Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 08:34:32 +01:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'upstream/master' into fix-instagram

Browse Source
This commit is contained in:
Andrew Udvare 2020-04-05 07:05:34 -04:00
commit b85ccc3be3
No known key found for this signature in database
GPG Key ID: 1AFD9AFC120C26DD
178 changed files with 6650 additions and 6907 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE/1_broken_site.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. 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 Issues with outdated version will be REJECTED.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 2020.03.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -26,7 +26,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support
- [ ] I've verified that I'm running youtube-dl version **2019.10.22**
- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar issues including closed ones
@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2019.10.22
[debug] youtube-dl version 2020.03.24
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

4
.github/ISSUE_TEMPLATE/2_site_support_request.md vendored
View File

@ -19,7 +19,7 @@ labels: 'site-support-request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. 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 2020.03.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that site you are requesting is not dedicated to copyright infringement, see https://yt-dl.org/copyright-infringement. youtube-dl does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
- Search the bugtracker for similar site support requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a new site support request
- [ ] I've verified that I'm running youtube-dl version **2019.10.22**
- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that none of provided URLs violate any copyrights
- [ ] I've searched the bugtracker for similar site support requests including closed ones

4
.github/ISSUE_TEMPLATE/3_site_feature_request.md vendored
View File

@ -18,13 +18,13 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. 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 2020.03.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar site feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a site feature request
- [ ] I've verified that I'm running youtube-dl version **2019.10.22**
- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
- [ ] I've searched the bugtracker for similar site feature requests including closed ones

6
.github/ISSUE_TEMPLATE/4_bug_report.md vendored
View File

@ -18,7 +18,7 @@ title: ''
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. 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 2020.03.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
@ -27,7 +27,7 @@ Carefully read and work through this check list in order to prevent the most com
-->
- [ ] I'm reporting a broken site support issue
- [ ] I've verified that I'm running youtube-dl version **2019.10.22**
- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
- [ ] I've checked that all provided URLs are alive and playable in a browser
- [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [ ] I've searched the bugtracker for similar bug reports including closed ones
@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2019.10.22
[debug] youtube-dl version 2020.03.24
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

4
.github/ISSUE_TEMPLATE/5_feature_request.md vendored
View File

@ -19,13 +19,13 @@ labels: 'request'
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2019.10.22. 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 2020.03.24. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Search the bugtracker for similar feature requests: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Finally, put x into all relevant boxes (like this [x])
-->
- [ ] I'm reporting a feature request
- [ ] I've verified that I'm running youtube-dl version **2019.10.22**
- [ ] I've verified that I'm running youtube-dl version **2020.03.24**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

13
.travis.yml
View File

@ -13,7 +13,7 @@ dist: trusty
env:
- YTDL_TEST_SET=core
- YTDL_TEST_SET=download
matrix:
jobs:
include:
- python: 3.7
dist: xenial
@ -21,6 +21,12 @@ matrix:
- python: 3.7
dist: xenial
env: YTDL_TEST_SET=download
- python: 3.8
dist: xenial
env: YTDL_TEST_SET=core
- python: 3.8
dist: xenial
env: YTDL_TEST_SET=download
- python: 3.8-dev
dist: xenial
env: YTDL_TEST_SET=core
@ -29,6 +35,11 @@ matrix:
env: YTDL_TEST_SET=download
- env: JYTHON=true; YTDL_TEST_SET=core
- env: JYTHON=true; YTDL_TEST_SET=download
- name: flake8
python: 3.8
dist: xenial
install: pip install flake8
script: flake8 .
fast_finish: true
allow_failures:
- env: YTDL_TEST_SET=download

406
ChangeLog
View File

@ -1,3 +1,405 @@
version 2020.03.24
Core
- [utils] Revert support for cookie files with spaces used instead of tabs
Extractors
* [teachable] Update upskillcourses and gns3 domains
* [generic] Look for teachable embeds before wistia
+ [teachable] Extract chapter metadata (#24421)
+ [bilibili] Add support for player.bilibili.com (#24402)
+ [bilibili] Add support for new URL schema with BV ids (#24439, #24442)
* [limelight] Remove disabled API requests (#24255)
* [soundcloud] Fix download URL extraction (#24394)
+ [cbc:watch] Add support for authentication (#19160)
* [hellporno] Fix extraction (#24399)
* [xtube] Fix formats extraction (#24348)
* [ndr] Fix extraction (#24326)
* [nhk] Update m3u8 URL and use native HLS downloader (#24329)
- [nhk] Remove obsolete rtmp formats (#24329)
* [nhk] Relax URL regular expression (#24329)
- [vimeo] Revert fix showcase password protected video extraction (#24224)
version 2020.03.08
Core
+ [utils] Add support for cookie files with spaces used instead of tabs
Extractors
+ [pornhub] Add support for pornhubpremium.com (#24288)
- [youtube] Remove outdated code and unnecessary requests
* [youtube] Improve extraction in 429 HTTP error conditions (#24283)
* [nhk] Update API version (#24270)
version 2020.03.06
Extractors
* [youtube] Fix age-gated videos support without login (#24248)
* [vimeo] Fix showcase password protected video extraction (#24224)
* [pornhub] Improve title extraction (#24184)
* [peertube] Improve extraction (#23657)
+ [servus] Add support for new URL schema (#23475, #23583, #24142)
* [vimeo] Fix subtitles URLs (#24209)
version 2020.03.01
Core
* [YoutubeDL] Force redirect URL to unicode on python 2
- [options] Remove duplicate short option -v for --version (#24162)
Extractors
* [xhamster] Fix extraction (#24205)
* [franceculture] Fix extraction (#24204)
+ [telecinco] Add support for article opening videos
* [telecinco] Fix extraction (#24195)
* [xtube] Fix metadata extraction (#21073, #22455)
* [youjizz] Fix extraction (#24181)
- Remove no longer needed compat_str around geturl
* [pornhd] Fix extraction (#24128)
+ [teachable] Add support for multiple videos per lecture (#24101)
+ [wistia] Add support for multiple generic embeds (#8347, 11385)
* [imdb] Fix extraction (#23443)
* [tv2dk:bornholm:play] Fix extraction (#24076)
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
Extractors
* [brightcove] Invalidate policy key cache on failing requests
* [pornhub] Improve locked videos detection (#22449, #22780)
+ [pornhub] Add support for m3u8 formats
* [pornhub] Fix extraction (#22749, #23082)
* [brightcove] Update policy key on failing requests
* [spankbang] Improve removed video detection (#23423)
* [spankbang] Fix extraction (#23307, #23423, #23444)
* [soundcloud] Automatically update client id on failing requests
* [prosiebensat1] Improve geo restriction handling (#23571)
* [brightcove] Cache brightcove player policy keys
* [teachable] Fail with error message if no video URL found
* [teachable] Improve locked lessons detection (#23528)
+ [scrippsnetworks] Add support for Scripps Networks sites (#19857, #22981)
* [mitele] Fix extraction (#21354, #23456)
* [soundcloud] Update client id (#23516)
* [mailru] Relax URL regular expressions (#23509)
version 2019.12.25
Core
* [utils] Improve str_to_int
+ [downloader/hls] Add ability to override AES decryption key URL (#17521)
Extractors
* [mediaset] Fix parse formats (#23508)
+ [tv2dk:bornholm:play] Add support for play.tv2bornholm.dk (#23291)
+ [slideslive] Add support for url and vimeo service names (#23414)
* [slideslive] Fix extraction (#23413)
* [twitch:clips] Fix extraction (#23375)
+ [soundcloud] Add support for token protected embeds (#18954)
* [vk] Improve extraction
* Fix User Videos extraction (#23356)
* Extract all videos for lists with more than 1000 videos (#23356)
+ Add support for video albums (#14327, #14492)
- [kontrtube] Remove extractor
- [videopremium] Remove extractor
- [musicplayon] Remove extractor (#9225)
+ [ufctv] Add support for ufcfightpass.imgdge.com and
ufcfightpass.imggaming.com (#23343)
+ [twitch] Extract m3u8 formats frame rate (#23333)
+ [imggaming] Add support for playlists and extract subtitles
+ [ufcarabia] Add support for UFC Arabia (#23312)
* [ufctv] Fix extraction
* [yahoo] Fix gyao brightcove player id (#23303)
* [vzaar] Override AES decryption key URL (#17521)
+ [vzaar] Add support for AES HLS manifests (#17521, #23299)
* [nrl] Fix extraction
* [teachingchannel] Fix extraction
* [nintendo] Fix extraction and partially add support for Nintendo Direct
videos (#4592)
+ [ooyala] Add better fallback values for domain and streams variables
+ [youtube] Add support youtubekids.com (#23272)
* [tv2] Detect DRM protection
+ [tv2] Add support for katsomo.fi and mtv.fi (#10543)
* [tv2] Fix tv2.no article extraction
* [msn] Improve extraction
+ Add support for YouTube and NBCSports embeds
+ Add support for articles with multiple videos
* Improve AOL embed support
* Improve format extraction
* [abcotvs] Relax URL regular expression and improve metadata extraction
(#18014)
* [channel9] Reduce response size
* [adobetv] Improve extaction
* Use OnDemandPagedList for list extractors
* Reduce show extraction requests
* Extract original video format and subtitles
+ Add support for adobe tv embeds
version 2019.11.28
Core
+ [utils] Add generic caesar cipher and rot47
* [utils] Handle rd-suffixed day parts in unified_strdate (#23199)
Extractors
* [vimeo] Improve extraction
* Fix review extraction
* Fix ondemand extraction
* Make password protected player case as an expected error (#22896)
* Simplify channel based extractors code
- [openload] Remove extractor (#11999)
- [verystream] Remove extractor
- [streamango] Remove extractor (#15406)
* [dailymotion] Improve extraction
* Extract http formats included in m3u8 manifest
* Fix user extraction (#3553, #21415)
+ Add suport for User Authentication (#11491)
* Fix password protected videos extraction (#23176)
* Respect age limit option and family filter cookie value (#18437)
* Handle video url playlist query param
* Report allowed countries for geo-restricted videos
* [corus] Improve extraction
+ Add support for Series Plus, W Network, YTV, ABC Spark, disneychannel.com
and disneylachaine.ca (#20861)
+ Add support for self hosted videos (#22075)
* Detect DRM protection (#14910, #9164)
* [vivo] Fix extraction (#22328, #22279)
+ [bitchute] Extract upload date (#22990, #23193)
* [soundcloud] Update client id (#23214)
version 2019.11.22
Core
+ [extractor/common] Clean jwplayer description HTML tags
+ [extractor/common] Add data, headers and query to all major extract formats
methods
Extractors
* [chaturbate] Fix extraction (#23010, #23012)
+ [ntvru] Add support for non relative file URLs (#23140)
* [vk] Fix wall audio thumbnails extraction (#23135)
* [ivi] Fix format extraction (#21991)
- [comcarcoff] Remove extractor
+ [drtv] Add support for new URL schema (#23059)
+ [nexx] Add support for Multi Player JS Setup (#23052)
+ [teamcoco] Add support for new videos (#23054)
* [soundcloud] Check if the soundtrack has downloads left (#23045)
* [facebook] Fix posts video data extraction (#22473)
- [addanime] Remove extractor
- [minhateca] Remove extractor
- [daisuki] Remove extractor
* [seeker] Fix extraction
- [revision3] Remove extractors
* [twitch] Fix video comments URL (#18593, #15828)
* [twitter] Improve extraction
+ Add support for generic embeds (#22168)
* Always extract http formats for native videos (#14934)
+ Add support for Twitter Broadcasts (#21369)
+ Extract more metadata
* Improve VMap format extraction
* Unify extraction code for both twitter statuses and cards
+ [twitch] Add support for Clip embed URLs
* [lnkgo] Fix extraction (#16834)
* [mixcloud] Improve extraction
* Improve metadata extraction (#11721)
* Fix playlist extraction (#22378)
* Fix user mixes extraction (#15197, #17865)
+ [kinja] Add support for Kinja embeds (#5756, #11282, #22237, #22384)
* [onionstudios] Fix extraction
+ [hotstar] Pass Referer header to format requests (#22836)
* [dplay] Minimize response size
+ [patreon] Extract uploader_id and filesize
* [patreon] Minimize response size
* [roosterteeth] Fix login request (#16094, #22689)
version 2019.11.05
Extractors
+ [scte] Add support for learning.scte.org (#22975)
+ [msn] Add support for Vidible and AOL embeds (#22195, #22227)
* [myspass] Fix video URL extraction and improve metadata extraction (#22448)
* [jamendo] Improve extraction
* Fix album extraction (#18564)
* Improve metadata extraction (#18565, #21379)
* [mediaset] Relax URL guid matching (#18352)
+ [mediaset] Extract unprotected M3U and MPD manifests (#17204)
* [telegraaf] Fix extraction
+ [bellmedia] Add support for marilyn.ca videos (#22193)
* [stv] Fix extraction (#22928)
- [iconosquare] Remove extractor
- [keek] Remove extractor
- [gameone] Remove extractor (#21778)
- [flipagram] Remove extractor
- [bambuser] Remove extractor
* [wistia] Reduce embed extraction false positives
+ [wistia] Add support for inline embeds (#22931)
- [go90] Remove extractor
* [kakao] Remove raw request
+ [kakao] Extract format total bitrate
* [daum] Fix VOD and Clip extracton (#15015)
* [kakao] Improve extraction
+ Add support for embed URLs
+ Add support for Kakao Legacy vid based embed URLs
* Only extract fields used for extraction
* Strip description and extract tags
* [mixcloud] Fix cloudcast data extraction (#22821)
* [yahoo] Improve extraction
+ Add support for live streams (#3597, #3779, #22178)
* Bypass cookie consent page for european domains (#16948, #22576)
+ Add generic support for embeds (#20332)
* [tv2] Fix and improve extraction (#22787)
+ [tv2dk] Add support for TV2 DK sites
* [onet] Improve extraction …
+ Add support for onet100.vod.pl
+ Extract m3u8 formats
* Correct audio only format info
* [fox9] Fix extraction
version 2019.10.29
Core
* [utils] Actualize major IPv4 address blocks per country
Extractors
+ [go] Add support for abc.com and freeform.com (#22823, #22864)
+ [mtv] Add support for mtvjapan.com
* [mtv] Fix extraction for mtv.de (#22113)
* [videodetective] Fix extraction
* [internetvideoarchive] Fix extraction
* [nbcnews] Fix extraction (#12569, #12576, #21703, #21923)
- [hark] Remove extractor
- [tutv] Remove extractor
- [learnr] Remove extractor
- [macgamestore] Remove extractor
* [la7] Update Kaltura service URL (#22358)
* [thesun] Fix extraction (#16966)
- [makertv] Remove extractor
+ [tenplay] Add support for 10play.com.au (#21446)
* [soundcloud] Improve extraction
* Improve format extraction (#22123)
+ Extract uploader_id and uploader_url (#21916)
+ Extract all known thumbnails (#19071, #20659)
* Fix extration for private playlists (#20976)
+ Add support for playlist embeds (#20976)
* Skip preview formats (#22806)
* [dplay] Improve extraction
+ Add support for dplay.fi, dplay.jp and es.dplay.com (#16969)
* Fix it.dplay.com extraction (#22826)
+ Extract creator, tags and thumbnails
* Handle playback API call errors
+ [discoverynetworks] Add support for dplay.co.uk
* [vk] Improve extraction
+ Add support for Odnoklassniki embeds
+ Extract more videos from user lists (#4470)
+ Fix wall post audio extraction (#18332)
* Improve error detection (#22568)
+ [odnoklassniki] Add support for embeds
* [puhutv] Improve extraction
* Fix subtitles extraction
* Transform HLS URLs to HTTP URLs
* Improve metadata extraction
* [ceskatelevize] Skip DRM media
+ [facebook] Extract subtitles (#22777)
* [globo] Handle alternative hash signing method
version 2019.10.22
Core
@ -412,7 +814,7 @@ Extractors
version 2019.04.17
Extractors
* [openload] Randomize User-Agent (closes #20688)
* [openload] Randomize User-Agent (#20688)
+ [openload] Add support for oladblock domains (#20471)
* [adn] Fix subtitle extraction (#12724)
+ [aol] Add support for localized websites
@ -977,7 +1379,7 @@ Extractors
+ [youtube] Extract channel meta fields (#9676, #12939)
* [porntube] Fix extraction (#17541)
* [asiancrush] Fix extraction (#15630)
+ [twitch:clips] Extend URL regular expression (closes #17559)
+ [twitch:clips] Extend URL regular expression (#17559)
+ [vzaar] Add support for HLS
* [tube8] Fix metadata extraction (#17520)
* [eporner] Extract JSON-LD (#17519)

8
README.md
View File

@ -752,8 +752,8 @@ As a last resort, you can also uninstall the version installed by your package m
Afterwards, simply follow [our manual installation instructions](https://ytdl-org.github.io/youtube-dl/download.html):
```
sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
sudo chmod a+x /usr/local/bin/youtube-dl
sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl
sudo chmod a+rx /usr/local/bin/youtube-dl
hash -r
```
@ -835,7 +835,9 @@ In February 2015, the new YouTube player contained a character sequence in a str
### HTTP Error 429: Too Many Requests or 402: Payment Required
These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
These two error codes indicate that the service is blocking your IP address because of overuse. Usually this is a soft block meaning that you can gain access again after solving CAPTCHA. Just open a browser and solve a CAPTCHA the service suggests you and after that [pass cookies](#how-do-i-pass-cookies-to-youtube-dl) to youtube-dl. Note that if your machine has multiple external IPs then you should also pass exactly the same IP you've used for solving CAPTCHA with [`--source-address`](#network-options). Also you may need to pass a `User-Agent` HTTP header of your browser with [`--user-agent`](#workarounds).
If this is not the case (no CAPTCHA suggested to solve by the service) then you can contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--source-address` options](#network-options) to select another IP address.
### SyntaxError: Non-ASCII character

18
devscripts/create-github-release.py
View File

@ -1,7 +1,6 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import base64
import io
import json
import mimetypes
@ -15,7 +14,6 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.compat import (
compat_basestring,
compat_input,
compat_getpass,
compat_print,
compat_urllib_request,
@ -40,28 +38,20 @@ class GitHubReleaser(object):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
self._username = info[0]
self._password = info[2]
self._token = info[2]
compat_print('Using GitHub credentials found in .netrc...')
return
else:
compat_print('No GitHub credentials found in .netrc')
except (IOError, netrc.NetrcParseError):
compat_print('Unable to parse .netrc')
self._username = compat_input(
'Type your GitHub username or email address and press [Return]: ')
self._password = compat_getpass(
'Type your GitHub password and press [Return]: ')
self._token = compat_getpass(
'Type your GitHub PAT (personal access token) and press [Return]: ')
def _call(self, req):
if isinstance(req, compat_basestring):
req = sanitized_Request(req)
# Authorizing manually since GitHub does not response with 401 with
# WWW-Authenticate header set (see
# https://developer.github.com/v3/#basic-authentication)
b64 = base64.b64encode(
('%s:%s' % (self._username, self._password)).encode('utf-8')).decode('ascii')
req.add_header('Authorization', 'Basic %s' % b64)
req.add_header('Authorization', 'token %s' % self._token)
response = self._opener.open(req).read().decode('utf-8')
return json.loads(response)

59
docs/supportedsites.md
View File

@ -26,13 +26,13 @@
- **AcademicEarth:Course**
- **acast**
- **acast:channel**
- **AddAnime**
- **ADN**: Anime Digital Network
- **AdobeConnect**
- **AdobeTV**
- **AdobeTVChannel**
- **AdobeTVShow**
- **AdobeTVVideo**
- **adobetv**
- **adobetv:channel**
- **adobetv:embed**
- **adobetv:show**
- **adobetv:video**
- **AdultSwim**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network and History Vault
- **afreecatv**: afreecatv.com
@ -76,8 +76,6 @@
- **awaan:video**
- **AZMedien**: AZ Medien videos
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **Bandcamp:weekly**
@ -100,6 +98,7 @@
- **BiliBili**
- **BilibiliAudio**
- **BilibiliAudioAlbum**
- **BiliBiliPlayer**
- **BioBioChileTV**
- **BIQLE**
- **BitChute**
@ -177,7 +176,6 @@
- **CNN**
- **CNNArticle**
- **CNNBlogs**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralFullEpisodes**
- **ComedyCentralShortname**
@ -205,8 +203,6 @@
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **DaisukiMotto**
- **DaisukiMottoPlaylist**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
@ -232,7 +228,6 @@
- **DouyuShow**
- **DouyuTV**: 斗鱼
- **DPlay**
- **DPlayIt**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
@ -285,12 +280,12 @@
- **FiveThirtyEight**
- **FiveTV**
- **Flickr**
- **Flipagram**
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **FootyRoom**
- **Formula1**
- **FOX**
- **FOX9**
- **FOX9News**
- **Foxgay**
- **foxnews**: Fox News and Fox Business Video
- **foxnews:article**
@ -316,8 +311,6 @@
- **FXNetworks**
- **Gaia**
- **GameInformer**
- **GameOne**
- **gameone:playlist**
- **GameSpot**
- **GameStar**
- **Gaskrank**
@ -332,14 +325,12 @@
- **Globo**
- **GloboArticle**
- **Go**
- **Go90**
- **GodTube**
- **Golem**
- **GoogleDrive**
- **Goshgay**
- **GPUTechConf**
- **Groupon**
- **Hark**
- **hbo**
- **HearThisAt**
- **Heise**
@ -368,7 +359,6 @@
- **Hungama**
- **HungamaSong**
- **Hypem**
- **Iconosquare**
- **ign.com**
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
@ -400,7 +390,6 @@
- **JeuxVideo**
- **Joj**
- **Jove**
- **jpopsuki.tv**
- **JWPlatform**
- **Kakao**
- **Kaltura**
@ -408,14 +397,14 @@
- **Kankan**
- **Karaoketv**
- **KarriereVideos**
- **keek**
- **Katsomo**
- **KeezMovies**
- **Ketnet**
- **KhanAcademy**
- **KickStarter**
- **KinjaEmbed**
- **KinoPoisk**
- **KonserthusetPlay**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
- **Ku6**
- **KUSI**
@ -432,7 +421,6 @@
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **Learnr**
- **Lecture2Go**
- **Lecturio**
- **LecturioCourse**
@ -466,11 +454,9 @@
- **lynda**: lynda.com videos
- **lynda:course**: lynda.com online courses
- **m6**
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **mailru:music**: Музыка@Mail.Ru
- **mailru:music:search**: Музыка@Mail.Ru
- **MakerTV**
- **MallTV**
- **mangomolo:live**
- **mangomolo:video**
@ -497,14 +483,12 @@
- **Mgoon**
- **MGTV**: 芒果TV
- **MiaoPai**
- **Minhateca**
- **MinistryGrid**
- **Minoto**
- **miomio.tv**
- **MiTele**: mitele.es
- **mixcloud**
- **mixcloud:playlist**
- **mixcloud:stream**
- **mixcloud:user**
- **Mixer:live**
- **Mixer:vod**
@ -526,11 +510,10 @@
- **mtg**: MTG services
- **mtv**
- **mtv.de**
- **mtv81**
- **mtv:video**
- **mtvjapan**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
- **mva**: Microsoft Virtual Academy videos
- **mva:course**: Microsoft Virtual Academy courses
- **Mwave**
@ -635,7 +618,6 @@
- **OnionStudios**
- **Ooyala**
- **OoyalaExternal**
- **Openload**
- **OraTV**
- **orf:fm4**: radio FM4
- **orf:fm4:story**: fm4.orf.at stories
@ -646,7 +628,6 @@
- **OutsideTV**
- **PacktPub**
- **PacktPubCourse**
- **PandaTV**: 熊猫TV
- **pandora.tv**: 판도라TV
- **ParamountNetwork**
- **parliamentlive.tv**: UK parliament videos
@ -682,6 +663,7 @@
- **Pokemon**
- **PolskieRadio**
- **PolskieRadioCategory**
- **Popcorntimes**
- **PopcornTV**
- **PornCom**
- **PornerBros**
@ -735,8 +717,6 @@
- **Restudy**
- **Reuters**
- **ReverbNation**
- **revision**
- **revision3:embed**
- **RICE**
- **RMCDecouverte**
- **RockstarGames**
@ -781,7 +761,10 @@
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
- **ScrippsNetworks**
- **scrippsnetworks:watch**
- **SCTE**
- **SCTECourse**
- **Seeker**
- **SenateISVP**
- **SendtoNews**
@ -815,6 +798,7 @@
- **soundcloud:set**
- **soundcloud:trackstation**
- **soundcloud:user**
- **SoundcloudEmbed**
- **soundgasm**
- **soundgasm:profile**
- **southpark.cc.com**
@ -841,7 +825,6 @@
- **Steam**
- **Stitcher**
- **Streamable**
- **Streamango**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -887,6 +870,7 @@
- **TeleTask**
- **Telewebion**
- **TennisTV**
- **TenPlay**
- **TF1**
- **TFO**
- **TheIntercept**
@ -925,11 +909,12 @@
- **tunein:topic**
- **TunePk**
- **Turbo**
- **Tutv**
- **tv.dfb.de**
- **TV2**
- **tv2.hu**
- **TV2Article**
- **TV2DK**
- **TV2DKBornholmPlay**
- **TV4**: tv4.se and tv4play.se
- **TV5MondePlus**: TV5MONDE+
- **TVA**
@ -966,10 +951,12 @@
- **twitch:vod**
- **twitter**
- **twitter:amplify**
- **twitter:broadcast**
- **twitter:card**
- **udemy**
- **udemy:course**
- **UDNEmbed**: 聯合影音
- **UFCArabia**
- **UFCTV**
- **UKTVPlay**
- **umg:de**: Universal Music Deutschland
@ -990,7 +977,6 @@
- **Vbox7**
- **VeeHD**
- **Veoh**
- **verystream**
- **Vesti**: Вести.Ru
- **Vevo**
- **VevoPlaylist**
@ -1010,7 +996,6 @@
- **videomore**
- **videomore:season**
- **videomore:video**
- **VideoPremium**
- **VideoPress**
- **Vidio**
- **VidLii**
@ -1020,8 +1005,8 @@
- **Vidzi**
- **vier**: vier.be and vijf.be
- **vier:videos**
- **ViewLift**
- **ViewLiftEmbed**
- **viewlift**
- **viewlift:embed**
- **Viidea**
- **viki**
- **viki:channel**

28
test/test_YoutubeDL.py
View File

@ -816,11 +816,15 @@ class TestYoutubeDL(unittest.TestCase):
'webpage_url': 'http://example.com',
}
def get_ids(params):
def get_downloaded_info_dicts(params):
ydl = YDL(params)
# make a copy because the dictionary can be modified
ydl.process_ie_result(playlist.copy())
return [int(v['id']) for v in ydl.downloaded_info_dicts]
# make a deep copy because the dictionary and nested entries
# can be modified
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({})
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'})
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):
# see https://github.com/ytdl-org/youtube-dl/issues/8227
ydl = YDL()

6
test/test_all_urls.py
View File

@ -123,12 +123,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
def test_yahoo_https(self):
# https://github.com/ytdl-org/youtube-dl/issues/2701
self.assertMatch(
'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
['Yahoo'])
def test_no_duplicated_ie_names(self):
name_accu = collections.defaultdict(list)
for ie in self.ies:

13
test/test_subtitles.py
View File

@ -26,7 +26,6 @@ from youtube_dl.extractor import (
ThePlatformIE,
ThePlatformFeedIE,
RTVEALaCartaIE,
FunnyOrDieIE,
DemocracynowIE,
)
@ -322,18 +321,6 @@ class TestRtveSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
class TestFunnyOrDieSubtitles(BaseTestSubtitles):
url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
IE = FunnyOrDieIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
class TestDemocracynowSubtitles(BaseTestSubtitles):
url = 'http://www.democracynow.org/shows/2015/7/3'
IE = DemocracynowIE

24
test/test_utils.py
View File

@ -19,6 +19,7 @@ from youtube_dl.utils import (
age_restricted,
args_to_str,
encode_base_n,
caesar,
clean_html,
date_from_str,
DateRange,
@ -69,6 +70,7 @@ from youtube_dl.utils import (
remove_start,
remove_end,
remove_quotes,
rot47,
shell_quote,
smuggle_url,
str_to_int,
@ -340,6 +342,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('July 15th, 2013'), '20130715')
self.assertEqual(unified_strdate('September 1st, 2013'), '20130901')
self.assertEqual(unified_strdate('Sep 2nd, 2013'), '20130902')
self.assertEqual(unified_strdate('November 3rd, 2019'), '20191103')
self.assertEqual(unified_strdate('October 23rd, 2005'), '20051023')
def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('December 21, 2010'), 1292889600)
@ -495,6 +499,12 @@ class TestUtil(unittest.TestCase):
def test_str_to_int(self):
self.assertEqual(str_to_int('123,456'), 123456)
self.assertEqual(str_to_int('123.456'), 123456)
self.assertEqual(str_to_int(523), 523)
# Python 3 has no long
if sys.version_info < (3, 0):
eval('self.assertEqual(str_to_int(123456L), 123456)')
self.assertEqual(str_to_int('noninteger'), None)
self.assertEqual(str_to_int([]), None)
def test_url_basename(self):
self.assertEqual(url_basename('http://foo.de/'), '')
@ -1367,6 +1377,20 @@ Line 1
self.assertRaises(ValueError, encode_base_n, 0, 70)
self.assertRaises(ValueError, encode_base_n, 0, 60, custom_table)
def test_caesar(self):
self.assertEqual(caesar('ace', 'abcdef', 2), 'cea')
self.assertEqual(caesar('cea', 'abcdef', -2), 'ace')
self.assertEqual(caesar('ace', 'abcdef', -2), 'eac')
self.assertEqual(caesar('eac', 'abcdef', 2), 'ace')
self.assertEqual(caesar('ace', 'abcdef', 0), 'ace')
self.assertEqual(caesar('xyz', 'abcdef', 2), 'xyz')
self.assertEqual(caesar('abc', 'acegik', 2), 'ebg')
self.assertEqual(caesar('ebg', 'acegik', -2), 'abc')
def test_rot47(self):
self.assertEqual(rot47('youtube-dl'), r'J@FEF36\5=')
self.assertEqual(rot47('YOUTUBE-DL'), r'*~&%&qt\s{')
def test_urshift(self):
self.assertEqual(urshift(3, 1), 1)
self.assertEqual(urshift(-3, 1), 2147483646)

6
youtube_dl/YoutubeDL.py
View File

@ -92,6 +92,7 @@ from .utils import (
YoutubeDLCookieJar,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
YoutubeDLRedirectHandler,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
@ -990,7 +991,7 @@ class YoutubeDL(object):
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_index': i + playliststart,
'playlist_index': playlistitems[i - 1] if playlistitems else i + playliststart,
'extractor': ie_result['extractor'],
'webpage_url': ie_result['webpage_url'],
'webpage_url_basename': url_basename(ie_result['webpage_url']),
@ -2343,6 +2344,7 @@ class YoutubeDL(object):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
redirect_handler = YoutubeDLRedirectHandler()
data_handler = compat_urllib_request_DataHandler()
# When passing our own FileHandler instance, build_opener won't add the
@ -2356,7 +2358,7 @@ class YoutubeDL(object):
file_handler.file_open = file_open
opener = compat_urllib_request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh, data_handler, file_handler)
proxy_handler, https_handler, cookie_processor, ydlh, redirect_handler, data_handler, file_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play

12
youtube_dl/compat.py
View File

@ -2754,6 +2754,17 @@ else:
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):
def compat_print(s):
from .utils import preferredencoding
@ -2998,6 +3009,7 @@ __all__ = [
'compat_os_name',
'compat_parse_qs',
'compat_print',
'compat_realpath',
'compat_setenv',
'compat_shlex_quote',
'compat_shlex_split',

4
youtube_dl/downloader/hls.py
View File

@ -64,7 +64,7 @@ class HlsFD(FragmentFD):
s = urlh.read().decode('utf-8', 'ignore')
if not self.can_download(s, info_dict):
if info_dict.get('extra_param_to_segment_url'):
if info_dict.get('extra_param_to_segment_url') or info_dict.get('_decryption_key_url'):
self.report_error('pycrypto not found. Please install it.')
return False
self.report_warning(
@ -169,7 +169,7 @@ class HlsFD(FragmentFD):
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
self._prepare_url(info_dict, decrypt_info['URI'])).read()
self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
self._append_fragment(ctx, frag_content)

20
youtube_dl/extractor/abc.py
View File

@ -110,17 +110,17 @@ class ABCIViewIE(InfoExtractor):
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
'url': 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00',
'md5': '67715ce3c78426b11ba167d875ac6abf',
'info_dict': {
'id': 'ZX9371A050S00',
'id': 'LE1927H001S00',
'ext': 'mp4',
'title': "Gaston's Birthday",
'series': "Ben And Holly's Little Kingdom",
'description': 'md5:f9de914d02f226968f598ac76f105bcf',
'upload_date': '20180604',
'uploader_id': 'abc4kids',
'timestamp': 1528140219,
'title': "Series 11 Ep 1",
'series': "Gruen",
'description': 'md5:52cc744ad35045baf6aded2ce7287f67',
'upload_date': '20190925',
'uploader_id': 'abc1',
'timestamp': 1569445289,
},
'params': {
'skip_download': True,
@ -148,7 +148,7 @@ class ABCIViewIE(InfoExtractor):
'hdnea': token,
})
for sd in ('sd', 'sd-low'):
for sd in ('720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:

