'] = display_id
|
||||
return info
|
||||
|
||||
|
||||
class YahooSearchIE(SearchInfoExtractor):
|
||||
IE_DESC = 'Yahoo screen search'
|
||||
|
@@ -1,8 +1,9 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import re
|
||||
import hashlib
|
||||
import itertools
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
@@ -209,17 +210,27 @@ class YandexMusicPlaylistBaseIE(YandexMusicBaseIE):
|
||||
missing_track_ids = [
|
||||
track_id for track_id in track_ids
|
||||
if track_id not in present_track_ids]
|
||||
missing_tracks = self._call_api(
|
||||
'track-entries', tld, url, item_id,
|
||||
'Downloading missing tracks JSON', {
|
||||
'entries': ','.join(missing_track_ids),
|
||||
'lang': tld,
|
||||
'external-domain': 'music.yandex.%s' % tld,
|
||||
'overembed': 'false',
|
||||
'strict': 'true',
|
||||
})
|
||||
if missing_tracks:
|
||||
tracks.extend(missing_tracks)
|
||||
# Request missing tracks in chunks to avoid exceeding max HTTP header size,
|
||||
# see https://github.com/ytdl-org/youtube-dl/issues/27355
|
||||
_TRACKS_PER_CHUNK = 250
|
||||
for chunk_num in itertools.count(0):
|
||||
start = chunk_num * _TRACKS_PER_CHUNK
|
||||
end = start + _TRACKS_PER_CHUNK
|
||||
missing_track_ids_req = missing_track_ids[start:end]
|
||||
assert missing_track_ids_req
|
||||
missing_tracks = self._call_api(
|
||||
'track-entries', tld, url, item_id,
|
||||
'Downloading missing tracks JSON chunk %d' % (chunk_num + 1), {
|
||||
'entries': ','.join(missing_track_ids_req),
|
||||
'lang': tld,
|
||||
'external-domain': 'music.yandex.%s' % tld,
|
||||
'overembed': 'false',
|
||||
'strict': 'true',
|
||||
})
|
||||
if missing_tracks:
|
||||
tracks.extend(missing_tracks)
|
||||
if end >= len(missing_track_ids):
|
||||
break
|
||||
|
||||
return tracks
|
||||
|
||||
|
@@ -25,6 +25,7 @@ class YouPornIE(InfoExtractor):
|
||||
'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
|
||||
'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'duration': 210,
|
||||
'uploader': 'Ask Dan And Jennifer',
|
||||
'upload_date': '20101217',
|
||||
'average_rating': int,
|
||||
@@ -54,6 +55,7 @@ class YouPornIE(InfoExtractor):
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
},
|
||||
'skip': '404',
|
||||
}, {
|
||||
'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
'only_matching': True,
|
||||
@@ -153,6 +155,8 @@ class YouPornIE(InfoExtractor):
|
||||
thumbnail = self._search_regex(
|
||||
r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
|
||||
webpage, 'thumbnail', fatal=False, group='thumbnail')
|
||||
duration = int_or_none(self._html_search_meta(
|
||||
'video:duration', webpage, 'duration', fatal=False))
|
||||
|
||||
uploader = self._html_search_regex(
|
||||
r'(?s)<div[^>]+class=["\']submitByLink["\'][^>]*>(.+?)</div>',
|
||||
@@ -194,6 +198,7 @@ class YouPornIE(InfoExtractor):
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'uploader': uploader,
|
||||
'upload_date': upload_date,
|
||||
'average_rating': average_rating,
|
||||
|
File diff suppressed because it is too large
Load Diff
@@ -7,7 +7,9 @@ from .common import InfoExtractor
|
||||
from ..compat import compat_str
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
NO_DEFAULT,
|
||||
orderedSet,
|
||||
parse_codecs,
|
||||
@@ -21,49 +23,17 @@ from ..utils import (
|
||||
|
||||
|
||||
class ZDFBaseIE(InfoExtractor):
|
||||
def _call_api(self, url, player, referrer, video_id, item):
|
||||
return self._download_json(
|
||||
url, video_id, 'Downloading JSON %s' % item,
|
||||
headers={
