tsia
GitHub
commit
620ca40bbb
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
6
.github/ISSUE_TEMPLATE/1_broken_site.md
vendored
@ -18,7 +18,7 @@ title: ''
|
|||||||
|
|
||||||
<!--
|
<!--
|
||||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
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 2020.01.01. 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 Issues with outdated version will be REJECTED.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 2020.02.16. 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 Issues with outdated version will be REJECTED.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 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.
|
- 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.
|
- 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'm reporting a broken site support
|
||||||
- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
|
- [ ] I've verified that I'm running youtube-dl version **2020.02.16**
|
||||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
- [ ] 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 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
|
- [ ] 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] User config: []
|
||||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
[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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||||
[debug] youtube-dl version 2020.01.01
|
[debug] youtube-dl version 2020.02.16
|
||||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
[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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||||
[debug] Proxy map: {}
|
[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:
|
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 2020.01.01. 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 2020.02.16. 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 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.
|
- 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.
|
- 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'm reporting a new site support request
|
||||||
- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
|
- [ ] I've verified that I'm running youtube-dl version **2020.02.16**
|
||||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
- [ ] 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 checked that none of provided URLs violate any copyrights
|
||||||
- [ ] I've searched the bugtracker for similar site support requests including closed ones
|
- [ ] 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:
|
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 2020.01.01. 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 2020.02.16. 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.
|
- 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])
|
- Finally, put x into all relevant boxes (like this [x])
|
||||||
-->
|
-->
|
||||||
|
|
||||||
- [ ] I'm reporting a site feature request
|
- [ ] I'm reporting a site feature request
|
||||||
- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
|
- [ ] I've verified that I'm running youtube-dl version **2020.02.16**
|
||||||
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
- [ ] I've searched the bugtracker for similar site feature requests including closed ones
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
6
.github/ISSUE_TEMPLATE/4_bug_report.md
vendored
@ -18,7 +18,7 @@ title: ''
|
|||||||
|
|
||||||
<!--
|
<!--
|
||||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
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 2020.01.01. 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 2020.02.16. 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 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.
|
- 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.
|
- 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'm reporting a broken site support issue
|
||||||
- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
|
- [ ] I've verified that I'm running youtube-dl version **2020.02.16**
|
||||||
- [ ] I've checked that all provided URLs are alive and playable in a browser
|
- [ ] 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 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
|
- [ ] 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] User config: []
|
||||||
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
|
[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] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
|
||||||
[debug] youtube-dl version 2020.01.01
|
[debug] youtube-dl version 2020.02.16
|
||||||
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
|
[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] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
|
||||||
[debug] Proxy map: {}
|
[debug] Proxy map: {}
|
||||||
|
|||||||
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
4
.github/ISSUE_TEMPLATE/5_feature_request.md
vendored
@ -19,13 +19,13 @@ labels: 'request'
|
|||||||
|
|
||||||
<!--
|
<!--
|
||||||
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
|
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 2020.01.01. 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 2020.02.16. 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.
|
- 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])
|
- Finally, put x into all relevant boxes (like this [x])
|
||||||
-->
|
-->
|
||||||
|
|
||||||
- [ ] I'm reporting a feature request
|
- [ ] I'm reporting a feature request
|
||||||
- [ ] I've verified that I'm running youtube-dl version **2020.01.01**
|
- [ ] I've verified that I'm running youtube-dl version **2020.02.16**
|
||||||
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
- [ ] I've searched the bugtracker for similar feature requests including closed ones
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@ -13,7 +13,7 @@ dist: trusty
|
|||||||
env:
|
env:
|
||||||
- YTDL_TEST_SET=core
|
- YTDL_TEST_SET=core
|
||||||
- YTDL_TEST_SET=download
|
- YTDL_TEST_SET=download
|
||||||
matrix:
|
jobs:
|
||||||
include:
|
include:
|
||||||
- python: 3.7
|
- python: 3.7
|
||||||
dist: xenial
|
dist: xenial
|
||||||
@ -35,6 +35,11 @@ matrix:
|
|||||||
env: YTDL_TEST_SET=download
|
env: YTDL_TEST_SET=download
|
||||||
- env: JYTHON=true; YTDL_TEST_SET=core
|
- 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
|
||||||
|
install: pip install flake8
|
||||||
|
script: flake8 .
|
||||||
fast_finish: true
|
fast_finish: true
|
||||||
allow_failures:
|
allow_failures:
|
||||||
- env: YTDL_TEST_SET=download
|
- env: YTDL_TEST_SET=download
|
||||||
|
|||||||
90
ChangeLog
90
ChangeLog
@ -1,3 +1,93 @@
|
|||||||
|
version 2020.02.16
|
||||||
|
|
||||||
|
Core
|
||||||
|
* [YoutubeDL] Fix playlist entry indexing with --playlist-items (#10591,
|
||||||
|
#10622)
|
||||||
|
* [update] Fix updating via symlinks (#23991)
|
||||||
|
+ [compat] Introduce compat_realpath (#23991)
|
||||||
|
|
||||||
|
Extractors
|
||||||
|
+ [npr] Add support for streams (#24042)
|
||||||
|
+ [24video] Add support for porn.24video.net (#23779, #23784)
|
||||||
|
- [jpopsuki] Remove extractor (#23858)
|
||||||
|
* [nova] Improve extraction (#23690)
|
||||||
|
* [nova:embed] Improve (#23690)
|
||||||
|
* [nova:embed] Fix extraction (#23672)
|
||||||
|
+ [abc:iview] Add support for 720p (#22907, #22921)
|
||||||
|
* [nytimes] Improve format sorting (#24010)
|
||||||
|
+ [toggle] Add support for mewatch.sg (#23895, #23930)
|
||||||
|
* [thisoldhouse] Fix extraction (#23951)
|
||||||
|
+ [popcorntimes] Add support for popcorntimes.tv (#23949)
|
||||||
|
* [sportdeutschland] Update to new API
|
||||||
|
* [twitch:stream] Lowercase channel id for stream request (#23917)
|
||||||
|
* [tv5mondeplus] Fix extraction (#23907, #23911)
|
||||||
|
* [tva] Relax URL regular expression (#23903)
|
||||||
|
* [vimeo] Fix album extraction (#23864)
|
||||||
|
* [viewlift] Improve extraction
|
||||||
|
* Fix extraction (#23851)
|
||||||
|
+ Add support for authentication
|
||||||
|
+ Add support for more domains
|
||||||
|
* [svt] Fix series extraction (#22297)
|
||||||
|
* [svt] Fix article extraction (#22897, #22919)
|
||||||
|
* [soundcloud] Imporve private playlist/set tracks extraction (#3707)
|
||||||
|
|
||||||
|
|
||||||
|
version 2020.01.24
|
||||||
|
|
||||||
|
Extractors
|
||||||
|
* [youtube] Fix sigfunc name extraction (#23819)
|
||||||
|
* [stretchinternet] Fix extraction (#4319)
|
||||||
|
* [voicerepublic] Fix extraction
|
||||||
|
* [azmedien] Fix extraction (#23783)
|
||||||
|
* [businessinsider] Fix jwplatform id extraction (#22929, #22954)
|
||||||
|
+ [24video] Add support for 24video.vip (#23753)
|
||||||
|
* [ivi:compilation] Fix entries extraction (#23770)
|
||||||
|
* [ard] Improve extraction (#23761)
|
||||||
|
* Simplify extraction
|
||||||
|
+ Extract age limit and series
|
||||||
|
* Bypass geo-restriction
|
||||||
|
+ [nbc] Add support for nbc multi network URLs (#23049)
|
||||||
|
* [americastestkitchen] Fix extraction
|
||||||
|
* [zype] Improve extraction
|
||||||
|
+ Extract subtitles (#21258)
|
||||||
|
+ Support URLs with alternative keys/tokens (#21258)
|
||||||
|
+ Extract more metadata
|
||||||
|
* [orf:tvthek] Improve geo restricted videos detection (#23741)
|
||||||
|
* [soundcloud] Restore previews extraction (#23739)
|
||||||
|
|
||||||
|
|
||||||
|
version 2020.01.15
|
||||||
|
|
||||||
|
Extractors
|
||||||
|
* [yourporn] Fix extraction (#21645, #22255, #23459)
|
||||||
|
+ [canvas] Add support for new API endpoint (#17680, #18629)
|
||||||
|
* [ndr:base:embed] Improve thumbnails extraction (#23731)
|
||||||
|
+ [vodplatform] Add support for embed.kwikmotion.com domain
|
||||||
|
+ [twitter] Add support for promo_video_website cards (#23711)
|
||||||
|
* [orf:radio] Clean description and improve extraction
|
||||||
|
* [orf:fm4] Fix extraction (#23599)
|
||||||
|
* [safari] Fix kaltura session extraction (#23679, #23670)
|
||||||
|
* [lego] Fix extraction and extract subtitle (#23687)
|
||||||
|
* [cloudflarestream] Improve extraction
|
||||||
|
+ Add support for bytehighway.net domain
|
||||||
|
+ Add support for signed URLs
|
||||||
|
+ Extract thumbnail
|
||||||
|
* [naver] Improve extraction
|
||||||
|
* Improve geo-restriction handling
|
||||||
|
+ Extract automatic captions
|
||||||
|
+ Extract uploader metadata
|
||||||
|
+ Extract VLive HLS formats
|
||||||
|
* Improve metadata extraction
|
||||||
|
- [pandatv] Remove extractor (#23630)
|
||||||
|
* [dctp] Fix format extraction (#23656)
|
||||||
|
+ [scrippsnetworks] Add support for www.discovery.com videos
|
||||||
|
* [discovery] Fix anonymous token extraction (#23650)
|
||||||
|
* [nrktv:seriebase] Fix extraction (#23625, #23537)
|
||||||
|
* [wistia] Improve format extraction and extract subtitles (#22590)
|
||||||
|
* [vice] Improve extraction (#23631)
|
||||||
|
* [redtube] Detect private videos (#23518)
|
||||||
|
|
||||||
|
|
||||||
version 2020.01.01
|
version 2020.01.01
|
||||||
|
|
||||||
Extractors
|
Extractors
|
||||||
|
|||||||
@ -389,7 +389,6 @@
|
|||||||
- **JeuxVideo**
|
- **JeuxVideo**
|
||||||
- **Joj**
|
- **Joj**
|
||||||
- **Jove**
|
- **Jove**
|
||||||
- **jpopsuki.tv**
|
|
||||||
- **JWPlatform**
|
- **JWPlatform**
|
||||||
- **Kakao**
|
- **Kakao**
|
||||||
- **Kaltura**
|
- **Kaltura**
|
||||||
@ -628,7 +627,6 @@
|
|||||||
- **OutsideTV**
|
- **OutsideTV**
|
||||||
- **PacktPub**
|
- **PacktPub**
|
||||||
- **PacktPubCourse**
|
- **PacktPubCourse**
|
||||||
- **PandaTV**: 熊猫TV
|
|
||||||
- **pandora.tv**: 판도라TV
|
- **pandora.tv**: 판도라TV
|
||||||
- **ParamountNetwork**
|
- **ParamountNetwork**
|
||||||
- **parliamentlive.tv**: UK parliament videos
|
- **parliamentlive.tv**: UK parliament videos
|
||||||
@ -664,6 +662,7 @@
|
|||||||
- **Pokemon**
|
- **Pokemon**
|
||||||
- **PolskieRadio**
|
- **PolskieRadio**
|
||||||
- **PolskieRadioCategory**
|
- **PolskieRadioCategory**
|
||||||
|
- **Popcorntimes**
|
||||||
- **PopcornTV**
|
- **PopcornTV**
|
||||||
- **PornCom**
|
- **PornCom**
|
||||||
- **PornerBros**
|
- **PornerBros**
|
||||||
@ -1005,8 +1004,8 @@
|
|||||||
- **Vidzi**
|
- **Vidzi**
|
||||||
- **vier**: vier.be and vijf.be
|
- **vier**: vier.be and vijf.be
|
||||||
- **vier:videos**
|
- **vier:videos**
|
||||||
- **ViewLift**
|
- **viewlift**
|
||||||
- **ViewLiftEmbed**
|
- **viewlift:embed**
|
||||||
- **Viidea**
|
- **Viidea**
|
||||||
- **viki**
|
- **viki**
|
||||||
- **viki:channel**
|
- **viki:channel**
|
||||||
|
|||||||
@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase):
|
|||||||
'webpage_url': 'http://example.com',
|
'webpage_url': 'http://example.com',
|
||||||
}
|
}
|
||||||
|
|
||||||
def get_ids(params):
|
def get_downloaded_info_dicts(params):
|
||||||
ydl = YDL(params)
|
ydl = YDL(params)
|
||||||
# make a copy because the dictionary can be modified
|
# make a deep copy because the dictionary and nested entries
|
||||||
ydl.process_ie_result(playlist.copy())
|
# can be modified
|
||||||
return [int(v['id']) for v in ydl.downloaded_info_dicts]
|
ydl.process_ie_result(copy.deepcopy(playlist))
|
||||||
|
return ydl.downloaded_info_dicts
|
||||||
|
|
||||||
|
def get_ids(params):
|
||||||
|
return [int(v['id']) for v in get_downloaded_info_dicts(params)]
|
||||||
|
|
||||||
result = get_ids({})
|
result = get_ids({})
|
||||||
self.assertEqual(result, [1, 2, 3, 4])
|
self.assertEqual(result, [1, 2, 3, 4])
|
||||||
@ -852,6 +856,22 @@ class TestYoutubeDL(unittest.TestCase):
|
|||||||
result = get_ids({'playlist_items': '2-4,3-4,3'})
|
result = get_ids({'playlist_items': '2-4,3-4,3'})
|
||||||
self.assertEqual(result, [2, 3, 4])
|
self.assertEqual(result, [2, 3, 4])
|
||||||
|
|
||||||
|
# Tests for https://github.com/ytdl-org/youtube-dl/issues/10591
|
||||||
|
# @{
|
||||||
|
result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
|
||||||
|
self.assertEqual(result[0]['playlist_index'], 2)
|
||||||
|
self.assertEqual(result[1]['playlist_index'], 3)
|
||||||
|
|
||||||
|
result = get_downloaded_info_dicts({'playlist_items': '2-4,3-4,3'})
|
||||||
|
self.assertEqual(result[0]['playlist_index'], 2)
|
||||||
|
self.assertEqual(result[1]['playlist_index'], 3)
|
||||||
|
self.assertEqual(result[2]['playlist_index'], 4)
|
||||||
|
|
||||||
|
result = get_downloaded_info_dicts({'playlist_items': '4,2'})
|
||||||
|
self.assertEqual(result[0]['playlist_index'], 4)
|
||||||
|
self.assertEqual(result[1]['playlist_index'], 2)
|
||||||
|
# @}
|
||||||
|
|
||||||
def test_urlopen_no_file_protocol(self):
|
def test_urlopen_no_file_protocol(self):
|
||||||
# see https://github.com/ytdl-org/youtube-dl/issues/8227
|
# see https://github.com/ytdl-org/youtube-dl/issues/8227
|
||||||
ydl = YDL()
|
ydl = YDL()
|
||||||
|
|||||||
@ -990,7 +990,7 @@ class YoutubeDL(object):
|
|||||||
'playlist_title': ie_result.get('title'),
|
'playlist_title': ie_result.get('title'),
|
||||||
'playlist_uploader': ie_result.get('uploader'),
|
'playlist_uploader': ie_result.get('uploader'),
|
||||||
'playlist_uploader_id': ie_result.get('uploader_id'),
|
'playlist_uploader_id': ie_result.get('uploader_id'),
|
||||||
'playlist_index': i + playliststart,
|
'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
|
||||||
'extractor': ie_result['extractor'],
|
'extractor': ie_result['extractor'],
|
||||||
'webpage_url': ie_result['webpage_url'],
|
'webpage_url': ie_result['webpage_url'],
|
||||||
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
'webpage_url_basename': url_basename(ie_result['webpage_url']),
|
||||||
|
|||||||
@ -2754,6 +2754,17 @@ else:
|
|||||||
compat_expanduser = os.path.expanduser
|
compat_expanduser = os.path.expanduser
|
||||||
|
|
||||||
|
|
||||||
|
if compat_os_name == 'nt' and sys.version_info < (3, 8):
|
||||||
|
# os.path.realpath on Windows does not follow symbolic links
|
||||||
|
# prior to Python 3.8 (see https://bugs.python.org/issue9949)
|
||||||
|
def compat_realpath(path):
|
||||||
|
while os.path.islink(path):
|
||||||
|
path = os.path.abspath(os.readlink(path))
|
||||||
|
return path
|
||||||
|
else:
|
||||||
|
compat_realpath = os.path.realpath
|
||||||
|
|
||||||
|
|
||||||
if sys.version_info < (3, 0):
|
if sys.version_info < (3, 0):
|
||||||
def compat_print(s):
|
def compat_print(s):
|
||||||
from .utils import preferredencoding
|
from .utils import preferredencoding
|
||||||
@ -2998,6 +3009,7 @@ __all__ = [
|
|||||||
'compat_os_name',
|
'compat_os_name',
|
||||||
'compat_parse_qs',
|
'compat_parse_qs',
|
||||||
'compat_print',
|
'compat_print',
|
||||||
|
'compat_realpath',
|
||||||
'compat_setenv',
|
'compat_setenv',
|
||||||
'compat_shlex_quote',
|
'compat_shlex_quote',
|
||||||
'compat_shlex_split',
|
'compat_shlex_split',
|
||||||
|
|||||||
@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor):