79
youtube_dl/extractor/abcotvs.py
View File

@ -4,29 +4,30 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
int_or_none,
parse_iso8601,
try_get,
)
class ABCOTVSIE(InfoExtractor):
IE_NAME = 'abcotvs'
IE_DESC = 'ABC Owned Television Stations'
_VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472581',
'id': '472548',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates vintage synthesizers',
'title': 'East Bay museum celebrates synthesized music',
'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1421123075,
'timestamp': 1421118520,
'upload_date': '20150113',
'uploader': 'Jonathan Bloom',
},
'params': {
# m3u8 download
@ -37,39 +38,63 @@ class ABCOTVSIE(InfoExtractor):
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
{
'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/',
'only_matching': True,
},
]
_SITE_MAP = {
'6abc': 'wpvi',
'abc11': 'wtvd',
'abc13': 'ktrk',
'abc30': 'kfsn',
'abc7': 'kabc',
'abc7chicago': 'wls',
'abc7news': 'kgo',
'abc7ny': 'wabc',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
site, display_id, video_id = re.match(self._VALID_URL, url).groups()
display_id = display_id or video_id
station = self._SITE_MAP[site]
webpage = self._download_webpage(url, display_id)
data = self._download_json(
'https://api.abcotvs.com/v2/content', display_id, query={
'id': video_id,
'key': 'otv.web.%s.story' % station,
'station': station,
})['data']
video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
title = video.get('title') or video['linkText']
m3u8 = self._html_search_meta(
'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
formats = []
m3u8_url = video.get('m3u8')
if m3u8_url:
formats = self._extract_m3u8_formats(
video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False)
mp4_url = video.get('mp4')
if mp4_url:
formats.append({
'abr': 128,
'format_id': 'https',
'height': 360,
'url': mp4_url,
'width': 640,
})
self._sort_formats(formats)
title = self._og_search_title(webpage).strip()
description = self._og_search_description(webpage).strip()
thumbnail = self._og_search_thumbnail(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'rel="author">([^<]+)</a>',
webpage, 'uploader', default=None)
image = video.get('image') or {}
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])),
'thumbnail': dict_get(image, ('source', 'dynamicSource')),
'timestamp': int_or_none(video.get('date')),
'duration': int_or_none(video.get('length')),
'formats': formats,
}

95
youtube_dl/extractor/addanime.py
View File

@ -1,95 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
qualities,
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
_TESTS = [{
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
'info_dict': {
'id': '24MR3YO5SAS9',
'ext': 'mp4',
'description': 'One Piece 606',
'title': 'One Piece 606',
},
'skip': 'Video is gone',
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
try:
webpage = self._download_webpage(url, video_id)
except ExtractorError as ee:
if not isinstance(ee.cause, compat_HTTPError) or \
ee.cause.code != 503:
raise
redir_webpage = ee.cause.read().decode('utf-8')
action = self._search_regex(
r'<form id="challenge-form" action="([^"]+)"',
redir_webpage, 'Redirect form')
vc = self._search_regex(
r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
redir_webpage, 'redirect vc value')
av = re.search(
r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
redir_webpage)
if av is None:
raise ExtractorError('Cannot find redirect math task')
av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
parsed_url = compat_urllib_parse_urlparse(url)
av_val = av_res + len(parsed_url.netloc)
confirm_url = (
parsed_url.scheme + '://' + parsed_url.netloc
+ action + '?'
+ compat_urllib_parse_urlencode({
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
self._download_webpage(
confirm_url, video_id,
note='Confirming after redirect')
webpage = self._download_webpage(url, video_id)
FORMATS = ('normal', 'hq')
quality = qualities(FORMATS)
formats = []
for format_id in FORMATS:
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
video_url = self._search_regex(rex, webpage, 'video file URLx',
fatal=False)
if not video_url:
continue
formats.append({
'format_id': format_id,
'url': video_url,
'quality': quality(format_id),
})
self._sort_formats(formats)
video_title = self._og_search_title(webpage)
video_description = self._og_search_description(webpage)
return {
'_type': 'video',
'id': video_id,
'formats': formats,
'title': video_title,
'description': video_description
}

239
youtube_dl/extractor/adobetv.py
View File

@ -1,25 +1,119 @@
from __future__ import unicode_literals
import functools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_duration,
unified_strdate,
str_to_int,
int_or_none,
float_or_none,
int_or_none,
ISO639Utils,
determine_ext,
OnDemandPagedList,
parse_duration,
str_or_none,
str_to_int,
unified_strdate,
)
class AdobeTVBaseIE(InfoExtractor):
_API_BASE_URL = 'http://tv.adobe.com/api/v4/'
def _call_api(self, path, video_id, query, note=None):
return self._download_json(
'http://tv.adobe.com/api/v4/' + path,
video_id, note, query=query)['data']
def _parse_subtitles(self, video_data, url_key):
subtitles = {}
for translation in video_data.get('translations', []):
vtt_path = translation.get(url_key)
if not vtt_path:
continue
lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
subtitles.setdefault(lang, []).append({
'ext': 'vtt',
'url': vtt_path,
})
return subtitles
def _parse_video_data(self, video_data):
video_id = compat_str(video_data['id'])
title = video_data['title']
s3_extracted = False
formats = []
for source in video_data.get('videos', []):
source_url = source.get('url')
if not source_url:
continue
f = {
'format_id': source.get('quality_level'),
'fps': int_or_none(source.get('frame_rate')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
'width': int_or_none(source.get('width')),
'url': source_url,
}
original_filename = source.get('original_filename')
if original_filename:
if not (f.get('height') and f.get('width')):
mobj = re.search(r'_(\d+)x(\d+)', original_filename)
if mobj:
f.update({
'height': int(mobj.group(2)),
'width': int(mobj.group(1)),
})
if original_filename.startswith('s3://') and not s3_extracted:
formats.append({
'format_id': 'original',
'preference': 1,
'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
})
s3_extracted = True
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
'subtitles': self._parse_subtitles(video_data, 'vtt'),
}
class AdobeTVEmbedIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:embed'
_VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
_TEST = {
'url': 'https://tv.adobe.com/embed/22/4153',
'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
'info_dict': {
'id': '4153',
'ext': 'flv',
'title': 'Creating Graphics Optimized for BlackBerry',
'description': 'md5:eac6e8dced38bdaae51cd94447927459',
'thumbnail': r're:https?://.*\.jpg$',
'upload_date': '20091109',
'duration': 377,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._call_api(
'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
return self._parse_video_data(video_data)
class AdobeTVIE(AdobeTVBaseIE):
IE_NAME = 'adobetv'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
_TEST = {
@ -42,45 +136,33 @@ class AdobeTVIE(AdobeTVBaseIE):
if not language:
language = 'en'
video_data = self._download_json(
self._API_BASE_URL + 'episode/get/?language=%s&show_urlname=%s&urlname=%s&disclosure=standard' % (language, show_urlname, urlname),
urlname)['data'][0]
formats = [{
'url': source['url'],
'format_id': source.get('quality_level') or source['url'].split('-')[-1].split('.')[0] or None,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('video_data_rate')),
} for source in video_data['videos']]
self._sort_formats(formats)
return {
'id': compat_str(video_data['id']),
'title': video_data['title'],
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'upload_date': unified_strdate(video_data.get('start_date')),
'duration': parse_duration(video_data.get('duration')),
'view_count': str_to_int(video_data.get('playcount')),
'formats': formats,
}
video_data = self._call_api(
'episode/get', urlname, {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
'urlname': urlname,
})[0]
return self._parse_video_data(video_data)
class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
def _parse_page_data(self, page_data):
return [self.url_result(self._get_element_url(element_data)) for element_data in page_data]
_PAGE_SIZE = 25
def _extract_playlist_entries(self, url, display_id):
page = self._download_json(url, display_id)
entries = self._parse_page_data(page['data'])
for page_num in range(2, page['paging']['pages'] + 1):
entries.extend(self._parse_page_data(
self._download_json(url + '&page=%d' % page_num, display_id)['data']))
return entries
def _fetch_page(self, display_id, query, page):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, 'Download Page %d' % page):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):
return OnDemandPagedList(functools.partial(
self._fetch_page, display_id, query), self._PAGE_SIZE)
class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:show'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
_TEST = {
@ -92,26 +174,31 @@ class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
},
'playlist_mincount': 136,
}
def _get_element_url(self, element_data):
return element_data['urls'][0]
_RESOURCE = 'episode'
_process_data = AdobeTVBaseIE._parse_video_data
def _real_extract(self, url):
language, show_urlname = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
query = 'language=%s&show_urlname=%s' % (language, show_urlname)
query = {
'disclosure': 'standard',
'language': language,
'show_urlname': show_urlname,
}
show_data = self._download_json(self._API_BASE_URL + 'show/get/?%s' % query, show_urlname)['data'][0]
show_data = self._call_api(
'show/get', show_urlname, query)[0]
return self.playlist_result(
self._extract_playlist_entries(self._API_BASE_URL + 'episode/?%s' % query, show_urlname),
compat_str(show_data['id']),
show_data['show_name'],
show_data['show_description'])
self._extract_playlist_entries(show_urlname, query),
str_or_none(show_data.get('id')),
show_data.get('show_name'),
show_data.get('show_description'))
class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
IE_NAME = 'adobetv:channel'
_VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
_TEST = {
@ -121,24 +208,30 @@ class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
},
'playlist_mincount': 96,
}
_RESOURCE = 'show'
def _get_element_url(self, element_data):
return element_data['url']
def _process_data(self, show_data):
return self.url_result(
show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
def _real_extract(self, url):
language, channel_urlname, category_urlname = re.match(self._VALID_URL, url).groups()
if not language:
language = 'en'
query = 'language=%s&channel_urlname=%s' % (language, channel_urlname)
query = {
'channel_urlname': channel_urlname,
'language': language,
}
if category_urlname:
query += '&category_urlname=%s' % category_urlname
query['category_urlname'] = category_urlname
return self.playlist_result(
self._extract_playlist_entries(self._API_BASE_URL + 'show/?%s' % query, channel_urlname),
self._extract_playlist_entries(channel_urlname, query),
channel_urlname)
class AdobeTVVideoIE(InfoExtractor):
class AdobeTVVideoIE(AdobeTVBaseIE):
IE_NAME = 'adobetv:video'
_VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
_TEST = {
@ -160,38 +253,36 @@ class AdobeTVVideoIE(InfoExtractor):
video_data = self._parse_json(self._search_regex(
r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
title = video_data['title']
formats = [{
'format_id': '%s-%s' % (determine_ext(source['src']), source.get('height')),
'url': source['src'],
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('bitrate')),
} for source in video_data['sources']]
formats = []
sources = video_data.get('sources') or []
for source in sources:
source_src = source.get('src')
if not source_src:
continue
formats.append({
'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
'format_id': '-'.join(filter(None, [source.get('format'), source.get('label')])),
'height': int_or_none(source.get('height') or None),
'tbr': int_or_none(source.get('bitrate') or None),
'width': int_or_none(source.get('width') or None),
'url': source_src,
})
self._sort_formats(formats)
# For both metadata and downloaded files the duration varies among
# formats. I just pick the max one
duration = max(filter(None, [
float_or_none(source.get('duration'), scale=1000)
for source in video_data['sources']]))
subtitles = {}
for translation in video_data.get('translations', []):
lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
if lang_id not in subtitles:
subtitles[lang_id] = []
subtitles[lang_id].append({
'url': translation['vttPath'],
'ext': 'vtt',
})
for source in sources]))
return {
'id': video_id,
'formats': formats,
'title': video_data['title'],
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data['video'].get('poster'),
'thumbnail': video_data.get('video', {}).get('poster'),
'duration': duration,
'subtitles': subtitles,
'subtitles': self._parse_subtitles(video_data, 'vttPath'),
}

42
youtube_dl/extractor/americastestkitchen.py
View File

@ -5,6 +5,7 @@ from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
js_to_json,
try_get,
unified_strdate,
)
@ -13,22 +14,21 @@ from ..utils import (
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
'url': 'https://www.americastestkitchen.com/episode/582-weeknight-japanese-suppers',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '1_5g5zua6e',
'title': 'Summer Dinner Party',
'id': '5b400b9ee338f922cb06450c',
'title': 'Weeknight Japanese Suppers',
'ext': 'mp4',
'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1497285541,
'upload_date': '20170612',
'uploader_id': 'roger.metcalf@americastestkitchen.com',
'release_date': '20170617',
'description': 'md5:3d0c1a44bb3b27607ce82652db25b4a8',
'thumbnail': r're:^https?://',
'timestamp': 1523664000,
'upload_date': '20180414',
'release_date': '20180414',
'series': "America's Test Kitchen",
'season_number': 17,
'episode': 'Summer Dinner Party',
'episode_number': 24,
'season_number': 18,
'episode': 'Weeknight Japanese Suppers',
'episode_number': 15,
},
'params': {
'skip_download': True,
@ -47,7 +47,7 @@ class AmericasTestKitchenIE(InfoExtractor):
self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
webpage, 'initial context'),
video_id)
video_id, js_to_json)
ep_data = try_get(
video_data,
@ -55,17 +55,7 @@ class AmericasTestKitchenIE(InfoExtractor):
lambda x: x['videoDetail']['content']['data']), dict)
ep_meta = ep_data.get('full_video', {})
zype_id = ep_meta.get('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'
zype_id = ep_data.get('zype_id') or ep_meta['zype_id']
title = ep_data.get('title') or ep_meta.get('title')
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
@ -79,8 +69,8 @@ class AmericasTestKitchenIE(InfoExtractor):
return {
'_type': 'url_transparent',
'url': embed_url,
'ie_key': ie_key,
'url': 'https://player.zype.com/embed/%s.js?api_key=jZ9GUhRmxcPvX7M3SlfejB6Hle9jyHTdk2jVxG7wOHPLODgncEKVdPYBhuz9iWXQ' % zype_id,
'ie_key': 'Zype',
'title': title,
'description': description,
'thumbnail': thumbnail,

330
youtube_dl/extractor/ard.py
View File

@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
@ -22,7 +23,101 @@ from ..utils import (
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'
_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):
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):
# determine video id from url
m = re.match(self._VALID_URL, url)
@ -302,19 +309,20 @@ class ARDIE(InfoExtractor):
}
class ARDBetaMediathekIE(InfoExtractor):
_VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/[^/]+/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
class ARDBetaMediathekIE(ARDMediathekBaseIE):
_VALID_URL = r'https://(?:beta|www)\.ardmediathek\.de/(?P<client>[^/]+)/(?:player|live)/(?P<video_id>[a-zA-Z0-9]+)(?:/(?P<display_id>[^/?#]+))?'
_TESTS = [{
'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
'md5': 'dfdc87d2e7e09d073d5a80770a9ce88f',
'info_dict': {
'display_id': 'die-robuste-roswita',
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'title': 'Tatort: Die robuste Roswita',
'id': '70153354',
'title': 'Die robuste Roswita',
'description': r're:^Der Mord.*trüber ist als die Ilm.',
'duration': 5316,
'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard',
'upload_date': '20180826',
'thumbnail': 'https://img.ardmediathek.de/standard/00/70/15/33/90/-1852531467/16x9/960?mandant=ard',
'timestamp': 1577047500,
'upload_date': '20191222',
'ext': 'mp4',
},
}, {
@ -330,71 +338,69 @@ class ARDBetaMediathekIE(InfoExtractor):
video_id = mobj.group('video_id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')
data = self._parse_json(data_json, display_id)
res = {
'id': video_id,
'display_id': display_id,
player_page = self._download_json(
'https://api.ardmediathek.de/public-gateway',
display_id, data=json.dumps({
'query': '''{
playerPage(client:"%s", clipId: "%s") {
blockedByFsk
broadcastedOn
maturityContentRating
mediaCollection {
_duration
_geoblocked
_isLive
_mediaArray {
_mediaStreamArray {
_quality
_server
_stream
}
formats = []
subtitles = {}
geoblocked = False
for widget in data.values():
if widget.get('_geoblocked') is True:
geoblocked = True
if '_duration' in widget:
res['duration'] = int_or_none(widget['_duration'])
if 'clipTitle' in widget:
res['title'] = widget['clipTitle']
if '_previewImage' in widget:
res['thumbnail'] = widget['_previewImage']
if 'broadcastedOn' in widget:
res['timestamp'] = unified_timestamp(widget['broadcastedOn'])
if 'synopsis' in widget:
res['description'] = widget['synopsis']
subtitle_url = url_or_none(widget.get('_subtitleUrl'))
if subtitle_url:
subtitles.setdefault('de', []).append({
'ext': 'ttml',
'url': subtitle_url,
}
_previewImage
_subtitleUrl
_type
}
show {
title
}
synopsis
title
tracking {
atiCustomVars {
contentId
}
}
}
}''' % (mobj.group('client'), video_id),
}).encode(), headers={
'Content-Type': 'application/json'
})['data']['playerPage']
title = player_page['title']
content_id = str_or_none(try_get(
player_page, lambda x: x['tracking']['atiCustomVars']['contentId']))
media_collection = player_page.get('mediaCollection') or {}
if not media_collection and content_id:
media_collection = self._download_json(
'https://www.ardmediathek.de/play/media/' + content_id,
content_id, fatal=False) or {}
info = self._parse_media_info(
media_collection, content_id or video_id,
player_page.get('blockedByFsk'))
age_limit = None
description = player_page.get('synopsis')
maturity_content_rating = player_page.get('maturityContentRating')
if maturity_content_rating:
age_limit = int_or_none(maturity_content_rating.lstrip('FSK'))
if not age_limit and description:
age_limit = int_or_none(self._search_regex(
r'\(FSK\s*(\d+)\)\s*$', description, 'age limit', default=None))
info.update({
'age_limit': age_limit,
'display_id': display_id,
'title': title,
'description': description,
'timestamp': unified_timestamp(player_page.get('broadcastedOn')),
'series': try_get(player_page, lambda x: x['show']['title']),
})
if '_quality' in widget:
format_url = url_or_none(try_get(
widget, lambda x: x['_stream']['json'][0]))
if not format_url:
continue
ext = determine_ext(format_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
format_url + '?hdcore=3.11.0',
video_id, f4m_id='hds', fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls',
fatal=False))
else:
# HTTP formats are not available when geoblocked is True,
# other formats are fine though
if geoblocked:
continue
quality = str_or_none(widget.get('_quality'))
formats.append({
'format_id': ('http-' + quality) if quality else 'http',
'url': format_url,
'preference': 10, # Plain HTTP, that's nice
})
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 res
return info

36
youtube_dl/extractor/azmedien.py
View File

@ -47,39 +47,19 @@ class AZMedienIE(InfoExtractor):
'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1',
'only_matching': True
}]
_API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d'
_PARTNER_ID = '1719221'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
video_id = mobj.group('id')
entry_id = mobj.group('kaltura_id')
host, display_id, article_id, entry_id = re.match(self._VALID_URL, url).groups()
if not entry_id:
api_url = 'https://www.%s/api/pub/gql/%s' % (host, host.split('.')[0])
payload = {
'query': '''query VideoContext($articleId: ID!) {
article: node(id: $articleId) {
... on Article {
mainAssetRelation {
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']
entry_id = self._download_json(
self._API_TEMPL % (host, host.split('.')[0]), display_id, query={
'variables': json.dumps({
'contextId': 'NewsArticle:' + article_id,
}),
})['data']['context']['mainAsset']['video']['kaltura']['kalturaId']
return self.url_result(
'kaltura:%s:%s' % (self._PARTNER_ID, entry_id),

142
youtube_dl/extractor/bambuser.py
View File

@ -1,142 +0,0 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
sanitized_Request,
urlencode_postdata,
)
class BambuserIE(InfoExtractor):
IE_NAME = 'bambuser'
_VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
_API_KEY = '005f64509e19a868399060af746a00aa'
_LOGIN_URL = 'https://bambuser.com/user'
_NETRC_MACHINE = 'bambuser'
_TEST = {
'url': 'http://bambuser.com/v/4050584',
# MD5 seems to be flaky, see https://travis-ci.org/ytdl-org/youtube-dl/jobs/14051016#L388
# 'md5': 'fba8f7693e48fd4e8641b3fd5539a641',
'info_dict': {
'id': '4050584',
'ext': 'flv',
'title': 'Education engineering days - lightning talks',
'duration': 3741,
'uploader': 'pixelversity',
'uploader_id': '344706',
'timestamp': 1382976692,
'upload_date': '20131028',
'view_count': int,
},
'params': {
# It doesn't respect the 'Range' header, it would download the whole video
# caused the travis builds to fail: https://travis-ci.org/ytdl-org/youtube-dl/jobs/14493845#L59
'skip_download': True,
},
}
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_form = {
'form_id': 'user_login',
'op': 'Log in',
'name': username,
'pass': password,
}
request = sanitized_Request(
self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
request, None, 'Logging in')
login_error = self._html_search_regex(
r'(?s)<div class="messages error">(.+?)</div>',
response, 'login error', default=None)
if login_error:
raise ExtractorError(
'Unable to login: %s' % login_error, expected=True)
def _real_initialize(self):
self._login()
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
% (self._API_KEY, video_id), video_id)
error = info.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
result = info['result']
return {
'id': video_id,
'title': result['title'],
'url': result['url'],
'thumbnail': result.get('preview'),
'duration': int_or_none(result.get('length')),
'uploader': result.get('username'),
'uploader_id': compat_str(result.get('owner', {}).get('uid')),
'timestamp': int_or_none(result.get('created')),
'fps': float_or_none(result.get('framerate')),
'view_count': int_or_none(result.get('views_total')),
'comment_count': int_or_none(result.get('comment_count')),
}
class BambuserChannelIE(InfoExtractor):
IE_NAME = 'bambuser:channel'
_VALID_URL = r'https?://bambuser\.com/channel/(?P<user>.*?)(?:/|#|\?|$)'
# The maximum number we can get with each request
_STEP = 50
_TEST = {
'url': 'http://bambuser.com/channel/pixelversity',
'info_dict': {
'title': 'pixelversity',
},
'playlist_mincount': 60,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user = mobj.group('user')
urls = []
last_id = ''
for i in itertools.count(1):
req_url = (
'http://bambuser.com/xhr-api/index.php?username={user}'
'&sort=created&access_mode=0%2C1%2C2&limit={count}'
'&method=broadcast&format=json&vid_older_than={last}'
).format(user=user, count=self._STEP, last=last_id)
req = sanitized_Request(req_url)
# Without setting this header, we wouldn't get any result
req.add_header('Referer', 'http://bambuser.com/channel/%s' % user)
data = self._download_json(
req, user, 'Downloading page %d' % i)
results = data['result']
if not results:
break
last_id = results[-1]['vid']
urls.extend(self.url_result(v['page'], 'Bambuser') for v in results)
return {
'_type': 'playlist',
'title': user,
'entries': urls,
}

4
youtube_dl/extractor/bellmedia.py
View File

@ -22,7 +22,8 @@ class BellMediaIE(InfoExtractor):
bravo|
mtv|
space|
etalk
etalk|
marilyn
)\.ca|
much\.com
)/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
@ -70,6 +71,7 @@ class BellMediaIE(InfoExtractor):
'animalplanet': 'aniplan',
'etalk': 'ctv',
'bnnbloomberg': 'bnn',
'marilyn': 'ctv_marilyn',
}
def _real_extract(self, url):

33
youtube_dl/extractor/bilibili.py
View File

@ -24,7 +24,18 @@ from ..utils import (
class BiliBiliIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|bangumi\.|)bilibili\.(?:tv|com)/(?:video/av|anime/(?P<anime_id>\d+)/play#)(?P<id>\d+)'
_VALID_URL = r'''(?x)
https?://
(?:(?:www|bangumi)\.)?
bilibili\.(?:tv|com)/
(?:
(?:
video/[aA][vV]|
anime/(?P<anime_id>\d+)/play\#
)(?P<id_bv>\d+)|
video/[bB][vV](?P<id>[^/?#&]+)
)
'''
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
@ -92,6 +103,10 @@ class BiliBiliIE(InfoExtractor):
'skip_download': True, # Test metadata only
},
}]
}, {
# new BV video id format
'url': 'https://www.bilibili.com/video/BV1JE411F741',
'only_matching': True,
}]
_APP_KEY = 'iVGUTjsxvpLeuDCf'
@ -109,7 +124,7 @@ class BiliBiliIE(InfoExtractor):
url, smuggled_data = unsmuggle_url(url, {})
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = mobj.group('id') or mobj.group('id_bv')
anime_id = mobj.group('anime_id')
webpage = self._download_webpage(url, video_id)
@ -419,3 +434,17 @@ class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
entries, am_id, album_title, album_data.get('intro'))
return self.playlist_result(entries, am_id)
class BiliBiliPlayerIE(InfoExtractor):
_VALID_URL = r'https?://player\.bilibili\.com/player\.html\?.*?\baid=(?P<id>\d+)'
_TEST = {
'url': 'http://player.bilibili.com/player.html?aid=92494333&cid=157926707&page=1',
'only_matching': True,
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'http://www.bilibili.tv/video/av%s/' % video_id,
ie=BiliBiliIE.ie_key(), video_id=video_id)

7
youtube_dl/extractor/bitchute.py
View File

@ -7,6 +7,7 @@ import re
from .common import InfoExtractor
from ..utils import (
orderedSet,
unified_strdate,
urlencode_postdata,
)
@ -23,6 +24,7 @@ class BitChuteIE(InfoExtractor):
'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Victoria X Rave',
'upload_date': '20170813',
},
}, {
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
@ -74,12 +76,17 @@ class BitChuteIE(InfoExtractor):
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>'),
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._search_regex(
r'class=["\']video-publish-date[^>]+>[^<]+ at \d+:\d+ UTC on (.+?)\.',
webpage, 'upload date', fatal=False))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
'formats': formats,
}

26
youtube_dl/extractor/brightcove.py
View File

@ -586,6 +586,12 @@ class BrightcoveNewIE(AdobePassIE):
account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups()
policy_key_id = '%s_%s' % (account_id, player_id)
policy_key = self._downloader.cache.load('brightcove', policy_key_id)
policy_key_extracted = False
store_pk = lambda x: self._downloader.cache.store('brightcove', policy_key_id, x)
def extract_policy_key():
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
@ -605,24 +611,36 @@ class BrightcoveNewIE(AdobePassIE):
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
store_pk(policy_key)
return policy_key
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/%ss/%s' % (account_id, content_type, video_id)
headers = {
'Accept': 'application/json;pk=%s' % policy_key,
}
headers = {}
referrer = smuggled_data.get('referrer')
if referrer:
headers.update({
'Referer': referrer,
'Origin': re.search(r'https?://[^/]+', referrer).group(0),
})
for _ in range(2):
if not policy_key:
policy_key = extract_policy_key()
policy_key_extracted = True
headers['Accept'] = 'application/json;pk=%s' % policy_key
try:
json_data = self._download_json(api_url, video_id, headers=headers)
break
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)
elif json_data.get('error_code') == 'INVALID_POLICY_KEY' and not policy_key_extracted:
policy_key = None
store_pk(None)
continue
raise ExtractorError(message, expected=True)
raise

28
youtube_dl/extractor/businessinsider.py
View File

@ -9,21 +9,26 @@ class BusinessInsiderIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
'md5': 'ffed3e1e12a6f950aa2f7d83851b497a',
'info_dict': {
'id': 'hZRllCfw',
'id': 'cjGDb0X9',
'ext': 'mp4',
'title': "Here's how much radiation you're exposed to in everyday life",
'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd',
'upload_date': '20170709',
'timestamp': 1499606400,
},
'params': {
'skip_download': True,
'title': "Bananas give you more radiation exposure than living next to a nuclear power plant",
'description': 'md5:0175a3baf200dd8fa658f94cade841b3',
'upload_date': '20160611',
'timestamp': 1465675620,
},
}, {
'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',
'only_matching': True,
@ -35,7 +40,8 @@ class BusinessInsiderIE(InfoExtractor):
jwplatform_id = self._search_regex(
(r'data-media-id=["\']([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')
return self.url_result(
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),

83
youtube_dl/extractor/canvas.py
View File

@ -13,6 +13,8 @@ from ..utils import (
int_or_none,
merge_dicts,
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>[^/?#&]+)'
_TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '90139b746a0a9bd7bb631283f6e2a64e',
'md5': '68993eda72ef62386a15ea2cf3c93107',
'info_dict': {
'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',
'description': 'md5:1db3f5dc4c7109c821261e7512975be7',
'description': 'Nachtwacht: De Greystook',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1468.03,
'duration': 1468.04,
},
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
}, {
@ -39,23 +41,45 @@ class CanvasIE(InfoExtractor):
'HLS': 'm3u8_native',
'HLS_AES': 'm3u8',
}
_REST_API_BASE = 'https://media-services-public.vrt.be/vualto-video-aggregator-web/rest/external/v1'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
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(
'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']
description = data.get('description')
formats = []
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:
continue
format_type = format_type.upper()
if format_type in self._HLS_ENTRY_PROTOCOLS_MAP:
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type],
@ -134,20 +158,20 @@ class CanvasEenIE(InfoExtractor):
},
'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': {
'id': 'mz-ast-11a587f8-b921-4266-82e2-0bce3e80d07f',
'display_id': 'herbekijk-sorry-voor-alles',
'id': 'md-ast-3a24ced2-64d7-44fb-b4ed-ed1aafbf90b8',
'display_id': 'emma-pakt-thilly-aan',
'ext': 'mp4',
'title': 'Herbekijk Sorry voor alles',
'description': 'md5:8bb2805df8164e5eb95d6a7a29dc0dd3',
'title': 'Emma pakt Thilly aan',
'description': 'md5:c5c9b572388a99b2690030afa3f3bad7',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 3788.06,
'duration': 118.24,
},
'params': {
'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',
'only_matching': True,
@ -183,19 +207,44 @@ class VrtNUIE(GigyaBaseIE):
IE_DESC = 'VrtNU.be'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
# Available via old API endpoint
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
'info_dict': {
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
'ext': 'flv',
'ext': 'mp4',
'title': 'De zwarte weduwe',
'description': 'md5:d90c21dced7db869a85db89a623998d4',
'description': 'md5:db1227b0f318c849ba5eab1fef895ee4',
'duration': 1457.04,
'thumbnail': r're:^https?://.*\.jpg$',
'season': '1',
'season': 'Season 1',
'season_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'
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'

46
youtube_dl/extractor/cbc.py
View File

@ -1,8 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import json
import re
from xml.sax.saxutils import escape
from .common import InfoExtractor
from ..compat import (
@ -216,6 +218,29 @@ class CBCWatchBaseIE(InfoExtractor):
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
_GEO_COUNTRIES = ['CA']
_LOGIN_URL = 'https://api.loginradius.com/identity/v2/auth/login'
_TOKEN_URL = 'https://cloud-api.loginradius.com/sso/jwt/api/token'
_API_KEY = '3f4beddd-2061-49b0-ae80-6f1f2ed65b37'
_NETRC_MACHINE = 'cbcwatch'
def _signature(self, email, password):
data = json.dumps({
'email': email,
'password': password,
}).encode()
headers = {'content-type': 'application/json'}
query = {'apikey': self._API_KEY}
resp = self._download_json(self._LOGIN_URL, None, data=data, headers=headers, query=query)
access_token = resp['access_token']
# token
query = {
'access_token': access_token,
'apikey': self._API_KEY,
'jwtapp': 'jwt',
}
resp = self._download_json(self._TOKEN_URL, None, headers=headers, query=query)
return resp['signature']
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
@ -239,7 +264,8 @@ class CBCWatchBaseIE(InfoExtractor):
def _real_initialize(self):
if self._valid_device_token():
return
device = self._downloader.cache.load('cbcwatch', 'device') or {}
device = self._downloader.cache.load(
'cbcwatch', self._cache_device_key()) or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if self._valid_device_token():
return
@ -248,16 +274,30 @@ class CBCWatchBaseIE(InfoExtractor):
def _valid_device_token(self):
return self._device_id and self._device_token
def _cache_device_key(self):
email, _ = self._get_login_info()
return '%s_device' % hashlib.sha256(email.encode()).hexdigest() if email else 'device'
def _register_device(self):
self._device_id = self._device_token = None
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, 'Acquiring device token',
data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
email, password = self._get_login_info()
if email and password:
signature = self._signature(email, password)
data = '<login><token>{0}</token><device><deviceId>{1}</deviceId><type>web</type></device></login>'.format(
escape(signature), escape(self._device_id)).encode()
url = self._API_BASE_URL + 'device/login'
result = self._download_xml(
url, None, data=data,
headers={'content-type': 'application/xml'})
self._device_token = xpath_text(result, 'token', fatal=True)
else:
self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
'cbcwatch', 'device', {
'cbcwatch', self._cache_device_key(), {
'id': self._device_id,
'token': self._device_token,
})

24
youtube_dl/extractor/channel9.py
View File

@ -32,7 +32,7 @@ class Channel9IE(InfoExtractor):
'upload_date': '20130828',
'session_code': 'KOS002',
'session_room': 'Arena 1A',
'session_speakers': ['Andrew Coates', 'Brady Gaster', 'Mads Kristensen', 'Ed Blankenship', 'Patrick Klug'],
'session_speakers': 'count:5',
},
}, {
'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
@ -64,15 +64,15 @@ class Channel9IE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
'info_dict': {
'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
'title': 'Channel 9',
},
'playlist_mincount': 100,
}, {
'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
'info_dict': {
'id': 'Events/DEVintersection/DEVintersection-2016',
'title': 'DEVintersection 2016 Orlando Sessions',
},
'playlist_mincount': 14,
}, {
'url': 'https://channel9.msdn.com/Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b/RSS',
'only_matching': True,
}, {
'url': 'https://channel9.msdn.com/Events/Speakers/scott-hanselman/RSS?UrlSafeName=scott-hanselman',
@ -112,11 +112,11 @@ class Channel9IE(InfoExtractor):
episode_data), content_path)
content_id = episode_data['contentId']
is_session = '/Sessions(' in episode_data['api']
content_url = 'https://channel9.msdn.com/odata' + episode_data['api']
content_url = 'https://channel9.msdn.com/odata' + episode_data['api'] + '?$select=Captions,CommentCount,MediaLengthInSeconds,PublishedDate,Rating,RatingCount,Title,VideoMP4High,VideoMP4Low,VideoMP4Medium,VideoPlayerPreviewImage,VideoWMV,VideoWMVHQ,Views,'
if is_session:
content_url += '?$expand=Speakers'
content_url += 'Code,Description,Room,Slides,Speakers,ZipFile&$expand=Speakers'
else:
content_url += '?$expand=Authors'
content_url += 'Authors,Body&$expand=Authors'
content_data = self._download_json(content_url, content_id)
title = content_data['Title']
@ -210,7 +210,7 @@ class Channel9IE(InfoExtractor):
'id': content_id,
'title': title,
'description': clean_html(content_data.get('Description') or content_data.get('Body')),
'thumbnail': content_data.get('Thumbnail') or content_data.get('VideoPlayerPreviewImage'),
'thumbnail': content_data.get('VideoPlayerPreviewImage'),
'duration': int_or_none(content_data.get('MediaLengthInSeconds')),
'timestamp': parse_iso8601(content_data.get('PublishedDate')),
'avg_rating': int_or_none(content_data.get('Rating')),

