1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2026-06-15 00:50:13 +00:00

Compare commits

..

85 Commits

Author SHA1 Message Date
Sergey M․ 3cb1a5dc73 release 2020.12.12 2020-12-12 07:09:59 +07:00
Sergey M․ ed40c02c9b [ChangeLog] Actualize
[ci skip]
2020-12-12 07:04:28 +07:00
Sergey M․ b5fdceb4d1 [ruutu] Extract more metadata and detect non-free videos (closes #21154) 2020-12-12 06:49:43 +07:00
Sergey M․ 1e6f7f3b45 [ruutu] Authenticate format URLs (closes #21031, closes #26782) 2020-12-12 05:57:14 +07:00
Sergey M․ 469ff02f4e [ruutu] Add support for static.nelonenmedia.fi (closes #25412) 2020-12-12 05:10:54 +07:00
Sergey M․ 56f1c5ad38 [ruutu] Extend _VALID_URL (closes #24839) 2020-12-12 05:10:54 +07:00
Remita Amine 3a6b8f4edf [facebook] Add support archived live video URLs(closes #15859) 2020-12-11 23:09:42 +01:00
Sergey M․ 3ae02d4a62 [wdr] Extent subtitles extraction and improve overall extraction (closes #22672, closes #22723) 2020-12-12 04:52:35 +07:00
Remita Amine 59fea63dc2 [facebook] add support for videos attached to Relay based story pages(#10795) 2020-12-11 22:44:18 +01:00
Sergey M․ 22933e02d4 [wdr:page] Add support for kinder.wdr.de (closes #27350) 2020-12-12 04:27:25 +07:00
Remita Amine 98a62d7cbd [facebook] Add another regex for handleServerJS 2020-12-11 21:50:40 +01:00
Remita Amine d6c5fdef34 [facebook] fix embed page extraction 2020-12-11 21:27:47 +01:00
compujo 4b9051cf39 [YoutubeDL] Improve thumbnails' filenames deducing (closes #26010) (#27244) 2020-12-12 03:12:31 +07:00
Remita Amine 00f5068908 [facebook] add support for Relay post pages(closes #26935) 2020-12-11 17:49:22 +01:00
Remita Amine 432c6b0f48 [facebook] proper support for watch videos(closes #22795)(#27062) 2020-12-11 16:05:47 +01:00
Remita Amine ad5e5788ff Revert "[facebook] add support for watch videos(closes #22795)"
This reverts commit dc65041c22.
2020-12-11 15:54:24 +01:00
Remita Amine dc65041c22 [facebook] add support for watch videos(closes #22795) 2020-12-11 13:54:22 +01:00
Remita Amine 9f88b07945 [facebook] add support for group posts with multiple videos(closes #19131) 2020-12-11 12:04:02 +01:00
Remita Amine 225646c4ca [itv] remove old extractio method and fix series metadata extraction
closes #23177
closes #26897
2020-12-10 22:28:44 +01:00
Remita Amine 5c6e9f0b6c [facebook] redirect Mobile URLs to Desktop URLs
closes #24831
closes #25624
2020-12-10 15:19:43 +01:00
Remita Amine 6c370bc149 [facebook] Add support for Relay based pages(closes #26823) 2020-12-10 14:52:35 +01:00
Remita Amine 37fd242342 [facebook] try to reduce unessessary tahoe requests 2020-12-10 12:10:33 +01:00
Remita Amine aee1f87168 [facebook] remove hardcoded chrome user-agent
closes #18974
closes #25411
closes #26958
closes #27329
2020-12-09 23:54:15 +01:00
Andrey Smirnoff b69bb1ed11 [smotri] Remove extractor (#27358) 2020-12-10 02:01:23 +07:00
Sergey M․ 772cefef8c [ChangeLog] Actualize
[ci skip]
2020-12-10 00:12:59 +07:00
谭九鼎 842654b6d0 [README.md] Update travis CI tld (#27354) 2020-12-09 21:50:42 +07:00
Remita Amine df5e50954b [beampro] Remove Extractor
closes #17290
closes #22871
closes #23020
closes #23061
closes #26099
2020-12-09 10:41:08 +01:00
Sergey M․ a4a2fa8754 release 2020.12.09 2020-12-09 04:25:24 +07:00
Sergey M․ 9da0504a09 [ChangeLog] Actualize
[ci skip]
2020-12-09 04:24:31 +07:00
Sergey M․ 470cf496f5 [youtube:tab] Improve identity token extraction (closes #27197) 2020-12-09 04:17:47 +07:00
Sergey M․ e029da9add [youtube:tab] Make click tracking params on continuation optional 2020-12-09 04:06:44 +07:00
Sergey M․ e00b8f60d4 [youtube:tab] Delegate inline playlists to tab-based playlists (closes #27298) 2020-12-09 03:40:02 +07:00
EntranceJew 644c3ef886 [tubitv] Extract release year (#27317) 2020-12-09 01:14:46 +07:00
Soneé John 9d8d0f8b4a [youtube] Remove unused code (#27343) 2020-12-09 00:41:47 +07:00
Sergey M․ 5a1fbbf8b7 [extractor/common] Fix inline HTML5 media tags processing and add test (closes #27345) 2020-12-09 00:05:21 +07:00
Remita Amine e2bdf8bf4f [amcnetworks] Fix free content extraction(closes #20354) 2020-12-08 17:11:28 +01:00
Remita Amine c368dc98e0 [lbry] add support for channel extraction(closes #25584) 2020-12-08 14:53:22 +01:00
Remita Amine e7eff914cd [lbry] add support for short and embed URLs and fix channel metadata extraction 2020-12-08 10:52:52 +01:00
Remita Amine 07333d0062 [telequebec] Fix Extraction and Add Support for video.telequebec.tv
closes #25733
closes #26883
closes #27339
2020-12-08 00:35:47 +01:00
Sergey M․ 5bd7ad2e81 [youtube:tab] Capture and output alerts (closes #27340) 2020-12-08 01:12:00 +07:00
Remita Amine 3ded751985 [generic] comment a test covered now by AmericasTestKitchenIE 2020-12-07 15:27:13 +01:00
Remita Amine 6956db3606 [tvplay:home] Fix extraction(closes #21153) 2020-12-07 15:12:54 +01:00
Remita Amine 17b01228f8 [americastestkitchen] Fix Extraction and add support for Cook's Country and Cook's Illustrated
closes #17234
closes #27322
2020-12-06 23:41:18 +01:00
Sergey M․ 4f1ecca58d [slideslive] Add support for yoda service videos and extract subtitles (closes #27323) 2020-12-07 03:27:21 +07:00
Sergey M․ 2717036489 release 2020.12.07 2020-12-07 02:03:34 +07:00
Sergey M․ d9482c0083 [ChangeLog] Actualize
[ci skip]
2020-12-07 02:01:53 +07:00
Sergey M․ 791b743765 [extractor/generic] Remove unused import 2020-12-07 02:01:47 +07:00
Remita Amine fa604d9083 [aenetworks] Fix extraction
- Fix Fastly format extraction
- Add support for play and watch subdomains
- Extract series metadata

closes #23363
closes #23390
closes #26795
closes #26985
2020-12-06 19:50:05 +01:00
Sergey M․ 2bf0634d16 [youtube] Improve youtu.be extraction in non-existing playlists (closes #27324) 2020-12-07 01:48:10 +07:00
Sergey M․ dccf4932e1 [extractor/common] Extract timestamp from Last-Modified header 2020-12-07 01:15:30 +07:00
Sergey M․ 91dd25fe1e [extractor/common] Add support for dl8-* media tags (closes #27283) 2020-12-07 01:08:22 +07:00
Sergey M․ 06bf2ac20f [extractor/common] Eliminate media tag name regex duplication 2020-12-07 00:56:29 +07:00
Sergey M․ 6ad0d8781e [extractor/common] Fix media type extraction for HTML5 media tags in start/end form 2020-12-07 00:45:16 +07:00
Sergey M․ f2c704e112 [generic] Extract RSS video itunes metadata 2020-12-06 23:08:03 +07:00
Sergey M․ 5e822c2526 [generic] Extract RSS video timestamp 2020-12-06 22:30:30 +07:00
renalid cc017e07ca [generic] Extract RSS video description (#27177) 2020-12-06 22:12:25 +07:00
Remita Amine 082da36416 [nrk] reduce requests for Radio series 2020-12-05 16:24:49 +01:00
Remita Amine 6bf95b15ee [nrk] reduce the number of instalments requests 2020-12-05 15:35:29 +01:00
Remita Amine 4c93b2fd15 [nrk] improve format extraction 2020-12-05 09:13:42 +01:00
Remita Amine 1b26bfd425 [nrk] improve extraction
- improve format extraction for old akamai formats
- update some of the tests
- add is_live value to entry info dict
- request instalments only when their available
- fix skole extraction
2020-12-05 00:40:03 +01:00
Sergey M․ 13ec444a98 [peertube] Extract fps 2020-12-05 04:45:30 +07:00
Sergey M․ 51579d87e4 [peertube] Recognize audio-only formats (closes #27295) 2020-12-05 04:41:33 +07:00
Sergey M․ e147619669 release 2020.12.05 2020-12-05 03:40:00 +07:00
Sergey M․ e7f93fbd85 [ChangeLog] Actualize
[ci skip]
2020-12-05 03:31:07 +07:00
Sergey M․ 58f7ada235 [teachable:course] Improve extraction (closes #24507, closes #27286) 2020-12-05 03:24:56 +07:00
Sergey M․ c67b33888f [nrk] Improve error extraction 2020-12-05 03:00:10 +07:00
Sergey M․ e8c0af04b7 [nrktv] Relax _VALID_URL 2020-12-05 02:46:28 +07:00
Sergey M․ 5d769860c3 [nrktv:series] Improve extraction (closes #21926) 2020-12-05 02:43:33 +07:00
Sergey M․ 02b04785ee [nrktv:series] Improve extraction 2020-12-05 02:21:07 +07:00
Sergey M․ 41c92b8d02 [nrktv:season] Improve extraction 2020-12-05 01:20:14 +07:00
Remita Amine fe0c28f956 [nrk] fix call to moved method 2020-12-04 18:08:08 +01:00
Remita Amine 957c65b9ea [nrk] fix typo 2020-12-04 18:05:27 +01:00
Remita Amine 5e95e18ce9 [nrk] improve format extraction and geo-restriction detection (closes #24221) 2020-12-04 18:04:38 +01:00
Sergey M․ e91df0c550 [pornhub] Handle HTTP errors gracefully (closes #26414) 2020-12-04 23:56:50 +07:00
Sergey M․ c5636e9bca [nrktv] Relax _VALID_URL (closes #27299, closes #26185) 2020-12-04 23:38:42 +07:00
Remita Amine 2e47264235 [zdf] extract webm formats(closes #26659) 2020-12-04 14:16:32 +01:00
Sergey M․ 1c78cb118c [travis] Disable download jobs
Until youtube-dl OSS approval by Travis or moving to GitHub Actions
[ci skip]
2020-12-03 23:25:36 +07:00
Matthew Rayermann beab2f88c9 [nhk] Add audio clip test to NHK extractor (#27269) 2020-12-03 07:47:56 +00:00
Remita Amine 0025447369 [gamespot] Extract DASH and HTTP formats 2020-12-03 00:35:47 +01:00
Remita Amine da4304609d [extractor/commons] improve Akamai HTTP formats extraction 2020-12-03 00:33:55 +01:00
Remita Amine ea89680aea [tver] correct episode_number key 2020-12-02 22:49:51 +01:00
Remita Amine 664dd8ba85 [extractor/common] improve Akamai HTTP format extraction
- Allow m3u8 manifest without an additional audio format
- Fix extraction for qualities starting with a number
Solution provided by @nixxo based on: https://stackoverflow.com/a/5984688
2020-12-02 21:49:09 +01:00
Remita Amine 64554c12e1 [tver] Add new extractor (closes #26662)(closes #27284) 2020-12-02 21:49:09 +01:00
opusforlife2 4ded9c0f00 [pornhub] Add support for pornhub.org (#27276)
Most ISPs block the other two TLDs through deep packet inspection
2020-12-03 01:30:08 +07:00
Remita Amine c0820dd52a [extractors] Add QubIE import 2020-12-02 00:41:21 +01:00
40 changed files with 1702 additions and 1676 deletions
+3 -3
View File
@@ -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 2020.12.02. 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 2020.12.12. 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 **2020.12.02**
- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
- [ ] 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 2020.12.02
[debug] youtube-dl version 2020.12.12
[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 2020.12.02. 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 2020.12.12. 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 **2020.12.02**
- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
- [ ] 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 2020.12.02. 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 2020.12.12. 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 **2020.12.02**
- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
+3 -3
View File
@@ -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 2020.12.02. 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 2020.12.12. 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 **2020.12.02**
- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
- [ ] 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 2020.12.02
[debug] youtube-dl version 2020.12.12
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
+2 -2
View File
@@ -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 2020.12.02. 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 2020.12.12. 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 **2020.12.02**
- [ ] I've verified that I'm running youtube-dl version **2020.12.12**
- [ ] I've searched the bugtracker for similar feature requests including closed ones
+13 -13
View File
@@ -12,29 +12,29 @@ python:
dist: trusty
env:
- YTDL_TEST_SET=core
- YTDL_TEST_SET=download
# - YTDL_TEST_SET=download
jobs:
include:
- python: 3.7
dist: xenial
env: YTDL_TEST_SET=core
- python: 3.7
dist: xenial
env: YTDL_TEST_SET=download
# - python: 3.7
# dist: xenial
# env: YTDL_TEST_SET=download
- python: 3.8
dist: xenial
env: YTDL_TEST_SET=core
- python: 3.8
dist: xenial
env: YTDL_TEST_SET=download
# - python: 3.8
# dist: xenial
# env: YTDL_TEST_SET=download
- python: 3.8-dev
dist: xenial
env: YTDL_TEST_SET=core
- python: 3.8-dev
dist: xenial
env: YTDL_TEST_SET=download
# - python: 3.8-dev
# dist: xenial
# env: YTDL_TEST_SET=download
- env: JYTHON=true; YTDL_TEST_SET=core
- env: JYTHON=true; YTDL_TEST_SET=download
# - env: JYTHON=true; YTDL_TEST_SET=download
- name: flake8
python: 3.8
dist: xenial
@@ -42,9 +42,9 @@ jobs:
script: flake8 .