|
|||||||
|
|
||||||
# ABC iview programs are normally available for 14 days only.
|
# ABC iview programs are normally available for 14 days only.
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
|
'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
|
||||||
'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
|
'md5': '67715ce3c78426b11ba167d875ac6abf',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'ZX9371A050S00',
|
'id': 'LE1927H001S00',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': "Gaston's Birthday",
|
'title': "Series 11 Ep 1",
|
||||||
'series': "Ben And Holly's Little Kingdom",
|
'series': "Gruen",
|
||||||
'description': 'md5:f9de914d02f226968f598ac76f105bcf',
|
'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
|
||||||
'upload_date': '20180604',
|
'upload_date': '20190925',
|
||||||
'uploader_id': 'abc4kids',
|
'uploader_id': 'abc1',
|
||||||
'timestamp': 1528140219,
|
'timestamp': 1569445289,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor):
|
|||||||
'hdnea': token,
|
'hdnea': token,
|
||||||
})
|
})
|
||||||
|
|
||||||
for sd in ('sd', 'sd-low'):
|
for sd in ('720', 'sd', 'sd-low'):
|
||||||
sd_url = try_get(
|
sd_url = try_get(
|
||||||
stream, lambda x: x['streams']['hls'][sd], compat_str)
|
stream, lambda x: x['streams']['hls'][sd], compat_str)
|
||||||
if not sd_url:
|
if not sd_url:
|
||||||
|
|||||||
@ -5,6 +5,7 @@ from .common import InfoExtractor
|
|||||||
from ..utils import (
|
from ..utils import (
|
||||||
clean_html,
|
clean_html,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
|
js_to_json,
|
||||||
try_get,
|
try_get,
|
||||||
unified_strdate,
|
unified_strdate,
|
||||||
)
|
)
|
||||||
@ -13,22 +14,21 @@ from ..utils import (
|
|||||||
class AmericasTestKitchenIE(InfoExtractor):
|
class AmericasTestKitchenIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
|
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
|
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
|
||||||
'md5': 'b861c3e365ac38ad319cfd509c30577f',
|
'md5': 'b861c3e365ac38ad319cfd509c30577f',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '1_5g5zua6e',
|
'id': '5b400b9ee338f922cb06450c',
|
||||||
'title': 'Summer Dinner Party',
|
'title': 'Weeknight Japanese Suppers',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
|
'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
|
||||||
'thumbnail': r're:^https?://.*\.jpg',
|
'thumbnail': r're:^https?://',
|
||||||
'timestamp': 1497285541,
|
'timestamp': 1523664000,
|
||||||
'upload_date': '20170612',
|
'upload_date': '20180414',
|
||||||
'uploader_id': 'roger.metcalf@americastestkitchen.com',
|
'release_date': '20180414',
|
||||||
'release_date': '20170617',
|
|
||||||
'series': "America's Test Kitchen",
|
'series': "America's Test Kitchen",
|
||||||
'season_number': 17,
|
'season_number': 18,
|
||||||
'episode': 'Summer Dinner Party',
|
'episode': 'Weeknight Japanese Suppers',
|
||||||
'episode_number': 24,
|
'episode_number': 15,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
@ -47,7 +47,7 @@ class AmericasTestKitchenIE(InfoExtractor):
|
|||||||
self._search_regex(
|
self._search_regex(
|
||||||
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
|
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
|
||||||
webpage, 'initial context'),
|
webpage, 'initial context'),
|
||||||
video_id)
|
video_id, js_to_json)
|
||||||
|
|
||||||
ep_data = try_get(
|
ep_data = try_get(
|
||||||
video_data,
|
video_data,
|
||||||
@ -55,17 +55,7 @@ class AmericasTestKitchenIE(InfoExtractor):
|
|||||||
lambda x: x['videoDetail']['content']['data']), dict)
|
lambda x: x['videoDetail']['content']['data']), dict)
|
||||||
ep_meta = ep_data.get('full_video', {})
|
ep_meta = ep_data.get('full_video', {})
|
||||||
|
|
||||||
zype_id = ep_meta.get('zype_id')
|
zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
|
||||||
if zype_id:
|
|
||||||
embed_url = 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id
|
|
||||||
ie_key = 'Zype'
|
|
||||||
else:
|
|
||||||
partner_id = self._search_regex(
|
|
||||||
r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
|
|
||||||
webpage, 'kaltura partner id')
|
|
||||||
external_id = ep_data.get('external_id') or ep_meta['external_id']
|
|
||||||
embed_url = 'kaltura:%s:%s' % (partner_id, external_id)
|
|
||||||
ie_key = 'Kaltura'
|
|
||||||
|
|
||||||
title = ep_data.get('title') or ep_meta.get('title')
|
title = ep_data.get('title') or ep_meta.get('title')
|
||||||
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
|
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
|
||||||
@ -79,8 +69,8 @@ class AmericasTestKitchenIE(InfoExtractor):
|
|||||||
|
|
||||||
return {
|
return {
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
'url': embed_url,
|
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
|
||||||
'ie_key': ie_key,
|
'ie_key': 'Zype',
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'description': description,
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
|
|||||||
@ -1,6 +1,7 @@
|
|||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import json
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
@ -22,7 +23,101 @@ from ..utils import (
|
|||||||
from ..compat import compat_etree_fromstring
|
from ..compat import compat_etree_fromstring
|
||||||
|
|
||||||
|
|
||||||
class ARDMediathekIE(InfoExtractor):
|
class ARDMediathekBaseIE(InfoExtractor):
|
||||||
|
_GEO_COUNTRIES = ['DE']
|
||||||
|
|
||||||
|
def _extract_media_info(self, media_info_url, webpage, video_id):
|
||||||
|
media_info = self._download_json(
|
||||||
|
media_info_url, video_id, 'Downloading media JSON')
|
||||||
|
return self._parse_media_info(media_info, video_id, '"fsk"' in webpage)
|
||||||
|
|
||||||
|
def _parse_media_info(self, media_info, video_id, fsk):
|
||||||
|
formats = self._extract_formats(media_info, video_id)
|
||||||
|
|
||||||
|
if not formats:
|
||||||
|
if fsk:
|
||||||
|
raise ExtractorError(
|
||||||
|
'This video is only available after 20:00', expected=True)
|
||||||
|
elif media_info.get('_geoblocked'):
|
||||||
|
self.raise_geo_restricted(
|
||||||
|
'This video is not available due to geoblocking',
|
||||||
|
countries=self._GEO_COUNTRIES)
|
||||||
|
|
||||||
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
subtitles = {}
|
||||||
|
subtitle_url = media_info.get('_subtitleUrl')
|
||||||
|
if subtitle_url:
|
||||||
|
subtitles['de'] = [{
|
||||||
|
'ext': 'ttml',
|
||||||
|
'url': subtitle_url,
|
||||||
|
}]
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'duration': int_or_none(media_info.get('_duration')),
|
||||||
|
'thumbnail': media_info.get('_previewImage'),
|
||||||
|
'is_live': media_info.get('_isLive') is True,
|
||||||
|
'formats': formats,
|
||||||
|
'subtitles': subtitles,
|
||||||
|
}
|
||||||
|
|
||||||
|
def _extract_formats(self, media_info, video_id):
|
||||||
|
type_ = media_info.get('_type')
|
||||||
|
media_array = media_info.get('_mediaArray', [])
|
||||||
|
formats = []
|
||||||
|
for num, media in enumerate(media_array):
|
||||||
|
for stream in media.get('_mediaStreamArray', []):
|
||||||
|
stream_urls = stream.get('_stream')
|
||||||
|
if not stream_urls:
|
||||||
|
continue
|
||||||
|
if not isinstance(stream_urls, list):
|
||||||
|
stream_urls = [stream_urls]
|
||||||
|
quality = stream.get('_quality')
|
||||||
|
server = stream.get('_server')
|
||||||
|
for stream_url in stream_urls:
|
||||||
|
if not url_or_none(stream_url):
|
||||||
|
continue
|
||||||
|
ext = determine_ext(stream_url)
|
||||||
|
if quality != 'auto' and ext in ('f4m', 'm3u8'):
|
||||||
|
continue
|
||||||
|
if ext == 'f4m':
|
||||||
|
formats.extend(self._extract_f4m_formats(
|
||||||
|
update_url_query(stream_url, {
|
||||||
|
'hdcore': '3.1.1',
|
||||||
|
'plugin': 'aasp-3.1.1.69.124'
|
||||||
|
}), video_id, f4m_id='hds', fatal=False))
|
||||||
|
elif ext == 'm3u8':
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
stream_url, video_id, 'mp4', 'm3u8_native',
|
||||||
|
m3u8_id='hls', fatal=False))
|
||||||
|
else:
|
||||||
|
if server and server.startswith('rtmp'):
|
||||||
|
f = {
|
||||||
|
'url': server,
|
||||||
|
'play_path': stream_url,
|
||||||
|
'format_id': 'a%s-rtmp-%s' % (num, quality),
|
||||||
|
}
|
||||||
|
else:
|
||||||
|
f = {
|
||||||
|
'url': stream_url,
|
||||||
|
'format_id': 'a%s-%s-%s' % (num, ext, quality)
|
||||||
|
}
|
||||||
|
m = re.search(
|
||||||
|
r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$',
|
||||||
|
stream_url)
|
||||||
|
if m:
|
||||||
|
f.update({
|
||||||
|
'width': int(m.group('width')),
|
||||||
|
'height': int(m.group('height')),
|
||||||
|
})
|
||||||
|
if type_ == 'audio':
|
||||||
|
f['vcodec'] = 'none'
|
||||||
|
formats.append(f)
|
||||||
|
return formats
|
||||||
|
|
||||||
|
|
||||||
|
class ARDMediathekIE(ARDMediathekBaseIE):
|
||||||
IE_NAME = 'ARD:mediathek'
|
IE_NAME = 'ARD:mediathek'
|
||||||
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
|
_VALID_URL = r'^https?://(?:(?:(?:www|classic)\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
|
||||||
|
|
||||||
@ -63,94 +158,6 @@ class ARDMediathekIE(InfoExtractor):
|
|||||||
def suitable(cls, url):
|
def suitable(cls, url):
|
||||||
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
|
return False if ARDBetaMediathekIE.suitable(url) else super(ARDMediathekIE, cls).suitable(url)
|
||||||
|
|
||||||
def _extract_media_info(self, media_info_url, webpage, video_id):
|
|
||||||
media_info = self._download_json(
|
|
||||||
media_info_url, video_id, 'Downloading media JSON')
|
|
||||||
|
|
||||||
formats = self._extract_formats(media_info, video_id)
|
|
||||||
|
|
||||||
if not formats:
|
|
||||||
if '"fsk"' in webpage:
|
|
||||||
raise ExtractorError(
|
|
||||||
'This video is only available after 20:00', expected=True)
|
|
||||||
elif media_info.get('_geoblocked'):
|
|
||||||
raise ExtractorError('This video is not available due to geo restriction', expected=True)
|
|
||||||
|
|
||||||
self._sort_formats(formats)
|
|
||||||
|
|
||||||
duration = int_or_none(media_info.get('_duration'))
|
|
||||||
thumbnail = media_info.get('_previewImage')
|
|
||||||
is_live = media_info.get('_isLive') is True
|
|
||||||
|
|
||||||
subtitles = {}
|
|
||||||
subtitle_url = media_info.get('_subtitleUrl')
|
|
||||||
if subtitle_url:
|
|
||||||
subtitles['de'] = [{
|
|
||||||
'ext': 'ttml',
|
|
||||||
'url': subtitle_url,
|
|
||||||
}]
|
|
||||||
|
|
||||||
return {
|
|
||||||
'id': video_id,
|
|
||||||
'duration': duration,
|
|
||||||
'thumbnail': thumbnail,
|
|
||||||
'is_live': is_live,
|
|
||||||
'formats': formats,
|
|
||||||
'subtitles': subtitles,
|
|
||||||
}
|
|
||||||
|
|
||||||
def _extract_formats(self, media_info, video_id):
|
|
||||||
type_ = media_info.get('_type')
|
|
||||||
media_array = media_info.get('_mediaArray', [])
|
|
||||||
formats = []
|
|
||||||
for num, media in enumerate(media_array):
|
|
||||||
for stream in media.get('_mediaStreamArray', []):
|
|
||||||
stream_urls = stream.get('_stream')
|
|
||||||
if not stream_urls:
|
|
||||||
continue
|
|
||||||
if not isinstance(stream_urls, list):
|
|
||||||
stream_urls = [stream_urls]
|
|
||||||
quality = stream.get('_quality')
|
|
||||||
server = stream.get('_server')
|
|
||||||
for stream_url in stream_urls:
|
|
||||||
if not url_or_none(stream_url):
|
|
||||||
continue
|
|
||||||
ext = determine_ext(stream_url)
|
|
||||||
if quality != 'auto' and ext in ('f4m', 'm3u8'):
|
|
||||||
continue
|
|
||||||
if ext == 'f4m':
|
|
||||||
formats.extend(self._extract_f4m_formats(
|
|
||||||
update_url_query(stream_url, {
|
|
||||||
'hdcore': '3.1.1',
|
|
||||||
'plugin': 'aasp-3.1.1.69.124'
|
|
||||||
}),
|
|
||||||
video_id, f4m_id='hds', fatal=False))
|
|
||||||
elif ext == 'm3u8':
|
|
||||||
formats.extend(self._extract_m3u8_formats(
|
|
||||||
stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
|
|
||||||
else:
|
|
||||||
if server and server.startswith('rtmp'):
|
|
||||||
f = {
|
|
||||||
'url': server,
|
|
||||||
'play_path': stream_url,
|
|
||||||
'format_id': 'a%s-rtmp-%s' % (num, quality),
|
|
||||||
}
|
|
||||||
else:
|
|
||||||
f = {
|
|
||||||
'url': stream_url,
|
|
||||||
'format_id': 'a%s-%s-%s' % (num, ext, quality)
|
|
||||||
}
|
|
||||||
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
|
|
||||||
if m:
|
|
||||||
f.update({
|
|
||||||
'width': int(m.group('width')),
|
|
||||||
'height': int(m.group('height')),
|
|
||||||
})
|
|
||||||
if type_ == 'audio':
|
|
||||||
f['vcodec'] = 'none'
|
|
||||||
formats.append(f)
|
|
||||||
return formats
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
# determine video id from url
|
# determine video id from url
|
||||||
m = re.match(self._VALID_URL, url)
|
m = re.match(self._VALID_URL, url)
|
||||||
@ -302,19 +309,20 @@ class ARDIE(InfoExtractor):
|
|||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
class ARDBetaMediathekIE(InfoExtractor):
|
class ARDBetaMediathekIE(ARDMediathekBaseIE):
|
||||||
_VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
|
_VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P<client>[^/]+)/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
|
'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
|
||||||
'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
|
'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'display_id': 'die-robuste-roswita',
|
'display_id': 'die-robuste-roswita',
|
||||||
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
|
'id': '70153354',
|
||||||
'title': 'Tatort: Die robuste Roswita',
|
'title': 'Die robuste Roswita',
|
||||||
'description': r're:^Der Mord.*trüber ist als die Ilm.',
|
'description': r're:^Der Mord.*trüber ist als die Ilm.',
|
||||||
'duration': 5316,
|
'duration': 5316,
|
||||||
'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard',
|
'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard',
|
||||||
'upload_date': '20180826',
|
'timestamp': 1577047500,
|
||||||
|
'upload_date': '20191222',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
@ -330,71 +338,69 @@ class ARDBetaMediathekIE(InfoExtractor):
|
|||||||
video_id = mobj.group('video_id')
|
video_id = mobj.group('video_id')
|
||||||
display_id = mobj.group('display_id') or video_id
|
display_id = mobj.group('display_id') or video_id
|
||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
player_page = self._download_json(
|
||||||
data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')
|
'https://api.ardmediathek.de/public-gateway',
|
||||||
data = self._parse_json(data_json, display_id)
|
display_id, data=json.dumps({
|
||||||
|
'query': '''{
|
||||||
res = {
|
playerPage(client:"%s", clipId: "%s") {
|
||||||
'id': video_id,
|
blockedByFsk
|
||||||
'display_id': display_id,
|
broadcastedOn
|
||||||
|
maturityContentRating
|
||||||
|
mediaCollection {
|
||||||
|
_duration
|
||||||
|
_geoblocked
|
||||||
|
_isLive
|
||||||
|
_mediaArray {
|
||||||
|
_mediaStreamArray {
|
||||||
|
_quality
|
||||||
|
_server
|
||||||
|
_stream
|
||||||
}
|
}
|
||||||
formats = []
|
}
|
||||||
subtitles = {}
|
_previewImage
|
||||||
geoblocked = False
|
_subtitleUrl
|
||||||
for widget in data.values():
|
_type
|
||||||
if widget.get('_geoblocked') is True:
|
}
|
||||||
geoblocked = True
|
show {
|
||||||
if '_duration' in widget:
|
title
|
||||||
res['duration'] = int_or_none(widget['_duration'])
|
}
|
||||||
if 'clipTitle' in widget:
|
synopsis
|
||||||
res['title'] = widget['clipTitle']
|
title
|
||||||
if '_previewImage' in widget:
|
tracking {
|
||||||
res['thumbnail'] = widget['_previewImage']
|
atiCustomVars {
|
||||||
if 'broadcastedOn' in widget:
|
contentId
|
||||||
res['timestamp'] = unified_timestamp(widget['broadcastedOn'])
|
}
|
||||||
if 'synopsis' in widget:
|
}
|
||||||
res['description'] = widget['synopsis']
|
}
|
||||||
subtitle_url = url_or_none(widget.get('_subtitleUrl'))
|
}''' % (mobj.group('client'), video_id),
|
||||||
if subtitle_url:
|
}).encode(), headers={
|
||||||
subtitles.setdefault('de', []).append({
|
'Content-Type': 'application/json'
|
||||||
'ext': 'ttml',
|
})['data']['playerPage']
|
||||||
'url': subtitle_url,
|
title = player_page['title']
|
||||||
})
|
content_id = str_or_none(try_get(
|
||||||
if '_quality' in widget:
|
player_page, lambda x: x['tracking']['atiCustomVars']['contentId']))
|
||||||
format_url = url_or_none(try_get(
|
media_collection = player_page.get('mediaCollection') or {}
|
||||||
widget, lambda x: x['_stream']['json'][0]))
|
if not media_collection and content_id:
|
||||||
if not format_url:
|
media_collection = self._download_json(
|
||||||
continue
|
'https://www.ardmediathek.de/play/media/' + content_id,
|
||||||
ext = determine_ext(format_url)
|
content_id, fatal=False) or {}
|
||||||
if ext == 'f4m':
|
info = self._parse_media_info(
|
||||||
formats.extend(self._extract_f4m_formats(
|
media_collection, content_id or video_id,
|
||||||
format_url + '?hdcore=3.11.0',
|
player_page.get('blockedByFsk'))
|
||||||
video_id, f4m_id='hds', fatal=False))
|
age_limit = None
|
||||||
elif ext == 'm3u8':
|
description = player_page.get('synopsis')
|
||||||
formats.extend(self._extract_m3u8_formats(
|
maturity_content_rating = player_page.get('maturityContentRating')
|
||||||
format_url, video_id, 'mp4', m3u8_id='hls',
|
if maturity_content_rating:
|
||||||
fatal=False))
|
age_limit = int_or_none(maturity_content_rating.lstrip('FSK'))
|
||||||
else:
|
if not age_limit and description:
|
||||||
# HTTP formats are not available when geoblocked is True,
|
age_limit = int_or_none(self._search_regex(
|
||||||
# other formats are fine though
|
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
|
||||||
if geoblocked:
|
info.update({
|
||||||
continue
|
'age_limit': age_limit,
|
||||||
quality = str_or_none(widget.get('_quality'))
|
'display_id': display_id,
|
||||||
formats.append({
|
'title': title,
|
||||||
'format_id': ('http-' + quality) if quality else 'http',
|
'description': description,
|
||||||
'url': format_url,
|
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
|
||||||
'preference': 10, # Plain HTTP, that's nice
|
'series': try_get(player_page, lambda x: x['show']['title']),
|
||||||
})
|
|
||||||
|
|
||||||
if not formats and geoblocked:
|
|
||||||
self.raise_geo_restricted(
|
|
||||||
msg='This video is not available due to geoblocking',
|
|
||||||
countries=['DE'])
|
|
||||||
|
|
||||||
self._sort_formats(formats)
|
|
||||||
res.update({
|
|
||||||
'subtitles': subtitles,
|
|
||||||
'formats': formats,
|
|
||||||
})
|
})
|
||||||
|
return info
|
||||||
return res
|
|
||||||
|
|||||||
@ -47,39 +47,19 @@ class AZMedienIE(InfoExtractor):
|
|||||||
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
|
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
|
||||||
'only_matching': True
|
'only_matching': True
|
||||||
}]
|
}]
|
||||||
|
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
|
||||||
_PARTNER_ID = '1719221'
|
_PARTNER_ID = '1719221'
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
host, display_id, article_id, entry_id = re.match(self._VALID_URL, url).groups()
|
||||||
host = mobj.group('host')
|
|
||||||
video_id = mobj.group('id')
|
|
||||||
entry_id = mobj.group('kaltura_id')
|
|
||||||
|
|
||||||
if not entry_id:
|
if not entry_id:
|
||||||
api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0])
|
entry_id = self._download_json(
|
||||||
payload = {
|
self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
|
||||||
'query': '''query VideoContext($articleId: ID!) {
|
'variables': json.dumps({
|
||||||
article: node(id: $articleId) {
|
'contextId': 'NewsArticle:' + article_id,
|
||||||
... on Article {
|
}),
|
||||||
mainAssetRelation {
|
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
|
||||||
asset {
|
|
||||||
... on VideoAsset {
|
|
||||||
kalturaId
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}''',
|
|
||||||
'variables': {'articleId': 'Article:%s' % mobj.group('article_id')},
|
|
||||||
}
|
|
||||||
json_data = self._download_json(
|
|
||||||
api_url, video_id, headers={
|
|
||||||
'Content-Type': 'application/json',
|
|
||||||
},
|
|
||||||
data=json.dumps(payload).encode())
|
|
||||||
entry_id = json_data['data']['article']['mainAssetRelation']['asset']['kalturaId']
|
|
||||||
|
|
||||||
return self.url_result(
|
return self.url_result(
|
||||||
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
|
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),
|
||||||
|
|||||||
@ -9,21 +9,26 @@ class BusinessInsiderIE(InfoExtractor):
|
|||||||
_VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
|
'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
|
||||||
'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
|
