Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-23 17:04:33 +01:00
Code Issues Releases Wiki Activity

Merge pull request #2 from ytdl-org/master

Browse Source 
Master 31.12.2019
This commit is contained in:
Oneboy1979 2019-12-31 20:03:13 +01:00 committed by GitHub
commit f22debf3e0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
201 changed files with 8251 additions and 8489 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 2019.06.27. 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 Issues with outdated version will be REJECTED.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 2019.12.25. 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 Issues with outdated version will be REJECTED.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 **2019.06.27**
- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
- [ ] 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 2019.06.27
[debug] youtube-dl version 2019.12.25
[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 2019.06.27. 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 2019.12.25. 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 **2019.06.27**
- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
- [ ] 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 2019.06.27. 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 2019.12.25. 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 **2019.06.27**
- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
- [ ] 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 2019.06.27. 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 2019.12.25. 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 **2019.06.27**
- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
- [ ] 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 2019.06.27
[debug] youtube-dl version 2019.12.25
[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 2019.06.27. 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 2019.12.25. 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 **2019.06.27**
- [ ] I've verified that I'm running youtube-dl version **2019.12.25**
- [ ] I've searched the bugtracker for similar feature requests including closed ones

6
.travis.yml
View File

@ -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

66
CONTRIBUTING.md
View File

@ -339,6 +339,72 @@ Incorrect:
'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
```
### Inline values
Extracting variables is acceptable for reducing code duplication and improving readability of complex expressions. However, you should avoid extracting variables used only once and moving them to opposite parts of the extractor file, which makes reading the linear flow difficult.
#### Example
Correct:
```python
title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
```
Incorrect:
```python
TITLE_RE = r'<title>([^<]+)</title>'
# ...some lines of code...
title = self._html_search_regex(TITLE_RE, webpage, 'title')
```
### Collapse fallbacks
Multiple fallback values can quickly become unwieldy. Collapse multiple fallback values into a single expression via a list of patterns.
#### Example
Good:
```python
description = self._html_search_meta(
['og:description', 'description', 'twitter:description'],
webpage, 'description', default=None)
```
Unwieldy:
```python
description = (
self._og_search_description(webpage, default=None)
or self._html_search_meta('description', webpage, default=None)
or self._html_search_meta('twitter:description', webpage, default=None))
```
Methods supporting list of patterns are: `_search_regex`, `_html_search_regex`, `_og_search_property`, `_html_search_meta`.
### Trailing parentheses
Always move trailing parentheses after the last argument.
#### Example
Correct:
```python
lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
list)
```
Incorrect:
```python
lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
list,
)
```
### Use convenience conversion and parsing functions
Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.

478
ChangeLog
View File

@ -1,3 +1,477 @@
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
* [utils] Improve subtitles_filename (#22753)
Extractors
* [facebook] Bypass download rate limits (#21018)
+ [contv] Add support for contv.com
- [viewster] Remove extractor
* [xfileshare] Improve extractor (#17032, #17906, #18237, #18239)
* Update the list of domains
+ Add support for aa-encoded video data
* Improve jwplayer format extraction
+ Add support for Clappr sources
* [mangomolo] Fix video format extraction and add support for player URLs
* [audioboom] Improve metadata extraction
* [twitch] Update VOD URL matching (#22395, #22727)
- [mit] Remove support for video.mit.edu (#22403)
- [servingsys] Remove extractor (#22639)
* [dumpert] Fix extraction (#22428, #22564)
* [atresplayer] Fix extraction (#16277, #16716)
version 2019.10.16
Core
* [extractor/common] Make _is_valid_url more relaxed
Extractors
* [vimeo] Improve album videos id extraction (#22599)
+ [globo] Extract subtitles (#22713)
* [bokecc] Improve player params extraction (#22638)
* [nexx] Handle result list (#22666)
* [vimeo] Fix VHX embed extraction
* [nbc] Switch to graphql API (#18581, #22693, #22701)
- [vessel] Remove extractor
- [promptfile] Remove extractor (#6239)
* [kaltura] Fix service URL extraction (#22658)
* [kaltura] Fix embed info strip (#22658)
* [globo] Fix format extraction (#20319)
* [redtube] Improve metadata extraction (#22492, #22615)
* [pornhub:uservideos:upload] Fix extraction (#22619)
+ [telequebec:squat] Add support for squat.telequebec.tv (#18503)
- [wimp] Remove extractor (#22088, #22091)
+ [gfycat] Extend URL regular expression (#22225)
+ [chaturbate] Extend URL regular expression (#22309)
* [peertube] Update instances (#22414)
+ [telequebec] Add support for coucou.telequebec.tv (#22482)
+ [xvideos] Extend URL regular expression (#22471)
- [youtube] Remove support for invidious.enkirton.net (#22543)
+ [openload] Add support for oload.monster (#22592)
* [nrktv:seriebase] Fix extraction (#22596)
+ [youtube] Add support for yt.lelux.fi (#22597)
* [orf:tvthek] Make manifest requests non fatal (#22578)
* [teachable] Skip login when already logged in (#22572)
* [viewlift] Improve extraction (#22545)
* [nonktube] Fix extraction (#22544)
version 2019.09.28
Core
* [YoutubeDL] Honour all --get-* options with --flat-playlist (#22493)
Extractors
* [vk] Fix extraction (#22522)
* [heise] Fix kaltura embeds extraction (#22514)
* [ted] Check for resources validity and extract subtitled downloads (#22513)
+ [youtube] Add support for
owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya.b32.i2p (#22292)
+ [nhk] Add support for clips
* [nhk] Fix video extraction (#22249, #22353)
* [byutv] Fix extraction (#22070)
+ [openload] Add support for oload.online (#22304)
+ [youtube] Add support for invidious.drycat.fr (#22451)
* [jwplatfom] Do not match video URLs (#20596, #22148)
* [youtube:playlist] Unescape playlist uploader (#22483)
+ [bilibili] Add support audio albums and songs (#21094)
+ [instagram] Add support for tv URLs
+ [mixcloud] Allow uppercase letters in format URLs (#19280)
* [brightcove] Delegate all supported legacy URLs to new extractor (#11523,
#12842, #13912, #15669, #16303)
* [hotstar] Use native HLS downloader by default
+ [hotstar] Extract more formats (#22323)
* [9now] Fix extraction (#22361)
* [zdf] Bypass geo restriction
+ [tv4] Extract series metadata
* [tv4] Fix extraction (#22443)
version 2019.09.12.1
Extractors
* [youtube] Remove quality and tbr for itag 43 (#22372)
version 2019.09.12
Extractors
* [youtube] Quick extraction tempfix (#22367, #22163)
version 2019.09.01
Core
+ [extractor/generic] Add support for squarespace embeds (#21294, #21802,
#21859)
+ [downloader/external] Respect mtime option for aria2c (#22242)
Extractors
+ [xhamster:user] Add support for user pages (#16330, #18454)
+ [xhamster] Add support for more domains
+ [verystream] Add support for woof.tube (#22217)
+ [dailymotion] Add support for lequipe.fr (#21328, #22152)
+ [openload] Add support for oload.vip (#22205)
+ [bbccouk] Extend URL regular expression (#19200)
+ [youtube] Add support for invidious.nixnet.xyz and yt.elukerio.org (#22223)
* [safari] Fix authentication (#22161, #22184)
* [usanetwork] Fix extraction (#22105)
+ [einthusan] Add support for einthusan.ca (#22171)
* [youtube] Improve unavailable message extraction (#22117)
+ [piksel] Extract subtitles (#20506)
version 2019.08.13
Core
* [downloader/fragment] Fix ETA calculation of resumed download (#21992)
* [YoutubeDL] Check annotations availability (#18582)
Extractors
* [youtube:playlist] Improve flat extraction (#21927)
* [youtube] Fix annotations extraction (#22045)
+ [discovery] Extract series meta field (#21808)
* [youtube] Improve error detection (#16445)
* [vimeo] Fix album extraction (#1933, #15704, #15855, #18967, #21986)
+ [roosterteeth] Add support for watch URLs
* [discovery] Limit video data by show slug (#21980)
version 2019.08.02
Extractors
+ [tvigle] Add support for HLS and DASH formats (#21967)
* [tvigle] Fix extraction (#21967)
+ [yandexvideo] Add support for DASH formats (#21971)
* [discovery] Use API call for video data extraction (#21808)
+ [mgtv] Extract format_note (#21881)
* [tvn24] Fix metadata extraction (#21833, #21834)
* [dlive] Relax URL regular expression (#21909)
+ [openload] Add support for oload.best (#21913)
* [youtube] Improve metadata extraction for age gate content (#21943)
version 2019.07.30
Extractors
* [youtube] Fix and improve title and description extraction (#21934)
version 2019.07.27
Extractors
+ [yahoo:japannews] Add support for yahoo.co.jp (#21698, #21265)
+ [discovery] Add support go.discovery.com URLs
* [youtube:playlist] Relax video regular expression (#21844)
* [generic] Restrict --default-search schemeless URLs detection pattern
(#21842)
* [vrv] Fix CMS signing query extraction (#21809)
version 2019.07.16
Extractors
+ [asiancrush] Add support for yuyutv.com, midnightpulp.com and cocoro.tv
(#21281, #21290)
* [kaltura] Check source format URL (#21290)
* [ctsnews] Fix YouTube embeds extraction (#21678)
+ [einthusan] Add support for einthusan.com (#21748, #21775)
+ [youtube] Add support for invidious.mastodon.host (#21777)
+ [gfycat] Extend URL regular expression (#21779, #21780)
* [youtube] Restrict is_live extraction (#21782)
version 2019.07.14
Extractors
* [porn91] Fix extraction (#21312)
+ [yandexmusic] Extract track number and disk number (#21421)
+ [yandexmusic] Add support for multi disk albums (#21420, #21421)
* [lynda] Handle missing subtitles (#20490, #20513)
+ [youtube] Add more invidious instances to URL regular expression (#21694)
* [twitter] Improve uploader id extraction (#21705)
* [spankbang] Fix and improve metadata extraction
* [spankbang] Fix extraction (#21763, #21764)
+ [dlive] Add support for dlive.tv (#18080)
+ [livejournal] Add support for livejournal.com (#21526)
* [roosterteeth] Fix free episode extraction (#16094)
* [dbtv] Fix extraction
* [bellator] Fix extraction
- [rudo] Remove extractor (#18430, #18474)
* [facebook] Fallback to twitter:image meta for thumbnail extraction (#21224)
* [bleacherreport] Fix Bleacher Report CMS extraction
* [espn] Fix fivethirtyeight.com extraction
* [5tv] Relax video URL regular expression and support https URLs
* [youtube] Fix is_live extraction (#21734)
* [youtube] Fix authentication (#11270)
version 2019.07.12
Core
+ [adobepass] Add support for AT&T U-verse (mso ATT) (#13938, #21016)
Extractors
+ [mgtv] Pass Referer HTTP header for format URLs (#21726)
+ [beeg] Add support for api/v6 v2 URLs without t argument (#21701)
* [voxmedia:volume] Improvevox embed extraction (#16846)
* [funnyordie] Move extraction to VoxMedia extractor (#16846)
* [gameinformer] Fix extraction (#8895, #15363, #17206)
* [funk] Fix extraction (#17915)
* [packtpub] Relax lesson URL regular expression (#21695)
* [packtpub] Fix extraction (#21268)
* [philharmoniedeparis] Relax URL regular expression (#21672)
* [peertube] Detect embed URLs in generic extraction (#21666)
* [mixer:vod] Relax URL regular expression (#21657, #21658)
+ [lecturio] Add support id based URLs (#21630)
+ [go] Add site info for disneynow (#21613)
* [ted] Restrict info regular expression (#21631)
* [twitch:vod] Actualize m3u8 URL (#21538, #21607)
* [vzaar] Fix videos with empty title (#21606)
* [tvland] Fix extraction (#21384)
* [arte] Clean extractor (#15583, #21614)
version 2019.07.02
Core
+ [utils] Introduce random_user_agent and use as default User-Agent (#21546)
Extractors
+ [vevo] Add support for embed.vevo.com URLs (#21565)
+ [openload] Add support for oload.biz (#21574)
* [xiami] Update API base URL (#21575)
* [yourporn] Fix extraction (#21585)
+ [acast] Add support for URLs with episode id (#21444)
+ [dailymotion] Add support for DM.player embeds
* [soundcloud] Update client id
version 2019.06.27
Extractors
@ -162,7 +636,7 @@ 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
@ -727,7 +1201,7 @@ 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)

70
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
```
@ -1216,6 +1216,72 @@ Incorrect:
'PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4'
```
### Inline values
Extracting variables is acceptable for reducing code duplication and improving readability of complex expressions. However, you should avoid extracting variables used only once and moving them to opposite parts of the extractor file, which makes reading the linear flow difficult.
#### Example
Correct:
```python
title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
```
Incorrect:
```python
TITLE_RE = r'<title>([^<]+)</title>'
# ...some lines of code...
title = self._html_search_regex(TITLE_RE, webpage, 'title')
```
### Collapse fallbacks
Multiple fallback values can quickly become unwieldy. Collapse multiple fallback values into a single expression via a list of patterns.
#### Example
Good:
```python
description = self._html_search_meta(
['og:description', 'description', 'twitter:description'],
webpage, 'description', default=None)
```
Unwieldy:
```python
description = (
self._og_search_description(webpage, default=None)
or self._html_search_meta('description', webpage, default=None)
or self._html_search_meta('twitter:description', webpage, default=None))
```
Methods supporting list of patterns are: `_search_regex`, `_html_search_regex`, `_og_search_property`, `_html_search_meta`.
### Trailing parentheses
Always move trailing parentheses after the last argument.
#### Example
Correct:
```python
lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
list)
```
Incorrect:
```python
lambda x: x['ResultSet']['Result'][0]['VideoUrlSet']['VideoUrl'],
list,
)
```
### Use convenience conversion and parsing functions
Wrap all extracted numeric data into safe functions from [`youtube_dl/utils.py`](https://github.com/ytdl-org/youtube-dl/blob/master/youtube_dl/utils.py): `int_or_none`, `float_or_none`. Use them for string to number conversions as well.

81
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
@ -58,16 +58,8 @@
- **ARD:mediathek**
- **ARDBetaMediathek**
- **Arkena**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:cinema**
- **arte.tv:concert**
- **arte.tv:creative**
- **arte.tv:ddc**
- **arte.tv:embed**
- **arte.tv:future**
- **arte.tv:info**
- **arte.tv:magazine**
- **arte.tv:playlist**
- **AsianCrush**
- **AsianCrushPlaylist**
@ -84,8 +76,6 @@
- **awaan:video**
- **AZMedien**: AZ Medien videos
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **Bandcamp:weekly**
@ -106,6 +96,8 @@
- **Bigflix**
- **Bild**: Bild.de
- **BiliBili**
- **BilibiliAudio**
- **BilibiliAudioAlbum**
- **BioBioChileTV**
- **BIQLE**
- **BitChute**
@ -183,12 +175,12 @@
- **CNN**
- **CNNArticle**
- **CNNBlogs**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralFullEpisodes**
- **ComedyCentralShortname**
- **ComedyCentralTV**
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **CONtv**
- **Corus**
- **Coub**
- **Cracked**
@ -210,8 +202,6 @@
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **DaisukiMotto**
- **DaisukiMottoPlaylist**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
@ -231,11 +221,12 @@
- **DiscoveryNetworksDe**
- **DiscoveryVR**
- **Disney**
- **dlive:stream**
- **dlive:vod**
- **Dotsub**
- **DouyuShow**
- **DouyuTV**: 斗鱼
- **DPlay**
- **DPlayIt**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
@ -288,12 +279,12 @@
- **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**
@ -313,16 +304,12 @@
- **FrontendMastersCourse**
- **FrontendMastersLesson**
- **Funimation**
- **FunkChannel**
- **FunkMix**
- **FunnyOrDie**
- **Funk**
- **Fusion**
- **Fux**
- **FXNetworks**
- **Gaia**
- **GameInformer**
- **GameOne**
- **gameone:playlist**
- **GameSpot**
- **GameStar**
- **Gaskrank**
@ -337,14 +324,12 @@
- **Globo**
- **GloboArticle**
- **Go**
- **Go90**
- **GodTube**
- **Golem**
- **GoogleDrive**
- **Goshgay**
- **GPUTechConf**
- **Groupon**
- **Hark**
- **hbo**
- **HearThisAt**
- **Heise**
@ -373,7 +358,6 @@
- **Hungama**
- **HungamaSong**
- **Hypem**
- **Iconosquare**
- **ign.com**
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
@ -413,14 +397,14 @@
- **Kankan**
- **Karaoketv**
- **KarriereVideos**
- **keek**
- **Katsomo**
- **KeezMovies**
- **Ketnet**
- **KhanAcademy**
- **KickStarter**
- **KinjaEmbed**
- **KinoPoisk**
- **KonserthusetPlay**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
- **Ku6**
- **KUSI**
@ -437,7 +421,6 @@
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **Learnr**
- **Lecture2Go**
- **Lecturio**
- **LecturioCourse**
@ -458,6 +441,7 @@
- **linkedin:learning:course**
- **LinuxAcademy**
- **LiTV**
- **LiveJournal**
- **LiveLeak**
- **LiveLeakEmbed**
- **livestream**
@ -470,11 +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**
@ -501,14 +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**
@ -530,11 +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**
@ -639,7 +618,6 @@
- **OnionStudios**
- **Ooyala**
- **OoyalaExternal**
- **Openload**
- **OraTV**
- **orf:fm4**: radio FM4
- **orf:fm4:story**: fm4.orf.at stories
@ -699,7 +677,6 @@
- **PornoXO**
- **PornTube**
- **PressTV**
- **PromptFile**
- **prosiebensat1**: ProSiebenSat.1 Digital
- **puhutv**
- **puhutv:serie**
@ -740,8 +717,6 @@
- **Restudy**
- **Reuters**
- **ReverbNation**
- **revision**
- **revision3:embed**
- **RICE**
- **RMCDecouverte**
- **RockstarGames**
@ -764,7 +739,6 @@
- **rtve.es:television**
- **RTVNH**
- **RTVS**
- **Rudo**
- **RUHD**
- **rutube**: Rutube videos
- **rutube:channel**: Rutube channels
@ -788,10 +762,11 @@
- **Screencast**
- **ScreencastOMatic**
- **scrippsnetworks:watch**
- **SCTE**
- **SCTECourse**
- **Seeker**
- **SenateISVP**
- **SendtoNews**
- **ServingSys**
- **Servus**
- **Sexu**
- **SeznamZpravy**
@ -822,6 +797,7 @@
- **soundcloud:set**
- **soundcloud:trackstation**
- **soundcloud:user**
- **SoundcloudEmbed**
- **soundgasm**
- **soundgasm:profile**
- **southpark.cc.com**
@ -848,7 +824,6 @@
- **Steam**
- **Stitcher**
- **Streamable**
- **Streamango**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -890,13 +865,14 @@
- **TeleQuebec**
- **TeleQuebecEmission**
- **TeleQuebecLive**
- **TeleQuebecSquat**
- **TeleTask**
- **Telewebion**
- **TennisTV**
- **TenPlay**
- **TF1**
- **TFO**
- **TheIntercept**
- **theoperaplatform**
- **ThePlatform**
- **ThePlatformFeed**
- **TheScene**
@ -932,11 +908,12 @@
- **tunein:topic**
- **TunePk**
- **Turbo**
- **Tutv**
- **tv.dfb.de**
- **TV2**
- **tv2.hu**
- **TV2Article**
- **TV2DK**
- **TV2DKBornholmPlay**
- **TV4**: tv4.se and tv4play.se
- **TV5MondePlus**: TV5MONDE+
- **TVA**
@ -973,10 +950,12 @@
- **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
@ -997,8 +976,6 @@
- **Vbox7**
- **VeeHD**
- **Veoh**
- **verystream**
- **Vessel**
- **Vesti**: Вести.Ru
- **Vevo**
- **VevoPlaylist**
@ -1013,13 +990,11 @@
- **Viddler**
- **Videa**
- **video.google:search**: Google Video search
- **video.mit.edu**
- **VideoDetective**
- **videofy.me**
- **videomore**
- **videomore:season**
- **videomore:video**
- **VideoPremium**
- **VideoPress**
- **Vidio**
- **VidLii**
@ -1031,7 +1006,6 @@
- **vier:videos**
- **ViewLift**
- **ViewLiftEmbed**
- **Viewster**
- **Viidea**
- **viki**
- **viki:channel**
@ -1097,7 +1071,6 @@
- **Weibo**
- **WeiboMobile**
- **WeiqiTV**: WQTV
- **Wimp**
- **Wistia**
- **wnl**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **WorldStarHipHop**
@ -1106,9 +1079,10 @@
- **WWE**
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV, FastVideo.me
- **XFileShare**: XFileShare based sites: ClipWatching, GoUnlimited, GoVid, HolaVid, Streamty, TheVideoBee, Uqload, VidBom, vidlo, VidLocker, VidShare, VUp, XVideoSharing
- **XHamster**
- **XHamsterEmbed**
- **XHamsterUser**
- **xiami:album**: 虾米音乐 - 专辑
- **xiami:artist**: 虾米音乐 - 歌手
- **xiami:collection**: 虾米音乐 - 精选集
@ -1126,6 +1100,7 @@
- **Yahoo**: Yahoo screen and movies
- **yahoo:gyao**
- **yahoo:gyao:player**
- **yahoo:japannews**: Yahoo! Japan News
- **YandexDisk**
- **yandexmusic:album**: Яндекс.Музыка - Альбом
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист

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:

30
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,
@ -69,11 +70,13 @@ from youtube_dl.utils import (
remove_start,
remove_end,
remove_quotes,
rot47,
shell_quote,
smuggle_url,
str_to_int,
strip_jsonp,
strip_or_none,
subtitles_filename,
timeconvert,
unescapeHTML,
unified_strdate,
@ -261,6 +264,11 @@ class TestUtil(unittest.TestCase):
self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
def test_subtitles_filename(self):
self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
self.assertEqual(subtitles_filename('abc.unexpected_ext', 'en', 'vtt', 'ext'), 'abc.unexpected_ext.en.vtt')
def test_remove_start(self):
self.assertEqual(remove_start(None, 'A - '), None)
self.assertEqual(remove_start('A - B', 'A - '), 'B')
@ -334,6 +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)
@ -489,6 +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/'), '')
@ -1361,6 +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)

66
youtube_dl/YoutubeDL.py
View File

@ -852,8 +852,9 @@ class YoutubeDL(object):
extract_flat = self.params.get('extract_flat', False)
if ((extract_flat == 'in_playlist' and 'playlist' in extra_info)
or extract_flat is True):
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(ie_result))
self.__forced_printings(
ie_result, self.prepare_filename(ie_result),
incomplete=True)
return ie_result
if result_type == 'video':
@ -1693,6 +1694,36 @@ class YoutubeDL(object):
subs[lang] = f
return subs
def __forced_printings(self, info_dict, filename, incomplete):
def print_mandatory(field):
if (self.params.get('force%s' % field, False)
and (not incomplete or info_dict.get(field) is not None)):
self.to_stdout(info_dict[field])
def print_optional(field):
if (self.params.get('force%s' % field, False)
and info_dict.get(field) is not None):
self.to_stdout(info_dict[field])
print_mandatory('title')
print_mandatory('id')
if self.params.get('forceurl', False) and not incomplete:
if info_dict.get('requested_formats') is not None:
for f in info_dict['requested_formats']:
self.to_stdout(f['url'] + f.get('play_path', ''))
else:
# For RTMP URLs, also include the playpath
self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
print_optional('thumbnail')
print_optional('description')
if self.params.get('forcefilename', False) and filename is not None:
self.to_stdout(filename)
if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
self.to_stdout(formatSeconds(info_dict['duration']))
print_mandatory('format')
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(info_dict))
def process_info(self, info_dict):
"""Process a single resolved IE result."""