fast_finish: true
allow_failures:
- env: YTDL_TEST_SET=download
# - env: YTDL_TEST_SET=download
- env: JYTHON=true; YTDL_TEST_SET=core
- env: JYTHON=true; YTDL_TEST_SET=download
# - env: JYTHON=true; YTDL_TEST_SET=download
before_install:
- if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
script: ./devscripts/run_tests.sh
+104
View File
@@ -1,3 +1,107 @@
version 2020.12.12
Core
* [YoutubeDL] Improve thumbnail filename deducing (#26010, #27244)
Extractors
+ [ruutu] Extract more metadata
+ [ruutu] Detect non-free videos (#21154)
* [ruutu] Authenticate format URLs (#21031, #26782)
+ [ruutu] Add support for static.nelonenmedia.fi (#25412)
+ [ruutu] Extend URL regular expression (#24839)
+ [facebook] Add support archived live video URLs (#15859)
* [wdr] Improve overall extraction
+ [wdr] Extend subtitles extraction (#22672, #22723)
+ [facebook] Add support for videos attached to Relay based story pages
(#10795)
+ [wdr:page] Add support for kinder.wdr.de (#27350)
+ [facebook] Add another regular expression for handleServerJS
* [facebook] Fix embed page extraction
+ [facebook] Add support for Relay post pages (#26935)
+ [facebook] Add support for watch videos (#22795, #27062)
+ [facebook] Add support for group posts with multiple videos (#19131)
* [itv] Fix series metadata extraction (#26897)
- [itv] Remove old extraction method (#23177)
* [facebook] Redirect mobile URLs to desktop URLs (#24831, #25624)
+ [facebook] Add support for Relay based pages (#26823)
* [facebook] Try to reduce unnecessary tahoe requests
- [facebook] Remove hardcoded Chrome User-Agent (#18974, #25411, #26958,
#27329)
- [smotri] Remove extractor (#27358)
- [beampro] Remove extractor (#17290, #22871, #23020, #23061, #26099)
version 2020.12.09
Core
* [extractor/common] Fix inline HTML5 media tags processing (#27345)
Extractors
* [youtube:tab] Improve identity token extraction (#27197)
* [youtube:tab] Make click tracking params on continuation optional
* [youtube:tab] Delegate inline playlists to tab-based playlists (27298)
+ [tubitv] Extract release year (#27317)
* [amcnetworks] Fix free content extraction (#20354)
+ [lbry:channel] Add support for channels (#25584)
+ [lbry] Add support for short and embed URLs
* [lbry] Fix channel metadata extraction
+ [telequebec] Add support for video.telequebec.tv (#27339)
* [telequebec] Fix extraction (#25733, #26883)
+ [youtube:tab] Capture and output alerts (#27340)
* [tvplay:home] Fix extraction (#21153)
* [americastestkitchen] Fix Extraction and add support
for Cook's Country and Cook's Illustrated (#17234, #27322)
+ [slideslive] Add support for yoda service videos and extract subtitles
(#27323)
version 2020.12.07
Core
* [extractor/common] Extract timestamp from Last-Modified header
+ [extractor/common] Add support for dl8-* media tags (#27283)
* [extractor/common] Fix media type extraction for HTML5 media tags
in start/end form
Extractors
* [aenetworks] Fix extraction (#23363, #23390, #26795, #26985)
* Fix Fastly format extraction
+ Add support for play and watch subdomains
+ Extract series metadata
* [youtube] Improve youtu.be extraction in non-existing playlists (#27324)
+ [generic] Extract RSS video description, timestamp and itunes metadata
(#27177)
* [nrk] Reduce the number of instalments and episodes requests
* [nrk] Improve extraction
* Improve format extraction for old akamai formats
+ Add is_live value to entry info dict
* Request instalments only when available
* Fix skole extraction
+ [peertube] Extract fps
+ [peertube] Recognize audio-only formats (#27295)
version 2020.12.05
Core
* [extractor/common] Improve Akamai HTTP format extraction
* Allow m3u8 manifest without an additional audio format
* Fix extraction for qualities starting with a number
Extractors
* [teachable:course] Improve extraction (#24507, #27286)
* [nrk] Improve error extraction
* [nrktv:series] Improve extraction (#21926)
* [nrktv:season] Improve extraction
* [nrk] Improve format extraction and geo-restriction detection (#24221)
* [pornhub] Handle HTTP errors gracefully (#26414)
* [nrktv] Relax URL regular expression (#27299, #26185)
+ [zdf] Extract webm formats (#26659)
+ [gamespot] Extract DASH and HTTP formats
+ [tver] Add support for tver.jp (#26662, #27284)
+ [pornhub] Add support for pornhub.org (#27276)
version 2020.12.02
Extractors
+2 -2
View File
@@ -1,4 +1,4 @@
[![Build Status](https://travis-ci.org/ytdl-org/youtube-dl.svg?branch=master)](https://travis-ci.org/ytdl-org/youtube-dl)
[![Build Status](https://travis-ci.com/ytdl-org/youtube-dl.svg?branch=master)](https://travis-ci.com/ytdl-org/youtube-dl)
youtube-dl - download videos from youtube.com or other video platforms
@@ -371,7 +371,7 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
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, smotri, youku)
--video-password PASSWORD Video password (vimeo, youku)
## Adobe Pass Options:
--ap-mso MSO Adobe Pass multiple-system operator (TV
+9 -7
View File
@@ -35,6 +35,8 @@
- **adobetv:video**
- **AdultSwim**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
- **aenetworks:collection**
- **aenetworks:show**
- **afreecatv**: afreecatv.com
- **AirMozilla**
- **AliExpressLive**
@@ -308,6 +310,7 @@
- **FrontendMasters**
- **FrontendMastersCourse**
- **FrontendMastersLesson**
- **FujiTVFODPlus7**
- **Funimation**
- **Funk**
- **Fusion**
@@ -421,7 +424,8 @@
- **la7.it**
- **laola1tv**
- **laola1tv:embed**
- **lbry.tv**
- **lbry**
- **lbry:channel**
- **LCI**
- **Lcp**
- **LcpPlay**
@@ -497,8 +501,6 @@
- **mixcloud**
- **mixcloud:playlist**
- **mixcloud:user**
- **Mixer:live**
- **Mixer:vod**
- **MLB**
- **Mnet**
- **MNetTV**
@@ -710,6 +712,7 @@
- **qqmusic:singer**: QQ音乐 - 歌手
- **qqmusic:toplist**: QQ音乐 - 排行榜
- **QuantumTV**
- **Qub**
- **Quickline**
- **QuicklineLive**
- **R7**
@@ -812,10 +815,6 @@
- **Slideshare**
- **SlidesLive**
- **Slutload**
- **smotri**: Smotri.com
- **smotri:broadcast**: Smotri.com broadcasts
- **smotri:community**: Smotri.com community videos
- **smotri:user**: Smotri.com user videos
- **Snotr**
- **Sohu**
- **SonyLIV**
@@ -896,6 +895,7 @@
- **TeleQuebecEmission**
- **TeleQuebecLive**
- **TeleQuebecSquat**
- **TeleQuebecVideo**
- **TeleTask**
- **Telewebion**
- **TennisTV**
@@ -952,6 +952,7 @@
- **TVANouvellesArticle**
- **TVC**
- **TVCArticle**
- **TVer**
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvland.com**
- **TVN24**
@@ -1161,6 +1162,7 @@
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:tab**: YouTube.com tab
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **YoutubeYtBe**
- **YoutubeYtUser**
- **Zapiks**
- **Zaq1**
+12
View File
@@ -108,6 +108,18 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
def test_parse_html5_media_entries(self):
# inline video tag
expect_dict(
self,
self.ie._parse_html5_media_entries(
'https://127.0.0.1/video.html',
r'<html><video src="/vid.mp4" /></html>', None)[0],
{
'formats': [{
'url': 'https://127.0.0.1/vid.mp4',
}],
})
# from https://www.r18.com/
# with kpbs in label
expect_dict(
+1 -1
View File
@@ -2410,7 +2410,7 @@ class YoutubeDL(object):
thumb_ext = determine_ext(t['url'], 'jpg')
suffix = '_%s' % t['id'] if len(thumbnails) > 1 else ''
thumb_display_id = '%s ' % t['id'] if len(thumbnails) > 1 else ''
t['filename'] = thumb_filename = os.path.splitext(filename)[0] + suffix + '.' + thumb_ext
t['filename'] = thumb_filename = replace_extension(filename + suffix, thumb_ext, info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(thumb_filename)):
self.to_screen('[%s] %s: Thumbnail %sis already present' %
+163 -114
View File
@@ -5,20 +5,30 @@ import re
from .theplatform import ThePlatformIE
from ..utils import (
extract_attributes,
ExtractorError,
int_or_none,
smuggle_url,
update_url_query,
)
from ..compat import (
compat_urlparse,
urlencode_postdata,
)
class AENetworksBaseIE(ThePlatformIE):
_BASE_URL_REGEX = r'''(?x)https?://
(?:(?:www|play|watch)\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/'''
_THEPLATFORM_KEY = 'crazyjava'
_THEPLATFORM_SECRET = 's3cr3t'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
query = {'mbr': 'true'}
@@ -31,7 +41,7 @@ class AENetworksBaseIE(ThePlatformIE):
'assetTypes': 'high_video_s3'
}, {
'assetTypes': 'high_video_s3',
'switch': 'hls_ingest_fastly'
'switch': 'hls_high_fastly',
}]
formats = []
subtitles = {}
@@ -61,20 +71,13 @@ class AENetworksBaseIE(ThePlatformIE):
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?P<domain>
(?:history(?:vault)?|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/
(?:
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
specials/(?P<special_display_id>[^/]+)/(?:full-special|preview-)|
collections/[^/]+/(?P<collection_display_id>[^/]+)
)
'''
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'''(?P<id>
shows/[^/]+/season-\d+/episode-\d+|
(?:
(?:movie|special)s/[^/]+|
(?:shows/[^/]+/)?videos
)/[^/?#&]+
)'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'info_dict': {
@@ -91,22 +94,23 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.history.com/shows/ancient-aliens/season-1',
'info_dict': {
'id': '71889446852',
},
'playlist_mincount': 5,
}, {
'url': 'http://www.mylifetime.com/shows/atlanta-plastic',
'info_dict': {
'id': 'SERIES4317',
'title': 'Atlanta Plastic',
},
'playlist_mincount': 2,
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'only_matching': True
'info_dict': {
'id': '600587331957',
'ext': 'mp4',
'title': 'Inlawful Entry',
'description': 'md5:57c12115a2b384d883fe64ca50529e08',
'timestamp': 1452634428,
'upload_date': '20160112',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
@@ -117,80 +121,152 @@ class AENetworksIE(AENetworksBaseIE):
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
}, {
'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/america-the-story-of-us/westward',
'only_matching': True
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
}]
_DOMAIN_TO_REQUESTOR_ID = {
'history.com': 'HISTORY',
'aetv.com': 'AETV',
'mylifetime.com': 'LIFETIME',
'lifetimemovieclub.com': 'LIFETIMEMOVIECLUB',
'fyi.tv': 'FYI',
}
def _real_extract(self, url):
domain, show_path, movie_display_id, special_display_id, collection_display_id = re.match(self._VALID_URL, url).groups()
display_id = show_path or movie_display_id or special_display_id or collection_display_id
webpage = self._download_webpage(url, display_id, headers=self.geo_verification_headers())
if show_path:
url_parts = show_path.split('/')
url_parts_len = len(url_parts)
if url_parts_len == 1:
entries = []
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
if entries:
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
else:
# single season
url_parts_len = 2
if url_parts_len == 2:
entries = []
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item)
episode_url = compat_urlparse.urljoin(
url, episode_attributes['data-canonical'])
entries.append(self.url_result(
episode_url, 'AENetworks',
episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage))
video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex(
[r"media_url\s*=\s*'(?P<url>[^']+)'",
r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
webpage, 'video url', group='url')
domain, canonical = re.match(self._VALID_URL, url).groups()
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
canonical, query={'filter[canonical]': '/' + canonical})['results'][0]
title = result['title']
video_id = result['id']
media_url = result['publicUrl']
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
auth = None
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._search_json_ld(webpage, video_id, fatal=False))
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
'series': result.get('seriesName'),
'season_number': int_or_none(result.get('tvSeasonNumber')),
'episode_number': int_or_none(result.get('tvSeasonEpisodeNumber')),
})
return info
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}))['data'][resource]
def _real_extract(self, url):
domain, slug = re.match(self._VALID_URL, url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
doc = self._get_doc(item)
canonical = doc.get('canonical')
if not canonical:
continue
entries.append(self.url_result(
base_url + canonical, AENetworksIE.ie_key(), doc.get('id')))
description = None
if self._PLAYLIST_DESCRIPTION_KEY:
description = playlist.get(self._PLAYLIST_DESCRIPTION_KEY)
return self.playlist_result(
entries, playlist.get('id'),
playlist.get(self._PLAYLIST_TITLE_KEY), description)
class AENetworksCollectionIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:collection'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'(?:[^/]+/)*(?:list|collections)/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'https://watch.historyvault.com/list/america-the-story-of-us',
'info_dict': {
'id': '282',
'title': 'America The Story of Us',
},
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
_PLAYLIST_TITLE_KEY = 'display_title'
_PLAYLIST_DESCRIPTION_KEY = None
_FIELDS = '''id
display_title
items {
... on ListVideoItem {
doc {
canonical
id
}
}
}'''
def _get_doc(self, item):
return item.get('doc') or {}
class AENetworksShowIE(AENetworksListBaseIE):
IE_NAME = 'aenetworks:show'
_VALID_URL = AENetworksBaseIE._BASE_URL_REGEX + r'shows/(?P<id>[^/?#&]+)/?(?:[?#&]|$)'
_TESTS = [{
'url': 'http://www.history.com/shows/ancient-aliens',
'info_dict': {
'id': 'SH012427480000',
'title': 'Ancient Aliens',
'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f',
},
'playlist_mincount': 168,
}]
_RESOURCE = 'series'
_ITEMS_KEY = 'episodes'
_PLAYLIST_TITLE_KEY = 'title'
_PLAYLIST_DESCRIPTION_KEY = 'description'
_FIELDS = '''description
id
title
episodes {
canonical
id
}'''
def _get_doc(self, item):
return item
class HistoryTopicIE(AENetworksBaseIE):
IE_NAME = 'history:topic'
IE_DESC = 'History.com Topic'
@@ -204,6 +280,7 @@ class HistoryTopicIE(AENetworksBaseIE):
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
'uploader': 'AENE-NEW',
},
'params': {
# m3u8 download
@@ -212,36 +289,8 @@ class HistoryTopicIE(AENetworksBaseIE):
'add_ie': ['ThePlatform'],
}]
def theplatform_url_result(self, theplatform_url, video_id, query):
return {
'_type': 'url_transparent',
'id': video_id,
'url': smuggle_url(
update_url_query(theplatform_url, query),
{
'sig': {
'key': self._THEPLATFORM_KEY,
'secret': self._THEPLATFORM_SECRET,
},
'force_smil_url': True
}),
'ie_key': 'ThePlatform',
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'<phoenix-iframe[^>]+src="[^"]+\btpid=(\d+)', webpage, 'tpid')
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/history/videos',
video_id, query={'filter[id]': video_id})['results'][0]
title = result['title']
info = self._extract_aen_smil(result['publicUrl'], video_id)
info.update({
'title': title,
'description': result.get('description'),
'duration': int_or_none(result.get('duration')),
'timestamp': int_or_none(result.get('added'), 1000),
})
return info
return self.url_result(
'http://www.history.com/videos/' + display_id,
AENetworksIE.ie_key())
+25 -25
View File
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from ..utils import (
int_or_none,
@@ -11,25 +13,22 @@ from ..utils import (
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
'info_dict': {
'id': 's3MX01Nl4vPH',
'id': '4Lq1dzOnZGt0',
'ext': 'mp4',
'title': 'Maron - Season 4 - Step 1',
'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
'age_limit': 17,
'upload_date': '20160505',
'timestamp': 1462468831,
'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
'upload_date': '20201120',
'timestamp': 1605904350,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Requires TV provider accounts',
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
@@ -55,32 +54,33 @@ class AMCNetworksIE(ThePlatformIE):
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
_REQUESTOR_ID_MAP = {
'amc': 'AMC',
'bbcamerica': 'BBCA',
'ifc': 'IFC',
'sundancetv': 'SUNDANCE',
'wetv': 'WETV',
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
site, display_id = re.match(self._VALID_URL, url).groups()
requestor_id = self._REQUESTOR_ID_MAP[site]
properties = self._download_json(
'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
display_id)['data']['properties']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
media_url = self._search_regex(
r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)',
webpage, 'media url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'link\.theplatform\.com/s/([^?]+)',
media_url, 'theplatform_path'), display_id)
tp_path = 'M_UwQC/media/' + properties['videoPid']
media_url = 'https://link.theplatform.com/s/' + tp_path
theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = try_get(
theplatform_metadata, lambda x: x['ratings'][0]['rating'])
auth_required = self._search_regex(
r'window\.authRequired\s*=\s*(true|false);',
webpage, 'auth required')
if auth_required == 'true':
requestor_id = self._search_regex(
r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)',
webpage, 'requestor id')
if properties.get('videoCategory') == 'TVE-Auth':
resource = self._get_mvpd_resource(
requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(
+26 -42
View File
@@ -1,33 +1,33 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
js_to_json,
try_get,
unified_strdate,
)
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:americastestkitchen|cooks(?:country|illustrated))\.com/(?P<resource_type>episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '5b400b9ee338f922cb06450c',
'title': 'Weeknight Japanese Suppers',
'title': 'Japanese Suppers',
'ext': 'mp4',
'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
'description': 'md5:64e606bfee910627efc4b5f050de92b3',
'thumbnail': r're:^https?://',
'timestamp': 1523664000,
'upload_date': '20180414',
'release_date': '20180414',
'release_date': '20180410',
'series': "America's Test Kitchen",
'season_number': 18,
'episode': 'Weeknight Japanese Suppers',
'episode': 'Japanese Suppers',
'episode_number': 15,
},
'params': {
@@ -36,47 +36,31 @@ class AmericasTestKitchenIE(InfoExtractor):
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}, {
'url': 'https://www.cookscountry.com/episode/564-when-only-chocolate-will-do',
'only_matching': True,
}, {
'url': 'https://www.cooksillustrated.com/videos/4478-beef-wellington',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
resource_type, video_id = re.match(self._VALID_URL, url).groups()
is_episode = resource_type == 'episode'
if is_episode:
resource_type = 'episodes'
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(
self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
webpage, 'initial context'),
video_id, js_to_json)
ep_data = try_get(
video_data,
(lambda x: x['episodeDetail']['content']['data'],
lambda x: x['videoDetail']['content']['data']), dict)
ep_meta = ep_data.get('full_video', {})
zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
title = ep_data.get('title') or ep_meta.get('title')
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
'description') or ep_meta.get('description'))
thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
release_date = unified_strdate(ep_data.get('aired_at'))
season_number = int_or_none(ep_meta.get('season_number'))
episode = ep_meta.get('title')
episode_number = int_or_none(ep_meta.get('episode_number'))
resource = self._download_json(
'https://www.americastestkitchen.com/api/v6/%s/%s' % (resource_type, video_id), video_id)
video = resource['video'] if is_episode else resource
episode = resource if is_episode else resource.get('episode') or {}
return {
'_type': 'url_transparent',
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % video['zypeId'],
'ie_key': 'Zype',
'title': title,
'description': description,
'thumbnail': thumbnail,
'release_date': release_date,
'series': "America's Test Kitchen",
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'description': clean_html(video.get('description')),
'release_date': unified_strdate(video.get('publishDate')),
'series': try_get(episode, lambda x: x['show']['title']),
'episode': episode.get('title'),
}
-194
View File
@@ -1,194 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
compat_str,
float_or_none,
int_or_none,
parse_iso8601,
try_get,
urljoin,
)
class BeamProBaseIE(InfoExtractor):
_API_BASE = 'https://mixer.com/api/v1'
_RATINGS = {'family': 0, 'teen': 13, '18+': 18}
def _extract_channel_info(self, chan):
user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
return {
'uploader': chan.get('token') or try_get(
chan, lambda x: x['user']['username'], compat_str),
'uploader_id': compat_str(user_id) if user_id else None,
'age_limit': self._RATINGS.get(chan.get('audience')),
}
class BeamProLiveIE(BeamProBaseIE):
IE_NAME = 'Mixer:live'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://mixer.com/niterhayven',
'info_dict': {
'id': '261562',
'ext': 'mp4',
'title': 'Introducing The Witcher 3 // The Grind Starts Now!',
'description': 'md5:0b161ac080f15fe05d18a07adb44a74d',
'thumbnail': r're:https://.*\.jpg$',
'timestamp': 1483477281,
'upload_date': '20170103',
'uploader': 'niterhayven',
'uploader_id': '373396',
'age_limit': 18,
'is_live': True,
'view_count': int,
},
'skip': 'niterhayven is offline',
'params': {
'skip_download': True,
},
}
_MANIFEST_URL_TEMPLATE = '%s/channels/%%s/manifest.%%s' % BeamProBaseIE._API_BASE
@classmethod
def suitable(cls, url):
return False if BeamProVodIE.suitable(url) else super(BeamProLiveIE, cls).suitable(url)
def _real_extract(self, url):
channel_name = self._match_id(url)
chan = self._download_json(
'%s/channels/%s' % (self._API_BASE, channel_name), channel_name)
if chan.get('online') is False:
raise ExtractorError(
'{0} is offline'.format(channel_name), expected=True)
channel_id = chan['id']
def manifest_url(kind):
return self._MANIFEST_URL_TEMPLATE % (channel_id, kind)
formats = self._extract_m3u8_formats(
manifest_url('m3u8'), channel_name, ext='mp4', m3u8_id='hls',
fatal=False)
formats.extend(self._extract_smil_formats(
manifest_url('smil'), channel_name, fatal=False))
self._sort_formats(formats)
info = {
'id': compat_str(chan.get('id') or channel_name),
'title': self._live_title(chan.get('name') or channel_name),
'description': clean_html(chan.get('description')),
'thumbnail': try_get(
chan, lambda x: x['thumbnail']['url'], compat_str),
'timestamp': parse_iso8601(chan.get('updatedAt')),
'is_live': True,
'view_count': int_or_none(chan.get('viewersTotal')),
'formats': formats,
}
info.update(self._extract_channel_info(chan))
return info
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>[^?#&]+)'
_TESTS = [{
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
'info_dict': {
'id': '2259830',
'ext': 'mp4',
'title': 'willow8714\'s Channel',
'duration': 6828.15,
'thumbnail': r're:https://.*source\.png$',
'timestamp': 1494046474,
'upload_date': '20170506',
'uploader': 'willow8714',
'uploader_id': '6085379',
'age_limit': 13,
'view_count': int,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://mixer.com/streamer?vod=IxFno1rqC0S_XJ1a2yGgNw',
'only_matching': True,
}, {
'url': 'https://mixer.com/streamer?vod=Rh3LY0VAqkGpEQUe2pN-ig',
'only_matching': True,
}]
@staticmethod
def _extract_format(vod, vod_type):
if not vod.get('baseUrl'):
return []
if vod_type == 'hls':
filename, protocol = 'manifest.m3u8', 'm3u8_native'
elif vod_type == 'raw':
filename, protocol = 'source.mp4', 'https'
else:
assert False
data = vod.get('data') if isinstance(vod.get('data'), dict) else {}
format_id = [vod_type]
if isinstance(data.get('Height'), compat_str):
format_id.append('%sp' % data['Height'])
return [{
'url': urljoin(vod['baseUrl'], filename),
'format_id': '-'.join(format_id),
'ext': 'mp4',
'protocol': protocol,
'width': int_or_none(data.get('Width')),
'height': int_or_none(data.get('Height')),
'fps': int_or_none(data.get('Fps')),
'tbr': int_or_none(data.get('Bitrate'), 1000),
}]
def _real_extract(self, url):
vod_id = self._match_id(url)
vod_info = self._download_json(
'%s/recordings/%s' % (self._API_BASE, vod_id), vod_id)
state = vod_info.get('state')
if state != 'AVAILABLE':
raise ExtractorError(
'VOD %s is not available (state: %s)' % (vod_id, state),
expected=True)
formats = []
thumbnail_url = None
for vod in vod_info['vods']:
vod_type = vod.get('format')
if vod_type in ('hls', 'raw'):
formats.extend(self._extract_format(vod, vod_type))
elif vod_type == 'thumbnail':
thumbnail_url = urljoin(vod.get('baseUrl'), 'source.png')
self._sort_formats(formats)
info = {
'id': vod_id,
'title': vod_info.get('name') or vod_id,
'duration': float_or_none(vod_info.get('duration')),
'thumbnail': thumbnail_url,
'timestamp': parse_iso8601(vod_info.get('createdAt')),
'view_count': int_or_none(vod_info.get('viewsTotal')),
'formats': formats,
}
info.update(self._extract_channel_info(vod_info.get('channel') or {}))
return info
+17 -16
View File
@@ -2513,16 +2513,18 @@ class InfoExtractor(object):
# amp-video and amp-audio are very similar to their HTML5 counterparts
# so we wll include them right here (see
# https://www.ampproject.org/docs/reference/components/amp-video)
media_tags = [(media_tag, media_type, '')
for media_tag, media_type
in re.findall(r'(?s)(<(?:amp-)?(video|audio)[^>]*/>)', webpage)]
# For dl8-* tags see https://delight-vr.com/documentation/dl8-video/
_MEDIA_TAG_NAME_RE = r'(?:(?:amp|dl8(?:-live)?)-)?(video|audio)'
media_tags = [(media_tag, media_tag_name, media_type, '')
for media_tag, media_tag_name, media_type
in re.findall(r'(?s)(<(%s)[^>]*/>)' % _MEDIA_TAG_NAME_RE, webpage)]