|
||||
'Referer': referrer,
|
||||
'Api-Auth': 'Bearer %s' % player['apiToken'],
|
||||
})
|
||||
|
||||
def _extract_player(self, webpage, video_id, fatal=True):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
|
||||
'player JSON', default='{}' if not fatal else NO_DEFAULT,
|
||||
group='json'),
|
||||
video_id)
|
||||
|
||||
|
||||
class ZDFIE(ZDFBaseIE):
|
||||
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?]+)\.html'
|
||||
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
|
||||
_GEO_COUNTRIES = ['DE']
|
||||
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
|
||||
|
||||
_TESTS = [{
|
||||
'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
|
||||
'info_dict': {
|
||||
'id': 'die-magie-der-farben-von-koenigspurpur-und-jeansblau-100',
|
||||
'ext': 'mp4',
|
||||
'title': 'Die Magie der Farben (2/2)',
|
||||
'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
|
||||
'duration': 2615,
|
||||
'timestamp': 1465021200,
|
||||
'upload_date': '20160604',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
def _call_api(self, url, video_id, item, api_token=None, referrer=None):
|
||||
headers = {}
|
||||
if api_token:
|
||||
headers['Api-Auth'] = 'Bearer %s' % api_token
|
||||
if referrer:
|
||||
headers['Referer'] = referrer
|
||||
return self._download_json(
|
||||
url, video_id, 'Downloading JSON %s' % item, headers=headers)
|
||||
|
||||
@staticmethod
|
||||
def _extract_subtitles(src):
|
||||
@@ -109,20 +79,11 @@ class ZDFIE(ZDFBaseIE):
|
||||
})
|
||||
formats.append(f)
|
||||
|
||||
def _extract_entry(self, url, player, content, video_id):
|
||||
title = content.get('title') or content['teaserHeadline']
|
||||
|
||||
t = content['mainVideoContent']['http://zdf.de/rels/target']
|
||||
|
||||
ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
|
||||
|
||||
if not ptmd_path:
|
||||
ptmd_path = t[
|
||||
'http://zdf.de/rels/streams/ptmd-template'].replace(
|
||||
'{playerId}', 'ngplayer_2_4')
|
||||
|
||||
def _extract_ptmd(self, ptmd_url, video_id, api_token, referrer):
|
||||
ptmd = self._call_api(
|
||||
urljoin(url, ptmd_path), player, url, video_id, 'metadata')
|
||||
ptmd_url, video_id, 'metadata', api_token, referrer)
|
||||
|
||||
content_id = ptmd.get('basename') or ptmd_url.split('/')[-1]
|
||||
|
||||
formats = []
|
||||
track_uris = set()
|
||||
@@ -140,7 +101,7 @@ class ZDFIE(ZDFBaseIE):
|
||||
continue
|
||||
for track in tracks:
|
||||
self._extract_format(
|
||||
video_id, formats, track_uris, {
|
||||
content_id, formats, track_uris, {
|
||||
'url': track.get('uri'),
|
||||
'type': f.get('type'),
|
||||
'mimeType': f.get('mimeType'),
|
||||
@@ -149,6 +110,103 @@ class ZDFIE(ZDFBaseIE):
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
duration = float_or_none(try_get(
|
||||
ptmd, lambda x: x['attributes']['duration']['value']), scale=1000)
|
||||
|
||||
return {
|
||||
'extractor_key': ZDFIE.ie_key(),
|
||||
'id': content_id,
|
||||
'duration': duration,
|
||||
'formats': formats,
|
||||
'subtitles': self._extract_subtitles(ptmd),
|
||||
}
|
||||
|
||||
def _extract_player(self, webpage, video_id, fatal=True):
|
||||
return self._parse_json(
|
||||
self._search_regex(
|
||||
r'(?s)data-zdfplayer-jsb=(["\'])(?P<json>{.+?})\1', webpage,
|
||||
'player JSON', default='{}' if not fatal else NO_DEFAULT,
|
||||
group='json'),
|
||||
video_id)
|
||||
|
||||
|
||||
class ZDFIE(ZDFBaseIE):
|
||||
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
|
||||
_TESTS = [{
|
||||