@ -1703,9 +1734,8 @@ class YoutubeDL(object):
if self._num_downloads >= int(max_downloads):
raise MaxDownloadsReached()
# TODO: backward compatibility, to be removed
info_dict['fulltitle'] = info_dict['title']
if len(info_dict['title']) > 200:
info_dict['title'] = info_dict['title'][:197] + '...'
if 'format' not in info_dict:
info_dict['format'] = info_dict['ext']
@ -1720,29 +1750,7 @@ class YoutubeDL(object):
info_dict['_filename'] = filename = self.prepare_filename(info_dict)
# Forced printings
if self.params.get('forcetitle', False):
self.to_stdout(info_dict['fulltitle'])
if self.params.get('forceid', False):
self.to_stdout(info_dict['id'])
if self.params.get('forceurl', False):
if info_dict.get('requested_formats') is not None:
for f in info_dict['requested_formats']:
self.to_stdout(f['url'] + f.get('play_path', ''))
else:
# For RTMP URLs, also include the playpath
self.to_stdout(info_dict['url'] + info_dict.get('play_path', ''))
if self.params.get('forcethumbnail', False) and info_dict.get('thumbnail') is not None:
self.to_stdout(info_dict['thumbnail'])
if self.params.get('forcedescription', False) and info_dict.get('description') is not None:
self.to_stdout(info_dict['description'])
if self.params.get('forcefilename', False) and filename is not None:
self.to_stdout(filename)
if self.params.get('forceduration', False) and info_dict.get('duration') is not None:
self.to_stdout(formatSeconds(info_dict['duration']))
if self.params.get('forceformat', False):
self.to_stdout(info_dict['format'])
if self.params.get('forcejson', False):
self.to_stdout(json.dumps(info_dict))
self.__forced_printings(info_dict, filename, incomplete=False)
# Do nothing else if in simulate mode
if self.params.get('simulate', False):
@ -1783,6 +1791,8 @@ class YoutubeDL(object):
annofn = replace_extension(filename, 'annotations.xml', info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(annofn)):
self.to_screen('[info] Video annotations are already present')
elif not info_dict.get('annotations'):
self.report_warning('There are no annotations to write.')
else:
try:
self.to_screen('[info] Writing video annotations to: ' + annofn)
@ -1804,7 +1814,7 @@ class YoutubeDL(object):
ie = self.get_info_extractor(info_dict['extractor_key'])
for sub_lang, sub_info in subtitles.items():
sub_format = sub_info['ext']
sub_filename = subtitles_filename(filename, sub_lang, sub_format)
sub_filename = subtitles_filename(filename, sub_lang, sub_format, info_dict.get('ext'))
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)):
self.to_screen('[info] Video subtitle %s.%s is already present' % (sub_lang, sub_format))
else:

2
youtube_dl/__init__.py
View File

@ -94,7 +94,7 @@ def _real_main(argv=None):
if opts.verbose:
write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
except IOError:
sys.exit('ERROR: batch file could not be read')
sys.exit('ERROR: batch file %s could not be read' % opts.batchfile)
all_urls = batch_urls + [url.strip() for url in args] # batch_urls are already striped in read_batch_urls
_enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]

2
youtube_dl/downloader/dash.py
View File

@ -53,7 +53,7 @@ class DashSegmentsFD(FragmentFD):
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
# whole download to fail. However if the same fragment is immediately
# retried with the same request data this usually succeeds (1-2 attemps
# retried with the same request data this usually succeeds (1-2 attempts
# is usually enough) thus allowing to download the whole file successfully.
# To be future-proof we will retry all fragments that fail with any
# HTTP error.

1
youtube_dl/downloader/external.py
View File

@ -194,6 +194,7 @@ class Aria2cFD(ExternalFD):
cmd += self._option('--interface', 'source_address')
cmd += self._option('--all-proxy', 'proxy')
cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
cmd += ['--', info_dict['url']]
return cmd

7
youtube_dl/downloader/fragment.py
View File

@ -190,12 +190,13 @@ class FragmentFD(FileDownloader):
})
def _start_frag_download(self, ctx):
resume_len = ctx['complete_frags_downloaded_bytes']
total_frags = ctx['total_frags']
# This dict stores the download progress, it's updated by the progress
# hook
state = {
'status': 'downloading',
'downloaded_bytes': ctx['complete_frags_downloaded_bytes'],
'downloaded_bytes': resume_len,
'fragment_index': ctx['fragment_index'],
'fragment_count': total_frags,
'filename': ctx['filename'],
@ -234,8 +235,8 @@ class FragmentFD(FileDownloader):
state['downloaded_bytes'] += frag_downloaded_bytes - ctx['prev_frag_downloaded_bytes']
if not ctx['live']:
state['eta'] = self.calc_eta(
start, time_now, estimated_size,
state['downloaded_bytes'])
start, time_now, estimated_size - resume_len,
state['downloaded_bytes'] - resume_len)
state['speed'] = s.get('speed') or ctx.get('speed')
ctx['speed'] = state['speed']
ctx['prev_frag_downloaded_bytes'] = frag_downloaded_bytes

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)

2
youtube_dl/downloader/ism.py
View File

@ -146,7 +146,7 @@ def write_piff_header(stream, params):
sps, pps = codec_private_data.split(u32.pack(1))[1:]
avcc_payload = u8.pack(1) # configuration version
avcc_payload += sps[1:4] # avc profile indication + profile compatibility + avc level indication
avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete represenation (1) + reserved (11111) + length size minus one
avcc_payload += u8.pack(0xfc | (params.get('nal_unit_length_field', 4) - 1)) # complete representation (1) + reserved (11111) + length size minus one
avcc_payload += u8.pack(1) # reserved (0) + number of sps (0000001)
avcc_payload += u16.pack(len(sps))
avcc_payload += sps

9
youtube_dl/extractor/abcnews.py
View File

@ -15,10 +15,13 @@ class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'''(?x)
https?://
abcnews\.go\.com/
(?:
[^/]+/video/(?P<display_id>[0-9a-z-]+)-|
video/embed\?.*?\bid=
abcnews\.go\.com/
(?:
[^/]+/video/(?P<display_id>[0-9a-z-]+)-|
video/embed\?.*?\bid=
)|
fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/
)
(?P<id>\d+)
'''

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,
}

24
youtube_dl/extractor/acast.py
View File

@ -7,6 +7,7 @@ import functools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
float_or_none,
int_or_none,
try_get,
@ -27,7 +28,7 @@ class ACastIE(InfoExtractor):
'''
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
@ -46,28 +47,37 @@ class ACastIE(InfoExtractor):
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}]
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
s = self._download_json(
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
display_id)['result']
'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
display_id)
media_url = s['url']
if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
episode_url = s.get('episodeUrl')
if episode_url:
display_id = episode_url
else:
channel, display_id = re.match(self._VALID_URL, s['link']).groups()
cast_data = self._download_json(
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
display_id)['result']
e = cast_data['episode']
title = e['name']
title = e.get('name') or s['title']
return {
'id': compat_str(e['id']),
'display_id': display_id,
'url': media_url,
'title': title,
'description': e.get('description') or e.get('summary'),
'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
'thumbnail': e.get('image'),
'timestamp': unified_timestamp(e.get('publishingDate')),
'duration': float_or_none(s.get('duration') or e.get('duration')),
'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
'duration': float_or_none(e.get('duration') or s.get('duration')),
'filesize': int_or_none(e.get('contentLength')),
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),

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
}

5
youtube_dl/extractor/adobepass.py
View File

@ -25,6 +25,11 @@ MSO_INFO = {
'username_field': 'username',
'password_field': 'password',
},
'ATT': {
'name': 'AT&T U-verse',
'username_field': 'userid',
'password_field': 'password',
},
'ATTOTT': {
'name': 'DIRECTV NOW',
'username_field': 'email',

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'),
}

330
youtube_dl/extractor/arte.py
View File

@ -4,17 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
find_xpath_attr,
get_element_by_attribute,
int_or_none,
NO_DEFAULT,
qualities,
try_get,
unified_strdate,
@ -25,59 +18,7 @@ from ..utils import (
# add tests.
class ArteTvIE(InfoExtractor):
_VALID_URL = r'https?://videos\.arte\.tv/(?P<lang>fr|de|en|es)/.*-(?P<id>.*?)\.html'
IE_NAME = 'arte.tv'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
lang = mobj.group('lang')
video_id = mobj.group('id')
ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
ref_xml_doc = self._download_xml(
ref_xml_url, video_id, note='Downloading metadata')
config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
config_xml_url = config_node.attrib['ref']
config = self._download_xml(
config_xml_url, video_id, note='Downloading configuration')
formats = [{
'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0],
'play_path': 'mp4:' + q.text.split('mp4:', 1)[1],
'ext': 'flv',
'quality': 2 if q.attrib['quality'] == 'hd' else 1,
} for q in config.findall('./urls/url')]
self._sort_formats(formats)
title = config.find('.//name').text
thumbnail = config.find('.//firstThumbnailUrl').text
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'formats': formats,
}
class ArteTVBaseIE(InfoExtractor):
@classmethod
def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang')
query = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
if 'vid' in query:
video_id = query['vid'][0]
else:
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
return video_id, lang
def _extract_from_json_url(self, json_url, video_id, lang, title=None):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
@ -108,13 +49,15 @@ class ArteTVBaseIE(InfoExtractor):
'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
}
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
LANGS = {
'fr': 'F',
'de': 'A',
'en': 'E[ANG]',
'es': 'E[ESP]',
'it': 'E[ITA]',
'pl': 'E[POL]',
}
langcode = LANGS.get(lang, lang)
@ -126,8 +69,8 @@ class ArteTVBaseIE(InfoExtractor):
l = re.escape(langcode)
# Language preference from most to least priority
# Reference: section 5.6.3 of
# http://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-05.pdf
# Reference: section 6.8 of
# https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
PREFERENCES = (
# original version in requested language, without subtitles
r'VO{0}$'.format(l),
@ -193,274 +136,59 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>\d{6}-\d{3}-[AF])'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
'only_matching': True,
}, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
'info_dict': {
'id': '088501-000-A',
'ext': 'mp4',
'title': 'Mexico: Stealing Petrol to Survive',
'upload_date': '20190628',
},
}]
@classmethod
def suitable(cls, url):
return False if ArteTVPlaylistIE.suitable(url) else super(ArteTVPlus7IE, cls).suitable(url)
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
patterns_templates = (r'arte_vp_url=["\'](.*?%s.*?)["\']', r'data-url=["\']([^"]+%s[^"]+)["\']')
ids = (video_id, '')
# some pages contain multiple videos (like
# http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D),
# so we first try to look for json URLs that contain the video id from
# the 'vid' parameter.
patterns = [t % re.escape(_id) for _id in ids for t in patterns_templates]
json_url = self._html_search_regex(
patterns, webpage, 'json vp url', default=None)
if not json_url:
def find_iframe_url(webpage, default=NO_DEFAULT):
return self._html_search_regex(
r'<iframe[^>]+src=(["\'])(?P<url>.+\bjson_url=.+?)\1',
webpage, 'iframe url', group='url', default=default)
iframe_url = find_iframe_url(webpage, None)
if not iframe_url:
embed_url = self._html_search_regex(
r'arte_vp_url_oembed=\'([^\']+?)\'', webpage, 'embed url', default=None)
if embed_url:
player = self._download_json(
embed_url, video_id, 'Downloading player page')
iframe_url = find_iframe_url(player['html'])
# en and es URLs produce react-based pages with different layout (e.g.
# http://www.arte.tv/guide/en/053330-002-A/carnival-italy?zone=world)
if not iframe_url:
program = self._search_regex(
r'program\s*:\s*({.+?["\']embed_html["\'].+?}),?\s*\n',
webpage, 'program', default=None)
if program:
embed_html = self._parse_json(program, video_id)
if embed_html:
iframe_url = find_iframe_url(embed_html['embed_html'])
if iframe_url:
json_url = compat_parse_qs(
compat_urllib_parse_urlparse(iframe_url).query)['json_url'][0]
if json_url:
title = self._search_regex(
r'<h3[^>]+title=(["\'])(?P<title>.+?)\1',
webpage, 'title', default=None, group='title')
return self._extract_from_json_url(json_url, video_id, lang, title=title)
# Different kind of embed URL (e.g.
# http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium)
entries = [
self.url_result(url)
for _, url in re.findall(r'<iframe[^>]+src=(["\'])(?P<url>.+?)\1', webpage)]
return self.playlist_result(entries)
# It also uses the arte_vp_url url from the webpage to extract the information
class ArteTVCreativeIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:creative'
_VALID_URL = r'https?://creative\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://creative.arte.tv/fr/episode/osmosis-episode-1',
'info_dict': {
'id': '057405-001-A',
'ext': 'mp4',
'title': 'OSMOSIS - N\'AYEZ PLUS PEUR D\'AIMER (1)',
'upload_date': '20150716',
},
}, {
'url': 'http://creative.arte.tv/fr/Monty-Python-Reunion',
'playlist_count': 11,
'add_ie': ['Youtube'],
}, {
'url': 'http://creative.arte.tv/de/episode/agentur-amateur-4-der-erste-kunde',
'only_matching': True,
}]
class ArteTVInfoIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:info'
_VALID_URL = r'https?://info\.arte\.tv/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://info.arte.tv/fr/service-civique-un-cache-misere',
'info_dict': {
'id': '067528-000-A',
'ext': 'mp4',
'title': 'Service civique, un cache misère ?',
'upload_date': '20160403',
},
}]
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://future.arte.tv/fr/info-sciences/les-ecrevisses-aussi-sont-anxieuses',
'info_dict': {
'id': '050940-028-A',
'ext': 'mp4',
'title': 'Les écrevisses aussi peuvent être anxieuses',
'upload_date': '20140902',
},
}, {
'url': 'http://future.arte.tv/fr/la-science-est-elle-responsable',
'only_matching': True,
}]
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:ddc'
_VALID_URL = r'https?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>[^/?#&]+)'
_TESTS = []
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)
class ArteTVConcertIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:concert'
_VALID_URL = r'https?://concert\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://concert.arte.tv/de/notwist-im-pariser-konzertclub-divan-du-monde',
'md5': '9ea035b7bd69696b67aa2ccaaa218161',
'info_dict': {
'id': '186',
'ext': 'mp4',
'title': 'The Notwist im Pariser Konzertclub "Divan du Monde"',
'upload_date': '20140128',
'description': 'md5:486eb08f991552ade77439fe6d82c305',
},
}]
class ArteTVCinemaIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:cinema'
_VALID_URL = r'https?://cinema\.arte\.tv/(?P<lang>fr|de|en|es)/(?P<id>.+)'
_TESTS = [{
'url': 'http://cinema.arte.tv/fr/article/les-ailes-du-desir-de-julia-reck',
'md5': 'a5b9dd5575a11d93daf0e3f404f45438',
'info_dict': {
'id': '062494-000-A',
'ext': 'mp4',
'title': 'Film lauréat du concours web - "Les ailes du désir" de Julia Reck',
'upload_date': '20150807',
},
}]
class ArteTVMagazineIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:magazine'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/magazine/[^/]+/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