media_tags.extend(re.findall(
# We only allow video|audio followed by a whitespace or '>'.
# Allowing more characters may end up in significant slow down (see
# https://github.com/ytdl-org/youtube-dl/issues/11979, example URL:
# http://www.porntrex.com/maps/videositemap.xml).
r'(?s)(<(?P<tag>(?:amp-)?(?:video|audio))(?:\s+[^>]*)?>)(.*?)</(?P=tag)>', webpage))
for media_tag, media_type, media_content in media_tags:
r'(?s)(<(?P<tag>%s)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>' % _MEDIA_TAG_NAME_RE, webpage))
for media_tag, _, media_type, media_content in media_tags:
media_info = {
'formats': [],
'subtitles': {},
@@ -2614,33 +2616,32 @@ class InfoExtractor(object):
hls_host = hosts.get('hls')
if hls_host:
m3u8_url = re.sub(r'(https?://)[^/]+', r'\1' + hls_host, m3u8_url)
formats.extend(self._extract_m3u8_formats(
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
http_host = hosts.get('http')
if http_host and 'hdnea=' not in manifest_url:
REPL_REGEX = r'https://[^/]+/i/([^,]+),([^/]+),([^/]+).csmil/.+'
if http_host and m3u8_formats and 'hdnea=' not in m3u8_url:
REPL_REGEX = r'https?://[^/]+/i/([^,]+),([^/]+),([^/]+)\.csmil/.+'
qualities = re.match(REPL_REGEX, m3u8_url).group(2).split(',')
qualities_length = len(qualities)
if len(formats) in (qualities_length + 1, qualities_length * 2 + 1):
if len(m3u8_formats) in (qualities_length, qualities_length + 1):
i = 0
http_formats = []
for f in formats:
if f['protocol'] == 'm3u8_native' and f['vcodec'] != 'none':
for f in m3u8_formats:
if f['vcodec'] != 'none':
for protocol in ('http', 'https'):
http_f = f.copy()
del http_f['manifest_url']
http_url = re.sub(
REPL_REGEX, protocol + r'://%s/\1%s\3' % (http_host, qualities[i]), f['url'])
REPL_REGEX, protocol + r'://%s/\g<1>%s\3' % (http_host, qualities[i]), f['url'])
http_f.update({
'format_id': http_f['format_id'].replace('hls-', protocol + '-'),
'url': http_url,
'protocol': protocol,
})
http_formats.append(http_f)
formats.append(http_f)
i += 1
formats.extend(http_formats)
return formats
+14 -12
View File
@@ -30,6 +30,8 @@ from .adobetv import (
from .adultswim import AdultSwimIE
from .aenetworks import (
AENetworksIE,
AENetworksCollectionIE,
AENetworksShowIE,
HistoryTopicIE,
)
from .afreecatv import AfreecaTVIE
@@ -89,10 +91,6 @@ from .bbc import (
BBCCoUkPlaylistIE,
BBCIE,
)
from .beampro import (
BeamProLiveIE,
BeamProVodIE,
)
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
@@ -393,6 +391,7 @@ from .frontendmasters import (
FrontendMastersLessonIE,
FrontendMastersCourseIE
)
from .fujitv import FujiTVFODPlus7IE
from .funimation import FunimationIE
from .funk import FunkIE
from .fusion import FusionIE
@@ -531,7 +530,10 @@ from .laola1tv import (
EHFTVIE,
ITTFIE,
)
from .lbry import LBRYIE
from .lbry import (
LBRYIE,
LBRYChannelIE,
)
from .lci import LCIIE
from .lcp import (
LcpPlayIE,
@@ -1039,12 +1041,6 @@ from .sky import (
from .slideshare import SlideshareIE
from .slideslive import SlidesLiveIE
from .slutload import SlutloadIE
from .smotri import (
SmotriIE,
SmotriCommunityIE,
SmotriUserIE,
SmotriBroadcastIE,
)
from .snotr import SnotrIE
from .sohu import SohuIE
from .sonyliv import SonyLIVIE
@@ -1149,6 +1145,7 @@ from .telequebec import (
TeleQuebecSquatIE,
TeleQuebecEmissionIE,
TeleQuebecLiveIE,
TeleQuebecVideoIE,
)
from .teletask import TeleTaskIE
from .telewebion import TelewebionIE
@@ -1221,7 +1218,10 @@ from .tv2dk import (
from .tv2hu import TV2HuIE
from .tv4 import TV4IE
from .tv5mondeplus import TV5MondePlusIE
from .tva import TVAIE
from .tva import (
TVAIE,
QubIE,
)
from .tvanouvelles import (
TVANouvellesIE,
TVANouvellesArticleIE,
@@ -1230,6 +1230,7 @@ from .tvc import (
TVCIE,
TVCArticleIE,
)
from .tver import TVerIE
from .tvigle import TvigleIE
from .tvland import TVLandIE
from .tvn24 import TVN24IE
@@ -1515,6 +1516,7 @@ from .youtube import (
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
YoutubeYtBeIE,
YoutubeYtUserIE,
YoutubeWatchLaterIE,
)
+188 -53
View File
@@ -16,14 +16,17 @@ from ..utils import (
clean_html,
error_to_compat_str,
ExtractorError,
float_or_none,
get_element_by_id,
int_or_none,
js_to_json,
limit_length,
parse_count,
qualities,
sanitized_Request,
try_get,
urlencode_postdata,
urljoin,
)
@@ -39,7 +42,8 @@ class FacebookIE(InfoExtractor):
photo\.php|
video\.php|
video/embed|
story\.php
story\.php|
watch(?:/live)?/?
)\?(?:.*?)(?:v|video_id|story_fbid)=|
[^/]+/videos/(?:[^/]+/)?|
[^/]+/posts/|
@@ -54,8 +58,6 @@ class FacebookIE(InfoExtractor):
_NETRC_MACHINE = 'facebook'
IE_NAME = 'facebook'
_CHROME_USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.97 Safari/537.36'
_VIDEO_PAGE_TEMPLATE = 'https://www.facebook.com/video/video.php?v=%s'
_VIDEO_PAGE_TAHOE_TEMPLATE = 'https://www.facebook.com/video/tahoe/async/%s/?chain=true&isvideo=true&payloadtype=primary'
@@ -72,6 +74,7 @@ class FacebookIE(InfoExtractor):
},
'skip': 'Requires logging in',
}, {
# data.video
'url': 'https://www.facebook.com/video.php?v=274175099429670',
'info_dict': {
'id': '274175099429670',
@@ -133,6 +136,7 @@ class FacebookIE(InfoExtractor):
},
}, {
# have 1080P, but only up to 720p in swf params
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
'md5': '9571fae53d4165bbbadb17a94651dcdc',
'info_dict': {
@@ -147,6 +151,7 @@ class FacebookIE(InfoExtractor):
},
}, {
# bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://www.facebook.com/yaroslav.korpan/videos/1417995061575415/',
'info_dict': {
'id': '1417995061575415',
@@ -174,6 +179,7 @@ class FacebookIE(InfoExtractor):
'skip_download': True,
},
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://www.facebook.com/groups/1024490957622648/permalink/1396382447100162/',
'info_dict': {
'id': '1396382447100162',
@@ -193,18 +199,23 @@ class FacebookIE(InfoExtractor):
'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
'only_matching': True,
}, {
# data.mediaset.currMedia.edges
'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
'only_matching': True,
}, {
# data.video.story.attachments[].media
'url': 'facebook:544765982287235',
'only_matching': True,
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/',
'only_matching': True,
}, {
# data.video.creation_story.attachments[].media
'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
'only_matching': True,
}, {
# data.video
'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
'only_matching': True,
}, {
@@ -212,6 +223,7 @@ class FacebookIE(InfoExtractor):
'url': 'https://www.facebook.com/onlycleverentertainment/videos/1947995502095005/',
'only_matching': True,
}, {
# data.video
'url': 'https://www.facebook.com/WatchESLOne/videos/359649331226507/',
'info_dict': {
'id': '359649331226507',
@@ -222,7 +234,54 @@ class FacebookIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.all_subattachments.nodes[].media
'url': 'https://www.facebook.com/100033620354545/videos/106560053808006/',
'info_dict': {
'id': '106560053808006',
},
'playlist_count': 2,
}, {
# data.video.story.attachments[].media
'url': 'https://www.facebook.com/watch/?v=647537299265662',
'only_matching': True,
}, {
# data.node.comet_sections.content.story.attachments[].style_type_renderer.attachment.all_subattachments.nodes[].media
'url': 'https://www.facebook.com/PankajShahLondon/posts/10157667649866271',
'info_dict': {
'id': '10157667649866271',
},
'playlist_count': 3,
}, {
# data.nodes[].comet_sections.content.story.attachments[].style_type_renderer.attachment.media
'url': 'https://m.facebook.com/Alliance.Police.Department/posts/4048563708499330',
'info_dict': {
'id': '117576630041613',
'ext': 'mp4',
# TODO: title can be extracted from video page
'title': 'Facebook video #117576630041613',
'uploader_id': '189393014416438',
'upload_date': '20201123',
'timestamp': 1606162592,
},
'skip': 'Requires logging in',
}, {
# node.comet_sections.content.story.attached_story.attachments.style_type_renderer.attachment.media
'url': 'https://www.facebook.com/groups/ateistiskselskab/permalink/10154930137678856/',
'info_dict': {
'id': '211567722618337',
'ext': 'mp4',
'title': 'Facebook video #211567722618337',
'uploader_id': '127875227654254',
'upload_date': '20161122',
'timestamp': 1479793574,
},
}, {
# data.video.creation_story.attachments[].media
'url': 'https://www.facebook.com/watch/live/?v=1823658634322275',
'only_matching': True,
}]
_SUPPORTED_PAGLETS_REGEX = r'(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_[0-9a-f]+)'
@staticmethod
def _extract_urls(webpage):
@@ -305,23 +364,24 @@ class FacebookIE(InfoExtractor):
def _real_initialize(self):
self._login()
def _extract_from_url(self, url, video_id, fatal_if_no_video=True):
req = sanitized_Request(url)
req.add_header('User-Agent', self._CHROME_USER_AGENT)
webpage = self._download_webpage(req, video_id)
def _extract_from_url(self, url, video_id):
webpage = self._download_webpage(
url.replace('://m.facebook.com/', '://www.facebook.com/'), video_id)
video_data = None
def extract_video_data(instances):
video_data = []
for item in instances:
if item[1][0] == 'VideoConfig':
if try_get(item, lambda x: x[1][0]) == 'VideoConfig':
video_item = item[2][0]
if video_item.get('video_id'):
return video_item['videoData']
video_data.append(video_item['videoData'])
return video_data
server_js_data = self._parse_json(self._search_regex(
r'handleServerJS\(({.+})(?:\);|,")', webpage,
'server js data', default='{}'), video_id, fatal=False)
[r'handleServerJS\(({.+})(?:\);|,")', r'\bs\.handle\(({.+?})\);'],
webpage, 'server js data', default='{}'), video_id, fatal=False)
if server_js_data:
video_data = extract_video_data(server_js_data.get('instances', []))
@@ -331,17 +391,111 @@ class FacebookIE(InfoExtractor):
return extract_video_data(try_get(
js_data, lambda x: x['jsmods']['instances'], list) or [])
def extract_dash_manifest(video, formats):
dash_manifest = video.get('dash_manifest')
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
def process_formats(formats):
# Downloads with browser's User-Agent are rate limited. Working around
# with non-browser User-Agent.
for f in formats:
f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1'
self._sort_formats(formats)
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_\d+)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
server_js_data = self._parse_json(self._search_regex([
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+' + self._SUPPORTED_PAGLETS_REGEX,
r'bigPipe\.onPageletArrive\(({.*?id\s*:\s*"%s".*?})\);' % self._SUPPORTED_PAGLETS_REGEX
], webpage, 'js data', default='{}'), video_id, js_to_json, False)
video_data = extract_from_jsmods_instances(server_js_data)
if not video_data:
if not fatal_if_no_video:
return webpage, False
graphql_data = self._parse_json(self._search_regex(
r'handleWithCustomApplyEach\([^,]+,\s*({.*?"(?:dash_manifest|playable_url(?:_quality_hd)?)"\s*:\s*"[^"]+".*?})\);',
webpage, 'graphql data', default='{}'), video_id, fatal=False) or {}
for require in (graphql_data.get('require') or []):
if require[0] == 'RelayPrefetchedStreamCache':
entries = []
def parse_graphql_video(video):
formats = []
q = qualities(['sd', 'hd'])
for (suffix, format_id) in [('', 'sd'), ('_quality_hd', 'hd')]:
playable_url = video.get('playable_url' + suffix)
if not playable_url:
continue
formats.append({
'format_id': format_id,
'quality': q(format_id),
'url': playable_url,
})
extract_dash_manifest(video, formats)
process_formats(formats)
v_id = video.get('videoId') or video.get('id') or video_id
info = {
'id': v_id,
'formats': formats,
'thumbnail': try_get(video, lambda x: x['thumbnailImage']['uri']),
'uploader_id': try_get(video, lambda x: x['owner']['id']),
'timestamp': int_or_none(video.get('publish_time')),
'duration': float_or_none(video.get('playable_duration_in_ms'), 1000),
}
description = try_get(video, lambda x: x['savable_description']['text'])
title = video.get('name')
if title:
info.update({
'title': title,
'description': description,
})
else:
info['title'] = description or 'Facebook video #%s' % v_id
entries.append(info)
def parse_attachment(attachment, key='media'):
media = attachment.get(key) or {}
if media.get('__typename') == 'Video':
return parse_graphql_video(media)
data = try_get(require, lambda x: x[3][1]['__bbox']['result']['data'], dict) or {}
nodes = data.get('nodes') or []
node = data.get('node') or {}
if not nodes and node:
nodes.append(node)
for node in nodes:
story = try_get(node, lambda x: x['comet_sections']['content']['story'], dict) or {}
attachments = try_get(story, [
lambda x: x['attached_story']['attachments'],
lambda x: x['attachments']
], list) or []
for attachment in attachments:
attachment = try_get(attachment, lambda x: x['style_type_renderer']['attachment'], dict)
ns = try_get(attachment, lambda x: x['all_subattachments']['nodes'], list) or []
for n in ns:
parse_attachment(n)
parse_attachment(attachment)
edges = try_get(data, lambda x: x['mediaset']['currMedia']['edges'], list) or []
for edge in edges:
parse_attachment(edge, key='node')
video = data.get('video') or {}
if video:
attachments = try_get(video, [
lambda x: x['story']['attachments'],
lambda x: x['creation_story']['attachments']
], list) or []
for attachment in attachments:
parse_attachment(attachment)
if not entries:
parse_graphql_video(video)
return self.playlist_result(entries, video_id)
if not video_data:
m_msg = re.search(r'class="[^"]*uiInterstitialContent[^"]*"><div>(.*?)</div>', webpage)
if m_msg is not None:
raise ExtractorError(
@@ -379,8 +533,19 @@ class FacebookIE(InfoExtractor):
if not video_data:
raise ExtractorError('Cannot parse data')
subtitles = {}
if len(video_data) > 1:
entries = []
for v in video_data:
video_url = v[0].get('video_url')
if not video_url:
continue
entries.append(self.url_result(urljoin(
url, video_url), self.ie_key(), v[0].get('video_id')))
return self.playlist_result(entries, video_id)
video_data = video_data[0]
formats = []
subtitles = {}
for f in video_data:
format_id = f['stream_type']
if f and isinstance(f, dict):
@@ -399,22 +564,14 @@ class FacebookIE(InfoExtractor):
'url': src,
'preference': preference,
})
dash_manifest = f[0].get('dash_manifest')
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
extract_dash_manifest(f[0], formats)
subtitles_src = f[0].get('subtitles_src')
if subtitles_src:
subtitles.setdefault('en', []).append({'url': subtitles_src})
if not formats:
raise ExtractorError('Cannot find video formats')