'md5': 'ffed3e1e12a6f950aa2f7d83851b497a',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'hZRllCfw',
|
'id': 'cjGDb0X9',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': "Here's how much radiation you're exposed to in everyday life",
|
'title': "Bananas give you more radiation exposure than living next to a nuclear power plant",
|
||||||
'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd',
|
'description': 'md5:0175a3baf200dd8fa658f94cade841b3',
|
||||||
'upload_date': '20170709',
|
'upload_date': '20160611',
|
||||||
'timestamp': 1499606400,
|
'timestamp': 1465675620,
|
||||||
},
|
|
||||||
'params': {
|
|
||||||
'skip_download': True,
|
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
|
'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
|
||||||
'only_matching': True,
|
'md5': '43f438dbc6da0b89f5ac42f68529d84a',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '5zJwd4FK',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Deze dingen zorgen ervoor dat je minder snel een date scoort',
|
||||||
|
'description': 'md5:2af8975825d38a4fed24717bbe51db49',
|
||||||
|
'upload_date': '20170705',
|
||||||
|
'timestamp': 1499270528,
|
||||||
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
|
'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
@ -35,7 +40,8 @@ class BusinessInsiderIE(InfoExtractor):
|
|||||||
jwplatform_id = self._search_regex(
|
jwplatform_id = self._search_regex(
|
||||||
(r'data-media-id=["\']([a-zA-Z0-9]{8})',
|
(r'data-media-id=["\']([a-zA-Z0-9]{8})',
|
||||||
r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
|
r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
|
||||||
r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})'),
|
r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})',
|
||||||
|
r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'),
|
||||||
webpage, 'jwplatform id')
|
webpage, 'jwplatform id')
|
||||||
return self.url_result(
|
return self.url_result(
|
||||||
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
|
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
|
||||||
|
|||||||
@ -13,6 +13,8 @@ from ..utils import (
|
|||||||
int_or_none,
|
int_or_none,
|
||||||
merge_dicts,
|
merge_dicts,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
|
str_or_none,
|
||||||
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -20,15 +22,15 @@ class CanvasIE(InfoExtractor):
|
|||||||
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||||
'md5': '90139b746a0a9bd7bb631283f6e2a64e',
|
'md5': '68993eda72ef62386a15ea2cf3c93107',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||||
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
|
||||||
'ext': 'flv',
|
'ext': 'mp4',
|
||||||
'title': 'Nachtwacht: De Greystook',
|
'title': 'Nachtwacht: De Greystook',
|
||||||
'description': 'md5:1db3f5dc4c7109c821261e7512975be7',
|
'description': 'Nachtwacht: De Greystook',
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
'thumbnail': r're:^https?://.*\.jpg$',
|
||||||
'duration': 1468.03,
|
'duration': 1468.04,
|
||||||
},
|
},
|
||||||
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
|
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
|
||||||
}, {
|
}, {
|
||||||
@ -39,23 +41,45 @@ class CanvasIE(InfoExtractor):
|
|||||||
'HLS': 'm3u8_native',
|
'HLS': 'm3u8_native',
|
||||||
'HLS_AES': 'm3u8',
|
'HLS_AES': 'm3u8',
|
||||||
}
|
}
|
||||||
|
_REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v1'
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
site_id, video_id = mobj.group('site_id'), mobj.group('id')
|
site_id, video_id = mobj.group('site_id'), mobj.group('id')
|
||||||
|
|
||||||
|
# Old API endpoint, serves more formats but may fail for some videos
|
||||||
data = self._download_json(
|
data = self._download_json(
|
||||||
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
|
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
|
||||||
% (site_id, video_id), video_id)
|
% (site_id, video_id), video_id, 'Downloading asset JSON',
|
||||||
|
'Unable to download asset JSON', fatal=False)
|
||||||
|
|
||||||
|
# New API endpoint
|
||||||
|
if not data:
|
||||||
|
token = self._download_json(
|
||||||
|
'%s/tokens' % self._REST_API_BASE, video_id,
|
||||||
|
'Downloading token', data=b'',
|
||||||
|
headers={'Content-Type': 'application/json'})['vrtPlayerToken']
|
||||||
|
data = self._download_json(
|
||||||
|
'%s/videos/%s' % (self._REST_API_BASE, video_id),
|
||||||
|
video_id, 'Downloading video JSON', fatal=False, query={
|
||||||
|
'vrtPlayerToken': token,
|
||||||
|
'client': '%s@PROD' % site_id,
|
||||||
|
}, expected_status=400)
|
||||||
|
message = data.get('message')
|
||||||
|
if message and not data.get('title'):
|
||||||
|
if data.get('code') == 'AUTHENTICATION_REQUIRED':
|
||||||
|
self.raise_login_required(message)
|
||||||
|
raise ExtractorError(message, expected=True)
|
||||||
|
|
||||||
title = data['title']
|
title = data['title']
|
||||||
description = data.get('description')
|
description = data.get('description')
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
for target in data['targetUrls']:
|
for target in data['targetUrls']:
|
||||||
format_url, format_type = target.get('url'), target.get('type')
|
format_url, format_type = url_or_none(target.get('url')), str_or_none(target.get('type'))
|
||||||
if not format_url or not format_type:
|
if not format_url or not format_type:
|
||||||
continue
|
continue
|
||||||
|
format_type = format_type.upper()
|
||||||
if format_type in self._HLS_ENTRY_PROTOCOLS_MAP:
|
if format_type in self._HLS_ENTRY_PROTOCOLS_MAP:
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.extend(self._extract_m3u8_formats(
|
||||||
format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type],
|
format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type],
|
||||||
@ -134,20 +158,20 @@ class CanvasEenIE(InfoExtractor):
|
|||||||
},
|
},
|
||||||
'skip': 'Pagina niet gevonden',
|
'skip': 'Pagina niet gevonden',
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
|
'url': 'https://www.een.be/thuis/emma-pakt-thilly-aan',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
|
'id': 'md-ast-3a24ced2-64d7-44fb-b4ed-ed1aafbf90b8',
|
||||||
'display_id': 'herbekijk-sorry-voor-alles',
|
'display_id': 'emma-pakt-thilly-aan',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Herbekijk Sorry voor alles',
|
'title': 'Emma pakt Thilly aan',
|
||||||
'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
|
'description': 'md5:c5c9b572388a99b2690030afa3f3bad7',
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
'thumbnail': r're:^https?://.*\.jpg$',
|
||||||
'duration': 3788.06,
|
'duration': 118.24,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
'skip': 'Episode no longer available',
|
'expected_warnings': ['is not a supported codec'],
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
|
'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
@ -183,19 +207,44 @@ class VrtNUIE(GigyaBaseIE):
|
|||||||
IE_DESC = 'VrtNU.be'
|
IE_DESC = 'VrtNU.be'
|
||||||
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
|
# Available via old API endpoint
|
||||||
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
|
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
|
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
|
||||||
'ext': 'flv',
|
'ext': 'mp4',
|
||||||
'title': 'De zwarte weduwe',
|
'title': 'De zwarte weduwe',
|
||||||
'description': 'md5:d90c21dced7db869a85db89a623998d4',
|
'description': 'md5:db1227b0f318c849ba5eab1fef895ee4',
|
||||||
'duration': 1457.04,
|
'duration': 1457.04,
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
'thumbnail': r're:^https?://.*\.jpg$',
|
||||||
'season': '1',
|
'season': 'Season 1',
|
||||||
'season_number': 1,
|
'season_number': 1,
|
||||||
'episode_number': 1,
|
'episode_number': 1,
|
||||||
},
|
},
|
||||||
'skip': 'This video is only available for registered users'
|
'skip': 'This video is only available for registered users',
|
||||||
|
'params': {
|
||||||
|
'username': '<snip>',
|
||||||
|
'password': '<snip>',
|
||||||
|
},
|
||||||
|
'expected_warnings': ['is not a supported codec'],
|
||||||
|
}, {
|
||||||
|
# Only available via new API endpoint
|
||||||
|
'url': 'https://www.vrt.be/vrtnu/a-z/kamp-waes/1/kamp-waes-s1a5/',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'pbs-pub-0763b56c-64fb-4d38-b95b-af60bf433c71$vid-ad36a73c-4735-4f1f-b2c0-a38e6e6aa7e1',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Aflevering 5',
|
||||||
|
'description': 'Wie valt door de mand tijdens een missie?',
|
||||||
|
'duration': 2967.06,
|
||||||
|
'season': 'Season 1',
|
||||||
|
'season_number': 1,
|
||||||
|
'episode_number': 5,
|
||||||
|
},
|
||||||
|
'skip': 'This video is only available for registered users',
|
||||||
|
'params': {
|
||||||
|
'username': '<snip>',
|
||||||
|
'password': '<snip>',
|
||||||
|
},
|
||||||
|
'expected_warnings': ['Unable to download asset JSON', 'is not a supported codec', 'Unknown MIME type'],
|
||||||
}]
|
}]
|
||||||
_NETRC_MACHINE = 'vrtnu'
|
_NETRC_MACHINE = 'vrtnu'
|
||||||
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
|
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
|
||||||
|
|||||||
@ -501,7 +501,6 @@ from .jeuxvideo import JeuxVideoIE
|
|||||||
from .jove import JoveIE
|
from .jove import JoveIE
|
||||||
from .joj import JojIE
|
from .joj import JojIE
|
||||||
from .jwplatform import JWPlatformIE
|
from .jwplatform import JWPlatformIE
|
||||||
from .jpopsukitv import JpopsukiIE
|
|
||||||
from .kakao import KakaoIE
|
from .kakao import KakaoIE
|
||||||
from .kaltura import KalturaIE
|
from .kaltura import KalturaIE
|
||||||
from .kanalplay import KanalPlayIE
|
from .kanalplay import KanalPlayIE
|
||||||
@ -854,6 +853,7 @@ from .polskieradio import (
|
|||||||
PolskieRadioIE,
|
PolskieRadioIE,
|
||||||
PolskieRadioCategoryIE,
|
PolskieRadioCategoryIE,
|
||||||
)
|
)
|
||||||
|
from .popcorntimes import PopcorntimesIE
|
||||||
from .popcorntv import PopcornTVIE
|
from .popcorntv import PopcornTVIE
|
||||||
from .porn91 import Porn91IE
|
from .porn91 import Porn91IE
|
||||||
from .porncom import PornComIE
|
from .porncom import PornComIE
|
||||||
|
|||||||
@ -2098,6 +2098,9 @@ class GenericIE(InfoExtractor):
|
|||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Smoky Barbecue Favorites',
|
'title': 'Smoky Barbecue Favorites',
|
||||||
'thumbnail': r're:^https?://.*\.jpe?g',
|
'thumbnail': r're:^https?://.*\.jpe?g',
|
||||||
|
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
|
||||||
|
'upload_date': '20170909',
|
||||||
|
'timestamp': 1504915200,
|
||||||
},
|
},
|
||||||
'add_ie': [ZypeIE.ie_key()],
|
'add_ie': [ZypeIE.ie_key()],
|
||||||
'params': {
|
'params': {
|
||||||
@ -2534,14 +2537,15 @@ class GenericIE(InfoExtractor):
|
|||||||
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
|
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
|
||||||
|
|
||||||
# Look for embedded Wistia player
|
# Look for embedded Wistia player
|
||||||
wistia_url = WistiaIE._extract_url(webpage)
|
wistia_urls = WistiaIE._extract_urls(webpage)
|
||||||
if wistia_url:
|
if wistia_urls:
|
||||||
return {
|
playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
|
||||||
'_type': 'url_transparent',
|
for entry in playlist['entries']:
|
||||||
'url': self._proto_relative_url(wistia_url),
|
entry.update({
|
||||||
'ie_key': WistiaIE.ie_key(),
|
'_type': 'url_transparent',
|
||||||
'uploader': video_uploader,
|
'uploader': video_uploader,
|
||||||
}
|
})
|
||||||
|
return playlist
|
||||||
|
|
||||||
# Look for SVT player
|
# Look for SVT player
|
||||||
svt_url = SVTIE._extract_url(webpage)
|
svt_url = SVTIE._extract_url(webpage)
|
||||||
|
|||||||
@ -1,5 +1,7 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import base64
|
||||||
|
import json
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
@ -8,6 +10,7 @@ from ..utils import (
|
|||||||
mimetype2ext,
|
mimetype2ext,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
qualities,
|
qualities,
|
||||||
|
try_get,
|
||||||
url_or_none,
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
|
||||||
@ -15,15 +18,16 @@ from ..utils import (
|
|||||||
class ImdbIE(InfoExtractor):
|
class ImdbIE(InfoExtractor):
|
||||||
IE_NAME = 'imdb'
|
IE_NAME = 'imdb'
|
||||||
IE_DESC = 'Internet Movie Database trailers'
|
IE_DESC = 'Internet Movie Database trailers'
|
||||||
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).+?[/-]vi(?P<id>\d+)'
|
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
|
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2524815897',
|
'id': '2524815897',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'No. 2 from Ice Age: Continental Drift (2012)',
|
'title': 'No. 2',
|
||||||
'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
|
'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
|
||||||
|
'duration': 152,
|
||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.imdb.com/video/_/vi2524815897',
|
'url': 'http://www.imdb.com/video/_/vi2524815897',
|
||||||
@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor):
|
|||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(
|
|
||||||
'https://www.imdb.com/videoplayer/vi' + video_id, video_id)
|
data = self._download_json(
|
||||||
video_metadata = self._parse_json(self._search_regex(
|
'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id,
|
||||||
r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage,
|
query={
|
||||||
'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id]
|
'key': base64.b64encode(json.dumps({
|
||||||
title = self._html_search_meta(
|
'type': 'VIDEO_PLAYER',
|
||||||
['og:title', 'twitter:title'], webpage) or self._html_search_regex(
|
'subType': 'FORCE_LEGACY',
|
||||||
r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title']
|
'id': 'vi%s' % video_id,
|
||||||
|
}).encode()).decode(),
|
||||||
|
})[0]
|
||||||
|
|
||||||
quality = qualities(('SD', '480p', '720p', '1080p'))
|
quality = qualities(('SD', '480p', '720p', '1080p'))
|
||||||
formats = []
|
formats = []
|
||||||
for encoding in video_metadata.get('encodings', []):
|
for encoding in data['videoLegacyEncodings']:
|
||||||
if not encoding or not isinstance(encoding, dict):
|
if not encoding or not isinstance(encoding, dict):
|
||||||
continue
|
continue
|
||||||
video_url = url_or_none(encoding.get('videoUrl'))
|
video_url = url_or_none(encoding.get('url'))
|
||||||
if not video_url:
|
if not video_url:
|
||||||
continue
|
continue
|
||||||
ext = mimetype2ext(encoding.get(
|
ext = mimetype2ext(encoding.get(
|
||||||
@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor):
|
|||||||
if ext == 'm3u8':
|
if ext == 'm3u8':
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.extend(self._extract_m3u8_formats(
|
||||||
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
||||||
m3u8_id='hls', fatal=False))
|
preference=1, m3u8_id='hls', fatal=False))
|
||||||
continue
|
continue
|
||||||
format_id = encoding.get('definition')
|
format_id = encoding.get('definition')
|
||||||
formats.append({
|
formats.append({
|
||||||
@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor):
|
|||||||
})
|
})
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
webpage = self._download_webpage(
|
||||||
|
'https://www.imdb.com/video/vi' + video_id, video_id)
|
||||||
|
video_metadata = self._parse_json(self._search_regex(
|
||||||
|
r'args\.push\(\s*({.+?})\s*\)\s*;', webpage,
|
||||||
|
'video metadata'), video_id)
|
||||||
|
|
||||||
|
video_info = video_metadata.get('VIDEO_INFO')
|
||||||
|
if video_info and isinstance(video_info, dict):
|
||||||
|
info = try_get(
|
||||||
|
video_info, lambda x: x[list(video_info.keys())[0]][0], dict)
|
||||||
|
else:
|
||||||
|
info = {}
|
||||||
|
|
||||||
|
title = self._html_search_meta(
|
||||||
|
['og:title', 'twitter:title'], webpage) or self._html_search_regex(
|
||||||
|
r'<title>(.+?)</title>', webpage, 'title',
|
||||||
|
default=None) or info['videoTitle']
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
|
'alt_title': info.get('videoSubTitle'),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'description': video_metadata.get('description'),
|
'description': info.get('videoDescription'),
|
||||||
'thumbnail': video_metadata.get('slate', {}).get('url'),
|
'thumbnail': url_or_none(try_get(
|
||||||
'duration': parse_duration(video_metadata.get('duration')),
|
video_metadata, lambda x: x['videoSlate']['source'])),
|
||||||
|
'duration': parse_duration(info.get('videoRuntime')),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@ -239,7 +239,7 @@ class IviCompilationIE(InfoExtractor):
|
|||||||
self.url_result(
|
self.url_result(
|
||||||
'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
|
'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
|
||||||
for serie in re.findall(
|
for serie in re.findall(
|
||||||
r'<a href="/watch/%s/(\d+)"[^>]+data-id="\1"' % compilation_id, html)]
|
r'<a\b[^>]+\bhref=["\']/watch/%s/(\d+)["\']' % compilation_id, html)]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
mobj = re.match(self._VALID_URL, url)
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
|||||||
@ -1,68 +0,0 @@
|
|||||||
# coding: utf-8
|
|
||||||
from __future__ import unicode_literals
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
|
||||||
from ..utils import (
|
|
||||||
int_or_none,
|
|
||||||
unified_strdate,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class JpopsukiIE(InfoExtractor):
|
|
||||||
IE_NAME = 'jpopsuki.tv'
|
|
||||||
_VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P<id>\S+)'
|
|
||||||
|
|
||||||
_TEST = {
|
|
||||||
'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
|
|
||||||
'md5': '88018c0c1a9b1387940e90ec9e7e198e',
|
|
||||||
'info_dict': {
|
|
||||||
'id': '00be659d23b0b40508169cdee4545771',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'title': 'ayumi hamasaki - evolution',
|
|
||||||
'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
|
|
||||||
'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
|
|
||||||
'uploader': 'plama_chan',
|
|
||||||
'uploader_id': '404',
|
|
||||||
'upload_date': '20121101'
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
video_id = self._match_id(url)
|
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
|
||||||
|
|
||||||
video_url = 'http://www.jpopsuki.tv' + self._html_search_regex(
|
|
||||||
r'<source src="(.*?)" type', webpage, 'video url')
|
|
||||||
|
|
||||||
video_title = self._og_search_title(webpage)
|
|
||||||
description = self._og_search_description(webpage)
|
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
|
||||||
uploader = self._html_search_regex(
|
|
||||||
r'<li>from: <a href="/user/view/user/(.*?)/uid/',
|
|
||||||
webpage, 'video uploader', fatal=False)
|
|
||||||
uploader_id = self._html_search_regex(
|
|
||||||
r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)',
|
|
||||||
webpage, 'video uploader_id', fatal=False)
|
|
||||||
upload_date = unified_strdate(self._html_search_regex(
|
|
||||||
r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date',
|
|
||||||
fatal=False))
|
|
||||||
view_count_str = self._html_search_regex(
|
|
||||||
r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
|
|
||||||
fatal=False)
|
|
||||||
comment_count_str = self._html_search_regex(
|
|
||||||
r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
|
|
||||||
fatal=False)
|
|
||||||
|
|
||||||
return {
|
|
||||||
'id': video_id,
|
|
||||||
'url': video_url,
|
|
||||||
'title': video_title,
|
|
||||||
'description': description,
|
|
||||||
'thumbnail': thumbnail,
|
|
||||||
'uploader': uploader,
|
|
||||||
'uploader_id': uploader_id,
|
|
||||||
'upload_date': upload_date,
|
|
||||||
'view_count': int_or_none(view_count_str),
|
|
||||||
'comment_count': int_or_none(comment_count_str),
|
|
||||||
}
|
|
||||||
@ -87,11 +87,25 @@ class NBCIE(AdobePassIE):
|
|||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
permalink, video_id = re.match(self._VALID_URL, url).groups()
|
permalink, video_id = re.match(self._VALID_URL, url).groups()
|
||||||
permalink = 'http' + compat_urllib_parse_unquote(permalink)
|
permalink = 'http' + compat_urllib_parse_unquote(permalink)
|
||||||
response = self._download_json(
|
video_data = self._download_json(
|
||||||
'https://friendship.nbc.co/v2/graphql', video_id, query={
|
'https://friendship.nbc.co/v2/graphql', video_id, query={
|
||||||
'query': '''{
|
'query': '''query bonanzaPage(
|
||||||
page(name: "%s", platform: web, type: VIDEO, userId: "0") {
|
$app: NBCUBrands! = nbc
|
||||||
data {
|
$name: String!
|
||||||
|
$oneApp: Boolean
|
||||||
|
$platform: SupportedPlatforms! = web
|
||||||
|
$type: EntityPageType! = VIDEO
|
||||||
|
$userId: String!