# Embedded via <iframe src="http://www.arte.tv/arte_vp/index.php?json_url=..."
'url': 'http://www.arte.tv/magazine/trepalium/fr/entretien-avec-le-realisateur-vincent-lannoo-trepalium',
'md5': '2a9369bcccf847d1c741e51416299f25',
'info_dict': {
'id': '065965-000-A',
'ext': 'mp4',
'title': 'Trepalium - Extrait Ep.01',
'upload_date': '20160121',
},
}, {
# Embedded via <iframe src="http://www.arte.tv/guide/fr/embed/054813-004-A/medium"
'url': 'http://www.arte.tv/magazine/trepalium/fr/episode-0406-replay-trepalium',
'md5': 'fedc64fc7a946110fe311634e79782ca',
'info_dict': {
'id': '054813-004_PLUS7-F',
'ext': 'mp4',
'title': 'Trepalium (4/6)',
'description': 'md5:10057003c34d54e95350be4f9b05cb40',
'upload_date': '20160218',
},
}, {
'url': 'http://www.arte.tv/magazine/metropolis/de/frank-woeste-german-paris-metropolis',
'only_matching': True,
}]
lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(
'https://api.arte.tv/api/player/v1/config/%s/%s' % (lang, video_id),
video_id, lang)
class ArteTVEmbedIE(ArteTVPlus7IE):
IE_NAME = 'arte.tv:embed'
_VALID_URL = r'''(?x)
http://www\.arte\.tv
/(?:playerv2/embed|arte_vp/index)\.php\?json_url=
https://www\.arte\.tv
/player/v3/index\.php\?json_url=
(?P<json_url>
http://arte\.tv/papi/tvguide/videos/stream/player/
(?P<lang>[^/]+)/(?P<id>[^/]+)[^&]*
https?://api\.arte\.tv/api/player/v1/config/
(?P<lang>[^/]+)/(?P<id>\d{6}-\d{3}-[AF])
)
'''
_TESTS = []
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
lang = mobj.group('lang')
json_url = mobj.group('json_url')
json_url, lang, video_id = re.match(self._VALID_URL, url).groups()
return self._extract_from_json_url(json_url, video_id, lang)
class TheOperaPlatformIE(ArteTVPlus7IE):
IE_NAME = 'theoperaplatform'
_VALID_URL = r'https?://(?:www\.)?theoperaplatform\.eu/(?P<lang>fr|de|en|es)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.theoperaplatform.eu/de/opera/verdi-otello',
'md5': '970655901fa2e82e04c00b955e9afe7b',
'info_dict': {
'id': '060338-009-A',
'ext': 'mp4',
'title': 'Verdi - OTELLO',
'upload_date': '20160927',
},
}]
class ArteTVPlaylistIE(ArteTVBaseIE):
IE_NAME = 'arte.tv:playlist'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/[^#]*#collection/(?P<id>PL-\d+)'
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>fr|de|en|es|it|pl)/videos/(?P<id>RC-\d{6})'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/plus7/?country=DE#collection/PL-013263/ARTETV',
'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
'info_dict': {
'id': 'PL-013263',
'title': 'Areva & Uramin',
'description': 'md5:a1dc0312ce357c262259139cfd48c9bf',
'id': 'RC-016954',
'title': 'Earn a Living',
'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
},
'playlist_mincount': 6,
}, {
'url': 'http://www.arte.tv/guide/de/playlists?country=DE#collection/PL-013190/ARTETV',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id, lang = self._extract_url_info(url)
lang, playlist_id = re.match(self._VALID_URL, url).groups()
collection = self._download_json(
'https://api.arte.tv/api/player/v1/collectionData/%s/%s?source=videos'
% (lang, playlist_id), playlist_id)

80
youtube_dl/extractor/asiancrush.py
View File

@ -5,14 +5,12 @@ import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
remove_end,
)
from ..utils import extract_attributes
class AsianCrushIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?asiancrush\.com/video/(?:[^/]+/)?0+(?P<id>\d+)v\b'
_VALID_URL_BASE = r'https?://(?:www\.)?(?P<host>(?:(?:asiancrush|yuyutv|midnightpulp)\.com|cocoro\.tv))'
_VALID_URL = r'%s/video/(?:[^/]+/)?0+(?P<id>\d+)v\b' % _VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/',
'md5': 'c3b740e48d0ba002a42c0b72857beae6',
@ -20,7 +18,7 @@ class AsianCrushIE(InfoExtractor):
'id': '1_y4tmjm5r',
'ext': 'mp4',
'title': 'Women Who Flirt',
'description': 'md5:3db14e9186197857e7063522cb89a805',
'description': 'md5:7e986615808bcfb11756eb503a751487',
'timestamp': 1496936429,
'upload_date': '20170608',
'uploader_id': 'craig@crifkin.com',
@ -28,10 +26,27 @@ class AsianCrushIE(InfoExtractor):
}, {
'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/013886v/the-act-of-killing/',
'only_matching': True,
}, {
'url': 'https://www.yuyutv.com/video/peep-show/013922v-warring-factions/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/010400v/drifters/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/video/mononoke/016378v-zashikiwarashi-part-1/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/video/the-wonderful-wizard-of-oz/008878v-the-wonderful-wizard-of-oz-ep01/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
@ -51,7 +66,7 @@ class AsianCrushIE(InfoExtractor):
r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
player = self._download_webpage(
'https://api.asiancrush.com/embeddedVideoPlayer', video_id,
'https://api.%s/embeddedVideoPlayer' % host, video_id,
query={'id': entry_id})
kaltura_id = self._search_regex(
@ -63,15 +78,23 @@ class AsianCrushIE(InfoExtractor):
r'/p(?:artner_id)?/(\d+)', player, 'partner id',
default='513551')
return self.url_result(
'kaltura:%s:%s' % (partner_id, kaltura_id),
ie=KalturaIE.ie_key(), video_id=kaltura_id,
video_title=title)
description = self._html_search_regex(
r'(?s)<div[^>]+\bclass=["\']description["\'][^>]*>(.+?)</div>',
webpage, 'description', fatal=False)
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, kaltura_id),
'ie_key': KalturaIE.ie_key(),
'id': video_id,
'title': title,
'description': description,
}
class AsianCrushPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?asiancrush\.com/series/0+(?P<id>\d+)s\b'
_TEST = {
_VALID_URL = r'%s/series/0+(?P<id>\d+)s\b' % AsianCrushIE._VALID_URL_BASE
_TESTS = [{
'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/',
'info_dict': {
'id': '12481',
@ -79,7 +102,16 @@ class AsianCrushPlaylistIE(InfoExtractor):
'description': 'md5:7addd7c5132a09fd4741152d96cce886',
},
'playlist_count': 20,
}
}, {
'url': 'https://www.yuyutv.com/series/013920s/peep-show/',
'only_matching': True,
}, {
'url': 'https://www.midnightpulp.com/series/016375s/mononoke/',
'only_matching': True,
}, {
'url': 'https://www.cocoro.tv/series/008549s/the-wonderful-wizard-of-oz/',
'only_matching': True,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
@ -96,15 +128,15 @@ class AsianCrushPlaylistIE(InfoExtractor):
entries.append(self.url_result(
mobj.group('url'), ie=AsianCrushIE.ie_key()))
title = remove_end(
self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False),
' | AsianCrush')
title = self._html_search_regex(
r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
'title', default=None) or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title',
default=None) or self._search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False)
if title:
title = re.sub(r'\s*\|\s*.+?$', '', title)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(

214
youtube_dl/extractor/atresplayer.py
View File

@ -1,202 +1,118 @@
# coding: utf-8
from __future__ import unicode_literals
import time
import hmac
import hashlib
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
sanitized_Request,
urlencode_postdata,
xpath_text,
)
class AtresPlayerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/[^/]+/[^/]+/[^/]+/[^/]+/(?P<display_id>.+?)_(?P<id>[0-9a-f]{24})'
_NETRC_MACHINE = 'atresplayer'
_TESTS = [
{
'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
'md5': 'efd56753cda1bb64df52a3074f62e38a',
'url': 'https://www.atresplayer.com/antena3/series/pequenas-coincidencias/temporada-1/capitulo-7-asuntos-pendientes_5d4aa2c57ed1a88fc715a615/',
'info_dict': {
'id': 'capitulo-10-especial-solidario-nochebuena',
'id': '5d4aa2c57ed1a88fc715a615',
'ext': 'mp4',
'title': 'Especial Solidario de Nochebuena',
'description': 'md5:e2d52ff12214fa937107d21064075bf1',
'duration': 5527.6,
'thumbnail': r're:^https?://.*\.jpg$',
'title': 'Capítulo 7: Asuntos pendientes',
'description': 'md5:7634cdcb4d50d5381bedf93efb537fbc',
'duration': 3413,
},
'params': {
'format': 'bestvideo',
},
'skip': 'This video is only available for registered users'
},
{
'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
'md5': '6e52cbb513c405e403dbacb7aacf8747',
'info_dict': {
'id': 'capitulo-112-david-bustamante',
'ext': 'flv',
'title': 'David Bustamante',
'description': 'md5:f33f1c0a05be57f6708d4dd83a3b81c6',
'duration': 1439.0,
'thumbnail': r're:^https?://.*\.jpg$',
},
'url': 'https://www.atresplayer.com/lasexta/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_5ad08edf986b2855ed47adc4/',
'only_matching': True,
},
{
'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
'url': 'https://www.atresplayer.com/antena3/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_5ad51046986b2886722ccdea/',
'only_matching': True,
},
]
_USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
_MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
_TIMESTAMP_SHIFT = 30000
_TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
_URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
_PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
_EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
_LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
_ERRORS = {
'UNPUBLISHED': 'We\'re sorry, but this video is not yet available.',
'DELETED': 'This video has expired and is no longer available for online streaming.',
'GEOUNPUBLISHED': 'We\'re sorry, but this video is not available in your region due to right restrictions.',
# 'PREMIUM': 'PREMIUM',
}
_API_BASE = 'https://api.atresplayer.com/'
def _real_initialize(self):
self._login()
def _handle_error(self, e, code):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == code:
error = self._parse_json(e.cause.read(), None)
if error.get('error') == 'required_registered':
self.raise_login_required()
raise ExtractorError(error['error_description'], expected=True)
raise
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_form = {
'j_username': username,
'j_password': password,
}
self._request_webpage(
self._API_BASE + 'login', None, 'Downloading login page')
request = sanitized_Request(
self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in')
try:
target_url = self._download_json(
'https://account.atresmedia.com/api/login', None,
'Logging in', headers={
'Content-Type': 'application/x-www-form-urlencoded'
}, data=urlencode_postdata({
'username': username,
'password': password,
}))['targetUrl']
except ExtractorError as e:
self._handle_error(e, 400)
error = self._html_search_regex(
r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',
response, 'error', default=None)
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
self._request_webpage(target_url, None, 'Following Target URL')
def _real_extract(self, url):
video_id = self._match_id(url)
display_id, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, video_id)
try:
episode = self._download_json(
self._API_BASE + 'client/v1/player/episode/' + video_id, video_id)
except ExtractorError as e:
self._handle_error(e, 403)
episode_id = self._search_regex(
r'episode="([^"]+)"', webpage, 'episode id')
request = sanitized_Request(
self._PLAYER_URL_TEMPLATE % episode_id,
headers={'User-Agent': self._USER_AGENT})
player = self._download_json(request, episode_id, 'Downloading player JSON')
episode_type = player.get('typeOfEpisode')
error_message = self._ERRORS.get(episode_type)
if error_message:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
title = episode['titulo']
formats = []
video_url = player.get('urlVideo')
if video_url:
format_info = {
'url': video_url,
'format_id': 'http',
}
mobj = re.search(r'(?P<bitrate>\d+)K_(?P<width>\d+)x(?P<height>\d+)', video_url)
if mobj:
format_info.update({
'width': int_or_none(mobj.group('width')),
'height': int_or_none(mobj.group('height')),
'tbr': int_or_none(mobj.group('bitrate')),
})
formats.append(format_info)
timestamp = int_or_none(self._download_webpage(
self._TIME_API_URL,
video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
token = hmac.new(
self._MAGIC.encode('ascii'),
(episode_id + timestamp_shifted).encode('utf-8'), hashlib.md5
).hexdigest()
request = sanitized_Request(
self._URL_VIDEO_TEMPLATE.format('windows', episode_id, timestamp_shifted, token),
headers={'User-Agent': self._USER_AGENT})
fmt_json = self._download_json(
request, video_id, 'Downloading windows video JSON')
result = fmt_json.get('resultDes')
if result.lower() != 'ok':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, result), expected=True)
for format_id, video_url in fmt_json['resultObject'].items():
if format_id == 'token' or not video_url.startswith('http'):
for source in episode.get('sources', []):
src = source.get('src')
if not src:
continue
if 'geodeswowsmpra3player' in video_url:
# f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
# f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
# this videos are protected by DRM, the f4m downloader doesn't support them
continue
video_url_hd = video_url.replace('free_es', 'es')
formats.extend(self._extract_f4m_formats(
video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds',
fatal=False))
formats.extend(self._extract_mpd_formats(
video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash',
fatal=False))
src_type = source.get('type')
if src_type == 'application/vnd.apple.mpegurl':
formats.extend(self._extract_m3u8_formats(
src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif src_type == 'application/dash+xml':
formats.extend(self._extract_mpd_formats(
src, video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats)
path_data = player.get('pathData')
episode = self._download_xml(
self._EPISODE_URL_TEMPLATE % path_data, video_id,
'Downloading episode XML')
duration = float_or_none(xpath_text(
episode, './media/asset/info/technical/contentDuration', 'duration'))
art = episode.find('./media/asset/info/art')
title = xpath_text(art, './name', 'title')
description = xpath_text(art, './description', 'description')
thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
subtitles = {}
subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
if subtitle_url:
subtitles['es'] = [{
'ext': 'srt',
'url': subtitle_url,
}]
heartbeat = episode.get('heartbeat') or {}
omniture = episode.get('omniture') or {}
get_meta = lambda x: heartbeat.get(x) or omniture.get(x)
return {
'display_id': display_id,
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'description': episode.get('descripcion'),
'thumbnail': episode.get('imgPoster'),
'duration': int_or_none(episode.get('duration')),
'formats': formats,
'subtitles': subtitles,
'channel': get_meta('channel'),
'season': get_meta('season'),
'episode_number': int_or_none(get_meta('episodeNumber')),
}

34
youtube_dl/extractor/audioboom.py
View File

@ -2,22 +2,25 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import float_or_none
from ..utils import (
clean_html,
float_or_none,
)
class AudioBoomIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audioboom\.com/(?:boos|posts)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://audioboom.com/boos/4279833-3-09-2016-czaban-hour-3?t=0',
'md5': '63a8d73a055c6ed0f1e51921a10a5a76',
'url': 'https://audioboom.com/posts/7398103-asim-chaudhry',
'md5': '7b00192e593ff227e6a315486979a42d',
'info_dict': {
'id': '4279833',
'id': '7398103',
'ext': 'mp3',
'title': '3/09/2016 Czaban Hour 3',
'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans',
'duration': 2245.72,
'uploader': 'SB Nation A.M.',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
'title': 'Asim Chaudhry',
'description': 'md5:2f3fef17dacc2595b5362e1d7d3602fc',
'duration': 4000.99,
'uploader': 'Sue Perkins: An hour or so with...',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/perkins',
}
}, {
'url': 'https://audioboom.com/posts/4279833-3-09-2016-czaban-hour-3?t=0',
@ -32,8 +35,8 @@ class AudioBoomIE(InfoExtractor):
clip = None
clip_store = self._parse_json(
self._search_regex(
r'data-new-clip-store=(["\'])(?P<json>{.*?"clipId"\s*:\s*%s.*?})\1' % video_id,
self._html_search_regex(
r'data-new-clip-store=(["\'])(?P<json>{.+?})\1',
webpage, 'clip store', default='{}', group='json'),
video_id, fatal=False)
if clip_store:
@ -47,14 +50,15 @@ class AudioBoomIE(InfoExtractor):
audio_url = from_clip('clipURLPriorToLoading') or self._og_search_property(
'audio', webpage, 'audio url')
title = from_clip('title') or self._og_search_title(webpage)
description = from_clip('description') or self._og_search_description(webpage)
title = from_clip('title') or self._html_search_meta(
['og:title', 'og:audio:title', 'audio_title'], webpage)
description = from_clip('description') or clean_html(from_clip('formattedDescription')) or self._og_search_description(webpage)
duration = float_or_none(from_clip('duration') or self._html_search_meta(
'weibo:audio:duration', webpage))
uploader = from_clip('author') or self._og_search_property(
'audio:artist', webpage, 'uploader', fatal=False)
uploader = from_clip('author') or self._html_search_meta(
['og:audio:artist', 'twitter:audio:artist_name', 'audio_artist'], webpage, 'uploader')
uploader_url = from_clip('author_url') or self._html_search_meta(
'audioboo:channel', webpage, 'uploader url')

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,
}

19
youtube_dl/extractor/bbc.py
View File

@ -40,6 +40,7 @@ class BBCCoUkIE(InfoExtractor):
iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
music/(?:clips|audiovideo/popular)[/#]|
radio/player/|
sounds/play/|
events/[^/]+/play/[^/]+/
)
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
@ -70,7 +71,7 @@ class BBCCoUkIE(InfoExtractor):
'info_dict': {
'id': 'b039d07m',
'ext': 'flv',
'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
'title': 'Kaleidoscope, Leonard Cohen',
'description': 'The Canadian poet and songwriter reflects on his musical career.',
},
'params': {
@ -220,6 +221,20 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
}, {
'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
'note': 'Audio',
'info_dict': {
'id': 'm0007jz9',
'ext': 'mp4',
'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra',
'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
'duration': 9840,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
'only_matching': True,
@ -609,7 +624,7 @@ class BBCIE(BBCCoUkIE):
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
'title': 'Russia stages massive WW2 parade despite Western boycott',
'title': 'Russia stages massive WW2 parade',
'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
},
'playlist_count': 2,

5
youtube_dl/extractor/beampro.py
View File

@ -99,7 +99,7 @@ class BeamProLiveIE(BeamProBaseIE):
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\w+)'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>[^?#&]+)'
_TESTS = [{
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
@ -122,6 +122,9 @@ class BeamProVodIE(BeamProBaseIE):
}, {
'url': 'https://mixer.com/streamer?vod=IxFno1rqC0S_XJ1a2yGgNw',
'only_matching': True,
}, {
'url': 'https://mixer.com/streamer?vod=Rh3LY0VAqkGpEQUe2pN-ig',
'only_matching': True,
}]
@staticmethod

17
youtube_dl/extractor/beeg.py
View File

@ -32,6 +32,10 @@ class BeegIE(InfoExtractor):
# api/v6 v2
'url': 'https://beeg.com/1941093077?t=911-1391',
'only_matching': True,
}, {
# api/v6 v2 w/o t
'url': 'https://beeg.com/1277207756',
'only_matching': True,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
@ -49,14 +53,17 @@ class BeegIE(InfoExtractor):
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
if len(video_id) >= 10:
query = {
'v': 2,
's': t[0],
'e': t[1],
}
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query.update({
's': t[0],
'e': t[1],
})
else:
query = {'v': 1}

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):

113
youtube_dl/extractor/bilibili.py
View File

@ -15,6 +15,7 @@ from ..utils import (
float_or_none,
parse_iso8601,
smuggle_url,
str_or_none,
strip_jsonp,
unified_timestamp,
unsmuggle_url,
@ -306,3 +307,115 @@ class BiliBiliBangumiIE(InfoExtractor):
return self.playlist_result(
entries, bangumi_id,
season_info.get('bangumi_title'), season_info.get('evaluate'))
class BilibiliAudioBaseIE(InfoExtractor):