# Downloads with browser's User-Agent are rate limited. Working around
# with non-browser User-Agent.
for f in formats:
f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1'
self._sort_formats(formats)
process_formats(formats)
video_title = self._html_search_regex(
r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage,
@@ -454,35 +611,13 @@ class FacebookIE(InfoExtractor):
'subtitles': subtitles,
}
return webpage, info_dict
return info_dict
def _real_extract(self, url):
video_id = self._match_id(url)
real_url = self._VIDEO_PAGE_TEMPLATE % video_id if url.startswith('facebook:') else url
webpage, info_dict = self._extract_from_url(real_url, video_id, fatal_if_no_video=False)
if info_dict:
return info_dict
if '/posts/' in url:
video_id_json = self._search_regex(
r'(["\'])video_ids\1\s*:\s*(?P<ids>\[.+?\])', webpage, 'video ids', group='ids',
default='')
if video_id_json:
entries = [
self.url_result('facebook:%s' % vid, FacebookIE.ie_key())
for vid in self._parse_json(video_id_json, video_id)]
return self.playlist_result(entries, video_id)
# Single Video?
video_id = self._search_regex(r'video_id:\s*"([0-9]+)"', webpage, 'single video id')
return self.url_result('facebook:%s' % video_id, FacebookIE.ie_key())
else:
_, info_dict = self._extract_from_url(
self._VIDEO_PAGE_TEMPLATE % video_id,
video_id, fatal_if_no_video=True)
return info_dict
return self._extract_from_url(real_url, video_id)
class FacebookPluginsVideoIE(InfoExtractor):
+35
View File
@@ -0,0 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class FujiTVFODPlus7IE(InfoExtractor):
_VALID_URL = r'https?://i\.fod\.fujitv\.co\.jp/plus7/web/[0-9a-z]{4}/(?P<id>[0-9a-z]+)'
_BASE_URL = 'http://i.fod.fujitv.co.jp/'
_BITRATE_MAP = {
300: (320, 180),
800: (640, 360),
1200: (1280, 720),
2000: (1280, 720),
}
def _real_extract(self, url):
video_id = self._match_id(url)
formats = self._extract_m3u8_formats(
self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id)
for f in formats:
wh = self._BITRATE_MAP.get(f.get('tbr'))
if wh:
f.update({
'width': wh[0],
'height': wh[1],
})
self._sort_formats(formats)
return {
'id': video_id,
'title': video_id,
'formats': formats,
'thumbnail': self._BASE_URL + 'pc/image/wbtn/wbtn_%s.jpg' % video_id,
}
+25 -85
View File
@@ -1,16 +1,7 @@
from __future__ import unicode_literals
import re
from .once import OnceIE
from ..compat import (
compat_urllib_parse_unquote,
)
from ..utils import (
unescapeHTML,
url_basename,
dict_get,
)
from ..compat import compat_urllib_parse_unquote
class GameSpotIE(OnceIE):
@@ -24,17 +15,16 @@ class GameSpotIE(OnceIE):
'title': 'Arma 3 - Community Guide: SITREP I',
'description': 'Check out this video where some of the basics of Arma 3 is explained.',
},
'skip': 'manifest URL give HTTP Error 404: Not Found',
}, {
'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
'md5': '173ea87ad762cf5d3bf6163dceb255a6',
'info_dict': {
'id': 'gs-2300-6424837',
'ext': 'mp4',
'title': 'Now Playing - The Witcher 3: Wild Hunt',
'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
},
'params': {
'skip_download': True, # m3u8 downloads
},
}, {
'url': 'https://www.gamespot.com/videos/embed/6439218/',
'only_matching': True,
@@ -49,90 +39,40 @@ class GameSpotIE(OnceIE):
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
data_video_json = self._search_regex(
r'data-video=["\'](.*?)["\']', webpage, 'data video')
data_video = self._parse_json(unescapeHTML(data_video_json), page_id)
data_video = self._parse_json(self._html_search_regex(
r'data-video=(["\'])({.*?})\1', webpage,
'video data', group=2), page_id)
title = compat_urllib_parse_unquote(data_video['title'])
streams = data_video['videoStreams']
manifest_url = None
formats = []
f4m_url = streams.get('f4m_stream')
if f4m_url:
manifest_url = f4m_url
formats.extend(self._extract_f4m_formats(
f4m_url + '?hdcore=3.7.0', page_id, f4m_id='hds', fatal=False))
m3u8_url = dict_get(streams, ('m3u8_stream', 'adaptive_stream'))
m3u8_url = streams.get('adaptive_stream')
if m3u8_url:
manifest_url = m3u8_url
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, page_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
progressive_url = dict_get(
streams, ('progressive_hd', 'progressive_high', 'progressive_low', 'other_lr'))
if progressive_url and manifest_url:
qualities_basename = self._search_regex(
r'/([^/]+)\.csmil/',
manifest_url, 'qualities basename', default=None)
if qualities_basename:
QUALITIES_RE = r'((,\d+)+,?)'
qualities = self._search_regex(
QUALITIES_RE, qualities_basename,
'qualities', default=None)
if qualities:
qualities = list(map(lambda q: int(q), qualities.strip(',').split(',')))
qualities.sort()
http_template = re.sub(QUALITIES_RE, r'%d', qualities_basename)
http_url_basename = url_basename(progressive_url)
if m3u8_formats:
self._sort_formats(m3u8_formats)
m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none', m3u8_formats))
if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy()
f.update({
'url': progressive_url.replace(
http_url_basename, http_template % q),
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
formats.append(f)
else:
for q in qualities:
formats.append({
'url': progressive_url.replace(
http_url_basename, http_template % q),
'ext': 'mp4',
'format_id': 'http-%d' % q,
'tbr': q,
})
for f in m3u8_formats:
formats.append(f)
http_f = f.copy()
del http_f['manifest_url']
http_f.update({
'format_id': f['format_id'].replace('hls-', 'http-'),
'protocol': 'http',
'url': f['url'].replace('.m3u8', '.mp4'),
})
formats.append(http_f)
onceux_json = self._search_regex(
r'data-onceux-options=["\'](.*?)["\']', webpage, 'data video', default=None)
if onceux_json:
onceux_url = self._parse_json(unescapeHTML(onceux_json), page_id).get('metadataUri')
if onceux_url:
formats.extend(self._extract_once_formats(re.sub(
r'https?://[^/]+', 'http://once.unicornmedia.com', onceux_url),
http_formats_preference=-1))
mpd_url = streams.get('adaptive_dash')
if mpd_url:
formats.extend(self._extract_mpd_formats(
mpd_url, page_id, mpd_id='dash', fatal=False))
if not formats:
for quality in ['sd', 'hd']:
# It's actually a link to a flv file
flv_url = streams.get('f4m_{0}'.format(quality))
if flv_url is not None:
formats.append({
'url': flv_url,
'ext': 'flv',
'format_id': quality,
})
self._sort_formats(formats)
return {
'id': data_video['guid'],
'id': data_video.get('guid') or page_id,
'display_id': page_id,
'title': compat_urllib_parse_unquote(data_video['title']),
'title': title,
'formats': formats,
'description': self._html_search_meta('description', webpage),
'thumbnail': self._og_search_thumbnail(webpage),
+68 -31
View File
@@ -20,19 +20,23 @@ from ..utils import (
ExtractorError,
float_or_none,
HEADRequest,
int_or_none,
is_html,
js_to_json,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
orderedSet,
parse_duration,
sanitized_Request,
smuggle_url,
unescapeHTML,
unified_strdate,
unified_timestamp,
unsmuggle_url,
UnsupportedError,
url_or_none,
xpath_text,
xpath_with_ns,
)
from .commonprotocols import RtmpIE
from .brightcove import (
@@ -48,7 +52,6 @@ from .ooyala import OoyalaIE
from .rutv import RUTVIE
from .tvc import TVCIE
from .sportbox import SportBoxIE
from .smotri import SmotriIE
from .myvi import MyviIE
from .condenast import CondeNastIE
from .udn import UDNEmbedIE
@@ -198,11 +201,21 @@ class GenericIE(InfoExtractor):
{
'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
'info_dict': {
'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
'ext': 'm4v',
'upload_date': '20150228',
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
'id': 'http://podcastfeeds.nbcnews.com/nbcnews/video/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
'title': 'MSNBC Rachel Maddow (video)',
'description': 're:.*her unique approach to storytelling.*',
},
'playlist': [{
'info_dict': {
'ext': 'mov',
'id': 'pdv_maddow_netcast_mov-12-04-2020-224335',
'title': 're:MSNBC Rachel Maddow',
'description': 're:.*her unique approach to storytelling.*',
'timestamp': int,
'upload_date': compat_str,
'duration': float,
},
}],
},
# RSS feed with enclosures and unsupported link URLs
{
@@ -2103,23 +2116,23 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
{
# Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
'info_dict': {
'id': '5b400b834b32992a310622b9',
'ext': 'mp4',
'title': 'Smoky Barbecue Favorites',
'thumbnail': r're:^https?://.*\.jpe?g',
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
'upload_date': '20170909',
'timestamp': 1504915200,
},
'add_ie': [ZypeIE.ie_key()],
'params': {
'skip_download': True,
},
},
# {
# # Zype embed
# 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
# 'info_dict': {
# 'id': '5b400b834b32992a310622b9',
# 'ext': 'mp4',
# 'title': 'Smoky Barbecue Favorites',
# 'thumbnail': r're:^https?://.*\.jpe?g',
# 'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
# 'upload_date': '20170909',
# 'timestamp': 1504915200,
# },
# 'add_ie': [ZypeIE.ie_key()],
# 'params': {
# 'skip_download': True,
# },
# },
{
# videojs embed
'url': 'https://video.sibnet.ru/shell.php?videoid=3422904',
@@ -2180,6 +2193,10 @@ class GenericIE(InfoExtractor):
playlist_desc_el = doc.find('./channel/description')
playlist_desc = None if playlist_desc_el is None else playlist_desc_el.text
NS_MAP = {
'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd',
}
entries = []
for it in doc.findall('./channel/item'):
next_url = None
@@ -2195,10 +2212,33 @@ class GenericIE(InfoExtractor):
if not next_url:
continue
def itunes(key):
return xpath_text(
it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
default=None)
duration = itunes('duration')
explicit = itunes('explicit')
if explicit == 'true':
age_limit = 18
elif explicit == 'false':
age_limit = 0
else:
age_limit = None
entries.append({
'_type': 'url_transparent',
'url': next_url,
'title': it.find('title').text,
'description': xpath_text(it, 'description', default=None),
'timestamp': unified_timestamp(
xpath_text(it, 'pubDate', default=None)),
'duration': int_or_none(duration) or parse_duration(duration),
'thumbnail': url_or_none(itunes('image')),
'episode': itunes('title'),
'episode_number': int_or_none(itunes('episode')),
'season_number': int_or_none(itunes('season')),
'age_limit': age_limit,
})
return {
@@ -2318,7 +2358,7 @@ class GenericIE(InfoExtractor):
info_dict = {
'id': video_id,
'title': self._generic_title(url),
'upload_date': unified_strdate(head_response.headers.get('Last-Modified'))
'timestamp': unified_timestamp(head_response.headers.get('Last-Modified'))
}
# Check for direct link to a video
@@ -2424,7 +2464,9 @@ class GenericIE(InfoExtractor):
# Sometimes embedded video player is hidden behind percent encoding
# (e.g. https://github.com/ytdl-org/youtube-dl/issues/2448)
# Unescaping the whole page allows to handle those cases in a generic way
webpage = compat_urllib_parse_unquote(webpage)
# FIXME: unescaping the whole page may break URLs, commenting out for now.
# There probably should be a second run of generic extractor on unescaped webpage.
# webpage = compat_urllib_parse_unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
@@ -2772,11 +2814,6 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for embedded smotri.com player
smotri_url = SmotriIE._extract_url(webpage)
if smotri_url:
return self.url_result(smotri_url, 'Smotri')
# Look for embedded Myvi.ru player
myvi_url = MyviIE._extract_url(webpage)
if myvi_url:
+91 -218
View File
@@ -1,29 +1,21 @@
# coding: utf-8
from __future__ import unicode_literals
import uuid
import xml.etree.ElementTree as etree
import json
import re
from .common import InfoExtractor
from .brightcove import BrightcoveNewIE
from ..compat import (
compat_str,
compat_etree_register_namespace,
)
from ..utils import (
determine_ext,
ExtractorError,
extract_attributes,
int_or_none,
get_element_by_class,
JSON_LD_RE,
merge_dicts,
parse_duration,
smuggle_url,
strip_or_none,
url_or_none,
xpath_with_ns,
xpath_element,
xpath_text,
)
@@ -31,14 +23,18 @@ class ITVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
_GEO_COUNTRIES = ['GB']
_TESTS = [{
'url': 'http://www.itv.com/hub/mr-bean-animated-series/2a2936a0053',
'url': 'https://www.itv.com/hub/liar/2a4547a0012',
'info_dict': {
'id': '2a2936a0053',
'ext': 'flv',
'title': 'Home Movie',
'id': '2a4547a0012',
'ext': 'mp4',
'title': 'Liar - Series 2 - Episode 6',
'description': 'md5:d0f91536569dec79ea184f0a44cca089',
'series': 'Liar',
'season_number': 2,
'episode_number': 6,
},
'params': {
# rtmp download
# m3u8 download
'skip_download': True,
},
}, {
@@ -61,220 +57,97 @@ class ITVIE(InfoExtractor):
params = extract_attributes(self._search_regex(
r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
ns_map = {
'soapenv': 'http://schemas.xmlsoap.org/soap/envelope/',
'tem': 'http://tempuri.org/',
'itv': 'http://schemas.datacontract.org/2004/07/Itv.BB.Mercury.Common.Types',
'com': 'http://schemas.itv.com/2009/05/Common',
}
for ns, full_ns in ns_map.items():
compat_etree_register_namespace(ns, full_ns)
def _add_ns(name):
return xpath_with_ns(name, ns_map)
def _add_sub_element(element, name):
return etree.SubElement(element, _add_ns(name))
production_id = (
params.get('data-video-autoplay-id')
or '%s#001' % (
params.get('data-video-episode-id')
or video_id.replace('a', '/')))
req_env = etree.Element(_add_ns('soapenv:Envelope'))
_add_sub_element(req_env, 'soapenv:Header')
body = _add_sub_element(req_env, 'soapenv:Body')
get_playlist = _add_sub_element(body, ('tem:GetPlaylist'))
request = _add_sub_element(get_playlist, 'tem:request')
_add_sub_element(request, 'itv:ProductionId').text = production_id
_add_sub_element(request, 'itv:RequestGuid').text = compat_str(uuid.uuid4()).upper()
vodcrid = _add_sub_element(request, 'itv:Vodcrid')
_add_sub_element(vodcrid, 'com:Id')
_add_sub_element(request, 'itv:Partition')
user_info = _add_sub_element(get_playlist, 'tem:userInfo')
_add_sub_element(user_info, 'itv:Broadcaster').text = 'Itv'
_add_sub_element(user_info, 'itv:DM')
_add_sub_element(user_info, 'itv:RevenueScienceValue')
_add_sub_element(user_info, 'itv:SessionId')
_add_sub_element(user_info, 'itv:SsoToken')
_add_sub_element(user_info, 'itv:UserToken')
site_info = _add_sub_element(get_playlist, 'tem:siteInfo')
_add_sub_element(site_info, 'itv:AdvertisingRestriction').text = 'None'
_add_sub_element(site_info, 'itv:AdvertisingSite').text = 'ITV'
_add_sub_element(site_info, 'itv:AdvertisingType').text = 'Any'
_add_sub_element(site_info, 'itv:Area').text = 'ITVPLAYER.VIDEO'
_add_sub_element(site_info, 'itv:Category')
_add_sub_element(site_info, 'itv:Platform').text = 'DotCom'
_add_sub_element(site_info, 'itv:Site').text = 'ItvCom'
device_info = _add_sub_element(get_playlist, 'tem:deviceInfo')
_add_sub_element(device_info, 'itv:ScreenSize').text = 'Big'
player_info = _add_sub_element(get_playlist, 'tem:playerInfo')
_add_sub_element(player_info, 'itv:Version').text = '2'
ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
hmac = params['data-video-hmac']
headers = self.geo_verification_headers()
headers.update({
'Content-Type': 'text/xml; charset=utf-8',
'SOAPAction': 'http://tempuri.org/PlaylistService/GetPlaylist',
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
'Content-Type': 'application/json',
'hmac': hmac.upper(),
})
ios_playlist = self._download_json(
ios_playlist_url, video_id, data=json.dumps({
'user': {
'itvUserId': '',
'entitlements': [],
'token': ''
},
'device': {
'manufacturer': 'Safari',
'model': '5',
'os': {
'name': 'Windows NT',
'version': '6.1',
'type': 'desktop'
}
},
'client': {
'version': '4.1',
'id': 'browser'
},
'variantAvailability': {
'featureset': {
'min': ['hls', 'aes', 'outband-webvtt'],
'max': ['hls', 'aes', 'outband-webvtt']
},
'platformTag': 'dotcom'
}
}).encode(), headers=headers)
video_data = ios_playlist['Playlist']['Video']
ios_base_url = video_data.get('Base')
info = self._search_json_ld(webpage, video_id, default={})
formats = []
subtitles = {}
def extract_subtitle(sub_url):
ext = determine_ext(sub_url, 'ttml')
subtitles.setdefault('en', []).append({
'url': sub_url,
'ext': 'ttml' if ext == 'xml' else ext,
})
resp_env = self._download_xml(
params['data-playlist-url'], video_id,
headers=headers, data=etree.tostring(req_env), fatal=False)
if resp_env:
playlist = xpath_element(resp_env, './/Playlist')
if playlist is None:
fault_code = xpath_text(resp_env, './/faultcode')
fault_string = xpath_text(resp_env, './/faultstring')
if fault_code == 'InvalidGeoRegion':
self.raise_geo_restricted(
msg=fault_string, countries=self._GEO_COUNTRIES)
elif fault_code not in (
'InvalidEntity', 'InvalidVodcrid', 'ContentUnavailable'):
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, fault_string), expected=True)
info.update({
'title': self._og_search_title(webpage),
'episode_title': params.get('data-video-episode'),
'series': params.get('data-video-title'),
})
for media_file in (video_data.get('MediaFiles') or []):
href = media_file.get('Href')
if not href:
continue
if ios_base_url:
href = ios_base_url + href
ext = determine_ext(href)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
title = xpath_text(playlist, 'EpisodeTitle', default=None)
info.update({
'title': title,
'episode_title': title,
'episode_number': int_or_none(xpath_text(playlist, 'EpisodeNumber')),
'series': xpath_text(playlist, 'ProgrammeTitle'),
'duration': parse_duration(xpath_text(playlist, 'Duration')),
formats.append({
'url': href,
})
video_element = xpath_element(playlist, 'VideoEntries/Video', fatal=True)
media_files = xpath_element(video_element, 'MediaFiles', fatal=True)
rtmp_url = media_files.attrib['base']
for media_file in media_files.findall('MediaFile'):
play_path = xpath_text(media_file, 'URL')
if not play_path:
continue
tbr = int_or_none(media_file.get('bitrate'), 1000)
f = {
'format_id': 'rtmp' + ('-%d' % tbr if tbr else ''),
'play_path': play_path,
# Providing this swfVfy allows to avoid truncated downloads
'player_url': 'http://www.itv.com/mercury/Mercury_VideoPlayer.swf',
'page_url': url,
'tbr': tbr,
'ext': 'flv',
}
app = self._search_regex(
'rtmpe?://[^/]+/(.+)$', rtmp_url, 'app', default=None)
if app:
f.update({
'url': rtmp_url.split('?', 1)[0],
'app': app,
})
else:
f['url'] = rtmp_url
formats.append(f)
for caption_url in video_element.findall('ClosedCaptioningURIs/URL'):
if caption_url.text:
extract_subtitle(caption_url.text)
ios_playlist_url = params.get('data-video-playlist') or params.get('data-video-id')
hmac = params.get('data-video-hmac')
if ios_playlist_url and hmac and re.match(r'https?://', ios_playlist_url):
headers = self.geo_verification_headers()
headers.update({
'Accept': 'application/vnd.itv.vod.playlist.v2+json',
'Content-Type': 'application/json',
'hmac': hmac.upper(),
})
ios_playlist = self._download_json(
ios_playlist_url, video_id, data=json.dumps({
'user': {
'itvUserId': '',
'entitlements': [],
'token': ''
},
'device': {
'manufacturer': 'Safari',
'model': '5',
'os': {
'name': 'Windows NT',
'version': '6.1',
'type': 'desktop'
}
},
'client': {
'version': '4.1',
'id': 'browser'
},
'variantAvailability': {
'featureset': {
'min': ['hls', 'aes', 'outband-webvtt'],
'max': ['hls', 'aes', 'outband-webvtt']
},
'platformTag': 'dotcom'
}
}).encode(), headers=headers, fatal=False)
if ios_playlist:
video_data = ios_playlist.get('Playlist', {}).get('Video', {})
ios_base_url = video_data.get('Base')
for media_file in video_data.get('MediaFiles', []):
href = media_file.get('Href')
if not href:
continue
if ios_base_url:
href = ios_base_url + href
ext = determine_ext(href)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
href, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': href,
})
subs = video_data.get('Subtitles')
if isinstance(subs, list):
for sub in subs:
if not isinstance(sub, dict):
continue
href = url_or_none(sub.get('Href'))
if href:
extract_subtitle(href)
if not info.get('duration'):
info['duration'] = parse_duration(video_data.get('Duration'))
self._sort_formats(formats)
info.update({
subtitles = {}
subs = video_data.get('Subtitles') or []
for sub in subs:
if not isinstance(sub, dict):
continue
href = url_or_none(sub.get('Href'))
if not href:
continue
subtitles.setdefault('en', []).append({
'url': href,
'ext': determine_ext(href, 'vtt'),
})
info = self._search_json_ld(webpage, video_id, default={})
if not info:
json_ld = self._parse_json(self._search_regex(
JSON_LD_RE, webpage, 'JSON-LD', '{}',
group='json_ld'), video_id, fatal=False)
if json_ld and json_ld.get('@type') == 'BreadcrumbList':
for ile in (json_ld.get('itemListElement:') or []):
item = ile.get('item:') or {}
if item.get('@type') == 'TVEpisode':
item['@context'] = 'http://schema.org'
info = self._json_ld(item, video_id, fatal=False) or {}
break
return merge_dicts({
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'formats': formats,
'subtitles': subtitles,
})
webpage_info = self._search_json_ld(webpage, video_id, default={})
if not webpage_info.get('title'):
webpage_info['title'] = self._html_search_regex(
r'(?s)<h\d+[^>]+\bclass=["\'][^>]*episode-title["\'][^>]*>([^<]+)<',
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or webpage_info['episode']
return merge_dicts(info, webpage_info)
'duration': parse_duration(video_data.get('Duration')),
'description': strip_or_none(get_element_by_class('episode-info__synopsis', webpage)),
}, info)
class ITVBTCCIE(InfoExtractor):
+163 -40
View File
@@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import functools
import json
from .common import InfoExtractor
@@ -10,13 +11,73 @@ from ..utils import (
ExtractorError,
int_or_none,
mimetype2ext,
OnDemandPagedList,
try_get,
urljoin,
)
class LBRYIE(InfoExtractor):
IE_NAME = 'lbry.tv'
_VALID_URL = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/(?P<id>@[^:]+:[0-9a-z]+/[^:]+:[0-9a-z])'
class LBRYBaseIE(InfoExtractor):
_BASE_URL_REGEX = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/'
_CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
_OPT_CLAIM_ID = '[^:/?#&]+(?::%s)?' % _CLAIM_ID_REGEX
_SUPPORTED_STREAM_TYPES = ['video', 'audio']
def _call_api_proxy(self, method, display_id, params, resource):
return self._download_json(
'https://api.lbry.tv/api/v1/proxy',
display_id, 'Downloading %s JSON metadata' % resource,
headers={'Content-Type': 'application/json-rpc'},
data=json.dumps({
'method': method,
'params': params,
}).encode())['result']
def _resolve_url(self, url, display_id, resource):
return self._call_api_proxy(
'resolve', display_id, {'urls': url}, resource)[url]
def _permanent_url(self, url, claim_name, claim_id):
return urljoin(url, '/%s:%s' % (claim_name, claim_id))
def _parse_stream(self, stream, url):
stream_value = stream.get('value') or {}
stream_type = stream_value.get('stream_type')
source = stream_value.get('source') or {}
media = stream_value.get(stream_type) or {}
signing_channel = stream.get('signing_channel') or {}
channel_name = signing_channel.get('name')
channel_claim_id = signing_channel.get('claim_id')
channel_url = None
if channel_name and channel_claim_id:
channel_url = self._permanent_url(url, channel_name, channel_claim_id)
info = {
'thumbnail': try_get(stream_value, lambda x: x['thumbnail']['url'], compat_str),
'description': stream_value.get('description'),
'license': stream_value.get('license'),
'timestamp': int_or_none(stream.get('timestamp')),
'tags': stream_value.get('tags'),
'duration': int_or_none(media.get('duration')),
'channel': try_get(signing_channel, lambda x: x['value']['title']),
'channel_id': channel_claim_id,
'channel_url': channel_url,
'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')),
'filesize': int_or_none(source.get('size')),
}
if stream_type == 'audio':
info['vcodec'] = 'none'
else:
info.update({
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
})
return info
class LBRYIE(LBRYBaseIE):
IE_NAME = 'lbry'
_VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>\$/[^/]+/[^/]+/{1}|@{0}/{0}|(?!@){0})'.format(LBRYBaseIE._OPT_CLAIM_ID, LBRYBaseIE._CLAIM_ID_REGEX)
_TESTS = [{
# Video
'url': 'https://lbry.tv/@Mantega:1/First-day-LBRY:1',
@@ -28,6 +89,8 @@ class LBRYIE(InfoExtractor):
'description': 'md5:f6cb5c704b332d37f5119313c2c98f51',
'timestamp': 1595694354,
'upload_date': '20200725',
'width': 1280,
'height': 720,
}
}, {
# Audio
@@ -40,6 +103,12 @@ class LBRYIE(InfoExtractor):
'description': 'md5:661ac4f1db09f31728931d7b88807a61',
'timestamp': 1591312601,
'upload_date': '20200604',
'tags': list,
'duration': 2570,
'channel': 'The LBRY Foundation',
'channel_id': '0ed629d2b9c601300cacf7eabe9da0be79010212',
'channel_url': 'https://lbry.tv/@LBRYFoundation:0ed629d2b9c601300cacf7eabe9da0be79010212',
'vcodec': 'none',
}
}, {
'url': 'https://odysee.com/@BrodieRobertson:5/apple-is-tracking-everything-you-do-on:e',
@@ -47,45 +116,99 @@ class LBRYIE(InfoExtractor):
}, {
'url': "https://odysee.com/@ScammerRevolts:b0/I-SYSKEY'D-THE-SAME-SCAMMERS-3-TIMES!:b",
'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/$/embed/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}, {
'url': 'https://lbry.tv/Episode-1:e7',
'only_matching': True,
}, {
'url': 'https://lbry.tv/@LBRYFoundation/Episode-1',
'only_matching': True,
}, {
'url': 'https://lbry.tv/$/download/Episode-1/e7d93d772bd87e2b62d5ab993c1c3ced86ebb396',
'only_matching': True,
}]
def _call_api_proxy(self, method, display_id, params):
return self._download_json(
'https://api.lbry.tv/api/v1/proxy', display_id,
headers={'Content-Type': 'application/json-rpc'},
data=json.dumps({
'method': method,
'params': params,
}).encode())['result']
def _real_extract(self, url):
display_id = self._match_id(url)
if display_id.startswith('$/'):
display_id = display_id.split('/', 2)[-1].replace('/', ':')
else:
display_id = display_id.replace(':', '#')
uri = 'lbry://' + display_id
result = self._resolve_url(uri, display_id, 'stream')
result_value = result['value']
if result_value.get('stream_type') not in self._SUPPORTED_STREAM_TYPES:
raise ExtractorError('Unsupported URL', expected=True)
claim_id = result['claim_id']
title = result_value['title']
streaming_url = self._call_api_proxy(
'get', claim_id, {'uri': uri}, 'streaming url')['streaming_url']
info = self._parse_stream(result, url)
info.update({
'id': claim_id,
'title': title,
'url': streaming_url,
})
return info
class LBRYChannelIE(LBRYBaseIE):
IE_NAME = 'lbry:channel'
_VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?#&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
_TESTS = [{
'url': 'https://lbry.tv/@LBRYFoundation:0',
'info_dict': {
'id': '0ed629d2b9c601300cacf7eabe9da0be79010212',
'title': 'The LBRY Foundation',
'description': 'Channel for the LBRY Foundation. Follow for updates and news.',
},
'playlist_count': 29,
}, {
'url': 'https://lbry.tv/@LBRYFoundation',
'only_matching': True,
}]
_PAGE_SIZE = 50
def _fetch_page(self, claim_id, url, page):
page += 1
result = self._call_api_proxy(
'claim_search', claim_id, {
'channel_ids': [claim_id],
'claim_type': 'stream',
'no_totals': True,
'page': page,
'page_size': self._PAGE_SIZE,
'stream_types': self._SUPPORTED_STREAM_TYPES,
}, 'page %d' % page)
for item in (result.get('items') or []):
stream_claim_name = item.get('name')
stream_claim_id = item.get('claim_id')
if not (stream_claim_name and stream_claim_id):
continue
info = self._parse_stream(item, url)
info.update({
'_type': 'url',
'id': stream_claim_id,
'title': try_get(item, lambda x: x['value']['title']),
'url': self._permanent_url(url, stream_claim_name, stream_claim_id),
})
yield info
def _real_extract(self, url):
display_id = self._match_id(url).replace(':', '#')
uri = 'lbry://' + display_id
result = self._call_api_proxy(
'resolve', display_id, {'urls': [uri]})[uri]
result_value = result['value']
if result_value.get('stream_type') not in ('video', 'audio'):
raise ExtractorError('Unsupported URL', expected=True)
streaming_url = self._call_api_proxy(
'get', display_id, {'uri': uri})['streaming_url']
source = result_value.get('source') or {}
media = result_value.get('video') or result_value.get('audio') or {}
signing_channel = result_value.get('signing_channel') or {}
return {
'id': result['claim_id'],
'title': result_value['title'],
'thumbnail': try_get(result_value, lambda x: x['thumbnail']['url'], compat_str),
'description': result_value.get('description'),
'license': result_value.get('license'),
'timestamp': int_or_none(result.get('timestamp')),
'tags': result_value.get('tags'),
'width': int_or_none(media.get('width')),
'height': int_or_none(media.get('height')),
'duration': int_or_none(media.get('duration')),
'channel': signing_channel.get('name'),
'channel_id': signing_channel.get('claim_id'),
'ext': determine_ext(source.get('name')) or mimetype2ext(source.get('media_type')),
'filesize': int_or_none(source.get('size')),
'url': streaming_url,
}
result = self._resolve_url(
'lbry://' + display_id, display_id, 'channel')
claim_id = result['claim_id']
entries = OnDemandPagedList(
functools.partial(self._fetch_page, claim_id, url),
self._PAGE_SIZE)
result_value = result.get('value') or {}
return self.playlist_result(
entries, claim_id, result_value.get('title'),
result_value.get('description'))
+14 -1
View File
@@ -10,7 +10,7 @@ class NhkVodIE(InfoExtractor):
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
# clip
# video clip
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
'md5': '256a1be14f48d960a7e61e2532d95ec3',
'info_dict': {
@@ -21,6 +21,19 @@ class NhkVodIE(InfoExtractor):
'timestamp': 1565965194,
'upload_date': '20190816',
},
}, {
# audio clip
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/r_inventions-20201104-1/',
'info_dict': {
'id': 'r_inventions-20201104-1-en',
'ext': 'm4a',
'title': "Japan's Top Inventions - Miniature Video Cameras",
'description': 'md5:07ea722bdbbb4936fdd360b6a480c25b',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
'only_matching': True,
+238 -194
View File
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import random
import re
from .common import InfoExtractor
@@ -12,17 +14,57 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
js_to_json,
NO_DEFAULT,
parse_age_limit,
parse_duration,
try_get,
urljoin,
url_or_none,
)
class NRKBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['NO']
_CDN_REPL_REGEX = r'''(?x)://
(?:
nrkod\d{1,2}-httpcache0-47115-cacheod0\.dna\.ip-only\.net/47115-cacheod0|
nrk-od-no\.telenorcdn\.net|
minicdn-od\.nrk\.no/od/nrkhd-osl-rr\.netwerk\.no/no
)/'''
def _extract_nrk_formats(self, asset_url, video_id):
if re.match(r'https?://[^/]+\.akamaihd\.net/i/', asset_url):
return self._extract_akamai_formats(
re.sub(r'(?:b=\d+-\d+|__a__=off)&?', '', asset_url), video_id)
asset_url = re.sub(r'(?:bw_(?:low|high)=\d+|no_audio_only)&?', '', asset_url)
formats = self._extract_m3u8_formats(
asset_url, video_id, 'mp4', 'm3u8_native', fatal=False)
if not formats and re.search(self._CDN_REPL_REGEX, asset_url):
formats = self._extract_m3u8_formats(
re.sub(self._CDN_REPL_REGEX, '://nrk-od-%02d.akamaized.net/no/' % random.randint(0, 99), asset_url),
video_id, 'mp4', 'm3u8_native', fatal=False)
return formats
def _raise_error(self, data):
MESSAGES = {
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
'ProgramRightsHasExpired': 'Programmet har gått ut',
'NoProgramRights': 'Ikke tilgjengelig',
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
}
message_type = data.get('messageType', '')
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
if 'IsGeoBlocked' in message_type or try_get(data, lambda x: x['usageRights']['isGeoBlocked']) is True:
self.raise_geo_restricted(
msg=MESSAGES.get('ProgramIsGeoBlocked'),
countries=self._GEO_COUNTRIES)
message = data.get('endUserMessage') or MESSAGES.get(message_type, message_type)
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
def _call_api(self, path, video_id, item=None, note=None, fatal=True, query=None):
return self._download_json(
urljoin('http://psapi.nrk.no/', path),
video_id, note or 'Downloading %s JSON' % item,
fatal=fatal, query=query)
class NRKIE(NRKBaseIE):
@@ -41,7 +83,7 @@ class NRKIE(NRKBaseIE):
_TESTS = [{
# video
'url': 'http://www.nrk.no/video/PS*150533',
'md5': '706f34cdf1322577589e369e522b50ef',
'md5': 'f46be075326e23ad0e524edfcb06aeb6',
'info_dict': {
'id': '150533',
'ext': 'mp4',
@@ -55,7 +97,7 @@ class NRKIE(NRKBaseIE):
# MD5 is unstable
'info_dict': {
'id': '154915',
'ext': 'flv',
'ext': 'mp4',
'title': 'Slik høres internett ut når du er blind',
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
'duration': 20,
@@ -78,9 +120,15 @@ class NRKIE(NRKBaseIE):
}]
def _extract_from_playback(self, video_id):
manifest = self._download_json(
'http://psapi.nrk.no/playback/manifest/%s' % video_id,
video_id, 'Downloading manifest JSON')
path_templ = 'playback/%s/' + video_id
def call_playback_api(item, query=None):
return self._call_api(path_templ % item, video_id, item, query=query)
# known values for preferredCdn: akamai, iponly, minicdn and telenor
manifest = call_playback_api('manifest', {'preferredCdn': 'akamai'})
if manifest.get('playability') == 'nonPlayable':
self._raise_error(manifest['nonPlayable'])
playable = manifest['playable']
@@ -94,14 +142,10 @@ class NRKIE(NRKBaseIE):
if not format_url:
continue
if asset.get('format') == 'HLS' or determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
formats.extend(self._extract_nrk_formats(format_url, video_id))
self._sort_formats(formats)
data = self._download_json(
'http://psapi.nrk.no/playback/metadata/%s' % video_id,
video_id, 'Downloading metadata JSON')
data = call_playback_api('metadata')
preplay = data['preplay']
titles = preplay['titles']
@@ -143,29 +187,22 @@ class NRKIE(NRKBaseIE):
class NRKTVIE(NRKBaseIE):
IE_DESC = 'NRK TV and NRK Radio'
_EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
_VALID_URL = r'''(?x)
https?://
(?:tv|radio)\.nrk(?:super)?\.no/
(?:serie(?:/[^/]+){1,2}|program)/
(?![Ee]pisodes)%s
(?:/\d{2}-\d{2}-\d{4})?
(?:\#del=(?P<part_id>\d+))?