|
||||||
|
) {
|
||||||
|
bonanzaPage(
|
||||||
|
app: $app
|
||||||
|
name: $name
|
||||||
|
oneApp: $oneApp
|
||||||
|
platform: $platform
|
||||||
|
type: $type
|
||||||
|
userId: $userId
|
||||||
|
) {
|
||||||
|
metadata {
|
||||||
... on VideoPageData {
|
... on VideoPageData {
|
||||||
description
|
description
|
||||||
episodeNumber
|
episodeNumber
|
||||||
@ -100,15 +114,20 @@ class NBCIE(AdobePassIE):
|
|||||||
mpxAccountId
|
mpxAccountId
|
||||||
mpxGuid
|
mpxGuid
|
||||||
rating
|
rating
|
||||||
|
resourceId
|
||||||
seasonNumber
|
seasonNumber
|
||||||
secondaryTitle
|
secondaryTitle
|
||||||
seriesShortTitle
|
seriesShortTitle
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}''' % permalink,
|
}''',
|
||||||
})
|
'variables': json.dumps({
|
||||||
video_data = response['data']['page']['data']
|
'name': permalink,
|
||||||
|
'oneApp': True,
|
||||||
|
'userId': '0',
|
||||||
|
}),
|
||||||
|
})['data']['bonanzaPage']['metadata']
|
||||||
query = {
|
query = {
|
||||||
'mbr': 'true',
|
'mbr': 'true',
|
||||||
'manifest': 'm3u',
|
'manifest': 'm3u',
|
||||||
@ -117,8 +136,8 @@ class NBCIE(AdobePassIE):
|
|||||||
title = video_data['secondaryTitle']
|
title = video_data['secondaryTitle']
|
||||||
if video_data.get('locked'):
|
if video_data.get('locked'):
|
||||||
resource = self._get_mvpd_resource(
|
resource = self._get_mvpd_resource(
|
||||||
'nbcentertainment', title, video_id,
|
video_data.get('resourceId') or 'nbcentertainment',
|
||||||
video_data.get('rating'))
|
title, video_id, video_data.get('rating'))
|
||||||
query['auth'] = self._extract_mvpd_auth(
|
query['auth'] = self._extract_mvpd_auth(
|
||||||
url, video_id, 'nbcentertainment', resource)
|
url, video_id, 'nbcentertainment', resource)
|
||||||
theplatform_url = smuggle_url(update_url_query(
|
theplatform_url = smuggle_url(update_url_query(
|
||||||
|
|||||||
@ -9,6 +9,8 @@ from ..utils import (
|
|||||||
int_or_none,
|
int_or_none,
|
||||||
parse_iso8601,
|
parse_iso8601,
|
||||||
qualities,
|
qualities,
|
||||||
|
try_get,
|
||||||
|
urljoin,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -220,11 +222,17 @@ class NDREmbedBaseIE(InfoExtractor):
|
|||||||
upload_date = ppjson.get('config', {}).get('publicationDate')
|
upload_date = ppjson.get('config', {}).get('publicationDate')
|
||||||
duration = int_or_none(config.get('duration'))
|
duration = int_or_none(config.get('duration'))
|
||||||
|
|
||||||
thumbnails = [{
|
thumbnails = []
|
||||||
'id': thumbnail.get('quality') or thumbnail_id,
|
poster = try_get(config, lambda x: x['poster'], dict) or {}
|
||||||
'url': thumbnail['src'],
|
for thumbnail_id, thumbnail in poster.items():
|
||||||
'preference': quality_key(thumbnail.get('quality')),
|
thumbnail_url = urljoin(url, thumbnail.get('src'))
|
||||||
} for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')]
|
if not thumbnail_url:
|
||||||
|
continue
|
||||||
|
thumbnails.append({
|
||||||
|
'id': thumbnail.get('quality') or thumbnail_id,
|
||||||
|
'url': thumbnail_url,
|
||||||
|
'preference': quality_key(thumbnail.get('quality')),
|
||||||
|
})
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
|
|||||||
@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor):
|
|||||||
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
|
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
|
||||||
'md5': 'b3834f6de5401baabf31ed57456463f7',
|
'md5': 'ee009bafcc794541570edd44b71cbea3',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '8o0n0r',
|
'id': '8o0n0r',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
@ -44,11 +44,17 @@ class NovaEmbedIE(InfoExtractor):
|
|||||||
formats = []
|
formats = []
|
||||||
for format_id, format_list in bitrates.items():
|
for format_id, format_list in bitrates.items():
|
||||||
if not isinstance(format_list, list):
|
if not isinstance(format_list, list):
|
||||||
continue
|
format_list = [format_list]
|
||||||
for format_url in format_list:
|
for format_url in format_list:
|
||||||
format_url = url_or_none(format_url)
|
format_url = url_or_none(format_url)
|
||||||
if not format_url:
|
if not format_url:
|
||||||
continue
|
continue
|
||||||
|
if format_id == 'hls':
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
format_url, video_id, ext='mp4',
|
||||||
|
entry_protocol='m3u8_native', m3u8_id='hls',
|
||||||
|
fatal=False))
|
||||||
|
continue
|
||||||
f = {
|
f = {
|
||||||
'url': format_url,
|
'url': format_url,
|
||||||
}
|
}
|
||||||
@ -91,7 +97,7 @@ class NovaIE(InfoExtractor):
|
|||||||
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
|
_VALID_URL = r'https?://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
|
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
|
||||||
'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
|
'md5': '249baab7d0104e186e78b0899c7d5f28',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '1757139',
|
'id': '1757139',
|
||||||
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
|
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
|
||||||
@ -113,7 +119,8 @@ class NovaIE(InfoExtractor):
|
|||||||
'params': {
|
'params': {
|
||||||
# rtmp download
|
# rtmp download
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
}
|
},
|
||||||
|
'skip': 'gone',
|
||||||
}, {
|
}, {
|
||||||
# media.cms.nova.cz embed
|
# media.cms.nova.cz embed
|
||||||
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
|
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
|
||||||
@ -128,6 +135,7 @@ class NovaIE(InfoExtractor):
|
|||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
'add_ie': [NovaEmbedIE.ie_key()],
|
'add_ie': [NovaEmbedIE.ie_key()],
|
||||||
|
'skip': 'CHYBA 404: STRÁNKA NENALEZENA',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
|
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
@ -152,14 +160,29 @@ class NovaIE(InfoExtractor):
|
|||||||
|
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
|
description = clean_html(self._og_search_description(webpage, default=None))
|
||||||
|
if site == 'novaplus':
|
||||||
|
upload_date = unified_strdate(self._search_regex(
|
||||||
|
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
|
||||||
|
elif site == 'fanda':
|
||||||
|
upload_date = unified_strdate(self._search_regex(
|
||||||
|
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
|
||||||
|
else:
|
||||||
|
upload_date = None
|
||||||
|
|
||||||
# novaplus
|
# novaplus
|
||||||
embed_id = self._search_regex(
|
embed_id = self._search_regex(
|
||||||
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
|
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
|
||||||
webpage, 'embed url', default=None)
|
webpage, 'embed url', default=None)
|
||||||
if embed_id:
|
if embed_id:
|
||||||
return self.url_result(
|
return {
|
||||||
'https://media.cms.nova.cz/embed/%s' % embed_id,
|
'_type': 'url_transparent',
|
||||||
ie=NovaEmbedIE.ie_key(), video_id=embed_id)
|
'url': 'https://media.cms.nova.cz/embed/%s' % embed_id,
|
||||||
|
'ie_key': NovaEmbedIE.ie_key(),
|
||||||
|
'id': embed_id,
|
||||||
|
'description': description,
|
||||||
|
'upload_date': upload_date
|
||||||
|
}
|
||||||
|
|
||||||
video_id = self._search_regex(
|
video_id = self._search_regex(
|
||||||
[r"(?:media|video_id)\s*:\s*'(\d+)'",
|
[r"(?:media|video_id)\s*:\s*'(\d+)'",
|
||||||
@ -233,18 +256,8 @@ class NovaIE(InfoExtractor):
|
|||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
|
title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage)
|
||||||
description = clean_html(self._og_search_description(webpage, default=None))
|
|
||||||
thumbnail = config.get('poster')
|
thumbnail = config.get('poster')
|
||||||
|
|
||||||
if site == 'novaplus':
|
|
||||||
upload_date = unified_strdate(self._search_regex(
|
|
||||||
r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None))
|
|
||||||
elif site == 'fanda':
|
|
||||||
upload_date = unified_strdate(self._search_regex(
|
|
||||||
r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None))
|
|
||||||
else:
|
|
||||||
upload_date = None
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
|
|||||||
@ -4,6 +4,7 @@ from .common import InfoExtractor
|
|||||||
from ..utils import (
|
from ..utils import (
|
||||||
int_or_none,
|
int_or_none,
|
||||||
qualities,
|
qualities,
|
||||||
|
url_or_none,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -48,6 +49,10 @@ class NprIE(InfoExtractor):
|
|||||||
},
|
},
|
||||||
}],
|
}],
|
||||||
'expected_warnings': ['Failed to download m3u8 information'],
|
'expected_warnings': ['Failed to download m3u8 information'],
|
||||||
|
}, {
|
||||||
|
# multimedia, no formats, stream
|
||||||
|
'url': 'https://www.npr.org/2020/02/14/805476846/laura-stevenson-tiny-desk-concert',
|
||||||
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
@ -95,6 +100,17 @@ class NprIE(InfoExtractor):
|
|||||||
'format_id': format_id,
|
'format_id': format_id,
|
||||||
'quality': quality(format_id),
|
'quality': quality(format_id),
|
||||||
})
|
})
|
||||||
|
for stream_id, stream_entry in media.get('stream', {}).items():
|
||||||
|
if not isinstance(stream_entry, dict):
|
||||||
|
continue
|
||||||
|
if stream_id != 'hlsUrl':
|
||||||
|
continue
|
||||||
|
stream_url = url_or_none(stream_entry.get('$text'))
|
||||||
|
if not stream_url:
|
||||||
|
continue
|
||||||
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
stream_url, stream_id, 'mp4', 'm3u8_native',
|
||||||
|
m3u8_id='hls', fatal=False))
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
entries.append({
|
entries.append({
|
||||||
|
|||||||
@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor):
|
|||||||
'width': int_or_none(video.get('width')),
|
'width': int_or_none(video.get('width')),
|
||||||
'height': int_or_none(video.get('height')),
|
'height': int_or_none(video.get('height')),
|
||||||
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
|
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
|
||||||
'tbr': int_or_none(video.get('bitrate'), 1000),
|
'tbr': int_or_none(video.get('bitrate'), 1000) or None,
|
||||||
'ext': ext,
|
'ext': ext,
|
||||||
})
|
})
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id'))
|
||||||
|
|
||||||
thumbnails = []
|
thumbnails = []
|
||||||
for image in video_data.get('images', []):
|
for image in video_data.get('images', []):
|
||||||
|
|||||||
@ -90,8 +90,11 @@ class ORFTVthekIE(InfoExtractor):
|
|||||||
format_id = '-'.join(format_id_list)
|
format_id = '-'.join(format_id_list)
|
||||||
ext = determine_ext(src)
|
ext = determine_ext(src)
|
||||||
if ext == 'm3u8':
|
if ext == 'm3u8':
|
||||||
formats.extend(self._extract_m3u8_formats(
|
m3u8_formats = self._extract_m3u8_formats(
|
||||||
src, video_id, 'mp4', m3u8_id=format_id, fatal=False))
|
src, video_id, 'mp4', m3u8_id=format_id, fatal=False)
|
||||||
|
if any('/geoprotection' in f['url'] for f in m3u8_formats):
|
||||||
|
self.raise_geo_restricted()
|
||||||
|
formats.extend(m3u8_formats)
|
||||||
elif ext == 'f4m':
|
elif ext == 'f4m':
|
||||||
formats.extend(self._extract_f4m_formats(
|
formats.extend(self._extract_f4m_formats(
|
||||||
src, video_id, f4m_id=format_id, fatal=False))
|
src, video_id, f4m_id=format_id, fatal=False))
|
||||||
|
|||||||
99
youtube_dl/extractor/popcorntimes.py
Normal file
99
youtube_dl/extractor/popcorntimes.py
Normal file
@ -0,0 +1,99 @@
|
|||||||
|
# coding: utf-8
|
||||||
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..compat import (
|
||||||
|
compat_b64decode,
|
||||||
|
compat_chr,
|
||||||
|
)
|
||||||
|
from ..utils import int_or_none
|
||||||
|
|
||||||
|
|
||||||
|
class PopcorntimesIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'https?://popcorntimes\.tv/[^/]+/m/(?P<id>[^/]+)/(?P<display_id>[^/?#&]+)'
|
||||||
|
_TEST = {
|
||||||
|
'url': 'https://popcorntimes.tv/de/m/A1XCFvz/haensel-und-gretel-opera-fantasy',
|
||||||
|
'md5': '93f210991ad94ba8c3485950a2453257',
|
||||||
|
'info_dict': {
|
||||||
|
'id': 'A1XCFvz',
|
||||||
|
'display_id': 'haensel-und-gretel-opera-fantasy',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': 'Hänsel und Gretel',
|
||||||
|
'description': 'md5:1b8146791726342e7b22ce8125cf6945',
|
||||||
|
'thumbnail': r're:^https?://.*\.jpg$',
|
||||||
|
'creator': 'John Paul',
|
||||||
|
'release_date': '19541009',
|
||||||
|
'duration': 4260,
|
||||||
|
'tbr': 5380,
|
||||||
|
'width': 720,
|
||||||
|
'height': 540,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
video_id, display_id = mobj.group('id', 'display_id')
|
||||||
|
|
||||||
|
webpage = self._download_webpage(url, display_id)
|
||||||
|
|
||||||
|
title = self._search_regex(
|
||||||
|
r'<h1>([^<]+)', webpage, 'title',
|
||||||
|
default=None) or self._html_search_meta(
|
||||||
|
'ya:ovs:original_name', webpage, 'title', fatal=True)
|
||||||
|
|
||||||
|
loc = self._search_regex(
|
||||||
|
r'PCTMLOC\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage, 'loc',
|
||||||
|
group='value')
|
||||||
|
|
||||||
|
loc_b64 = ''
|
||||||
|
for c in loc:
|
||||||
|
c_ord = ord(c)
|
||||||
|
if ord('a') <= c_ord <= ord('z') or ord('A') <= c_ord <= ord('Z'):
|
||||||
|
upper = ord('Z') if c_ord <= ord('Z') else ord('z')
|
||||||
|
c_ord += 13
|
||||||
|
if upper < c_ord:
|
||||||
|
c_ord -= 26
|
||||||
|
loc_b64 += compat_chr(c_ord)
|
||||||
|
|
||||||
|
video_url = compat_b64decode(loc_b64).decode('utf-8')
|
||||||
|
|
||||||
|
description = self._html_search_regex(
|
||||||
|
r'(?s)<div[^>]+class=["\']pt-movie-desc[^>]+>(.+?)</div>', webpage,
|
||||||
|
'description', fatal=False)
|
||||||
|
|
||||||
|
thumbnail = self._search_regex(
|
||||||
|
r'<img[^>]+class=["\']video-preview[^>]+\bsrc=(["\'])(?P<value>(?:(?!\1).)+)\1',
|
||||||
|
webpage, 'thumbnail', default=None,
|
||||||
|
group='value') or self._og_search_thumbnail(webpage)
|
||||||
|
|
||||||
|
creator = self._html_search_meta(
|
||||||
|
'video:director', webpage, 'creator', default=None)
|
||||||
|
|
||||||
|
release_date = self._html_search_meta(
|
||||||
|
'video:release_date', webpage, default=None)
|
||||||
|
if release_date:
|
||||||
|
release_date = release_date.replace('-', '')
|
||||||
|
|
||||||
|
def int_meta(name):
|
||||||
|
return int_or_none(self._html_search_meta(
|
||||||
|
name, webpage, default=None))
|
||||||
|
|
||||||
|
return {
|
||||||
|
'id': video_id,
|
||||||
|
'display_id': display_id,
|
||||||
|
'url': video_url,
|
||||||
|
'title': title,
|
||||||
|
'description': description,
|
||||||
|
'thumbnail': thumbnail,
|
||||||
|
'creator': creator,
|
||||||
|
'release_date': release_date,
|
||||||
|
'duration': int_meta('video:duration'),
|
||||||
|
'tbr': int_meta('ya:ovs:bitrate'),
|
||||||
|
'width': int_meta('og:video:width'),
|
||||||
|
'height': int_meta('og:video:height'),
|
||||||
|
'http_headers': {
|
||||||
|
'Referer': url,
|
||||||
|
},
|
||||||
|
}
|
||||||
@ -8,6 +8,7 @@ from ..utils import (
|
|||||||
ExtractorError,
|
ExtractorError,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
js_to_json,
|
js_to_json,
|
||||||
|
merge_dicts,
|
||||||
urljoin,
|
urljoin,
|
||||||
)
|
)
|
||||||
|
|
||||||
@ -27,23 +28,22 @@ class PornHdIE(InfoExtractor):
|
|||||||
'view_count': int,
|
'view_count': int,
|
||||||
'like_count': int,
|
'like_count': int,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
}
|
},
|
||||||
|
'skip': 'HTTP Error 404: Not Found',
|
||||||
}, {
|
}, {
|
||||||
# removed video
|
|
||||||
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
|
'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
|
||||||
'md5': '956b8ca569f7f4d8ec563e2c41598441',
|
'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '1962',
|
'id': '1962',
|
||||||
'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
|
'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Sierra loves doing laundry',
|
'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759',
|
||||||
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
|
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
|
||||||
'thumbnail': r're:^https?://.*\.jpg',
|
'thumbnail': r're:^https?://.*\.jpg',
|
||||||
'view_count': int,
|
'view_count': int,
|
||||||
'like_count': int,
|
'like_count': int,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
},
|
},
|
||||||
'skip': 'Not available anymore',
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
@ -61,7 +61,13 @@ class PornHdIE(InfoExtractor):
|
|||||||
r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
|
r"(?s)sources'?\s*[:=]\s*(\{.+?\})",
|
||||||
webpage, 'sources', default='{}')), video_id)
|
webpage, 'sources', default='{}')), video_id)
|
||||||
|
|
||||||
|
info = {}
|
||||||
if not sources:
|
if not sources:
|
||||||
|
entries = self._parse_html5_media_entries(url, webpage, video_id)
|
||||||
|
if entries:
|
||||||
|
info = entries[0]
|
||||||
|
|
||||||
|
if not sources and not info:
|
||||||
message = self._html_search_regex(
|
message = self._html_search_regex(
|
||||||
r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
|
r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
|
||||||
webpage, 'error message', group='value')
|
webpage, 'error message', group='value')
|
||||||
@ -80,23 +86,29 @@ class PornHdIE(InfoExtractor):
|
|||||||
'format_id': format_id,
|
'format_id': format_id,
|
||||||
'height': height,
|
'height': height,
|
||||||
})
|
})
|
||||||
self._sort_formats(formats)
|
if formats:
|
||||||
|
info['formats'] = formats
|
||||||
|
self._sort_formats(info['formats'])
|
||||||
|
|
||||||
description = self._html_search_regex(
|
description = self._html_search_regex(
|
||||||
r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
|
(r'(?s)<section[^>]+class=["\']video-description[^>]+>(?P<value>.+?)</section>',
|
||||||
webpage, 'description', fatal=False, group='value')
|
r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1'),
|
||||||
|
webpage, 'description', fatal=False,
|
||||||
|
group='value') or self._html_search_meta(
|
||||||
|
'description', webpage, default=None) or self._og_search_description(webpage)
|
||||||
view_count = int_or_none(self._html_search_regex(
|
view_count = int_or_none(self._html_search_regex(
|
||||||
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
|
r'(\d+) views\s*<', webpage, 'view count', fatal=False))
|
||||||
thumbnail = self._search_regex(
|
thumbnail = self._search_regex(
|
||||||
r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
|
r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
|
||||||
'thumbnail', fatal=False, group='url')
|
'thumbnail', default=None, group='url')
|
||||||
|
|
||||||
like_count = int_or_none(self._search_regex(
|
like_count = int_or_none(self._search_regex(
|
||||||
(r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes',
|
(r'(\d+)</span>\s*likes',
|
||||||
|
r'(\d+)\s*</11[^>]+>(?: |\s)*\blikes',
|
||||||
r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
|
r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
|
||||||
webpage, 'like count', fatal=False))
|
webpage, 'like count', fatal=False))
|
||||||
|
|
||||||
return {
|
return merge_dicts(info, {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
@ -106,4 +118,4 @@ class PornHdIE(InfoExtractor):
|
|||||||
'like_count': like_count,
|
'like_count': like_count,
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
}
|
})
|
||||||
|
|||||||
@ -96,7 +96,7 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
'repost_count': int,
|
'repost_count': int,
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
# not streamable song
|
# not streamable song, preview
|
||||||
{
|
{
|
||||||
'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
|
'url': 'https://soundcloud.com/the-concept-band/goldrushed-mastered?in=the-concept-band/sets/the-royal-concept-ep',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
@ -119,7 +119,6 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
# rtmp
|
# rtmp
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
},
|
},
|
||||||
'skip': 'Preview',
|
|
||||||
},
|
},
|
||||||
# private link
|
# private link
|
||||||
{
|
{
|
||||||
@ -239,7 +238,7 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
'ext': 'mp3',
|
'ext': 'mp3',
|
||||||
'title': 'Mezzo Valzer',
|
'title': 'Mezzo Valzer',
|
||||||
'description': 'md5:4138d582f81866a530317bae316e8b61',
|
'description': 'md5:4138d582f81866a530317bae316e8b61',
|
||||||
'uploader': 'Giovanni Sarani',
|
'uploader': 'Micronie',
|
||||||
'uploader_id': '3352531',
|
'uploader_id': '3352531',
|
||||||
'timestamp': 1551394171,
|
'timestamp': 1551394171,
|
||||||
'upload_date': '20190228',
|
'upload_date': '20190228',
|
||||||
@ -346,9 +345,9 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
})
|
})
|
||||||
|
|
||||||
def invalid_url(url):
|
def invalid_url(url):
|
||||||
return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url)
|
return not url or url in format_urls
|
||||||
|
|
||||||
def add_format(f, protocol):
|
def add_format(f, protocol, is_preview=False):
|
||||||
mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
|
mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
|
||||||
if mobj:
|
if mobj:
|
||||||
for k, v in mobj.groupdict().items():
|
for k, v in mobj.groupdict().items():
|
||||||
@ -361,12 +360,16 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
v = f.get(k)
|
v = f.get(k)
|
||||||
if v:
|
if v:
|
||||||
format_id_list.append(v)
|
format_id_list.append(v)
|
||||||
|
preview = is_preview or re.search(r'/(?:preview|playlist)/0/30/', f['url'])
|
||||||
|
if preview:
|
||||||
|
format_id_list.append('preview')
|
||||||
abr = f.get('abr')
|
abr = f.get('abr')
|
||||||
if abr:
|
if abr:
|
||||||
f['abr'] = int(abr)
|
f['abr'] = int(abr)
|
||||||
f.update({
|
f.update({
|
||||||
'format_id': '_'.join(format_id_list),
|
'format_id': '_'.join(format_id_list),
|
||||||
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
|
'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
|
||||||
|
'preference': -10 if preview else None,
|
||||||
})
|
})
|
||||||
formats.append(f)
|
formats.append(f)
|
||||||
|
|
||||||
@ -377,7 +380,7 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
if not isinstance(t, dict):
|
if not isinstance(t, dict):
|
||||||
continue
|
continue
|
||||||
format_url = url_or_none(t.get('url'))
|
format_url = url_or_none(t.get('url'))
|
||||||
if not format_url or t.get('snipped') or '/preview/' in format_url:
|
if not format_url:
|
||||||
continue
|
continue
|
||||||
stream = self._download_json(
|
stream = self._download_json(
|
||||||
format_url, track_id, query=query, fatal=False)
|
format_url, track_id, query=query, fatal=False)
|
||||||
@ -400,7 +403,8 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
add_format({
|
add_format({
|
||||||
'url': stream_url,
|
'url': stream_url,
|
||||||
'ext': ext,
|
'ext': ext,
|
||||||
}, 'http' if protocol == 'progressive' else protocol)
|
}, 'http' if protocol == 'progressive' else protocol,
|
||||||
|
t.get('snipped') or '/preview/' in format_url)
|
||||||
|
|
||||||
if not formats:
|
if not formats:
|
||||||
# Old API, does not work for some tracks (e.g.
|
# Old API, does not work for some tracks (e.g.
|
||||||
@ -520,7 +524,17 @@ class SoundcloudIE(InfoExtractor):
|
|||||||
|
|
||||||
|
|
||||||
class SoundcloudPlaylistBaseIE(SoundcloudIE):
|
class SoundcloudPlaylistBaseIE(SoundcloudIE):
|
||||||
def _extract_track_entries(self, tracks, token=None):
|
def _extract_set(self, playlist, token=None):
|
||||||
|
playlist_id = compat_str(playlist['id'])
|
||||||
|
tracks = playlist.get('tracks') or []
|
||||||
|
if not all([t.get('permalink_url') for t in tracks]) and token:
|
||||||
|
tracks = self._download_json(
|
||||||
|
self._API_V2_BASE + 'tracks', playlist_id,
|
||||||
|
'Downloading tracks', query={
|
||||||
|
'ids': ','.join([compat_str(t['id']) for t in tracks]),
|
||||||
|
'playlistId': playlist_id,
|
||||||
|
'playlistSecretToken': token,
|
||||||
|
})
|
||||||
entries = []
|
entries = []
|
||||||
for track in tracks:
|
for track in tracks:
|
||||||
track_id = str_or_none(track.get('id'))
|
track_id = str_or_none(track.get('id'))
|
||||||
@ -533,7 +547,10 @@ class SoundcloudPlaylistBaseIE(SoundcloudIE):
|
|||||||
url += '?secret_token=' + token
|
url += '?secret_token=' + token
|
||||||
entries.append(self.url_result(
|
entries.append(self.url_result(
|
||||||
url, SoundcloudIE.ie_key(), track_id))
|
url, SoundcloudIE.ie_key(), track_id))
|
||||||
return entries
|
return self.playlist_result(
|
||||||
|
entries, playlist_id,
|
||||||
|
playlist.get('title'),
|
||||||
|
playlist.get('description'))
|
||||||
|
|
||||||
|
|
||||||
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
||||||
@ -544,6 +561,7 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
|||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2284613',
|
'id': '2284613',
|
||||||
'title': 'The Royal Concept EP',
|
'title': 'The Royal Concept EP',
|
||||||
|
'description': 'md5:71d07087c7a449e8941a70a29e34671e',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 5,
|
'playlist_mincount': 5,
|
||||||
}, {
|
}, {
|
||||||
@ -566,13 +584,10 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
|
|||||||
msgs = (compat_str(err['error_message']) for err in info['errors'])
|
msgs = (compat_str(err['error_message']) for err in info['errors'])
|
||||||
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
|
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
|
||||||
|
|
||||||
entries = self._extract_track_entries(info['tracks'], token)
|
return self._extract_set(info, token)
|
||||||
|
|
||||||
return self.playlist_result(
|
|
||||||
entries, str_or_none(info.get('id')), info.get('title'))
|
|
||||||
|
|
||||||
|
|
||||||
class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
|
class SoundcloudPagedPlaylistBaseIE(SoundcloudIE):
|
||||||
def _extract_playlist(self, base_url, playlist_id, playlist_title):
|
def _extract_playlist(self, base_url, playlist_id, playlist_title):
|
||||||
COMMON_QUERY = {
|
COMMON_QUERY = {
|
||||||
'limit': 2000000000,
|
'limit': 2000000000,
|
||||||
@ -770,10 +785,7 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
|
|||||||
self._API_V2_BASE + 'playlists/' + playlist_id,
|
self._API_V2_BASE + 'playlists/' + playlist_id,
|
||||||
playlist_id, 'Downloading playlist', query=query)
|
playlist_id, 'Downloading playlist', query=query)
|
||||||
|
|
||||||
entries = self._extract_track_entries(data['tracks'], token)
|
return self._extract_set(data, token)
|
||||||
|
|
||||||
return self.playlist_result(
|
|
||||||
entries, playlist_id, data.get('title'), data.get('description'))
|
|
||||||
|
|
||||||
|
|
||||||
class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
|
class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
|
||||||
|
|||||||
@ -13,36 +13,18 @@ from ..utils import (
|
|||||||
class SportDeutschlandIE(InfoExtractor):
|
class SportDeutschlandIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
|
_VALID_URL = r'https?://sportdeutschland\.tv/(?P<sport>[^/?#]+)/(?P<id>[^?#/]+)(?:$|[?#])'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://sportdeutschland.tv/badminton/live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
|
'url': 'https://sportdeutschland.tv/badminton/re-live-deutsche-meisterschaften-2020-halbfinals?playlistId=0',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen',
|
'id': 're-live-deutsche-meisterschaften-2020-halbfinals',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen',
|
'title': 're:Re-live: Deutsche Meisterschaften 2020.*Halbfinals',
|
||||||
'categories': ['Badminton'],
|
'categories': ['Badminton-Deutschland'],
|
||||||
'view_count': int,
|
'view_count': int,
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
'thumbnail': r're:^https?://.*\.(?:jpg|png)$',
|
||||||
'description': r're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV',
|
|
||||||
'timestamp': int,
|
'timestamp': int,
|
||||||
'upload_date': 're:^201408[23][0-9]$',
|
'upload_date': '20200201',
|
||||||
|
'description': 're:.*', # meaningless description for THIS video
|
||||||
},
|
},
|
||||||
'params': {
|
|
||||||
'skip_download': 'Live stream',
|
|
||||||
},
|
|
||||||
}, {
|
|
||||||
'url': 'http://sportdeutschland.tv/li-ning-badminton-wm-2014/lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
|
|
||||||
'info_dict': {
|
|
||||||
'id': 'lee-li-ning-badminton-weltmeisterschaft-2014-kopenhagen-herren-einzel-wei-vs',
|
|
||||||
'ext': 'mp4',
|
|
||||||
'upload_date': '20140825',
|
|
||||||
'description': 'md5:60a20536b57cee7d9a4ec005e8687504',
|
|
||||||
'timestamp': 1408976060,
|
|
||||||
'duration': 2732,
|
|
||||||
'title': 'Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen: Herren Einzel, Wei Lee vs. Keun Lee',
|
|
||||||
'thumbnail': r're:^https?://.*\.jpg$',
|
|
||||||
'view_count': int,
|
|
||||||
'categories': ['Li-Ning Badminton WM 2014'],
|
|
||||||
|
|
||||||
}
|
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
@ -50,7 +32,7 @@ class SportDeutschlandIE(InfoExtractor):
|
|||||||
video_id = mobj.group('id')
|
video_id = mobj.group('id')
|
||||||
sport_id = mobj.group('sport')
|
sport_id = mobj.group('sport')
|
||||||
|
|
||||||
api_url = 'http://proxy.vidibusdynamic.net/sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
|
api_url = 'https://proxy.vidibusdynamic.net/ssl/backend.sportdeutschland.tv/api/permalinks/%s/%s?access_token=true' % (
|
||||||
sport_id, video_id)
|
sport_id, video_id)
|
||||||
req = sanitized_Request(api_url, headers={
|
req = sanitized_Request(api_url, headers={
|
||||||
'Accept': 'application/vnd.vidibus.v2.html+json',
|
'Accept': 'application/vnd.vidibus.v2.html+json',
|
||||||
|
|||||||
@ -1,14 +1,14 @@
|
|||||||
# coding: utf-8
|
# coding: utf-8
|
||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from .ard import ARDMediathekIE
|
from .ard import ARDMediathekBaseIE
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
get_element_by_attribute,
|
get_element_by_attribute,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class SRMediathekIE(ARDMediathekIE):
|
class SRMediathekIE(ARDMediathekBaseIE):
|
||||||
IE_NAME = 'sr:mediathek'
|
IE_NAME = 'sr:mediathek'
|
||||||
IE_DESC = 'Saarländischer Rundfunk'
|
IE_DESC = 'Saarländischer Rundfunk'
|
||||||
_VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
|
_VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
|
||||||
|
|||||||
@ -5,44 +5,28 @@ from ..utils import int_or_none
|
|||||||
|
|
||||||
|
|
||||||
class StretchInternetIE(InfoExtractor):
|
class StretchInternetIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/portal\.htm\?.*?\beventId=(?P<id>\d+)'
|
_VALID_URL = r'https?://portal\.stretchinternet\.com/[^/]+/(?:portal|full)\.htm\?.*?\beventId=(?P<id>\d+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=313900&streamType=video',
|
'url': 'https://portal.stretchinternet.com/umary/portal.htm?eventId=573272&streamType=video',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '313900',
|
'id': '573272',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Augustana (S.D.) Baseball vs University of Mary',
|
'title': 'University of Mary Wrestling vs. Upper Iowa',
|
||||||
'description': 'md5:7578478614aae3bdd4a90f578f787438',
|
'timestamp': 1575668361,
|
||||||
'timestamp': 1490468400,
|
'upload_date': '20191206',
|
||||||
'upload_date': '20170325',
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
stream = self._download_json(
|
|
||||||
'https://neo-client.stretchinternet.com/streamservice/v1/media/stream/v%s'
|
|
||||||
% video_id, video_id)
|
|
||||||
|
|
||||||
video_url = 'https://%s' % stream['source']
|
|
||||||
|
|
||||||
event = self._download_json(
|
event = self._download_json(
|
||||||
'https://neo-client.stretchinternet.com/portal-ws/getEvent.json',
|
'https://api.stretchinternet.com/trinity/event/tcg/' + video_id,
|
||||||
video_id, query={
|
video_id)[0]
|
||||||
'clientID': 99997,
|
|
||||||
'eventID': video_id,
|
|
||||||
'token': 'asdf',
|
|
||||||
})['event']
|
|
||||||
|
|
||||||
title = event.get('title') or event['mobileTitle']
|
|
||||||
description = event.get('customText')
|
|
||||||
timestamp = int_or_none(event.get('longtime'))
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'title': title,
|
'title': event['title'],
|
||||||
'description': description,
|
'timestamp': int_or_none(event.get('dateCreated'), 1000),
|
||||||
'timestamp': timestamp,
|
'url': 'https://' + event['media'][0]['url'],
|
||||||
'url': video_url,
|
|
||||||
}
|
}
|
||||||
|
|||||||
@ -4,19 +4,14 @@ from __future__ import unicode_literals
|
|||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import (
|
from ..compat import compat_str
|
||||||
compat_parse_qs,
|
|
||||||
compat_urllib_parse_urlparse,
|
|
||||||
)
|
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
determine_ext,
|
determine_ext,
|
||||||
dict_get,
|
dict_get,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
orderedSet,
|
str_or_none,
|
||||||
strip_or_none,
|
strip_or_none,
|
||||||
try_get,
|
try_get,
|
||||||
urljoin,
|
|
||||||
compat_str,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -237,23 +232,23 @@ class SVTPlayIE(SVTPlayBaseIE):
|
|||||||
|
|
||||||
|
|
||||||
class SVTSeriesIE(SVTPlayBaseIE):
|
class SVTSeriesIE(SVTPlayBaseIE):
|
||||||
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)'
|
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.svtplay.se/rederiet',
|
'url': 'https://www.svtplay.se/rederiet',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'rederiet',
|
'id': '14445680',
|
||||||
'title': 'Rederiet',
|
'title': 'Rederiet',
|
||||||
'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
|
'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 318,
|
'playlist_mincount': 318,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.svtplay.se/rederiet?tab=sasong2',
|
'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'rederiet-sasong2',
|
'id': 'season-2-14445680',
|
||||||
'title': 'Rederiet - Säsong 2',
|
'title': 'Rederiet - Säsong 2',
|
||||||
'description': 'md5:505d491a58f4fcf6eb418ecab947e69e',
|
'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
|
||||||
},
|
},
|
||||||
'playlist_count': 12,
|
'playlist_mincount': 12,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
@ -261,83 +256,87 @@ class SVTSeriesIE(SVTPlayBaseIE):
|
|||||||
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
|
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTSeriesIE, cls).suitable(url)
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
series_id = self._match_id(url)
|
series_slug, season_id = re.match(self._VALID_URL, url).groups()
|
||||||
|
|
||||||
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
|
series = self._download_json(
|
||||||
season_slug = qs.get('tab', [None])[0]
|
'https://api.svt.se/contento/graphql', series_slug,
|
||||||
|
'Downloading series page', query={
|
||||||
if season_slug:
|
'query': '''{
|
||||||
series_id += '-%s' % season_slug
|
listablesBySlug(slugs: ["%s"]) {
|
||||||
|
associatedContent(include: [productionPeriod, season]) {
|
||||||
webpage = self._download_webpage(
|
items {
|
||||||
url, series_id, 'Downloading series page')
|
item {
|
||||||
|
... on Episode {
|
||||||
root = self._parse_json(
|
videoSvtId
|
||||||
self._search_regex(
|
}
|
||||||
self._SVTPLAY_RE, webpage, 'content', group='json'),
|
}
|
||||||
series_id)
|
}
|
||||||
|
id
|
||||||
|
name
|
||||||
|
}
|
||||||
|
id
|
||||||
|
longDescription
|
||||||
|
name
|
||||||
|
shortDescription
|
||||||
|
}
|
||||||
|
}''' % series_slug,
|
||||||
|
})['data']['listablesBySlug'][0]
|
||||||
|
|
||||||
season_name = None
|
season_name = None
|
||||||
|
|
||||||
entries = []
|
entries = []
|
||||||
for season in root['relatedVideoContent']['relatedVideosAccordion']:
|
for season in series['associatedContent']:
|
||||||
if not isinstance(season, dict):
|
if not isinstance(season, dict):
|
||||||
continue
|
continue
|
||||||
if season_slug:
|
if season_id:
|
||||||
if season.get('slug') != season_slug:
|
if season.get('id') != season_id:
|
||||||
continue
|
continue
|
||||||
season_name = season.get('name')
|
season_name = season.get('name')
|
||||||
videos = season.get('videos')
|
items = season.get('items')
|
||||||
if not isinstance(videos, list):
|
if not isinstance(items, list):
|
||||||
continue
|
continue
|
||||||
for video in videos:
|
for item in items:
|
||||||
content_url = video.get('contentUrl')
|
video = item.get('item') or {}
|
||||||
if not content_url or not isinstance(content_url, compat_str):
|
content_id = video.get('videoSvtId')
|
||||||
|
if not content_id or not isinstance(content_id, compat_str):
|
||||||
continue
|
continue
|
||||||
entries.append(
|
entries.append(self.url_result(
|
||||||
self.url_result(
|
'svt:' + content_id, SVTPlayIE.ie_key(), content_id))
|
||||||
urljoin(url, content_url),
|
|
||||||
ie=SVTPlayIE.ie_key(),
|
|
||||||
video_title=video.get('title')
|
|
||||||
))
|
|
||||||
|
|
||||||
metadata = root.get('metaData')
|
title = series.get('name')
|
||||||
if not isinstance(metadata, dict):
|
season_name = season_name or season_id
|
||||||
metadata = {}
|
|
||||||
|
|
||||||
title = metadata.get('title')
|
|
||||||
season_name = season_name or season_slug
|
|
||||||
|
|
||||||
if title and season_name:
|
if title and season_name:
|
||||||
title = '%s - %s' % (title, season_name)
|
title = '%s - %s' % (title, season_name)
|
||||||
elif season_slug:
|
elif season_id:
|
||||||
title = season_slug
|
title = season_id
|
||||||
|
|
||||||
return self.playlist_result(
|
return self.playlist_result(
|
||||||
entries, series_id, title, metadata.get('description'))
|
entries, season_id or series.get('id'), title,
|
||||||
|
dict_get(series, ('longDescription', 'shortDescription')))
|
||||||
|
|
||||||
|
|
||||||
class SVTPageIE(InfoExtractor):
|
class SVTPageIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/]+/)*(?P<id>[^/?&#]+)'
|
_VALID_URL = r'https?://(?:www\.)?svt\.se/(?P<path>(?:[^/]+/)*(?P<id>[^/?&#]+))'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.svt.se/sport/oseedat/guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
|
'url': 'https://www.svt.se/sport/ishockey/bakom-masken-lehners-kamp-mot-mental-ohalsa',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'guide-sommartraningen-du-kan-gora-var-och-nar-du-vill',
|
'id': '25298267',
|
||||||
'title': 'GUIDE: Sommarträning du kan göra var och när du vill',
|
'title': 'Bakom masken – Lehners kamp mot mental ohälsa',
|
||||||
},
|
},
|
||||||
'playlist_count': 7,
|
'playlist_count': 4,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.svt.se/nyheter/inrikes/ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
|
'url': 'https://www.svt.se/nyheter/utrikes/svenska-andrea-ar-en-mil-fran-branderna-i-kalifornien',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'ebba-busch-thor-kd-har-delvis-ratt-om-no-go-zoner',
|
'id': '24243746',
|
||||||
'title': 'Ebba Busch Thor har bara delvis rätt om ”no-go-zoner”',
|
'title': 'Svenska Andrea redo att fly sitt hem i Kalifornien',
|
||||||
},
|
},
|
||||||
'playlist_count': 1,
|
'playlist_count': 2,
|
||||||
}, {
|
}, {
|
||||||
# only programTitle
|
# only programTitle
|
||||||
'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
|
'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2900353',
|
'id': '8439V2K',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Stjärnorna skojar till det - under SVT-intervjun',
|
'title': 'Stjärnorna skojar till det - under SVT-intervjun',
|
||||||
'duration': 27,
|
'duration': 27,
|
||||||
@ -356,16 +355,26 @@ class SVTPageIE(InfoExtractor):
|
|||||||
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
|
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
playlist_id = self._match_id(url)
|
path, display_id = re.match(self._VALID_URL, url).groups()
|
||||||
|
|
||||||
webpage = self._download_webpage(url, playlist_id)
|
article = self._download_json(
|
||||||
|
'https://api.svt.se/nss-api/page/' + path, display_id,
|
||||||
|
query={'q': 'articles'})['articles']['content'][0]
|
||||||
|
|
||||||
entries = [
|
entries = []
|
||||||
self.url_result(
|
|
||||||
'svt:%s' % video_id, ie=SVTPlayIE.ie_key(), video_id=video_id)
|
|
||||||
for video_id in orderedSet(re.findall(
|
|
||||||
r'data-video-id=["\'](\d+)', webpage))]
|
|
||||||
|
|
||||||
title = strip_or_none(self._og_search_title(webpage, default=None))
|
def _process_content(content):
|
||||||
|
if content.get('_type') in ('VIDEOCLIP', 'VIDEOEPISODE'):
|
||||||
|
video_id = compat_str(content['image']['svtId'])
|
||||||
|
entries.append(self.url_result(
|
||||||
|
'svt:' + video_id, SVTPlayIE.ie_key(), video_id))
|