def _call_api(self, path, sid, query=None):
if not query:
query = {'sid': sid}
return self._download_json(
'https://www.bilibili.com/audio/music-service-c/web/' + path,
sid, query=query)['data']
class BilibiliAudioIE(BilibiliAudioBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/au(?P<id>\d+)'
_TEST = {
'url': 'https://www.bilibili.com/audio/au1003142',
'md5': 'fec4987014ec94ef9e666d4d158ad03b',
'info_dict': {
'id': '1003142',
'ext': 'm4a',
'title': '【tsukimi】YELLOW / 神山羊',
'artist': 'tsukimi',
'comment_count': int,
'description': 'YELLOW的mp3版！',
'duration': 183,
'subtitles': {
'origin': [{
'ext': 'lrc',
}],
},
'thumbnail': r're:^https?://.+\.jpg',
'timestamp': 1564836614,
'upload_date': '20190803',
'uploader': 'tsukimi-つきみぐー',
'view_count': int,
},
}
def _real_extract(self, url):
au_id = self._match_id(url)
play_data = self._call_api('url', au_id)
formats = [{
'url': play_data['cdns'][0],
'filesize': int_or_none(play_data.get('size')),
}]
song = self._call_api('song/info', au_id)
title = song['title']
statistic = song.get('statistic') or {}
subtitles = None
lyric = song.get('lyric')
if lyric:
subtitles = {
'origin': [{
'url': lyric,
}]
}
return {
'id': au_id,
'title': title,
'formats': formats,
'artist': song.get('author'),
'comment_count': int_or_none(statistic.get('comment')),
'description': song.get('intro'),
'duration': int_or_none(song.get('duration')),
'subtitles': subtitles,
'thumbnail': song.get('cover'),
'timestamp': int_or_none(song.get('passtime')),
'uploader': song.get('uname'),
'view_count': int_or_none(statistic.get('play')),
}
class BilibiliAudioAlbumIE(BilibiliAudioBaseIE):
_VALID_URL = r'https?://(?:www\.)?bilibili\.com/audio/am(?P<id>\d+)'
_TEST = {
'url': 'https://www.bilibili.com/audio/am10624',
'info_dict': {
'id': '10624',
'title': '每日新曲推荐（每日11:00更新）',
'description': '每天11:00更新，为你推送最新音乐',
},
'playlist_count': 19,
}
def _real_extract(self, url):
am_id = self._match_id(url)
songs = self._call_api(
'song/of-menu', am_id, {'sid': am_id, 'pn': 1, 'ps': 100})['data']
entries = []
for song in songs:
sid = str_or_none(song.get('id'))
if not sid:
continue
entries.append(self.url_result(
'https://www.bilibili.com/audio/au' + sid,
BilibiliAudioIE.ie_key(), sid))
if entries:
album_data = self._call_api('menu/info', am_id) or {}
album_title = album_data.get('title')
if album_title:
for entry in entries:
entry['album'] = album_title
return self.playlist_result(
entries, am_id, album_title, album_data.get('intro'))
return self.playlist_result(entries, am_id)

19
youtube_dl/extractor/biobiochiletv.py
View File

@ -6,7 +6,6 @@ from ..utils import (
ExtractorError,
remove_end,
)
from .rudo import RudoIE
class BioBioChileTVIE(InfoExtractor):
@ -41,11 +40,15 @@ class BioBioChileTVIE(InfoExtractor):
}, {
'url': 'http://www.biobiochile.cl/noticias/bbtv/comentarios-bio-bio/2016/07/08/edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos.shtml',
'info_dict': {
'id': 'edecanes-del-congreso-figuras-decorativas-que-le-cuestan-muy-caro-a-los-chilenos',
'id': 'b4xd0LK3SK',
'ext': 'mp4',
'uploader': '(none)',
'upload_date': '20160708',
'title': 'Edecanes del Congreso: Figuras decorativas que le cuestan muy caro a los chilenos',
# TODO: fix url_transparent information overriding
# 'uploader': 'Juan Pablo Echenique',
'title': 'Comentario Oscar Cáceres',
},
'params': {
# empty m3u8 manifest
'skip_download': True,
},
}, {
'url': 'http://tv.biobiochile.cl/notas/2015/10/22/ninos-transexuales-de-quien-es-la-decision.shtml',
@ -60,7 +63,9 @@ class BioBioChileTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
rudo_url = RudoIE._extract_url(webpage)
rudo_url = self._search_regex(
r'<iframe[^>]+src=(?P<q1>[\'"])(?P<url>(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
webpage, 'embed URL', None, group='url')
if not rudo_url:
raise ExtractorError('No videos found')
@ -68,7 +73,7 @@ class BioBioChileTVIE(InfoExtractor):
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._html_search_regex(
r'<a[^>]+href=["\']https?://(?:busca|www)\.biobiochile\.cl/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
r'<a[^>]+href=["\'](?:https?://(?:busca|www)\.biobiochile\.cl)?/(?:lista/)?(?:author|autor)[^>]+>(.+?)</a>',
webpage, 'uploader', fatal=False)
return {

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,
}

8
youtube_dl/extractor/bleacherreport.py
View File

@ -71,7 +71,7 @@ class BleacherReportIE(InfoExtractor):
video = article_data.get('video')
if video:
video_type = video['type']
if video_type == 'cms.bleacherreport.com':
if video_type in ('cms.bleacherreport.com', 'vid.bleacherreport.com'):
info['url'] = 'http://bleacherreport.com/video_embed?id=%s' % video['id']
elif video_type == 'ooyala.com':
info['url'] = 'ooyala:%s' % video['id']
@ -87,9 +87,9 @@ class BleacherReportIE(InfoExtractor):
class BleacherReportCMSIE(AMPIE):
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36}|\d{5})'
_TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms',
'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
'info_dict': {
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
@ -101,6 +101,6 @@ class BleacherReportCMSIE(AMPIE):
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._extract_feed_info('http://cms.bleacherreport.com/media/items/%s/akamai.json' % video_id)
info = self._extract_feed_info('http://vid.bleacherreport.com/videos/%s.akamai' % video_id)
info['id'] = video_id
return info

8
youtube_dl/extractor/bokecc.py
View File

@ -11,8 +11,8 @@ from ..utils import ExtractorError
class BokeCCBaseIE(InfoExtractor):
def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
player_params_str = self._html_search_regex(
r'<(?:script|embed)[^>]+src="http://p\.bokecc\.com/player\?([^"]+)',
webpage, 'player params')
r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
webpage, 'player params', group='query')
player_params = compat_parse_qs(player_params_str)
@ -36,9 +36,9 @@ class BokeCCIE(BokeCCBaseIE):
_VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
_TESTS = [{
'url': 'http://union.bokecc.com/playvideo.bo?vid=E44D40C15E65EA30&uid=CD0C5D3C8614B28B',
'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A',
'info_dict': {
'id': 'CD0C5D3C8614B28B_E44D40C15E65EA30',
'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461',
'ext': 'flv',
'title': 'BokeCC Video',
},

268
youtube_dl/extractor/brightcove.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
import base64
import json
import re
import struct
@ -11,14 +10,12 @@ from .adobepass import AdobePassIE
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
compat_urlparse,
compat_xml_parse_error,
compat_HTTPError,
)
from ..utils import (
determine_ext,
ExtractorError,
extract_attributes,
find_xpath_attr,
@ -27,18 +24,19 @@ from ..utils import (
js_to_json,
int_or_none,
parse_iso8601,
smuggle_url,
unescapeHTML,
unsmuggle_url,
update_url_query,
clean_html,
mimetype2ext,
UnsupportedError,
)
class BrightcoveLegacyIE(InfoExtractor):
IE_NAME = 'brightcove:legacy'
_VALID_URL = r'(?:https?://.*brightcove\.com/(services|viewer).*?\?|brightcove:)(?P<query>.*)'
_FEDERATED_URL = 'http://c.brightcove.com/services/viewer/htmlFederated'
_TESTS = [
{
@ -55,7 +53,8 @@ class BrightcoveLegacyIE(InfoExtractor):
'timestamp': 1368213670,
'upload_date': '20130510',
'uploader_id': '1589608506001',
}
},
'skip': 'The player has been deactivated by the content owner',
},
{
# From http://medianetwork.oracle.com/video/player/1785452137001
@ -70,6 +69,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'upload_date': '20120814',
'uploader_id': '1460825906',
},
'skip': 'video not playable',
},
{
# From http://mashable.com/2013/10/26/thermoelectric-bracelet-lets-you-control-your-body-temperature/
@ -79,7 +79,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'ext': 'mp4',
'title': 'This Bracelet Acts as a Personal Thermostat',
'description': 'md5:547b78c64f4112766ccf4e151c20b6a0',
'uploader': 'Mashable',
# 'uploader': 'Mashable',
'timestamp': 1382041798,
'upload_date': '20131017',
'uploader_id': '1130468786001',
@ -124,6 +124,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'id': '3550319591001',
},
'playlist_mincount': 7,
'skip': 'Unsupported URL',
},
{
# playlist with 'playlistTab' (https://github.com/ytdl-org/youtube-dl/issues/9965)
@ -133,6 +134,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'title': 'Lesson 08',
},
'playlist_mincount': 10,
'skip': 'Unsupported URL',
},
{
# playerID inferred from bcpid
@ -141,12 +143,6 @@ class BrightcoveLegacyIE(InfoExtractor):
'only_matching': True, # Tested in GenericIE
}
]
FLV_VCODECS = {
1: 'SORENSON',
2: 'ON2',
3: 'H264',
4: 'VP8',
}
@classmethod
def _build_brighcove_url(cls, object_str):
@ -238,7 +234,8 @@ class BrightcoveLegacyIE(InfoExtractor):
@classmethod
def _make_brightcove_url(cls, params):
return update_url_query(cls._FEDERATED_URL, params)
return update_url_query(
'http://c.brightcove.com/services/viewer/htmlFederated', params)
@classmethod
def _extract_brightcove_url(cls, webpage):
@ -297,38 +294,12 @@ class BrightcoveLegacyIE(InfoExtractor):
videoPlayer = query.get('@videoPlayer')
if videoPlayer:
# We set the original url as the default 'Referer' header
referer = smuggled_data.get('Referer', url)
referer = query.get('linkBaseURL', [None])[0] or smuggled_data.get('Referer', url)
video_id = videoPlayer[0]
if 'playerID' not in query:
mobj = re.search(r'/bcpid(\d+)', url)
if mobj is not None:
query['playerID'] = [mobj.group(1)]
return self._get_video_info(
videoPlayer[0], query, referer=referer)
elif 'playerKey' in query:
player_key = query['playerKey']
return self._get_playlist_info(player_key[0])
else:
raise ExtractorError(
'Cannot find playerKey= variable. Did you forget quotes in a shell invocation?',
expected=True)
def _brightcove_new_url_result(self, publisher_id, video_id):
brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
def _get_video_info(self, video_id, query, referer=None):
headers = {}
linkBase = query.get('linkBaseURL')
if linkBase is not None:
referer = linkBase[0]
if referer is not None:
headers['Referer'] = referer
webpage = self._download_webpage(self._FEDERATED_URL, video_id, headers=headers, query=query)
error_msg = self._html_search_regex(
r"<h1>We're sorry.</h1>([\s\n]*<p>.*?</p>)+", webpage,
'error message', default=None)
if error_msg is not None:
publisher_id = query.get('publisherId')
if publisher_id and publisher_id[0].isdigit():
publisher_id = publisher_id[0]
@ -339,6 +310,9 @@ class BrightcoveLegacyIE(InfoExtractor):
else:
player_id = query.get('playerID')
if player_id and player_id[0].isdigit():
headers = {}
if referer:
headers['Referer'] = referer
player_page = self._download_webpage(
'http://link.brightcove.com/services/player/bcpid' + player_id[0],
video_id, headers=headers, fatal=False)
@ -349,136 +323,16 @@ class BrightcoveLegacyIE(InfoExtractor):
if player_key:
enc_pub_id = player_key.split(',')[1].replace('~', '=')
publisher_id = struct.unpack('>Q', base64.urlsafe_b64decode(enc_pub_id))[0]
if publisher_id:
return self._brightcove_new_url_result(publisher_id, video_id)
raise ExtractorError(
'brightcove said: %s' % error_msg, expected=True)
self.report_extraction(video_id)
info = self._search_regex(r'var experienceJSON = ({.*});', webpage, 'json')
info = json.loads(info)['data']
video_info = info['programmedContent']['videoPlayer']['mediaDTO']
video_info['_youtubedl_adServerURL'] = info.get('adServerURL')
return self._extract_video_info(video_info)
def _get_playlist_info(self, player_key):
info_url = 'http://c.brightcove.com/services/json/experience/runtime/?command=get_programming_for_experience&playerKey=%s' % player_key
playlist_info = self._download_webpage(
info_url, player_key, 'Downloading playlist information')
json_data = json.loads(playlist_info)
if 'videoList' in json_data:
playlist_info = json_data['videoList']
playlist_dto = playlist_info['mediaCollectionDTO']
elif 'playlistTabs' in json_data:
playlist_info = json_data['playlistTabs']
playlist_dto = playlist_info['lineupListDTO']['playlistDTOs'][0]
else:
raise ExtractorError('Empty playlist')
videos = [self._extract_video_info(video_info) for video_info in playlist_dto['videoDTOs']]
return self.playlist_result(videos, playlist_id='%s' % playlist_info['id'],
playlist_title=playlist_dto['displayName'])
def _extract_video_info(self, video_info):
video_id = compat_str(video_info['id'])
publisher_id = video_info.get('publisherId')
info = {
'id': video_id,
'title': video_info['displayName'].strip(),
'description': video_info.get('shortDescription'),
'thumbnail': video_info.get('videoStillURL') or video_info.get('thumbnailURL'),
'uploader': video_info.get('publisherName'),
'uploader_id': compat_str(publisher_id) if publisher_id else None,
'duration': float_or_none(video_info.get('length'), 1000),
'timestamp': int_or_none(video_info.get('creationDate'), 1000),
}
renditions = video_info.get('renditions', []) + video_info.get('IOSRenditions', [])
if renditions:
formats = []
for rend in renditions:
url = rend['defaultURL']
if not url:
continue
ext = None
if rend['remote']:
url_comp = compat_urllib_parse_urlparse(url)
if url_comp.path.endswith('.m3u8'):
formats.extend(
self._extract_m3u8_formats(
url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
continue
elif 'akamaihd.net' in url_comp.netloc:
# This type of renditions are served through
# akamaihd.net, but they don't use f4m manifests
url = url.replace('control/', '') + '?&v=3.3.0&fp=13&r=FEEFJ&g=RTSJIMBMPFPB'
ext = 'flv'
if ext is None:
ext = determine_ext(url)
tbr = int_or_none(rend.get('encodingRate'), 1000)
a_format = {
'format_id': 'http%s' % ('-%s' % tbr if tbr else ''),
'url': url,
'ext': ext,
'filesize': int_or_none(rend.get('size')) or None,
'tbr': tbr,
}
if rend.get('audioOnly'):
a_format.update({
'vcodec': 'none',
})
else:
a_format.update({
'height': int_or_none(rend.get('frameHeight')),
'width': int_or_none(rend.get('frameWidth')),
'vcodec': rend.get('videoCodec'),
})
# m3u8 manifests with remote == false are media playlists
# Not calling _extract_m3u8_formats here to save network traffic
if ext == 'm3u8':
a_format.update({
'format_id': 'hls%s' % ('-%s' % tbr if tbr else ''),
'ext': 'mp4',
'protocol': 'm3u8_native',
})
formats.append(a_format)
self._sort_formats(formats)
info['formats'] = formats
elif video_info.get('FLVFullLengthURL') is not None:
info.update({
'url': video_info['FLVFullLengthURL'],
'vcodec': self.FLV_VCODECS.get(video_info.get('FLVFullCodec')),
'filesize': int_or_none(video_info.get('FLVFullSize')),
})
if self._downloader.params.get('include_ads', False):
adServerURL = video_info.get('_youtubedl_adServerURL')
if adServerURL:
ad_info = {
'_type': 'url',
'url': adServerURL,
}
if 'url' in info:
return {
'_type': 'playlist',
'title': info['title'],
'entries': [ad_info, info],
}
else:
return ad_info
if not info.get('url') and not info.get('formats'):
uploader_id = info.get('uploader_id')
if uploader_id:
info.update(self._brightcove_new_url_result(uploader_id, video_id))
else:
raise ExtractorError('Unable to extract video url for %s' % video_id)
return info
if publisher_id:
brightcove_new_url = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id)
if referer:
brightcove_new_url = smuggle_url(brightcove_new_url, {'referrer': referer})
return self.url_result(brightcove_new_url, BrightcoveNewIE.ie_key(), video_id)
# TODO: figure out if it's possible to extract playlistId from playerKey
# elif 'playerKey' in query:
# player_key = query['playerKey']
# return self._get_playlist_info(player_key[0])
raise UnsupportedError(url)
class BrightcoveNewIE(AdobePassIE):
@ -732,45 +586,63 @@ class BrightcoveNewIE(AdobePassIE):
account_id, player_id, embed, content_type, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
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)
policy_key = None
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)
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
policy_key = None
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
policy_key = catalog.get('policyKey')
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
if not policy_key:
policy_key = self._search_regex(
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),
})
try:
json_data = self._download_json(api_url, video_id, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 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)
raise ExtractorError(message, expected=True)
raise
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 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
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':

53
youtube_dl/extractor/byutv.py
View File

@ -3,7 +3,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_duration
from ..utils import (
determine_ext,
merge_dicts,
parse_duration,
url_or_none,
)
class BYUtvIE(InfoExtractor):
@ -51,7 +56,7 @@ class BYUtvIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
info = self._download_json(
video = self._download_json(
'https://api.byutv.org/api3/catalog/getvideosforcontent',
display_id, query={
'contentid': video_id,
@ -62,7 +67,7 @@ class BYUtvIE(InfoExtractor):
'x-byutv-platformkey': 'xsaaw9c7y5',
})
ep = info.get('ooyalaVOD')
ep = video.get('ooyalaVOD')
if ep:
return {
'_type': 'url_transparent',
@ -75,18 +80,38 @@ class BYUtvIE(InfoExtractor):
'thumbnail': ep.get('imageThumbnail'),
}
ep = info['dvr']
title = ep['title']
formats = self._extract_m3u8_formats(
ep['videoUrl'], video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
info = {}
formats = []
for format_id, ep in video.items():
if not isinstance(ep, dict):
continue
video_url = url_or_none(ep.get('videoUrl'))
if not video_url:
continue
ext = determine_ext(video_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))
else:
formats.append({
'url': video_url,
'format_id': format_id,
})
merge_dicts(info, {
'title': ep.get('title'),
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
'duration': parse_duration(ep.get('length')),
})
self._sort_formats(formats)
return {
return merge_dicts(info, {
'id': video_id,
'display_id': display_id,
'title': title,
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
'duration': parse_duration(ep.get('length')),
'title': display_id,
'formats': formats,
}
})

2
youtube_dl/extractor/ceskatelevize.py
View File

@ -147,6 +147,8 @@ class CeskaTelevizeIE(InfoExtractor):
is_live = item.get('type') == 'LIVE'
formats = []
for format_id, stream_url in item.get('streamUrls', {}).items():
if 'drmOnly=true' in stream_url:
continue
if 'playerType=flash' in stream_url:
stream_formats = self._extract_m3u8_formats(
stream_url, playlist_id, 'mp4', 'm3u8_native',

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')),

50
youtube_dl/extractor/chaturbate.py
View File

@ -3,11 +3,15 @@ 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):
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
@ -21,6 +25,9 @@ class ChaturbateIE(InfoExtractor):
'skip_download': True,
},
'skip': 'Room is offline',
}, {
'url': 'https://chaturbate.com/fullvideo/?b=caylin',
'only_matching': True,
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
@ -32,14 +39,34 @@ class ChaturbateIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, headers=self.geo_verification_headers())
'https://chaturbate.com/%s/' % video_id, video_id,
headers=self.geo_verification_headers())
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):
found_m3u8_urls.append(m.group('url'))
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', '')
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)
@ -59,7 +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

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'))),
}

44
youtube_dl/extractor/common.py
View File

@ -220,7 +220,7 @@ class InfoExtractor(object):
* "preference" (optional, int) - quality of the image
* "width" (optional, int)
* "height" (optional, int)
* "resolution" (optional, string "{width}x{height"},
* "resolution" (optional, string "{width}x{height}",
deprecated)
* "filesize" (optional, int)
thumbnail: Full URL to a video thumbnail image.