# Same as https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html
|
||||
'url': 'https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html',
|
||||
'md5': '34ec321e7eb34231fd88616c65c92db0',
|
||||
'info_dict': {
|
||||
'id': '210222_phx_nachgehakt_corona_protest',
|
||||
'ext': 'mp4',
|
||||
'title': 'Wohin führt der Protest in der Pandemie?',
|
||||
'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
|
||||
'duration': 1691,
|
||||
'timestamp': 1613948400,
|
||||
'upload_date': '20210221',
|
||||
},
|
||||
}, {
|
||||
# Same as https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html
|
||||
'url': 'https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html',
|
||||
'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
|
||||
'info_dict': {
|
||||
'id': '141007_ab18_10wochensommer_film',
|
||||
'ext': 'mp4',
|
||||
'title': 'Ab 18! - 10 Wochen Sommer',
|
||||
'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
|
||||
'duration': 2660,
|
||||
'timestamp': 1608604200,
|
||||
'upload_date': '20201222',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/dokumentation/terra-x/die-magie-der-farben-von-koenigspurpur-und-jeansblau-100.html',
|
||||
'info_dict': {
|
||||
'id': '151025_magie_farben2_tex',
|
||||
'ext': 'mp4',
|
||||
'title': 'Die Magie der Farben (2/2)',
|
||||
'description': 'md5:a89da10c928c6235401066b60a6d5c1a',
|
||||
'duration': 2615,
|
||||
'timestamp': 1465021200,
|
||||
'upload_date': '20160604',
|
||||
},
|
||||
}, {
|
||||
# Same as https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche
|
||||
'url': 'https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.3sat.de/film/spielfilm/der-hauptmann-100.html
|
||||
'url': 'https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
# Same as https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
|
||||
'url': 'https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/service-und-hilfe/die-neue-zdf-mediathek/zdfmediathek-trailer-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/filme/taunuskrimi/die-lebenden-und-die-toten-1---ein-taunuskrimi-100.html',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'https://www.zdf.de/dokumentation/planet-e/planet-e-uebersichtsseite-weitere-dokumentationen-von-planet-e-100.html',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _extract_entry(self, url, player, content, video_id):
|
||||
title = content.get('title') or content['teaserHeadline']
|
||||
|
||||
t = content['mainVideoContent']['http://zdf.de/rels/target']
|
||||
|
||||
ptmd_path = t.get('http://zdf.de/rels/streams/ptmd')
|
||||
|
||||
if not ptmd_path:
|
||||
ptmd_path = t[
|
||||
'http://zdf.de/rels/streams/ptmd-template'].replace(
|
||||
'{playerId}', 'ngplayer_2_4')
|
||||
|
||||
info = self._extract_ptmd(
|
||||
urljoin(url, ptmd_path), video_id, player['apiToken'], url)
|
||||
|
||||
thumbnails = []
|
||||
layouts = try_get(
|
||||
content, lambda x: x['teaserImageRef']['layouts'], dict)
|
||||
@@ -169,33 +227,33 @@ class ZDFIE(ZDFBaseIE):
|
||||
})
|
||||
thumbnails.append(thumbnail)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
return merge_dicts(info, {
|
||||
'title': title,
|
||||
'description': content.get('leadParagraph') or content.get('teasertext'),
|
||||
'duration': int_or_none(t.get('duration')),
|
||||
'timestamp': unified_timestamp(content.get('editorialDate')),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': self._extract_subtitles(ptmd),
|
||||
'formats': formats,
|
||||
}
|
||||
})
|
||||
|
||||
def _extract_regular(self, url, player, video_id):