38
youtube_dl/extractor/chaturbate.py
View File

@ -3,7 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
from ..utils import (
ExtractorError,
lowercase_escape,
url_or_none,
)
class ChaturbateIE(InfoExtractor):
@ -38,12 +42,31 @@ class ChaturbateIE(InfoExtractor):
'https://chaturbate.com/%s/' % video_id, video_id,
headers=self.geo_verification_headers())
m3u8_urls = []
found_m3u8_urls = []
data = self._parse_json(
self._search_regex(
r'initialRoomDossier\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'data', default='{}', group='value'),
video_id, transform_source=lowercase_escape, fatal=False)
if data:
m3u8_url = url_or_none(data.get('hls_source'))
if m3u8_url:
found_m3u8_urls.append(m3u8_url)
if not found_m3u8_urls:
for m in re.finditer(
r'(\\u002[27])(?P<url>http.+?\.m3u8.*?)\1', webpage):
found_m3u8_urls.append(lowercase_escape(m.group('url')))
if not found_m3u8_urls:
for m in re.finditer(
r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
m3u8_fast_url, m3u8_no_fast_url = m.group('url'), m.group(
'url').replace('_fast', '')
found_m3u8_urls.append(m.group('url'))
m3u8_urls = []
for found_m3u8_url in found_m3u8_urls:
m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '')
for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
if m3u8_url not in m3u8_urls:
m3u8_urls.append(m3u8_url)
@ -63,7 +86,12 @@ class ChaturbateIE(InfoExtractor):
formats = []
for m3u8_url in m3u8_urls:
m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow'
for known_id in ('fast', 'slow'):
if '_%s' % known_id in m3u8_url:
m3u8_id = known_id
break
else:
m3u8_id = None
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4',
# ffmpeg skips segments for fast m3u8

29
youtube_dl/extractor/cloudflarestream.py
View File

@ -1,20 +1,24 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
class CloudflareStreamIE(InfoExtractor):
_DOMAIN_RE = r'(?:cloudflarestream\.com|(?:videodelivery|bytehighway)\.net)'
_EMBED_RE = r'embed\.%s/embed/[^/]+\.js\?.*?\bvideo=' % _DOMAIN_RE
_ID_RE = r'[\da-f]{32}|[\w-]+\.[\w-]+\.[\w-]+'
_VALID_URL = r'''(?x)
https?://
(?:
(?:watch\.)?(?:cloudflarestream\.com|videodelivery\.net)/|
embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=
(?:watch\.)?%s/|
%s
)
(?P<id>[\da-f]+)
'''
(?P<id>%s)
''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE)
_TESTS = [{
'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
'info_dict': {
@ -41,23 +45,28 @@ class CloudflareStreamIE(InfoExtractor):
return [
mobj.group('url')
for mobj in re.finditer(
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE),
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
base_url = 'https://%s/%s/' % (domain, video_id)
if '.' in video_id:
video_id = self._parse_json(base64.urlsafe_b64decode(
video_id.split('.')[1]), video_id)['sub']
manifest_base_url = base_url + 'manifest/video.'
formats = self._extract_m3u8_formats(
'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id,
video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False)
manifest_base_url + 'm3u8', video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
formats.extend(self._extract_mpd_formats(
'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id,
video_id, mpd_id='dash', fatal=False))
manifest_base_url + 'mpd', video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats)
return {
'id': video_id,
'title': video_id,
'thumbnail': base_url + 'thumbnails/thumbnail.jpg',
'formats': formats,
}

74
youtube_dl/extractor/comcarcoff.py
View File

@ -1,74 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class ComCarCoffIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
_TESTS = [{
'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
'info_dict': {
'id': '2494164',
'ext': 'mp4',
'upload_date': '20141127',
'timestamp': 1417107600,
'duration': 1232,
'title': 'Happy Thanksgiving Miranda',
'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
},
'params': {
'skip_download': 'requires ffmpeg',
}
}]
def _real_extract(self, url):
display_id = self._match_id(url)
if not display_id:
display_id = 'comediansincarsgettingcoffee.com'
webpage = self._download_webpage(url, display_id)
full_data = self._parse_json(
self._search_regex(
r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
display_id)['videoData']
display_id = full_data['activeVideo']['video']
video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
video_id = compat_str(video_data['mediaId'])
title = video_data['title']
formats = self._extract_m3u8_formats(
video_data['mediaUrl'], video_id, 'mp4')
self._sort_formats(formats)
thumbnails = [{
'url': video_data['images']['thumb'],
}, {
'url': video_data['images']['poster'],
}]
timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
video_data.get('pubDate'))
duration = int_or_none(video_data.get('durationSeconds')) or parse_duration(
video_data.get('duration'))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': video_data.get('description'),
'timestamp': timestamp,
'duration': duration,
'thumbnails': thumbnails,
'formats': formats,
'season_number': int_or_none(video_data.get('season')),
'episode_number': int_or_none(video_data.get('episode')),
'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
}

32
youtube_dl/extractor/common.py
View File

@ -1455,14 +1455,14 @@ class InfoExtractor(object):
def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None,
transform_source=lambda s: fix_xml_ampersands(s).strip(),
fatal=True, m3u8_id=None):
fatal=True, m3u8_id=None, data=None, headers={}, query={}):
manifest = self._download_xml(
manifest_url, video_id, 'Downloading f4m manifest',
'Unable to download f4m manifest',
# Some manifests may be malformed, e.g. prosiebensat1 generated manifests
# (see https://github.com/ytdl-org/youtube-dl/issues/6215#issuecomment-121704244)
transform_source=transform_source,
fatal=fatal)
fatal=fatal, data=data, headers=headers, query=query)
if manifest is False:
return []
@ -1586,12 +1586,13 @@ class InfoExtractor(object):
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
entry_protocol='m3u8', preference=None,
m3u8_id=None, note=None, errnote=None,
fatal=True, live=False):
fatal=True, live=False, data=None, headers={},
query={}):
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal)
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
return []
@ -1765,6 +1766,19 @@ class InfoExtractor(object):
# the same GROUP-ID
f['acodec'] = 'none'
formats.append(f)
# for DailyMotion
progressive_uri = last_stream_inf.get('PROGRESSIVE-URI')
if progressive_uri:
http_f = f.copy()
del http_f['manifest_url']
http_f.update({
'format_id': f['format_id'].replace('hls-', 'http-'),
'protocol': 'http',
'url': progressive_uri,
})
formats.append(http_f)
last_stream_inf = {}
return formats
@ -2009,12 +2023,12 @@ class InfoExtractor(object):
})
return entries
def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}):
def _extract_mpd_formats(self, mpd_url, video_id, mpd_id=None, note=None, errnote=None, fatal=True, formats_dict={}, data=None, headers={}, query={}):
res = self._download_xml_handle(
mpd_url, video_id,
note=note or 'Downloading MPD manifest',
errnote=errnote or 'Failed to download MPD manifest',
fatal=fatal)
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
return []
mpd_doc, urlh = res
@ -2317,12 +2331,12 @@ class InfoExtractor(object):
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True):
def _extract_ism_formats(self, ism_url, video_id, ism_id=None, note=None, errnote=None, fatal=True, data=None, headers={}, query={}):
res = self._download_xml_handle(
ism_url, video_id,
note=note or 'Downloading ISM manifest',
errnote=errnote or 'Failed to download ISM manifest',
fatal=fatal)
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
return []
ism_doc, urlh = res
@ -2689,7 +2703,7 @@ class InfoExtractor(object):
entry = {
'id': this_video_id,
'title': unescapeHTML(video_data['title'] if require_title else video_data.get('title')),
'description': video_data.get('description'),
'description': clean_html(video_data.get('description')),
'thumbnail': urljoin(base_url, self._proto_relative_url(video_data.get('image'))),
'timestamp': int_or_none(video_data.get('pubdate')),
'duration': float_or_none(jwplayer_data.get('duration') or video_data.get('duration')),

169
youtube_dl/extractor/corus.py
View File

@ -4,7 +4,12 @@ from __future__ import unicode_literals
import re
from .theplatform import ThePlatformFeedIE
from ..utils import int_or_none
from ..utils import (
dict_get,
ExtractorError,
float_or_none,
int_or_none,
)
class CorusIE(ThePlatformFeedIE):
@ -12,24 +17,49 @@ class CorusIE(ThePlatformFeedIE):
https?://
(?:www\.)?
(?P<domain>
(?:globaltv|etcanada)\.com|
(?:hgtv|foodnetwork|slice|history|showcase|bigbrothercanada)\.ca
(?:
globaltv|
etcanada|
seriesplus|
wnetwork|
ytv
)\.com|
(?:
hgtv|
foodnetwork|
slice|
history|
showcase|
bigbrothercanada|
abcspark|
disney(?:channel|lachaine)
)\.ca
)
/(?:[^/]+/)*
(?:
video\.html\?.*?\bv=|
videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)?
)
(?P<id>
[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}|
(?:[A-Z]{4})?\d{12,20}
)
/(?:video/(?:[^/]+/)?|(?:[^/]+/)+(?:videos/[a-z0-9-]+-|video\.html\?.*?\bv=))
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://www.hgtv.ca/shows/bryan-inc/videos/movie-night-popcorn-with-bryan-870923331648/',
'md5': '05dcbca777bf1e58c2acbb57168ad3a6',
'info_dict': {
'id': '870923331648',
'ext': 'mp4',
'title': 'Movie Night Popcorn with Bryan',
'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
'uploader': 'SHWM-NEW',
'upload_date': '20170206',
'timestamp': 1486392197,
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
'expected_warnings': ['Failed to parse JSON'],
}, {
'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
'only_matching': True,
@ -48,58 +78,83 @@ class CorusIE(ThePlatformFeedIE):
}, {
'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/',
'only_matching': True
}, {
'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/',
'only_matching': True
}, {
'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/',
'only_matching': True
}]
_TP_FEEDS = {
'globaltv': {
'feed_id': 'ChQqrem0lNUp',
'account_id': 2269680845,
},
'etcanada': {
'feed_id': 'ChQqrem0lNUp',
'account_id': 2269680845,
},
'hgtv': {
'feed_id': 'L0BMHXi2no43',
'account_id': 2414428465,
},
'foodnetwork': {
'feed_id': 'ukK8o58zbRmJ',
'account_id': 2414429569,
},
'slice': {
'feed_id': '5tUJLgV2YNJ5',
'account_id': 2414427935,
},
'history': {
'feed_id': 'tQFx_TyyEq4J',
'account_id': 2369613659,
},
'showcase': {
'feed_id': '9H6qyshBZU3E',
'account_id': 2414426607,
},
'bigbrothercanada': {
'feed_id': 'ChQqrem0lNUp',
'account_id': 2269680845,
},
_GEO_BYPASS = False
_SITE_MAP = {
'globaltv': 'series',
'etcanada': 'series',
'foodnetwork': 'food',
'bigbrothercanada': 'series',
'disneychannel': 'disneyen',
'disneylachaine': 'disneyfr',
}
def _real_extract(self, url):
domain, video_id = re.match(self._VALID_URL, url).groups()
feed_info = self._TP_FEEDS[domain.split('.')[0]]
return self._extract_feed_info('dtjsEC', feed_info['feed_id'], 'byId=' + video_id, video_id, lambda e: {
'episode_number': int_or_none(e.get('pl1$episode')),
'season_number': int_or_none(e.get('pl1$season')),
'series': e.get('pl1$show'),
}, {
'HLS': {
'manifest': 'm3u',
},
'DesktopHLS Default': {
'manifest': 'm3u',
},
'MP4 MBR': {
'manifest': 'm3u',
},
}, feed_info['account_id'])
site = domain.split('.')[0]
path = self._SITE_MAP.get(site, site)
if path != 'series':
path = 'migration/' + path
video = self._download_json(
'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path,
video_id, query={'byId': video_id},
headers={'Accept': 'application/json'})[0]
title = video['title']
formats = []
for source in video.get('sources', []):
smil_url = source.get('file')
if not smil_url:
continue
source_type = source.get('type')
note = 'Downloading%s smil file' % (' ' + source_type if source_type else '')
resp = self._download_webpage(
smil_url, video_id, note, fatal=False,
headers=self.geo_verification_headers())
if not resp:
continue
error = self._parse_json(resp, video_id, fatal=False)
if error:
if error.get('exception') == 'GeoLocationBlocked':
self.raise_geo_restricted(countries=['CA'])
raise ExtractorError(error['description'])
smil = self._parse_xml(resp, video_id, fatal=False)
if smil is None:
continue
namespace = self._parse_smil_namespace(smil)
formats.extend(self._parse_smil_formats(
smil, smil_url, video_id, namespace))
if not formats and video.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
subtitles = {}
for track in video.get('tracks', []):
track_url = track.get('file')
if not track_url:
continue
lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en'
subtitles.setdefault(lang, []).append({'url': track_url})
metadata = video.get('metadata') or {}
get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number'))
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')),
'description': video.get('description'),
'timestamp': int_or_none(video.get('availableDate'), 1000),
'subtitles': subtitles,
'duration': float_or_none(metadata.get('duration')),
'series': dict_get(video, ('show', 'pl1$show')),
'season_number': get_number('season'),
'episode_number': get_number('episode'),
}

557
youtube_dl/extractor/dailymotion.py
View File

@ -1,50 +1,93 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import functools
import hashlib
import itertools
import json
import random
import re
import string
from .common import InfoExtractor
from ..compat import compat_struct_pack
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
error_to_compat_str,
age_restricted,
clean_html,
ExtractorError,
int_or_none,
mimetype2ext,
OnDemandPagedList,
parse_iso8601,
sanitized_Request,
str_to_int,
try_get,
unescapeHTML,
update_url_query,
url_or_none,
urlencode_postdata,
)
class DailymotionBaseInfoExtractor(InfoExtractor):
_FAMILY_FILTER = None
_HEADERS = {
'Content-Type': 'application/json',
'Origin': 'https://www.dailymotion.com',
}
_NETRC_MACHINE = 'dailymotion'
def _get_dailymotion_cookies(self):
return self._get_cookies('https://www.dailymotion.com/')
@staticmethod
def _build_request(url):
"""Build a request with the family filter disabled"""
request = sanitized_Request(url)
request.add_header('Cookie', 'family_filter=off; ff=off')
return request
def _get_cookie_value(cookies, name):
cookie = cookies.get('name')
if cookie:
return cookie.value
def _download_webpage_handle_no_ff(self, url, *args, **kwargs):
request = self._build_request(url)
return self._download_webpage_handle(request, *args, **kwargs)
def _set_dailymotion_cookie(self, name, value):
self._set_cookie('www.dailymotion.com', name, value)
def _download_webpage_no_ff(self, url, *args, **kwargs):
request = self._build_request(url)
return self._download_webpage(request, *args, **kwargs)
def _real_initialize(self):
cookies = self._get_dailymotion_cookies()
ff = self._get_cookie_value(cookies, 'ff')
self._FAMILY_FILTER = ff == 'on' if ff else age_restricted(18, self._downloader.params.get('age_limit'))
self._set_dailymotion_cookie('ff', 'on' if self._FAMILY_FILTER else 'off')
def _call_api(self, object_type, xid, object_fields, note, filter_extra=None):
if not self._HEADERS.get('Authorization'):
cookies = self._get_dailymotion_cookies()
token = self._get_cookie_value(cookies, 'access_token') or self._get_cookie_value(cookies, 'client_token')
if not token:
data = {
'client_id': 'f1a362d288c1b98099c7',
'client_secret': 'eea605b96e01c796ff369935357eca920c5da4c5',
}
username, password = self._get_login_info()
if username:
data.update({
'grant_type': 'password',
'password': password,
'username': username,
})
else:
data['grant_type'] = 'client_credentials'
try:
token = self._download_json(
'https://graphql.api.dailymotion.com/oauth/token',
None, 'Downloading Access Token',
data=urlencode_postdata(data))['access_token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
raise ExtractorError(self._parse_json(
e.cause.read().decode(), xid)['error_description'], expected=True)
raise
self._set_dailymotion_cookie('access_token' if username else 'client_token', token)
self._HEADERS['Authorization'] = 'Bearer ' + token
resp = self._download_json(
'https://graphql.api.dailymotion.com/', xid, note, data=json.dumps({
'query': '''{
%s(xid: "%s"%s) {
%s
}
}''' % (object_type, xid, ', ' + filter_extra if filter_extra else '', object_fields),
}).encode(), headers=self._HEADERS)
obj = resp['data'][object_type]
if not obj:
raise ExtractorError(resp['errors'][0]['message'], expected=True)
return obj
class DailymotionIE(DailymotionBaseInfoExtractor):
@ -54,18 +97,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
(?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)|
(?:www\.)?lequipe\.fr/video
)
/(?P<id>[^/?_]+)
/(?P<id>[^/?_]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
'''
IE_NAME = 'dailymotion'
_FORMATS = [
('stream_h264_ld_url', 'ld'),
('stream_h264_url', 'standard'),
('stream_h264_hq_url', 'hq'),
('stream_h264_hd_url', 'hd'),
('stream_h264_hd1080_url', 'hd180'),
]
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
@ -74,7 +108,6 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'ext': 'mp4',
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 187,
'timestamp': 1493651285,
'upload_date': '20170501',
@ -146,7 +179,16 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}, {
'url': 'https://www.lequipe.fr/video/k7MtHciueyTcrFtFKA2',
'only_matching': True,
}, {
'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw',
'only_matching': True,
}]
_GEO_BYPASS = False
_COMMON_MEDIA_FIELDS = '''description
geoblockedCountries {
allowed
}
xid'''
@staticmethod
def _extract_urls(webpage):
@ -162,264 +204,140 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
return urls
def _real_extract(self, url):
video_id = self._match_id(url)
video_id, playlist_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage_no_ff(
'https://www.dailymotion.com/video/%s' % video_id, video_id)
if playlist_id:
if not self._downloader.params.get('noplaylist'):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
return self.url_result(
'http://www.dailymotion.com/playlist/' + playlist_id,
'DailymotionPlaylist', playlist_id)
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
age_limit = self._rta_search(webpage)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'description', webpage, 'description')
view_count_str = self._search_regex(
(r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([\s\d,.]+)"',
r'video_views_count[^>]+>\s+([\s\d\,.]+)'),
webpage, 'view count', default=None)
if view_count_str:
view_count_str = re.sub(r'\s', '', view_count_str)
view_count = str_to_int(view_count_str)
comment_count = int_or_none(self._search_regex(
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"',
webpage, 'comment count', default=None))
player_v5 = self._search_regex(
[r'buildPlayer\(({.+?})\);\n', # See https://github.com/ytdl-org/youtube-dl/issues/7826
r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
r'buildPlayer\(({.+?})\);',
r'var\s+config\s*=\s*({.+?});',
# New layout regex (see https://github.com/ytdl-org/youtube-dl/issues/13580)
r'__PLAYER_CONFIG__\s*=\s*({.+?});'],
webpage, 'player v5', default=None)
if player_v5:
player = self._parse_json(player_v5, video_id, fatal=False) or {}
metadata = try_get(player, lambda x: x['metadata'], dict)
if not metadata:
metadata_url = url_or_none(try_get(
player, lambda x: x['context']['metadata_template_url1']))
if metadata_url:
metadata_url = metadata_url.replace(':videoId', video_id)
else:
metadata_url = update_url_query(
'https://www.dailymotion.com/player/metadata/video/%s'
% video_id, {
'embedder': url,
'integration': 'inline',
'GK_PV5_NEON': '1',
})
metadata = self._download_json(
metadata_url, video_id, 'Downloading metadata JSON')
if try_get(metadata, lambda x: x['error']['type']) == 'password_protected':
password = self._downloader.params.get('videopassword')
if password:
r = int(metadata['id'][1:], 36)
us64e = lambda x: base64.urlsafe_b64encode(x).decode().strip('=')
t = ''.join(random.choice(string.ascii_letters) for i in range(10))
n = us64e(compat_struct_pack('I', r))
i = us64e(hashlib.md5(('%s%d%s' % (password, r, t)).encode()).digest())
media = self._call_api(
'media', video_id, '''... on Video {
%s
stats {
likes {
total
}
views {
total
}
}
}
... on Live {
%s
audienceCount
isOnAir
}''' % (self._COMMON_MEDIA_FIELDS, self._COMMON_MEDIA_FIELDS), 'Downloading media JSON metadata',
'password: "%s"' % self._downloader.params.get('videopassword') if password else None)
xid = media['xid']
metadata = self._download_json(
'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id)
'https://www.dailymotion.com/player/metadata/video/' + xid,
xid, 'Downloading metadata JSON',
query={'app': 'com.dailymotion.neon'})
self._check_error(metadata)
formats = []
for quality, media_list in metadata['qualities'].items():
for media in media_list:
media_url = media.get('url')
if not media_url:
continue
type_ = media.get('type')
if type_ == 'application/vnd.lumberjack.manifest':
continue
ext = mimetype2ext(type_) or determine_ext(media_url)
if ext == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
media_url, video_id, 'mp4', preference=-1,
m3u8_id='hls', fatal=False)
for f in m3u8_formats:
f['url'] = f['url'].split('#')[0]
formats.append(f)
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
media_url, video_id, preference=-1, f4m_id='hds', fatal=False))
else:
f = {
'url': media_url,
'format_id': 'http-%s' % quality,
'ext': ext,
}
m = re.search(r'H264-(?P<width>\d+)x(?P<height>\d+)', media_url)
if m:
f.update({
'width': int(m.group('width')),
'height': int(m.group('height')),
})
formats.append(f)
self._sort_formats(formats)
title = metadata['title']
duration = int_or_none(metadata.get('duration'))
timestamp = int_or_none(metadata.get('created_time'))
thumbnail = metadata.get('poster_url')
uploader = metadata.get('owner', {}).get('screenname')
uploader_id = metadata.get('owner', {}).get('id')
subtitles = {}
subtitles_data = metadata.get('subtitles', {}).get('data', {})
if subtitles_data and isinstance(subtitles_data, dict):
for subtitle_lang, subtitle in subtitles_data.items():
subtitles[subtitle_lang] = [{
'ext': determine_ext(subtitle_url),
'url': subtitle_url,
} for subtitle_url in subtitle.get('urls', [])]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader': uploader,
'uploader_id': uploader_id,
'age_limit': age_limit,
'view_count': view_count,
'comment_count': comment_count,
'formats': formats,
'subtitles': subtitles,
}
# vevo embed
vevo_id = self._search_regex(
r'<link rel="video_src" href="[^"]*?vevo\.com[^"]*?video=(?P<id>[\w]*)',
webpage, 'vevo embed', default=None)
if vevo_id:
return self.url_result('vevo:%s' % vevo_id, 'Vevo')
# fallback old player
embed_page = self._download_webpage_no_ff(
'https://www.dailymotion.com/embed/video/%s' % video_id,
video_id, 'Downloading embed page')
timestamp = parse_iso8601(self._html_search_meta(
'video:release_date', webpage, 'upload date'))
info = self._parse_json(
self._search_regex(
r'var info = ({.*?}),$', embed_page,
'video info', flags=re.MULTILINE),
video_id)
self._check_error(info)
formats = []
for (key, format_id) in self._FORMATS:
video_url = info.get(key)
if video_url is not None:
m_size = re.search(r'H264-(\d+)x(\d+)', video_url)
if m_size is not None:
width, height = map(int_or_none, (m_size.group(1), m_size.group(2)))
else:
width, height = None, None
formats.append({
'url': video_url,
'ext': 'mp4',
'format_id': format_id,
'width': width,
'height': height,
})
self._sort_formats(formats)
# subtitles
video_subtitles = self.extract_subtitles(video_id, webpage)
title = self._og_search_title(webpage, default=None)
if title is None:
title = self._html_search_regex(
r'(?s)<span\s+id="video_title"[^>]*>(.*?)</span>', webpage,
'title')
return {
'id': video_id,
'formats': formats,
'uploader': info['owner.screenname'],
'timestamp': timestamp,
'title': title,
'description': description,
'subtitles': video_subtitles,
'thumbnail': info['thumbnail_url'],
'age_limit': age_limit,
'view_count': view_count,
'duration': info['duration']
}
def _check_error(self, info):
error = info.get('error')
error = metadata.get('error')
if error:
title = error.get('title') or error['message']
title = error.get('title') or error['raw_message']
# See https://developer.dailymotion.com/api#access-error
if error.get('code') == 'DM007':
self.raise_geo_restricted(msg=title)
allowed_countries = try_get(media, lambda x: x['geoblockedCountries']['allowed'], list)
self.raise_geo_restricted(msg=title, countries=allowed_countries)
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, title), expected=True)
def _get_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(
'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id,
video_id, note=False)
except ExtractorError as err:
self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
return {}
info = json.loads(sub_list)
if (info['total'] > 0):
sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list'])
return sub_lang_list
self._downloader.report_warning('video doesn\'t have subtitles')
return {}
title = metadata['title']
is_live = media.get('isOnAir')
formats = []
for quality, media_list in metadata['qualities'].items():
for m in media_list:
media_url = m.get('url')
media_type = m.get('type')
if not media_url or media_type == 'application/vnd.lumberjack.manifest':
continue
if media_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4',
'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
f = {
'url': media_url,
'format_id': 'http-' + quality,
}
m = re.search(r'/H264-(\d+)x(\d+)(?:-(60)/)?', media_url)
if m:
width, height, fps = map(int_or_none, m.groups())
f.update({
'fps': fps,
'height': height,
'width': width,
})
formats.append(f)
for f in formats:
f['url'] = f['url'].split('#')[0]
if not f.get('fps') and f['format_id'].endswith('@60'):
f['fps'] = 60
self._sort_formats(formats)
subtitles = {}
subtitles_data = try_get(metadata, lambda x: x['subtitles']['data'], dict) or {}
for subtitle_lang, subtitle in subtitles_data.items():
subtitles[subtitle_lang] = [{
'url': subtitle_url,
} for subtitle_url in subtitle.get('urls', [])]
thumbnails = []
for height, poster_url in metadata.get('posters', {}).items():
thumbnails.append({
'height': int_or_none(height),
'id': height,
'url': poster_url,
})
owner = metadata.get('owner') or {}
stats = media.get('stats') or {}
get_count = lambda x: int_or_none(try_get(stats, lambda y: y[x + 's']['total']))
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': clean_html(media.get('description')),
'thumbnails': thumbnails,
'duration': int_or_none(metadata.get('duration')) or None,
'timestamp': int_or_none(metadata.get('created_time')),
'uploader': owner.get('screenname'),
'uploader_id': owner.get('id') or metadata.get('screenname'),
'age_limit': 18 if metadata.get('explicit') else 0,
'tags': metadata.get('tags'),
'view_count': get_count('view') or int_or_none(media.get('audienceCount')),
'like_count': get_count('like'),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}
class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
IE_NAME = 'dailymotion:playlist'
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)'
_TESTS = [{
'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
'info_dict': {
'title': 'SPORT',
'id': 'xv4bw',
},
'playlist_mincount': 20,
}]
class DailymotionPlaylistBaseIE(DailymotionBaseInfoExtractor):
_PAGE_SIZE = 100
def _fetch_page(self, playlist_id, authorizaion, page):
def _fetch_page(self, playlist_id, page):
page += 1
videos = self._download_json(
'https://graphql.api.dailymotion.com',
playlist_id, 'Downloading page %d' % page,
data=json.dumps({
'query': '''{
collection(xid: "%s") {
videos(first: %d, page: %d) {
pageInfo {
hasNextPage
nextPage
}
videos = self._call_api(
self._OBJECT_TYPE, playlist_id,
'''videos(allowExplicit: %s, first: %d, page: %d) {
edges {
node {
xid
url
}
}
}
}
}''' % (playlist_id, self._PAGE_SIZE, page)
}).encode(), headers={
'Authorization': authorizaion,
'Origin': 'https://www.dailymotion.com',
})['data']['collection']['videos']
}''' % ('false' if self._FAMILY_FILTER else 'true', self._PAGE_SIZE, page),
'Downloading page %d' % page)['videos']
for edge in videos['edges']:
node = edge['node']
yield self.url_result(
@ -427,86 +345,49 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
api = self._parse_json(self._search_regex(
r'__PLAYER_CONFIG__\s*=\s*({.+?});',
webpage, 'player config'), playlist_id)['context']['api']
auth = self._download_json(
api.get('auth_url', 'https://graphql.api.dailymotion.com/oauth/token'),
playlist_id, data=urlencode_postdata({
'client_id': api.get('client_id', 'f1a362d288c1b98099c7'),
'client_secret': api.get('client_secret', 'eea605b96e01c796ff369935357eca920c5da4c5'),
'grant_type': 'client_credentials',
}))
authorizaion = '%s %s' % (auth.get('token_type', 'Bearer'), auth['access_token'])
entries = OnDemandPagedList(functools.partial(
self._fetch_page, playlist_id, authorizaion), self._PAGE_SIZE)
self._fetch_page, playlist_id), self._PAGE_SIZE)
return self.playlist_result(
entries, playlist_id,
self._og_search_title(webpage))
entries, playlist_id)
class DailymotionUserIE(DailymotionBaseInfoExtractor):
class DailymotionPlaylistIE(DailymotionPlaylistBaseIE):
IE_NAME = 'dailymotion:playlist'
_VALID_URL = r'(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/playlist/(?P<id>x[0-9a-z]+)'
_TESTS = [{
'url': 'http://www.dailymotion.com/playlist/xv4bw_nqtv_sport/1#video=xl8v3q',
'info_dict': {
'id': 'xv4bw',
},
'playlist_mincount': 20,
}]
_OBJECT_TYPE = 'collection'
class DailymotionUserIE(DailymotionPlaylistBaseIE):
IE_NAME = 'dailymotion:user'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<user>[^/]+)'
_MORE_PAGES_INDICATOR = r'(?s)<div class="pages[^"]*">.*?<a\s+class="[^"]*?icon-arrow_right[^"]*?"'
_PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|swf|#|video|playlist)/)(?:(?:old/)?user/)?(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',
'info_dict': {
'id': 'nqtv',
'title': 'Rémi Gaillard',
},
'playlist_mincount': 100,
'playlist_mincount': 152,
}, {
'url': 'http://www.dailymotion.com/user/UnderProject',
'info_dict': {
'id': 'UnderProject',
'title': 'UnderProject',
},
'playlist_mincount': 1800,
'expected_warnings': [
'Stopped at duplicated page',
],
'playlist_mincount': 1000,
'skip': 'Takes too long time',
}, {
'url': 'https://www.dailymotion.com/user/nqtv',
'info_dict': {
'id': 'nqtv',
},
'playlist_mincount': 148,
'params': {
'age_limit': 0,
},
}]
def _extract_entries(self, id):
video_ids = set()
processed_urls = set()
for pagenum in itertools.count(1):
page_url = self._PAGE_TEMPLATE % (id, pagenum)
webpage, urlh = self._download_webpage_handle_no_ff(
page_url, id, 'Downloading page %s' % pagenum)
if urlh.geturl() in processed_urls:
self.report_warning('Stopped at duplicated page %s, which is the same as %s' % (
page_url, urlh.geturl()), id)
break
processed_urls.add(urlh.geturl())
for video_id in re.findall(r'data-xid="(.+?)"', webpage):
if video_id not in video_ids:
yield self.url_result(
'http://www.dailymotion.com/video/%s' % video_id,
DailymotionIE.ie_key(), video_id)
video_ids.add(video_id)
if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:
break
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user = mobj.group('user')
webpage = self._download_webpage(
'https://www.dailymotion.com/user/%s' % user, user)
full_user = unescapeHTML(self._html_search_regex(
r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user),
webpage, 'user'))
return {
'_type': 'playlist',
'id': user,
'title': full_user,
'entries': self._extract_entries(user),
}
_OBJECT_TYPE = 'channel'

154
youtube_dl/extractor/daisuki.py
View File

@ -1,154 +0,0 @@
from __future__ import unicode_literals
import base64
import json
import random
import re
from .common import InfoExtractor
from ..aes import (
aes_cbc_decrypt,
aes_cbc_encrypt,
)
from ..compat import compat_b64decode
from ..utils import (
bytes_to_intlist,
bytes_to_long,
extract_attributes,
ExtractorError,
intlist_to_bytes,
js_to_json,
int_or_none,
long_to_bytes,
pkcs1pad,
)
class DaisukiMottoIE(InfoExtractor):
_VALID_URL = r'https?://motto\.daisuki\.net/framewatch/embed/[^/]+/(?P<id>[0-9a-zA-Z]{3})'
_TEST = {
'url': 'http://motto.daisuki.net/framewatch/embed/embedDRAGONBALLSUPERUniverseSurvivalsaga/V2e/760/428',
'info_dict': {
'id': 'V2e',
'ext': 'mp4',
'title': '#117 SHOWDOWN OF LOVE! ANDROIDS VS UNIVERSE 2!!',
'subtitles': {
'mul': [{
'ext': 'ttml',
}],
},
},
'params': {
'skip_download': True, # AES-encrypted HLS stream
},
}
# The public key in PEM format can be found in clientlibs_anime_watch.min.js
_RSA_KEY = (0xc5524c25e8e14b366b3754940beeb6f96cb7e2feef0b932c7659a0c5c3bf173d602464c2df73d693b513ae06ff1be8f367529ab30bf969c5640522181f2a0c51ea546ae120d3d8d908595e4eff765b389cde080a1ef7f1bbfb07411cc568db73b7f521cedf270cbfbe0ddbc29b1ac9d0f2d8f4359098caffee6d07915020077d, 65537)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
flashvars = self._parse_json(self._search_regex(
r'(?s)var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
video_id, transform_source=js_to_json)
iv = [0] * 16
data = {}
for key in ('device_cd', 'mv_id', 'ss1_prm', 'ss2_prm', 'ss3_prm', 'ss_id'):
data[key] = flashvars.get(key, '')
encrypted_rtn = None
# Some AES keys are rejected. Try it with different AES keys
for idx in range(5):
aes_key = [random.randint(0, 254) for _ in range(32)]
padded_aeskey = intlist_to_bytes(pkcs1pad(aes_key, 128))
n, e = self._RSA_KEY
encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n))
init_data = self._download_json(
'http://motto.daisuki.net/fastAPI/bgn/init/',
video_id, query={
's': flashvars.get('s', ''),
'c': flashvars.get('ss3_prm', ''),
'e': url,
'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt(
bytes_to_intlist(json.dumps(data)),
aes_key, iv))).decode('ascii'),
'a': base64.b64encode(encrypted_aeskey).decode('ascii'),
}, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else ''))
if 'rtn' in init_data:
encrypted_rtn = init_data['rtn']
break
self._sleep(5, video_id)
if encrypted_rtn is None:
raise ExtractorError('Failed to fetch init data')
rtn = self._parse_json(
intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist(
compat_b64decode(encrypted_rtn)),
aes_key, iv)).decode('utf-8').rstrip('\0'),
video_id)
title = rtn['title_str']
formats = self._extract_m3u8_formats(
rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native')
subtitles = {}
caption_url = rtn.get('caption_url')
if caption_url:
# mul: multiple languages
subtitles['mul'] = [{
'url': caption_url,
'ext': 'ttml',
}]
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
}
class DaisukiMottoPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://motto\.daisuki\.net/(?P<id>information)/'
_TEST = {
'url': 'http://motto.daisuki.net/information/',
'info_dict': {
'title': 'DRAGON BALL SUPER',
},
'playlist_mincount': 117,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = []
for li in re.findall(r'(<li[^>]+?data-product_id="[a-zA-Z0-9]{3}"[^>]+>)', webpage):
attr = extract_attributes(li)
ad_id = attr.get('data-ad_id')
product_id = attr.get('data-product_id')
if ad_id and product_id:
episode_id = attr.get('data-chapter')
entries.append({
'_type': 'url_transparent',
'url': 'http://motto.daisuki.net/framewatch/embed/%s/%s/760/428' % (ad_id, product_id),
'episode_id': episode_id,
'episode_number': int_or_none(episode_id),
'ie_key': 'DaisukiMotto',
})
return self.playlist_result(entries, playlist_title='DRAGON BALL SUPER')