@ -1424,12 +1424,10 @@ class InfoExtractor(object):
try:
self._request_webpage(url, video_id, 'Checking %s URL' % item, headers=headers)
return True
except ExtractorError as e:
if isinstance(e.cause, compat_urllib_error.URLError):
self.to_screen(
'%s: %s URL is invalid, skipping' % (video_id, item))
return False
raise
except ExtractorError:
self.to_screen(
'%s: %s URL is invalid, skipping' % (video_id, item))
return False
def http_scheme(self):
""" Either "http:" or "https:", depending on the user's preferences """
@ -1457,14 +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 []
@ -1588,12 +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 []
@ -1767,6 +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
@ -2011,12 +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
@ -2319,12 +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
@ -2691,7 +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')),

118
youtube_dl/extractor/contv.py Normal file
View File

@ -0,0 +1,118 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
)
class CONtvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter',
'info_dict': {
'id': 'CEG10022949',
'ext': 'mp4',
'title': 'Days Of Thrills & Laughter',
'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb',
'upload_date': '20180703',
'timestamp': 1530634789.61,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites',
'info_dict': {
'id': 'CLIP-show_fotld_bts',
'title': 'Fight of the Living Dead: Behind the Scenes Bites',
},
'playlist_mincount': 7,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
details = self._download_json(
'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id,
video_id, query={'device': 'web'})
if details.get('type') == 'episodic':
seasons = self._download_json(
'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id,
video_id)
entries = []
for season in seasons:
for episode in season.get('episodes', []):
episode_id = episode.get('id')
if not episode_id:
continue
entries.append(self.url_result(
'https://www.contv.com/details-movie/' + episode_id,
CONtvIE.ie_key(), episode_id))
return self.playlist_result(entries, video_id, details.get('title'))
m_details = details['details']
title = details['title']
formats = []
media_hls_url = m_details.get('media_hls_url')
if media_hls_url:
formats.extend(self._extract_m3u8_formats(
media_hls_url, video_id, 'mp4',
m3u8_id='hls', fatal=False))
media_mp4_url = m_details.get('media_mp4_url')
if media_mp4_url:
formats.append({
'format_id': 'http',
'url': media_mp4_url,
})
self._sort_formats(formats)
subtitles = {}
captions = m_details.get('captions') or {}
for caption_url in captions.values():
subtitles.setdefault('en', []).append({
'url': caption_url
})
thumbnails = []
for image in m_details.get('images', []):
image_url = image.get('url')
if not image_url:
continue
thumbnails.append({
'url': image_url,
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
})
description = None
for p in ('large_', 'medium_', 'small_', ''):
d = m_details.get(p + 'description')
if d:
description = d
break
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnails': thumbnails,
'description': description,
'timestamp': float_or_none(details.get('metax_added_on'), 1000),
'subtitles': subtitles,
'duration': float_or_none(m_details.get('duration'), 1000),
'view_count': int_or_none(details.get('num_watched')),
'like_count': int_or_none(details.get('num_fav')),
'categories': details.get('category'),
'tags': details.get('tags'),
'season_number': int_or_none(details.get('season')),
'episode_number': int_or_none(details.get('episode')),
'release_year': int_or_none(details.get('pub_year')),
}

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'),
}

10
youtube_dl/extractor/ctsnews.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_timestamp
from .youtube import YoutubeIE
class CtsNewsIE(InfoExtractor):
@ -14,8 +15,8 @@ class CtsNewsIE(InfoExtractor):
'info_dict': {
'id': '201501291578109',
'ext': 'mp4',
'title': '以色列.真主黨交火 3人死亡',
'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...',
'title': '以色列.真主黨交火 3人死亡 - 華視新聞網',
'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人員也不幸罹難。大陸陝西、河南、安徽、江蘇和湖北五個省份出現大暴雪，嚴重影響陸空交通，不過九華山卻出現...',
'timestamp': 1422528540,
'upload_date': '20150129',
}
@ -26,7 +27,7 @@ class CtsNewsIE(InfoExtractor):
'info_dict': {
'id': '201309031304098',
'ext': 'mp4',
'title': '韓國31歲童顏男 貌如十多歲小孩',
'title': '韓國31歲童顏男 貌如十多歲小孩 - 華視新聞網',
'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1378205880,
@ -62,8 +63,7 @@ class CtsNewsIE(InfoExtractor):
video_url = mp4_feed['source_url']
else:
self.to_screen('Not CTSPlayer video, trying Youtube...')
youtube_url = self._search_regex(
r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url')
youtube_url = YoutubeIE._extract_url(page)
return self.url_result(youtube_url, ie='Youtube')

584
youtube_dl/extractor/dailymotion.py
View File

@ -1,64 +1,105 @@
# 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):
_VALID_URL = r'(?i)https?://(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|#)/)?video|swf)/(?P<id>[^/?_]+)'
_VALID_URL = r'''(?ix)
https?://
(?:
(?:(?:www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|\#)/)?video|swf)|
(?:www\.)?lequipe\.fr/video
)
/(?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',
@ -67,7 +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',
@ -133,274 +173,171 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}, {
'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun',
'only_matching': True,
}, {
'url': 'https://www.lequipe.fr/video/x791mem',
'only_matching': True,
}, {
'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):
urls = []
# Look for embedded Dailymotion player
matches = re.findall(
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage)
return list(map(lambda m: unescapeHTML(m[1]), matches))
# https://developer.dailymotion.com/player#player-parameters
for mobj in re.finditer(
r'<(?:(?:embed|iframe)[^>]+?src=|input[^>]+id=[\'"]dmcloudUrlEmissionSelect[\'"][^>]+value=)(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.com/(?:embed|swf)/video/.+?)\1', webpage):
urls.append(unescapeHTML(mobj.group('url')))
for mobj in re.finditer(
r'(?s)DM\.player\([^,]+,\s*{.*?video[\'"]?\s*:\s*["\']?(?P<id>[0-9a-zA-Z]+).+?}\s*\);', webpage):
urls.append('https://www.dailymotion.com/embed/video/' + mobj.group('id'))
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())
metadata = self._download_json(
'http://www.dailymotion.com/player/metadata/video/p' + i + t + n, video_id)
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']
password = self._downloader.params.get('videopassword')
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']
def _check_error(self, info):
error = info.get('error')
metadata = self._download_json(
'https://www.dailymotion.com/player/metadata/video/' + xid,
xid, 'Downloading metadata JSON',
query={'app': 'com.dailymotion.neon'})
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(
@ -408,86 +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):

51
youtube_dl/extractor/dbtv.py
View File

@ -7,50 +7,51 @@ from .common import InfoExtractor
class DBTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dbtv\.no/(?:[^/]+/)?(?P<id>[0-9]+)(?:#(?P<display_id>.+))?'
_VALID_URL = r'https?://(?:www\.)?dagbladet\.no/video/(?:(?:embed|(?P<display_id>[^/]+))/)?(?P<id>[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8})'
_TESTS = [{
'url': 'http://dbtv.no/3649835190001#Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
'md5': '2e24f67936517b143a234b4cadf792ec',
'url': 'https://www.dagbladet.no/video/PynxJnNWChE/',
'md5': 'b8f850ba1860adbda668d367f9b77699',
'info_dict': {
'id': '3649835190001',
'display_id': 'Skulle_teste_ut_fornøyelsespark,_men_kollegaen_var_bare_opptatt_av_bikinikroppen',
'id': 'PynxJnNWChE',
'ext': 'mp4',
'title': 'Skulle teste ut fornøyelsespark, men kollegaen var bare opptatt av bikinikroppen',
'description': 'md5:1504a54606c4dde3e4e61fc97aa857e0',
'description': 'md5:49cc8370e7d66e8a2ef15c3b4631fd3f',
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1404039863,
'upload_date': '20140629',
'duration': 69.544,
'uploader_id': '1027729757001',
'upload_date': '20160916',
'duration': 69,
'uploader_id': 'UCk5pvsyZJoYJBd7_oFPTlRQ',
'uploader': 'Dagbladet',
},
'add_ie': ['BrightcoveNew']
'add_ie': ['Youtube']
}, {
'url': 'http://dbtv.no/3649835190001',
'url': 'https://www.dagbladet.no/video/embed/xlGmyIeN9Jo/?autoplay=false',
'only_matching': True,
}, {
'url': 'http://www.dbtv.no/lazyplayer/4631135248001',
'only_matching': True,
}, {
'url': 'http://dbtv.no/vice/5000634109001',
'only_matching': True,
}, {
'url': 'http://dbtv.no/filmtrailer/3359293614001',
'url': 'https://www.dagbladet.no/video/truer-iran-bor-passe-dere/PalfB2Cw',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1',
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dagbladet\.no/video/embed/(?:[0-9A-Za-z_-]{11}|[a-zA-Z0-9]{8}).*?)\1',
webpage)]
def _real_extract(self, url):
video_id, display_id = re.match(self._VALID_URL, url).groups()
return {
display_id, video_id = re.match(self._VALID_URL, url).groups()
info = {
'_type': 'url_transparent',
'url': 'http://players.brightcove.net/1027729757001/default_default/index.html?videoId=%s' % video_id,
'id': video_id,
'display_id': display_id,
'ie_key': 'BrightcoveNew',
}
if len(video_id) == 11:
info.update({
'url': video_id,
'ie_key': 'Youtube',
})
else:
info.update({
'url': 'jwplatform:' + video_id,
'ie_key': 'JWPlatform',
})
return info

71
youtube_dl/extractor/discovery.py
View File

@ -5,23 +5,17 @@ import re
import string
from .discoverygo import DiscoveryGoBaseIE
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
ExtractorError,
try_get,
)
from ..compat import compat_urllib_parse_unquote
from ..utils import ExtractorError
from ..compat import compat_HTTPError
class DiscoveryIE(DiscoveryGoBaseIE):
_VALID_URL = r'''(?x)https?://
(?P<site>
(?:(?:www|go)\.)?discovery|
(?:www\.)?
(?:
discovery|
investigationdiscovery|
discoverylife|
animalplanet|
@ -40,15 +34,15 @@ class DiscoveryIE(DiscoveryGoBaseIE):
cookingchanneltv|
motortrend
)
)\.com(?P<path>/tv-shows/[^/]+/(?:video|full-episode)s/(?P<id>[^./?#]+))'''
)\.com/tv-shows/(?P<show_slug>[^/]+)/(?:video|full-episode)s/(?P<id>[^./?#]+)'''
_TESTS = [{
'url': 'https://www.discovery.com/tv-shows/cash-cab/videos/dave-foley',
'url': 'https://go.discovery.com/tv-shows/cash-cab/videos/riding-with-matthew-perry',
'info_dict': {
'id': '5a2d9b4d6b66d17a5026e1fd',
'id': '5a2f35ce6b66d17a5026e29e',
'ext': 'mp4',
'title': 'Dave Foley',
'description': 'md5:4b39bcafccf9167ca42810eb5f28b01f',
'duration': 608,
'title': 'Riding with Matthew Perry',
'description': 'md5:a34333153e79bc4526019a5129e7f878',
'duration': 84,
},
'params': {
'skip_download': True, # requires ffmpeg
@ -56,20 +50,20 @@ class DiscoveryIE(DiscoveryGoBaseIE):
}, {
'url': 'https://www.investigationdiscovery.com/tv-shows/final-vision/full-episodes/final-vision',
'only_matching': True,
}, {
'url': 'https://go.discovery.com/tv-shows/alaskan-bush-people/videos/follow-your-own-road',
'only_matching': True,
}, {
# using `show_slug` is important to get the correct video data
'url': 'https://www.sciencechannel.com/tv-shows/mythbusters-on-science/full-episodes/christmas-special',
'only_matching': True,
}]
_GEO_COUNTRIES = ['US']
_GEO_BYPASS = False
_API_BASE_URL = 'https://api.discovery.com/v1/'
def _real_extract(self, url):
site, path, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
react_data = self._parse_json(self._search_regex(
r'window\.__reactTransmitPacket\s*=\s*({.+?});',
webpage, 'react data'), display_id)
content_blocks = react_data['layout'][path]['contentBlocks']
video = next(cb for cb in content_blocks if cb.get('type') == 'video')['content']['items'][0]
video_id = video['id']
site, show_slug, display_id = re.match(self._VALID_URL, url).groups()
access_token = None
cookies = self._get_cookies(url)
@ -79,27 +73,36 @@ class DiscoveryIE(DiscoveryGoBaseIE):
if auth_storage_cookie and auth_storage_cookie.value:
auth_storage = self._parse_json(compat_urllib_parse_unquote(
compat_urllib_parse_unquote(auth_storage_cookie.value)),
video_id, fatal=False) or {}
display_id, fatal=False) or {}
access_token = auth_storage.get('a') or auth_storage.get('access_token')
if not access_token:
access_token = self._download_json(
'https://%s.com/anonymous' % site, display_id, query={
'https://%s.com/anonymous' % site, display_id,
'Downloading token JSON metadata', query={
'authRel': 'authorization',
'client_id': try_get(
react_data, lambda x: x['application']['apiClientId'],
compat_str) or '3020a40c2356a645b4b4',
'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,
})['access_token']
try:
headers = self.geo_verification_headers()
headers['Authorization'] = 'Bearer ' + access_token
headers = self.geo_verification_headers()
headers['Authorization'] = 'Bearer ' + access_token
try:
video = self._download_json(
self._API_BASE_URL + 'content/videos',
display_id, 'Downloading content JSON metadata',
headers=headers, query={
'embed': 'show.name',
'fields': 'authenticated,description.detailed,duration,episodeNumber,id,name,parental.rating,season.number,show,tags',
'slug': display_id,
'show_slug': show_slug,
})[0]
video_id = video['id']
stream = self._download_json(
'https://api.discovery.com/v1/streaming/video/' + video_id,
display_id, headers=headers)
self._API_BASE_URL + 'streaming/video/' + video_id,
display_id, 'Downloading streaming JSON metadata', headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (401, 403):
e_description = self._parse_json(

63
youtube_dl/extractor/discoverynetworks.py
View File

@ -3,63 +3,38 @@ from __future__ import unicode_literals
import re
from .brightcove import BrightcoveLegacyIE
from .dplay import DPlayIE
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
from ..utils import smuggle_url
class DiscoveryNetworksDeIE(DPlayIE):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?P<site>discovery|tlc|animalplanet|dmax)\.de/
(?:
.*\#(?P<id>\d+)|
(?:[^/]+/)*videos/(?P<display_id>[^/?#]+)|
programme/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)
)'''
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:tlc|dmax)\.de|dplay\.co\.uk)/(?:programme|show)/(?P<programme>[^/]+)/video/(?P<alternate_id>[^/]+)'
_TESTS = [{
'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
'url': 'https://www.tlc.de/programme/breaking-amish/video/die-welt-da-drauen/DCB331270001100',
'info_dict': {
'id': '3235167922001',
'id': '78867',
'ext': 'mp4',
'title': 'Breaking Amish: Die Welt da draußen',
'description': (
'Vier Amische und eine Mennonitin wagen in New York'
' den Sprung in ein komplett anderes Leben. Begleitet sie auf'
' ihrem spannenden Weg.'),
'timestamp': 1396598084,
'upload_date': '20140404',
'uploader_id': '1659832546',
'title': 'Die Welt da draußen',
'description': 'md5:61033c12b73286e409d99a41742ef608',
'timestamp': 1554069600,
'upload_date': '20190331',
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
}, {
'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/',
'url': 'https://www.dmax.de/programme/dmax-highlights/video/tuning-star-sidney-hoffmann-exklusiv-bei-dmax/191023082312316',
'only_matching': True,
}, {
'url': 'http://www.discovery.de/#5332316765001',
'url': 'https://www.dplay.co.uk/show/ghost-adventures/video/hotel-leger-103620/EHD_280313B',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
alternate_id = mobj.group('alternate_id')
if alternate_id:
self._initialize_geo_bypass({
'countries': ['DE'],
})
return self._get_disco_api_info(
url, '%s/%s' % (mobj.group('programme'), alternate_id),
'sonic-eu1-prod.disco-api.com', mobj.group('site') + 'de')
brightcove_id = mobj.group('id')
if not brightcove_id:
title = mobj.group('title')
webpage = self._download_webpage(url, title)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
brightcove_legacy_url).query)['@videoPlayer'][0]
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}),
'BrightcoveNew', brightcove_id)
domain, programme, alternate_id = re.match(self._VALID_URL, url).groups()
country = 'GB' if domain == 'dplay.co.uk' else 'DE'
realm = 'questuk' if country == 'GB' else domain.replace('.', '')
return self._get_disco_api_info(
url, '%s/%s' % (programme, alternate_id),
'sonic-eu1-prod.disco-api.com', realm, country)

97
youtube_dl/extractor/dlive.py Normal file
View File

@ -0,0 +1,97 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import int_or_none
class DLiveVODIE(InfoExtractor):
IE_NAME = 'dlive:vod'
_VALID_URL = r'https?://(?:www\.)?dlive\.tv/p/(?P<uploader_id>.+?)\+(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://dlive.tv/p/pdp+3mTzOl4WR',
'info_dict': {
'id': '3mTzOl4WR',
'ext': 'mp4',
'title': 'Minecraft with james charles epic',
'upload_date': '20190701',
'timestamp': 1562011015,
'uploader_id': 'pdp',
}
}, {
'url': 'https://dlive.tv/p/pdpreplay+D-RD-xSZg',
'only_matching': True,
}]
def _real_extract(self, url):
uploader_id, vod_id = re.match(self._VALID_URL, url).groups()
broadcast = self._download_json(
'https://graphigo.prd.dlive.tv/', vod_id,
data=json.dumps({'query': '''query {
pastBroadcast(permlink:"%s+%s") {
content
createdAt
length
playbackUrl
title
thumbnailUrl
viewCount
}
}''' % (uploader_id, vod_id)}).encode())['data']['pastBroadcast']
title = broadcast['title']
formats = self._extract_m3u8_formats(
broadcast['playbackUrl'], vod_id, 'mp4', 'm3u8_native')
self._sort_formats(formats)
return {
'id': vod_id,
'title': title,
'uploader_id': uploader_id,
'formats': formats,
'description': broadcast.get('content'),
'thumbnail': broadcast.get('thumbnailUrl'),
'timestamp': int_or_none(broadcast.get('createdAt'), 1000),
'view_count': int_or_none(broadcast.get('viewCount')),
}
class DLiveStreamIE(InfoExtractor):
IE_NAME = 'dlive:stream'
_VALID_URL = r'https?://(?:www\.)?dlive\.tv/(?!p/)(?P<id>[\w.-]+)'
def _real_extract(self, url):
display_name = self._match_id(url)
user = self._download_json(
'https://graphigo.prd.dlive.tv/', display_name,
data=json.dumps({'query': '''query {
userByDisplayName(displayname:"%s") {
livestream {
content
createdAt
title
thumbnailUrl
watchingCount
}
username
}
}''' % display_name}).encode())['data']['userByDisplayName']
livestream = user['livestream']
title = livestream['title']
username = user['username']
formats = self._extract_m3u8_formats(
'https://live.prd.dlive.tv/hls/live/%s.m3u8' % username,
display_name, 'mp4')
self._sort_formats(formats)
return {
'id': display_name,
'title': self._live_title(title),
'uploader': display_name,
'uploader_id': username,
'formats': formats,
'description': livestream.get('content'),
'thumbnail': livestream.get('thumbnailUrl'),
'is_live': True,
'timestamp': int_or_none(livestream.get('createdAt'), 1000),
'view_count': int_or_none(livestream.get('watchingCount')),
}

403
youtube_dl/extractor/dplay.py
View File

@ -1,74 +1,68 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
import time
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
int_or_none,
remove_end,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
urljoin,
USER_AGENTS,
)
class DPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?P<domain>www\.(?P<host>dplay\.(?P<country>dk|se|no)))/(?:video(?:er|s)/)?(?P<id>[^/]+/[^/?#]+)'
_VALID_URL = r'''(?x)https?://
(?P<domain>
(?:www\.)?(?P<host>dplay\.(?P<country>dk|fi|jp|se|no))|
(?P<subdomain_country>es|it)\.dplay\.com
)/[^/]+/(?P<id>[^/]+/[^/?#]+)'''
_TESTS = [{
# non geo restricted, via secure api, unsigned download hls URL
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
'url': 'https://www.dplay.se/videos/nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
'info_dict': {
'id': '3172',
'display_id': 'nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet',
'id': '13628',
'display_id': 'nugammalt-77-handelser-som-format-sverige/nugammalt-77-handelser-som-format-sverige-101',
'ext': 'mp4',
'title': 'Svensken lär sig njuta av livet',
'description': 'md5:d3819c9bccffd0fe458ca42451dd50d8',
'duration': 2650,
'timestamp': 1365454320,
'duration': 2649.856,
'timestamp': 1365453720,
'upload_date': '20130408',
'creator': 'Kanal 5 (Home)',
'creator': 'Kanal 5',
'series': 'Nugammalt - 77 händelser som format Sverige',
'season_number': 1,
'episode_number': 1,
'age_limit': 0,
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
}, {
# geo restricted, via secure api, unsigned download hls URL
'url': 'http://www.dplay.dk/mig-og-min-mor/season-6-episode-12/',
'url': 'http://www.dplay.dk/videoer/ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
'info_dict': {
'id': '70816',
'display_id': 'mig-og-min-mor/season-6-episode-12',
'id': '104465',
'display_id': 'ted-bundy-mind-of-a-monster/ted-bundy-mind-of-a-monster',
'ext': 'mp4',
'title': 'Episode 12',
'description': 'md5:9c86e51a93f8a4401fc9641ef9894c90',
'duration': 2563,
'timestamp': 1429696800,
'upload_date': '20150422',
'creator': 'Kanal 4 (Home)',
'series': 'Mig og min mor',
'season_number': 6,
'episode_number': 12,
'age_limit': 0,
'title': 'Ted Bundy: Mind Of A Monster',
'description': 'md5:8b780f6f18de4dae631668b8a9637995',
'duration': 5290.027,
'timestamp': 1570694400,
'upload_date': '20191010',
'creator': 'ID - Investigation Discovery',
'series': 'Ted Bundy: Mind Of A Monster',
'season_number': 1,
'episode_number': 1,
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
}, {
# geo restricted, via direct unsigned hls URL
'url': 'http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/',
'only_matching': True,
}, {
# disco-api
'url': 'https://www.dplay.no/videoer/i-kongens-klr/sesong-1-episode-7',
@ -89,19 +83,59 @@ class DPlayIE(InfoExtractor):
'format': 'bestvideo',
'skip_download': True,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.dplay.dk/videoer/singleliv/season-5-episode-3',
'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
'md5': '2b808ffb00fc47b884a172ca5d13053c',
'info_dict': {
'id': '6918',
'display_id': 'biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij',
'ext': 'mp4',
'title': 'Luigi Di Maio: la psicosi di Stanislawskij',
'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
'thumbnail': r're:^https?://.*\.jpe?g',
'upload_date': '20160524',
'timestamp': 1464076800,
'series': 'Biografie imbarazzanti',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
},
}, {
'url': 'https://es.dplay.com/dmax/la-fiebre-del-oro/temporada-8-episodio-1/',
'info_dict': {
'id': '21652',
'display_id': 'la-fiebre-del-oro/temporada-8-episodio-1',
'ext': 'mp4',
'title': 'Episodio 1',
'description': 'md5:b9dcff2071086e003737485210675f69',
'thumbnail': r're:^https?://.*\.png',
'upload_date': '20180709',
'timestamp': 1531173540,
'series': 'La fiebre del oro',
'season_number': 8,
'episode': 'Episode 1',
'episode_number': 1,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dplay.fi/videot/shifting-gears-with-aaron-kaufman/episode-16',
'only_matching': True,
}, {
'url': 'https://www.dplay.se/videos/sofias-anglar/sofias-anglar-1001',
'url': 'https://www.dplay.jp/video/gold-rush/24086',
'only_matching': True,
}]
def _get_disco_api_info(self, url, display_id, disco_host, realm):
disco_base = 'https://' + disco_host
def _get_disco_api_info(self, url, display_id, disco_host, realm, country):
geo_countries = [country.upper()]
self._initialize_geo_bypass({
'countries': geo_countries,
})
disco_base = 'https://%s/' % disco_host
token = self._download_json(
'%s/token' % disco_base, display_id, 'Downloading token',
disco_base + 'token', display_id, 'Downloading token',
query={
'realm': realm,
})['data']['attributes']['token']
@ -110,17 +144,35 @@ class DPlayIE(InfoExtractor):
'Authorization': 'Bearer ' + token,
}
video = self._download_json(
'%s/content/videos/%s' % (disco_base, display_id), display_id,
disco_base + 'content/videos/' + display_id, display_id,
headers=headers, query={
'include': 'show'
'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']
info = video['data']['attributes']
title = info['name']
title = info['name'].strip()
formats = []
for format_id, format_dict in self._download_json(
'%s/playback/videoPlaybackInfo/%s' % (disco_base, video_id),
display_id, headers=headers)['data']['attributes']['streaming'].items():
try:
streaming = self._download_json(
disco_base + 'playback/videoPlaybackInfo/' + video_id,
display_id, headers=headers)['data']['attributes']['streaming']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
error_code = error.get('code')
if error_code == 'access.denied.geoblocked':
self.raise_geo_restricted(countries=geo_countries)
elif error_code == 'access.denied.missingpackage':
self.raise_login_required()
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
for format_id, format_dict in streaming.items():
if not isinstance(format_dict, dict):
continue
format_url = format_dict.get('url')
@ -142,235 +194,54 @@ class DPlayIE(InfoExtractor):
})
self._sort_formats(formats)
series = None
try:
included = video.get('included')
if isinstance(included, list):
show = next(e for e in included if e.get('type') == 'show')
series = try_get(
show, lambda x: x['attributes']['name'], compat_str)
except StopIteration:
pass
creator = series = None
tags = []
thumbnails = []
included = video.get('included') or []
if isinstance(included, list):
for e in included:
attributes = e.get('attributes')
if not attributes:
continue
e_type = e.get('type')
if e_type == 'channel':
creator = attributes.get('name')
elif e_type == 'image':
src = attributes.get('src')
if src:
thumbnails.append({
'url': src,
'width': int_or_none(attributes.get('width')),
'height': int_or_none(attributes.get('height')),
})
if e_type == 'show':
series = attributes.get('name')
elif e_type == 'tag':
name = attributes.get('name')
if name:
tags.append(name)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': info.get('description'),
'duration': float_or_none(
info.get('videoDuration'), scale=1000),
'duration': float_or_none(info.get('videoDuration'), 1000),
'timestamp': unified_timestamp(info.get('publishStart')),
'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,
'formats': formats,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id')
domain = mobj.group('domain')
self._initialize_geo_bypass({
'countries': [mobj.group('country').upper()],
})
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-video-id=["\'](\d+)', webpage, 'video id', default=None)
if not video_id:
host = mobj.group('host')
return self._get_disco_api_info(
url, display_id, 'disco-api.' + host, host.replace('.', ''))
info = self._download_json(
'http://%s/api/v2/ajax/videos?video_id=%s' % (domain, video_id),
video_id)['data'][0]
title = info['title']
PROTOCOLS = ('hls', 'hds')
formats = []
def extract_formats(protocol, manifest_url):
if protocol == 'hls':
m3u8_formats = self._extract_m3u8_formats(
manifest_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id=protocol, fatal=False)
