Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-02-03 15:23:12 +08:00
Code Issues Releases Wiki Activity

Merge remote-tracking branch 'upstream/master'

Browse Source
This commit is contained in:
Mark 2017-06-01 00:01:52 +02:00
commit 1685db18a0
190 changed files with 7510 additions and 3141 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/ISSUE_TEMPLATE.md vendored
View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.03.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.03.24**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.05.29*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.05.29**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[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 2017.03.24
[debug] youtube-dl version 2017.05.29
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

2
.gitignore vendored
View File

@ -35,8 +35,8 @@ updates_key.pem
*.mkv
*.swf
*.part
*.ytdl
*.swp
test/testdata
test/local_parameters.json
.tox
youtube-dl.zsh

7
AUTHORS
View File

@ -210,3 +210,10 @@ Lars Vierbergen
Juanjo Benages
Xiao Di Guan
Thomas Winant
Daniel Twardowski
Jeremie Jarosh
Gerard Rovira
Marvin Ewald
Frédéric Bournival
Timendum
gritstub

386
ChangeLog
View File

@ -1,7 +1,391 @@
version <unreleased>
version 2017.05.29
Extractors
* [youtube] Fix DASH MPD extraction for videos with non-encrypted format URLs
(#13211)
* [xhamster] Fix uploader and like/dislike count extraction (#13216))
+ [xhamster] Extract categories (#11728)
+ [abcnews] Add support for embed URLs (#12851)
* [gaskrank] Fix extraction (#12493)
* [medialaan] Fix videos with missing videoUrl (#12774)
* [dvtv] Fix playlist support
+ [dvtv] Add support for DASH and HLS formats (#3063)
+ [beam:vod] Add support for beam.pro/mixer.com VODs (#13032))
* [cbsinteractive] Relax URL regular expression (#13213)
* [adn] Fix formats extraction
+ [youku] Extract more metadata (#10433)
* [cbsnews] Fix extraction (#13205)
version 2017.05.26
Core
+ [utils] strip_jsonp() can recognize more patterns
* [postprocessor/ffmpeg] Fix metadata filename handling on Python 2 (#13182)
Extractors
+ [youtube] DASH MPDs with cipher signatures are recognized now (#11381)
+ [bbc] Add support for authentication
* [tudou] Merge into youku extractor (#12214)
* [youku:show] Fix extraction
* [youku] Fix extraction (#13191)
* [udemy] Fix extraction for outputs' format entries without URL (#13192)
* [vimeo] Fix formats' sorting (#13189)
* [cbsnews] Fix extraction for 60 Minutes videos (#12861)
version 2017.05.23
Core
+ [downloader/external] Pass -loglevel to ffmpeg downloader (#13183)
+ [adobepass] Add support for Bright House Networks (#13149)
Extractors
+ [streamcz] Add support for subtitles (#13174)
* [youtube] Fix DASH manifest signature decryption (#8944, #13156)
* [toggle] Relax URL regular expression (#13172)
* [toypics] Fix extraction (#13077)
* [njpwworld] Fix extraction (#13162, #13169)
+ [hitbox] Add support for smashcast.tv (#13154)
* [mitele] Update app key regular expression (#13158)
version 2017.05.18.1
Core
* [jsinterp] Fix typo and cleanup regular expressions (#13134)
version 2017.05.18
Core
+ [jsinterp] Add support for quoted names and indexers (#13123, #13124, #13125,
#13126, #13128, #13129, #13130, #13131, #13132)
+ [extractor/common] Add support for schemeless URLs in _extract_wowza_formats
(#13088, #13092)
+ [utils] Recognize more audio codecs (#13081)
Extractors
+ [vier] Extract more metadata (#12539)
* [vier] Improve extraction (#12801)
+ Add support for authentication
* Bypass authentication when no credentials provided
* Improve extraction robustness
* [dailymail] Fix sources extraction (#13057)
* [dailymotion] Extend URL regular expression (#13079)
version 2017.05.14
Core
+ [extractor/common] Respect Width and Height attributes in ISM manifests
+ [postprocessor/metadatafromtitle] Add support regular expression syntax for
--metadata-from-title (#13065)
Extractors
+ [mediaset] Add support for video.mediaset.it (#12708, #12964)
* [orf:radio] Fix extraction (#11643, #12926)
* [aljazeera] Extend URL regular expression (#13053)