106
youtube_dl/extractor/daum.py
View File

@ -2,25 +2,21 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
int_or_none,
str_to_int,
xpath_text,
unescapeHTML,
)
class DaumIE(InfoExtractor):
class DaumBaseIE(InfoExtractor):
_KAKAO_EMBED_BASE = 'http://tv.kakao.com/embed/player/cliplink/'
class DaumIE(DaumBaseIE):
_VALID_URL = r'https?://(?:(?:m\.)?tvpot\.daum\.net/v/|videofarm\.daum\.net/controller/player/VodPlayer\.swf\?vid=)(?P<id>[^?#&]+)'
IE_NAME = 'daum.net'
@ -36,6 +32,9 @@ class DaumIE(InfoExtractor):
'duration': 2117,
'view_count': int,
'comment_count': int,
'uploader_id': 186139,
'uploader': '콘간지',
'timestamp': 1387310323,
},
}, {
'url': 'http://m.tvpot.daum.net/v/65139429',
@ -44,11 +43,14 @@ class DaumIE(InfoExtractor):
'ext': 'mp4',
'title': '1297회, \'아빠 아들로 태어나길 잘 했어\' 민수, 감동의 눈물[아빠 어디가] 20150118',
'description': 'md5:79794514261164ff27e36a21ad229fc5',
'upload_date': '20150604',
'upload_date': '20150118',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'duration': 154,
'view_count': int,
'comment_count': int,
'uploader': 'MBC 예능',
'uploader_id': 132251,
'timestamp': 1421604228,
},
}, {
'url': 'http://tvpot.daum.net/v/07dXWRka62Y%24',
@ -59,12 +61,15 @@ class DaumIE(InfoExtractor):
'id': 'vwIpVpCQsT8$',
'ext': 'flv',
'title': '01-Korean War ( Trouble on the horizon )',
'description': '\nKorean War 01\nTrouble on the horizon\n전쟁의 먹구름',
'description': 'Korean War 01\r\nTrouble on the horizon\r\n전쟁의 먹구름',
'upload_date': '20080223',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'duration': 249,
'view_count': int,
'comment_count': int,
'uploader': '까칠한 墮落始祖 황비홍님의',
'uploader_id': 560824,
'timestamp': 1203770745,
},
}, {
# Requires dte_type=WEB (#9972)
@ -73,60 +78,24 @@ class DaumIE(InfoExtractor):
'info_dict': {
'id': 's3794Uf1NZeZ1qMpGpeqeRU',
'ext': 'mp4',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny) [쇼! 음악중심] 508회 20160611',
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\n\n[쇼! 음악중심] 20160611, 507회',
'upload_date': '20160611',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
'upload_date': '20170129',
'uploader': '쇼! 음악중심',
'uploader_id': 2653210,
'timestamp': 1485684628,
},
}]
def _real_extract(self, url):
video_id = compat_urllib_parse_unquote(self._match_id(url))
movie_data = self._download_json(
'http://videofarm.daum.net/controller/api/closed/v1_2/IntegratedMovieData.json',
video_id, 'Downloading video formats info', query={'vid': video_id, 'dte_type': 'WEB'})
# For urls like http://m.tvpot.daum.net/v/65139429, where the video_id is really a clipid
if not movie_data.get('output_list', {}).get('output_list') and re.match(r'^\d+$', video_id):
return self.url_result('http://tvpot.daum.net/clip/ClipView.do?clipid=%s' % video_id)
info = self._download_xml(
'http://tvpot.daum.net/clip/ClipInfoXml.do', video_id,
'Downloading video info', query={'vid': video_id})
formats = []
for format_el in movie_data['output_list']['output_list']:
profile = format_el['profile']
format_query = compat_urllib_parse_urlencode({
'vid': video_id,
'profile': profile,
})
url_doc = self._download_xml(
'http://videofarm.daum.net/controller/api/open/v1_2/MovieLocation.apixml?' + format_query,
video_id, note='Downloading video data for %s format' % profile)
format_url = url_doc.find('result/url').text
formats.append({
'url': format_url,
'format_id': profile,
'width': int_or_none(format_el.get('width')),
'height': int_or_none(format_el.get('height')),
'filesize': int_or_none(format_el.get('filesize')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info.find('TITLE').text,
'formats': formats,
'thumbnail': xpath_text(info, 'THUMB_URL'),
'description': xpath_text(info, 'CONTENTS'),
'duration': int_or_none(xpath_text(info, 'DURATION')),
'upload_date': info.find('REGDTTM').text[:8],
'view_count': str_to_int(xpath_text(info, 'PLAY_CNT')),
'comment_count': str_to_int(xpath_text(info, 'COMMENT_CNT')),
}
if not video_id.isdigit():
video_id += '@my'
return self.url_result(
self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
class DaumClipIE(InfoExtractor):
class DaumClipIE(DaumBaseIE):
_VALID_URL = r'https?://(?:m\.)?tvpot\.daum\.net/(?:clip/ClipView.(?:do|tv)|mypot/View.do)\?.*?clipid=(?P<id>\d+)'
IE_NAME = 'daum.net:clip'
_URL_TEMPLATE = 'http://tvpot.daum.net/clip/ClipView.do?clipid=%s'
@ -142,6 +111,9 @@ class DaumClipIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'duration': 3868,
'view_count': int,
'uploader': 'GOMeXP',
'uploader_id': 6667,
'timestamp': 1377911092,
},
}, {
'url': 'http://m.tvpot.daum.net/clip/ClipView.tv?clipid=54999425',
@ -154,22 +126,8 @@ class DaumClipIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
clip_info = self._download_json(
'http://tvpot.daum.net/mypot/json/GetClipInfo.do?clipid=%s' % video_id,
video_id, 'Downloading clip info')['clip_bean']
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'http://tvpot.daum.net/v/%s' % clip_info['vid'],
'title': unescapeHTML(clip_info['title']),
'thumbnail': clip_info.get('thumb_url'),
'description': clip_info.get('contents'),
'duration': int_or_none(clip_info.get('duration')),
'upload_date': clip_info.get('up_date')[:8],
'view_count': int_or_none(clip_info.get('play_count')),
'ie_key': 'Daum',
}
return self.url_result(
self._KAKAO_EMBED_BASE + video_id, 'Kakao', video_id)
class DaumListIE(InfoExtractor):

50
youtube_dl/extractor/dctp.py
View File

@ -16,10 +16,11 @@ class DctpTvIE(InfoExtractor):
_TESTS = [{
# 4x3
'url': 'http://www.dctp.tv/filme/videoinstallation-fuer-eine-kaufhausfassade/',
'md5': '3ffbd1556c3fe210724d7088fad723e3',
'info_dict': {
'id': '95eaa4f33dad413aa17b4ee613cccc6c',
'display_id': 'videoinstallation-fuer-eine-kaufhausfassade',
'ext': 'flv',
'ext': 'm4v',
'title': 'Videoinstallation für eine Kaufhausfassade',
'description': 'Kurzfilm',
'thumbnail': r're:^https?://.*\.jpg$',
@ -27,10 +28,6 @@ class DctpTvIE(InfoExtractor):
'timestamp': 1302172322,
'upload_date': '20110407',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
# 16x9
'url': 'http://www.dctp.tv/filme/sind-youtuber-die-besseren-lehrer/',
@ -59,33 +56,26 @@ class DctpTvIE(InfoExtractor):
uuid = media['uuid']
title = media['title']
ratio = '16x9' if media.get('is_wide') else '4x3'
play_path = 'mp4:%s_dctp_0500_%s.m4v' % (uuid, ratio)
is_wide = media.get('is_wide')
formats = []
servers = self._download_json(
'http://www.dctp.tv/streaming_servers/', display_id,
note='Downloading server list JSON', fatal=False)
def add_formats(suffix):
templ = 'https://%%s/%s_dctp_%s.m4v' % (uuid, suffix)
formats.extend([{
'format_id': 'hls-' + suffix,
'url': templ % 'cdn-segments.dctp.tv' + '/playlist.m3u8',
'protocol': 'm3u8_native',
}, {
'format_id': 's3-' + suffix,
'url': templ % 'completed-media.s3.amazonaws.com',
}, {
'format_id': 'http-' + suffix,
'url': templ % 'cdn-media.dctp.tv',
}])
if servers:
endpoint = next(
server['endpoint']
for server in servers
if url_or_none(server.get('endpoint'))
and 'cloudfront' in server['endpoint'])
else:
endpoint = 'rtmpe://s2pqqn4u96e4j8.cloudfront.net/cfx/st/'
app = self._search_regex(
r'^rtmpe?://[^/]+/(?P<app>.*)$', endpoint, 'app')
formats = [{
'url': endpoint,
'app': app,
'play_path': play_path,
'page_url': url,
'player_url': 'http://svm-prod-dctptv-static.s3.amazonaws.com/dctptv-relaunch2012-110.swf',
'ext': 'flv',
}]
add_formats('0500_' + ('16x9' if is_wide else '4x3'))
if is_wide:
add_formats('720p')
thumbnails = []
images = media.get('images')

9
youtube_dl/extractor/discovery.py
View File

@ -13,8 +13,8 @@ from ..compat import compat_HTTPError
class DiscoveryIE(DiscoveryGoBaseIE):
_VALID_URL = r'''(?x)https?://
(?P<site>
(?:(?:www|go)\.)?discovery|
(?:www\.)?
go\.discovery|
www\.
(?:
investigationdiscovery|
discoverylife|
@ -22,8 +22,7 @@ class DiscoveryIE(DiscoveryGoBaseIE):
ahctv|
destinationamerica|
sciencechannel|
tlc|
velocity
tlc
)|
watch\.
(?:
@ -83,7 +82,7 @@ class DiscoveryIE(DiscoveryGoBaseIE):
'authRel': 'authorization',
'client_id': '3020a40c2356a645b4b4',
'nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
'redirectUri': 'https://fusion.ddmcdn.com/app/mercury-sdk/180/redirectHandler.html?https://www.%s.com' % site,
'redirectUri': 'https://www.discovery.com/',
})['access_token']
headers = self.geo_verification_headers()

6
youtube_dl/extractor/dplay.py
View File

@ -146,6 +146,11 @@ class DPlayIE(InfoExtractor):
video = self._download_json(
disco_base + 'content/videos/' + display_id, display_id,
headers=headers, query={
'fields[channel]': 'name',
'fields[image]': 'height,src,width',
'fields[show]': 'name',
'fields[tag]': 'name',
'fields[video]': 'description,episodeNumber,name,publishStart,seasonNumber,videoDuration',
'include': 'images,primaryChannel,show,tags'
})
video_id = video['data']['id']
@ -226,7 +231,6 @@ class DPlayIE(InfoExtractor):
'series': series,
'season_number': int_or_none(info.get('seasonNumber')),
'episode_number': int_or_none(info.get('episodeNumber')),
'age_limit': int_or_none(info.get('minimum_age')),
'creator': creator,
'tags': tags,
'thumbnails': thumbnails,

57
youtube_dl/extractor/drtv.py
View File

@ -17,6 +17,7 @@ from ..utils import (
float_or_none,
mimetype2ext,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
url_or_none,
@ -24,7 +25,14 @@ from ..utils import (
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio(?:/ondemand)?)/(?:[^/]+/)*|
(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode)/
)
(?P<id>[\da-z_-]+)
'''
_GEO_BYPASS = False
_GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv'
@ -83,6 +91,26 @@ class DRTVIE(InfoExtractor):
}, {
'url': 'https://www.dr.dk/radio/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
'only_matching': True,
}, {
'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769',
'info_dict': {
'id': '00951930010',
'ext': 'mp4',
'title': 'Bonderøven (1:8)',
'description': 'md5:3cf18fc0d3b205745d4505f896af8121',
'timestamp': 1546542000,
'upload_date': '20190103',
'duration': 2576.6,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
'only_matching': True,
}, {
'url': 'https://dr-massive.com/drtv/se/bonderoeven_71769',
'only_matching': True,
}]
def _real_extract(self, url):
@ -100,13 +128,32 @@ class DRTVIE(InfoExtractor):
webpage, 'video id', default=None)
if not video_id:
video_id = compat_urllib_parse_unquote(self._search_regex(
video_id = self._search_regex(
r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
webpage, 'urn'))
webpage, 'urn', default=None)
if video_id:
video_id = compat_urllib_parse_unquote(video_id)
_PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard'
query = {'expanded': 'true'}
if video_id:
programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id)
else:
programcard_url = _PROGRAMCARD_BASE
page = self._parse_json(
self._search_regex(
r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage,
'data'), '1')['cache']['page']
page = page[list(page.keys())[0]]
item = try_get(
page, (lambda x: x['item'], lambda x: x['entries'][0]['item']),
dict)
video_id = item['customId'].split(':')[-1]
query['productionnumber'] = video_id
data = self._download_json(
'https://www.dr.dk/mu-online/api/1.4/programcard/%s' % video_id,
video_id, 'Downloading video JSON', query={'expanded': 'true'})
programcard_url, video_id, 'Downloading video JSON', query=query)
title = str_or_none(data.get('Title')) or re.sub(
r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',

3
youtube_dl/extractor/eporner.py
View File

@ -4,7 +4,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
encode_base_n,
ExtractorError,
@ -55,7 +54,7 @@ class EpornerIE(InfoExtractor):
webpage, urlh = self._download_webpage_handle(url, display_id)
video_id = self._match_id(compat_str(urlh.geturl()))
video_id = self._match_id(urlh.geturl())
hash = self._search_regex(
r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')

67
youtube_dl/extractor/extractors.py
View File

@ -18,10 +18,10 @@ from .acast import (
ACastIE,
ACastChannelIE,
)
from .addanime import AddAnimeIE
from .adn import ADNIE
from .adobeconnect import AdobeConnectIE
from .adobetv import (
AdobeTVEmbedIE,
AdobeTVIE,
AdobeTVShowIE,
AdobeTVChannelIE,
@ -80,7 +80,6 @@ from .awaan import (
)
from .azmedien import AZMedienIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
from .bbc import (
BBCCoUkIE,
@ -106,6 +105,7 @@ from .bilibili import (
BiliBiliBangumiIE,
BilibiliAudioIE,
BilibiliAudioAlbumIE,
BiliBiliPlayerIE,
)
from .biobiochiletv import BioBioChileTVIE
from .bitchute import (
@ -224,7 +224,6 @@ from .comedycentral import (
ComedyCentralTVIE,
ToshIE,
)
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import (
MmsIE,
@ -255,10 +254,6 @@ from .dailymotion import (
DailymotionPlaylistIE,
DailymotionUserIE,
)
from .daisuki import (
DaisukiMottoIE,
DaisukiMottoPlaylistIE,
)
from .daum import (
DaumIE,
DaumClipIE,
@ -356,7 +351,6 @@ from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
from .fivetv import FiveTVIE
from .flickr import FlickrIE
from .flipagram import FlipagramIE
from .folketinget import FolketingetIE
from .footyroom import FootyRoomIE
from .formula1 import Formula1IE
@ -367,7 +361,10 @@ from .fourtube import (
FuxIE,
)
from .fox import FOXIE
from .fox9 import FOX9IE
from .fox9 import (
FOX9IE,
FOX9NewsIE,
)
from .foxgay import FoxgayIE
from .foxnews import (
FoxNewsIE,
@ -400,10 +397,6 @@ from .fusion import FusionIE
from .fxnetworks import FXNetworksIE
from .gaia import GaiaIE
from .gameinformer import GameInformerIE
from .gameone import (
GameOneIE,
GameOnePlaylistIE,
)
from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gaskrank import GaskrankIE
@ -419,7 +412,6 @@ from .globo import (
GloboArticleIE,
)
from .go import GoIE
from .go90 import Go90IE
from .godtube import GodTubeIE
from .golem import GolemIE
from .googledrive import GoogleDriveIE
@ -428,7 +420,6 @@ from .googlesearch import GoogleSearchIE
from .goshgay import GoshgayIE
from .gputechconf import GPUTechConfIE
from .groupon import GrouponIE
from .hark import HarkIE
from .hbo import HBOIE
from .hearthisat import HearThisAtIE
from .heise import HeiseIE
@ -460,7 +451,6 @@ from .hungama import (
HungamaSongIE,
)
from .hypem import HypemIE
from .iconosquare import IconosquareIE
from .ign import (
IGNIE,
OneUPIE,
@ -508,7 +498,6 @@ from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE
from .joj import JojIE
from .jwplatform import JWPlatformIE
from .jpopsukitv import JpopsukiIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kanalplay import KanalPlayIE
@ -519,10 +508,9 @@ from .keezmovies import KeezMoviesIE
from .ketnet import KetnetIE
from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE
from .kinja import KinjaEmbedIE
from .kinopoisk import KinoPoiskIE
from .keek import KeekIE
from .konserthusetplay import KonserthusetPlayIE
from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE
from .ku6 import Ku6IE
from .kusi import KUSIIE
@ -546,7 +534,6 @@ from .lcp import (
LcpPlayIE,
LcpIE,
)
from .learnr import LearnrIE
from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioIE,
@ -598,13 +585,11 @@ from .lynda import (
LyndaCourseIE
)
from .m6 import M6IE
from .macgamestore import MacGameStoreIE
from .mailru import (
MailRuIE,
MailRuMusicIE,
MailRuMusicSearchIE,
)
from .makertv import MakerTVIE
from .malltv import MallTVIE
from .mangomolo import (
MangomoloVideoIE,
@ -638,7 +623,6 @@ from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyIE,
MicrosoftVirtualAcademyCourseIE,
)
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE
from .minoto import MinotoIE
from .miomio import MioMioIE
@ -648,7 +632,6 @@ from .mixcloud import (
MixcloudIE,
MixcloudUserIE,
MixcloudPlaylistIE,
MixcloudStreamIE,
)
from .mlb import MLBIE
from .mnet import MnetIE
@ -670,10 +653,9 @@ from .mtv import (
MTVVideoIE,
MTVServicesEmbeddedIE,
MTVDEIE,
MTV81IE,
MTVJapanIE,
)
from .muenchentv import MuenchenTVIE
from .musicplayon import MusicPlayOnIE
from .mwave import MwaveIE, MwaveMeetGreetIE
from .mychannels import MyChannelsIE
from .myspace import MySpaceIE, MySpaceAlbumIE
@ -813,10 +795,6 @@ from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
)
from .openload import (
OpenloadIE,
VerystreamIE,
)
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
@ -830,7 +808,6 @@ from .packtpub import (
PacktPubIE,
PacktPubCourseIE,
)
from .pandatv import PandaTVIE
from .pandoratv import PandoraTVIE
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
@ -873,6 +850,7 @@ from .polskieradio import (
PolskieRadioIE,
PolskieRadioCategoryIE,
)
from .popcorntimes import PopcorntimesIE
from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE
from .porncom import PornComIE
@ -942,10 +920,6 @@ from .rentv import (
from .restudy import RestudyIE
from .reuters import ReutersIE
from .reverbnation import ReverbNationIE
from .revision3 import (
Revision3EmbedIE,
Revision3IE,
)
from .rice import RICEIE
from .rmcdecouverte import RMCDecouverteIE
from .ro220 import Ro220IE
@ -989,7 +963,14 @@ from .savefrom import SaveFromIE
from .sbs import SBSIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .scrippsnetworks import ScrippsNetworksWatchIE
from .scrippsnetworks import (
ScrippsNetworksWatchIE,
ScrippsNetworksIE,
)
from .scte import (
SCTEIE,
SCTECourseIE,
)
from .seeker import SeekerIE
from .senateisvp import SenateISVPIE
from .sendtonews import SendtoNewsIE
@ -1077,7 +1058,6 @@ from .srmediathek import SRMediathekIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamable import StreamableIE
from .streamango import StreamangoIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
@ -1186,10 +1166,14 @@ from .tunein import (
)
from .tunepk import TunePkIE
from .turbo import TurboIE
from .tutv import TutvIE
from .tv2 import (
TV2IE,
TV2ArticleIE,
KatsomoIE,
)
from .tv2dk import (
TV2DKIE,
TV2DKBornholmPlayIE,
)
from .tv2hu import TV2HuIE
from .tv4 import TV4IE
@ -1247,13 +1231,17 @@ from .twitter import (
TwitterCardIE,
TwitterIE,
TwitterAmplifyIE,
TwitterBroadcastIE,
)
from .udemy import (
UdemyIE,
UdemyCourseIE
)
from .udn import UDNEmbedIE
from .ufctv import UFCTVIE
from .ufctv import (
UFCTVIE,
UFCArabiaIE,
)
from .uktvplay import UKTVPlayIE
from .digiteka import DigitekaIE
from .dlive import (
@ -1307,7 +1295,6 @@ from .videomore import (
VideomoreVideoIE,
VideomoreSeasonIE,
)
from .videopremium import VideoPremiumIE
from .videopress import VideoPressIE
from .vidio import VidioIE
from .vidlii import VidLiiIE

2
youtube_dl/extractor/facebook.py
View File

@ -334,7 +334,7 @@ class FacebookIE(InfoExtractor):
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:pagelet_group_mall|permalink_video_pagelet|hyperfeed_story_id_\d+)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
video_data = extract_from_jsmods_instances(server_js_data)

115
youtube_dl/extractor/flipagram.py
View File

@ -1,115 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
float_or_none,
try_get,
unified_timestamp,
)
class FlipagramIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?flipagram\.com/f/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://flipagram.com/f/nyvTSJMKId',
'md5': '888dcf08b7ea671381f00fab74692755',
'info_dict': {
'id': 'nyvTSJMKId',
'ext': 'mp4',
'title': 'Flipagram by sjuria101 featuring Midnight Memories by One Direction',
'description': 'md5:d55e32edc55261cae96a41fa85ff630e',
'duration': 35.571,
'timestamp': 1461244995,
'upload_date': '20160421',
'uploader': 'kitty juria',
'uploader_id': 'sjuria101',
'creator': 'kitty juria',
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
'comments': list,
'formats': 'mincount:2',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(
self._search_regex(
r'window\.reactH2O\s*=\s*({.+});', webpage, 'video data'),
video_id)
flipagram = video_data['flipagram']
video = flipagram['video']
json_ld = self._search_json_ld(webpage, video_id, default={})
title = json_ld.get('title') or flipagram['captionText']
description = json_ld.get('description') or flipagram.get('captionText')
formats = [{
'url': video['url'],
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'filesize': int_or_none(video_data.get('size')),
}]
preview_url = try_get(
flipagram, lambda x: x['music']['track']['previewUrl'], compat_str)
if preview_url:
formats.append({
'url': preview_url,
'ext': 'm4a',
'vcodec': 'none',
})
self._sort_formats(formats)
counts = flipagram.get('counts', {})
user = flipagram.get('user', {})
video_data = flipagram.get('video', {})
thumbnails = [{
'url': self._proto_relative_url(cover['url']),
'width': int_or_none(cover.get('width')),
'height': int_or_none(cover.get('height')),
'filesize': int_or_none(cover.get('size')),
} for cover in flipagram.get('covers', []) if cover.get('url')]
# Note that this only retrieves comments that are initially loaded.
# For videos with large amounts of comments, most won't be retrieved.
comments = []
for comment in video_data.get('comments', {}).get(video_id, {}).get('items', []):
text = comment.get('comment')
if not text or not isinstance(text, list):
continue
comments.append({
'author': comment.get('user', {}).get('name'),
'author_id': comment.get('user', {}).get('username'),
'id': comment.get('id'),
'text': text[0],
'timestamp': unified_timestamp(comment.get('created')),
})
return {
'id': video_id,
'title': title,
'description': description,
'duration': float_or_none(flipagram.get('duration'), 1000),
'thumbnails': thumbnails,
'timestamp': unified_timestamp(flipagram.get('iso8601Created')),
'uploader': user.get('name'),
'uploader_id': user.get('username'),
'creator': user.get('name'),
'view_count': int_or_none(counts.get('plays')),
'like_count': int_or_none(counts.get('likes')),
'repost_count': int_or_none(counts.get('reflips')),
'comment_count': int_or_none(counts.get('comments')),
'comments': comments,
'formats': formats,
}

43
youtube_dl/extractor/fox9.py
View File

@ -1,13 +1,23 @@
# coding: utf-8
from __future__ import unicode_literals
from .anvato import AnvatoIE
from .common import InfoExtractor
class FOX9IE(AnvatoIE):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
_TESTS = [{
'url': 'http://www.fox9.com/news/215123287-story',
class FOX9IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)'
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result(
'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id,
'Anvato', video_id)
class FOX9NewsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota',
'md5': 'd6e1b2572c3bab8a849c9103615dd243',
'info_dict': {
'id': '314473',
@ -21,22 +31,11 @@ class FOX9IE(AnvatoIE):
'categories': ['News', 'Sports'],
'tags': ['news', 'video'],
},
}, {
'url': 'http://www.fox9.com/news/investigators/214070684-story',
'only_matching': True,
}]
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id = self._parse_json(
self._search_regex(
r"this\.videosJson\s*=\s*'(\[.+?\])';",
webpage, 'anvato playlist'),
video_id)[0]['video']
return self._get_anvato_videos(
'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
video_id)
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
anvato_id = self._search_regex(
r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id')
return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9')

8
youtube_dl/extractor/franceculture.py
View File

@ -31,7 +31,13 @@ class FranceCultureIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_data = extract_attributes(self._search_regex(
r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)',
r'''(?sx)
(?:
</h1>|
<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>
).*?
(<button[^>]+data-asset-source="[^"]+"[^>]+>)
''',
webpage, 'video data'))
video_url = video_data['data-asset-source']

134
youtube_dl/extractor/gameone.py
View File

@ -1,134 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
xpath_with_ns,
parse_iso8601,
float_or_none,
int_or_none,
)
NAMESPACE_MAP = {
'media': 'http://search.yahoo.com/mrss/',
}
# URL prefix to download the mp4 files directly instead of streaming via rtmp
# Credits go to XBox-Maniac
# http://board.jdownloader.org/showpost.php?p=185835&postcount=31
RAW_MP4_URL = 'http://cdn.riptide-mtvn.com/'
class GameOneIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gameone\.de/tv/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.gameone.de/tv/288',
'md5': '136656b7fb4c9cb4a8e2d500651c499b',
'info_dict': {
'id': '288',
'ext': 'mp4',
'title': 'Game One - Folge 288',
'duration': 1238,
'thumbnail': 'http://s3.gameone.de/gameone/assets/video_metas/teaser_images/000/643/636/big/640x360.jpg',
'description': 'FIFA-Pressepokal 2014, Star Citizen, Kingdom Come: Deliverance, Project Cars, Schöner Trants Nerdquiz Folge 2 Runde 1',
'age_limit': 16,
'upload_date': '20140513',
'timestamp': 1399980122,
}
},
{
'url': 'http://gameone.de/tv/220',
'md5': '5227ca74c4ae6b5f74c0510a7c48839e',
'info_dict': {
'id': '220',
'ext': 'mp4',
'upload_date': '20120918',
'description': 'Jet Set Radio HD, Tekken Tag Tournament 2, Source Filmmaker',
'timestamp': 1347971451,
'title': 'Game One - Folge 220',
'duration': 896.62,
'age_limit': 16,
}
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
og_video = self._og_search_video_url(webpage, secure=False)
description = self._html_search_meta('description', webpage)
age_limit = int(
self._search_regex(
r'age=(\d+)',
self._html_search_meta(
'age-de-meta-label',
webpage),
'age_limit',
'0'))
mrss_url = self._search_regex(r'mrss=([^&]+)', og_video, 'mrss')
mrss = self._download_xml(mrss_url, video_id, 'Downloading mrss')
title = mrss.find('.//item/title').text
thumbnail = mrss.find('.//item/image').get('url')
timestamp = parse_iso8601(mrss.find('.//pubDate').text, delimiter=' ')
content = mrss.find(xpath_with_ns('.//media:content', NAMESPACE_MAP))
content_url = content.get('url')
content = self._download_xml(
content_url,
video_id,
'Downloading media:content')
rendition_items = content.findall('.//rendition')
duration = float_or_none(rendition_items[0].get('duration'))
formats = [
{
'url': re.sub(r'.*/(r2)', RAW_MP4_URL + r'\1', r.find('./src').text),
'width': int_or_none(r.get('width')),
'height': int_or_none(r.get('height')),
'tbr': int_or_none(r.get('bitrate')),
}
for r in rendition_items
]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'description': description,
'age_limit': age_limit,
'timestamp': timestamp,
}
class GameOnePlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gameone\.de(?:/tv)?/?$'
IE_NAME = 'gameone:playlist'
_TEST = {
'url': 'http://www.gameone.de/tv',
'info_dict': {
'title': 'GameOne',
},
'playlist_mincount': 294,
}
def _real_extract(self, url):
webpage = self._download_webpage('http://www.gameone.de/tv', 'TV')
max_id = max(map(int, re.findall(r'<a href="/tv/(\d+)"', webpage)))
entries = [
self.url_result('http://www.gameone.de/tv/%d' %
video_id, 'GameOne')
for video_id in range(max_id, 0, -1)]
return {
'_type': 'playlist',
'title': 'GameOne',
'entries': entries,
}

66
youtube_dl/extractor/generic.py
View File

@ -88,10 +88,6 @@ from .piksel import PikselIE
from .videa import VideaIE
from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
from .openload import (
OpenloadIE,
VerystreamIE,
)
from .videopress import VideoPressIE
from .rutube import RutubeIE
from .limelight import LimelightBaseIE
@ -119,6 +115,7 @@ from .viqeo import ViqeoIE
from .expressen import ExpressenIE
from .zype import ZypeIE
from .odnoklassniki import OdnoklassnikiIE
from .kinja import KinjaEmbedIE
class GenericIE(InfoExtractor):
@ -1487,16 +1484,18 @@ class GenericIE(InfoExtractor):
'timestamp': 1432570283,
},
},
# OnionStudios embed
# Kinja embed
{
'url': 'http://www.clickhole.com/video/dont-understand-bitcoin-man-will-mumble-explanatio-2537',
'info_dict': {
'id': '2855',
'id': '106351',
'ext': 'mp4',
'title': 'Don’t Understand Bitcoin? This Man Will Mumble An Explanation At You',
'description': 'Migrated from OnionStudios',
'thumbnail': r're:^https?://.*\.jpe?g$',
'uploader': 'ClickHole',
'uploader_id': 'clickhole',
'uploader': 'clickhole',
'upload_date': '20150527',
'timestamp': 1432744860,
}
},
# SnagFilms embed
@ -2099,6 +2098,9 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Smoky Barbecue Favorites',
'thumbnail': r're:^https?://.*\.jpe?g',
'description': 'md5:5ff01e76316bd8d46508af26dc86023b',
'upload_date': '20170909',
'timestamp': 1504915200,
},
'add_ie': [ZypeIE.ie_key()],
'params': {
@ -2285,7 +2287,7 @@ class GenericIE(InfoExtractor):
if head_response is not False:
# Check for redirect
new_url = compat_str(head_response.geturl())
new_url = head_response.geturl()
if url != new_url:
self.report_following_redirect(new_url)
if force_videoid:
@ -2385,12 +2387,12 @@ class GenericIE(InfoExtractor):
return self.playlist_result(
self._parse_xspf(
doc, video_id, xspf_url=url,
xspf_base_url=compat_str(full_response.geturl())),
xspf_base_url=full_response.geturl()),
video_id)
elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
info_dict['formats'] = self._parse_mpd_formats(
doc,
mpd_base_url=compat_str(full_response.geturl()).rpartition('/')[0],
mpd_base_url=full_response.geturl().rpartition('/')[0],
mpd_url=url)
self._sort_formats(info_dict['formats'])
return info_dict
@ -2534,15 +2536,21 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
dailymail_urls, video_id, video_title, ie=DailyMailIE.ie_key())
# Look for Teachable embeds, must be before Wistia
teachable_url = TeachableIE._extract_url(webpage, url)
if teachable_url:
return self.url_result(teachable_url)
# Look for embedded Wistia player
wistia_url = WistiaIE._extract_url(webpage)
if wistia_url:
return {
wistia_urls = WistiaIE._extract_urls(webpage)
if wistia_urls:
playlist = self.playlist_from_matches(wistia_urls, video_id, video_title, ie=WistiaIE.ie_key())
for entry in playlist['entries']:
entry.update({
'_type': 'url_transparent',
'url': self._proto_relative_url(wistia_url),
'ie_key': WistiaIE.ie_key(),
'uploader': video_uploader,
}
})
return playlist
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
@ -2894,6 +2902,12 @@ class GenericIE(InfoExtractor):
if senate_isvp_url:
return self.url_result(senate_isvp_url, 'SenateISVP')
# Look for Kinja embeds
kinja_embed_urls = KinjaEmbedIE._extract_urls(webpage, url)
if kinja_embed_urls:
return self.playlist_from_matches(
kinja_embed_urls, video_id, video_title)
# Look for OnionStudios embeds
onionstudios_url = OnionStudiosIE._extract_url(webpage)
if onionstudios_url:
@ -2955,7 +2969,7 @@ class GenericIE(InfoExtractor):
# Look for VODPlatform embeds
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(
@ -3039,18 +3053,6 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
# Look for Openload embeds
openload_urls = OpenloadIE._extract_urls(webpage)
if openload_urls:
return self.playlist_from_matches(
openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
# Look for Verystream embeds
verystream_urls = VerystreamIE._extract_urls(webpage)
if verystream_urls:
return self.playlist_from_matches(
verystream_urls, video_id, video_title, ie=VerystreamIE.ie_key())
# Look for VideoPress embeds
videopress_urls = VideoPressIE._extract_urls(webpage)
if videopress_urls:
@ -3144,10 +3146,6 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key())
teachable_url = TeachableIE._extract_url(webpage, url)
if teachable_url:
return self.url_result(teachable_url)
indavideo_urls = IndavideoEmbedIE._extract_urls(webpage)
if indavideo_urls:
return self.playlist_from_matches(