# Sometimes final URLs inside m3u8 are unsigned, let's fix this
# ourselves. Also fragments' URLs are only served signed for
# Safari user agent.
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(manifest_url).query)
for m3u8_format in m3u8_formats:
m3u8_format.update({
'url': update_url_query(m3u8_format['url'], query),
'http_headers': {
'User-Agent': USER_AGENTS['Safari'],
},
})
formats.extend(m3u8_formats)
elif protocol == 'hds':
formats.extend(self._extract_f4m_formats(
manifest_url + '&hdcore=3.8.0&plugin=flowplayer-3.8.0.0',
video_id, f4m_id=protocol, fatal=False))
domain_tld = domain.split('.')[-1]
if domain_tld in ('se', 'dk', 'no'):
for protocol in PROTOCOLS:
# Providing dsc-geo allows to bypass geo restriction in some cases
self._set_cookie(
'secure.dplay.%s' % domain_tld, 'dsc-geo',
json.dumps({
'countryCode': domain_tld.upper(),
'expiry': (time.time() + 20 * 60) * 1000,
}))
stream = self._download_json(
'https://secure.dplay.%s/secure/api/v2/user/authorization/stream/%s?stream_type=%s'
% (domain_tld, video_id, protocol), video_id,
'Downloading %s stream JSON' % protocol, fatal=False)
if stream and stream.get(protocol):
extract_formats(protocol, stream[protocol])
# The last resort is to try direct unsigned hls/hds URLs from info dictionary.
# Sometimes this does work even when secure API with dsc-geo has failed (e.g.
# http://www.dplay.no/pga-tour/season-1-hoydepunkter-18-21-februar/).
if not formats:
for protocol in PROTOCOLS:
if info.get(protocol):
extract_formats(protocol, info[protocol])
self._sort_formats(formats)
subtitles = {}
for lang in ('se', 'sv', 'da', 'nl', 'no'):
for format_id in ('web_vtt', 'vtt', 'srt'):
subtitle_url = info.get('subtitles_%s_%s' % (lang, format_id))
if subtitle_url:
subtitles.setdefault(lang, []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': info.get('video_metadata_longDescription'),
'duration': int_or_none(info.get('video_metadata_length'), scale=1000),
'timestamp': int_or_none(info.get('video_publish_date')),
'creator': info.get('video_metadata_homeChannel'),
'series': info.get('video_metadata_show'),
'season_number': int_or_none(info.get('season')),
'episode_number': int_or_none(info.get('episode')),
'age_limit': int_or_none(info.get('minimum_age')),
'formats': formats,
'subtitles': subtitles,
}
class DPlayItIE(InfoExtractor):
_VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['IT']
_TEST = {
'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
'md5': '2b808ffb00fc47b884a172ca5d13053c',
'info_dict': {
'id': '6918',
'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
'ext': 'mp4',
'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
'thumbnail': r're:^https?://.*\.jpe?g',
'upload_date': '20160524',
'series': 'Biografie imbarazzanti',
'season_number': 1,
'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
'episode_number': 1,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = remove_end(self._og_search_title(webpage), ' | Dplay')
video_id = None
info = self._search_regex(
r'playback_json\s*:\s*JSON\.parse\s*\(\s*("(?:\\.|[^"\\])+?")',
webpage, 'playback JSON', default=None)
if info:
for _ in range(2):
info = self._parse_json(info, display_id, fatal=False)
if not info:
break
else:
video_id = try_get(info, lambda x: x['data']['id'])
if not info:
info_url = self._search_regex(
(r'playback_json_url\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1',
r'url\s*[:=]\s*["\'](?P<url>(?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)'),
webpage, 'info url', group='url')
info_url = urljoin(url, info_url)
video_id = info_url.rpartition('/')[-1]
try:
info = self._download_json(
info_url, display_id, headers={
'Authorization': 'Bearer %s' % self._get_cookies(url).get(
'dplayit_token').value,
'Referer': url,
})
if isinstance(info, compat_str):
info = self._parse_json(info, display_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
if error.get('code') == 'access.denied.geoblocked':
self.raise_geo_restricted(
msg=error.get('detail'), countries=self._GEO_COUNTRIES)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
hls_url = info['data']['attributes']['streaming']['hls']['url']
formats = self._extract_m3u8_formats(
hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
self._sort_formats(formats)
series = self._html_search_regex(
r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',
webpage, 'series', fatal=False)
episode = self._search_regex(
r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
webpage, 'episode', fatal=False)
mobj = re.search(
r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
webpage)
if mobj:
season_number = int(mobj.group('season_number'))
episode_number = int(mobj.group('episode_number'))
upload_date = unified_strdate(mobj.group('upload_date'))
else:
season_number = episode_number = upload_date = None
return {
'id': compat_str(video_id or display_id),
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'upload_date': upload_date,
'formats': formats,
}
domain = mobj.group('domain').lstrip('www.')
country = mobj.group('country') or mobj.group('subdomain_country')
host = 'disco-api.' + domain if domain.startswith('dplay.') else 'eu2-prod.disco-api.com'
return self._get_disco_api_info(
url, display_id, host, 'dplay' + country, country)

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)$', '',

83
youtube_dl/extractor/dumpert.py
View File

@ -1,20 +1,17 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import (
int_or_none,
qualities,
sanitized_Request,
)
class DumpertIE(InfoExtractor):
_VALID_URL = r'(?P<protocol>https?)://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
_VALID_URL = r'(?P<protocol>https?)://(?:(?:www|legacy)\.)?dumpert\.nl/(?:mediabase|embed|item)/(?P<id>[0-9]+[/_][0-9a-zA-Z]+)'
_TESTS = [{
'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
'url': 'https://www.dumpert.nl/item/6646981_951bc60f',
'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
'info_dict': {
'id': '6646981/951bc60f',
@ -24,46 +21,60 @@ class DumpertIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/',
'url': 'https://www.dumpert.nl/embed/6675421_dc440fe7',
'only_matching': True,
}, {
'url': 'http://legacy.dumpert.nl/mediabase/6646981/951bc60f',
'only_matching': True,
}, {
'url': 'http://legacy.dumpert.nl/embed/6675421/dc440fe7',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
protocol = mobj.group('protocol')
url = '%s://www.dumpert.nl/mediabase/%s' % (protocol, video_id)
req = sanitized_Request(url)
req.add_header('Cookie', 'nsfw=1; cpc=10')
webpage = self._download_webpage(req, video_id)
files_base64 = self._search_regex(
r'data-files="([^"]+)"', webpage, 'data files')
files = self._parse_json(
compat_b64decode(files_base64).decode('utf-8'),
video_id)
video_id = self._match_id(url).replace('_', '/')
item = self._download_json(
'http://api-live.dumpert.nl/mobile_api/json/info/' + video_id.replace('/', '_'),
video_id)['items'][0]
title = item['title']
media = next(m for m in item['media'] if m.get('mediatype') == 'VIDEO')
quality = qualities(['flv', 'mobile', 'tablet', '720p'])
formats = [{
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
} for format_id, video_url in files.items() if format_id != 'still']
formats = []
for variant in media.get('variants', []):
uri = variant.get('uri')
if not uri:
continue
version = variant.get('version')
formats.append({
'url': uri,
'format_id': version,
'quality': quality(version),
})
self._sort_formats(formats)
title = self._html_search_meta(
'title', webpage) or self._og_search_title(webpage)
description = self._html_search_meta(
'description', webpage) or self._og_search_description(webpage)
thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
thumbnails = []
stills = item.get('stills') or {}
for t in ('thumb', 'still'):
for s in ('', '-medium', '-large'):
still_id = t + s
still_url = stills.get(still_id)
if not still_url:
continue
thumbnails.append({
'id': still_id,
'url': still_url,
})
stats = item.get('stats') or {}
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats
'description': item.get('description'),
'thumbnails': thumbnails,
'formats': formats,
'duration': int_or_none(media.get('duration')),
'like_count': int_or_none(stats.get('kudos_total')),
'view_count': int_or_none(stats.get('views_total')),
}

15
youtube_dl/extractor/einthusan.py
View File

@ -2,6 +2,7 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import (
@ -18,7 +19,7 @@ from ..utils import (
class EinthusanIE(InfoExtractor):
_VALID_URL = r'https?://einthusan\.tv/movie/watch/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?P<host>einthusan\.(?:tv|com|ca))/movie/watch/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://einthusan.tv/movie/watch/9097/',
'md5': 'ff0f7f2065031b8a2cf13a933731c035',
@ -32,6 +33,12 @@ class EinthusanIE(InfoExtractor):
}, {
'url': 'https://einthusan.tv/movie/watch/51MZ/?lang=hindi',
'only_matching': True,
}, {
'url': 'https://einthusan.com/movie/watch/9097/',
'only_matching': True,
}, {
'url': 'https://einthusan.ca/movie/watch/4E9n/?lang=hindi',
'only_matching': True,
}]
# reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js
@ -41,7 +48,9 @@ class EinthusanIE(InfoExtractor):
)).decode('utf-8'), video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
@ -53,7 +62,7 @@ class EinthusanIE(InfoExtractor):
page_id = self._html_search_regex(
'<html[^>]+data-pageid="([^"]+)"', webpage, 'page ID')
video_data = self._download_json(
'https://einthusan.tv/ajax/movie/watch/%s/' % video_id, video_id,
'https://%s/ajax/movie/watch/%s/' % (host, video_id), video_id,
data=urlencode_postdata({
'xEvent': 'UIVideoPlayer.PingOutcome',
'xJson': json.dumps({

16
youtube_dl/extractor/espn.py
View File

@ -216,17 +216,14 @@ class FiveThirtyEightIE(InfoExtractor):
_TEST = {
'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/',
'info_dict': {
'id': '21846851',
'ext': 'mp4',
'id': '56032156',
'ext': 'flv',
'title': 'FiveThirtyEight: The Raiders can still make the playoffs',
'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.',
'timestamp': 1513960621,
'upload_date': '20171222',
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}
def _real_extract(self, url):
@ -234,9 +231,8 @@ class FiveThirtyEightIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_id = self._search_regex(
r'data-video-id=["\'](?P<id>\d+)',
webpage, 'video id', group='id')
embed_url = self._search_regex(
r'<iframe[^>]+src=["\'](https?://fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/\d+)',
webpage, 'embed url')
return self.url_result(
'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key())
return self.url_result(embed_url, 'AbcNewsVideo')

104
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,
@ -58,17 +58,8 @@ from .ard import (
ARDMediathekIE,
)
from .arte import (
ArteTvIE,
ArteTVPlus7IE,
ArteTVCreativeIE,
ArteTVConcertIE,
ArteTVInfoIE,
ArteTVFutureIE,
ArteTVCinemaIE,
ArteTVDDCIE,
ArteTVMagazineIE,
ArteTVEmbedIE,
TheOperaPlatformIE,
ArteTVPlaylistIE,
)
from .asiancrush import (
@ -89,7 +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,
@ -113,6 +103,8 @@ from .bild import BildIE
from .bilibili import (
BiliBiliIE,
BiliBiliBangumiIE,
BilibiliAudioIE,
BilibiliAudioAlbumIE,
)
from .biobiochiletv import BioBioChileTVIE
from .bitchute import (
@ -231,13 +223,13 @@ from .comedycentral import (
ComedyCentralTVIE,
ToshIE,
)
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import (
MmsIE,
RtmpIE,
)
from .condenast import CondeNastIE
from .contv import CONtvIE
from .corus import CorusIE
from .cracked import CrackedIE
from .crackle import CrackleIE
@ -261,10 +253,6 @@ from .dailymotion import (
DailymotionPlaylistIE,
DailymotionUserIE,
)
from .daisuki import (
DaisukiMottoIE,
DaisukiMottoPlaylistIE,
)
from .daum import (
DaumIE,
DaumClipIE,
@ -283,10 +271,7 @@ from .douyutv import (
DouyuShowIE,
DouyuTVIE,
)
from .dplay import (
DPlayIE,
DPlayItIE,
)
from .dplay import DPlayIE
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
@ -365,7 +350,6 @@ 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
@ -376,7 +360,10 @@ 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,
@ -404,19 +391,11 @@ from .frontendmasters import (
FrontendMastersCourseIE
)
from .funimation import FunimationIE
from .funk import (
FunkMixIE,
FunkChannelIE,
)
from .funnyordie import FunnyOrDieIE
from .funk import FunkIE
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
@ -432,7 +411,6 @@ from .globo import (
GloboArticleIE,
)
from .go import GoIE
from .go90 import Go90IE
from .godtube import GodTubeIE
from .golem import GolemIE
from .googledrive import GoogleDriveIE
@ -441,7 +419,6 @@ 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
@ -473,7 +450,6 @@ from .hungama import (
HungamaSongIE,
)
from .hypem import HypemIE
from .iconosquare import IconosquareIE
from .ign import (
IGNIE,
OneUPIE,
@ -532,10 +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
@ -559,7 +534,6 @@ from .lcp import (
LcpPlayIE,
LcpIE,
)
from .learnr import LearnrIE
from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioIE,
@ -592,6 +566,7 @@ from .linkedin import (
)
from .linuxacademy import LinuxAcademyIE
from .litv import LiTVIE
from .livejournal import LiveJournalIE
from .liveleak import (
LiveLeakIE,
LiveLeakEmbedIE,
@ -610,13 +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,
@ -650,17 +623,15 @@ from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyIE,
MicrosoftVirtualAcademyCourseIE,
)
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE
from .minoto import MinotoIE
from .miomio import MioMioIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mit import TechTVMITIE, OCWMITIE
from .mitele import MiTeleIE
from .mixcloud import (
MixcloudIE,
MixcloudUserIE,
MixcloudPlaylistIE,
MixcloudStreamIE,
)
from .mlb import MLBIE
from .mnet import MnetIE
@ -682,10 +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
@ -825,10 +795,6 @@ from .ooyala import (
OoyalaIE,
OoyalaExternalIE,
)
from .openload import (
OpenloadIE,
VerystreamIE,
)
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
@ -903,7 +869,6 @@ from .puhutv import (
PuhuTVSerieIE,
)
from .presstv import PressTVIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE
from .pyvideo import PyvideoIE
@ -955,10 +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
@ -980,7 +941,6 @@ from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
from .rtvnh import RTVNHIE
from .rtvs import RTVSIE
from .rudo import RudoIE
from .ruhd import RUHDIE
from .rutube import (
RutubeIE,
@ -1003,11 +963,17 @@ 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
from .servingsys import ServingSysIE
from .servus import ServusIE
from .sevenplus import SevenPlusIE
from .sexu import SexuIE
@ -1048,6 +1014,7 @@ from .snotr import SnotrIE
from .sohu import SohuIE
from .sonyliv import SonyLIVIE
from .soundcloud import (
SoundcloudEmbedIE,
SoundcloudIE,
SoundcloudSetIE,
SoundcloudUserIE,
@ -1091,7 +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
@ -1140,12 +1106,14 @@ from .telegraaf import TelegraafIE
from .telemb import TeleMBIE
from .telequebec import (
TeleQuebecIE,
TeleQuebecSquatIE,
TeleQuebecEmissionIE,
TeleQuebecLiveIE,
)
from .teletask import TeleTaskIE
from .telewebion import TelewebionIE
from .tennistv import TennisTVIE
from .tenplay import TenPlayIE
from .testurl import TestURLIE
from .tf1 import TF1IE
from .tfo import TFOIE
@ -1198,10 +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
@ -1259,15 +1231,23 @@ 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 (
DLiveVODIE,
DLiveStreamIE,
)
from .umg import UMGDeIE
from .unistra import UnistraIE
from .unity import UnityIE
@ -1289,7 +1269,6 @@ from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veehd import VeeHDIE
from .veoh import VeohIE
from .vessel import VesselIE
from .vesti import VestiIE
from .vevo import (
VevoIE,
@ -1316,7 +1295,6 @@ from .videomore import (
VideomoreVideoIE,
VideomoreSeasonIE,
)
from .videopremium import VideoPremiumIE
from .videopress import VideoPressIE
from .vidio import VidioIE
from .vidlii import VidLiiIE
@ -1331,7 +1309,6 @@ from .viewlift import (
ViewLiftIE,
ViewLiftEmbedIE,
)
from .viewster import ViewsterIE
from .viidea import ViideaIE
from .vimeo import (
VimeoIE,
@ -1420,7 +1397,6 @@ from .weibo import (
WeiboMobileIE
)
from .weiqitv import WeiqiTVIE
from .wimp import WimpIE
from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE
from .wsj import (
@ -1434,6 +1410,7 @@ from .xfileshare import XFileShareIE
from .xhamster import (
XHamsterIE,
XHamsterEmbedIE,
XHamsterUserIE,
)
from .xiami import (
XiamiSongIE,
@ -1457,6 +1434,7 @@ from .yahoo import (
YahooSearchIE,
YahooGyaOPlayerIE,
YahooGyaOIE,
YahooJapanNewsIE,
)
from .yandexdisk import YandexDiskIE
from .yandexmusic import (

14
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)
@ -379,6 +379,7 @@ class FacebookIE(InfoExtractor):
if not video_data:
raise ExtractorError('Cannot parse data')
subtitles = {}
formats = []
for f in video_data:
format_id = f['stream_type']
@ -402,9 +403,17 @@ class FacebookIE(InfoExtractor):
if dash_manifest:
formats.extend(self._parse_mpd_formats(
compat_etree_fromstring(compat_urllib_parse_unquote_plus(dash_manifest))))
subtitles_src = f[0].get('subtitles_src')
if subtitles_src:
subtitles.setdefault('en', []).append({'url': subtitles_src})
if not formats:
raise ExtractorError('Cannot find video formats')