|
||||
content = self._call_api(
|
||||
player['content'], player, url, video_id, 'content')
|
||||
player['content'], video_id, 'content', player['apiToken'], url)
|
||||
return self._extract_entry(player['content'], player, content, video_id)
|
||||
|
||||
def _extract_mobile(self, video_id):
|
||||
document = self._download_json(
|
||||
video = self._download_json(
|
||||
'https://zdf-cdn.live.cellular.de/mediathekV2/document/%s' % video_id,
|
||||
video_id)['document']
|
||||
video_id)
|
||||
|
||||
document = video['document']
|
||||
|
||||
title = document['titel']
|
||||
content_id = document['basename']
|
||||
|
||||
formats = []
|
||||
format_urls = set()
|
||||
for f in document['formitaeten']:
|
||||
self._extract_format(video_id, formats, format_urls, f)
|
||||
self._extract_format(content_id, formats, format_urls, f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnails = []
|
||||
@@ -213,12 +271,12 @@ class ZDFIE(ZDFBaseIE):
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'id': content_id,
|
||||
'title': title,
|
||||
'description': document.get('beschreibung'),
|
||||
'duration': int_or_none(document.get('length')),
|
||||
'timestamp': unified_timestamp(try_get(
|
||||
document, lambda x: x['meta']['editorialDate'], compat_str)),
|
||||
'timestamp': unified_timestamp(document.get('date')) or unified_timestamp(
|
||||
try_get(video, lambda x: x['meta']['editorialDate'], compat_str)),
|
||||
'thumbnails': thumbnails,
|
||||
'subtitles': self._extract_subtitles(document),
|
||||
'formats': formats,
|
||||
|
69
youtube_dl/extractor/zhihu.py
Normal file
69
youtube_dl/extractor/zhihu.py
Normal file
@@ -0,0 +1,69 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import float_or_none, int_or_none
|
||||
|
||||
|
||||
class ZhihuIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?zhihu\.com/zvideo/(?P<id>[0-9]+)'
|
||||
_TEST = {
|
||||
'url': 'https://www.zhihu.com/zvideo/1342930761977176064',
|
||||
'md5': 'c8d4c9cd72dd58e6f9bc9c2c84266464',
|
||||
'info_dict': {
|
||||
'id': '1342930761977176064',
|
||||
'ext': 'mp4',
|
||||
'title': '写春联也太难了吧!',
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
'uploader': '桥半舫',
|
||||
'timestamp': 1612959715,
|
||||
'upload_date': '20210210',
|
||||
'uploader_id': '244ecb13b0fd7daf92235288c8ca3365',
|
||||
'duration': 146.333,
|
||||
'view_count': int,
|
||||
'like_count': int,
|
||||
'comment_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
zvideo = self._download_json(
|
||||
'https://www.zhihu.com/api/v4/zvideos/' + video_id, video_id)
|
||||
title = zvideo['title']
|
||||
video = zvideo.get('video') or {}
|
||||
|
||||
formats = []
|
||||
for format_id, q in (video.get('playlist') or {}).items():
|
||||
play_url = q.get('url') or q.get('play_url')
|
||||
if not play_url:
|
||||
continue
|
||||
formats.append({
|
||||
'asr': int_or_none(q.get('sample_rate')),
|
||||
'filesize': int_or_none(q.get('size')),
|
||||
'format_id': format_id,
|
||||
'fps': int_or_none(q.get('fps')),
|
||||
'height': int_or_none(q.get('height')),
|
||||
'tbr': float_or_none(q.get('bitrate')),
|
||||
'url': play_url,
|
||||
'width': int_or_none(q.get('width')),
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
|
||||
author = zvideo.get('author') or {}
|
||||
url_token = author.get('url_token')
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'thumbnail': video.get('thumbnail') or zvideo.get('image_url'),
|
||||
'uploader': author.get('name'),
|
||||
'timestamp': int_or_none(zvideo.get('published_at')),