49
youtube_dl/extractor/go.py
View File

@ -40,8 +40,17 @@ class GoIE(AdobePassIE):
'resource_id': 'Disney',
}
}
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|(?P<sub_domain_2>disneynow))\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))'\
% '|'.join(list(_SITE_INFO.keys()) + ['disneynow'])
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?P<sub_domain>%s)\.)?go|
(?P<sub_domain_2>abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
''' % '|'.join(list(_SITE_INFO.keys()))
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': {
@ -54,6 +63,7 @@ class GoIE(AdobePassIE):
# m3u8 download
'skip_download': True,
},
'skip': 'This content is no longer available.',
}, {
'url': 'http://watchdisneyxd.go.com/doraemon',
'info_dict': {
@ -61,6 +71,34 @@ class GoIE(AdobePassIE):
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
'ext': 'mp4',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'age_limit': 14,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet',
'info_dict': {
'id': 'VDKA13435179',
'ext': 'mp4',
'title': 'The Bet',
'description': 'md5:c66de8ba2e92c6c5c113c3ade84ab404',
'age_limit': 14,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
@ -95,10 +133,13 @@ class GoIE(AdobePassIE):
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
video_id = self._search_regex(
(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id',
default=video_id)
r'data-video-id=["\']*(VDKA\w+)',
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)'
), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',

149
youtube_dl/extractor/go90.py
View File

@ -1,149 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_age_limit,
parse_iso8601,
)
class Go90IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?go90\.com/(?:videos|embed)/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://www.go90.com/videos/84BUqjLpf9D',
'md5': 'efa7670dbbbf21a7b07b360652b24a32',
'info_dict': {
'id': '84BUqjLpf9D',
'ext': 'mp4',
'title': 'Daily VICE - Inside The Utah Coalition Against Pornography Convention',
'description': 'VICE\'s Karley Sciortino meets with activists who discuss the state\'s strong anti-porn stance. Then, VICE Sports explains NFL contracts.',
'timestamp': 1491868800,
'upload_date': '20170411',
'age_limit': 14,
}
}, {
'url': 'https://www.go90.com/embed/261MflWkD3N',
'only_matching': True,
}]
_GEO_BYPASS = False
def _real_extract(self, url):
video_id = self._match_id(url)
try:
headers = self.geo_verification_headers()
headers.update({
'Content-Type': 'application/json; charset=utf-8',
})
video_data = self._download_json(
'https://www.go90.com/api/view/items/' + video_id, video_id,
headers=headers, data=b'{"client":"web","device_type":"pc"}')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
message = self._parse_json(e.cause.read().decode(), None)['error']['message']
if 'region unavailable' in message:
self.raise_geo_restricted(countries=['US'])
raise ExtractorError(message, expected=True)
raise
if video_data.get('requires_drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
main_video_asset = video_data['main_video_asset']
episode_number = int_or_none(video_data.get('episode_number'))
series = None
season = None
season_id = None
season_number = None
for metadata in video_data.get('__children', {}).get('Item', {}).values():
if metadata.get('type') == 'show':
series = metadata.get('title')
elif metadata.get('type') == 'season':
season = metadata.get('title')
season_id = metadata.get('id')
season_number = int_or_none(metadata.get('season_number'))
title = episode = video_data.get('title') or series
if series and series != title:
title = '%s - %s' % (series, title)
thumbnails = []
formats = []
subtitles = {}
for asset in video_data.get('assets'):
if asset.get('id') == main_video_asset:
for source in asset.get('sources', []):
source_location = source.get('location')
if not source_location:
continue
source_type = source.get('type')
if source_type == 'hls':
m3u8_formats = self._extract_m3u8_formats(
source_location, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
for f in m3u8_formats:
mobj = re.search(r'/hls-(\d+)-(\d+)K', f['url'])
if mobj:
height, tbr = mobj.groups()
height = int_or_none(height)
f.update({
'height': f.get('height') or height,
'width': f.get('width') or int_or_none(height / 9.0 * 16.0 if height else None),
'tbr': f.get('tbr') or int_or_none(tbr),
})
formats.extend(m3u8_formats)
elif source_type == 'dash':
formats.extend(self._extract_mpd_formats(
source_location, video_id, mpd_id='dash', fatal=False))
else:
formats.append({
'format_id': source.get('name'),
'url': source_location,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'tbr': int_or_none(source.get('bitrate')),
})
for caption in asset.get('caption_metadata', []):
caption_url = caption.get('source_url')
if not caption_url:
continue
subtitles.setdefault(caption.get('language', 'en'), []).append({
'url': caption_url,
'ext': determine_ext(caption_url, 'vtt'),
})
elif asset.get('type') == 'image':
asset_location = asset.get('location')
if not asset_location:
continue
thumbnails.append({
'url': asset_location,
'width': int_or_none(asset.get('width')),
'height': int_or_none(asset.get('height')),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnails': thumbnails,
'description': video_data.get('short_description'),
'like_count': int_or_none(video_data.get('like_count')),
'timestamp': parse_iso8601(video_data.get('released_at')),
'series': series,
'episode': episode,
'season': season,
'season_id': season_id,
'season_number': season_number,
'episode_number': episode_number,
'subtitles': subtitles,
'age_limit': parse_age_limit(video_data.get('rating')),
}

33
youtube_dl/extractor/hark.py
View File

@ -1,33 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class HarkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hark\.com/clips/(?P<id>.+?)-.+'
_TEST = {
'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
'md5': '6783a58491b47b92c7c1af5a77d4cbee',
'info_dict': {
'id': 'mmbzyhkgny',
'ext': 'mp3',
'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
'duration': 11,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'http://www.hark.com/clips/%s.json' % video_id, video_id)
return {
'id': video_id,
'url': data['url'],
'title': data['name'],
'description': data.get('description'),
'thumbnail': data.get('image_original'),
'duration': data.get('duration'),
}

71
youtube_dl/extractor/hellporno.py
View File

@ -1,12 +1,11 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
int_or_none,
merge_dicts,
remove_end,
determine_ext,
unified_timestamp,
)
@ -14,15 +13,21 @@ class HellPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
'md5': '1fee339c610d2049699ef2aa699439f1',
'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
'info_dict': {
'id': '149116',
'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
'ext': 'mp4',
'title': 'Dixie is posing with naked ass very erotic',
'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
'categories': list,
'thumbnail': r're:https?://.*\.jpg$',
'duration': 240,
'timestamp': 1398762720,
'upload_date': '20140429',
'view_count': int,
'age_limit': 18,
}
},
}, {
'url': 'http://hellporno.net/v/186271/',
'only_matching': True,
@ -36,40 +41,36 @@ class HellPornoIE(InfoExtractor):
title = remove_end(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), ' - Hell Porno')
flashvars = self._parse_json(self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
display_id, transform_source=js_to_json)
info = self._parse_html5_media_entries(url, webpage, display_id)[0]
self._sort_formats(info['formats'])
video_id = flashvars.get('video_id')
thumbnail = flashvars.get('preview_url')
ext = determine_ext(flashvars.get('postfix'), 'mp4')
formats = []
for video_url_key in ['video_url', 'video_alt_url']:
video_url = flashvars.get(video_url_key)
if not video_url:
continue
video_text = flashvars.get('%s_text' % video_url_key)
fmt = {
'url': video_url,
'ext': ext,
'format_id': video_text,
}
m = re.search(r'^(?P<height>\d+)[pP]', video_text)
if m:
fmt['height'] = int(m.group('height'))
formats.append(fmt)
self._sort_formats(formats)
categories = self._html_search_meta(
video_id = self._search_regex(
(r'chs_object\s*=\s*["\'](\d+)',
r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
default=display_id)
description = self._search_regex(
r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
'description', fatal=False)
categories = [
c.strip()
for c in self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
if c.strip()]
duration = int_or_none(self._og_search_property(
'video:duration', webpage, fatal=False))
timestamp = unified_timestamp(self._og_search_property(
'video:release_date', webpage, fatal=False))
view_count = int_or_none(self._search_regex(
r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
return {
return merge_dicts(info, {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'description': description,
'categories': categories,
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'age_limit': 18,
'formats': formats,
}
})

9
youtube_dl/extractor/hotstar.py
View File

@ -118,6 +118,7 @@ class HotStarIE(HotStarBaseIE):
if video_data.get('drmProtected'):
raise ExtractorError('This video is DRM protected.', expected=True)
headers = {'Referer': url}
formats = []
geo_restricted = False
playback_sets = self._call_api_v2('h/v2/play', video_id)['playBackSets']
@ -137,10 +138,11 @@ class HotStarIE(HotStarBaseIE):
if 'package:hls' in tags or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls'))
entry_protocol='m3u8_native',
m3u8_id='hls', headers=headers))
elif 'package:dash' in tags or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash'))
format_url, video_id, mpd_id='dash', headers=headers))
elif ext == 'f4m':
# produce broken files
pass
@ -158,6 +160,9 @@ class HotStarIE(HotStarBaseIE):
self.raise_geo_restricted(countries=['IN'])
self._sort_formats(formats)
for f in formats:
f.setdefault('http_headers', {}).update(headers)
return {
'id': video_id,
'title': title,

85
youtube_dl/extractor/iconosquare.py
View File

@ -1,85 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
get_element_by_id,
remove_end,
)
class IconosquareIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
_TEST = {
'url': 'http://statigr.am/p/522207370455279102_24101272',
'md5': '6eb93b882a3ded7c378ee1d6884b1814',
'info_dict': {
'id': '522207370455279102_24101272',
'ext': 'mp4',
'title': 'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
'timestamp': 1376471991,
'upload_date': '20130814',
'uploader': 'aguynamedpatrick',
'uploader_id': '24101272',
'comment_count': int,
'like_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
media = self._parse_json(
get_element_by_id('mediaJson', webpage),
video_id)
formats = [{
'url': f['url'],
'format_id': format_id,
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height'))
} for format_id, f in media['videos'].items()]
self._sort_formats(formats)
title = remove_end(self._og_search_title(webpage), ' - via Iconosquare')
timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
description = media.get('caption', {}).get('text')
uploader = media.get('user', {}).get('username')
uploader_id = media.get('user', {}).get('id')
comment_count = int_or_none(media.get('comments', {}).get('count'))
like_count = int_or_none(media.get('likes', {}).get('count'))
thumbnails = [{
'url': t['url'],
'id': thumbnail_id,
'width': int_or_none(t.get('width')),
'height': int_or_none(t.get('height'))
} for thumbnail_id, t in media.get('images', {}).items()]
comments = [{
'id': comment.get('id'),
'text': comment['text'],
'timestamp': int_or_none(comment.get('created_time')),
'author': comment.get('from', {}).get('full_name'),
'author_id': comment.get('from', {}).get('username'),
} for comment in media.get('comments', {}).get('data', []) if 'text' in comment]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnails': thumbnails,
'timestamp': timestamp,
'uploader': uploader,
'uploader_id': uploader_id,
'comment_count': comment_count,
'like_count': like_count,
'formats': formats,
'comments': comments,
}

58
youtube_dl/extractor/imdb.py
View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals
import base64
import json
import re
from .common import InfoExtractor
@ -8,6 +10,7 @@ from ..utils import (
mimetype2ext,
parse_duration,
qualities,
try_get,
url_or_none,
)
@ -15,15 +18,16 @@ from ..utils import (
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
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 = [{
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
'title': 'No. 2 from Ice Age: Continental Drift (2012)',
'title': 'No. 2',
'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
'duration': 152,
}
}, {
'url': 'http://www.imdb.com/video/_/vi2524815897',
@ -47,21 +51,23 @@ class ImdbIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.imdb.com/videoplayer/vi' + video_id, video_id)
video_metadata = self._parse_json(self._search_regex(
r'window\.IMDbReactInitialState\.push\(({.+?})\);', webpage,
'video metadata'), video_id)['videos']['videoMetadata']['vi' + video_id]
title = self._html_search_meta(
['og:title', 'twitter:title'], webpage) or self._html_search_regex(
r'<title>(.+?)</title>', webpage, 'title', fatal=False) or video_metadata['title']
data = self._download_json(
'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id,
query={
'key': base64.b64encode(json.dumps({
'type': 'VIDEO_PLAYER',
'subType': 'FORCE_LEGACY',
'id': 'vi%s' % video_id,
}).encode()).decode(),
})[0]
quality = qualities(('SD', '480p', '720p', '1080p'))
formats = []
for encoding in video_metadata.get('encodings', []):
for encoding in data['videoLegacyEncodings']:
if not encoding or not isinstance(encoding, dict):
continue
video_url = url_or_none(encoding.get('videoUrl'))
video_url = url_or_none(encoding.get('url'))
if not video_url:
continue
ext = mimetype2ext(encoding.get(
@ -69,7 +75,7 @@ class ImdbIE(InfoExtractor):
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
preference=1, m3u8_id='hls', fatal=False))
continue
format_id = encoding.get('definition')
formats.append({
@ -80,13 +86,33 @@ class ImdbIE(InfoExtractor):
})
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 {
'id': video_id,
'title': title,
'alt_title': info.get('videoSubTitle'),
'formats': formats,
'description': video_metadata.get('description'),
'thumbnail': video_metadata.get('slate', {}).get('url'),
'duration': parse_duration(video_metadata.get('duration')),
'description': info.get('videoDescription'),
'thumbnail': url_or_none(try_get(
video_metadata, lambda x: x['videoSlate']['source'])),
'duration': parse_duration(info.get('videoRuntime')),
}

133
youtube_dl/extractor/imggaming.py Normal file
View File

@ -0,0 +1,133 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
int_or_none,
str_or_none,
try_get,
)
class ImgGamingBaseIE(InfoExtractor):
_API_BASE = 'https://dce-frontoffice.imggaming.com/api/v2/'
_API_KEY = '857a1e5d-e35e-4fdf-805b-a87b6f8364bf'
_HEADERS = None
_MANIFEST_HEADERS = {'Accept-Encoding': 'identity'}
_REALM = None
_VALID_URL_TEMPL = r'https?://(?P<domain>%s)/(?P<type>live|playlist|video)/(?P<id>\d+)(?:\?.*?\bplaylistId=(?P<playlist_id>\d+))?'
def _real_initialize(self):
self._HEADERS = {
'Realm': 'dce.' + self._REALM,
'x-api-key': self._API_KEY,
}
email, password = self._get_login_info()
if email is None:
self.raise_login_required()
p_headers = self._HEADERS.copy()
p_headers['Content-Type'] = 'application/json'
self._HEADERS['Authorization'] = 'Bearer ' + self._download_json(
self._API_BASE + 'login',
None, 'Logging in', data=json.dumps({
'id': email,
'secret': password,
}).encode(), headers=p_headers)['authorisationToken']
def _call_api(self, path, media_id):
return self._download_json(
self._API_BASE + path + media_id, media_id, headers=self._HEADERS)
def _extract_dve_api_url(self, media_id, media_type):
stream_path = 'stream'
if media_type == 'video':
stream_path += '/vod/'
else:
stream_path += '?eventId='
try:
return self._call_api(
stream_path, media_id)['playerUrlCallback']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
raise ExtractorError(
self._parse_json(e.cause.read().decode(), media_id)['messages'][0],
expected=True)
raise
def _real_extract(self, url):
domain, media_type, media_id, playlist_id = re.match(self._VALID_URL, url).groups()
if playlist_id:
if self._downloader.params.get('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % media_id)
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
media_type, media_id = 'playlist', playlist_id
if media_type == 'playlist':
playlist = self._call_api('vod/playlist/', media_id)
entries = []
for video in try_get(playlist, lambda x: x['videos']['vods']) or []:
video_id = str_or_none(video.get('id'))
if not video_id:
continue
entries.append(self.url_result(
'https://%s/video/%s' % (domain, video_id),
self.ie_key(), video_id))
return self.playlist_result(
entries, media_id, playlist.get('title'),
playlist.get('description'))
dve_api_url = self._extract_dve_api_url(media_id, media_type)
video_data = self._download_json(dve_api_url, media_id)
is_live = media_type == 'live'
if is_live:
title = self._live_title(self._call_api('event/', media_id)['title'])
else:
title = video_data['name']
formats = []
for proto in ('hls', 'dash'):
media_url = video_data.get(proto + 'Url') or try_get(video_data, lambda x: x[proto]['url'])
if not media_url:
continue
if proto == 'hls':
m3u8_formats = self._extract_m3u8_formats(
media_url, media_id, 'mp4', 'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False, headers=self._MANIFEST_HEADERS)
for f in m3u8_formats:
f.setdefault('http_headers', {}).update(self._MANIFEST_HEADERS)
formats.append(f)
else:
formats.extend(self._extract_mpd_formats(
media_url, media_id, mpd_id='dash', fatal=False,
headers=self._MANIFEST_HEADERS))
self._sort_formats(formats)
subtitles = {}
for subtitle in video_data.get('subtitles', []):
subtitle_url = subtitle.get('url')
if not subtitle_url:
continue
subtitles.setdefault(subtitle.get('lang', 'en_US'), []).append({
'url': subtitle_url,
})
return {
'id': media_id,
'title': title,
'formats': formats,
'thumbnail': video_data.get('thumbnailUrl'),
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'tags': video_data.get('tags'),
'is_live': is_live,
'subtitles': subtitles,
}

86
youtube_dl/extractor/internetvideoarchive.py
View File

@ -1,15 +1,13 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
from ..utils import (
determine_ext,
int_or_none,
xpath_text,
)
class InternetVideoArchiveIE(InfoExtractor):
@ -20,7 +18,7 @@ class InternetVideoArchiveIE(InfoExtractor):
'info_dict': {
'id': '194487',
'ext': 'mp4',
'title': 'KICK-ASS 2',
'title': 'Kick-Ass 2',
'description': 'md5:c189d5b7280400630a1d3dd17eaa8d8a',
},
'params': {
@ -33,68 +31,34 @@ class InternetVideoArchiveIE(InfoExtractor):
def _build_json_url(query):
return 'http://video.internetvideoarchive.net/player/6/configuration.ashx?' + query
@staticmethod
def _build_xml_url(query):
return 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?' + query
def _real_extract(self, url):
query = compat_urlparse.urlparse(url).query
query_dic = compat_parse_qs(query)
video_id = query_dic['publishedid'][0]
if '/player/' in url:
configuration = self._download_json(url, video_id)
# There are multiple videos in the playlist whlie only the first one
# matches the video played in browsers
video_info = configuration['playlist'][0]
title = video_info['title']
formats = []
for source in video_info['sources']:
file_url = source['file']
if determine_ext(file_url) == 'm3u8':
m3u8_formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
file_url = m3u8_formats[0]['url']
query = compat_parse_qs(compat_urlparse.urlparse(url).query)
video_id = query['publishedid'][0]
data = self._download_json(
'https://video.internetvideoarchive.net/videojs7/videojs7.ivasettings.ashx',
video_id, data=json.dumps({
'customerid': query['customerid'][0],
'publishedid': video_id,
}).encode())
title = data['Title']
formats = self._extract_m3u8_formats(
data['VideoUrl'], video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
file_url = formats[0]['url']
if '.ism/' in file_url:
replace_url = lambda x: re.sub(r'\.ism/[^?]+', '.ism/' + x, file_url)
formats.extend(self._extract_f4m_formats(
file_url.replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False))
replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
file_url.replace('.m3u8', '.mpd'),
video_id, mpd_id='dash', fatal=False))
else:
a_format = {
'url': file_url,
}
if source.get('label') and source['label'][-4:] == ' kbs':
tbr = int_or_none(source['label'][:-4])
a_format.update({
'tbr': tbr,
'format_id': 'http-%d' % tbr,
})
formats.append(a_format)
replace_url('.mpd'), video_id, mpd_id='dash', fatal=False))
formats.extend(self._extract_ism_formats(
replace_url('Manifest'), video_id, ism_id='mss', fatal=False))
self._sort_formats(formats)
description = video_info.get('description')
thumbnail = video_info.get('image')
else:
configuration = self._download_xml(url, video_id)
formats = [{
'url': xpath_text(configuration, './file', 'file URL', fatal=True),
}]
thumbnail = xpath_text(configuration, './image', 'thumbnail')
title = 'InternetVideoArchive video %s' % video_id
description = None
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'thumbnail': data.get('PosterUrl'),
'description': data.get('Description'),
}

97
youtube_dl/extractor/ivi.py
View File

@ -1,8 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
import re
import sys
from .common import InfoExtractor
from ..utils import (
@ -18,6 +19,8 @@ class IviIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ivi\.(?:ru|tv)/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['RU']
_LIGHT_KEY = b'\xf1\x02\x32\xb7\xbc\x5c\x7a\xe8\xf7\x96\xc1\x33\x2b\x27\xa1\x8c'
_LIGHT_URL = 'https://api.ivi.ru/light/'
_TESTS = [
# Single movie
@ -80,48 +83,96 @@ class IviIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
data = {
data = json.dumps({
'method': 'da.content.get',
'params': [
video_id, {
'site': 's183',
'site': 's%d',
'referrer': 'http://www.ivi.ru/watch/%s' % video_id,
'contentid': video_id
}
]
})
bundled = hasattr(sys, 'frozen')
for site in (353, 183):
content_data = (data % site).encode()
if site == 353:
if bundled:
continue
try:
from Cryptodome.Cipher import Blowfish
from Cryptodome.Hash import CMAC
pycryptodomex_found = True
except ImportError:
pycryptodomex_found = False
continue
timestamp = (self._download_json(
self._LIGHT_URL, video_id,
'Downloading timestamp JSON', data=json.dumps({
'method': 'da.timestamp.get',
'params': []
}).encode(), fatal=False) or {}).get('result')
if not timestamp:
continue
query = {
'ts': timestamp,
'sign': CMAC.new(self._LIGHT_KEY, timestamp.encode() + content_data, Blowfish).hexdigest(),
}
else:
query = {}
video_json = self._download_json(
'http://api.digitalaccess.ru/api/json/', video_id,
'Downloading video JSON', data=json.dumps(data))
self._LIGHT_URL, video_id,
'Downloading video JSON', data=content_data, query=query)
if 'error' in video_json:
error = video_json['error']
origin = error['origin']
error = video_json.get('error')
if error:
origin = error.get('origin')
message = error.get('message') or error.get('user_message')
extractor_msg = 'Unable to download video %s'
if origin == 'NotAllowedForLocation':
self.raise_geo_restricted(
msg=error['message'], countries=self._GEO_COUNTRIES)
self.raise_geo_restricted(message, self._GEO_COUNTRIES)
elif origin == 'NoRedisValidData':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
extractor_msg = 'Video %s does not exist'
elif site == 353:
continue
elif bundled:
raise ExtractorError(
'Unable to download video %s: %s' % (video_id, error['message']),
'This feature does not work from bundled exe. Run youtube-dl from sources.',
expected=True)
elif not pycryptodomex_found:
raise ExtractorError(
'pycryptodomex not found. Please install it.',
expected=True)
elif message:
extractor_msg += ': ' + message
raise ExtractorError(extractor_msg % video_id, expected=True)
else:
break
result = video_json['result']
title = result['title']
quality = qualities(self._KNOWN_FORMATS)
formats = [{
'url': x['url'],
'format_id': x.get('content_format'),
'quality': quality(x.get('content_format')),
} for x in result['files'] if x.get('url')]
formats = []
for f in result.get('files', []):
f_url = f.get('url')
content_format = f.get('content_format')
if not f_url or '-MDRM-' in content_format or '-FPS-' in content_format:
continue
formats.append({
'url': f_url,
'format_id': content_format,
'quality': quality(content_format),
'filesize': int_or_none(f.get('size_in_bytes')),
})
self._sort_formats(formats)
title = result['title']
duration = int_or_none(result.get('duration'))
compilation = result.get('compilation')
episode = title if compilation else None
@ -158,7 +209,7 @@ class IviIE(InfoExtractor):
'episode_number': episode_number,
'thumbnails': thumbnails,
'description': description,
'duration': duration,
'duration': int_or_none(result.get('duration')),
'formats': formats,
}
@ -188,7 +239,7 @@ class IviCompilationIE(InfoExtractor):
self.url_result(
'http://www.ivi.ru/watch/%s/%s' % (compilation_id, serie), IviIE.ie_key())
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):
mobj = re.match(self._VALID_URL, url)

157
youtube_dl/extractor/jamendo.py
View File

@ -1,38 +1,26 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import hashlib
import random
from ..compat import compat_urlparse
from ..compat import compat_str
from .common import InfoExtractor
from ..utils import parse_duration
from ..utils import (
clean_html,
int_or_none,
try_get,
)
class JamendoBaseIE(InfoExtractor):
def _extract_meta(self, webpage, fatal=True):
title = self._og_search_title(
webpage, default=None) or self._search_regex(
r'<title>([^<]+)', webpage,
'title', default=None)
if title:
title = self._search_regex(
r'(.+?)\s*\|\s*Jamendo Music', title, 'title', default=None)
if not title:
title = self._html_search_meta(
'name', webpage, 'title', fatal=fatal)
mobj = re.search(r'(.+) - (.+)', title or '')
artist, second = mobj.groups() if mobj else [None] * 2
return title, artist, second
class JamendoIE(JamendoBaseIE):
class JamendoIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
licensing\.jamendo\.com/[^/]+|
(?:www\.)?jamendo\.com
)
/track/(?P<id>[0-9]+)/(?P<display_id>[^/?#&]+)
/track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))?
'''
_TESTS = [{
'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
@ -45,7 +33,9 @@ class JamendoIE(JamendoBaseIE):
'artist': 'Maya Filipič',
'track': 'Stories from Emona I',
'duration': 210,
'thumbnail': r're:^https?://.*\.jpg'
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1217438117,
'upload_date': '20080730',
}
}, {
'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
@ -53,15 +43,20 @@ class JamendoIE(JamendoBaseIE):
}]
def _real_extract(self, url):
mobj = self._VALID_URL_RE.match(url)
track_id = mobj.group('id')
display_id = mobj.group('display_id')
track_id, display_id = self._VALID_URL_RE.match(url).groups()
webpage = self._download_webpage(
'https://www.jamendo.com/track/%s/%s' % (track_id, display_id),
display_id)
title, artist, track = self._extract_meta(webpage)
'https://www.jamendo.com/track/' + track_id, track_id)
models = self._parse_json(self._html_search_regex(
r"data-bundled-models='([^']+)",
webpage, 'bundled models'), track_id)
track = models['track']['models'][0]
title = track_name = track['name']
get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
artist = get_model('artist')
artist_name = artist.get('name')
if artist_name:
title = '%s - %s' % (artist_name, title)
album = get_model('album')
formats = [{
'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@ -77,31 +72,58 @@ class JamendoIE(JamendoBaseIE):
))]
self._sort_formats(formats)
thumbnail = self._html_search_meta(
'image', webpage, 'thumbnail', fatal=False)
duration = parse_duration(self._search_regex(
r'<span[^>]+itemprop=["\']duration["\'][^>]+content=["\'](.+?)["\']',
webpage, 'duration', fatal=False))
urls = []
thumbnails = []
for _, covers in track.get('cover', {}).items():
for cover_id, cover_url in covers.items():
if not cover_url or cover_url in urls:
continue
urls.append(cover_url)
size = int_or_none(cover_id.lstrip('size'))
thumbnails.append({
'id': cover_id,
'url': cover_url,
'width': size,
'height': size,
})
tags = []
for tag in track.get('tags', []):
tag_name = tag.get('name')
if not tag_name:
continue
tags.append(tag_name)
stats = track.get('stats') or {}
return {
'id': track_id,
'display_id': display_id,
'thumbnail': thumbnail,
'thumbnails': thumbnails,
'title': title,
'duration': duration,
'artist': artist,
'track': track,
'formats': formats
'description': track.get('description'),
'duration': int_or_none(track.get('duration')),
'artist': artist_name,
'track': track_name,
'album': album.get('name'),
'formats': formats,
'license': '-'.join(track.get('licenseCC', [])) or None,
'timestamp': int_or_none(track.get('dateCreated')),
'view_count': int_or_none(stats.get('listenedAll')),
'like_count': int_or_none(stats.get('favorited')),
'average_rating': int_or_none(stats.get('averageNote')),
'tags': tags,
}
class JamendoAlbumIE(JamendoBaseIE):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)/(?P<display_id>[\w-]+)'
class JamendoAlbumIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
'info_dict': {
'id': '121486',
'title': 'Shearer - Duck On Cover'
'title': 'Duck On Cover',
'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239',
},
'playlist': [{
'md5': 'e1a2fcb42bda30dfac990212924149a8',
@ -111,6 +133,8 @@ class JamendoAlbumIE(JamendoBaseIE):
'title': 'Shearer - Warmachine',
'artist': 'Shearer',
'track': 'Warmachine',
'timestamp': 1368089771,
'upload_date': '20130509',
}
}, {
'md5': '1f358d7b2f98edfe90fd55dac0799d50',
@ -120,6 +144,8 @@ class JamendoAlbumIE(JamendoBaseIE):
'title': 'Shearer - Without Your Ghost',
'artist': 'Shearer',
'track': 'Without Your Ghost',
'timestamp': 1368089771,
'upload_date': '20130509',
}
}],
'params': {
@ -127,24 +153,35 @@ class JamendoAlbumIE(JamendoBaseIE):
}
}
def _call_api(self, resource, resource_id):
path = '/api/%ss' % resource
rand = compat_str(random.random())
return self._download_json(
'https://www.jamendo.com' + path, resource_id, query={
'id[]': resource_id,
}, headers={
'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
})[0]
def _real_extract(self, url):
mobj = self._VALID_URL_RE.match(url)
album_id = mobj.group('id')
album_id = self._match_id(url)
album = self._call_api('album', album_id)
album_name = album.get('name')
webpage = self._download_webpage(url, mobj.group('display_id'))
title, artist, album = self._extract_meta(webpage, fatal=False)
entries = [{
entries = []
for track in album.get('tracks', []):
track_id = track.get('id')
if not track_id:
continue
track_id = compat_str(track_id)
entries.append({
'_type': 'url_transparent',
'url': compat_urlparse.urljoin(url, m.group('path')),
'url': 'https://www.jamendo.com/track/' + track_id,
'ie_key': JamendoIE.ie_key(),
'id': self._search_regex(
r'/track/(\d+)', m.group('path'), 'track id', default=None),
'artist': artist,
'album': album,
} for m in re.finditer(
r'<a[^>]+href=(["\'])(?P<path>(?:(?!\1).)+)\1[^>]+class=["\'][^>]*js-trackrow-albumpage-link',
webpage)]
'id': track_id,
'album': album_name,
})
return self.playlist_result(entries, album_id, title)
return self.playlist_result(
entries, album_id, album_name,
clean_html(try_get(album, lambda x: x['description']['en'], compat_str)))

68
youtube_dl/extractor/jpopsukitv.py
View File

@ -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),
}

60
youtube_dl/extractor/kakao.py
View File

@ -6,14 +6,15 @@ from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
strip_or_none,
unified_timestamp,
update_url_query,
)
class KakaoIE(InfoExtractor):
_VALID_URL = r'https?://tv\.kakao\.com/channel/(?P<channel>\d+)/cliplink/(?P<id>\d+)'
_API_BASE = 'http://tv.kakao.com/api/v1/ft/cliplinks'
_VALID_URL = r'https?://(?:play-)?tv\.kakao\.com/(?:channel/\d+|embed/player)/cliplink/(?P<id>\d+|[^?#&]+@my)'
_API_BASE_TMPL = 'http://tv.kakao.com/api/v1/ft/cliplinks/%s/'
_TESTS = [{
'url': 'http://tv.kakao.com/channel/2671005/cliplink/301965083',
@ -36,7 +37,7 @@ class KakaoIE(InfoExtractor):
'description': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)\r\n\r\n[쇼! 음악중심] 20160611, 507회',
'title': '러블리즈 - Destiny (나의 지구) (Lovelyz - Destiny)',
'uploader_id': 2653210,
'uploader': '쇼 음악중심',
'uploader': '쇼! 음악중심',
'timestamp': 1485684628,
'upload_date': '20170129',
}
@ -44,6 +45,8 @@ class KakaoIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = video_id.rstrip('@my')
api_base = self._API_BASE_TMPL % video_id
player_header = {
'Referer': update_url_query(
@ -55,20 +58,23 @@ class KakaoIE(InfoExtractor):
})
}
QUERY_COMMON = {
query = {
'player': 'monet_html5',
'referer': url,
'uuid': '',
'service': 'kakao_tv',
'section': '',
'dteType': 'PC',
'fields': ','.join([
'-*', 'tid', 'clipLink', 'displayTitle', 'clip', 'title',
'description', 'channelId', 'createTime', 'duration', 'playCount',
'likeCount', 'commentCount', 'tagList', 'channel', 'name',
'clipChapterThumbnailList', 'thumbnailUrl', 'timeInSec', 'isDefault',
'videoOutputList', 'width', 'height', 'kbps', 'profile', 'label'])
}
query = QUERY_COMMON.copy()
query['fields'] = 'clipLink,clip,channel,hasPlusFriend,-service,-tagList'
impress = self._download_json(
'%s/%s/impress' % (self._API_BASE, video_id),
video_id, 'Downloading video info',
api_base + 'impress', display_id, 'Downloading video info',
query=query, headers=player_header)
clip_link = impress['clipLink']
@ -76,32 +82,22 @@ class KakaoIE(InfoExtractor):
title = clip.get('title') or clip_link.get('displayTitle')
tid = impress.get('tid', '')
query = QUERY_COMMON.copy()
query.update({
'tid': tid,
'profile': 'HIGH',
})
raw = self._download_json(
'%s/%s/raw' % (self._API_BASE, video_id),
video_id, 'Downloading video formats info',
query=query, headers=player_header)
query['tid'] = impress.get('tid', '')
formats = []
for fmt in raw.get('outputList', []):
for fmt in clip.get('videoOutputList', []):
try:
profile_name = fmt['profile']
if profile_name == 'AUDIO':
continue
query.update({
'profile': profile_name,
'fields': '-*,url',
})
fmt_url_json = self._download_json(
'%s/%s/raw/videolocation' % (self._API_BASE, video_id),
video_id,
api_base + 'raw/videolocation', display_id,
'Downloading video URL for profile %s' % profile_name,
query={
'service': 'kakao_tv',
'section': '',
'tid': tid,
'profile': profile_name
}, headers=player_header, fatal=False)
query=query, headers=player_header, fatal=False)
if fmt_url_json is None:
continue
@ -113,7 +109,8 @@ class KakaoIE(InfoExtractor):
'width': int_or_none(fmt.get('width')),
'height': int_or_none(fmt.get('height')),
'format_note': fmt.get('label'),
'filesize': int_or_none(fmt.get('filesize'))
'filesize': int_or_none(fmt.get('filesize')),
'tbr': int_or_none(fmt.get('kbps')),
})
except KeyError:
pass
@ -134,9 +131,9 @@ class KakaoIE(InfoExtractor):
})
return {
'id': video_id,
'id': display_id,
'title': title,
'description': clip.get('description'),
'description': strip_or_none(clip.get('description')),
'uploader': clip_link.get('channel', {}).get('name'),
'uploader_id': clip_link.get('channelId'),
'thumbnails': thumbs,
@ -146,4 +143,5 @@ class KakaoIE(InfoExtractor):
'like_count': int_or_none(clip.get('likeCount')),
'comment_count': int_or_none(clip.get('commentCount')),
'formats': formats,
'tags': clip.get('tagList'),
}