# Downloads with browser's User-Agent are rate limited. Working around
# with non-browser User-Agent.
for f in formats:
f.setdefault('http_headers', {})['User-Agent'] = 'facebookexternalhit/1.1'
self._sort_formats(formats)
video_title = self._html_search_regex(
@ -428,7 +437,7 @@ class FacebookIE(InfoExtractor):
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))
thumbnail = self._og_search_thumbnail(webpage)
thumbnail = self._html_search_meta(['og:image', 'twitter:image'], webpage)
view_count = parse_count(self._search_regex(
r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
@ -442,6 +451,7 @@ class FacebookIE(InfoExtractor):
'timestamp': timestamp,
'thumbnail': thumbnail,
'view_count': view_count,
'subtitles': subtitles,
}
return webpage, info_dict

6
youtube_dl/extractor/fivetv.py
View File

@ -9,7 +9,7 @@ from ..utils import int_or_none
class FiveTVIE(InfoExtractor):
_VALID_URL = r'''(?x)
http://
https?://
(?:www\.)?5-tv\.ru/
(?:
(?:[^/]+/)+(?P<id>\d+)|
@ -39,6 +39,7 @@ class FiveTVIE(InfoExtractor):
'duration': 180,
},
}, {
# redirect to https://www.5-tv.ru/projects/1000095/izvestia-glavnoe/
'url': 'http://www.5-tv.ru/glavnoe/#itemDetails',
'info_dict': {
'id': 'glavnoe',
@ -46,6 +47,7 @@ class FiveTVIE(InfoExtractor):
'title': r're:^Итоги недели с \d+ по \d+ \w+ \d{4} года$',
'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'redirect to «Известия. Главное» project page',
}, {
'url': 'http://www.5-tv.ru/glavnoe/broadcasts/508645/',
'only_matching': True,
@ -70,7 +72,7 @@ class FiveTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
[r'<div[^>]+?class="flowplayer[^>]+?data-href="([^"]+)"',
[r'<div[^>]+?class="(?:flow)?player[^>]+?data-href="([^"]+)"',
r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"'],
webpage, 'video url')

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')

171
youtube_dl/extractor/funk.py
View File

@ -1,89 +1,21 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import re
from .common import InfoExtractor
from .nexx import NexxIE
from ..compat import compat_str
from ..utils import (
int_or_none,
try_get,
str_or_none,
)
class FunkBaseIE(InfoExtractor):
_HEADERS = {
'Accept': '*/*',
'Accept-Language': 'en-US,en;q=0.9,ru;q=0.8',
'authorization': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4',
}
_AUTH = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnROYW1lIjoid2ViYXBwLXYzMSIsInNjb3BlIjoic3RhdGljLWNvbnRlbnQtYXBpLGN1cmF0aW9uLWFwaSxuZXh4LWNvbnRlbnQtYXBpLXYzMSx3ZWJhcHAtYXBpIn0.mbuG9wS9Yf5q6PqgR4fiaRFIagiHk9JhwoKES7ksVX4'
@staticmethod
def _make_headers(referer):
headers = FunkBaseIE._HEADERS.copy()
headers['Referer'] = referer
return headers
def _make_url_result(self, video):
return {
'_type': 'url_transparent',
'url': 'nexx:741:%s' % video['sourceId'],
'ie_key': NexxIE.ie_key(),
'id': video['sourceId'],
'title': video.get('title'),
'description': video.get('description'),
'duration': int_or_none(video.get('duration')),
'season_number': int_or_none(video.get('seasonNr')),
'episode_number': int_or_none(video.get('episodeNr')),
}
class FunkMixIE(FunkBaseIE):
_VALID_URL = r'https?://(?:www\.)?funk\.net/mix/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
class FunkIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funk\.net/(?:channel|playlist)/[^/]+/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.funk.net/mix/59d65d935f8b160001828b5b/die-realste-kifferdoku-aller-zeiten',
'md5': '8edf617c2f2b7c9847dfda313f199009',
'info_dict': {
'id': '123748',
'ext': 'mp4',
'title': '"Die realste Kifferdoku aller Zeiten"',
'description': 'md5:c97160f5bafa8d47ec8e2e461012aa9d',
'timestamp': 1490274721,
'upload_date': '20170323',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
mix_id = mobj.group('id')
alias = mobj.group('alias')
lists = self._download_json(
'https://www.funk.net/api/v3.1/curation/curatedLists/',
mix_id, headers=self._make_headers(url), query={
'size': 100,
})['_embedded']['curatedListList']
metas = next(
l for l in lists
if mix_id in (l.get('entityId'), l.get('alias')))['videoMetas']
video = next(
meta['videoDataDelegate']
for meta in metas
if try_get(
meta, lambda x: x['videoDataDelegate']['alias'],
compat_str) == alias)
return self._make_url_result(video)
class FunkChannelIE(FunkBaseIE):
_VALID_URL = r'https?://(?:www\.)?funk\.net/channel/(?P<id>[^/]+)/(?P<alias>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.funk.net/channel/ba/die-lustigsten-instrumente-aus-dem-internet-teil-2',
'url': 'https://www.funk.net/channel/ba-793/die-lustigsten-instrumente-aus-dem-internet-teil-2-1155821',
'md5': '8dd9d9ab59b4aa4173b3197f2ea48e81',
'info_dict': {
'id': '1155821',
'ext': 'mp4',
@ -92,83 +24,26 @@ class FunkChannelIE(FunkBaseIE):
'timestamp': 1514507395,
'upload_date': '20171229',
},
'params': {
'skip_download': True,
},
}, {
# only available via byIdList API
'url': 'https://www.funk.net/channel/informr/martin-sonneborn-erklaert-die-eu',
'info_dict': {
'id': '205067',
'ext': 'mp4',
'title': 'Martin Sonneborn erklärt die EU',
'description': 'md5:050f74626e4ed87edf4626d2024210c0',
'timestamp': 1494424042,
'upload_date': '20170510',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.funk.net/channel/59d5149841dca100012511e3/mein-erster-job-lovemilla-folge-1/lovemilla/',
'url': 'https://www.funk.net/playlist/neuesteVideos/kameras-auf-dem-fusion-festival-1618699',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
channel_id = mobj.group('id')
alias = mobj.group('alias')
headers = self._make_headers(url)
video = None
# Id-based channels are currently broken on their side: webplayer
# tries to process them via byChannelAlias endpoint and fails
# predictably.
for page_num in itertools.count():
by_channel_alias = self._download_json(
'https://www.funk.net/api/v3.1/webapp/videos/byChannelAlias/%s'
% channel_id,
'Downloading byChannelAlias JSON page %d' % (page_num + 1),
headers=headers, query={
'filterFsk': 'false',
'sort': 'creationDate,desc',
'size': 100,
'page': page_num,
}, fatal=False)
if not by_channel_alias:
break
video_list = try_get(
by_channel_alias, lambda x: x['_embedded']['videoList'], list)
if not video_list:
break
try:
video = next(r for r in video_list if r.get('alias') == alias)
break
except StopIteration:
pass
if not try_get(
by_channel_alias, lambda x: x['_links']['next']):
break
if not video:
by_id_list = self._download_json(
'https://www.funk.net/api/v3.0/content/videos/byIdList',
channel_id, 'Downloading byIdList JSON', headers=headers,
query={
'ids': alias,
}, fatal=False)
if by_id_list:
video = try_get(by_id_list, lambda x: x['result'][0], dict)
if not video:
results = self._download_json(
'https://www.funk.net/api/v3.0/content/videos/filter',
channel_id, 'Downloading filter JSON', headers=headers, query={
'channelId': channel_id,
'size': 100,
})['result']
video = next(r for r in results if r.get('alias') == alias)
return self._make_url_result(video)
display_id, nexx_id = re.match(self._VALID_URL, url).groups()
video = self._download_json(
'https://www.funk.net/api/v4.0/videos/' + nexx_id, nexx_id)
return {
'_type': 'url_transparent',
'url': 'nexx:741:' + nexx_id,
'ie_key': NexxIE.ie_key(),
'id': nexx_id,
'title': video.get('title'),
'description': video.get('description'),
'duration': int_or_none(video.get('duration')),
'channel_id': str_or_none(video.get('channelId')),
'display_id': display_id,
'tags': video.get('tags'),
'thumbnail': video.get('imageUrlLandscape'),
}

162
youtube_dl/extractor/funnyordie.py
View File

@ -1,162 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
unified_timestamp,
)
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])'
_TESTS = [{
'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9',
'info_dict': {
'id': '0732f586d7',
'ext': 'mp4',
'title': 'Heart-Shaped Box: Literal Video Version',
'description': 'md5:ea09a01bc9a1c46d9ab696c01747c338',
'thumbnail': r're:^http:.*\.jpg$',
'uploader': 'DASjr',
'timestamp': 1317904928,
'upload_date': '20111006',
'duration': 318.3,
},
}, {
'url': 'http://www.funnyordie.com/embed/e402820827',
'info_dict': {
'id': 'e402820827',
'ext': 'mp4',
'title': 'Please Use This Song (Jon Lajoie)',
'description': 'Please use this to sell something. www.jonlajoie.com',
'thumbnail': r're:^http:.*\.jpg$',
'timestamp': 1398988800,
'upload_date': '20140502',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage)
if not links:
raise ExtractorError('No media links available for %s' % video_id)
links.sort(key=lambda link: 1 if link[1] == 'mp4' else 0)
m3u8_url = self._search_regex(
r'<source[^>]+src=(["\'])(?P<url>.+?/master\.m3u8[^"\']*)\1',
webpage, 'm3u8 url', group='url')
formats = []
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
source_formats = list(filter(
lambda f: f.get('vcodec') != 'none', m3u8_formats))
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
bitrates.sort()
if source_formats:
self._sort_formats(source_formats)
for bitrate, f in zip(bitrates, source_formats or [{}] * len(bitrates)):
for path, ext in links:
ff = f.copy()
if ff:
if ext != 'mp4':
ff = dict(
[(k, v) for k, v in ff.items()
if k in ('height', 'width', 'format_id')])
ff.update({
'format_id': ff['format_id'].replace('hls', ext),
'ext': ext,
'protocol': 'http',
})
else:
ff.update({
'format_id': '%s-%d' % (ext, bitrate),
'vbr': bitrate,
})
ff['url'] = self._proto_relative_url(
'%s%d.%s' % (path, bitrate, ext))
formats.append(ff)
self._check_formats(formats, video_id)
formats.extend(m3u8_formats)
self._sort_formats(
formats, field_preference=('height', 'width', 'tbr', 'format_id'))
subtitles = {}
for src, src_lang in re.findall(r'<track kind="captions" src="([^"]+)" srclang="([^"]+)"', webpage):
subtitles[src_lang] = [{
'ext': src.split('/')[-1],
'url': 'http://www.funnyordie.com%s' % src,
}]
timestamp = unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp', default=None))
uploader = self._html_search_regex(
r'<h\d[^>]+\bclass=["\']channel-preview-name[^>]+>(.+?)</h',
webpage, 'uploader', default=None)
title, description, thumbnail, duration = [None] * 4
medium = self._parse_json(
self._search_regex(
r'jsonMedium\s*=\s*({.+?});', webpage, 'JSON medium',
default='{}'),
video_id, fatal=False)
if medium:
title = medium.get('title')
duration = float_or_none(medium.get('duration'))
if not timestamp:
timestamp = unified_timestamp(medium.get('publishDate'))
post = self._parse_json(
self._search_regex(
r'fb_post\s*=\s*(\{.*?\});', webpage, 'post details',
default='{}'),
video_id, fatal=False)
if post:
if not title:
title = post.get('name')
description = post.get('description')
thumbnail = post.get('picture')
if not title:
title = self._og_search_title(webpage)
if not description:
description = self._og_search_description(webpage)
if not duration:
duration = int_or_none(self._html_search_meta(
('video:duration', 'duration'), webpage, 'duration', default=False))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}

34
youtube_dl/extractor/gameinformer.py
View File

@ -1,12 +1,19 @@
# coding: utf-8
from __future__ import unicode_literals
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import (
clean_html,
get_element_by_class,
get_element_by_id,
)
class GameInformerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>.+)\.aspx'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?gameinformer\.com/(?:[^/]+/)*(?P<id>[^.?&#]+)'
_TESTS = [{
# normal Brightcove embed code extracted with BrightcoveNewIE._extract_url
'url': 'http://www.gameinformer.com/b/features/archive/2015/09/26/replay-animal-crossing.aspx',
'md5': '292f26da1ab4beb4c9099f1304d2b071',
'info_dict': {
@ -18,16 +25,25 @@ class GameInformerIE(InfoExtractor):
'upload_date': '20150928',
'uploader_id': '694940074001',
},
}
}, {
# Brightcove id inside unique element with field--name-field-brightcove-video-id class
'url': 'https://www.gameinformer.com/video-feature/new-gameplay-today/2019/07/09/new-gameplay-today-streets-of-rogue',
'info_dict': {
'id': '6057111913001',
'ext': 'mp4',
'title': 'New Gameplay Today – Streets Of Rogue',
'timestamp': 1562699001,
'upload_date': '20190709',
'uploader_id': '694940074001',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/694940074001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(
url, display_id, headers=self.geo_verification_headers())
brightcove_id = self._search_regex(
[r'<[^>]+\bid=["\']bc_(\d+)', r"getVideo\('[^']+video_id=(\d+)"],
webpage, 'brightcove id')
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew',
brightcove_id)
brightcove_id = clean_html(get_element_by_class('field--name-field-brightcove-video-id', webpage) or get_element_by_id('video-source-content', webpage))
brightcove_url = self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id if brightcove_id else BrightcoveNewIE._extract_url(self, webpage)
return self.url_result(brightcove_url, 'BrightcoveNew', brightcove_id)

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,
}

101
youtube_dl/extractor/generic.py
View File

@ -77,11 +77,10 @@ from .instagram import InstagramIE
from .liveleak import LiveLeakIE
from .threeqsdn import ThreeQSDNIE
from .theplatform import ThePlatformIE
from .vessel import VesselIE
from .kaltura import KalturaIE
from .eagleplatform import EaglePlatformIE
from .facebook import FacebookIE
from .soundcloud import SoundcloudIE
from .soundcloud import SoundcloudEmbedIE
from .tunein import TuneInBaseIE
from .vbox7 import Vbox7IE
from .dbtv import DBTVIE
@ -89,10 +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 +114,8 @@ from .foxnews import FoxNewsIE
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
@ -2075,6 +2074,22 @@ class GenericIE(InfoExtractor):
},
'playlist_count': 6,
},
{
# Squarespace video embed, 2019-08-28
'url': 'http://ootboxford.com',
'info_dict': {
'id': 'Tc7b_JGdZfw',
'title': 'Out of the Blue, at Childish Things 10',
'ext': 'mp4',
'description': 'md5:a83d0026666cf5ee970f8bd1cfd69c7f',
'uploader_id': 'helendouglashouse',
'uploader': 'Helen & Douglas House',
'upload_date': '20140328',
},
'params': {
'skip_download': True,
},
},
{
# Zype embed
'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites',
@ -2104,6 +2119,23 @@ class GenericIE(InfoExtractor):
},
'expected_warnings': ['Failed to download MPD manifest'],
},
{
# DailyMotion embed with DM.player
'url': 'https://www.beinsports.com/us/copa-del-rey/video/the-locker-room-valencia-beat-barca-in-copa/1203804',
'info_dict': {
'id': 'k6aKkGHd9FJs4mtJN39',
'ext': 'mp4',
'title': 'The Locker Room: Valencia Beat Barca In Copa del Rey Final',
'description': 'This video is private.',
'uploader_id': 'x1jf30l',
'uploader': 'beIN SPORTS USA',
'upload_date': '20190528',
'timestamp': 1559062971,
},
'params': {
'skip_download': True,
},
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -2209,7 +2241,7 @@ class GenericIE(InfoExtractor):
default_search = 'fixup_error'
if default_search in ('auto', 'auto_warning', 'fixup_error'):
if '/' in url:
if re.match(r'^[^\s/]+\.[^\s/]+/', url):
self._downloader.report_warning('The url doesn\'t specify the protocol, trying with http')
return self.url_result('http://' + url)
elif default_search != 'fixup_error':
@ -2378,6 +2410,12 @@ class GenericIE(InfoExtractor):
# Unescaping the whole page allows to handle those cases in a generic way
webpage = compat_urllib_parse_unquote(webpage)
# Unescape squarespace embeds to be detected by generic extractor,
# see https://github.com/ytdl-org/youtube-dl/issues/21294
webpage = re.sub(
r'<div[^>]+class=[^>]*?\bsqs-video-wrapper\b[^>]*>',
lambda x: unescapeHTML(x.group(0)), webpage)
# it's tempting to parse this further, but you would
# have to take into account all the variations like
# Video Title - Site Name
@ -2452,11 +2490,6 @@ class GenericIE(InfoExtractor):
if tp_urls:
return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
# Look for Vessel embeds
vessel_urls = VesselIE._extract_urls(webpage)
if vessel_urls:
return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
# Look for embedded rtl.nl player
matches = re.findall(
r'<iframe[^>]+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"',
@ -2594,9 +2627,9 @@ class GenericIE(InfoExtractor):
return self.url_result(mobj.group('url'), 'VK')
# Look for embedded Odnoklassniki player
mobj = re.search(r'<iframe[^>]+?src=(["\'])(?P<url>https?://(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'), 'Odnoklassniki')
odnoklassniki_url = OdnoklassnikiIE._extract_url(webpage)
if odnoklassniki_url:
return self.url_result(odnoklassniki_url, OdnoklassnikiIE.ie_key())
# Look for embedded ivi player
mobj = re.search(r'<embed[^>]+?src=(["\'])(?P<url>https?://(?:www\.)?ivi\.ru/video/player.+?)\1', webpage)
@ -2715,9 +2748,9 @@ class GenericIE(InfoExtractor):
return self.url_result(myvi_url)
# Look for embedded soundcloud player
soundcloud_urls = SoundcloudIE._extract_urls(webpage)
soundcloud_urls = SoundcloudEmbedIE._extract_urls(webpage)
if soundcloud_urls:
return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML)
# Look for tunein player
tunein_urls = TuneInBaseIE._extract_urls(webpage)
@ -2860,6 +2893,12 @@ 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:
@ -2929,10 +2968,14 @@ class GenericIE(InfoExtractor):
# Look for Mangomolo embeds
mobj = re.search(
r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?admin\.mangomolo\.com/analytics/index\.php/customers/embed/
r'''(?x)<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//
(?:
admin\.mangomolo\.com/analytics/index\.php/customers/embed|
player\.mangomolo\.com/v1
)/
(?:
video\?.*?\bid=(?P<video_id>\d+)|
index\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
(?:index|live)\?.*?\bchannelid=(?P<channel_id>(?:[A-Za-z0-9+/=]|%2B|%2F|%3D)+)
).+?)\1''', webpage)
if mobj is not None:
info = {
@ -3001,18 +3044,6 @@ 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:

11
youtube_dl/extractor/gfycat.py
View File

@ -11,7 +11,7 @@ from ..utils import (
class GfycatIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?:ifr/|gifs/detail/)?(?P<id>[^-/?#]+)'
_VALID_URL = r'https?://(?:(?:www|giant|thumbs)\.)?gfycat\.com/(?:ru/|ifr/|gifs/detail/)?(?P<id>[^-/?#\.]+)'
_TESTS = [{
'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
'info_dict': {
@ -44,12 +44,21 @@ class GfycatIE(InfoExtractor):
'categories': list,
'age_limit': 0,
}
}, {
'url': 'https://gfycat.com/ru/RemarkableDrearyAmurstarfish',
'only_matching': True
}, {
'url': 'https://gfycat.com/gifs/detail/UnconsciousLankyIvorygull',
'only_matching': True
}, {
'url': 'https://gfycat.com/acceptablehappygoluckyharborporpoise-baseball',
'only_matching': True
}, {
'url': 'https://thumbs.gfycat.com/acceptablehappygoluckyharborporpoise-size_restricted.gif',
'only_matching': True
}, {
'url': 'https://giant.gfycat.com/acceptablehappygoluckyharborporpoise.mp4',
'only_matching': True
}]
def _real_extract(self, url):

40
youtube_dl/extractor/globo.py