|
||||
'uploader_id': author.get('id'),
|
||||
'uploader_url': 'https://www.zhihu.com/people/' + url_token if url_token else None,
|
||||
'duration': float_or_none(video.get('duration')),
|
||||
'view_count': int_or_none(zvideo.get('play_count')),
|
||||
'like_count': int_or_none(zvideo.get('liked_count')),
|
||||
'comment_count': int_or_none(zvideo.get('comment_count')),
|
||||
}
|
@@ -87,11 +87,16 @@ class ZypeIE(InfoExtractor):
|
||||
r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
|
||||
body, 'm3u8 url', group='url', default=None)
|
||||
if not m3u8_url:
|
||||
source = self._parse_json(self._search_regex(
|
||||
r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body,
|
||||
'source'), video_id, js_to_json)
|
||||
if source.get('integration') == 'verizon-media':
|
||||
m3u8_url = 'https://content.uplynk.com/%s.m3u8' % source['id']
|
||||
source = self._search_regex(
|
||||
r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source')
|
||||
|
||||
def get_attr(key):
|
||||
return self._search_regex(
|
||||
r'\b%s\s*:\s*([\'"])(?P<val>(?:(?!\1).)+)\1' % key,
|
||||
source, key, group='val')
|
||||
|
||||
if get_attr('integration') == 'verizon-media':
|
||||
m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id')
|
||||
formats = self._extract_m3u8_formats(
|
||||
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
|
||||
text_tracks = self._search_regex(
|
||||
|
@@ -689,6 +689,10 @@ def parseOpts(overrideArguments=None):
|
||||
'-o', '--output',
|
||||
dest='outtmpl', metavar='TEMPLATE',
|
||||
help=('Output filename template, see the "OUTPUT TEMPLATE" for all the info'))
|
||||
filesystem.add_option(
|
||||
'--output-na-placeholder',
|
||||
dest='outtmpl_na_placeholder', metavar='PLACEHOLDER', default='NA',
|
||||
help=('Placeholder value for unavailable meta fields in output filename template (default is "%default")'))
|
||||
filesystem.add_option(
|
||||
'--autonumber-size',
|
||||
dest='autonumber_size', metavar='NUMBER', type=int,
|
||||
@@ -782,7 +786,7 @@ def parseOpts(overrideArguments=None):
|
||||
postproc.add_option(
|
||||
'-x', '--extract-audio',
|
||||
action='store_true', dest='extractaudio', default=False,
|
||||
help='Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)')
|
||||
help='Convert video files to audio-only files (requires ffmpeg/avconv and ffprobe/avprobe)')
|
||||
postproc.add_option(
|
||||
'--audio-format', metavar='FORMAT', dest='audioformat', default='best',
|
||||
help='Specify audio format: "best", "aac", "flac", "mp3", "m4a", "opus", "vorbis", or "wav"; "%default" by default; No effect without -x')
|
||||
|
@@ -89,10 +89,14 @@ class EmbedThumbnailPP(FFmpegPostProcessor):
|
||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||
|
||||
elif info['ext'] in ['m4a', 'mp4']:
|
||||
if not check_executable('AtomicParsley', ['-v']):
|
||||
atomicparsley = next((x
|
||||
for x in ['AtomicParsley', 'atomicparsley']
|
||||
if check_executable(x, ['-v'])), None)
|
||||
|
||||
if atomicparsley is None:
|
||||
raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.')
|
||||
|
||||
cmd = [encodeFilename('AtomicParsley', True),
|
||||
cmd = [encodeFilename(atomicparsley, True),
|
||||
encodeFilename(filename, True),
|
||||
encodeArgument('--artwork'),
|
||||
encodeFilename(thumbnail_filename, True),
|
||||
|
@@ -1,3 +1,3 @@
|
||||
from __future__ import unicode_literals
|
||||
|
||||
__version__ = '2021.01.16'
|
||||
__version__ = '2021.03.02'
|
||||
|
Reference in New Issue
Block a user