39
youtube_dl/extractor/keek.py
View File

@ -1,39 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class KeekIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?keek\.com/keek/(?P<id>\w+)'
IE_NAME = 'keek'
_TEST = {
'url': 'https://www.keek.com/keek/NODfbab',
'md5': '9b0636f8c0f7614afa4ea5e4c6e57e83',
'info_dict': {
'id': 'NODfbab',
'ext': 'mp4',
'title': 'md5:35d42050a3ece241d5ddd7fdcc6fd896',
'uploader': 'ytdl',
'uploader_id': 'eGT5bab',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
return {
'id': video_id,
'url': self._og_search_video_url(webpage),
'ext': 'mp4',
'title': self._og_search_description(webpage).strip(),
'thumbnail': self._og_search_thumbnail(webpage),
'uploader': self._search_regex(
r'data-username=(["\'])(?P<uploader>.+?)\1', webpage,
'uploader', fatal=False, group='uploader'),
'uploader_id': self._search_regex(
r'data-user-id=(["\'])(?P<uploader_id>.+?)\1', webpage,
'uploader id', fatal=False, group='uploader_id'),
}

221
youtube_dl/extractor/kinja.py Normal file
View File

@ -0,0 +1,221 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
int_or_none,
parse_iso8601,
strip_or_none,
try_get,
unescapeHTML,
urljoin,
)
class KinjaEmbedIE(InfoExtractor):
IENAME = 'kinja:embed'
_DOMAIN_REGEX = r'''(?:[^.]+\.)?
(?:
avclub|
clickhole|
deadspin|
gizmodo|
jalopnik|
jezebel|
kinja|
kotaku|
lifehacker|
splinternews|
the(?:inventory|onion|root|takeout)
)\.com'''
_COMMON_REGEX = r'''/
(?:
ajax/inset|
embed/video
)/iframe\?.*?\bid='''
_VALID_URL = r'''(?x)https?://%s%s
(?P<type>
fb|
imgur|
instagram|
jwp(?:layer)?-video|
kinjavideo|
mcp|
megaphone|
ooyala|
soundcloud(?:-playlist)?|
tumblr-post|
twitch-stream|
twitter|
ustream-channel|
vimeo|
vine|
youtube-(?:list|video)
)-(?P<id>[^&]+)''' % (_DOMAIN_REGEX, _COMMON_REGEX)
_TESTS = [{
'url': 'https://kinja.com/ajax/inset/iframe?id=fb-10103303356633621',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=kinjavideo-100313',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=megaphone-PPY1300931075',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=ooyala-xzMXhleDpopuT0u1ijt_qZj3Va-34pEX%2FZTIxYmJjZDM2NWYzZDViZGRiOWJjYzc5',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-128574047',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=soundcloud-playlist-317413750',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=tumblr-post-160130699814-daydreams-at-midnight',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=twitch-stream-libratus_extra',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=twitter-1068875942473404422',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=ustream-channel-10414700',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=vimeo-120153502',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=vine-5BlvV5qqPrD',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-list-BCQ3KyrPjgA/PLE6509247C270A72E',
'only_matching': True,
}, {
'url': 'https://kinja.com/ajax/inset/iframe?id=youtube-video-00QyL0AgPAE',
'only_matching': True,
}]
_JWPLATFORM_PROVIDER = ('cdn.jwplayer.com/v2/media/', 'JWPlatform')
_PROVIDER_MAP = {
'fb': ('facebook.com/video.php?v=', 'Facebook'),
'imgur': ('imgur.com/', 'Imgur'),
'instagram': ('instagram.com/p/', 'Instagram'),
'jwplayer-video': _JWPLATFORM_PROVIDER,
'jwp-video': _JWPLATFORM_PROVIDER,
'megaphone': ('player.megaphone.fm/', 'Generic'),
'ooyala': ('player.ooyala.com/player.js?embedCode=', 'Ooyala'),
'soundcloud': ('api.soundcloud.com/tracks/', 'Soundcloud'),
'soundcloud-playlist': ('api.soundcloud.com/playlists/', 'SoundcloudPlaylist'),
'tumblr-post': ('%s.tumblr.com/post/%s', 'Tumblr'),
'twitch-stream': ('twitch.tv/', 'TwitchStream'),
'twitter': ('twitter.com/i/cards/tfw/v1/', 'TwitterCard'),
'ustream-channel': ('ustream.tv/embed/', 'Ustream'),
'vimeo': ('vimeo.com/', 'Vimeo'),
'vine': ('vine.co/v/', 'Vine'),
'youtube-list': ('youtube.com/embed/%s?list=%s', 'YoutubePlaylist'),
'youtube-video': ('youtube.com/embed/', 'Youtube'),
}
@staticmethod
def _extract_urls(webpage, url):
return [urljoin(url, unescapeHTML(mobj.group('url'))) for mobj in re.finditer(
r'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//%s)?%s(?:(?!\1).)+)\1' % (KinjaEmbedIE._DOMAIN_REGEX, KinjaEmbedIE._COMMON_REGEX),
webpage)]
def _real_extract(self, url):
video_type, video_id = re.match(self._VALID_URL, url).groups()
provider = self._PROVIDER_MAP.get(video_type)
if provider:
video_id = compat_urllib_parse_unquote(video_id)
if video_type == 'tumblr-post':
video_id, blog = video_id.split('-', 1)
result_url = provider[0] % (blog, video_id)
elif video_type == 'youtube-list':
video_id, playlist_id = video_id.split('/')
result_url = provider[0] % (video_id, playlist_id)
else:
if video_type == 'ooyala':
video_id = video_id.split('/')[0]
result_url = provider[0] + video_id
return self.url_result('http://' + result_url, provider[1])
if video_type == 'kinjavideo':
data = self._download_json(
'https://kinja.com/api/core/video/views/videoById',
video_id, query={'videoId': video_id})['data']
title = data['title']
formats = []
for k in ('signedPlaylist', 'streaming'):
m3u8_url = data.get(k + 'Url')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
self._sort_formats(formats)
thumbnail = None
poster = data.get('poster') or {}
poster_id = poster.get('id')
if poster_id:
thumbnail = 'https://i.kinja-img.com/gawker-media/image/upload/%s.%s' % (poster_id, poster.get('format') or 'jpg')
return {
'id': video_id,
'title': title,
'description': strip_or_none(data.get('description')),
'formats': formats,
'tags': data.get('tags'),
'timestamp': int_or_none(try_get(
data, lambda x: x['postInfo']['publishTimeMillis']), 1000),
'thumbnail': thumbnail,
'uploader': data.get('network'),
}
else:
video_data = self._download_json(
'https://api.vmh.univision.com/metadata/v1/content/' + video_id,
video_id)['videoMetadata']
iptc = video_data['photoVideoMetadataIPTC']
title = iptc['title']['en']
fmg = video_data.get('photoVideoMetadata_fmg') or {}
tvss_domain = fmg.get('tvssDomain') or 'https://auth.univision.com'
data = self._download_json(
tvss_domain + '/api/v3/video-auth/url-signature-tokens',
video_id, query={'mcpids': video_id})['data'][0]
formats = []
rendition_url = data.get('renditionUrl')
if rendition_url:
formats = self._extract_m3u8_formats(
rendition_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
fallback_rendition_url = data.get('fallbackRenditionUrl')
if fallback_rendition_url:
formats.append({
'format_id': 'fallback',
'tbr': int_or_none(self._search_regex(
r'_(\d+)\.mp4', fallback_rendition_url,
'bitrate', default=None)),
'url': fallback_rendition_url,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': try_get(iptc, lambda x: x['cloudinaryLink']['link'], compat_str),
'uploader': fmg.get('network'),
'duration': int_or_none(iptc.get('fileDuration')),
'formats': formats,
'description': try_get(iptc, lambda x: x['description']['en'], compat_str),
'timestamp': parse_iso8601(iptc.get('dateReleased')),
}

73
youtube_dl/extractor/kontrtube.py
View File

@ -1,73 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
)
class KontrTubeIE(InfoExtractor):
IE_NAME = 'kontrtube'
IE_DESC = 'KontrTube.ru - Труба зовёт'
_VALID_URL = r'https?://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/(?P<display_id>[^/]+)/'
_TEST = {
'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
'md5': '975a991a4926c9a85f383a736a2e6b80',
'info_dict': {
'id': '2678',
'display_id': 'nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag',
'ext': 'mp4',
'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
'duration': 270,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(
url, display_id, 'Downloading page')
video_url = self._search_regex(
r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
thumbnail = self._search_regex(
r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False)
title = self._html_search_regex(
r'(?s)<h2>(.+?)</h2>', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description')
duration = self._search_regex(
r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False)
if duration:
duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec'))
view_count = self._search_regex(
r'Просмотров: <em>([^<]+)</em>',
webpage, 'view count', fatal=False)
if view_count:
view_count = int_or_none(view_count.replace(' ', ''))
comment_count = int_or_none(self._search_regex(
r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'thumbnail': thumbnail,
'title': title,
'description': description,
'duration': duration,
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
}

4
youtube_dl/extractor/la7.py
View File

@ -20,7 +20,7 @@ class LA7IE(InfoExtractor):
'url': 'http://www.la7.it/crozza/video/inccool8-02-10-2015-163722',
'md5': '8b613ffc0c4bf9b9e377169fc19c214c',
'info_dict': {
'id': 'inccool8-02-10-2015-163722',
'id': '0_42j6wd36',
'ext': 'mp4',
'title': 'Inc.Cool8',
'description': 'Benvenuti nell\'incredibile mondo della INC. COOL. 8. dove “INC.” sta per “Incorporated” “COOL” sta per “fashion” ed Eight sta per il gesto atletico',
@ -57,7 +57,7 @@ class LA7IE(InfoExtractor):
return {
'_type': 'url_transparent',
'url': smuggle_url('kaltura:103:%s' % player_data['vid'], {
'service_url': 'http://kdam.iltrovatore.it',
'service_url': 'http://nkdam.iltrovatore.it',
}),
'id': video_id,
'title': player_data['title'],

33
youtube_dl/extractor/learnr.py
View File

@ -1,33 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class LearnrIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?learnr\.pro/view/video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.learnr.pro/view/video/51624-web-development-tutorial-for-beginners-1-how-to-build-webpages-with-html-css-javascript',
'md5': '3719fdf0a68397f49899e82c308a89de',
'info_dict': {
'id': '51624',
'ext': 'mp4',
'title': 'Web Development Tutorial for Beginners (#1) - How to build webpages with HTML, CSS, Javascript',
'description': 'md5:b36dbfa92350176cdf12b4d388485503',
'uploader': 'LearnCode.academy',
'uploader_id': 'learncodeacademy',
'upload_date': '20131021',
},
'add_ie': ['Youtube'],
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
return {
'_type': 'url_transparent',
'url': self._search_regex(
r"videoId\s*:\s*'([^']+)'", webpage, 'youtube id'),
'id': video_id,
}

3
youtube_dl/extractor/lecturio.py
View File

@ -4,7 +4,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
@ -36,7 +35,7 @@ class LecturioBaseIE(InfoExtractor):
self._LOGIN_URL, None, 'Downloading login popup')
def is_logged(url_handle):
return self._LOGIN_URL not in compat_str(url_handle.geturl())
return self._LOGIN_URL not in url_handle.geturl()
# Already logged in
if is_logged(urlh):

185
youtube_dl/extractor/lego.py
View File

@ -2,23 +2,24 @@
from __future__ import unicode_literals
import re
import uuid
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import compat_HTTPError
from ..utils import (
unescapeHTML,
parse_duration,
get_element_by_class,
ExtractorError,
int_or_none,
qualities,
)
class LEGOIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[^/]+)/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]+)'
_VALID_URL = r'https?://(?:www\.)?lego\.com/(?P<locale>[a-z]{2}-[a-z]{2})/(?:[^/]+/)*videos/(?:[^/]+/)*[^/?#]+-(?P<id>[0-9a-f]{32})'
_TESTS = [{
'url': 'http://www.lego.com/en-us/videos/themes/club/blocumentary-kawaguchi-55492d823b1b4d5e985787fa8c2973b1',
'md5': 'f34468f176cfd76488767fc162c405fa',
'info_dict': {
'id': '55492d823b1b4d5e985787fa8c2973b1',
'id': '55492d82-3b1b-4d5e-9857-87fa8c2973b1_en-US',
'ext': 'mp4',
'title': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
'description': 'Blocumentary Great Creations: Akiyuki Kawaguchi',
@ -26,103 +27,123 @@ class LEGOIE(InfoExtractor):
}, {
# geo-restricted but the contentUrl contain a valid url
'url': 'http://www.lego.com/nl-nl/videos/themes/nexoknights/episode-20-kingdom-of-heroes-13bdc2299ab24d9685701a915b3d71e7##sp=399',
'md5': '4c3fec48a12e40c6e5995abc3d36cc2e',
'md5': 'c7420221f7ffd03ff056f9db7f8d807c',
'info_dict': {
'id': '13bdc2299ab24d9685701a915b3d71e7',
'id': '13bdc229-9ab2-4d96-8570-1a915b3d71e7_nl-NL',
'ext': 'mp4',
'title': 'Aflevering 20 - Helden van het koninkrijk',
'title': 'Aflevering 20: Helden van het koninkrijk',
'description': 'md5:8ee499aac26d7fa8bcb0cedb7f9c3941',
'age_limit': 5,
},
}, {
# special characters in title
'url': 'http://www.lego.com/en-us/starwars/videos/lego-star-wars-force-surprise-9685ee9d12e84ff38e84b4e3d0db533d',
# with subtitle
'url': 'https://www.lego.com/nl-nl/kids/videos/classic/creative-storytelling-the-little-puppy-aa24f27c7d5242bc86102ebdc0f24cba',
'info_dict': {
'id': '9685ee9d12e84ff38e84b4e3d0db533d',
'id': 'aa24f27c-7d52-42bc-8610-2ebdc0f24cba_nl-NL',
'ext': 'mp4',
'title': 'Force Surprise – LEGO® Star Wars™ Microfighters',
'description': 'md5:9c673c96ce6f6271b88563fe9dc56de3',
'title': 'De kleine puppy',
'description': 'md5:5b725471f849348ac73f2e12cfb4be06',
'age_limit': 1,
'subtitles': {
'nl': [{
'ext': 'srt',
'url': r're:^https://.+\.srt$',
}],
},
},
'params': {
'skip_download': True,
},
}]
_BITRATES = [256, 512, 1024, 1536, 2560]
_QUALITIES = {
'Lowest': (64, 180, 320),
'Low': (64, 270, 480),
'Medium': (96, 360, 640),
'High': (128, 540, 960),
'Highest': (128, 720, 1280),
}
def _real_extract(self, url):
locale, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, video_id)
title = get_element_by_class('video-header', webpage).strip()
progressive_base = 'https://lc-mediaplayerns-live-s.legocdn.com/'
streaming_base = 'http://legoprod-f.akamaihd.net/'
content_url = self._html_search_meta('contentUrl', webpage)
path = self._search_regex(
r'(?:https?:)?//[^/]+/(?:[iz]/s/)?public/(.+)_[0-9,]+\.(?:mp4|webm)',
content_url, 'video path', default=None)
if not path:
player_url = self._proto_relative_url(self._search_regex(
r'<iframe[^>]+src="((?:https?)?//(?:www\.)?lego\.com/[^/]+/mediaplayer/video/[^"]+)',
webpage, 'player url', default=None))
if not player_url:
base_url = self._proto_relative_url(self._search_regex(
r'data-baseurl="([^"]+)"', webpage, 'base url',
default='http://www.lego.com/%s/mediaplayer/video/' % locale))
player_url = base_url + video_id
player_webpage = self._download_webpage(player_url, video_id)
video_data = self._parse_json(unescapeHTML(self._search_regex(
r"video='([^']+)'", player_webpage, 'video data')), video_id)
progressive_base = self._search_regex(
r'data-video-progressive-url="([^"]+)"',
player_webpage, 'progressive base', default='https://lc-mediaplayerns-live-s.legocdn.com/')
streaming_base = self._search_regex(
r'data-video-streaming-url="([^"]+)"',
player_webpage, 'streaming base', default='http://legoprod-f.akamaihd.net/')
item_id = video_data['ItemId']
net_storage_path = video_data.get('NetStoragePath') or '/'.join([item_id[:2], item_id[2:4]])
base_path = '_'.join([item_id, video_data['VideoId'], video_data['Locale'], compat_str(video_data['VideoVersion'])])
path = '/'.join([net_storage_path, base_path])
streaming_path = ','.join(map(lambda bitrate: compat_str(bitrate), self._BITRATES))
formats = self._extract_akamai_formats(
'%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none',
formats))
if len(m3u8_formats) == len(self._BITRATES):
self._sort_formats(m3u8_formats)
for bitrate, m3u8_format in zip(self._BITRATES, m3u8_formats):
progressive_base_url = '%spublic/%s_%d.' % (progressive_base, path, bitrate)
mp4_f = m3u8_format.copy()
mp4_f.update({
'url': progressive_base_url + 'mp4',
'format_id': m3u8_format['format_id'].replace('hls', 'mp4'),
'protocol': 'http',
countries = [locale.split('-')[1].upper()]
self._initialize_geo_bypass({
'countries': countries,
})
web_f = {
'url': progressive_base_url + 'webm',
'format_id': m3u8_format['format_id'].replace('hls', 'webm'),
'width': m3u8_format['width'],
'height': m3u8_format['height'],
'tbr': m3u8_format.get('tbr'),
'ext': 'webm',
}
formats.extend([web_f, mp4_f])
try:
item = self._download_json(
# https://contentfeed.services.lego.com/api/v2/item/[VIDEO_ID]?culture=[LOCALE]&contentType=Video
'https://services.slingshot.lego.com/mediaplayer/v2',
video_id, query={
'videoId': '%s_%s' % (uuid.UUID(video_id), locale),
}, headers=self.geo_verification_headers())
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 451:
self.raise_geo_restricted(countries=countries)
raise
video = item['Video']
video_id = video['Id']
title = video['Title']
q = qualities(['Lowest', 'Low', 'Medium', 'High', 'Highest'])
formats = []
for video_source in item.get('VideoFormats', []):
video_source_url = video_source.get('Url')
if not video_source_url:
continue
video_source_format = video_source.get('Format')
if video_source_format == 'F4M':
formats.extend(self._extract_f4m_formats(
video_source_url, video_id,
f4m_id=video_source_format, fatal=False))
elif video_source_format == 'M3U8':
formats.extend(self._extract_m3u8_formats(
video_source_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=video_source_format, fatal=False))
else:
for bitrate in self._BITRATES:
for ext in ('web', 'mp4'):
formats.append({
'format_id': '%s-%s' % (ext, bitrate),
'url': '%spublic/%s_%d.%s' % (progressive_base, path, bitrate, ext),
'tbr': bitrate,
'ext': ext,
})
video_source_quality = video_source.get('Quality')
format_id = []
for v in (video_source_format, video_source_quality):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'quality': q(video_source_quality),
'url': video_source_url,
}
quality = self._QUALITIES.get(video_source_quality)
if quality:
f.update({
'abr': quality[0],
'height': quality[1],
'width': quality[2],
}),
formats.append(f)
self._sort_formats(formats)
subtitles = {}
sub_file_id = video.get('SubFileId')
if sub_file_id and sub_file_id != '00000000-0000-0000-0000-000000000000':
net_storage_path = video.get('NetstoragePath')
invariant_id = video.get('InvariantId')
video_file_id = video.get('VideoFileId')
video_version = video.get('VideoVersion')
if net_storage_path and invariant_id and video_file_id and video_version:
subtitles.setdefault(locale[:2], []).append({
'url': 'https://lc-mediaplayerns-live-s.legocdn.com/public/%s/%s_%s_%s_%s_sub.srt' % (net_storage_path, invariant_id, video_file_id, locale, video_version),
})
return {
'id': video_id,
'title': title,
'description': self._html_search_meta('description', webpage),
'thumbnail': self._html_search_meta('thumbnail', webpage),
'duration': parse_duration(self._html_search_meta('duration', webpage)),
'description': video.get('Description'),
'thumbnail': video.get('GeneratedCoverImage') or video.get('GeneratedThumbnail'),
'duration': int_or_none(video.get('Length')),
'formats': formats,
'subtitles': subtitles,
'age_limit': int_or_none(video.get('AgeFrom')),
'season': video.get('SeasonTitle'),
'season_number': int_or_none(video.get('Season')) or None,
'episode_number': int_or_none(video.get('Episode')) or None,
}

121
youtube_dl/extractor/limelight.py
View File

@ -18,7 +18,6 @@ from ..utils import (
class LimelightBaseIE(InfoExtractor):
_PLAYLIST_SERVICE_URL = 'http://production-ps.lvp.llnw.net/r/PlaylistService/%s/%s/%s'
_API_URL = 'http://api.video.limelight.com/rest/organizations/%s/%s/%s/%s.json'
@classmethod
def _extract_urls(cls, webpage, source_url):
@ -70,7 +69,8 @@ class LimelightBaseIE(InfoExtractor):
try:
return self._download_json(
self._PLAYLIST_SERVICE_URL % (self._PLAYLIST_SERVICE_PATH, item_id, method),
item_id, 'Downloading PlaylistService %s JSON' % method, fatal=fatal, headers=headers)
item_id, 'Downloading PlaylistService %s JSON' % method,
fatal=fatal, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read().decode(), item_id)['detail']['contentAccessPermission']
@ -79,22 +79,22 @@ class LimelightBaseIE(InfoExtractor):
raise ExtractorError(error, expected=True)
raise
def _call_api(self, organization_id, item_id, method):
return self._download_json(
self._API_URL % (organization_id, self._API_PATH, item_id, method),
item_id, 'Downloading API %s JSON' % method)
def _extract(self, item_id, pc_method, mobile_method, meta_method, referer=None):
def _extract(self, item_id, pc_method, mobile_method, referer=None):
pc = self._call_playlist_service(item_id, pc_method, referer=referer)
metadata = self._call_api(pc['orgId'], item_id, meta_method)
mobile = self._call_playlist_service(item_id, mobile_method, fatal=False, referer=referer)
return pc, mobile, metadata
mobile = self._call_playlist_service(
item_id, mobile_method, fatal=False, referer=referer)
return pc, mobile
def _extract_info(self, pc, mobile, i, referer):
get_item = lambda x, y: try_get(x, lambda x: x[y][i], dict) or {}
pc_item = get_item(pc, 'playlistItems')
mobile_item = get_item(mobile, 'mediaList')
video_id = pc_item.get('mediaId') or mobile_item['mediaId']
title = pc_item.get('title') or mobile_item['title']
def _extract_info(self, streams, mobile_urls, properties):
video_id = properties['media_id']
formats = []
urls = []
for stream in streams:
for stream in pc_item.get('streams', []):
stream_url = stream.get('url')
if not stream_url or stream.get('drmProtected') or stream_url in urls:
continue
@ -155,7 +155,7 @@ class LimelightBaseIE(InfoExtractor):
})
formats.append(fmt)
for mobile_url in mobile_urls:
for mobile_url in mobile_item.get('mobileUrls', []):
media_url = mobile_url.get('mobileUrl')
format_id = mobile_url.get('targetMediaPlatform')
if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
@ -179,54 +179,34 @@ class LimelightBaseIE(InfoExtractor):
self._sort_formats(formats)
title = properties['title']
description = properties.get('description')
timestamp = int_or_none(properties.get('publish_date') or properties.get('create_date'))
duration = float_or_none(properties.get('duration_in_milliseconds'), 1000)
filesize = int_or_none(properties.get('total_storage_in_bytes'))
categories = [properties.get('category')]
tags = properties.get('tags', [])
thumbnails = [{
'url': thumbnail['url'],
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
} for thumbnail in properties.get('thumbnails', []) if thumbnail.get('url')]
subtitles = {}
for caption in properties.get('captions', []):
lang = caption.get('language_code')
subtitles_url = caption.get('url')
if lang and subtitles_url:
for flag in mobile_item.get('flags'):
if flag == 'ClosedCaptions':
closed_captions = self._call_playlist_service(
video_id, 'getClosedCaptionsDetailsByMediaId',
False, referer) or []
for cc in closed_captions:
cc_url = cc.get('webvttFileUrl')
if not cc_url:
continue
lang = cc.get('languageCode') or self._search_regex(r'/[a-z]{2}\.vtt', cc_url, 'lang', default='en')
subtitles.setdefault(lang, []).append({
'url': subtitles_url,
})
closed_captions_url = properties.get('closed_captions_url')
if closed_captions_url:
subtitles.setdefault('en', []).append({
'url': closed_captions_url,
'ext': 'ttml',
'url': cc_url,
})
break
get_meta = lambda x: pc_item.get(x) or mobile_item.get(x)
return {
'id': video_id,
'title': title,
'description': description,
'description': get_meta('description'),
'formats': formats,
'timestamp': timestamp,
'duration': duration,
'filesize': filesize,
'categories': categories,
'tags': tags,
'thumbnails': thumbnails,
'duration': float_or_none(get_meta('durationInMilliseconds'), 1000),
'thumbnail': get_meta('previewImageUrl') or get_meta('thumbnailImageUrl'),
'subtitles': subtitles,
}
def _extract_info_helper(self, pc, mobile, i, metadata):
return self._extract_info(
try_get(pc, lambda x: x['playlistItems'][i]['streams'], list) or [],
try_get(mobile, lambda x: x['mediaList'][i]['mobileUrls'], list) or [],
metadata)
class LimelightMediaIE(LimelightBaseIE):
IE_NAME = 'limelight'
@ -251,8 +231,6 @@ class LimelightMediaIE(LimelightBaseIE):
'description': 'md5:8005b944181778e313d95c1237ddb640',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 144.23,
'timestamp': 1244136834,
'upload_date': '20090604',
},
'params': {
# m3u8 download
@ -268,30 +246,29 @@ class LimelightMediaIE(LimelightBaseIE):
'title': '3Play Media Overview Video',
'thumbnail': r're:^https?://.*\.jpeg$',
'duration': 78.101,
'timestamp': 1338929955,
'upload_date': '20120605',
'subtitles': 'mincount:9',
# TODO: extract all languages that were accessible via API
# 'subtitles': 'mincount:9',
'subtitles': 'mincount:1',
},
}, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'media'
_API_PATH = 'media'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
pc, mobile, metadata = self._extract(
pc, mobile = self._extract(
video_id, 'getPlaylistByMediaId',
'getMobilePlaylistByMediaId', 'properties',
smuggled_data.get('source_url'))
'getMobilePlaylistByMediaId', source_url)
return self._extract_info_helper(pc, mobile, 0, metadata)
return self._extract_info(pc, mobile, 0, source_url)
class LimelightChannelIE(LimelightBaseIE):
@ -313,6 +290,7 @@ class LimelightChannelIE(LimelightBaseIE):
'info_dict': {
'id': 'ab6a524c379342f9b23642917020c082',
'title': 'Javascript Sample Code',
'description': 'Javascript Sample Code - http://www.delvenetworks.com/sample-code/playerCode-demo.html',
},
'playlist_mincount': 3,
}, {
@ -320,22 +298,23 @@ class LimelightChannelIE(LimelightBaseIE):
'only_matching': True,
}]
_PLAYLIST_SERVICE_PATH = 'channel'
_API_PATH = 'channels'
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
channel_id = self._match_id(url)
source_url = smuggled_data.get('source_url')
pc, mobile, medias = self._extract(
pc, mobile = self._extract(
channel_id, 'getPlaylistByChannelId',
'getMobilePlaylistWithNItemsByChannelId?begin=0&count=-1',
'media', smuggled_data.get('source_url'))
source_url)
entries = [
self._extract_info_helper(pc, mobile, i, medias['media_list'][i])
for i in range(len(medias['media_list']))]
self._extract_info(pc, mobile, i, source_url)
for i in range(len(pc['playlistItems']))]
return self.playlist_result(entries, channel_id, pc['title'])
return self.playlist_result(
entries, channel_id, pc.get('title'), mobile.get('description'))
class LimelightChannelListIE(LimelightBaseIE):
@ -368,10 +347,12 @@ class LimelightChannelListIE(LimelightBaseIE):
def _real_extract(self, url):
channel_list_id = self._match_id(url)
channel_list = self._call_playlist_service(channel_list_id, 'getMobileChannelListById')
channel_list = self._call_playlist_service(
channel_list_id, 'getMobileChannelListById')
entries = [
self.url_result('limelight:channel:%s' % channel['id'], 'LimelightChannel')
for channel in channel_list['channelList']]
return self.playlist_result(entries, channel_list_id, channel_list['title'])
return self.playlist_result(
entries, channel_list_id, channel_list['title'])

5
youtube_dl/extractor/linuxacademy.py
View File

@ -8,7 +8,6 @@ from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_HTTPError,
compat_str,
)
from ..utils import (
ExtractorError,
@ -99,7 +98,7 @@ class LinuxAcademyIE(InfoExtractor):
'sso': 'true',
})
login_state_url = compat_str(urlh.geturl())
login_state_url = urlh.geturl()
try:
login_page = self._download_webpage(
@ -129,7 +128,7 @@ class LinuxAcademyIE(InfoExtractor):
})
access_token = self._search_regex(
r'access_token=([^=&]+)', compat_str(urlh.geturl()),
r'access_token=([^=&]+)', urlh.geturl(),
'access token')
self._download_webpage(

100
youtube_dl/extractor/lnkgo.py
View File

@ -5,24 +5,27 @@ import re
from .common import InfoExtractor
from ..utils import (
clean_html,
compat_str,
int_or_none,
unified_strdate,
parse_iso8601,
)
class LnkGoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?lnkgo\.(?:alfa\.)?lt/visi-video/(?P<show>[^/]+)/ziurek-(?P<id>[A-Za-z0-9-]+)'
_VALID_URL = r'https?://(?:www\.)?lnk(?:go)?\.(?:alfa\.)?lt/(?:visi-video/[^/]+|video)/(?P<id>[A-Za-z0-9-]+)(?:/(?P<episode_id>\d+))?'
_TESTS = [{
'url': 'http://lnkgo.alfa.lt/visi-video/yra-kaip-yra/ziurek-yra-kaip-yra-162',
'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
'info_dict': {
'id': '46712',
'id': '10809',
'ext': 'mp4',
'title': 'Yra kaip yra',
'upload_date': '20150107',
'description': 'md5:d82a5e36b775b7048617f263a0e3475e',
'age_limit': 7,
'duration': 3019,
'thumbnail': r're:^https?://.*\.jpg$'
'title': "Put'ka: Trys Klausimai",
'upload_date': '20161216',
'description': 'Seniai matytas Put’ka užduoda tris klausimėlius. Pabandykime surasti atsakymus.',
'age_limit': 18,
'duration': 117,
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1481904000,
},
'params': {
'skip_download': True, # HLS download
@ -30,20 +33,21 @@ class LnkGoIE(InfoExtractor):
}, {
'url': 'http://lnkgo.alfa.lt/visi-video/aktualai-pratesimas/ziurek-nerdas-taiso-kompiuteri-2',
'info_dict': {
'id': '47289',
'id': '10467',
'ext': 'mp4',
'title': 'Nėrdas: Kompiuterio Valymas',
'upload_date': '20150113',
'description': 'md5:7352d113a242a808676ff17e69db6a69',
'age_limit': 18,
'duration': 346,
'thumbnail': r're:^https?://.*\.jpg$'
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1421164800,
},
'params': {
'skip_download': True, # HLS download
},
}, {
'url': 'http://www.lnkgo.lt/visi-video/aktualai-pratesimas/ziurek-putka-trys-klausimai',
'url': 'https://lnk.lt/video/neigalieji-tv-bokste/37413',
'only_matching': True,
}]
_AGE_LIMITS = {
@ -51,66 +55,34 @@ class LnkGoIE(InfoExtractor):
'N-14': 14,
'S': 18,
}
_M3U8_TEMPL = 'https://vod.lnk.lt/lnk_vod/lnk/lnk/%s:%s/playlist.m3u8%s'
def _real_extract(self, url):
display_id = self._match_id(url)
display_id, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
url, display_id, 'Downloading player webpage')
video_id = self._search_regex(
r'data-ep="([^"]+)"', webpage, 'video ID')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
upload_date = unified_strdate(self._search_regex(
r'class="[^"]*meta-item[^"]*air-time[^"]*">.*?<strong>([^<]+)</strong>', webpage, 'upload date', fatal=False))
thumbnail_w = int_or_none(
self._og_search_property('image:width', webpage, 'thumbnail width', fatal=False))
thumbnail_h = int_or_none(
self._og_search_property('image:height', webpage, 'thumbnail height', fatal=False))
thumbnail = {
'url': self._og_search_thumbnail(webpage),
}
if thumbnail_w and thumbnail_h:
thumbnail.update({
'width': thumbnail_w,
'height': thumbnail_h,
})
config = self._parse_json(self._search_regex(
r'episodePlayer\((\{.*?\}),\s*\{', webpage, 'sources'), video_id)
if config.get('pGeo'):
self.report_warning(
'This content might not be available in your country due to copyright reasons')
formats = [{
'format_id': 'hls',
'ext': 'mp4',
'url': config['EpisodeVideoLink_HLS'],
}]
m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<play_path>.+)$', config['EpisodeVideoLink'])
if m:
formats.append({
'format_id': 'rtmp',
'ext': 'flv',
'url': m.group('url'),
'play_path': m.group('play_path'),
'page_url': url,
})
video_info = self._download_json(
'https://lnk.lt/api/main/video-page/%s/%s/false' % (display_id, video_id or '0'),
display_id)['videoConfig']['videoInfo']
video_id = compat_str(video_info['id'])
title = video_info['title']
prefix = 'smil' if video_info.get('isQualityChangeAvailable') else 'mp4'
formats = self._extract_m3u8_formats(
self._M3U8_TEMPL % (prefix, video_info['videoUrl'], video_info.get('secureTokenParams') or ''),
video_id, 'mp4', 'm3u8_native')
self._sort_formats(formats)
poster_image = video_info.get('posterImage')
return {
'id': video_id,
'display_id': display_id,
'title': title,
'formats': formats,
'thumbnails': [thumbnail],
'duration': int_or_none(config.get('VideoTime')),
'description': description,
'age_limit': self._AGE_LIMITS.get(config.get('PGRating'), 0),
'upload_date': upload_date,
'thumbnail': 'https://lnk.lt/all-images/' + poster_image if poster_image else None,
'duration': int_or_none(video_info.get('duration')),
'description': clean_html(video_info.get('htmlDescription')),
'age_limit': self._AGE_LIMITS.get(video_info.get('pgRating'), 0),
'timestamp': parse_iso8601(video_info.get('airDate')),
'view_count': int_or_none(video_info.get('viewsCount')),
}