View File

@ -96,21 +96,31 @@ class GloboIE(InfoExtractor):
video = self._download_json(
'http://api.globovideos.com/videos/%s/playlist' % video_id,
video_id)['videos'][0]
if video.get('encrypted') is True:
raise ExtractorError('This video is DRM protected.', expected=True)
title = video['title']
formats = []
subtitles = {}
for resource in video['resources']:
resource_id = resource.get('_id')
resource_url = resource.get('url')
if not resource_id or not resource_url:
resource_type = resource.get('type')
if not resource_url or (resource_type == 'media' and not resource_id) or resource_type not in ('subtitle', 'media'):
continue
if resource_type == 'subtitle':
subtitles.setdefault(resource.get('language') or 'por', []).append({
'url': resource_url,
})
continue
security = self._download_json(
'http://security.video.globo.com/videos/%s/hash' % video_id,
video_id, 'Downloading security hash for %s' % resource_id, query={
'player': 'flash',
'version': '17.0.0.132',
'player': 'desktop',
'version': '5.19.1',
'resource_id': resource_id,
})
@ -123,18 +133,23 @@ class GloboIE(InfoExtractor):
continue
hash_code = security_hash[:2]
received_time = security_hash[2:12]
received_random = security_hash[12:22]
received_md5 = security_hash[22:]
sign_time = compat_str(int(received_time) + 86400)
padding = '%010d' % random.randint(1, 10000000000)
if hash_code in ('04', '14'):
received_time = security_hash[3:13]
received_md5 = security_hash[24:]
hash_prefix = security_hash[:23]
elif hash_code in ('02', '12', '03', '13'):
received_time = security_hash[2:12]
received_md5 = security_hash[22:]
padding += '1'
hash_prefix = '05' + security_hash[:22]
md5_data = (received_md5 + sign_time + padding + '0xFF01DD').encode()
padded_sign_time = compat_str(int(received_time) + 86400) + padding
md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode()
signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=')
signed_hash = hash_code + received_time + received_random + sign_time + padding + signed_md5
signed_hash = hash_prefix + padded_sign_time + signed_md5
signed_url = '%s?h=%s&k=html5&a=%s&u=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A', security.get('user') or '')
signed_url = '%s?h=%s&k=%s' % (resource_url, signed_hash, 'flash')
if resource_id.endswith('m3u8') or resource_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(
signed_url, resource_id, 'mp4', entry_protocol='m3u8_native',
@ -164,7 +179,8 @@ class GloboIE(InfoExtractor):
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats
'formats': formats,
'subtitles': subtitles,
}

61
youtube_dl/extractor/go.py
View File

@ -34,10 +34,23 @@ class GoIE(AdobePassIE):
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
},
'disneynow': {
'brand': '011',
'resource_id': 'Disney',
}
}
_VALID_URL = r'https?://(?:(?:(?P<sub_domain>%s)\.)?go|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': {
@ -50,6 +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': {
@ -57,6 +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,
@ -83,16 +125,21 @@ class GoIE(AdobePassIE):
display_id)['video']
def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
mobj = re.match(self._VALID_URL, url)
sub_domain = mobj.group('sub_domain') or mobj.group('sub_domain_2')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
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)
(
# 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+)',
# 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'),
}

13
youtube_dl/extractor/heise.py
View File

@ -105,8 +105,7 @@ class HeiseIE(InfoExtractor):
webpage, default=None) or self._html_search_meta(
'description', webpage)
kaltura_url = KalturaIE._extract_url(webpage)
if kaltura_url:
def _make_kaltura_result(kaltura_url):
return {
'_type': 'url_transparent',
'url': smuggle_url(kaltura_url, {'source_url': url}),
@ -115,6 +114,16 @@ class HeiseIE(InfoExtractor):
'description': description,
}
kaltura_url = KalturaIE._extract_url(webpage)
if kaltura_url:
return _make_kaltura_result(kaltura_url)
kaltura_id = self._search_regex(
r'entry-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'kaltura id',
default=None, group='id')
if kaltura_id:
return _make_kaltura_result('kaltura:2238431:%s' % kaltura_id)
yt_urls = YoutubeIE._extract_urls(webpage)
if yt_urls:
return self.playlist_from_matches(

13
youtube_dl/extractor/hotstar.py
View File

@ -3,6 +3,7 @@ from __future__ import unicode_literals
import hashlib
import hmac
import re
import time
import uuid
@ -117,6 +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']
@ -126,6 +128,8 @@ class HotStarIE(HotStarBaseIE):
format_url = url_or_none(playback_set.get('playbackUrl'))
if not format_url:
continue
format_url = re.sub(
r'(?<=//staragvod)(\d)', r'web\1', format_url)
tags = str_or_none(playback_set.get('tagsCombination')) or ''
if tags and 'encryption:plain' not in tags:
continue
@ -133,10 +137,12 @@ class HotStarIE(HotStarBaseIE):
try:
if 'package:hls' in tags or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls'))
format_url, video_id, 'mp4',
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
@ -154,6 +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,
}

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,
}

5
youtube_dl/extractor/instagram.py
View File

@ -22,7 +22,7 @@ from ..utils import (
class InstagramIE(InfoExtractor):
_VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/p/(?P<id>[^/?#&]+))'
_VALID_URL = r'(?P<url>https?://(?:www\.)?instagram\.com/(?:p|tv)/(?P<id>[^/?#&]+))'
_TESTS = [{
'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
@ -92,6 +92,9 @@ class InstagramIE(InfoExtractor):
}, {
'url': 'http://instagram.com/p/9o6LshA7zy/embed/',
'only_matching': True,
}, {
'url': 'https://www.instagram.com/tv/aye83DjauH/',
'only_matching': True,
}]
@staticmethod

92
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']
formats.extend(self._extract_f4m_formats(
file_url.replace('.m3u8', '.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)
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
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(
replace_url('.f4m'), video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
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)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'description': description,
'thumbnail': data.get('PosterUrl'),
'description': data.get('Description'),
}

107
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
}
]
}
})
video_json = self._download_json(
'http://api.digitalaccess.ru/api/json/', video_id,
'Downloading video JSON', data=json.dumps(data))
bundled = hasattr(sys, 'frozen')
if 'error' in video_json:
error = video_json['error']
origin = error['origin']
if origin == 'NotAllowedForLocation':
self.raise_geo_restricted(
msg=error['message'], countries=self._GEO_COUNTRIES)
elif origin == 'NoRedisValidData':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
raise ExtractorError(
'Unable to download video %s: %s' % (video_id, error['message']),
expected=True)
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(
self._LIGHT_URL, video_id,
'Downloading video JSON', data=content_data, query=query)
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(message, self._GEO_COUNTRIES)
elif origin == 'NoRedisValidData':
extractor_msg = 'Video %s does not exist'
elif site == 353:
continue
elif bundled:
raise ExtractorError(
'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,
}

161
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'))
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': 'https://www.jamendo.com/track/' + track_id,
'ie_key': JamendoIE.ie_key(),
'id': track_id,
'album': album_name,
})
title, artist, album = self._extract_meta(webpage, fatal=False)
entries = [{
'_type': 'url_transparent',
'url': compat_urlparse.urljoin(url, m.group('path')),
'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)]
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)))

2
youtube_dl/extractor/jwplatform.py
View File

@ -7,7 +7,7 @@ from .common import InfoExtractor
class JWPlatformIE(InfoExtractor):
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview|video)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
_VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview)s|jw6|v2/media)/|jwplatform:)(?P<id>[a-zA-Z0-9]{8})'
_TESTS = [{
'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js',
'md5': 'fa8899fa601eb7c83a64e9d568bdf325',

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'),
}

23
youtube_dl/extractor/kaltura.py
View File

@ -103,6 +103,11 @@ class KalturaIE(InfoExtractor):
{
'url': 'https://www.kaltura.com:443/index.php/extwidget/preview/partner_id/1770401/uiconf_id/37307382/entry_id/0_58u8kme7/embed/iframe?&flashvars[streamerType]=auto',
'only_matching': True,
},
{
# unavailable source format
'url': 'kaltura:513551:1_66x4rg7o',
'only_matching': True,
}
]
@ -146,14 +151,15 @@ class KalturaIE(InfoExtractor):
if mobj:
embed_info = mobj.groupdict()
for k, v in embed_info.items():
embed_info[k] = v.strip()
if v:
embed_info[k] = v.strip()
url = 'kaltura:%(partner_id)s:%(id)s' % embed_info
escaped_pid = re.escape(embed_info['partner_id'])
service_url = re.search(
r'<script[^>]+src=["\']((?:https?:)?//.+?)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
service_mobj = re.search(
r'<script[^>]+src=(["\'])(?P<id>(?:https?:)?//(?:(?!\1).)+)/p/%s/sp/%s00/embedIframeJs' % (escaped_pid, escaped_pid),
webpage)
if service_url:
url = smuggle_url(url, {'service_url': service_url.group(1)})
if service_mobj:
url = smuggle_url(url, {'service_url': service_mobj.group('id')})
return url
def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):
@ -306,12 +312,17 @@ class KalturaIE(InfoExtractor):
f['fileExt'] = 'mp4'
video_url = sign_url(
'%s/flavorId/%s' % (data_url, f['id']))
format_id = '%(fileExt)s-%(bitrate)s' % f
# Source format may not be available (e.g. kaltura:513551:1_66x4rg7o)
if f.get('isOriginal') is True and not self._is_valid_url(
video_url, entry_id, format_id):
continue
# audio-only has no videoCodecId (e.g. kaltura:1926081:0_c03e1b5g
# -f mp4-56)
vcodec = 'none' if 'videoCodecId' not in f and f.get(
'frameRate') == 0 else f.get('videoCodecId')
formats.append({
'format_id': '%(fileExt)s-%(bitrate)s' % f,
'format_id': format_id,
'ext': f.get('fileExt'),
'tbr': int_or_none(f['bitrate']),
'fps': int_or_none(f.get('frameRate')),

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,
}

113
youtube_dl/extractor/lecturio.py
View File

@ -6,8 +6,8 @@ import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
extract_attributes,
ExtractorError,
float_or_none,
int_or_none,
@ -19,6 +19,7 @@ from ..utils import (
class LecturioBaseIE(InfoExtractor):
_API_BASE_URL = 'https://app.lecturio.com/api/en/latest/html5/'
_LOGIN_URL = 'https://app.lecturio.com/en/login'
_NETRC_MACHINE = 'lecturio'
@ -67,51 +68,56 @@ class LecturioIE(LecturioBaseIE):
_VALID_URL = r'''(?x)
https://
(?:
app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.lecture|
(?:www\.)?lecturio\.de/[^/]+/(?P<id_de>[^/?#&]+)\.vortrag
app\.lecturio\.com/([^/]+/(?P<nt>[^/?#&]+)\.lecture|(?:\#/)?lecture/c/\d+/(?P<id>\d+))|
(?:www\.)?lecturio\.de/[^/]+/(?P<nt_de>[^/?#&]+)\.vortrag
)
'''
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/important-concepts-and-terms-introduction-to-microbiology.lecture#tab/videos',
'md5': 'f576a797a5b7a5e4e4bbdfc25a6a6870',
'md5': '9a42cf1d8282a6311bf7211bbde26fde',
'info_dict': {
'id': '39634',
'ext': 'mp4',
'title': 'Important Concepts and Terms – Introduction to Microbiology',
'title': 'Important Concepts and Terms — Introduction to Microbiology',
},
'skip': 'Requires lecturio account credentials',
}, {
'url': 'https://www.lecturio.de/jura/oeffentliches-recht-staatsexamen.vortrag',
'only_matching': True,
}, {
'url': 'https://app.lecturio.com/#/lecture/c/6434/39634',
'only_matching': True,
}]
_CC_LANGS = {
'Arabic': 'ar',
'Bulgarian': 'bg',
'German': 'de',
'English': 'en',
'Spanish': 'es',
'Persian': 'fa',
'French': 'fr',
'Japanese': 'ja',
'Polish': 'pl',
'Pashto': 'ps',
'Russian': 'ru',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('id') or mobj.group('id_de')
webpage = self._download_webpage(
'https://app.lecturio.com/en/lecture/%s/player.html' % display_id,
display_id)
lecture_id = self._search_regex(
r'lecture_id\s*=\s*(?:L_)?(\d+)', webpage, 'lecture id')
api_url = self._search_regex(
r'lectureDataLink\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'api url', group='url')
video = self._download_json(api_url, display_id)
nt = mobj.group('nt') or mobj.group('nt_de')
lecture_id = mobj.group('id')
display_id = nt or lecture_id
api_path = 'lectures/' + lecture_id if lecture_id else 'lecture/' + nt + '.json'
video = self._download_json(
self._API_BASE_URL + api_path, display_id)
title = video['title'].strip()
if not lecture_id:
pid = video.get('productId') or video.get('uid')
if pid:
spid = pid.split('_')
if spid and len(spid) == 2:
lecture_id = spid[1]
formats = []
for format_ in video['content']['media']:
@ -129,24 +135,30 @@ class LecturioIE(LecturioBaseIE):
continue
label = str_or_none(format_.get('label'))
filesize = int_or_none(format_.get('fileSize'))
formats.append({
f = {
'url': file_url,
'format_id': label,
'filesize': float_or_none(filesize, invscale=1000)
})
}
if label:
mobj = re.match(r'(\d+)p\s*\(([^)]+)\)', label)
if mobj:
f.update({
'format_id': mobj.group(2),
'height': int(mobj.group(1)),
})
formats.append(f)
self._sort_formats(formats)
subtitles = {}
automatic_captions = {}
cc = self._parse_json(
self._search_regex(
r'subtitleUrls\s*:\s*({.+?})\s*,', webpage, 'subtitles',
default='{}'), display_id, fatal=False)
for cc_label, cc_url in cc.items():
cc_url = url_or_none(cc_url)
captions = video.get('captions') or []
for cc in captions:
cc_url = cc.get('url')
if not cc_url:
continue
lang = self._search_regex(
cc_label = cc.get('translatedCode')
lang = cc.get('languageCode') or self._search_regex(
r'/([a-z]{2})_', cc_url, 'lang',
default=cc_label.split()[0] if cc_label else 'en')
original_lang = self._search_regex(
@ -160,7 +172,7 @@ class LecturioIE(LecturioBaseIE):
})
return {
'id': lecture_id,
'id': lecture_id or nt,
'title': title,
'formats': formats,
'subtitles': subtitles,
@ -169,37 +181,40 @@ class LecturioIE(LecturioBaseIE):
class LecturioCourseIE(LecturioBaseIE):
_VALID_URL = r'https://app\.lecturio\.com/[^/]+/(?P<id>[^/?#&]+)\.course'
_TEST = {
_VALID_URL = r'https://app\.lecturio\.com/(?:[^/]+/(?P<nt>[^/?#&]+)\.course|(?:#/)?course/c/(?P<id>\d+))'
_TESTS = [{
'url': 'https://app.lecturio.com/medical-courses/microbiology-introduction.course#/',
'info_dict': {
'id': 'microbiology-introduction',
'title': 'Microbiology: Introduction',
'description': 'md5:13da8500c25880c6016ae1e6d78c386a',
},
'playlist_count': 45,
'skip': 'Requires lecturio account credentials',
}
}, {
'url': 'https://app.lecturio.com/#/course/c/6434',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
nt, course_id = re.match(self._VALID_URL, url).groups()
display_id = nt or course_id
api_path = 'courses/' + course_id if course_id else 'course/content/' + nt + '.json'
course = self._download_json(
self._API_BASE_URL + api_path, display_id)
entries = []
for mobj in re.finditer(
r'(?s)<[^>]+\bdata-url=(["\'])(?:(?!\1).)+\.lecture\b[^>]+>',
webpage):
params = extract_attributes(mobj.group(0))
lecture_url = urljoin(url, params.get('data-url'))
lecture_id = params.get('data-id')
for lecture in course.get('lectures', []):
lecture_id = str_or_none(lecture.get('id'))
lecture_url = lecture.get('url')
if lecture_url:
lecture_url = urljoin(url, lecture_url)
else:
lecture_url = 'https://app.lecturio.com/#/lecture/c/%s/%s' % (course_id, lecture_id)
entries.append(self.url_result(
lecture_url, ie=LecturioIE.ie_key(), video_id=lecture_id))
title = self._search_regex(
r'<span[^>]+class=["\']content-title[^>]+>([^<]+)', webpage,
'title', default=None)
return self.playlist_result(entries, display_id, title)
return self.playlist_result(
entries, display_id, course.get('title'),
clean_html(course.get('description')))
class LecturioDeCourseIE(LecturioBaseIE):

2
youtube_dl/extractor/leeco.py
View File

@ -326,7 +326,7 @@ class LetvCloudIE(InfoExtractor):
elif play_json.get('code'):
raise ExtractorError('Letv cloud returned error %d' % play_json['code'], expected=True)
else:
raise ExtractorError('Letv cloud returned an unknwon error')
raise ExtractorError('Letv cloud returned an unknown error')
def b64decode(s):
return compat_b64decode(s).decode('utf-8')

42
youtube_dl/extractor/livejournal.py Normal file
View File

@ -0,0 +1,42 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
class LiveJournalIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^.]+\.)?livejournal\.com/video/album/\d+.+?\bid=(?P<id>\d+)'
_TEST = {
'url': 'https://andrei-bt.livejournal.com/video/album/407/?mode=view&id=51272',
'md5': 'adaf018388572ced8a6f301ace49d4b2',
'info_dict': {
'id': '1263729',
'ext': 'mp4',
'title': 'Истребители против БПЛА',
'upload_date': '20190624',
'timestamp': 1561406715,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
record = self._parse_json(self._search_regex(
r'Site\.page\s*=\s*({.+?});', webpage,
'page data'), video_id)['video']['record']
storage_id = compat_str(record['storageid'])
title = record.get('name')
if title:
# remove filename extension(.mp4, .mov, etc...)
title = title.rsplit('.', 1)[0]
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'thumbnail': record.get('thumbnail'),
'timestamp': int_or_none(record.get('timecreate')),
'url': 'eagleplatform:vc.videos.livejournal.com:' + storage_id,
'ie_key': 'EaglePlatform',
}

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')),
}

15
youtube_dl/extractor/lynda.py
View File

@ -117,6 +117,10 @@ class LyndaIE(LyndaBaseIE):
}, {
'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html',
'only_matching': True,
}, {
# Status="NotFound", Message="Transcript not found"
'url': 'https://www.lynda.com/ASP-NET-tutorials/What-you-should-know/5034180/2811512-4.html',
'only_matching': True,
}]
def _raise_unavailable(self, video_id):
@ -247,12 +251,17 @@ class LyndaIE(LyndaBaseIE):
def _get_subtitles(self, video_id):
url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id
subs = self._download_json(url, None, False)
subs = self._download_webpage(
url, video_id, 'Downloading subtitles JSON', fatal=False)
if not subs or 'Status="NotFound"' in subs:
return {}
subs = self._parse_json(subs, video_id, fatal=False)
if not subs:
return {}
fixed_subs = self._fix_subtitles(subs)
if fixed_subs:
return {'en': [{'ext': 'srt', 'data': fixed_subs}]}
else:
return {}
return {}
class LyndaCourseIE(LyndaBaseIE):

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',
}

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