''' % _EPISODE_RE
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:[^/]+/)*%s' % _EPISODE_RE
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
_TESTS = [{
'url': 'https://tv.nrk.no/program/MDDP12000117',
'md5': '8270824df46ec629b66aeaa5796b36fb',
'md5': 'c4a5960f1b00b40d47db65c1064e0ab1',
'info_dict': {
'id': 'MDDP12000117AA',
'ext': 'mp4',
'title': 'Alarm Trolltunga',
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
'duration': 2223,
'duration': 2223.44,
'age_limit': 6,
},
}, {
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': '9a167e54d04671eb6317a37b7bc8a280',
'md5': '8d40dab61cea8ab0114e090b029a0565',
'info_dict': {
'id': 'MUHH48000314AA',
'ext': 'mp4',
@@ -175,7 +212,6 @@ class NRKTVIE(NRKBaseIE):
'series': '20 spørsmål',
'episode': '23.05.2014',
},
'skip': 'NoProgramRights',
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',
'info_dict': {
@@ -183,7 +219,7 @@ class NRKTVIE(NRKBaseIE):
'ext': 'mp4',
'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
'duration': 4605,
'duration': 4605.08,
'series': 'Kunnskapskanalen',
'episode': '24.05.2014',
},
@@ -194,51 +230,25 @@ class NRKTVIE(NRKBaseIE):
# single playlist video
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
'info_dict': {
'id': 'MSPO40010515-part2',
'ext': 'flv',
'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
'description': 'md5:c03aba1e917561eface5214020551b7a',
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Video is geo restricted'],
'expected_warnings': ['Failed to download m3u8 information'],
'skip': 'particular part is not supported currently',
}, {
'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
'playlist': [{
'info_dict': {
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'duration': 772,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}, {
'info_dict': {
'id': 'MSPO40010515BH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'duration': 6175,
'series': 'Tour de Ski',
'episode': '06.01.2015',
},
'params': {
'skip_download': True,
},
}],
'info_dict': {
'id': 'MSPO40010515',
'id': 'MSPO40010515AH',
'ext': 'mp4',
'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',
'description': 'md5:c03aba1e917561eface5214020551b7a',
},
'expected_warnings': ['Video is geo restricted'],
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
'info_dict': {
@@ -269,12 +279,16 @@ class NRKTVIE(NRKBaseIE):
'params': {
'skip_download': True,
},
'skip': 'ProgramRightsHasExpired',
}, {
'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
'only_matching': True,
}, {
'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',
'only_matching': True,
}, {
'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201507/NPUB21019315',
'only_matching': True,
}]
_api_host = None
@@ -295,6 +309,7 @@ class NRKTVIE(NRKBaseIE):
title = data.get('fullTitle') or data.get('mainTitle') or data['title']
video_id = data.get('id') or video_id
urls = []
entries = []
conviva = data.get('convivaStatistics') or {}
@@ -311,19 +326,14 @@ class NRKTVIE(NRKBaseIE):
else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
for num, asset in enumerate(media_assets, 1):
asset_url = asset.get('url')
if not asset_url:
if not asset_url or asset_url in urls:
continue
formats = self._extract_akamai_formats(asset_url, video_id)
urls.append(asset_url)
formats = self._extract_nrk_formats(asset_url, video_id)
if not formats:
continue
self._sort_formats(formats)
# Some f4m streams may not work with hdcore in fragments' URLs
for f in formats:
extra_param = f.get('extra_param_to_segment_url')
if extra_param and 'hdcore' in extra_param:
del f['extra_param_to_segment_url']
entry_id, entry_title = video_id_and_title(num)
duration = parse_duration(asset.get('duration'))
subtitles = {}
@@ -339,38 +349,26 @@ class NRKTVIE(NRKBaseIE):
'duration': duration,
'subtitles': subtitles,
'formats': formats,
'is_live': live,
})
if not entries:
media_url = data.get('mediaUrl')
if media_url:
formats = self._extract_akamai_formats(media_url, video_id)
self._sort_formats(formats)
duration = parse_duration(data.get('duration'))
entries = [{
'id': video_id,
'title': make_title(title),
'duration': duration,
'formats': formats,
}]
if media_url and media_url not in urls:
formats = self._extract_nrk_formats(media_url, video_id)
if formats:
self._sort_formats(formats)
duration = parse_duration(data.get('duration'))
entries = [{
'id': video_id,
'title': make_title(title),
'duration': duration,
'formats': formats,
'is_live': live,
}]
if not entries:
MESSAGES = {
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
'ProgramRightsHasExpired': 'Programmet har gått ut',
'NoProgramRights': 'Ikke tilgjengelig',
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
}
message_type = data.get('messageType', '')
# Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
if 'IsGeoBlocked' in message_type:
self.raise_geo_restricted(
msg=MESSAGES.get('ProgramIsGeoBlocked'),
countries=self._GEO_COUNTRIES)
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, MESSAGES.get(
message_type, message_type)),
expected=True)
self._raise_error(data)
series = conviva.get('seriesName') or data.get('seriesTitle')
episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
@@ -512,57 +510,98 @@ class NRKTVEpisodeIE(InfoExtractor):
return info
class NRKTVSerieBaseIE(InfoExtractor):
def _extract_series(self, webpage, display_id, fatal=True):
config = self._parse_json(
self._search_regex(
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False, transform_source=js_to_json)
if not config:
return
return try_get(
config,
(lambda x: x['initialState']['series'], lambda x: x['series']),
dict)
def _extract_seasons(self, seasons):
if not isinstance(seasons, list):
return []
entries = []
for season in seasons:
entries.extend(self._extract_episodes(season))
return entries
def _extract_episodes(self, season):
if not isinstance(season, dict):
return []
return self._extract_entries(season.get('episodes'))
class NRKTVSerieBaseIE(NRKBaseIE):
def _extract_entries(self, entry_list):
if not isinstance(entry_list, list):
return []
entries = []
for episode in entry_list:
nrk_id = episode.get('prfId')
nrk_id = episode.get('prfId') or episode.get('episodeId')
if not nrk_id or not isinstance(nrk_id, compat_str):
continue
if not re.match(NRKTVIE._EPISODE_RE, nrk_id):
continue
entries.append(self.url_result(
'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))
return entries
_ASSETS_KEYS = ('episodes', 'instalments',)
def _extract_assets_key(self, embedded):
for asset_key in self._ASSETS_KEYS:
if embedded.get(asset_key):
return asset_key
def _entries(self, data, display_id):
for page_num in itertools.count(1):
embedded = data.get('_embedded') or data
if not isinstance(embedded, dict):
break
assets_key = self._extract_assets_key(embedded)
if not assets_key:
break
# Extract entries
entries = try_get(
embedded,
(lambda x: x[assets_key]['_embedded'][assets_key],
lambda x: x[assets_key]),
list)
for e in self._extract_entries(entries):
yield e
# Find next URL
next_url_path = try_get(
data,
(lambda x: x['_links']['next']['href'],
lambda x: x['_embedded'][assets_key]['_links']['next']['href']),
compat_str)
if not next_url_path:
break
data = self._call_api(
next_url_path, display_id,
note='Downloading %s JSON page %d' % (assets_key, page_num),
fatal=False)
if not data:
break
class NRKTVSeasonIE(NRKTVSerieBaseIE):
_VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'
_TEST = {
_VALID_URL = r'https?://(?P<domain>tv|radio)\.nrk\.no/serie/(?P<serie>[^/]+)/(?:sesong/)?(?P<id>\d+)'
_TESTS = [{
'url': 'https://tv.nrk.no/serie/backstage/sesong/1',
'info_dict': {
'id': '1',
'id': 'backstage/1',
'title': 'Sesong 1',
},
'playlist_mincount': 30,
}
}, {
# no /sesong/ in path
'url': 'https://tv.nrk.no/serie/lindmo/2016',
'info_dict': {
'id': 'lindmo/2016',
'title': '2016',
},
'playlist_mincount': 29,
}, {
# weird nested _embedded in catalog JSON response
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens/sesong/1',
'info_dict': {
'id': 'dickie-dick-dickens/1',
'title': 'Sesong 1',
},
'playlist_mincount': 11,
}, {
# 841 entries, multi page
'url': 'https://radio.nrk.no/serie/dagsnytt/sesong/201509',
'info_dict': {
'id': 'dagsnytt/201509',
'title': 'September 2015',
},
'playlist_mincount': 841,
}, {
# 180 entries, single page
'url': 'https://tv.nrk.no/serie/spangas/sesong/1',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
@@ -570,25 +609,35 @@ class NRKTVSeasonIE(NRKTVSerieBaseIE):
else super(NRKTVSeasonIE, cls).suitable(url))
def _real_extract(self, url):
display_id = self._match_id(url)
domain, serie, season_id = re.match(self._VALID_URL, url).groups()
display_id = '%s/%s' % (serie, season_id)
webpage = self._download_webpage(url, display_id)
data = self._call_api(
'%s/catalog/series/%s/seasons/%s' % (domain, serie, season_id),
display_id, 'season', query={'pageSize': 50})
series = self._extract_series(webpage, display_id)
season = next(
s for s in series['seasons']
if int(display_id) == s.get('seasonNumber'))
title = try_get(season, lambda x: x['titles']['title'], compat_str)
title = try_get(data, lambda x: x['titles']['title'], compat_str) or display_id
return self.playlist_result(
self._extract_episodes(season), display_id, title)
self._entries(data, display_id),
display_id, title)
class NRKTVSeriesIE(NRKTVSerieBaseIE):
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
_VALID_URL = r'https?://(?P<domain>(?:tv|radio)\.nrk|(?:tv\.)?nrksuper)\.no/serie/(?P<id>[^/]+)'
_TESTS = [{
# new layout, instalments
'url': 'https://tv.nrk.no/serie/groenn-glede',
'info_dict': {
'id': 'groenn-glede',
'title': 'Grønn glede',
'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
},
'playlist_mincount': 90,
}, {
# new layout, instalments, more entries
'url': 'https://tv.nrk.no/serie/lindmo',
'only_matching': True,
}, {
'url': 'https://tv.nrk.no/serie/blank',
'info_dict': {
'id': 'blank',
@@ -602,25 +651,16 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
'info_dict': {
'id': 'backstage',
'title': 'Backstage',
'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',
'description': 'md5:63692ceb96813d9a207e9910483d948b',
},
'playlist_mincount': 60,
}, {
# new layout, instalments
'url': 'https://tv.nrk.no/serie/groenn-glede',
'info_dict': {
'id': 'groenn-glede',
'title': 'Grønn glede',
'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
},
'playlist_mincount': 10,
}, {
# old layout
'url': 'https://tv.nrksuper.no/serie/labyrint',
'info_dict': {
'id': 'labyrint',
'title': 'Labyrint',
'description': 'md5:318b597330fdac5959247c9b69fdb1ec',
'description': 'I Daidalos sin undersjøiske Labyrint venter spennende oppgaver, skumle robotskapninger og slim.',
},
'playlist_mincount': 3,
}, {
@@ -632,6 +672,17 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
}, {
'url': 'https://tv.nrk.no/serie/postmann-pat',
'only_matching': True,
}, {
'url': 'https://radio.nrk.no/serie/dickie-dick-dickens',
'info_dict': {
'id': 'dickie-dick-dickens',
'title': 'Dickie Dick Dickens',
'description': 'md5:19e67411ffe57f7dce08a943d7a0b91f',
},
'playlist_mincount': 8,
}, {
'url': 'https://nrksuper.no/serie/labyrint',
'only_matching': True,
}]
@classmethod
@@ -642,43 +693,42 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
else super(NRKTVSeriesIE, cls).suitable(url))
def _real_extract(self, url):
series_id = self._match_id(url)
site, series_id = re.match(self._VALID_URL, url).groups()
is_radio = site == 'radio.nrk'
domain = 'radio' if is_radio else 'tv'
webpage = self._download_webpage(url, series_id)
size_prefix = 'p' if is_radio else 'embeddedInstalmentsP'
series = self._call_api(
'%s/catalog/series/%s' % (domain, series_id),
series_id, 'serie', query={size_prefix + 'ageSize': 50})
titles = try_get(series, [
lambda x: x['titles'],
lambda x: x[x['type']]['titles'],
lambda x: x[x['seriesType']]['titles'],
]) or {}
# New layout (e.g. https://tv.nrk.no/serie/backstage)
series = self._extract_series(webpage, series_id, fatal=False)
if series:
title = try_get(series, lambda x: x['titles']['title'], compat_str)
description = try_get(
series, lambda x: x['titles']['subtitle'], compat_str)
entries = []
entries.extend(self._extract_seasons(series.get('seasons')))
entries.extend(self._extract_entries(series.get('instalments')))
entries.extend(self._extract_episodes(series.get('extraMaterial')))
return self.playlist_result(entries, series_id, title, description)
entries = []
entries.extend(self._entries(series, series_id))
embedded = series.get('_embedded') or {}
linked_seasons = try_get(series, lambda x: x['_links']['seasons']) or []
embedded_seasons = embedded.get('seasons') or []
if len(linked_seasons) > len(embedded_seasons):
for season in linked_seasons:
season_name = season.get('name')
if season_name and isinstance(season_name, compat_str):
entries.append(self.url_result(
'https://%s.nrk.no/serie/%s/sesong/%s'
% (domain, series_id, season_name),
ie=NRKTVSeasonIE.ie_key(),
video_title=season.get('title')))
else:
for season in embedded_seasons:
entries.extend(self._entries(season, series_id))
entries.extend(self._entries(
embedded.get('extraMaterial') or {}, series_id))
# Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)
entries = [
self.url_result(
'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
series=series_id, season=season_id))
for season_id in re.findall(self._ITEM_RE, webpage)
]
title = self._html_search_meta(
'seriestitle', webpage,
'title', default=None) or self._og_search_title(
webpage, fatal=False)
if title:
title = self._search_regex(
r'NRK (?:Super )?TV\s*[-]\s*(.+)', title, 'title', default=title)
description = self._html_search_meta(
'series_description', webpage,
'description', default=None) or self._og_search_description(webpage)
return self.playlist_result(entries, series_id, title, description)
return self.playlist_result(
entries, series_id, titles.get('title'), titles.get('subtitle'))
class NRKTVDirekteIE(NRKTVIE):
@@ -782,14 +832,8 @@ class NRKSkoleIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
video_id)
nrk_id = self._parse_json(
self._search_regex(
r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
webpage, 'application json'),
video_id)['activeMedia']['psId']
nrk_id = self._download_json(
'https://nrkno-skole-prod.kube.nrk.no/skole/api/media/%s' % video_id,
video_id)['psId']
return self.url_result('nrk:%s' % nrk_id)
+4
View File
@@ -541,6 +541,10 @@ class PeerTubeIE(InfoExtractor):
'format_id': format_id,
'filesize': file_size,
})
if format_id == '0p':
f['vcodec'] = 'none'
else:
f['fps'] = int_or_none(file_.get('fps'))
formats.append(f)
self._sort_formats(formats)
+14 -6
View File
@@ -31,7 +31,12 @@ class PornHubBaseIE(InfoExtractor):
def dl(*args, **kwargs):
return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
webpage, urlh = dl(*args, **kwargs)
ret = dl(*args, **kwargs)
if not ret:
return ret
webpage, urlh = ret
if any(re.search(p, webpage) for p in (
r'<body\b[^>]+\bonload=["\']go\(\)',
@@ -53,7 +58,7 @@ class PornHubIE(PornHubBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
@@ -152,6 +157,9 @@ class PornHubIE(PornHubBaseIE):
}, {
'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
'only_matching': True,
}, {
'url': 'https://www.pornhub.org/view_video.php?viewkey=203640933',
'only_matching': True,
}, {
'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82',
'only_matching': True,
@@ -160,7 +168,7 @@ class PornHubIE(PornHubBaseIE):
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net|org)/embed/[\da-z]+)',
webpage)
def _extract_count(self, pattern, webpage, name):
@@ -422,7 +430,7 @@ class PornHubPlaylistBaseIE(PornHubBaseIE):
class PornHubUserIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph',
'playlist_mincount': 118,
@@ -490,7 +498,7 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
@@ -605,7 +613,7 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
_TESTS = [{
'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
'info_dict': {
+83 -9
View File
@@ -6,14 +6,24 @@ from ..compat import compat_urllib_parse_urlparse
from ..utils import (
determine_ext,
ExtractorError,
find_xpath_attr,
int_or_none,
unified_strdate,
url_or_none,
xpath_attr,
xpath_text,
)
class RuutuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla)/(?P<id>\d+)'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
)
(?P<id>\d+)
'''
_TESTS = [
{
'url': 'http://www.ruutu.fi/video/2058907',
@@ -71,15 +81,53 @@ class RuutuIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 0,
},
'expected_warnings': ['HTTP Error 502: Bad Gateway'],
}
'expected_warnings': [
'HTTP Error 502: Bad Gateway',
'Failed to download m3u8 information',
],
},
{
'url': 'http://www.supla.fi/audio/2231370',
'only_matching': True,
},
{
'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
'only_matching': True,
},
{
# episode
'url': 'https://www.ruutu.fi/video/3401964',
'info_dict': {
'id': '3401964',
'ext': 'mp4',
'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2582,
'age_limit': 12,
'upload_date': '20190508',
'series': 'Temptation Island Suomi',
'season_number': 5,
'episode_number': 17,
'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
},
'params': {
'skip_download': True,
},
},
{
# premium
'url': 'https://www.ruutu.fi/video/3618715',
'only_matching': True,
},
]
_API_BASE = 'https://gatling.nelonenmedia.fi'
def _real_extract(self, url):
video_id = self._match_id(url)
video_xml = self._download_xml(
'https://gatling.nelonenmedia.fi/media-xml-cache', video_id,
'%s/media-xml-cache' % self._API_BASE, video_id,
query={'id': video_id})
formats = []
@@ -96,9 +144,18 @@ class RuutuIE(InfoExtractor):
continue
processed_urls.append(video_url)
ext = determine_ext(video_url)
auth_video_url = url_or_none(self._download_webpage(
'%s/auth/access/v2' % self._API_BASE, video_id,
note='Downloading authenticated %s stream URL' % ext,
fatal=False, query={'stream': video_url}))
if auth_video_url:
processed_urls.append(auth_video_url)
video_url = auth_video_url
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
video_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds', fatal=False))
@@ -136,18 +193,35 @@ class RuutuIE(InfoExtractor):
extract_formats(video_xml.find('./Clip'))
drm = xpath_text(video_xml, './Clip/DRM', default=None)
if not formats and drm:
raise ExtractorError('This video is DRM protected.', expected=True)
def pv(name):
node = find_xpath_attr(
video_xml, './Clip/PassthroughVariables/variable', 'name', name)
if node is not None:
return node.get('value')
if not formats:
drm = xpath_text(video_xml, './Clip/DRM', default=None)
if drm:
raise ExtractorError('This video is DRM protected.', expected=True)
ns_st_cds = pv('ns_st_cds')
if ns_st_cds != 'free':
raise ExtractorError('This video is %s.' % ns_st_cds, expected=True)
self._sort_formats(formats)
themes = pv('themes')
return {
'id': video_id,
'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')),
'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