42
youtube_dl/extractor/macgamestore.py
View File

@ -1,42 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError
class MacGameStoreIE(InfoExtractor):
IE_NAME = 'macgamestore'
IE_DESC = 'MacGameStore trailers'
_VALID_URL = r'https?://(?:www\.)?macgamestore\.com/mediaviewer\.php\?trailer=(?P<id>\d+)'
_TEST = {
'url': 'http://www.macgamestore.com/mediaviewer.php?trailer=2450',
'md5': '8649b8ea684b6666b4c5be736ecddc61',
'info_dict': {
'id': '2450',
'ext': 'm4v',
'title': 'Crow',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, 'Downloading trailer page')
if '>Missing Media<' in webpage:
raise ExtractorError(
'Trailer %s does not exist' % video_id, expected=True)
video_title = self._html_search_regex(
r'<title>MacGameStore: (.*?) Trailer</title>', webpage, 'title')
video_url = self._html_search_regex(
r'(?s)<div\s+id="video-player".*?href="([^"]+)"\s*>',
webpage, 'video URL')
return {
'id': video_id,
'url': video_url,
'title': video_title
}

16
youtube_dl/extractor/mailru.py
View File

@ -20,10 +20,10 @@ class MailRuIE(InfoExtractor):
IE_DESC = 'Видео@Mail.Ru'
_VALID_URL = r'''(?x)
https?://
(?:(?:www|m)\.)?my\.mail\.ru/
(?:(?:www|m)\.)?my\.mail\.ru/+
(?:
video/.*\#video=/?(?P<idv1>(?:[^/]+/){3}\d+)|
(?:(?P<idv2prefix>(?:[^/]+/){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
(?:(?P<idv2prefix>(?:[^/]+/+){2})video/(?P<idv2suffix>[^/]+/\d+))\.html|
(?:video/embed|\+/video/meta)/(?P<metaid>\d+)
)
'''
@ -85,6 +85,14 @@ class MailRuIE(InfoExtractor):
{
'url': 'http://my.mail.ru/+/video/meta/7949340477499637815',
'only_matching': True,
},
{
'url': 'https://my.mail.ru//list/sinyutin10/video/_myvideo/4.html',
'only_matching': True,
},
{
'url': 'https://my.mail.ru//list//sinyutin10/video/_myvideo/4.html',
'only_matching': True,
}
]
@ -237,7 +245,7 @@ class MailRuMusicSearchBaseIE(InfoExtractor):
class MailRuMusicIE(MailRuMusicSearchBaseIE):
IE_NAME = 'mailru:music'
IE_DESC = 'Музыка@Mail.Ru'
_VALID_URL = r'https?://my\.mail\.ru/music/songs/[^/?#&]+-(?P<id>[\da-f]+)'
_VALID_URL = r'https?://my\.mail\.ru/+music/+songs/+[^/?#&]+-(?P<id>[\da-f]+)'
_TESTS = [{
'url': 'https://my.mail.ru/music/songs/%D0%BC8%D0%BB8%D1%82%D1%85-l-a-h-luciferian-aesthetics-of-herrschaft-single-2017-4e31f7125d0dfaef505d947642366893',
'md5': '0f8c22ef8c5d665b13ac709e63025610',
@ -273,7 +281,7 @@ class MailRuMusicIE(MailRuMusicSearchBaseIE):
class MailRuMusicSearchIE(MailRuMusicSearchBaseIE):
IE_NAME = 'mailru:music:search'
IE_DESC = 'Музыка@Mail.Ru'
_VALID_URL = r'https?://my\.mail\.ru/music/search/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://my\.mail\.ru/+music/+search/+(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://my.mail.ru/music/search/black%20shadow',
'info_dict': {

32
youtube_dl/extractor/makertv.py
View File

@ -1,32 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class MakerTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?maker\.tv/(?:[^/]+/)*video|makerplayer\.com/embed/maker)/(?P<id>[a-zA-Z0-9]{12})'
_TEST = {
'url': 'http://www.maker.tv/video/Fh3QgymL9gsc',
'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
'info_dict': {
'id': 'Fh3QgymL9gsc',
'ext': 'mp4',
'title': 'Maze Runner: The Scorch Trials Official Movie Review',
'description': 'md5:11ff3362d7ef1d679fdb649f6413975a',
'upload_date': '20150918',
'timestamp': 1442549540,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
jwplatform_id = self._search_regex(r'jw_?id="([^"]+)"', webpage, 'jwplatform id')
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'jwplatform:%s' % jwplatform_id,
'ie_key': 'JWPlatform',
}

28
youtube_dl/extractor/mediaset.py
View File

@ -6,7 +6,6 @@ import re
from .theplatform import ThePlatformBaseIE
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..utils import (
@ -27,7 +26,7 @@ class MediasetIE(ThePlatformBaseIE):
(?:video|on-demand)/(?:[^/]+/)+[^/]+_|
player/index\.html\?.*?\bprogramGuid=
)
)(?P<id>[0-9A-Z]{16})
)(?P<id>[0-9A-Z]{16,})
'''
_TESTS = [{
# full episode
@ -62,7 +61,6 @@ class MediasetIE(ThePlatformBaseIE):
'uploader': 'Canale 5',
'uploader_id': 'C5',
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
# clip
'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
@ -78,6 +76,18 @@ class MediasetIE(ThePlatformBaseIE):
}, {
'url': 'mediaset:FAFU000000665924',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/mediasethaacuoreilfuturo/palmieri-alicudi-lisola-dei-tre-bambini-felici--un-decreto-per-alicudi-e-tutte-le-microscuole_FD00000000102295',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/cherryseason/anticipazioni-degli-episodi-del-23-ottobre_F306837101005C02',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/tg5/ambiente-onda-umana-per-salvare-il-pianeta_F309453601079D01',
'only_matching': True,
}, {
'url': 'https://www.mediasetplay.mediaset.it/video/grandefratellovip/benedetta-una-doccia-gelata_F309344401044C135',
'only_matching': True,
}]
@staticmethod
@ -103,12 +113,17 @@ class MediasetIE(ThePlatformBaseIE):
continue
urlh = ie._request_webpage(
embed_url, video_id, note='Following embed URL redirect')
embed_url = compat_str(urlh.geturl())
embed_url = urlh.geturl()
program_guid = _program_guid(_qs(embed_url))
if program_guid:
entries.append(embed_url)
return entries
def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
for video in smil.findall(self._xpath_ns('.//video', namespace)):
video.attrib['src'] = re.sub(r'(https?://vod05)t(-mediaset-it\.akamaized\.net/.+?.mpd)\?.+', r'\1\2', video.attrib['src'])
return super(MediasetIE, self)._parse_smil_formats(smil, smil_url, video_id, namespace, f4m_params, transform_rtmp_url)
def _real_extract(self, url):
guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid
@ -118,14 +133,15 @@ class MediasetIE(ThePlatformBaseIE):
subtitles = {}
first_e = None
for asset_type in ('SD', 'HD'):
for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
# TODO: fixup ISM+none manifest URLs
for f in ('MPEG4', 'MPEG-DASH+none', 'M3U+none'):
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
'mbr': 'true',
'formats': f,
'assetTypes': asset_type,
}), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
}), guid, 'Downloading %s %s SMIL data' % (f.split('+')[0], asset_type))
except ExtractorError as e:
if not first_e:
first_e = e

2
youtube_dl/extractor/mediasite.py
View File

@ -129,7 +129,7 @@ class MediasiteIE(InfoExtractor):
query = mobj.group('query')
webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer?
redirect_url = compat_str(urlh.geturl())
redirect_url = urlh.geturl()
# XXX: might have also extracted UrlReferrer and QueryString from the html
service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex(

70
youtube_dl/extractor/minhateca.py
View File

@ -1,70 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_filesize,
sanitized_Request,
urlencode_postdata,
)
class MinhatecaIE(InfoExtractor):
_VALID_URL = r'https?://minhateca\.com\.br/[^?#]+,(?P<id>[0-9]+)\.'
_TEST = {
'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)',
'info_dict': {
'id': '125848331',
'ext': 'mp4',
'title': 'youtube-dl test video',
'thumbnail': r're:^https?://.*\.jpg$',
'filesize_approx': 1530000,
'duration': 9,
'view_count': int,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
token = self._html_search_regex(
r'<input name="__RequestVerificationToken".*?value="([^"]+)"',
webpage, 'request token')
token_data = [
('fileId', video_id),
('__RequestVerificationToken', token),
]
req = sanitized_Request(
'http://minhateca.com.br/action/License/Download',
data=urlencode_postdata(token_data))
req.add_header('Content-Type', 'application/x-www-form-urlencoded')
data = self._download_json(
req, video_id, note='Downloading metadata')
video_url = data['redirectUrl']
title_str = self._html_search_regex(
r'<h1.*?>(.*?)</h1>', webpage, 'title')
title, _, ext = title_str.rpartition('.')
filesize_approx = parse_filesize(self._html_search_regex(
r'<p class="fileSize">(.*?)</p>',
webpage, 'file size approximation', fatal=False))
duration = parse_duration(self._html_search_regex(
r'(?s)<p class="fileLeng[ht][th]">.*?class="bold">(.*?)<',
webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex(
r'<p class="downloadsCounter">([0-9]+)</p>',
webpage, 'view count', fatal=False))
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': ext,
'filesize_approx': filesize_approx,
'duration': duration,
'view_count': view_count,
'thumbnail': self._og_search_thumbnail(webpage),
}

99
youtube_dl/extractor/mitele.py
View File

@ -4,8 +4,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
smuggle_url,
parse_duration,
)
@ -18,16 +18,18 @@ class MiTeleIE(InfoExtractor):
'info_dict': {
'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
'ext': 'mp4',
'title': 'Tor, la web invisible',
'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
'title': 'Diario de La redacción Programa 144',
'description': 'md5:07c35a7b11abb05876a6a79185b58d27',
'series': 'Diario de',
'season': 'La redacción',
'season': 'Season 14',
'season_number': 14,
'season_id': 'diario_de_t14_11981',
'episode': 'Programa 144',
'episode': 'Tor, la web invisible',
'episode_number': 3,
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'duration': 2913,
'age_limit': 16,
'timestamp': 1471209401,
'upload_date': '20160814',
},
'add_ie': ['Ooyala'],
}, {
@ -39,13 +41,15 @@ class MiTeleIE(InfoExtractor):
'title': 'Cuarto Milenio Temporada 6 Programa 226',
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
'series': 'Cuarto Milenio',
'season': 'Temporada 6',
'season': 'Season 6',
'season_number': 6,
'season_id': 'cuarto_milenio_t06_12715',
'episode': 'Programa 226',
'episode': 'Episode 24',
'episode_number': 24,
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'duration': 7313,
'age_limit': 12,
'timestamp': 1471209021,
'upload_date': '20160814',
},
'params': {
'skip_download': True,
@ -54,67 +58,36 @@ class MiTeleIE(InfoExtractor):
}, {
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
'only_matching': True,
}, {
'url': 'https://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144-40_1006364575251/player/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
paths = self._download_json(
'https://www.mitele.es/amd/agp/web/metadata/general_configuration',
video_id, 'Downloading paths JSON')
ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com')
full_path = ooyala_s.get('full_path', '/search/v1/full/providers/')
source = self._download_json(
'%s://%s%s%s/docs/%s' % (
ooyala_s.get('protocol', 'https'), base_url, full_path,
ooyala_s.get('provider_id', '104951'), video_id),
video_id, 'Downloading data JSON', query={
'include_titles': 'Series,Season',
'product_name': ooyala_s.get('product_name', 'test'),
'format': 'full',
})['hits']['hits'][0]['_source']
embedCode = source['offers'][0]['embed_codes'][0]
titles = source['localizable_titles'][0]
title = titles.get('title_medium') or titles['title_long']
description = titles.get('summary_long') or titles.get('summary_medium')
def get(key1, key2):
value1 = source.get(key1)
if not value1 or not isinstance(value1, list):
return
if not isinstance(value1[0], dict):
return
return value1[0].get(key2)
series = get('localizable_titles_series', 'title_medium')
season = get('localizable_titles_season', 'title_medium')
season_number = int_or_none(source.get('season_number'))
season_id = source.get('season_id')
episode = titles.get('title_sort_name')
episode_number = int_or_none(source.get('episode_number'))
duration = parse_duration(get('videos', 'duration'))
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
pre_player = self._parse_json(self._search_regex(
r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})',
webpage, 'Pre Player'), display_id)['prePlayer']
title = pre_player['title']
video = pre_player['video']
video_id = video['dataMediaId']
content = pre_player.get('content') or {}
info = content.get('info') or {}
return {
'_type': 'url_transparent',
# for some reason only HLS is supported
'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
'id': video_id,
'title': title,
'description': description,
'series': series,
'season': season,
'season_number': season_number,
'season_id': season_id,
'episode': episode,
'episode_number': episode_number,
'duration': duration,
'thumbnail': get('images', 'url'),
'description': info.get('synopsis'),
'series': content.get('title'),
'season_number': int_or_none(info.get('season_number')),
'episode': content.get('subtitle'),
'episode_number': int_or_none(info.get('episode_number')),
'duration': int_or_none(info.get('duration')),
'thumbnail': video.get('dataPoster'),
'age_limit': int_or_none(info.get('rating')),
'timestamp': parse_iso8601(pre_player.get('publishedTime')),
}

467
youtube_dl/extractor/mixcloud.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import functools
import itertools
import re
@ -11,28 +10,37 @@ from ..compat import (
compat_ord,
compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
compat_zip
)
from ..utils import (
clean_html,
ExtractorError,
int_or_none,
OnDemandPagedList,
str_to_int,
parse_iso8601,
strip_or_none,
try_get,
urljoin,
)
class MixcloudIE(InfoExtractor):
class MixcloudBaseIE(InfoExtractor):
def _call_api(self, object_type, object_fields, display_id, username, slug=None):
lookup_key = object_type + 'Lookup'
return self._download_json(
'https://www.mixcloud.com/graphql', display_id, query={
'query': '''{
%s(lookup: {username: "%s"%s}) {
%s
}
}''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields)
})['data'][lookup_key]
class MixcloudIE(MixcloudBaseIE):
_VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
IE_NAME = 'mixcloud'
_TESTS = [{
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
'id': 'dholbach-cryptkeeper',
'id': 'dholbach_cryptkeeper',
'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
@ -40,11 +48,13 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
'timestamp': 1321359578,
'upload_date': '20111115',
},
}, {
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
'info_dict': {
'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
@ -52,11 +62,14 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
'view_count': int,
'timestamp': 1422987057,
'upload_date': '20150203',
},
}, {
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
'only_matching': True,
}]
_DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'
@staticmethod
def _decrypt_xor_cipher(key, ciphertext):
@ -66,114 +79,66 @@ class MixcloudIE(InfoExtractor):
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
uploader = mobj.group(1)
cloudcast_name = mobj.group(2)
track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
username, slug = re.match(self._VALID_URL, url).groups()
username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
track_id = '%s_%s' % (username, slug)
webpage = self._download_webpage(url, track_id)
cloudcast = self._call_api('cloudcast', '''audioLength
comments(first: 100) {
edges {
node {
comment
created
user {
displayName
username
}
}
}
totalCount
}
description
favorites {
totalCount
}
featuringArtistList
isExclusive
name
owner {
displayName
url
username
}
picture(width: 1024, height: 1024) {
url
}
plays
publishDate
reposts {
totalCount
}
streamInfo {
dashUrl
hlsUrl
url
}
tags {
tag {
name
}
}''', track_id, username, slug)
# Legacy path
encrypted_play_info = self._search_regex(
r'm-play-info="([^"]+)"', webpage, 'play info', default=None)
title = cloudcast['name']
if encrypted_play_info is not None:
# Decode
encrypted_play_info = compat_b64decode(encrypted_play_info)
else:
# New path
full_info_json = self._parse_json(self._html_search_regex(
r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>',
webpage, 'play info'), 'play info')
for item in full_info_json:
item_data = try_get(
item, lambda x: x['cloudcast']['data']['cloudcastLookup'],
dict)
if try_get(item_data, lambda x: x['streamInfo']['url']):
info_json = item_data
break
else:
raise ExtractorError('Failed to extract matching stream info')
message = self._html_search_regex(
r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
webpage, 'error message', default=None)
js_url = self._search_regex(
r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)',
webpage, 'js url')
js = self._download_webpage(js_url, track_id, 'Downloading JS')
# Known plaintext attack
if encrypted_play_info:
kps = ['{"stream_url":']
kpa_target = encrypted_play_info
else:
kps = ['https://', 'http://']
kpa_target = compat_b64decode(info_json['streamInfo']['url'])
for kp in kps:
partial_key = self._decrypt_xor_cipher(kpa_target, kp)
for quote in ["'", '"']:
key = self._search_regex(
r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)),
js, 'encryption key', default=None)
if key is not None:
break
else:
continue
break
else:
raise ExtractorError('Failed to extract encryption key')
if encrypted_play_info is not None:
play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info')
if message and 'stream_url' not in play_info:
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
song_url = play_info['stream_url']
formats = [{
'format_id': 'normal',
'url': song_url
}]
title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
thumbnail = self._proto_relative_url(self._html_search_regex(
r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
uploader = self._html_search_regex(
r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
uploader_id = self._search_regex(
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>',
r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
webpage, 'play count', default=None))
else:
title = info_json['name']
thumbnail = urljoin(
'https://thumbnailer.mixcloud.com/unsafe/600x600/',
try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str))
uploader = try_get(info_json, lambda x: x['owner']['displayName'])
uploader_id = try_get(info_json, lambda x: x['owner']['username'])
description = try_get(info_json, lambda x: x['description'])
view_count = int_or_none(try_get(info_json, lambda x: x['plays']))
stream_info = info_json['streamInfo']
stream_info = cloudcast['streamInfo']
formats = []
def decrypt_url(f_url):
for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'):
decrypted_url = self._decrypt_xor_cipher(k, f_url)
if re.search(r'^https?://[0-9A-Za-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url):
return decrypted_url
for url_key in ('url', 'hlsUrl', 'dashUrl'):
format_url = stream_info.get(url_key)
if not format_url:
continue
decrypted = decrypt_url(compat_b64decode(format_url))
if not decrypted:
continue
decrypted = self._decrypt_xor_cipher(
self._DECRYPTION_KEY, compat_b64decode(format_url))
if url_key == 'hlsUrl':
formats.extend(self._extract_m3u8_formats(
decrypted, track_id, 'mp4', entry_protocol='m3u8_native',
@ -190,52 +155,117 @@ class MixcloudIE(InfoExtractor):
'http_chunk_size': 5242880,
},
})
if not formats and cloudcast.get('isExclusive'):
self.raise_login_required()
self._sort_formats(formats)
comments = []
for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []):
node = edge.get('node') or {}
text = strip_or_none(node.get('comment'))
if not text:
continue
user = node.get('user') or {}
comments.append({
'author': user.get('displayName'),
'author_id': user.get('username'),
'text': text,
'timestamp': parse_iso8601(node.get('created')),
})
tags = []
for t in cloudcast.get('tags'):
tag = try_get(t, lambda x: x['tag']['name'], compat_str)
if not tag:
tags.append(tag)
get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount']))
owner = cloudcast.get('owner') or {}
return {
'id': track_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'description': cloudcast.get('description'),
'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str),
'uploader': owner.get('displayName'),
'timestamp': parse_iso8601(cloudcast.get('publishDate')),
'uploader_id': owner.get('username'),
'uploader_url': owner.get('url'),
'duration': int_or_none(cloudcast.get('audioLength')),
'view_count': int_or_none(cloudcast.get('plays')),
'like_count': get_count('favorites'),
'repost_count': get_count('reposts'),
'comment_count': get_count('comments'),
'comments': comments,
'tags': tags,
'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None,
}
class MixcloudPlaylistBaseIE(InfoExtractor):
_PAGE_SIZE = 24
class MixcloudPlaylistBaseIE(MixcloudBaseIE):
def _get_cloudcast(self, node):
return node
def _find_urls_in_page(self, page):
for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page):
yield self.url_result(
compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
MixcloudIE.ie_key())
def _get_playlist_title(self, title, slug):
return title
def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None):
real_page_number = real_page_number or current_page + 1
return self._download_webpage(
'https://www.mixcloud.com/%s/' % path, video_id,
note='Download %s (page %d)' % (page_name, current_page + 1),
errnote='Unable to download %s' % page_name,
query={'page': real_page_number, 'list': 'main', '_ajax': '1'},
headers={'X-Requested-With': 'XMLHttpRequest'})
def _real_extract(self, url):
username, slug = re.match(self._VALID_URL, url).groups()
username = compat_urllib_parse_unquote(username)
if not slug:
slug = 'uploads'
else:
slug = compat_urllib_parse_unquote(slug)
playlist_id = '%s_%s' % (username, slug)
def _tracks_page_func(self, page, video_id, page_name, current_page):
resp = self._fetch_tracks_page(page, video_id, page_name, current_page)
is_playlist_type = self._ROOT_TYPE == 'playlist'
playlist_type = 'items' if is_playlist_type else slug
list_filter = ''
for item in self._find_urls_in_page(resp):
yield item
has_next_page = True
entries = []
while has_next_page:
playlist = self._call_api(
self._ROOT_TYPE, '''%s
%s
%s(first: 100%s) {
edges {
node {
%s
}
}
pageInfo {
endCursor
hasNextPage
}
}''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE),
playlist_id, username, slug if is_playlist_type else None)
def _get_user_description(self, page_content):
return self._html_search_regex(
r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>',
page_content, 'user description', fatal=False)
items = playlist.get(playlist_type) or {}
for edge in items.get('edges', []):
cloudcast = self._get_cloudcast(edge.get('node') or {})
cloudcast_url = cloudcast.get('url')
if not cloudcast_url:
continue
entries.append(self.url_result(
cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug')))
page_info = items['pageInfo']
has_next_page = page_info['hasNextPage']
list_filter = ', after: "%s"' % page_info['endCursor']
return self.playlist_result(
entries, playlist_id,
self._get_playlist_title(playlist[self._TITLE_KEY], slug),
playlist.get(self._DESCRIPTION_KEY))
class MixcloudUserIE(MixcloudPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
_VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/(?P<type>uploads|favorites|listens|stream)?/?$'
IE_NAME = 'mixcloud:user'
_TESTS = [{
@ -243,68 +273,58 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
'description': 'md5:def36060ac8747b3aabca54924897e47',
'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
'playlist_mincount': 11,
'playlist_mincount': 36,
}, {
'url': 'http://www.mixcloud.com/dholbach/uploads/',
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
'description': 'md5:def36060ac8747b3aabca54924897e47',
'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
'playlist_mincount': 11,
'playlist_mincount': 36,
}, {
'url': 'http://www.mixcloud.com/dholbach/favorites/',
'info_dict': {
'id': 'dholbach_favorites',
'title': 'Daniel Holbach (favorites)',
'description': 'md5:def36060ac8747b3aabca54924897e47',
'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
'params': {
'playlist_items': '1-100',
},
'playlist_mincount': 100,
# 'params': {
# 'playlist_items': '1-100',
# },
'playlist_mincount': 396,
}, {
'url': 'http://www.mixcloud.com/dholbach/listens/',
'info_dict': {
'id': 'dholbach_listens',
'title': 'Daniel Holbach (listens)',
'description': 'md5:def36060ac8747b3aabca54924897e47',
'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
'params': {
'playlist_items': '1-100',
# 'params': {
# 'playlist_items': '1-100',
# },
'playlist_mincount': 1623,
'skip': 'Large list',
}, {
'url': 'https://www.mixcloud.com/FirstEar/stream/',
'info_dict': {
'id': 'FirstEar_stream',
'title': 'First Ear (stream)',
'description': 'Curators of good music\r\n\r\nfirstearmusic.com',
},
'playlist_mincount': 100,
'playlist_mincount': 271,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user')
list_type = mobj.group('type')
_TITLE_KEY = 'displayName'
_DESCRIPTION_KEY = 'biog'
_ROOT_TYPE = 'user'
_NODE_TEMPLATE = '''slug
url'''
# if only a profile URL was supplied, default to download all uploads
if list_type is None:
list_type = 'uploads'
video_id = '%s_%s' % (user_id, list_type)
profile = self._download_webpage(
'https://www.mixcloud.com/%s/' % user_id, video_id,
note='Downloading user profile',
errnote='Unable to download user profile')
username = self._og_search_title(profile)
description = self._get_user_description(profile)
entries = OnDemandPagedList(
functools.partial(
self._tracks_page_func,
'%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
self._PAGE_SIZE)
return self.playlist_result(
entries, video_id, '%s (%s)' % (username, list_type), description)
def _get_playlist_title(self, title, slug):
return '%s (%s)' % (title, slug)
class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
@ -312,87 +332,20 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
IE_NAME = 'mixcloud:playlist'
_TESTS = [{
'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
'info_dict': {
'id': 'RedBullThre3style_tokyo-finalists-2015',
'title': 'National Champions 2015',
'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
},
'playlist_mincount': 16,
}, {
'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user')
playlist_id = mobj.group('playlist')
video_id = '%s_%s' % (user_id, playlist_id)
webpage = self._download_webpage(
url, user_id,
note='Downloading playlist page',
errnote='Unable to download playlist page')
title = self._html_search_regex(
r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)',
webpage, 'playlist title',
default=None) or self._og_search_title(webpage, fatal=False)
description = self._get_user_description(webpage)
entries = OnDemandPagedList(
functools.partial(
self._tracks_page_func,
'%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
self._PAGE_SIZE)
return self.playlist_result(entries, video_id, title, description)
class MixcloudStreamIE(MixcloudPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
IE_NAME = 'mixcloud:stream'
_TEST = {
'url': 'https://www.mixcloud.com/FirstEar/stream/',
'info_dict': {
'id': 'FirstEar',
'title': 'First Ear',
'description': 'Curators of good music\nfirstearmusic.com',
'id': 'maxvibes_jazzcat-on-ness-radio',
'title': 'Ness Radio sessions',
},
'playlist_mincount': 192,
}
'playlist_mincount': 59,
}]
_TITLE_KEY = 'name'
_DESCRIPTION_KEY = 'description'
_ROOT_TYPE = 'playlist'
_NODE_TEMPLATE = '''cloudcast {
slug
url
}'''
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(url, user_id)
entries = []
prev_page_url = None
def _handle_page(page):
entries.extend(self._find_urls_in_page(page))
return self._search_regex(
r'm-next-page-url="([^"]+)"', page,
'next page URL', default=None)
next_page_url = _handle_page(webpage)
for idx in itertools.count(0):
if not next_page_url or prev_page_url == next_page_url:
break
prev_page_url = next_page_url
current_page = int(self._search_regex(
r'\?page=(\d+)', next_page_url, 'next page number'))
next_page_url = _handle_page(self._fetch_tracks_page(
'%s/stream' % user_id, user_id, 'stream', idx,
real_page_number=current_page))
username = self._og_search_title(webpage)
description = self._get_user_description(webpage)
return self.playlist_result(entries, user_id, username, description)
def _get_cloudcast(self, node):
return node.get('cloudcast') or {}

118
youtube_dl/extractor/msn.py
View File

@ -14,20 +14,27 @@ from ..utils import (
class MSNIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_VALID_URL = r'https?://(?:(?:www|preview)\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/criminal-minds-shemar-moore-shares-a-touching-goodbye-message/vp-BBqQYNE',
'md5': '8442f66c116cbab1ff7098f986983458',
'url': 'https://www.msn.com/en-in/money/video/7-ways-to-get-rid-of-chest-congestion/vi-BBPxU6d',
'md5': '087548191d273c5c55d05028f8d2cbcd',
'info_dict': {
'id': 'BBqQYNE',
'display_id': 'criminal-minds-shemar-moore-shares-a-touching-goodbye-message',
'id': 'BBPxU6d',
'display_id': '7-ways-to-get-rid-of-chest-congestion',
'ext': 'mp4',
'title': 'Criminal Minds - Shemar Moore Shares A Touching Goodbye Message',
'description': 'md5:e8e89b897b222eb33a6b5067a8f1bc25',
'duration': 104,
'uploader': 'CBS Entertainment',
'uploader_id': 'IT0X5aoJ6bJgYerJXSDCgFmYPB1__54v',
'title': 'Seven ways to get rid of chest congestion',
'description': '7 Ways to Get Rid of Chest Congestion',
'duration': 88,
'uploader': 'Health',
'uploader_id': 'BBPrMqa',
},
}, {
# Article, multiple Dailymotion Embeds
'url': 'https://www.msn.com/en-in/money/sports/hottest-football-wags-greatest-footballers-turned-managers-and-more/ar-BBpc7Nl',
'info_dict': {
'id': 'BBpc7Nl',
},
'playlist_mincount': 4,
}, {
'url': 'http://www.msn.com/en-ae/news/offbeat/meet-the-nine-year-old-self-made-millionaire/ar-BBt6ZKf',
'only_matching': True,
@ -41,26 +48,60 @@ class MSNIE(InfoExtractor):
}, {
'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6',
'only_matching': True,
}, {
# Vidible(AOL) Embed
'url': 'https://www.msn.com/en-us/money/other/jupiter-is-about-to-come-so-close-you-can-see-its-moons-with-binoculars/vi-AACqsHR',
'only_matching': True,
}, {
# Dailymotion Embed
'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L',
'only_matching': True,
}, {
# YouTube Embed
'url': 'https://www.msn.com/en-in/money/news/meet-vikram-%E2%80%94-chandrayaan-2s-lander/vi-AAGUr0v',
'only_matching': True,
}, {
# NBCSports Embed
'url': 'https://www.msn.com/en-us/money/football_nfl/week-13-preview-redskins-vs-panthers/vi-BBXsCDb',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, display_id = mobj.group('id', 'display_id')
display_id, page_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
video = self._parse_json(
self._search_regex(
r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1',
webpage, 'video data', default='{}', group='data'),
display_id, transform_source=unescapeHTML)
entries = []
for _, metadata in re.findall(r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1', webpage):
video = self._parse_json(unescapeHTML(metadata), display_id)
if not video:
error = unescapeHTML(self._search_regex(
r'data-error=(["\'])(?P<error>.+?)\1',
webpage, 'error', group='error'))
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
provider_id = video.get('providerId')
player_name = video.get('playerName')
if player_name and provider_id:
entry = None
if player_name == 'AOL':
if provider_id.startswith('http'):
provider_id = self._search_regex(
r'https?://delivery\.vidible\.tv/video/redirect/([0-9a-f]{24})',
provider_id, 'vidible id')
entry = self.url_result(
'aol-video:' + provider_id, 'Aol', provider_id)
elif player_name == 'Dailymotion':
entry = self.url_result(
'https://www.dailymotion.com/video/' + provider_id,
'Dailymotion', provider_id)
elif player_name == 'YouTube':
entry = self.url_result(
provider_id, 'Youtube', provider_id)
elif player_name == 'NBCSports':
entry = self.url_result(
'http://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/' + provider_id,
'NBCSportsVPlayer', provider_id)
if entry:
entries.append(entry)
continue
video_id = video['uuid']
title = video['title']
formats = []
@ -68,23 +109,30 @@ class MSNIE(InfoExtractor):
format_url = file_.get('url')
if not format_url:
continue
if 'm3u8' in format_url:
if 'format=m3u8-aapl' in format_url:
# m3u8_native should not be used here until
# https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed
m3u8_formats = self._extract_m3u8_formats(
formats.extend(self._extract_m3u8_formats(
format_url, display_id, 'mp4',
m3u8_id='hls', fatal=False)
formats.extend(m3u8_formats)
elif determine_ext(format_url) == 'ism':
m3u8_id='hls', fatal=False))
elif 'format=mpd-time-csf' in format_url:
formats.extend(self._extract_mpd_formats(
format_url, display_id, 'dash', fatal=False))
elif '.ism' in format_url:
if format_url.endswith('.ism'):
format_url += '/manifest'
formats.extend(self._extract_ism_formats(
format_url + '/Manifest', display_id, 'mss', fatal=False))
format_url, display_id, 'mss', fatal=False))
else:
format_id = file_.get('formatCode')
formats.append({
'url': format_url,
'ext': 'mp4',
'format_id': 'http',
'format_id': format_id,
'width': int_or_none(file_.get('width')),
'height': int_or_none(file_.get('height')),
'vbr': int_or_none(self._search_regex(r'_(\d+)\.mp4', format_url, 'vbr', default=None)),
'preference': 1 if format_id == '1001' else None,
})
self._sort_formats(formats)
@ -100,7 +148,7 @@ class MSNIE(InfoExtractor):
'url': format_url,
})
return {
entries.append({
'id': video_id,
'display_id': display_id,
'title': title,
@ -112,4 +160,12 @@ class MSNIE(InfoExtractor):
'creator': video.get('creator'),
'subtitles': subtitles,
'formats': formats,
}
})
if not entries:
error = unescapeHTML(self._search_regex(
r'data-error=(["\'])(?P<error>.+?)\1',
webpage, 'error', group='error'))
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
return self.playlist_result(entries, page_id)