* [imdb] Relax URL regular expression (#13056)
+ [francetv] Add support for mobile.france.tv (#13068)
+ [upskill] Add support for upskillcourses.com (#13043)
* [thescene] Fix extraction (#13061)
* [condenast] Improve embed support
* [liveleak] Fix extraction (#12053)
+ [douyu] Support Douyu shows (#12228)
* [myspace] Improve URL regular expression (#13040)
* [adultswim] Use desktop platform in assets URL (#13041)
version 2017.05.09
Core
* [YoutubeDL] Force --restrict-filenames when no locale is set on all python
versions (#13027)
Extractors
* [francetv] Adapt to site redesign (#13034)
+ [packtpub] Add support for authentication (#12622)
* [drtv] Lower preference for SignLanguage formats (#13013, #13016)
+ [cspan] Add support for brightcove live embeds (#13028)
* [vrv] Extract DASH formats and subtitles
* [funimation] Fix authentication (#13021)
* [adultswim] Fix extraction (#8640, #10950, #11042, #12121)
+ Add support for Adobe Pass authentication
+ Add support for live streams
+ Add support for show pages
* [turner] Extract thumbnail, is_live and strip description
+ [nonktube] Add support for nonktube.com (#8647, #13024)
+ [nuevo] Pass headers to _extract_nuevo
* [nbc] Improve extraction (#12364)
version 2017.05.07
Common
* [extractor/common] Fix typo in _extract_akamai_formats
+ [postprocessor/ffmpeg] Embed chapters into media file with --add-metadata
+ [extractor/common] Introduce chapters meta field
Extractors
* [youtube] Fix authentication (#12820, #12927, #12973, #12992, #12993, #12995,
#13003)
* [bilibili] Fix video downloading (#13001)
* [rmcdecouverte] Fix extraction (#12937)
* [theplatform] Extract chapters
* [bandcamp] Fix thumbnail extraction (#12980)
* [pornhub] Extend URL regular expression (#12996)
+ [youtube] Extract chapters
+ [nrk] Extract chapters
+ [vice] Add support for ooyala embeds in article pages
+ [vice] Support vice articles (#12968)
* [vice] Fix extraction for non en_us videos (#12967)
* [gdcvault] Fix extraction for some videos (#12733)
* [pbs] Improve multipart video support (#12981)
* [laola1tv] Fix extraction (#12880)
+ [cda] Support birthday verification (#12789)
* [leeco] Fix extraction (#12974)
+ [pbs] Extract chapters
* [amp] Imporove thumbnail and subtitles extraction
* [foxsports] Fix extraction (#12945)
- [coub] Remove comment count extraction (#12941)
version 2017.05.01
Core
+ [extractor/common] Extract view count from JSON-LD
* [utils] Improve unified_timestamp
+ [utils] Add video/mp2t to mimetype2ext
* [downloader/external] Properly handle live stream downloading cancellation
(#8932)
+ [utils] Add support for unicode whitespace in clean_html on python 2 (#12906)
Extractors
* [infoq] Make audio format extraction non fatal (#12938)
* [brightcove] Allow whitespace around attribute names in embedded code
+ [zaq1] Add support for zaq1.pl (#12693)
+ [xvideos] Extract duration (#12828)
* [vevo] Fix extraction (#12879)
+ [noovo] Add support for noovo.ca (#12792)
+ [washingtonpost] Add support for embeds (#12699)
* [yandexmusic:playlist] Fix extraction for python 3 (#12888)
* [anvato] Improve extraction (#12913)
* Promote to regular shortcut based extractor
* Add mcp to access key mapping table
* Add support for embeds extraction
* Add support for anvato embeds in generic extractor
* [xtube] Fix extraction for older FLV videos (#12734)
* [tvplayer] Fix extraction (#12908)
version 2017.04.28
Core
+ [adobepass] Use geo verification headers for all requests
- [downloader/fragment] Remove assert for resume_len when no fragments
downloaded
+ [extractor/common] Add manifest_url for explicit group rendition formats
* [extractor/common] Fix manifest_url for m3u8 formats
- [extractor/common] Don't list master m3u8 playlists in format list (#12832)
Extractor
* [aenetworks] Fix extraction for shows with single season
+ [go] Add support for Disney, DisneyJunior and DisneyXD show pages
* [youtube] Recognize new locale-based player URLs (#12885)
+ [streamable] Add support for new embedded URL schema (#12844)
* [arte:+7] Relax URL regular expression (#12837)