||||||
|
|
||||||
return self.playlist_result(entries, playlist_id, title)
|
for media in article.get('media', []):
|
||||||
|
_process_content(media)
|
||||||
|
|
||||||
|
for obj in article.get('structuredBody', []):
|
||||||
|
_process_content(obj.get('content') or {})
|
||||||
|
|
||||||
|
return self.playlist_result(
|
||||||
|
entries, str_or_none(article.get('id')),
|
||||||
|
strip_or_none(article.get('title')))
|
||||||
|
|||||||
@ -160,8 +160,8 @@ class TeachableIE(TeachableBaseIE):
|
|||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
wistia_url = WistiaIE._extract_url(webpage)
|
wistia_urls = WistiaIE._extract_urls(webpage)
|
||||||
if not wistia_url:
|
if not wistia_urls:
|
||||||
if any(re.search(p, webpage) for p in (
|
if any(re.search(p, webpage) for p in (
|
||||||
r'class=["\']lecture-contents-locked',
|
r'class=["\']lecture-contents-locked',
|
||||||
r'>\s*Lecture contents locked',
|
r'>\s*Lecture contents locked',
|
||||||
@ -174,12 +174,14 @@ class TeachableIE(TeachableBaseIE):
|
|||||||
|
|
||||||
title = self._og_search_title(webpage, default=None)
|
title = self._og_search_title(webpage, default=None)
|
||||||
|
|
||||||
return {
|
entries = [{
|
||||||
'_type': 'url_transparent',
|
'_type': 'url_transparent',
|
||||||
'url': wistia_url,
|
'url': wistia_url,
|
||||||
'ie_key': WistiaIE.ie_key(),
|
'ie_key': WistiaIE.ie_key(),
|
||||||
'title': title,
|
'title': title,
|
||||||
}
|
} for wistia_url in wistia_urls]
|
||||||
|
|
||||||
|
return self.playlist_result(entries, video_id, title)
|
||||||
|
|
||||||
|
|
||||||
class TeachableCourseIE(TeachableBaseIE):
|
class TeachableCourseIE(TeachableBaseIE):
|
||||||
|
|||||||
@ -2,43 +2,42 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import compat_str
|
|
||||||
from ..utils import try_get
|
|
||||||
|
|
||||||
|
|
||||||
class ThisOldHouseIE(InfoExtractor):
|
class ThisOldHouseIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode)/(?P<id>[^/?#]+)'
|
_VALID_URL = r'https?://(?:www\.)?thisoldhouse\.com/(?:watch|how-to|tv-episode|(?:[^/]+/)?\d+)/(?P<id>[^/?#]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
|
'url': 'https://www.thisoldhouse.com/how-to/how-to-build-storage-bench',
|
||||||
'md5': '568acf9ca25a639f0c4ff905826b662f',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '2REGtUDQ',
|
'id': '5dcdddf673c3f956ef5db202',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'How to Build a Storage Bench',
|
'title': 'How to Build a Storage Bench',
|
||||||
'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',
|
'description': 'In the workshop, Tom Silva and Kevin O\'Connor build a storage bench for an entryway.',
|
||||||
'timestamp': 1442548800,
|
'timestamp': 1442548800,
|
||||||
'upload_date': '20150918',
|
'upload_date': '20150918',
|
||||||
}
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
|
'url': 'https://www.thisoldhouse.com/watch/arlington-arts-crafts-arts-and-crafts-class-begins',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
|
'url': 'https://www.thisoldhouse.com/tv-episode/ask-toh-shelf-rough-electric',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.thisoldhouse.com/furniture/21017078/how-to-build-a-storage-bench',
|
||||||
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.thisoldhouse.com/21113884/s41-e13-paradise-lost',
|
||||||
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
_ZYPE_TMPL = 'https://player.zype.com/embed/%s.html?api_key=hsOk_yMSPYNrT22e9pu8hihLXjaZf0JW5jsOWv4ZqyHJFvkJn6rtToHl09tbbsbe'
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
display_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, display_id)
|
webpage = self._download_webpage(url, display_id)
|
||||||
video_id = self._search_regex(
|
video_id = self._search_regex(
|
||||||
(r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1',
|
r'<iframe[^>]+src=[\'"](?:https?:)?//thisoldhouse\.chorus\.build/videos/zype/([0-9a-f]{24})',
|
||||||
r'id=(["\'])inline-video-player-(?P<id>(?:(?!\1).)+)\1'),
|
webpage, 'video id')
|
||||||
webpage, 'video id', default=None, group='id')
|
return self.url_result(self._ZYPE_TMPL % video_id, 'Zype', video_id)
|
||||||
if not video_id:
|
|
||||||
drupal_settings = self._parse_json(self._search_regex(
|
|
||||||
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
|
|
||||||
webpage, 'drupal settings'), display_id)
|
|
||||||
video_id = try_get(
|
|
||||||
drupal_settings, lambda x: x['jwplatform']['video_id'],
|
|
||||||
compat_str) or list(drupal_settings['comScore'])[0]
|
|
||||||
return self.url_result('jwplatform:' + video_id, 'JWPlatform', video_id)
|
|
||||||
|
|||||||
@ -17,9 +17,9 @@ from ..utils import (
|
|||||||
|
|
||||||
class ToggleIE(InfoExtractor):
|
class ToggleIE(InfoExtractor):
|
||||||
IE_NAME = 'toggle'
|
IE_NAME = 'toggle'
|
||||||
_VALID_URL = r'https?://video\.toggle\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
|
_VALID_URL = r'https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}(?P<id>[0-9]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://video.toggle.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
|
'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '343115',
|
'id': '343115',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
@ -33,7 +33,7 @@ class ToggleIE(InfoExtractor):
|
|||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
'note': 'DRM-protected video',
|
'note': 'DRM-protected video',
|
||||||
'url': 'http://video.toggle.sg/en/movies/dug-s-special-mission/341413',
|
'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '341413',
|
'id': '341413',
|
||||||
'ext': 'wvm',
|
'ext': 'wvm',
|
||||||
@ -48,7 +48,7 @@ class ToggleIE(InfoExtractor):
|
|||||||
}, {
|
}, {
|
||||||
# this also tests correct video id extraction
|
# this also tests correct video id extraction
|
||||||
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
|
'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
|
||||||
'url': 'http://video.toggle.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
|
'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '332861',
|
'id': '332861',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
@ -65,19 +65,22 @@ class ToggleIE(InfoExtractor):
|
|||||||
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
|
'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://video.toggle.sg/zh/series/zero-calling-s2-hd/ep13/336367',
|
'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://video.toggle.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
|
'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://video.toggle.sg/en/movies/seven-days/321936',
|
'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'https://video.toggle.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
|
'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://video.toggle.sg/en/channels/eleven-plus/401585',
|
'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
|
||||||
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
|||||||
@ -1,21 +1,12 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
|
||||||
dict_get,
|
|
||||||
float_or_none,
|
|
||||||
int_or_none,
|
|
||||||
unified_timestamp,
|
|
||||||
update_url_query,
|
|
||||||
url_or_none,
|
|
||||||
)
|
|
||||||
|
|
||||||
|
|
||||||
class TruNewsIE(InfoExtractor):
|
class TruNewsIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)'
|
_VALID_URL = r'https?://(?:www\.)?trunews\.com/stream/(?P<id>[^/?#&]+)'
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
|
'url': 'https://www.trunews.com/stream/will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
|
||||||
'md5': 'a19c024c3906ff954fac9b96ce66bb08',
|
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '5c5a21e65d3c196e1c0020cc',
|
'id': '5c5a21e65d3c196e1c0020cc',
|
||||||
'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
|
'display_id': 'will-democrats-stage-a-circus-during-president-trump-s-state-of-the-union-speech',
|
||||||
@ -28,48 +19,16 @@ class TruNewsIE(InfoExtractor):
|
|||||||
},
|
},
|
||||||
'add_ie': ['Zype'],
|
'add_ie': ['Zype'],
|
||||||
}
|
}
|
||||||
|
_ZYPE_TEMPL = 'https://player.zype.com/embed/%s.js?api_key=X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
display_id = self._match_id(url)
|
||||||
|
|
||||||
video = self._download_json(
|
zype_id = self._download_json(
|
||||||
'https://api.zype.com/videos', display_id, query={
|
'https://api.zype.com/videos', display_id, query={
|
||||||
'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H',
|
'app_key': 'PUVKp9WgGUb3-JUw6EqafLx8tFVP6VKZTWbUOR-HOm__g4fNDt1bCsm_LgYf_k9H',
|
||||||
'per_page': 1,
|
'per_page': 1,
|
||||||
'active': 'true',
|
'active': 'true',
|
||||||
'friendly_title': display_id,
|
'friendly_title': display_id,
|
||||||
})['response'][0]
|
})['response'][0]['_id']
|
||||||
|
return self.url_result(self._ZYPE_TEMPL % zype_id, 'Zype', zype_id)
|
||||||
zype_id = video['_id']
|
|
||||||
|
|
||||||
thumbnails = []
|
|
||||||
thumbnails_list = video.get('thumbnails')
|
|
||||||
if isinstance(thumbnails_list, list):
|
|
||||||
for thumbnail in thumbnails_list:
|
|
||||||
if not isinstance(thumbnail, dict):
|
|
||||||
continue
|
|
||||||
thumbnail_url = url_or_none(thumbnail.get('url'))
|
|
||||||
if not thumbnail_url:
|
|
||||||
continue
|
|
||||||
thumbnails.append({
|
|
||||||
'url': thumbnail_url,
|
|
||||||
'width': int_or_none(thumbnail.get('width')),
|
|
||||||
'height': int_or_none(thumbnail.get('height')),
|
|
||||||
})
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'url': update_url_query(
|
|
||||||
'https://player.zype.com/embed/%s.js' % zype_id,
|
|
||||||
{'api_key': 'X5XnahkjCwJrT_l5zUqypnaLEObotyvtUKJWWlONxDoHVjP8vqxlArLV8llxMbyt'}),
|
|
||||||
'ie_key': 'Zype',
|
|
||||||
'id': zype_id,
|
|
||||||
'display_id': display_id,
|
|
||||||
'title': video.get('title'),
|
|
||||||
'description': dict_get(video, ('description', 'ott_description', 'short_description')),
|
|
||||||
'duration': int_or_none(video.get('duration')),
|
|
||||||
'timestamp': unified_timestamp(video.get('published_at')),
|
|
||||||
'average_rating': float_or_none(video.get('rating')),
|
|
||||||
'view_count': int_or_none(video.get('request_count')),
|
|
||||||
'thumbnails': thumbnails,
|
|
||||||
}
|
|
||||||
|
|||||||
@ -106,7 +106,7 @@ class TV2DKBornholmPlayIE(InfoExtractor):
|
|||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
video = self._download_json(
|
video = self._download_json(
|
||||||
'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
|
'https://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
|
||||||
data=json.dumps({
|
data=json.dumps({
|
||||||
'playlist_id': video_id,
|
'playlist_id': video_id,
|
||||||
'serienavn': '',
|
'serienavn': '',
|
||||||
|
|||||||
@ -3,31 +3,51 @@ from __future__ import unicode_literals
|
|||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
clean_html,
|
|
||||||
determine_ext,
|
determine_ext,
|
||||||
extract_attributes,
|
extract_attributes,
|
||||||
get_element_by_class,
|
|
||||||
int_or_none,
|
int_or_none,
|
||||||
parse_duration,
|
parse_duration,
|
||||||
parse_iso8601,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class TV5MondePlusIE(InfoExtractor):
|
class TV5MondePlusIE(InfoExtractor):
|
||||||
IE_DESC = 'TV5MONDE+'
|
IE_DESC = 'TV5MONDE+'
|
||||||
_VALID_URL = r'https?://(?:www\.)?tv5mondeplus\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
|
_VALID_URL = r'https?://(?:www\.)?(?:tv5mondeplus|revoir\.tv5monde)\.com/toutes-les-videos/[^/]+/(?P<id>[^/?#]+)'
|
||||||
_TEST = {
|
_TESTS = [{
|
||||||
'url': 'http://www.tv5mondeplus.com/toutes-les-videos/documentaire/tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
|
# movie
|
||||||
'md5': '12130fc199f020673138a83466542ec6',
|
'url': 'https://revoir.tv5monde.com/toutes-les-videos/cinema/rendez-vous-a-atlit',
|
||||||
|
'md5': '8cbde5ea7b296cf635073e27895e227f',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'tdah-mon-amour-tele-quebec-tdah-mon-amour-ep001-enfants',
|
'id': '822a4756-0712-7329-1859-a13ac7fd1407',
|
||||||
|
'display_id': 'rendez-vous-a-atlit',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Tdah, mon amour - Enfants',
|
'title': 'Rendez-vous à Atlit',
|
||||||
'description': 'md5:230e3aca23115afcf8006d1bece6df74',
|
'description': 'md5:2893a4c5e1dbac3eedff2d87956e4efb',
|
||||||
'upload_date': '20170401',
|
'upload_date': '20200130',
|
||||||
'timestamp': 1491022860,
|
},
|
||||||
}
|
}, {
|
||||||
}
|
# series episode
|
||||||
|
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/c-est-la-vie-ennemie-juree',
|
||||||
|
'info_dict': {
|
||||||
|
'id': '0df7007c-4900-3936-c601-87a13a93a068',
|
||||||
|
'display_id': 'c-est-la-vie-ennemie-juree',
|
||||||
|
'ext': 'mp4',
|
||||||
|
'title': "C'est la vie - Ennemie jurée",
|
||||||
|
'description': 'md5:dfb5c63087b6f35fe0cc0af4fe44287e',
|
||||||
|
'upload_date': '20200130',
|
||||||
|
'series': "C'est la vie",
|
||||||
|
'episode': 'Ennemie jurée',
|
||||||
|
},
|
||||||
|
'params': {
|
||||||
|
'skip_download': True,
|
||||||
|
},
|
||||||
|
}, {
|
||||||
|
'url': 'https://revoir.tv5monde.com/toutes-les-videos/series-fictions/neuf-jours-en-hiver-neuf-jours-en-hiver',
|
||||||
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://revoir.tv5monde.com/toutes-les-videos/info-societe/le-journal-de-la-rts-edition-du-30-01-20-19h30',
|
||||||
|
'only_matching': True,
|
||||||
|
}]
|
||||||
_GEO_BYPASS = False
|
_GEO_BYPASS = False
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
@ -37,11 +57,7 @@ class TV5MondePlusIE(InfoExtractor):
|
|||||||
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
|
if ">Ce programme n'est malheureusement pas disponible pour votre zone géographique.<" in webpage:
|
||||||
self.raise_geo_restricted(countries=['FR'])
|
self.raise_geo_restricted(countries=['FR'])
|
||||||
|
|
||||||
series = get_element_by_class('video-detail__title', webpage)
|
title = episode = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
|
||||||
title = episode = get_element_by_class(
|
|
||||||
'video-detail__subtitle', webpage) or series
|
|
||||||
if series and series != title:
|
|
||||||
title = '%s - %s' % (series, title)
|
|
||||||
vpl_data = extract_attributes(self._search_regex(
|
vpl_data = extract_attributes(self._search_regex(
|
||||||
r'(<[^>]+class="video_player_loader"[^>]+>)',
|
r'(<[^>]+class="video_player_loader"[^>]+>)',
|
||||||
webpage, 'video player loader'))
|
webpage, 'video player loader'))
|
||||||
@ -65,15 +81,37 @@ class TV5MondePlusIE(InfoExtractor):
|
|||||||
})
|
})
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
|
description = self._html_search_regex(
|
||||||
|
r'(?s)<div[^>]+class=["\']episode-texte[^>]+>(.+?)</div>', webpage,
|
||||||
|
'description', fatal=False)
|
||||||
|
|
||||||
|
series = self._html_search_regex(
|
||||||
|
r'<p[^>]+class=["\']episode-emission[^>]+>([^<]+)', webpage,
|
||||||
|
'series', default=None)
|
||||||
|
|
||||||
|
if series and series != title:
|
||||||
|
title = '%s - %s' % (series, title)
|
||||||
|
|
||||||
|
upload_date = self._search_regex(
|
||||||
|
r'(?:date_publication|publish_date)["\']\s*:\s*["\'](\d{4}_\d{2}_\d{2})',
|
||||||
|
webpage, 'upload date', default=None)
|
||||||
|
if upload_date:
|
||||||
|
upload_date = upload_date.replace('_', '')
|
||||||
|
|
||||||
|
video_id = self._search_regex(
|
||||||
|
(r'data-guid=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})',
|
||||||
|
r'id_contenu["\']\s:\s*(\d+)'), webpage, 'video id',
|
||||||
|
default=display_id)
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': display_id,
|
'id': video_id,
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': clean_html(get_element_by_class('video-detail__description', webpage)),
|
'description': description,
|
||||||
'thumbnail': vpl_data.get('data-image'),
|
'thumbnail': vpl_data.get('data-image'),
|
||||||
'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
|
'duration': int_or_none(vpl_data.get('data-duration')) or parse_duration(self._html_search_meta('duration', webpage)),
|
||||||
'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage)),
|
'upload_date': upload_date,
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
'episode': episode,
|
|
||||||
'series': series,
|
'series': series,
|
||||||
|
'episode': episode,
|
||||||
}
|
}
|
||||||
|
|||||||
@ -9,8 +9,8 @@ from ..utils import (
|
|||||||
|
|
||||||
|
|
||||||
class TVAIE(InfoExtractor):
|
class TVAIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://videos\.tva\.ca/details/_(?P<id>\d+)'
|
_VALID_URL = r'https?://videos?\.tva\.ca/details/_(?P<id>\d+)'
|
||||||
_TEST = {
|
_TESTS = [{
|
||||||
'url': 'https://videos.tva.ca/details/_5596811470001',
|
'url': 'https://videos.tva.ca/details/_5596811470001',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '5596811470001',
|
'id': '5596811470001',
|
||||||
@ -24,7 +24,10 @@ class TVAIE(InfoExtractor):
|
|||||||
# m3u8 download
|
# m3u8 download
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
}
|
}
|
||||||
}
|
}, {
|
||||||
|
'url': 'https://video.tva.ca/details/_5596811470001',
|
||||||
|
'only_matching': True,
|
||||||
|
}]
|
||||||
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
|
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/5481942443001/default_default/index.html?videoId=%s'
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
|
|||||||
@ -17,8 +17,8 @@ class TwentyFourVideoIE(InfoExtractor):
|
|||||||
_VALID_URL = r'''(?x)
|
_VALID_URL = r'''(?x)
|
||||||
https?://
|
https?://
|
||||||
(?P<host>
|
(?P<host>
|
||||||
(?:(?:www|porno)\.)?24video\.
|
(?:(?:www|porno?)\.)?24video\.