88
youtube_dl/extractor/mtv.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor):
}]
class MTV81IE(InfoExtractor):
IE_NAME = 'mtv81'
_VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)'
class MTVJapanIE(MTVServicesInfoExtractor):
IE_NAME = 'mtvjapan'
_VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
_TEST = {
'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/',
'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
'info_dict': {
'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
'ext': 'mp4',
'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
'timestamp': 1468846800,
'upload_date': '20160718',
'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
},
'params': {
'skip_download': True,
},
}
_GEO_COUNTRIES = ['JP']
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
def _extract_mgid(self, webpage):
return self._search_regex(
r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage,
'mgid', group='id')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
mgid = self._extract_mgid(webpage)
return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
def _get_feed_query(self, uri):
return {
'arcEp': 'mtvjapan.com',
'mgid': uri,
}
class MTVVideoIE(MTVServicesInfoExtractor):
@ -425,14 +422,14 @@ class MTVVideoIE(MTVServicesInfoExtractor):
class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
_TESTS = [{
'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
'info_dict': {
'id': 'music_video-a50bc5f0b3aa4b3190aa',
'ext': 'flv',
'title': 'MusicVideo_cro-traum',
'description': 'Cro - Traum',
'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
'ext': 'mp4',
'title': 'Traum',
'description': 'Traum',
},
'params': {
# rtmp download
@ -441,11 +438,12 @@ class MTVDEIE(MTVServicesInfoExtractor):
'skip': 'Blocked at Travis CI',
}, {
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
'info_dict': {
'id': 'local_playlist-f5ae778b9832cc837189',
'ext': 'flv',
'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
'ext': 'mp4',
'title': 'Teen Mom 2',
'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
},
'params': {
# rtmp download
@ -453,7 +451,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
},
'skip': 'Blocked at Travis CI',
}, {
'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344',
'ext': 'mp4',
@ -466,25 +464,11 @@ class MTVDEIE(MTVServicesInfoExtractor):
},
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
}]
_GEO_COUNTRIES = ['DE']
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist = self._parse_json(
self._search_regex(
r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
video_id)
def _mrss_url(item):
return item['mrss'] + item.get('mrssvars', '')
# news pages contain single video in playlist with different id
if len(playlist) == 1:
return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
for item in playlist:
item_id = item.get('id')
if item_id and compat_str(item_id) == video_id:
return self._get_videos_info_from_url(_mrss_url(item), video_id)
def _get_feed_query(self, uri):
return {
'arcEp': 'mtv.de',
'mgid': uri,
}

66
youtube_dl/extractor/musicplayon.py
View File

@ -1,66 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
js_to_json,
mimetype2ext,
)
class MusicPlayOnIE(InfoExtractor):
_VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=\d+&play)=(?P<id>\d+)'
_TESTS = [{
'url': 'http://en.musicplayon.com/play?v=433377',
'md5': '00cdcdea1726abdf500d1e7fd6dd59bb',
'info_dict': {
'id': '433377',
'ext': 'mp4',
'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
'description': 'Rick Ross Interview On Chelsea Lately',
'duration': 342,
'uploader': 'ultrafish',
},
}, {
'url': 'http://en.musicplayon.com/play?pl=102&play=442629',
'only_matching': True,
}]
_URL_TEMPLATE = 'http://en.musicplayon.com/play?v=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
url = self._URL_TEMPLATE % video_id
page = self._download_webpage(url, video_id)
title = self._og_search_title(page)
description = self._og_search_description(page)
thumbnail = self._og_search_thumbnail(page)
duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
view_count = self._og_search_property('count', page, fatal=False)
uploader = self._html_search_regex(
r'<div>by&nbsp;<a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
sources = self._parse_json(
self._search_regex(r'setup\[\'_sources\'\]\s*=\s*([^;]+);', page, 'video sources'),
video_id, transform_source=js_to_json)
formats = [{
'url': compat_urlparse.urljoin(url, source['src']),
'ext': mimetype2ext(source.get('type')),
'format_note': source.get('data-res'),
} for source in sources]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'duration': int_or_none(duration),
'view_count': int_or_none(view_count),
'formats': formats,
}

75
youtube_dl/extractor/myspass.py
View File

@ -1,73 +1,56 @@
# coding: utf-8
from __future__ import unicode_literals
import os.path
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
parse_duration,
xpath_text,
)
class MySpassIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
_VALID_URL = r'https?://(?:www\.)?myspass\.de/([^/]+/)*(?P<id>\d+)'
_TEST = {
'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
'md5': '0b49f4844a068f8b33f4b7c88405862b',
'info_dict': {
'id': '11741',
'ext': 'mp4',
'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2',
'description': 'Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
'title': '17.02.2013 - Die Highlights, Teil 2',
},
}
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
video_id = self._match_id(url)
# video id is the last path element of the URL
# usually there is a trailing slash, so also try the second but last
url_path = compat_urllib_parse_urlparse(url).path
url_parent_path, video_id = os.path.split(url_path)
if not video_id:
_, video_id = os.path.split(url_parent_path)
# get metadata
metadata_url = META_DATA_URL_TEMPLATE % video_id
metadata = self._download_xml(
metadata_url, video_id, transform_source=lambda s: s.strip())
'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=' + video_id,
video_id)
# extract values from metadata
url_flv_el = metadata.find('url_flv')
if url_flv_el is None:
raise ExtractorError('Unable to extract download url')
video_url = url_flv_el.text
title_el = metadata.find('title')
if title_el is None:
raise ExtractorError('Unable to extract title')
title = title_el.text
format_id_el = metadata.find('format_id')
if format_id_el is None:
format = 'mp4'
else:
format = format_id_el.text
description_el = metadata.find('description')
if description_el is not None:
description = description_el.text
else:
description = None
imagePreview_el = metadata.find('imagePreview')
if imagePreview_el is not None:
thumbnail = imagePreview_el.text
else:
thumbnail = None
title = xpath_text(metadata, 'title', fatal=True)
video_url = xpath_text(metadata, 'url_flv', 'download url', True)
video_id_int = int(video_id)
for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
group_int = int(group)
if group_int > video_id_int:
video_url = video_url.replace(
group, compat_str(group_int // video_id_int))
return {
'id': video_id,
'url': video_url,
'title': title,
'format': format,
'thumbnail': thumbnail,
'description': description,
'thumbnail': xpath_text(metadata, 'imagePreview'),
'description': xpath_text(metadata, 'description'),
'duration': parse_duration(xpath_text(metadata, 'duration')),
'series': xpath_text(metadata, 'format'),
'season_number': int_or_none(xpath_text(metadata, 'season')),
'season_id': xpath_text(metadata, 'season_id'),
'episode': title,
'episode_number': int_or_none(xpath_text(metadata, 'episode')),
}

158
youtube_dl/extractor/naver.py
View File

@ -1,68 +1,33 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
ExtractorError,
int_or_none,
parse_duration,
try_get,
update_url_query,
)
class NaverIE(InfoExtractor):
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/v/(?P<id>\d+)'
class NaverBaseIE(InfoExtractor):
_CAPTION_EXT_RE = r'\.(?:ttml|vtt)'
_TESTS = [{
'url': 'http://tv.naver.com/v/81652',
'info_dict': {
'id': '81652',
'ext': 'mp4',
'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
'upload_date': '20130903',
},
}, {
'url': 'http://tv.naver.com/v/395837',
'md5': '638ed4c12012c458fefcddfd01f173cd',
'info_dict': {
'id': '395837',
'ext': 'mp4',
'title': '9년이 지나도 아픈 기억, 전효성의 아버지',
'description': 'md5:5bf200dcbf4b66eb1b350d1eb9c753f7',
'upload_date': '20150519',
},
'skip': 'Georestricted',
}, {
'url': 'http://tvcast.naver.com/v/81652',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
vid = self._search_regex(
r'videoId["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
'video id', fatal=None, group='value')
in_key = self._search_regex(
r'inKey["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
'key', default=None, group='value')
if not vid or not in_key:
error = self._html_search_regex(
r'(?s)<div class="(?:nation_error|nation_box|error_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
webpage, 'error', default=None)
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('couldn\'t extract vid and key')
def _extract_video_info(self, video_id, vid, key):
video_data = self._download_json(
'http://play.rmcnmv.naver.com/vod/play/v2.0/' + vid,
video_id, query={
'key': in_key,
'key': key,
})
meta = video_data['meta']
title = meta['subject']
formats = []
get_list = lambda x: try_get(video_data, lambda y: y[x + 's']['list'], list) or []
def extract_formats(streams, stream_type, query={}):
for stream in streams:
@ -73,7 +38,7 @@ class NaverIE(InfoExtractor):
encoding_option = stream.get('encodingOption', {})
bitrate = stream.get('bitrate', {})
formats.append({
'format_id': '%s_%s' % (stream.get('type') or stream_type, encoding_option.get('id') or encoding_option.get('name')),
'format_id': '%s_%s' % (stream.get('type') or stream_type, dict_get(encoding_option, ('name', 'id'))),
'url': stream_url,
'width': int_or_none(encoding_option.get('width')),
'height': int_or_none(encoding_option.get('height')),
@ -83,7 +48,7 @@ class NaverIE(InfoExtractor):
'protocol': 'm3u8_native' if stream_type == 'HLS' else None,
})
extract_formats(video_data.get('videos', {}).get('list', []), 'H264')
extract_formats(get_list('video'), 'H264')
for stream_set in video_data.get('streams', []):
query = {}
for param in stream_set.get('keys', []):
@ -101,28 +66,101 @@ class NaverIE(InfoExtractor):
'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False))
self._sort_formats(formats)
replace_ext = lambda x, y: re.sub(self._CAPTION_EXT_RE, '.' + y, x)
def get_subs(caption_url):
if re.search(self._CAPTION_EXT_RE, caption_url):
return [{
'url': replace_ext(caption_url, 'ttml'),
}, {
'url': replace_ext(caption_url, 'vtt'),
}]
else:
return [{'url': caption_url}]
automatic_captions = {}
subtitles = {}
for caption in video_data.get('captions', {}).get('list', []):
for caption in get_list('caption'):
caption_url = caption.get('source')
if not caption_url:
continue
subtitles.setdefault(caption.get('language') or caption.get('locale'), []).append({
'url': caption_url,
})
sub_dict = automatic_captions if caption.get('type') == 'auto' else subtitles
sub_dict.setdefault(dict_get(caption, ('locale', 'language')), []).extend(get_subs(caption_url))
upload_date = self._search_regex(
r'<span[^>]+class="date".*?(\d{4}\.\d{2}\.\d{2})',
webpage, 'upload date', fatal=False)
if upload_date:
upload_date = upload_date.replace('.', '')
user = meta.get('user', {})
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
'description': self._og_search_description(webpage),
'thumbnail': meta.get('cover', {}).get('source') or self._og_search_thumbnail(webpage),
'automatic_captions': automatic_captions,
'thumbnail': try_get(meta, lambda x: x['cover']['source']),
'view_count': int_or_none(meta.get('count')),
'upload_date': upload_date,
'uploader_id': user.get('id'),
'uploader': user.get('name'),
'uploader_url': user.get('url'),
}
class NaverIE(NaverBaseIE):
_VALID_URL = r'https?://(?:m\.)?tv(?:cast)?\.naver\.com/(?:v|embed)/(?P<id>\d+)'
_GEO_BYPASS = False
_TESTS = [{
'url': 'http://tv.naver.com/v/81652',
'info_dict': {
'id': '81652',
'ext': 'mp4',
'title': '[9월 모의고사 해설강의][수학_김상희] 수학 A형 16~20번',
'description': '메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.',
'timestamp': 1378200754,
'upload_date': '20130903',
'uploader': '메가스터디, 합격불변의 법칙',
'uploader_id': 'megastudy',
},
}, {
'url': 'http://tv.naver.com/v/395837',
'md5': '8a38e35354d26a17f73f4e90094febd3',
'info_dict': {
'id': '395837',
'ext': 'mp4',
'title': '9년이 지나도 아픈 기억, 전효성의 아버지',
'description': 'md5:eb6aca9d457b922e43860a2a2b1984d3',
'timestamp': 1432030253,
'upload_date': '20150519',
'uploader': '4가지쇼 시즌2',
'uploader_id': 'wrappinguser29',
},
'skip': 'Georestricted',
}, {
'url': 'http://tvcast.naver.com/v/81652',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
content = self._download_json(
'https://tv.naver.com/api/json/v/' + video_id,
video_id, headers=self.geo_verification_headers())
player_info_json = content.get('playerInfoJson') or {}
current_clip = player_info_json.get('currentClip') or {}
vid = current_clip.get('videoId')
in_key = current_clip.get('inKey')
if not vid or not in_key:
player_auth = try_get(player_info_json, lambda x: x['playerOption']['auth'])
if player_auth == 'notCountry':
self.raise_geo_restricted(countries=['KR'])
elif player_auth == 'notLogin':
self.raise_login_required()
raise ExtractorError('couldn\'t extract vid and key')
info = self._extract_video_info(video_id, vid, in_key)
info.update({
'description': clean_html(current_clip.get('description')),
'timestamp': int_or_none(current_clip.get('firstExposureTime'), 1000),
'duration': parse_duration(current_clip.get('displayPlayTime')),
'like_count': int_or_none(current_clip.get('recommendPoint')),
'age_limit': 19 if current_clip.get('adult') else None,
})
return info

117
youtube_dl/extractor/nbc.py
View File

@ -9,9 +9,13 @@ from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..compat import compat_urllib_parse_unquote
from ..utils import (
smuggle_url,
update_url_query,
int_or_none,
js_to_json,
parse_duration,
smuggle_url,
try_get,
unified_timestamp,
update_url_query,
)
@ -83,11 +87,25 @@ class NBCIE(AdobePassIE):
def _real_extract(self, url):
permalink, video_id = re.match(self._VALID_URL, url).groups()
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={
'query': '''{
page(name: "%s", platform: web, type: VIDEO, userId: "0") {
data {
'query': '''query bonanzaPage(
$app: NBCUBrands! = nbc
$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 {
description
episodeNumber
@ -96,15 +114,20 @@ class NBCIE(AdobePassIE):
mpxAccountId
mpxGuid
rating
resourceId
seasonNumber
secondaryTitle
seriesShortTitle
}
}
}
}''' % permalink,
})
video_data = response['data']['page']['data']
}''',
'variables': json.dumps({
'name': permalink,
'oneApp': True,
'userId': '0',
}),
})['data']['bonanzaPage']['metadata']
query = {
'mbr': 'true',
'manifest': 'm3u',
@ -113,8 +136,8 @@ class NBCIE(AdobePassIE):
title = video_data['secondaryTitle']
if video_data.get('locked'):
resource = self._get_mvpd_resource(
'nbcentertainment', title, video_id,
video_data.get('rating'))
video_data.get('resourceId') or 'nbcentertainment',
title, video_id, video_data.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'nbcentertainment', resource)
theplatform_url = smuggle_url(update_url_query(
@ -285,13 +308,12 @@ class NBCNewsIE(ThePlatformIE):
_TESTS = [
{
'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
'md5': 'af1adfa51312291a017720403826bb64',
'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
'info_dict': {
'id': '269389891880',
'ext': 'mp4',
'title': 'How Twitter Reacted To The Snowden Interview',
'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
'uploader': 'NBCU-NEWS',
'timestamp': 1401363060,
'upload_date': '20140529',
},
@ -309,28 +331,26 @@ class NBCNewsIE(ThePlatformIE):
},
{
'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
'md5': '73135a2e0ef819107bbb55a5a9b2a802',
'md5': '8eb831eca25bfa7d25ddd83e85946548',
'info_dict': {
'id': '394064451844',
'ext': 'mp4',
'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
'timestamp': 1423104900,
'uploader': 'NBCU-NEWS',
'upload_date': '20150205',
},
},
{
'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
'md5': 'a49e173825e5fcd15c13fc297fced39d',
'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
'info_dict': {
'id': '529953347624',
'id': 'n431456',
'ext': 'mp4',
'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
'description': 'md5:c8be487b2d80ff0594c005add88d8351',
'title': "Volkswagen U.S. Chief: We 'Totally Screwed Up'",
'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
'upload_date': '20150922',
'timestamp': 1442917800,
'uploader': 'NBCU-NEWS',
},
},
{
@ -343,7 +363,6 @@ class NBCNewsIE(ThePlatformIE):
'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
'upload_date': '20160420',
'timestamp': 1461152093,
'uploader': 'NBCU-NEWS',
},
},
{
@ -357,7 +376,6 @@ class NBCNewsIE(ThePlatformIE):
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1406937606,
'upload_date': '20140802',
'uploader': 'NBCU-NEWS',
},
},
{
@ -373,20 +391,61 @@ class NBCNewsIE(ThePlatformIE):
def _real_extract(self, url):
video_id = self._match_id(url)
if not video_id.isdigit():
webpage = self._download_webpage(url, video_id)
data = self._parse_json(self._search_regex(
r'window\.__data\s*=\s*({.+});', webpage,
'bootstrap json'), video_id)
video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
'bootstrap json'), video_id, js_to_json)
video_data = try_get(data, lambda x: x['video']['current'], dict)
if not video_data:
video_data = data['article']['content'][0]['primaryMedia']['video']
title = video_data['headline']['primary']
formats = []
for va in video_data.get('videoAssets', []):
public_url = va.get('publicUrl')
if not public_url:
continue
if '://link.theplatform.com/' in public_url:
public_url = update_url_query(public_url, {'format': 'redirect'})
format_id = va.get('format')
if format_id == 'M3U':
formats.extend(self._extract_m3u8_formats(
public_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False))
continue
tbr = int_or_none(va.get('bitrate'), 1000)
if tbr:
format_id += '-%d' % tbr
formats.append({
'format_id': format_id,
'url': public_url,
'width': int_or_none(va.get('width')),
'height': int_or_none(va.get('height')),
'tbr': tbr,
'ext': 'mp4',
})
self._sort_formats(formats)
subtitles = {}
closed_captioning = video_data.get('closedCaptioning')
if closed_captioning:
for cc_url in closed_captioning.values():
if not cc_url:
continue
subtitles.setdefault('en', []).append({
'url': cc_url,
})
return {
'_type': 'url_transparent',
'id': video_id,
# http://feed.theplatform.com/f/2E2eJC/nbcnews also works
'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
'ie_key': 'ThePlatformFeed',
'title': title,
'description': try_get(video_data, lambda x: x['description']['primary']),
'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']),
'duration': parse_duration(video_data.get('duration')),
'timestamp': unified_timestamp(video_data.get('datePublished')),
'formats': formats,
'subtitles': subtitles,
}

27
youtube_dl/extractor/ndr.py
View File

@ -7,8 +7,11 @@ from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
merge_dicts,
parse_iso8601,
qualities,
try_get,
urljoin,
)
@ -85,21 +88,25 @@ class NDRIE(NDRBaseIE):
def _extract_embed(self, webpage, display_id):
embed_url = self._html_search_meta(
'embedURL', webpage, 'embed URL', fatal=True)
'embedURL', webpage, 'embed URL',
default=None) or self._search_regex(
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'embed URL', group='url')
description = self._search_regex(
r'<p[^>]+itemprop="description">([^<]+)</p>',
webpage, 'description', default=None) or self._og_search_description(webpage)
timestamp = parse_iso8601(
self._search_regex(
r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
webpage, 'upload date', fatal=False))
return {
webpage, 'upload date', default=None))
info = self._search_json_ld(webpage, display_id, default={})
return merge_dicts({
'_type': 'url_transparent',
'url': embed_url,
'display_id': display_id,
'description': description,
'timestamp': timestamp,
}
}, info)
class NJoyIE(NDRBaseIE):
@ -220,11 +227,17 @@ class NDREmbedBaseIE(InfoExtractor):
upload_date = ppjson.get('config', {}).get('publicationDate')
duration = int_or_none(config.get('duration'))
thumbnails = [{
thumbnails = []
poster = try_get(config, lambda x: x['poster'], dict) or {}
for thumbnail_id, thumbnail in poster.items():
thumbnail_url = urljoin(url, thumbnail.get('src'))
if not thumbnail_url:
continue
thumbnails.append({
'id': thumbnail.get('quality') or thumbnail_id,
'url': thumbnail['src'],
'url': thumbnail_url,
'preference': quality_key(thumbnail.get('quality')),
} for thumbnail_id, thumbnail in config.get('poster', {}).items() if thumbnail.get('src')]
})
return {
'id': video_id,

14
youtube_dl/extractor/nexx.py
View File

@ -108,7 +108,7 @@ class NexxIE(InfoExtractor):
@staticmethod
def _extract_domain_id(webpage):
mobj = re.search(
r'<script\b[^>]+\bsrc=["\'](?:https?:)?//require\.nexx(?:\.cloud|cdn\.com)/(?P<id>\d+)',
r'<script\b[^>]+\bsrc=["\'](?:https?:)?//(?:require|arc)\.nexx(?:\.cloud|cdn\.com)/(?:sdk/)?(?P<id>\d+)',
webpage)
return mobj.group('id') if mobj else None
@ -123,7 +123,7 @@ class NexxIE(InfoExtractor):
domain_id = NexxIE._extract_domain_id(webpage)
if domain_id:
for video_id in re.findall(
r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)',
r'(?is)onPLAYReady.+?_play\.(?:init|(?:control\.)?addPlayer)\s*\(.+?\s*,\s*["\']?(\d+)',
webpage):
entries.append(
'https://api.nexx.cloud/v3/%s/videos/byid/%s'
@ -410,8 +410,8 @@ class NexxIE(InfoExtractor):
class NexxEmbedIE(InfoExtractor):
_VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P<id>[^/?#&]+)'
_TEST = {
_VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1',
'md5': '16746bfc28c42049492385c989b26c4a',
'info_dict': {
@ -420,7 +420,6 @@ class NexxEmbedIE(InfoExtractor):
'title': 'Nervenkitzel Achterbahn',
'alt_title': 'Karussellbauer in Deutschland',
'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
'release_year': 2005,
'creator': 'SPIEGEL TV',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2761,
@ -431,7 +430,10 @@ class NexxEmbedIE(InfoExtractor):
'format': 'bestvideo',
'skip_download': True,
},
}
}, {
'url': 'https://embed.nexx.cloud/11888/video/DSRTO7UVOX06S7',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):

19
youtube_dl/extractor/nhk.py
View File

@ -6,7 +6,7 @@ from .common import InfoExtractor
class NhkVodIE(InfoExtractor):
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[a-z]+-\d{8}-\d+)'
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/(?P<lang>[a-z]{2})/ondemand/(?P<type>video|audio)/(?P<id>\d{7}|[^/]+?-\d{8}-\d+)'
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
@ -30,8 +30,11 @@ class NhkVodIE(InfoExtractor):
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
'only_matching': True,
}, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/audio/j_art-20150903-1/',
'only_matching': True,
}]
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
_API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7a/episode/%s/%s/all%s.json'
def _real_extract(self, url):
lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
@ -82,15 +85,9 @@ class NhkVodIE(InfoExtractor):
audio = episode['audio']
audio_path = audio['audio']
info['formats'] = self._extract_m3u8_formats(
'https://nhks-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
episode_id, 'm4a', m3u8_id='hls', fatal=False)
for proto in ('rtmpt', 'rtmp'):
info['formats'].append({
'ext': 'flv',
'format_id': proto,
'url': '%s://flv.nhk.or.jp/ondemand/mp4:flv%s' % (proto, audio_path),
'vcodec': 'none',
})
'https://nhkworld-vh.akamaihd.net/i%s/master.m3u8' % audio_path,
episode_id, 'm4a', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False)
for f in info['formats']:
f['language'] = lang
return info

28
youtube_dl/extractor/nintendo.py
View File

@ -5,13 +5,12 @@ import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import unescapeHTML
class NintendoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nintendo\.com/games/detail/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?nintendo\.com/(?:games/detail|nintendo-direct)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.nintendo.com/games/detail/yEiAzhU2eQI1KZ7wOHhngFoAHc1FpHwj',
'url': 'https://www.nintendo.com/games/detail/duck-hunt-wii-u/',
'info_dict': {
'id': 'MzMmticjp0VPzO3CCj4rmFOuohEuEWoW',
'ext': 'flv',
@ -28,7 +27,19 @@ class NintendoIE(InfoExtractor):
'id': 'tokyo-mirage-sessions-fe-wii-u',
'title': 'Tokyo Mirage Sessions ♯FE',
},
'playlist_count': 3,
'playlist_count': 4,
}, {
'url': 'https://www.nintendo.com/nintendo-direct/09-04-2019/',
'info_dict': {
'id': 'J2bXdmaTE6fe3dWJTPcc7m23FNbc_A1V',
'ext': 'mp4',
'title': 'Switch_ROS_ND0904-H264.mov',
'duration': 2324.758,
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
}]
def _real_extract(self, url):
@ -39,8 +50,11 @@ class NintendoIE(InfoExtractor):
entries = [
OoyalaIE._build_url_result(m.group('code'))
for m in re.finditer(
r'class=(["\'])embed-video\1[^>]+data-video-code=(["\'])(?P<code>(?:(?!\2).)+)\2',
webpage)]
r'data-(?:video-id|directVideoId)=(["\'])(?P<code>(?:(?!\1).)+)\1', webpage)]
title = self._html_search_regex(
r'(?s)<(?:span|div)[^>]+class="(?:title|wrapper)"[^>]*>.*?<h1>(.+?)</h1>',
webpage, 'title', fatal=False)
return self.playlist_result(
entries, page_id, unescapeHTML(self._og_search_title(webpage, fatal=False)))
entries, page_id, title)

47
youtube_dl/extractor/nova.py
View File

@ -18,7 +18,7 @@ class NovaEmbedIE(InfoExtractor):
_VALID_URL = r'https?://media\.cms\.nova\.cz/embed/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://media.cms.nova.cz/embed/8o0n0r?autoplay=1',
'md5': 'b3834f6de5401baabf31ed57456463f7',
'md5': 'ee009bafcc794541570edd44b71cbea3',
'info_dict': {
'id': '8o0n0r',
'ext': 'mp4',
@ -44,11 +44,17 @@ class NovaEmbedIE(InfoExtractor):
formats = []
for format_id, format_list in bitrates.items():
if not isinstance(format_list, list):
continue
format_list = [format_list]
for format_url in format_list:
format_url = url_or_none(format_url)
if not format_url:
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 = {
'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|/|$)'
_TESTS = [{
'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260',
'md5': '1dd7b9d5ea27bc361f110cd855a19bd3',
'md5': '249baab7d0104e186e78b0899c7d5f28',
'info_dict': {
'id': '1757139',
'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci',
@ -113,7 +119,8 @@ class NovaIE(InfoExtractor):
'params': {
# rtmp download
'skip_download': True,
}
},
'skip': 'gone',
}, {
# media.cms.nova.cz embed
'url': 'https://novaplus.nova.cz/porad/ulice/epizoda/18760-2180-dil',
@ -128,6 +135,7 @@ class NovaIE(InfoExtractor):
'skip_download': True,
},
'add_ie': [NovaEmbedIE.ie_key()],
'skip': 'CHYBA 404: STRÁNKA NENALEZENA',
}, {
'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html',
'only_matching': True,
@ -152,14 +160,29 @@ class NovaIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
description = clean_html(self._og_search_description(webpage, default=None))
if site == 'novaplus':
upload_date = unified_strdate(self._search_regex(
r'(\d{1,2}-\d{1,2}-\d{4})$', 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
embed_id = self._search_regex(
r'<iframe[^>]+\bsrc=["\'](?:https?:)?//media\.cms\.nova\.cz/embed/([^/?#&]+)',
webpage, 'embed url', default=None)
if embed_id:
return self.url_result(
'https://media.cms.nova.cz/embed/%s' % embed_id,
ie=NovaEmbedIE.ie_key(), video_id=embed_id)
return {
'_type': 'url_transparent',
'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(
[r"(?:media|video_id)\s*:\s*'(\d+)'",
@ -233,18 +256,8 @@ class NovaIE(InfoExtractor):
self._sort_formats(formats)
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')
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 {
'id': video_id,
'display_id': display_id,

16
youtube_dl/extractor/npr.py
View File

@ -4,6 +4,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
url_or_none,
)
@ -48,6 +49,10 @@ class NprIE(InfoExtractor):
},
}],
'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):
@ -95,6 +100,17 @@ class NprIE(InfoExtractor):
'format_id': 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)
entries.append({

48
youtube_dl/extractor/nrk.py
View File

@ -12,6 +12,7 @@ from ..utils import (
ExtractorError,
int_or_none,
JSON_LD_RE,
js_to_json,
NO_DEFAULT,
parse_age_limit,
parse_duration,
@ -105,6 +106,7 @@ class NRKBaseIE(InfoExtractor):
MESSAGES = {
'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
'ProgramRightsHasExpired': 'Programmet har gått ut',
'NoProgramRights': 'Ikke tilgjengelig',
'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
}
message_type = data.get('messageType', '')
@ -255,6 +257,17 @@ class NRKTVIE(NRKBaseIE):
''' % _EPISODE_RE
_API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')
_TESTS = [{
'url': 'https://tv.nrk.no/program/MDDP12000117',
'md5': '8270824df46ec629b66aeaa5796b36fb',
'info_dict': {
'id': 'MDDP12000117AA',
'ext': 'mp4',
'title': 'Alarm Trolltunga',
'description': 'md5:46923a6e6510eefcce23d5ef2a58f2ce',
'duration': 2223,
'age_limit': 6,
},
}, {
'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
'md5': '9a167e54d04671eb6317a37b7bc8a280',
'info_dict': {
@ -266,6 +279,7 @@ class NRKTVIE(NRKBaseIE):
'series': '20 spørsmål',
'episode': '23.05.2014',
},
'skip': 'NoProgramRights',
}, {
'url': 'https://tv.nrk.no/program/mdfp15000514',
'info_dict': {
@ -370,7 +384,24 @@ class NRKTVIE(NRKBaseIE):
class NRKTVEpisodeIE(InfoExtractor):
_VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'
_TEST = {
_TESTS = [{
'url': 'https://tv.nrk.no/serie/hellums-kro/sesong/1/episode/2',
'info_dict': {
'id': 'MUHH36005220BA',
'ext': 'mp4',
'title': 'Kro, krig og kjærlighet 2:6',
'description': 'md5:b32a7dc0b1ed27c8064f58b97bda4350',
'duration': 1563,
'series': 'Hellums kro',
'season_number': 1,
'episode_number': 2,
'episode': '2:6',
'age_limit': 6,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',
'info_dict': {
'id': 'MSUI14000816AA',
@ -386,7 +417,8 @@ class NRKTVEpisodeIE(InfoExtractor):
'params': {
'skip_download': True,
},
}
'skip': 'ProgramRightsHasExpired',
}]
def _real_extract(self, url):
display_id = self._match_id(url)
@ -409,7 +441,7 @@ class NRKTVSerieBaseIE(InfoExtractor):
(r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False)
display_id, fatal=False, transform_source=js_to_json)
if not config:
return
return try_get(
@ -479,6 +511,14 @@ class NRKTVSeriesIE(NRKTVSerieBaseIE):
_VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
_ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
_TESTS = [{
'url': 'https://tv.nrk.no/serie/blank',
'info_dict': {
'id': 'blank',
'title': 'Blank',
'description': 'md5:7664b4e7e77dc6810cd3bca367c25b6e',
},
'playlist_mincount': 30,
}, {
# new layout, seasons
'url': 'https://tv.nrk.no/serie/backstage',
'info_dict': {
@ -648,7 +688,7 @@ class NRKSkoleIE(InfoExtractor):
_TESTS = [{
'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
'md5': '18c12c3d071953c3bf8d54ef6b2587b7',
'info_dict': {
'id': '6021',
'ext': 'mp4',

4
youtube_dl/extractor/nrl.py
View File

@ -23,8 +23,8 @@ class NRLTVIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
q_data = self._parse_json(self._search_regex(
r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
q_data = self._parse_json(self._html_search_regex(
r'(?s)q-data="({.+?})"', webpage, 'player data'), display_id)
ooyala_id = q_data['videoId']
return self.url_result(
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))

49
youtube_dl/extractor/ntvru.py
View File

@ -3,9 +3,10 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
xpath_text,
int_or_none,
strip_or_none,
unescapeHTML,
xpath_text,
)
@ -47,10 +48,10 @@ class NTVRuIE(InfoExtractor):
'duration': 1496,
},
}, {
'url': 'http://www.ntv.ru/kino/Koma_film',
'md5': 'f825770930937aa7e5aca0dc0d29319a',
'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/',
'md5': 'e9c7cde24d9d3eaed545911a04e6d4f4',
'info_dict': {
'id': '1007609',
'id': '1126480',
'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»',
@ -68,6 +69,10 @@ class NTVRuIE(InfoExtractor):
'thumbnail': r're:^http://.*\.jpg',
'duration': 2590,
},
}, {
# Schemeless file URL
'url': 'https://www.ntv.ru/video/1797442',
'only_matching': True,
}]
_VIDEO_ID_REGEXES = [
@ -96,37 +101,31 @@ class NTVRuIE(InfoExtractor):
'http://www.ntv.ru/vi%s/' % video_id,
video_id, 'Downloading video XML')
title = clean_html(xpath_text(player, './data/title', 'title', fatal=True))
description = clean_html(xpath_text(player, './data/description', 'description'))
title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True)))
video = player.find('./data/video')
video_id = xpath_text(video, './id', 'video id')
thumbnail = xpath_text(video, './splash', 'thumbnail')
duration = int_or_none(xpath_text(video, './totaltime', 'duration'))
view_count = int_or_none(xpath_text(video, './views', 'view count'))
token = self._download_webpage(
'http://stat.ntv.ru/services/access/token',
video_id, 'Downloading access token')
formats = []
for format_id in ['', 'hi', 'webm']:
file_ = video.find('./%sfile' % format_id)
if file_ is None:
file_ = xpath_text(video, './%sfile' % format_id)
if not file_:
continue
size = video.find('./%ssize' % format_id)
if file_.startswith('//'):
file_ = self._proto_relative_url(file_)
elif not file_.startswith('http'):
file_ = 'http://media.ntv.ru/vod/' + file_
formats.append({
'url': 'http://media2.ntv.ru/vod/%s&tok=%s' % (file_.text, token),
'filesize': int_or_none(size.text if size is not None else None),
'url': file_,
'filesize': int_or_none(xpath_text(video, './%ssize' % format_id)),
})
self._sort_formats(formats)
return {
'id': video_id,
'id': xpath_text(video, './id'),
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))),
'thumbnail': xpath_text(video, './splash'),
'duration': int_or_none(xpath_text(video, './totaltime')),
'view_count': int_or_none(xpath_text(video, './views')),
'formats': formats,
}

4
youtube_dl/extractor/nytimes.py
View File

@ -69,10 +69,10 @@ class NYTimesBaseIE(InfoExtractor):
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'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,
})
self._sort_formats(formats)
self._sort_formats(formats, ('height', 'width', 'filesize', 'tbr', 'fps', 'format_id'))
thumbnails = []
for image in video_data.get('images', []):

Some files were not shown because too many files have changed in this diff Show More