'upload_date': unified_strdate(pv('date_start')),
'series': pv('series_name'),
'season_number': int_or_none(pv('season_number')),
'episode_number': int_or_none(pv('episode_number')),
'categories': themes.split(',') if themes else [],
'formats': formats,
}
+51 -4
View File
@@ -2,7 +2,12 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
from ..utils import (
bool_or_none,
smuggle_url,
try_get,
url_or_none,
)
class SlidesLiveIE(InfoExtractor):
@@ -18,8 +23,21 @@ class SlidesLiveIE(InfoExtractor):
'description': 'Watch full version of this video at https://slideslive.com/38902413.',
'uploader': 'SlidesLive Videos - A',
'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
'timestamp': 1597615266,
'upload_date': '20170925',
}
}, {
# video_service_name = yoda
'url': 'https://slideslive.com/38935785',
'md5': '575cd7a6c0acc6e28422fe76dd4bcb1a',
'info_dict': {
'id': 'RMraDYN5ozA_',
'ext': 'mp4',
'title': 'Offline Reinforcement Learning: From Algorithms to Practical Challenges',
},
'params': {
'format': 'bestvideo',
},
}, {
# video_service_name = youtube
'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend',
@@ -39,18 +57,47 @@ class SlidesLiveIE(InfoExtractor):
video_data = self._download_json(
'https://ben.slideslive.com/player/' + video_id, video_id)
service_name = video_data['video_service_name'].lower()
assert service_name in ('url', 'vimeo', 'youtube')
assert service_name in ('url', 'yoda', 'vimeo', 'youtube')
service_id = video_data['video_service_id']
subtitles = {}
for sub in try_get(video_data, lambda x: x['subtitles'], list) or []:
if not isinstance(sub, dict):
continue
webvtt_url = url_or_none(sub.get('webvtt_url'))
if not webvtt_url:
continue
lang = sub.get('language') or 'en'
subtitles.setdefault(lang, []).append({
'url': webvtt_url,
})
info = {
'id': video_id,
'thumbnail': video_data.get('thumbnail'),
'url': service_id,
'is_live': bool_or_none(video_data.get('is_live')),
'subtitles': subtitles,
}
if service_name == 'url':
if service_name in ('url', 'yoda'):
info['title'] = video_data['title']
if service_name == 'url':
info['url'] = service_id
else:
formats = []
_MANIFEST_PATTERN = 'https://01.cdn.yoda.slideslive.com/%s/master.%s'
formats.extend(self._extract_m3u8_formats(
_MANIFEST_PATTERN % (service_id, 'm3u8'), service_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
formats.extend(self._extract_mpd_formats(
_MANIFEST_PATTERN % (service_id, 'mpd'), service_id,
mpd_id='dash', fatal=False))
self._sort_formats(formats)
info.update({
'id': service_id,
'formats': formats,
})
else:
info.update({
'_type': 'url_transparent',
'url': service_id,
'ie_key': service_name.capitalize(),
'title': video_data.get('title'),
})
-416
View File
@@ -1,416 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
import hashlib
import uuid
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
unified_strdate,
urlencode_postdata,
xpath_text,
)
class SmotriIE(InfoExtractor):
IE_DESC = 'Smotri.com'
IE_NAME = 'smotri'
_VALID_URL = r'https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
_NETRC_MACHINE = 'smotri'
_TESTS = [
# real video id 2610366
{
'url': 'http://smotri.com/video/view/?id=v261036632ab',
'md5': '02c0dfab2102984e9c5bb585cc7cc321',
'info_dict': {
'id': 'v261036632ab',
'ext': 'mp4',
'title': 'катастрофа с камер видеонаблюдения',
'uploader': 'rbc2008',
'uploader_id': 'rbc08',
'upload_date': '20131118',
'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg',
},
},
# real video id 57591
{
'url': 'http://smotri.com/video/view/?id=v57591cb20',
'md5': '830266dfc21f077eac5afd1883091bcd',
'info_dict': {
'id': 'v57591cb20',
'ext': 'flv',
'title': 'test',
'uploader': 'Support Photofile@photofile',
'uploader_id': 'support-photofile',
'upload_date': '20070704',
'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg',
},
},
# video-password, not approved by moderator
{
'url': 'http://smotri.com/video/view/?id=v1390466a13c',
'md5': 'f6331cef33cad65a0815ee482a54440b',
'info_dict': {
'id': 'v1390466a13c',
'ext': 'mp4',
'title': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1',
'uploader': 'timoxa40',
'uploader_id': 'timoxa40',
'upload_date': '20100404',
'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg',
},
'params': {
'videopassword': 'qwerty',
},
'skip': 'Video is not approved by moderator',
},
# video-password
{
'url': 'http://smotri.com/video/view/?id=v6984858774#',
'md5': 'f11e01d13ac676370fc3b95b9bda11b0',
'info_dict': {
'id': 'v6984858774',
'ext': 'mp4',
'title': 'Дача Солженицина ПАРОЛЬ 223322',
'uploader': 'psavari1',
'uploader_id': 'psavari1',
'upload_date': '20081103',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'videopassword': '223322',
},
},
# age limit + video-password, not approved by moderator
{
'url': 'http://smotri.com/video/view/?id=v15408898bcf',
'md5': '91e909c9f0521adf5ee86fbe073aad70',
'info_dict': {
'id': 'v15408898bcf',
'ext': 'flv',
'title': 'этот ролик не покажут по ТВ',
'uploader': 'zzxxx',
'uploader_id': 'ueggb',
'upload_date': '20101001',
'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg',
'age_limit': 18,
},
'params': {
'videopassword': '333'
},
'skip': 'Video is not approved by moderator',
},
# age limit + video-password
{
'url': 'http://smotri.com/video/view/?id=v7780025814',
'md5': 'b4599b068422559374a59300c5337d72',
'info_dict': {
'id': 'v7780025814',
'ext': 'mp4',
'title': 'Sexy Beach (пароль 123)',
'uploader': 'вАся',
'uploader_id': 'asya_prosto',
'upload_date': '20081218',
'thumbnail': r're:^https?://.*\.jpg$',
'age_limit': 18,
},
'params': {
'videopassword': '123'
},
},
# swf player
{
'url': 'http://pics.smotri.com/scrubber_custom8.swf?file=v9188090500',
'md5': '31099eeb4bc906712c5f40092045108d',
'info_dict': {
'id': 'v9188090500',
'ext': 'mp4',
'title': 'Shakira - Don\'t Bother',
'uploader': 'HannahL',
'uploader_id': 'lisaha95',
'upload_date': '20090331',
'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg',
},
},
]
@classmethod
def _extract_url(cls, webpage):
mobj = re.search(
r'<embed[^>]src=(["\'])(?P<url>http://pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=v.+?\1)',
webpage)
if mobj is not None:
return mobj.group('url')
mobj = re.search(
r'''(?x)<div\s+class="video_file">http://smotri\.com/video/download/file/[^<]+</div>\s*
<div\s+class="video_image">[^<]+</div>\s*
<div\s+class="video_id">(?P<id>[^<]+)</div>''', webpage)
if mobj is not None:
return 'http://smotri.com/video/view/?id=%s' % mobj.group('id')
def _search_meta(self, name, html, display_name=None):
if display_name is None:
display_name = name
return self._html_search_meta(name, html, display_name)
def _real_extract(self, url):
video_id = self._match_id(url)
video_form = {
'ticket': video_id,
'video_url': '1',
'frame_url': '1',
'devid': 'LoadupFlashPlayer',
'getvideoinfo': '1',
}
video_password = self._downloader.params.get('videopassword')
if video_password:
video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
video = self._download_json(
'http://smotri.com/video/view/url/bot/',
video_id, 'Downloading video JSON',
data=urlencode_postdata(video_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
if not video_url:
if video.get('_moderate_no'):
raise ExtractorError(
'Video %s has not been approved by moderator' % video_id, expected=True)
if video.get('error'):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
if video.get('_pass_protected') == 1:
msg = ('Invalid video password' if video_password
else 'This video is protected by a password, use the --video-password option')
raise ExtractorError(msg, expected=True)
title = video['title']
thumbnail = video.get('_imgURL')
upload_date = unified_strdate(video.get('added'))
uploader = video.get('userNick')
uploader_id = video.get('userLogin')
duration = int_or_none(video.get('duration'))
# Video JSON does not provide enough meta data
# We will extract some from the video web page instead
webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id
webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page')
# Warning if video is unavailable
warning = self._html_search_regex(
r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,
'warning message', default=None)
if warning is not None:
self._downloader.report_warning(
'Video %s may not be available; smotri said: %s ' %
(video_id, warning))
# Adult content
if 'EroConfirmText">' in webpage:
self.report_age_confirmation()
confirm_string = self._html_search_regex(
r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,
webpage, 'confirm string')
confirm_url = webpage_url + '&confirm=%s' % confirm_string
webpage = self._download_webpage(
confirm_url, video_id,
'Downloading video page (age confirmed)')
adult_content = True
else:
adult_content = False
view_count = self._html_search_regex(
r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
webpage, 'view count', fatal=False)
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
'uploader_id': uploader_id,
'duration': duration,
'view_count': int_or_none(view_count),
'age_limit': 18 if adult_content else 0,
}
class SmotriCommunityIE(InfoExtractor):
IE_DESC = 'Smotri.com community videos'
IE_NAME = 'smotri:community'
_VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'
_TEST = {
'url': 'http://smotri.com/community/video/kommuna',
'info_dict': {
'id': 'kommuna',
},
'playlist_mincount': 4,
}
def _real_extract(self, url):
community_id = self._match_id(url)
rss = self._download_xml(
'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
community_id, 'Downloading community RSS')
entries = [
self.url_result(video_url.text, SmotriIE.ie_key())
for video_url in rss.findall('./channel/item/link')]
return self.playlist_result(entries, community_id)
class SmotriUserIE(InfoExtractor):
IE_DESC = 'Smotri.com user videos'
IE_NAME = 'smotri:user'
_VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'
_TESTS = [{
'url': 'http://smotri.com/user/inspector',
'info_dict': {
'id': 'inspector',
'title': 'Inspector',
},
'playlist_mincount': 9,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
rss = self._download_xml(
'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
user_id, 'Downloading user RSS')
entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')]
description_text = xpath_text(rss, './channel/description') or ''
user_nickname = self._search_regex(
'^Видео режиссера (.+)$', description_text,
'user nickname', fatal=False)
return self.playlist_result(entries, user_id, user_nickname)
class SmotriBroadcastIE(InfoExtractor):
IE_DESC = 'Smotri.com broadcasts'
IE_NAME = 'smotri:broadcast'
_VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
_NETRC_MACHINE = 'smotri'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
broadcast_id = mobj.group('id')
broadcast_url = 'http://' + mobj.group('url')
broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
if re.search('>Режиссер с логином <br/>"%s"<br/> <span>не существует<' % broadcast_id, broadcast_page) is not None:
raise ExtractorError(
'Broadcast %s does not exist' % broadcast_id, expected=True)
# Adult content
if re.search('EroConfirmText">', broadcast_page) is not None:
(username, password) = self._get_login_info()
if username is None:
self.raise_login_required(
'Erotic broadcasts allowed only for registered users')
login_form = {
'login-hint53': '1',
'confirm_erotic': '1',
'login': username,
'password': password,
}
request = sanitized_Request(
broadcast_url + '/?no_redirect=1', urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
broadcast_page = self._download_webpage(
request, broadcast_id, 'Logging in and confirming age')
if '>Неверный логин или пароль<' in broadcast_page:
raise ExtractorError(
'Unable to log in: bad username or password', expected=True)
adult_content = True
else:
adult_content = False
ticket = self._html_search_regex(
(r'data-user-file=(["\'])(?P<ticket>(?!\1).+)\1',
r"window\.broadcast_control\.addFlashVar\('file'\s*,\s*'(?P<ticket>[^']+)'\)"),
broadcast_page, 'broadcast ticket', group='ticket')
broadcast_url = 'http://smotri.com/broadcast/view/url/?ticket=%s' % ticket
broadcast_password = self._downloader.params.get('videopassword')
if broadcast_password:
broadcast_url += '&pass=%s' % hashlib.md5(broadcast_password.encode('utf-8')).hexdigest()
broadcast_json_page = self._download_webpage(
broadcast_url, broadcast_id, 'Downloading broadcast JSON')
try:
broadcast_json = json.loads(broadcast_json_page)
protected_broadcast = broadcast_json['_pass_protected'] == 1
if protected_broadcast and not broadcast_password:
raise ExtractorError(
'This broadcast is protected by a password, use the --video-password option',
expected=True)
broadcast_offline = broadcast_json['is_play'] == 0
if broadcast_offline:
raise ExtractorError('Broadcast %s is offline' % broadcast_id, expected=True)
rtmp_url = broadcast_json['_server']
mobj = re.search(r'^rtmp://[^/]+/(?P<app>.+)/?$', rtmp_url)
if not mobj:
raise ExtractorError('Unexpected broadcast rtmp URL')
broadcast_playpath = broadcast_json['_streamName']
broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
broadcast_thumbnail = broadcast_json.get('_imgURL')
broadcast_title = self._live_title(broadcast_json['title'])
broadcast_description = broadcast_json.get('description')
broadcaster_nick = broadcast_json.get('nick')
broadcaster_login = broadcast_json.get('login')
rtmp_conn = 'S:%s' % uuid.uuid4().hex
except KeyError:
if protected_broadcast:
raise ExtractorError('Bad broadcast password', expected=True)
raise ExtractorError('Unexpected broadcast JSON')
return {
'id': broadcast_id,
'url': rtmp_url,
'title': broadcast_title,
'thumbnail': broadcast_thumbnail,
'description': broadcast_description,
'uploader': broadcaster_nick,
'uploader_id': broadcaster_login,
'age_limit': 18 if adult_content else 0,
'ext': 'flv',
'play_path': broadcast_playpath,
'player_url': 'http://pics.smotri.com/broadcast_play.swf',
'app': broadcast_app,
'rtmp_live': True,
'rtmp_conn': rtmp_conn,
'is_live': True,
}
+1 -1
View File
@@ -269,7 +269,7 @@ class TeachableCourseIE(TeachableBaseIE):
r'(?s)(?P<li><li[^>]+class=(["\'])(?:(?!\2).)*?section-item[^>]+>.+?</li>)',
webpage):
li = mobj.group('li')
if 'fa-youtube-play' not in li:
if 'fa-youtube-play' not in li and not re.search(r'\d{1,2}:\d{2}', li):
continue
lecture_url = self._search_regex(
r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', li,
+87 -73
View File
@@ -12,25 +12,16 @@ from ..utils import (
class TeleQuebecBaseIE(InfoExtractor):
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
@staticmethod
def _result(url, ie_key):
def _brightcove_result(brightcove_id, player_id, account_id='6150020952001'):
return {
'_type': 'url_transparent',
'url': smuggle_url(url, {'geo_countries': ['CA']}),
'ie_key': ie_key,
'url': smuggle_url(TeleQuebecBaseIE.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, brightcove_id), {'geo_countries': ['CA']}),
'ie_key': 'BrightcoveNew',
}
@staticmethod
def _limelight_result(media_id):
return TeleQuebecBaseIE._result(
'limelight:media:' + media_id, 'LimelightMedia')
@staticmethod
def _brightcove_result(brightcove_id):
return TeleQuebecBaseIE._result(
'http://players.brightcove.net/6150020952001/default_default/index.html?videoId=%s'
% brightcove_id, 'BrightcoveNew')
class TeleQuebecIE(TeleQuebecBaseIE):
_VALID_URL = r'''(?x)
@@ -44,14 +35,18 @@ class TeleQuebecIE(TeleQuebecBaseIE):
# available till 01.01.2023
'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
'info_dict': {
'id': '577116881b4b439084e6b1cf4ef8b1b3',
'id': '6155972771001',
'ext': 'mp4',
'title': 'Un petit choc et puis repart!',
'description': 'md5:067bc84bd6afecad85e69d1000730907',
'description': 'md5:b04a7e6b3f74e32d7b294cffe8658374',
'timestamp': 1589262469,
'uploader_id': '6150020952001',
'upload_date': '20200512',
},
'params': {
'skip_download': True,
'format': 'bestvideo',
},
'add_ie': ['BrightcoveNew'],
}, {
'url': 'https://zonevideo.telequebec.tv/media/55267/le-soleil/passe-partout',
'info_dict': {
@@ -65,7 +60,6 @@ class TeleQuebecIE(TeleQuebecBaseIE):
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
'add_ie': ['BrightcoveNew'],
}, {
@@ -79,25 +73,20 @@ class TeleQuebecIE(TeleQuebecBaseIE):
def _real_extract(self, url):
media_id = self._match_id(url)
media_data = self._download_json(
'https://mnmedias.api.telequebec.tv/api/v2/media/' + media_id,
media = self._download_json(
'https://mnmedias.api.telequebec.tv/api/v3/media/' + media_id,
media_id)['media']
source_id = media_data['streamInfo']['sourceId']
source = (try_get(
media_data, lambda x: x['streamInfo']['source'],
compat_str) or 'limelight').lower()
if source == 'brightcove':
info = self._brightcove_result(source_id)
else:
info = self._limelight_result(source_id)
source_id = next(source_info['sourceId'] for source_info in media['streamInfos'] if source_info.get('source') == 'Brightcove')
info = self._brightcove_result(source_id, '22gPKdt7f')
product = media.get('product') or {}
season = product.get('season') or {}
info.update({
'title': media_data.get('title'),
'description': try_get(
media_data, lambda x: x['descriptions'][0]['text'], compat_str),
'duration': int_or_none(
media_data.get('durationInMilliseconds'), 1000),
'description': try_get(media, lambda x: x['descriptions'][-1]['text'], compat_str),
'series': try_get(season, lambda x: x['serie']['titre']),
'season': season.get('name'),
'season_number': int_or_none(season.get('seasonNo')),
'episode': product.get('titre'),
'episode_number': int_or_none(product.get('episodeNo')),
})
return info
@@ -148,7 +137,7 @@ class TeleQuebecSquatIE(InfoExtractor):
}
class TeleQuebecEmissionIE(TeleQuebecBaseIE):
class TeleQuebecEmissionIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
@@ -160,15 +149,16 @@ class TeleQuebecEmissionIE(TeleQuebecBaseIE):
_TESTS = [{
'url': 'http://lindicemcsween.telequebec.tv/emissions/100430013/des-soins-esthetiques-a-377-d-interets-annuels-ca-vous-tente',
'info_dict': {
'id': '66648a6aef914fe3badda25e81a4d50a',
'id': '6154476028001',
'ext': 'mp4',
'title': "Des soins esthétiques à 377 % d'intérêts annuels, ça vous tente?",
'description': 'md5:369e0d55d0083f1fc9b71ffb640ea014',
'upload_date': '20171024',
'timestamp': 1508862118,
'title': 'Des soins esthétiques à 377 % dintérêts annuels, ça vous tente?',
'description': 'md5:cb4d378e073fae6cce1f87c00f84ae9f',
'upload_date': '20200505',
'timestamp': 1588713424,
'uploader_id': '6150020952001',
},
'params': {
'skip_download': True,
'format': 'bestvideo',
},
}, {
'url': 'http://bancpublic.telequebec.tv/emissions/emission-49/31986/jeunes-meres-sous-pression',
@@ -187,26 +177,26 @@ class TeleQuebecEmissionIE(TeleQuebecBaseIE):
webpage = self._download_webpage(url, display_id)
media_id = self._search_regex(
r'mediaUID\s*:\s*["\'][Ll]imelight_(?P<id>[a-z0-9]{32})', webpage,
'limelight id')
r'mediaId\s*:\s*(?P<id>\d+)', webpage, 'media id')
info = self._limelight_result(media_id)
info.update({
'title': self._og_search_title(webpage, default=None),
'description': self._og_search_description(webpage, default=None),