|
||||||
(?:net|me|xxx|sexy?|tube|adult|site)
|
(?:net|me|xxx|sexy?|tube|adult|site|vip)
|
||||||
)/
|
)/
|
||||||
(?:
|
(?:
|
||||||
video/(?:(?:view|xml)/)?|
|
video/(?:(?:view|xml)/)?|
|
||||||
@ -59,6 +59,12 @@ class TwentyFourVideoIE(InfoExtractor):
|
|||||||
}, {
|
}, {
|
||||||
'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
|
'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.24video.vip/video/view/1044982',
|
||||||
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://porn.24video.net/video/2640421-vsya-takay',
|
||||||
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
|
|||||||
@ -575,8 +575,8 @@ class TwitchStreamIE(TwitchBaseIE):
|
|||||||
channel_id = self._match_id(url)
|
channel_id = self._match_id(url)
|
||||||
|
|
||||||
stream = self._call_api(
|
stream = self._call_api(
|
||||||
'kraken/streams/%s?stream_type=all' % channel_id, channel_id,
|
'kraken/streams/%s?stream_type=all' % channel_id.lower(),
|
||||||
'Downloading stream JSON').get('stream')
|
channel_id, 'Downloading stream JSON').get('stream')
|
||||||
|
|
||||||
if not stream:
|
if not stream:
|
||||||
raise ExtractorError('%s is offline' % channel_id, expected=True)
|
raise ExtractorError('%s is offline' % channel_id, expected=True)
|
||||||
|
|||||||
@ -1,28 +1,62 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import base64
|
import json
|
||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import compat_urllib_parse_unquote
|
from ..compat import compat_HTTPError
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
clean_html,
|
|
||||||
determine_ext,
|
|
||||||
int_or_none,
|
int_or_none,
|
||||||
js_to_json,
|
|
||||||
parse_age_limit,
|
parse_age_limit,
|
||||||
parse_duration,
|
|
||||||
try_get,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
class ViewLiftBaseIE(InfoExtractor):
|
class ViewLiftBaseIE(InfoExtractor):
|
||||||
_DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm)\.com|hoichoi\.tv'
|
_API_BASE = 'https://prod-api.viewlift.com/'
|
||||||
|
_DOMAINS_REGEX = r'(?:(?:main\.)?snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|(?:monumental|lax)sportsnetwork|vayafilm|failarmy|ftfnext|lnppass\.legapallacanestro|moviespree|app\.myoutdoortv|neoufitness|pflmma|theidentitytb)\.com|(?:hoichoi|app\.horseandcountry|kronon|marquee|supercrosslive)\.tv'
|
||||||
|
_SITE_MAP = {
|
||||||
|
'ftfnext': 'lax',
|
||||||
|
'funnyforfree': 'snagfilms',
|
||||||
|
'hoichoi': 'hoichoitv',
|
||||||
|
'kiddovid': 'snagfilms',
|
||||||
|
'laxsportsnetwork': 'lax',
|
||||||
|
'legapallacanestro': 'lnp',
|
||||||
|
'marquee': 'marquee-tv',
|
||||||
|
'monumentalsportsnetwork': 'monumental-network',
|
||||||
|
'moviespree': 'bingeflix',
|
||||||
|
'pflmma': 'pfl',
|
||||||
|
'snagxtreme': 'snagfilms',
|
||||||
|
'theidentitytb': 'tampabay',
|
||||||
|
'vayafilm': 'snagfilms',
|
||||||
|
}
|
||||||
|
_TOKENS = {}
|
||||||
|
|
||||||
|
def _call_api(self, site, path, video_id, query):
|
||||||
|
token = self._TOKENS.get(site)
|
||||||
|
if not token:
|
||||||
|
token_query = {'site': site}
|
||||||
|
email, password = self._get_login_info(netrc_machine=site)
|
||||||
|
if email:
|
||||||
|
resp = self._download_json(
|
||||||
|
self._API_BASE + 'identity/signin', video_id,
|
||||||
|
'Logging in', query=token_query, data=json.dumps({
|
||||||
|
'email': email,
|
||||||
|
'password': password,
|
||||||
|
}).encode())
|
||||||
|
else:
|
||||||
|
resp = self._download_json(
|
||||||
|
self._API_BASE + 'identity/anonymous-token', video_id,
|
||||||
|
'Downloading authorization token', query=token_query)
|
||||||
|
self._TOKENS[site] = token = resp['authorizationToken']
|
||||||
|
return self._download_json(
|
||||||
|
self._API_BASE + path, video_id,
|
||||||
|
headers={'Authorization': token}, query=query)
|
||||||
|
|
||||||
|
|
||||||
class ViewLiftEmbedIE(ViewLiftBaseIE):
|
class ViewLiftEmbedIE(ViewLiftBaseIE):
|
||||||
_VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
|
IE_NAME = 'viewlift:embed'
|
||||||
|
_VALID_URL = r'https?://(?:(?:www|embed)\.)?(?P<domain>%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})' % ViewLiftBaseIE._DOMAINS_REGEX
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
|
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
|
||||||
'md5': '2924e9215c6eff7a55ed35b72276bd93',
|
'md5': '2924e9215c6eff7a55ed35b72276bd93',
|
||||||
@ -30,6 +64,9 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
|
|||||||
'id': '74849a00-85a9-11e1-9660-123139220831',
|
'id': '74849a00-85a9-11e1-9660-123139220831',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': '#whilewewatch',
|
'title': '#whilewewatch',
|
||||||
|
'description': 'md5:b542bef32a6f657dadd0df06e26fb0c8',
|
||||||
|
'timestamp': 1334350096,
|
||||||
|
'upload_date': '20120413',
|
||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
# invalid labels, 360p is better that 480p
|
# invalid labels, 360p is better that 480p
|
||||||
@ -39,7 +76,8 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
|
|||||||
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
|
'id': '17ca0950-a74a-11e0-a92a-0026bb61d036',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Life in Limbo',
|
'title': 'Life in Limbo',
|
||||||
}
|
},
|
||||||
|
'skip': 'The video does not exist',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
|
'url': 'http://www.snagfilms.com/embed/player?filmId=0000014c-de2f-d5d6-abcf-ffef58af0017',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
@ -54,67 +92,68 @@ class ViewLiftEmbedIE(ViewLiftBaseIE):
|
|||||||
return mobj.group('url')
|
return mobj.group('url')
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
domain, film_id = re.match(self._VALID_URL, url).groups()
|
||||||
|
site = domain.split('.')[-2]
|
||||||
webpage = self._download_webpage(url, video_id)
|
if site in self._SITE_MAP:
|
||||||
|
site = self._SITE_MAP[site]
|
||||||
if '>This film is not playable in your area.<' in webpage:
|
try:
|
||||||
raise ExtractorError(
|
content_data = self._call_api(
|
||||||
'Film %s is not playable in your area.' % video_id, expected=True)
|
site, 'entitlement/video/status', film_id, {
|
||||||
|
'id': film_id
|
||||||
|
})['video']
|
||||||
|
except ExtractorError as e:
|
||||||
|
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
|
||||||
|
error_message = self._parse_json(e.cause.read().decode(), film_id).get('errorMessage')
|
||||||
|
if error_message == 'User does not have a valid subscription or has not purchased this content.':
|
||||||
|
self.raise_login_required()
|
||||||
|
raise ExtractorError(error_message, expected=True)
|
||||||
|
raise
|
||||||
|
gist = content_data['gist']
|
||||||
|
title = gist['title']
|
||||||
|
video_assets = content_data['streamingInfo']['videoAssets']
|
||||||
|
|
||||||
formats = []
|
formats = []
|
||||||
has_bitrate = False
|
mpeg_video_assets = video_assets.get('mpeg') or []
|
||||||
sources = self._parse_json(self._search_regex(
|
for video_asset in mpeg_video_assets:
|
||||||
r'(?s)sources:\s*(\[.+?\]),', webpage,
|
video_asset_url = video_asset.get('url')
|
||||||
'sources', default='[]'), video_id, js_to_json)
|
if not video_asset:
|
||||||
for source in sources:
|
|
||||||
file_ = source.get('file')
|
|
||||||
if not file_:
|
|
||||||
continue
|
continue
|
||||||
type_ = source.get('type')
|
bitrate = int_or_none(video_asset.get('bitrate'))
|
||||||
ext = determine_ext(file_)
|
height = int_or_none(self._search_regex(
|
||||||
format_id = source.get('label') or ext
|
r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
|
||||||
if all(v in ('m3u8', 'hls') for v in (type_, ext)):
|
'height', default=None))
|
||||||
formats.extend(self._extract_m3u8_formats(
|
formats.append({
|
||||||
file_, video_id, 'mp4', 'm3u8_native',
|
'url': video_asset_url,
|
||||||
m3u8_id='hls', fatal=False))
|
'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
|
||||||
else:
|
'tbr': bitrate,
|
||||||
bitrate = int_or_none(self._search_regex(
|
'height': height,
|
||||||
[r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
|
'vcodec': video_asset.get('codec'),
|
||||||
file_, 'bitrate', default=None))
|
})
|
||||||
if not has_bitrate and bitrate:
|
|
||||||
has_bitrate = True
|
|
||||||
height = int_or_none(self._search_regex(
|
|
||||||
r'^(\d+)[pP]$', format_id, 'height', default=None))
|
|
||||||
formats.append({
|
|
||||||
'url': file_,
|
|
||||||
'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')),
|
|
||||||
'tbr': bitrate,
|
|
||||||
'height': height,
|
|
||||||
})
|
|
||||||
if not formats:
|
|
||||||
hls_url = self._parse_json(self._search_regex(
|
|
||||||
r'filmInfo\.src\s*=\s*({.+?});',
|
|
||||||
webpage, 'src'), video_id, js_to_json)['src']
|
|
||||||
formats = self._extract_m3u8_formats(
|
|
||||||
hls_url, video_id, 'mp4', 'm3u8_native',
|
|
||||||
m3u8_id='hls', fatal=False)
|
|
||||||
field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
|
|
||||||
self._sort_formats(formats, field_preference)
|
|
||||||
|
|
||||||
title = self._search_regex(
|
hls_url = video_assets.get('hls')
|
||||||
[r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
|
if hls_url:
|
||||||
webpage, 'title')
|
formats.extend(self._extract_m3u8_formats(
|
||||||
|
hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
||||||
|
self._sort_formats(formats, ('height', 'tbr', 'format_id'))
|
||||||
|
|
||||||
return {
|
info = {
|
||||||
'id': video_id,
|
'id': film_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
|
'description': gist.get('description'),
|
||||||
|
'thumbnail': gist.get('videoImageUrl'),
|
||||||
|
'duration': int_or_none(gist.get('runtime')),
|
||||||
|
'age_limit': parse_age_limit(content_data.get('parentalRating')),
|
||||||
|
'timestamp': int_or_none(gist.get('publishDate'), 1000),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
for k in ('categories', 'tags'):
|
||||||
|
info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
|
||||||
|
return info
|
||||||
|
|
||||||
|
|
||||||
class ViewLiftIE(ViewLiftBaseIE):
|
class ViewLiftIE(ViewLiftBaseIE):
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?:/(?:films/title|show|(?:news/)?videos?))?/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
|
IE_NAME = 'viewlift'
|
||||||
|
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)(?P<path>(?:/(?:films/title|show|(?:news/)?videos?|watch))?/(?P<id>[^?#]+))' % ViewLiftBaseIE._DOMAINS_REGEX
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
|
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
|
||||||
'md5': '19844f897b35af219773fd63bdec2942',
|
'md5': '19844f897b35af219773fd63bdec2942',
|
||||||
@ -151,10 +190,13 @@ class ViewLiftIE(ViewLiftBaseIE):
|
|||||||
'id': '00000148-7b53-de26-a9fb-fbf306f70020',
|
'id': '00000148-7b53-de26-a9fb-fbf306f70020',
|
||||||
'display_id': 'augie_alone/s_2_ep_12_love',
|
'display_id': 'augie_alone/s_2_ep_12_love',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Augie, Alone:S. 2 Ep. 12 - Love',
|
'title': 'S. 2 Ep. 12 - Love',
|
||||||
'description': 'md5:db2a5c72d994f16a780c1eb353a8f403',
|
'description': 'Augie finds love.',
|
||||||
'thumbnail': r're:^https?://.*\.jpg',
|
'thumbnail': r're:^https?://.*\.jpg',
|
||||||
'duration': 107,
|
'duration': 107,
|
||||||
|
'upload_date': '20141012',
|
||||||
|
'timestamp': 1413129540,
|
||||||
|
'age_limit': 17,
|
||||||
},
|
},
|
||||||
'params': {
|
'params': {
|
||||||
'skip_download': True,
|
'skip_download': True,
|
||||||
@ -177,6 +219,9 @@ class ViewLiftIE(ViewLiftBaseIE):
|
|||||||
# Was once Kaltura embed
|
# Was once Kaltura embed
|
||||||
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
|
'url': 'https://www.monumentalsportsnetwork.com/videos/john-carlson-postgame-2-25-15',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
}, {
|
||||||
|
'url': 'https://www.marquee.tv/watch/sadlerswells-sacredmonsters',
|
||||||
|
'only_matching': True,
|
||||||
}]
|
}]
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
@ -184,119 +229,22 @@ class ViewLiftIE(ViewLiftBaseIE):
|
|||||||
return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
|
return False if ViewLiftEmbedIE.suitable(url) else super(ViewLiftIE, cls).suitable(url)
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
domain, display_id = re.match(self._VALID_URL, url).groups()
|
domain, path, display_id = re.match(self._VALID_URL, url).groups()
|
||||||
|
site = domain.split('.')[-2]
|
||||||
webpage = self._download_webpage(url, display_id)
|
if site in self._SITE_MAP:
|
||||||
|
site = self._SITE_MAP[site]
|
||||||
if ">Sorry, the Film you're looking for is not available.<" in webpage:
|
modules = self._call_api(
|
||||||
raise ExtractorError(
|
site, 'content/pages', display_id, {
|
||||||
'Film %s is not available.' % display_id, expected=True)
|
'includeContent': 'true',
|
||||||
|
'moduleOffset': 1,
|
||||||
initial_store_state = self._search_regex(
|
'path': path,
|
||||||
r"window\.initialStoreState\s*=.*?JSON\.parse\(unescape\(atob\('([^']+)'\)\)\)",
|
'site': site,
|
||||||
webpage, 'Initial Store State', default=None)
|
})['modules']
|
||||||
if initial_store_state:
|
film_id = next(m['contentData'][0]['gist']['id'] for m in modules if m.get('moduleType') == 'VideoDetailModule')
|
||||||
modules = self._parse_json(compat_urllib_parse_unquote(base64.b64decode(
|
return {
|
||||||
initial_store_state).decode()), display_id)['page']['data']['modules']
|
'_type': 'url_transparent',
|
||||||
content_data = next(m['contentData'][0] for m in modules if m.get('moduleType') == 'VideoDetailModule')
|
'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
|
||||||
gist = content_data['gist']
|
'id': film_id,
|
||||||
film_id = gist['id']
|
'display_id': display_id,
|
||||||
title = gist['title']
|
'ie_key': 'ViewLiftEmbed',
|
||||||
video_assets = try_get(
|
}
|
||||||
content_data, lambda x: x['streamingInfo']['videoAssets'], dict)
|
|
||||||
if not video_assets:
|
|
||||||
token = self._download_json(
|
|
||||||
'https://prod-api.viewlift.com/identity/anonymous-token',
|
|
||||||
film_id, 'Downloading authorization token',
|
|
||||||
query={'site': 'snagfilms'})['authorizationToken']
|
|
||||||
video_assets = self._download_json(
|
|
||||||
'https://prod-api.viewlift.com/entitlement/video/status',
|
|
||||||
film_id, headers={
|
|
||||||
'Authorization': token,
|
|
||||||
'Referer': url,
|
|
||||||
}, query={
|
|
||||||
'id': film_id
|
|
||||||
})['video']['streamingInfo']['videoAssets']
|
|
||||||
|
|
||||||
formats = []
|
|
||||||
mpeg_video_assets = video_assets.get('mpeg') or []
|
|
||||||
for video_asset in mpeg_video_assets:
|
|
||||||
video_asset_url = video_asset.get('url')
|
|
||||||
if not video_asset:
|
|
||||||
continue
|
|
||||||
bitrate = int_or_none(video_asset.get('bitrate'))
|
|
||||||
height = int_or_none(self._search_regex(
|
|
||||||
r'^_?(\d+)[pP]$', video_asset.get('renditionValue'),
|
|
||||||
'height', default=None))
|
|
||||||
formats.append({
|
|
||||||
'url': video_asset_url,
|
|
||||||
'format_id': 'http%s' % ('-%d' % bitrate if bitrate else ''),
|
|
||||||
'tbr': bitrate,
|
|
||||||
'height': height,
|
|
||||||
'vcodec': video_asset.get('codec'),
|
|
||||||
})
|
|
||||||
|
|
||||||
hls_url = video_assets.get('hls')
|
|
||||||
if hls_url:
|
|
||||||
formats.extend(self._extract_m3u8_formats(
|
|
||||||
hls_url, film_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
|
|
||||||
self._sort_formats(formats, ('height', 'tbr', 'format_id'))
|
|
||||||
|
|
||||||
info = {
|
|
||||||
'id': film_id,
|
|
||||||
'display_id': display_id,
|
|
||||||
'title': title,
|
|
||||||
'description': gist.get('description'),
|
|
||||||
'thumbnail': gist.get('videoImageUrl'),
|
|
||||||
'duration': int_or_none(gist.get('runtime')),
|
|
||||||
'age_limit': parse_age_limit(content_data.get('parentalRating')),
|
|
||||||
'timestamp': int_or_none(gist.get('publishDate'), 1000),
|
|
||||||
'formats': formats,
|
|
||||||
}
|
|
||||||
for k in ('categories', 'tags'):
|
|
||||||
info[k] = [v['title'] for v in content_data.get(k, []) if v.get('title')]
|
|
||||||
return info
|
|
||||||
else:
|
|
||||||
film_id = self._search_regex(r'filmId=([\da-f-]{36})"', webpage, 'film id')
|
|
||||||
|
|
||||||
snag = self._parse_json(
|
|
||||||
self._search_regex(
|
|
||||||
r'Snag\.page\.data\s*=\s*(\[.+?\]);', webpage, 'snag', default='[]'),
|
|
||||||
display_id)
|
|
||||||
|
|
||||||
for item in snag:
|
|
||||||
if item.get('data', {}).get('film', {}).get('id') == film_id:
|
|
||||||
data = item['data']['film']
|
|
||||||
title = data['title']
|
|
||||||
description = clean_html(data.get('synopsis'))
|
|
||||||
thumbnail = data.get('image')
|
|
||||||
duration = int_or_none(data.get('duration') or data.get('runtime'))
|
|
||||||
categories = [
|
|
||||||
category['title'] for category in data.get('categories', [])
|
|
||||||
if category.get('title')]
|
|
||||||
break
|
|
||||||
else:
|
|
||||||
title = self._html_search_regex(
|
|
||||||
(r'itemprop="title">([^<]+)<',
|
|
||||||
r'(?s)itemprop="title">(.+?)<div'), webpage, 'title')
|
|
||||||
description = self._html_search_regex(
|
|
||||||
r'(?s)<div itemprop="description" class="film-synopsis-inner ">(.+?)</div>',
|
|
||||||
webpage, 'description', default=None) or self._og_search_description(webpage)
|
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
|
||||||
duration = parse_duration(self._search_regex(
|
|
||||||
r'<span itemprop="duration" class="film-duration strong">([^<]+)<',
|
|
||||||
webpage, 'duration', fatal=False))
|
|
||||||
categories = re.findall(r'<a href="/movies/[^"]+">([^<]+)</a>', webpage)
|
|
||||||
|
|
||||||
return {
|
|
||||||
'_type': 'url_transparent',
|
|
||||||
'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
|
|
||||||
'id': film_id,
|
|
||||||
'display_id': display_id,
|
|
||||||
'title': title,
|
|
||||||
'description': description,
|
|
||||||
'thumbnail': thumbnail,
|
|
||||||
'duration': duration,
|
|
||||||
'categories': categories,
|
|
||||||
'ie_key': 'ViewLiftEmbed',
|
|
||||||
}
|
|
||||||
|
|||||||
@ -841,33 +841,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
|
|||||||
return self._TITLE or self._html_search_regex(
|
return self._TITLE or self._html_search_regex(
|
||||||
self._TITLE_RE, webpage, 'list title', fatal=False)
|
self._TITLE_RE, webpage, 'list title', fatal=False)
|
||||||
|
|
||||||
def _login_list_password(self, page_url, list_id, webpage):
|
|
||||||
login_form = self._search_regex(
|
|
||||||
r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
|
|
||||||
webpage, 'login form', default=None)
|
|
||||||
if not login_form:
|
|
||||||
return webpage
|
|
||||||
|
|
||||||
password = self._downloader.params.get('videopassword')
|
|
||||||
if password is None:
|
|
||||||
raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
|
|
||||||
fields = self._hidden_inputs(login_form)
|
|
||||||
token, vuid = self._extract_xsrft_and_vuid(webpage)
|
|
||||||
fields['token'] = token
|
|
||||||
fields['password'] = password
|
|
||||||
post = urlencode_postdata(fields)
|
|
||||||
password_path = self._search_regex(
|
|
||||||
r'action="([^"]+)"', login_form, 'password URL')
|
|
||||||
password_url = compat_urlparse.urljoin(page_url, password_path)
|
|
||||||
password_request = sanitized_Request(password_url, post)
|
|
||||||
password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
|
|
||||||
self._set_vimeo_cookie('vuid', vuid)
|
|
||||||
self._set_vimeo_cookie('xsrft', token)
|
|
||||||
|
|
||||||
return self._download_webpage(
|
|
||||||
password_request, list_id,
|
|
||||||
'Verifying the password', 'Wrong password')
|
|
||||||
|
|
||||||
def _title_and_entries(self, list_id, base_url):
|
def _title_and_entries(self, list_id, base_url):
|
||||||
for pagenum in itertools.count(1):
|
for pagenum in itertools.count(1):
|
||||||
page_url = self._page_url(base_url, pagenum)
|
page_url = self._page_url(base_url, pagenum)
|
||||||
@ -876,7 +849,6 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
|
|||||||
'Downloading page %s' % pagenum)
|
'Downloading page %s' % pagenum)
|
||||||
|
|
||||||
if pagenum == 1:
|
if pagenum == 1:
|
||||||
webpage = self._login_list_password(page_url, list_id, webpage)