})
return info
return self.url_result(
'http://zonevideo.telequebec.tv/media/' + media_id,
TeleQuebecIE.ie_key())
class TeleQuebecLiveIE(InfoExtractor):
class TeleQuebecLiveIE(TeleQuebecBaseIE):
_VALID_URL = r'https?://zonevideo\.telequebec\.tv/(?P<id>endirect)'
_TEST = {
'url': 'http://zonevideo.telequebec.tv/endirect/',
'info_dict': {
'id': 'endirect',
'id': '6159095684001',
'ext': 'mp4',
'title': 're:^Télé-Québec - En direct [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^Télé-Québec [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
'description': 'Canal principal de Télé-Québec',
'uploader_id': '6150020952001',
'timestamp': 1590439901,
'upload_date': '20200525',
},
'params': {
'skip_download': True,
@@ -214,25 +204,49 @@ class TeleQuebecLiveIE(InfoExtractor):
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._brightcove_result('6159095684001', 'skCsmi2Uw')
m3u8_url = None
webpage = self._download_webpage(
'https://player.telequebec.tv/Tq_VideoPlayer.js', video_id,
fatal=False)
if webpage:
m3u8_url = self._search_regex(
r'm3U8Url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'm3u8 url', default=None, group='url')
if not m3u8_url:
m3u8_url = 'https://teleqmmd.mmdlive.lldns.net/teleqmmd/f386e3b206814e1f8c8c1c71c0f8e748/manifest.m3u8'
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls')
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title('Télé-Québec - En direct'),
'is_live': True,
'formats': formats,
}
class TeleQuebecVideoIE(TeleQuebecBaseIE):
_VALID_URL = r'https?://video\.telequebec\.tv/player(?:-live)?/(?P<id>\d+)'
_TESTS = [{
'url': 'https://video.telequebec.tv/player/31110/stream',
'info_dict': {
'id': '6202570652001',
'ext': 'mp4',
'title': 'Le coût du véhicule le plus vendu au Canada / Tous les frais liés à la procréation assistée',
'description': 'md5:685a7e4c450ba777c60adb6e71e41526',
'upload_date': '20201019',
'timestamp': 1603115930,
'uploader_id': '6101674910001',
},
'params': {
'format': 'bestvideo',
},
}, {
'url': 'https://video.telequebec.tv/player-live/28527',
'only_matching': True,
}]
def _call_api(self, path, video_id):
return self._download_json(
'http://beacon.playback.api.brightcove.com/telequebec/api/assets/' + path,
video_id, query={'device_layout': 'web', 'device_type': 'web'})['data']
def _real_extract(self, url):
asset_id = self._match_id(url)
asset = self._call_api(asset_id, asset_id)['asset']
stream = self._call_api(
asset_id + '/streams/' + asset['streams'][0]['id'], asset_id)['stream']
stream_url = stream['url']
account_id = try_get(
stream, lambda x: x['video_provider_details']['account_id']) or '6101674910001'
info = self._brightcove_result(stream_url, 'default', account_id)
info.update({
'description': asset.get('long_description') or asset.get('short_description'),
'series': asset.get('series_original_name'),
'season_number': int_or_none(asset.get('season_number')),
'episode': asset.get('original_name'),
'episode_number': int_or_none(asset.get('episode_number')),
})
return info
+14
View File
@@ -33,6 +33,19 @@ class TubiTvIE(InfoExtractor):
}, {
'url': 'http://tubitv.com/movies/383676/tracker',
'only_matching': True,
}, {
'url': 'https://tubitv.com/movies/560057/penitentiary?start=true',
'info_dict': {
'id': '560057',
'ext': 'mp4',
'title': 'Penitentiary',
'description': 'md5:8d2fc793a93cc1575ff426fdcb8dd3f9',
'uploader_id': 'd8fed30d4f24fcb22ec294421b9defc2',
'release_year': 1979,
},
'params': {
'skip_download': True,
},
}]
def _login(self):
@@ -93,4 +106,5 @@ class TubiTvIE(InfoExtractor):
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'uploader_id': video_data.get('publisher_id'),
'release_year': int_or_none(video_data.get('year')),
}
+67
View File
@@ -0,0 +1,67 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
remove_start,
smuggle_url,
try_get,
)
class TVerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tver\.jp/(?P<path>(?:corner|episode|feature)/(?P<id>f?\d+))'
# videos are only available for 7 days
_TESTS = [{
'url': 'https://tver.jp/corner/f0062178',
'only_matching': True,
}, {
'url': 'https://tver.jp/feature/f0062413',
'only_matching': True,
}, {
'url': 'https://tver.jp/episode/79622438',
'only_matching': True,
}]
_TOKEN = None
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
def _real_initialize(self):
self._TOKEN = self._download_json(
'https://tver.jp/api/access_token.php', None)['token']
def _real_extract(self, url):
path, video_id = re.match(self._VALID_URL, url).groups()
main = self._download_json(
'https://api.tver.jp/v4/' + path, video_id,
query={'token': self._TOKEN})['main']
p_id = main['publisher_id']
service = remove_start(main['service'], 'ts_')
info = {
'_type': 'url_transparent',
'description': try_get(main, lambda x: x['note'][0]['text'], compat_str),
'episode_number': int_or_none(try_get(main, lambda x: x['ext']['episode_number'])),
}
if service == 'cx':
info.update({
'title': main.get('subtitle') or main['title'],
'url': 'https://i.fod.fujitv.co.jp/plus7/web/%s/%s.html' % (p_id[:4], p_id),
'ie_key': 'FujiTVFODPlus7',
})
else:
r_id = main['reference_id']
if service not in ('tx', 'russia2018', 'sebare2018live', 'gorin'):
r_id = 'ref:' + r_id
bc_url = smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id),
{'geo_countries': ['JP']})
info.update({
'url': bc_url,
'ie_key': 'BrightcoveNew',
})
return info
+35 -55
View File
@@ -12,11 +12,13 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
qualities,
try_get,
update_url_query,
url_or_none,
urljoin,
)
@@ -414,7 +416,7 @@ class ViafreeIE(InfoExtractor):
class TVPlayHomeIE(InfoExtractor):
_VALID_URL = r'https?://tvplay\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/[^/]+/[^/?#&]+-(?P<id>\d+)'
_VALID_URL = r'https?://(?:tv3?)?play\.(?:tv3\.lt|skaties\.lv|tv3\.ee)/(?:[^/]+/)*[^/?#&]+-(?P<id>\d+)'
_TESTS = [{
'url': 'https://tvplay.tv3.lt/aferistai-n-7/aferistai-10047125/',
'info_dict': {
@@ -433,80 +435,58 @@ class TVPlayHomeIE(InfoExtractor):
'params': {
'skip_download': True,
},
'add_ie': [TVPlayIE.ie_key()],
}, {
'url': 'https://tvplay.skaties.lv/vinas-melo-labak/vinas-melo-labak-10280317/',
'only_matching': True,
}, {
'url': 'https://tvplay.tv3.ee/cool-d-ga-mehhikosse/cool-d-ga-mehhikosse-10044354/',
'only_matching': True,
}, {
'url': 'https://play.tv3.lt/aferistai-10047125',
'only_matching': True,
}, {
'url': 'https://tv3play.skaties.lv/vinas-melo-labak-10280317',
'only_matching': True,
}, {
'url': 'https://play.tv3.ee/cool-d-ga-mehhikosse-10044354',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
asset = self._download_json(
urljoin(url, '/sb/public/asset/' + video_id), video_id)
video_id = self._search_regex(
r'data-asset-id\s*=\s*["\'](\d{5,})\b', webpage, 'video id')
if len(video_id) < 8:
return self.url_result(
'mtg:%s' % video_id, ie=TVPlayIE.ie_key(), video_id=video_id)
m3u8_url = self._search_regex(
r'data-file\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'm3u8 url', group='url')
m3u8_url = asset['movie']['contentUrl']
video_id = asset['assetId']
asset_title = asset['title']
title = asset_title['title']
formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats)
title = self._search_regex(
r'data-title\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
'title', default=None, group='value') or self._html_search_meta(
'title', webpage, default=None) or self._og_search_title(
webpage)
thumbnails = None
image_url = asset.get('imageUrl')
if image_url:
thumbnails = [{
'url': urljoin(url, image_url),
'ext': 'jpg',
}]
description = self._html_search_meta(
'description', webpage,
default=None) or self._og_search_description(webpage)
thumbnail = self._search_regex(
r'data-image\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', default=None, group='url') or self._html_search_meta(
'thumbnail', webpage, default=None) or self._og_search_thumbnail(
webpage)
duration = int_or_none(self._search_regex(
r'data-duration\s*=\s*["\'](\d+)', webpage, 'duration',
fatal=False))
season = self._search_regex(
(r'data-series-title\s*=\s*(["\'])[^/]+/(?P<value>(?:(?!\1).)+)\1',
r'\bseason\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'season', default=None, group='value')
season_number = int_or_none(self._search_regex(
r'(\d+)(?:[.\s]+sezona|\s+HOOAEG)', season or '', 'season number',
default=None))
episode = self._search_regex(
(r'\bepisode\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
r'data-subtitle\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
'episode', default=None, group='value')
episode_number = int_or_none(self._search_regex(
r'(?:S[eē]rija|Osa)\s+(\d+)', episode or '', 'episode number',
default=None))
metadata = asset.get('metadata') or {}
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'season': season,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'description': asset_title.get('summaryLong') or asset_title.get('summaryShort'),
'thumbnails': thumbnails,
'duration': parse_duration(asset_title.get('runTime')),
'series': asset.get('tvSeriesTitle'),
'season': asset.get('tvSeasonTitle'),
'season_number': int_or_none(metadata.get('seasonNumber')),
'episode': asset_title.get('titleBrief'),
'episode_number': int_or_none(metadata.get('episodeNumber')),
'formats': formats,
}
+23 -6
View File
@@ -17,6 +17,7 @@ from ..utils import (
unified_strdate,
update_url_query,
urlhandle_detect_ext,
url_or_none,
)
@@ -42,16 +43,20 @@ class WDRIE(InfoExtractor):
is_live = metadata.get('mediaType') == 'live'
tracker_data = metadata['trackerData']
title = tracker_data['trackerClipTitle']
media_resource = metadata['mediaResource']
formats = []
# check if the metadata contains a direct URL to a file
for kind, media_resource in media_resource.items():
for kind, media in media_resource.items():
if not isinstance(media, dict):
continue
if kind not in ('dflt', 'alt'):
continue
for tag_name, medium_url in media_resource.items():
for tag_name, medium_url in media.items():
if tag_name not in ('videoURL', 'audioURL'):
continue
@@ -88,8 +93,16 @@ class WDRIE(InfoExtractor):
'url': caption_url,
'ext': 'ttml',
}]
title = tracker_data['trackerClipTitle']
captions_hash = media_resource.get('captionsHash')
if isinstance(captions_hash, dict):
for ext, format_url in captions_hash.items():
format_url = url_or_none(format_url)
if not format_url:
continue
subtitles.setdefault('de', []).append({
'url': format_url,
'ext': determine_ext(format_url, None) or ext,
})
return {
'id': tracker_data.get('trackerClipId', video_id),
@@ -105,7 +118,7 @@ class WDRIE(InfoExtractor):
class WDRPageIE(InfoExtractor):
_CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5'
_PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html'
_VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
_VALID_URL = r'https?://(?:www\d?\.)?(?:(?:kinder\.)?wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL
_TESTS = [
{
@@ -212,7 +225,11 @@ class WDRPageIE(InfoExtractor):
{
'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html',
'only_matching': True,
}
},
{
'url': 'https://kinder.wdr.de/tv/die-sendung-mit-dem-elefanten/av/video-folge---astronaut-100.html',
'only_matching': True,
},
]
def _real_extract(self, url):
+99 -42
View File
@@ -67,11 +67,6 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
_PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
_YOUTUBE_CLIENT_HEADERS = {
'x-youtube-client-name': '1',
'x-youtube-client-version': '1.20200609.04.02',
}
def _set_language(self):
self._set_cookie(
'.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
@@ -2693,6 +2688,10 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
# no longer available?
'url': 'https://www.youtube.com/feed/recommended',
'only_matching': True,
}, {
# inline playlist with not always working continuations
'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
'only_matching': True,
}
# TODO
# {
@@ -2871,6 +2870,16 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
for entry in self._post_thread_entries(renderer):
yield entry
@staticmethod
def _build_continuation_query(continuation, ctp=None):
query = {
'ctoken': continuation,
'continuation': continuation,
}
if ctp:
query['itct'] = ctp
return query
@staticmethod
def _extract_next_continuation_data(renderer):
next_continuation = try_get(
@@ -2881,11 +2890,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
if not continuation:
return
ctp = next_continuation.get('clickTrackingParams')
return {
'ctoken': continuation,
'continuation': continuation,
'itct': ctp,
}
return YoutubeTabIE._build_continuation_query(continuation, ctp)
@classmethod
def _extract_continuation(cls, renderer):
@@ -2908,13 +2913,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
if not continuation:
continue
ctp = continuation_ep.get('clickTrackingParams')
if not ctp:
continue
return {
'ctoken': continuation,
'continuation': continuation,
'itct': ctp,
}
return YoutubeTabIE._build_continuation_query(continuation, ctp)
def _entries(self, tab, identity_token):
tab_content = try_get(tab, lambda x: x['content'], dict)
@@ -3060,6 +3059,24 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
return uploader
@staticmethod
def _extract_alert(data):
alerts = []
for alert in try_get(data, lambda x: x['alerts'], list) or []:
if not isinstance(alert, dict):
continue
alert_text = try_get(
alert, lambda x: x['alertRenderer']['text'], dict)
if not alert_text:
continue
text = try_get(
alert_text,
(lambda x: x['simpleText'], lambda x: x['runs'][0]['text']),
compat_str)
if text:
alerts.append(text)
return '\n'.join(alerts)
def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
selected_tab = self._extract_selected_tab(tabs)
renderer = try_get(
@@ -3086,14 +3103,37 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
playlist.update(self._extract_uploader(data))
return playlist
def _extract_from_playlist(self, item_id, data, playlist):
def _extract_from_playlist(self, item_id, url, data, playlist):
title = playlist.get('title') or try_get(
data, lambda x: x['titleText']['simpleText'], compat_str)
playlist_id = playlist.get('playlistId') or item_id
# Inline playlist rendition continuation does not always work
# at Youtube side, so delegating regular tab-based playlist URL
# processing whenever possible.
playlist_url = urljoin(url, try_get(
playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
compat_str))
if playlist_url and playlist_url != url:
return self.url_result(
playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
video_title=title)
return self.playlist_result(
self._playlist_entries(playlist), playlist_id=playlist_id,
playlist_title=title)
def _extract_identity_token(self, webpage, item_id):
ytcfg = self._parse_json(
self._search_regex(
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), item_id, fatal=False)
if ytcfg:
token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
if token:
return token
return self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
def _real_extract(self, url):
item_id = self._match_id(url)
url = compat_urlparse.urlunparse(
@@ -3108,9 +3148,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
identity_token = self._extract_identity_token(webpage, item_id)
data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
@@ -3119,7 +3157,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
playlist = try_get(
data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
if playlist:
return self._extract_from_playlist(item_id, data, playlist)
return self._extract_from_playlist(item_id, url, data, playlist)
# Fallback to video extraction if no playlist alike page is recognized.
# First check for the current video then try the v attribute of URL query.
video_id = try_get(
@@ -3127,6 +3165,10 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
compat_str) or video_id
if video_id:
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
# Capture and output alerts
alert = self._extract_alert(data)
if alert:
raise ExtractorError(alert, expected=True)
# Failed to recognize
raise ExtractorError('Unable to recognize tab page')
@@ -3139,8 +3181,7 @@ class YoutubePlaylistIE(InfoExtractor):
(?:
(?:
youtube(?:kids)?\.com|
invidio\.us|
youtu\.be
invidio\.us
)
/.*?\?.*?\blist=
)?
@@ -3185,6 +3226,32 @@ class YoutubePlaylistIE(InfoExtractor):
'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
}
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
}, {
# music album playlist
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if YoutubeTabIE.suitable(url) else super(
YoutubePlaylistIE, cls).suitable(url)
def _real_extract(self, url):
playlist_id = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if not qs:
qs = {'list': playlist_id}
return self.url_result(
update_url_query('https://www.youtube.com/playlist', qs),
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeYtBeIE(InfoExtractor):
_VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
_TESTS = [{
'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
'info_dict': {
'id': 'yeWKywCrFtk',
@@ -3207,28 +3274,18 @@ class YoutubePlaylistIE(InfoExtractor):
}, {
'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
'only_matching': True,
}, {
'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
'only_matching': True,
}, {
# music album playlist
'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if YoutubeTabIE.suitable(url) else super(
YoutubePlaylistIE, cls).suitable(url)
def _real_extract(self, url):
playlist_id = self._match_id(url)
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
if not qs:
qs = {'list': playlist_id}
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id')
return self.url_result(
update_url_query('https://www.youtube.com/playlist', qs),
ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
update_url_query('https://www.youtube.com/watch', {
'v': video_id,
'list': playlist_id,
'feature': 'youtu.be',
}), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
class YoutubeYtUserIE(InfoExtractor):
+2 -2
View File
@@ -40,7 +40,7 @@ class ZDFBaseIE(InfoExtractor):
class ZDFIE(ZDFBaseIE):
_VALID_URL = r'https?://www\.zdf\.de/(?:[^/]+/)*(?P<id>[^/?]+)\.html'
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh')
_QUALITIES = ('auto', 'low', 'med', 'high', 'veryhigh', 'hd')
_GEO_COUNTRIES = ['DE']
_TESTS = [{
@@ -119,7 +119,7 @@ class ZDFIE(ZDFBaseIE):
if not ptmd_path:
ptmd_path = t[
'http://zdf.de/rels/streams/ptmd-template'].replace(
'{playerId}', 'portal')
'{playerId}', 'ngplayer_2_4')
ptmd = self._call_api(
urljoin(url, ptmd_path), player, url, video_id, 'metadata')
+1 -1
View File
@@ -369,7 +369,7 @@ def parseOpts(overrideArguments=None):
authentication.add_option(
'--video-password',
dest='videopassword', metavar='PASSWORD',
help='Video password (vimeo, smotri, youku)')
help='Video password (vimeo, youku)')
adobe_pass = optparse.OptionGroup(parser, 'Adobe Pass Options')
adobe_pass.add_option(
+1 -1
View File
@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2020.12.02'
__version__ = '2020.12.12'