|
|
||||||
yield self._extract_list_title(webpage)
|
yield self._extract_list_title(webpage)
|
||||||
|
|
||||||
# Try extracting href first since not all videos are available via
|
# Try extracting href first since not all videos are available via
|
||||||
@ -923,7 +895,7 @@ class VimeoUserIE(VimeoChannelIE):
|
|||||||
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
|
_BASE_URL_TEMPL = 'https://vimeo.com/%s'
|
||||||
|
|
||||||
|
|
||||||
class VimeoAlbumIE(VimeoChannelIE):
|
class VimeoAlbumIE(VimeoBaseInfoExtractor):
|
||||||
IE_NAME = 'vimeo:album'
|
IE_NAME = 'vimeo:album'
|
||||||
_VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
|
_VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
|
||||||
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
|
_TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
|
||||||
@ -973,13 +945,39 @@ class VimeoAlbumIE(VimeoChannelIE):
|
|||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
album_id = self._match_id(url)
|
album_id = self._match_id(url)
|
||||||
webpage = self._download_webpage(url, album_id)
|
webpage = self._download_webpage(url, album_id)
|
||||||
webpage = self._login_list_password(url, album_id, webpage)
|
viewer = self._parse_json(self._search_regex(
|
||||||
api_config = self._extract_vimeo_config(webpage, album_id)['api']
|
r'bootstrap_data\s*=\s*({.+?})</script>',
|
||||||
|
webpage, 'bootstrap data'), album_id)['viewer']
|
||||||
|
jwt = viewer['jwt']
|
||||||
|
album = self._download_json(
|
||||||
|
'https://api.vimeo.com/albums/' + album_id,
|
||||||
|
album_id, headers={'Authorization': 'jwt ' + jwt},
|
||||||
|
query={'fields': 'description,name,privacy'})
|
||||||
|
hashed_pass = None
|
||||||
|
if try_get(album, lambda x: x['privacy']['view']) == 'password':
|
||||||
|
password = self._downloader.params.get('videopassword')
|
||||||
|
if not password:
|
||||||
|
raise ExtractorError(
|
||||||
|
'This album is protected by a password, use the --video-password option',
|
||||||
|
expected=True)
|
||||||
|
self._set_vimeo_cookie('vuid', viewer['vuid'])
|
||||||
|
try:
|
||||||
|
hashed_pass = self._download_json(
|
||||||
|
'https://vimeo.com/showcase/%s/auth' % album_id,
|
||||||
|
album_id, 'Verifying the password', data=urlencode_postdata({
|
||||||
|
'password': password,
|
||||||
|
'token': viewer['xsrft'],
|
||||||
|
}), headers={
|
||||||
|
'X-Requested-With': 'XMLHttpRequest',
|
||||||
|
})['hashed_pass']
|
||||||
|
except ExtractorError as e:
|
||||||
|
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
|
||||||
|
raise ExtractorError('Wrong password', expected=True)
|
||||||
|
raise
|
||||||
entries = OnDemandPagedList(functools.partial(
|
entries = OnDemandPagedList(functools.partial(
|
||||||
self._fetch_page, album_id, api_config['jwt'],
|
self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
|
||||||
api_config.get('hashed_pass')), self._PAGE_SIZE)
|
return self.playlist_result(
|
||||||
return self.playlist_result(entries, album_id, self._html_search_regex(
|
entries, album_id, album.get('name'), album.get('description'))
|
||||||
r'<title>\s*(.+?)(?:\s+on Vimeo)?</title>', webpage, 'title', fatal=False))
|
|
||||||
|
|
||||||
|
|
||||||
class VimeoGroupsIE(VimeoChannelIE):
|
class VimeoGroupsIE(VimeoChannelIE):
|
||||||
|
|||||||
@ -1,17 +1,12 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
import re
|
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
from ..compat import (
|
from ..compat import compat_str
|
||||||
compat_str,
|
|
||||||
compat_urlparse,
|
|
||||||
)
|
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
ExtractorError,
|
ExtractorError,
|
||||||
determine_ext,
|
determine_ext,
|
||||||
int_or_none,
|
int_or_none,
|
||||||
sanitized_Request,
|
urljoin,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@ -26,8 +21,7 @@ class VoiceRepublicIE(InfoExtractor):
|
|||||||
'ext': 'm4a',
|
'ext': 'm4a',
|
||||||
'title': 'Watching the Watchers: Building a Sousveillance State',
|
'title': 'Watching the Watchers: Building a Sousveillance State',
|
||||||
'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
|
'description': 'Secret surveillance programs have metadata too. The people and companies that operate secret surveillance programs can be surveilled.',
|
||||||
'thumbnail': r're:^https?://.*\.(?:png|jpg)$',
|
'duration': 1556,
|
||||||
'duration': 1800,
|
|
||||||
'view_count': int,
|
'view_count': int,
|
||||||
}
|
}
|
||||||
}, {
|
}, {
|
||||||
@ -38,63 +32,31 @@ class VoiceRepublicIE(InfoExtractor):
|
|||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
display_id = self._match_id(url)
|
display_id = self._match_id(url)
|
||||||
|
|
||||||
req = sanitized_Request(
|
webpage = self._download_webpage(url, display_id)
|
||||||
compat_urlparse.urljoin(url, '/talks/%s' % display_id))
|
|
||||||
# Older versions of Firefox get redirected to an "upgrade browser" page
|
|
||||||
req.add_header('User-Agent', 'youtube-dl')
|
|
||||||
webpage = self._download_webpage(req, display_id)
|
|
||||||
|
|
||||||
if '>Queued for processing, please stand by...<' in webpage:
|
if '>Queued for processing, please stand by...<' in webpage:
|
||||||
raise ExtractorError(
|
raise ExtractorError(
|
||||||
'Audio is still queued for processing', expected=True)
|
'Audio is still queued for processing', expected=True)
|
||||||
|
|
||||||
config = self._search_regex(
|
talk = self._parse_json(self._search_regex(
|
||||||
r'(?s)return ({.+?});\s*\n', webpage,
|
r'initialSnapshot\s*=\s*({.+?});',
|
||||||
'data', default=None)
|
webpage, 'talk'), display_id)['talk']
|
||||||
data = self._parse_json(config, display_id, fatal=False) if config else None
|
title = talk['title']
|
||||||
if data:
|
formats = [{
|
||||||
title = data['title']
|
'url': urljoin(url, talk_url),
|
||||||
description = data.get('teaser')
|
'format_id': format_id,
|
||||||
talk_id = compat_str(data.get('talk_id') or display_id)
|
'ext': determine_ext(talk_url) or format_id,
|
||||||
talk = data['talk']
|
'vcodec': 'none',
|
||||||
duration = int_or_none(talk.get('duration'))
|
} for format_id, talk_url in talk['media_links'].items()]
|
||||||
formats = [{
|
|
||||||
'url': compat_urlparse.urljoin(url, talk_url),
|
|
||||||
'format_id': format_id,
|
|
||||||
'ext': determine_ext(talk_url) or format_id,
|
|
||||||
'vcodec': 'none',
|
|
||||||
} for format_id, talk_url in talk['links'].items()]
|
|
||||||
else:
|
|
||||||
title = self._og_search_title(webpage)
|
|
||||||
description = self._html_search_regex(
|
|
||||||
r"(?s)<div class='talk-teaser'[^>]*>(.+?)</div>",
|
|
||||||
webpage, 'description', fatal=False)
|
|
||||||
talk_id = self._search_regex(
|
|
||||||
[r"id='jc-(\d+)'", r"data-shareable-id='(\d+)'"],
|
|
||||||
webpage, 'talk id', default=None) or display_id
|
|
||||||
duration = None
|
|
||||||
player = self._search_regex(
|
|
||||||
r"class='vr-player jp-jplayer'([^>]+)>", webpage, 'player')
|
|
||||||
formats = [{
|
|
||||||
'url': compat_urlparse.urljoin(url, talk_url),
|
|
||||||
'format_id': format_id,
|
|
||||||
'ext': determine_ext(talk_url) or format_id,
|
|
||||||
'vcodec': 'none',
|
|
||||||
} for format_id, talk_url in re.findall(r"data-([^=]+)='([^']+)'", player)]
|
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
thumbnail = self._og_search_thumbnail(webpage)
|
|
||||||
view_count = int_or_none(self._search_regex(
|
|
||||||
r"class='play-count[^']*'>\s*(\d+) plays",
|
|
||||||
webpage, 'play count', fatal=False))
|
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': talk_id,
|
'id': compat_str(talk.get('id') or display_id),
|
||||||
'display_id': display_id,
|
'display_id': display_id,
|
||||||
'title': title,
|
'title': title,
|
||||||
'description': description,
|
'description': talk.get('teaser'),
|
||||||
'thumbnail': thumbnail,
|
'thumbnail': talk.get('image_url'),
|
||||||
'duration': duration,
|
'duration': int_or_none(talk.get('archived_duration')),
|
||||||
'view_count': view_count,
|
'view_count': int_or_none(talk.get('play_count')),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
}
|
}
|
||||||
|
|||||||
@ -45,22 +45,23 @@ class WistiaIE(InfoExtractor):
|
|||||||
# https://wistia.com/support/embed-and-share/video-on-your-website
|
# https://wistia.com/support/embed-and-share/video-on-your-website
|
||||||
@staticmethod
|
@staticmethod
|
||||||
def _extract_url(webpage):
|
def _extract_url(webpage):
|
||||||
match = re.search(
|
urls = WistiaIE._extract_urls(webpage)
|
||||||
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage)
|
return urls[0] if urls else None
|
||||||
if match:
|
|
||||||
return unescapeHTML(match.group('url'))
|
|
||||||
|
|
||||||
match = re.search(
|
@staticmethod
|
||||||
r'''(?sx)
|
def _extract_urls(webpage):
|
||||||
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
|
urls = []
|
||||||
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
|
for match in re.finditer(
|
||||||
''', webpage)
|
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
|
||||||
if match:
|
urls.append(unescapeHTML(match.group('url')))
|
||||||
return 'wistia:%s' % match.group('id')
|
for match in re.finditer(
|
||||||
|
r'''(?sx)
|
||||||
match = re.search(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage)
|
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]{10})\b.*?\2
|
||||||
if match:
|
''', webpage):
|
||||||
return 'wistia:%s' % match.group('id')
|
urls.append('wistia:%s' % match.group('id'))
|
||||||
|
for match in re.finditer(r'(?:data-wistia-?id=["\']|Wistia\.embed\(["\']|id=["\']wistia_)(?P<id>[a-z0-9]{10})', webpage):
|
||||||
|
urls.append('wistia:%s' % match.group('id'))
|
||||||
|
return urls
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|||||||
@ -1,6 +1,7 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..compat import compat_str
|
||||||
from ..utils import (
|
from ..utils import (
|
||||||
parse_duration,
|
parse_duration,
|
||||||
urljoin,
|
urljoin,
|
||||||
@ -8,9 +9,9 @@ from ..utils import (
|
|||||||
|
|
||||||
|
|
||||||
class YourPornIE(InfoExtractor):
|
class YourPornIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?:yourporn\.sexy|sxyprn\.com)/post/(?P<id>[^/?#&.]+)'
|
_VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
|
'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
|
||||||
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
|
'md5': '6f8682b6464033d87acaa7a8ff0c092e',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': '57ffcb2e1179b',
|
'id': '57ffcb2e1179b',
|
||||||
@ -33,11 +34,19 @@ class YourPornIE(InfoExtractor):
|
|||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
webpage = self._download_webpage(url, video_id)
|
||||||
|
|
||||||
video_url = urljoin(url, self._parse_json(
|
parts = self._parse_json(
|
||||||
self._search_regex(
|
self._search_regex(
|
||||||
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
|
r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
|
||||||
group='data'),
|
group='data'),
|
||||||
video_id)[video_id]).replace('/cdn/', '/cdn5/')
|
video_id)[video_id].split('/')
|
||||||
|
|
||||||
|
num = 0
|
||||||
|
for c in parts[6] + parts[7]:
|
||||||
|
if c.isnumeric():
|
||||||
|
num += int(c)
|
||||||
|
parts[5] = compat_str(int(parts[5]) - num)
|
||||||
|
parts[1] += '8'
|
||||||
|
video_url = urljoin(url, '/'.join(parts))
|
||||||
|
|
||||||
title = (self._search_regex(
|
title = (self._search_regex(
|
||||||
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
|
r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
|
||||||
@ -54,4 +63,5 @@ class YourPornIE(InfoExtractor):
|
|||||||
'thumbnail': thumbnail,
|
'thumbnail': thumbnail,
|
||||||
'duration': duration,
|
'duration': duration,
|
||||||
'age_limit': 18,
|
'age_limit': 18,
|
||||||
|
'ext': 'mp4',
|
||||||
}
|
}
|
||||||
|
|||||||
@ -1343,6 +1343,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
funcname = self._search_regex(
|
funcname = self._search_regex(
|
||||||
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
(r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
||||||
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
||||||
|
r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
|
||||||
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
|
r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
|
||||||
# Obsolete patterns
|
# Obsolete patterns
|
||||||
r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
|
||||||
|
|||||||
@ -4,10 +4,20 @@ from __future__ import unicode_literals
|
|||||||
import re
|
import re
|
||||||
|
|
||||||
from .common import InfoExtractor
|
from .common import InfoExtractor
|
||||||
|
from ..compat import compat_HTTPError
|
||||||
|
from ..utils import (
|
||||||
|
dict_get,
|
||||||
|
ExtractorError,
|
||||||
|
int_or_none,
|
||||||
|
js_to_json,
|
||||||
|
parse_iso8601,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
class ZypeIE(InfoExtractor):
|
class ZypeIE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://player\.zype\.com/embed/(?P<id>[\da-fA-F]+)\.js\?.*?api_key=[^&]+'
|
_ID_RE = r'[\da-fA-F]+'
|
||||||
|
_COMMON_RE = r'//player\.zype\.com/embed/%s\.(?:js|json|html)\?.*?(?:access_token|(?:ap[ip]|player)_key)='
|
||||||
|
_VALID_URL = r'https?:%s[^&]+' % (_COMMON_RE % ('(?P<id>%s)' % _ID_RE))
|
||||||
_TEST = {
|
_TEST = {
|
||||||
'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false',
|
'url': 'https://player.zype.com/embed/5b400b834b32992a310622b9.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ&autoplay=false&controls=true&da=false',
|
||||||
'md5': 'eaee31d474c76a955bdaba02a505c595',
|
'md5': 'eaee31d474c76a955bdaba02a505c595',
|
||||||
@ -16,6 +26,9 @@ class ZypeIE(InfoExtractor):
|
|||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Smoky Barbecue Favorites',
|
'title': 'Smoky Barbecue Favorites',
|
||||||
'thumbnail': r're:^https?://.*\.jpe?g',
|
'thumbnail': r're:^https?://.*\.jpe?g',
|
||||||
|
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
|
||||||
|
'timestamp': 1504915200,
|
||||||
|
'upload_date': '20170909',
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -24,34 +37,98 @@ class ZypeIE(InfoExtractor):
|
|||||||
return [
|
return [
|
||||||
mobj.group('url')
|
mobj.group('url')
|
||||||
for mobj in re.finditer(
|
for mobj in re.finditer(
|
||||||
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//player\.zype\.com/embed/[\da-fA-F]+\.js\?.*?api_key=.+?)\1',
|
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?%s.+?)\1' % (ZypeIE._COMMON_RE % ZypeIE._ID_RE),
|
||||||
webpage)]
|
webpage)]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id)
|
try:
|
||||||
|
response = self._download_json(re.sub(
|
||||||
|
r'\.(?:js|html)\?', '.json?', url), video_id)['response']
|
||||||
|
except ExtractorError as e:
|
||||||
|
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 401, 403):
|
||||||
|
raise ExtractorError(self._parse_json(
|
||||||
|
e.cause.read().decode(), video_id)['message'], expected=True)
|
||||||
|
raise
|
||||||
|
|
||||||
title = self._search_regex(
|
body = response['body']
|
||||||
r'video_title\s*[:=]\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
|
video = response['video']
|
||||||
'title', group='value')
|
title = video['title']
|
||||||
|
|
||||||
m3u8_url = self._search_regex(
|
if isinstance(body, dict):
|
||||||
r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', webpage,
|
formats = []
|
||||||
'm3u8 url', group='url')
|
for output in body.get('outputs', []):
|
||||||
|
output_url = output.get('url')
|
||||||
formats = self._extract_m3u8_formats(
|
if not output_url:
|
||||||
m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
|
continue
|
||||||
m3u8_id='hls')
|
name = output.get('name')
|
||||||
|
if name == 'm3u8':
|
||||||
|
formats = self._extract_m3u8_formats(
|
||||||
|
output_url, video_id, 'mp4',
|
||||||
|
'm3u8_native', m3u8_id='hls', fatal=False)
|
||||||
|
else:
|
||||||
|
f = {
|
||||||
|
'format_id': name,
|
||||||
|
'tbr': int_or_none(output.get('bitrate')),
|
||||||
|
'url': output_url,
|
||||||
|
}
|
||||||
|
if name in ('m4a', 'mp3'):
|
||||||
|
f['vcodec'] = 'none'
|
||||||
|
else:
|
||||||
|
f.update({
|
||||||
|
'height': int_or_none(output.get('height')),
|
||||||
|
'width': int_or_none(output.get('width')),
|
||||||
|
})
|
||||||
|
formats.append(f)
|
||||||
|
text_tracks = body.get('subtitles') or []
|
||||||
|
else:
|
||||||
|
m3u8_url = self._search_regex(
|
||||||
|
r'(["\'])(?P<url>(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1',
|
||||||
|
body, 'm3u8 url', group='url')
|
||||||
|
formats = self._extract_m3u8_formats(
|
||||||
|
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')
|
||||||
|
text_tracks = self._search_regex(
|
||||||
|
r'textTracks\s*:\s*(\[[^]]+\])',
|
||||||
|
body, 'text tracks', default=None)
|
||||||
|
if text_tracks:
|
||||||
|
text_tracks = self._parse_json(
|
||||||
|
text_tracks, video_id, js_to_json, False)
|
||||||
self._sort_formats(formats)
|
self._sort_formats(formats)
|
||||||
|
|
||||||
thumbnail = self._search_regex(
|
subtitles = {}
|
||||||
r'poster\s*[:=]\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'thumbnail',
|
if text_tracks:
|
||||||
default=False, group='url')
|
for text_track in text_tracks:
|
||||||
|
tt_url = dict_get(text_track, ('file', 'src'))
|
||||||
|
if not tt_url:
|
||||||
|
continue
|
||||||
|
subtitles.setdefault(text_track.get('label') or 'English', []).append({
|
||||||
|
'url': tt_url,
|
||||||
|
})
|
||||||
|
|
||||||
|
thumbnails = []
|
||||||
|
for thumbnail in video.get('thumbnails', []):
|
||||||
|
thumbnail_url = thumbnail.get('url')
|
||||||
|
if not thumbnail_url:
|
||||||
|
continue
|
||||||
|
thumbnails.append({
|
||||||
|
'url': thumbnail_url,
|
||||||
|
'width': int_or_none(thumbnail.get('width')),
|
||||||
|
'height': int_or_none(thumbnail.get('height')),
|
||||||
|
})
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
|
'display_id': video.get('friendly_title'),
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': thumbnail,
|
'thumbnails': thumbnails,
|
||||||
|
'description': dict_get(video, ('description', 'ott_description', 'short_description')),
|
||||||
|
'timestamp': parse_iso8601(video.get('published_at')),
|
||||||
|
'duration': int_or_none(video.get('duration')),
|
||||||
|
'view_count': int_or_none(video.get('request_count')),
|
||||||
|
'average_rating': int_or_none(video.get('rating')),
|
||||||
|
'season_number': int_or_none(video.get('season')),
|
||||||
|
'episode_number': int_or_none(video.get('episode')),
|
||||||
'formats': formats,
|
'formats': formats,
|
||||||
|
'subtitles': subtitles,
|
||||||
}
|
}
|
||||||
|
|||||||
@ -9,6 +9,7 @@ import subprocess
|
|||||||
import sys
|
import sys
|
||||||
from zipimport import zipimporter
|
from zipimport import zipimporter
|
||||||
|
|
||||||
|
from .compat import compat_realpath
|
||||||
from .utils import encode_compat_str
|
from .utils import encode_compat_str
|
||||||
|
|
||||||
from .version import __version__
|
from .version import __version__
|
||||||
@ -84,7 +85,9 @@ def update_self(to_screen, verbose, opener):
|
|||||||
print_notes(to_screen, versions_info['versions'])
|
print_notes(to_screen, versions_info['versions'])
|
||||||
|
|
||||||
# sys.executable is set to the full pathname of the exe-file for py2exe
|
# sys.executable is set to the full pathname of the exe-file for py2exe
|
||||||
filename = sys.executable if hasattr(sys, 'frozen') else sys.argv[0]
|
# though symlinks are not followed so that we need to do this manually
|
||||||
|
# with help of realpath
|
||||||
|
filename = compat_realpath(sys.executable if hasattr(sys, 'frozen') else sys.argv[0])
|
||||||
|
|
||||||
if not os.access(filename, os.W_OK):
|
if not os.access(filename, os.W_OK):
|
||||||
to_screen('ERROR: no write permissions on %s' % filename)
|
to_screen('ERROR: no write permissions on %s' % filename)
|
||||||
|
|||||||
@ -1,3 +1,3 @@
|
|||||||
from __future__ import unicode_literals
|
from __future__ import unicode_literals
|
||||||
|
|
||||||
__version__ = '2020.01.01'
|
__version__ = '2020.02.16'
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user