version 2017.04.26
Core
* Introduce --keep-fragments for keeping fragments of fragmented download
on disk after download is finished
* [YoutubeDL] Fix output template for missing timestamp (#12796)
* [socks] Handle cases where credentials are required but missing
* [extractor/common] Improve HLS extraction (#12211)
* Extract m3u8 parsing to separate method
* Improve rendition groups extraction
* Build stream name according stream GROUP-ID
* Ignore reference to AUDIO group without URI when stream has no CODECS
* Use float for scaled tbr in _parse_m3u8_formats
* [utils] Add support for TTML styles in dfxp2srt
* [downloader/hls] No need to download keys for fragments that have been
already downloaded
* [downloader/fragment] Improve fragment downloading
* Resume immediately
* Don't concatenate fragments and decrypt them on every resume
* Optimize disk storage usage, don't store intermediate fragments on disk
* Store bookkeeping download state file
+ [extractor/common] Add support for multiple getters in try_get
+ [extractor/common] Add support for video of WebPage context in _json_ld
(#12778)
+ [extractor/common] Relax JWPlayer regular expression and remove
duplicate URLs (#12768)
Extractors
* [iqiyi] Fix extraction of Yule videos
* [vidio] Improve extraction and sort formats
+ [brightcove] Match only video elements with data-video-id attribute
* [iqiyi] Fix playlist detection (#12504)
- [azubu] Remove extractor (#12813)
* [porn91] Fix extraction (#12814)
* [vidzi] Fix extraction (#12793)
+ [amp] Extract error message (#12795)
+ [xfileshare] Add support for gorillavid.com and daclips.com (#12776)
* [instagram] Fix extraction (#12777)
+ [generic] Support Brightcove videos in <iframe> (#12482)
+ [brightcove] Support URLs with bcpid instead of playerID (#12482)
* [brightcove] Fix _extract_url (#12782)
+ [odnoklassniki] Extract HLS formats
version 2017.04.17
Extractors
* [limelight] Improve extraction LimelightEmbeddedPlayerFlash media embeds and
add support for channel and channelList embeds
* [generic] Extract multiple Limelight embeds (#12761)
+ [itv] Extract series metadata
* [itv] Fix RTMP formats downloading (#12759)
* [itv] Use native HLS downloader by default
+ [go90] Extract subtitles (#12752)
+ [go90] Extract series metadata (#12752)
version 2017.04.16
Core
* [YoutubeDL] Apply expand_path after output template substitution
+ [YoutubeDL] Propagate overridden meta fields to extraction results of type
url (#11163)
Extractors
+ [generic] Extract RSS entries as url_transparent (#11163)
+ [streamango] Add support for streamango.com (#12643)
+ [wsj:article] Add support for articles (#12558)
* [brightcove] Relax video tag embeds extraction and validate ambiguous embeds'
URLs (#9163, #12005, #12178, #12480)
+ [udemy] Add support for react rendition (#12744)
version 2017.04.15
Extractors
* [youku] Fix fileid extraction (#12741, #12743)
version 2017.04.14
Core
+ [downloader/hls] Add basic support for EXT-X-BYTERANGE tag (#10955)
+ [adobepass] Improve Comcast and Verison login code (#10803)
+ [adobepass] Add support for Verizon (#10803)
Extractors
+ [aenetworks] Add support for specials (#12723)
+ [hbo] Extract HLS formats
+ [go90] Add support for go90.com (#10127)
+ [tv2hu] Add support for tv2.hu (#10509)
+ [generic] Exclude URLs with xml ext from valid video URLs (#10768, #11654)
* [youtube] Improve HLS formats extraction
* [afreecatv] Fix extraction for videos with different key layout (#12718)
- [youtube] Remove explicit preference for audio-only and video-only formats in
order not to break sorting when new formats appear
* [canalplus] Bypass geo restriction
version 2017.04.11
Extractors
* [afreecatv] Fix extraction (#12706)
+ [generic] Add support for <object> YouTube embeds (#12637)
* [bbccouk] Treat bitrate as audio+video bitrate in media selector
+ [bbccouk] Skip unrecognized formats in media selector (#12701)
+ [bbccouk] Add support for https protocol in media selector (#12701)
* [curiositystream] Fix extraction (#12638)
* [adn] Update subtitle decryption key
* [chaturbate] Fix extraction (#12665, #12688, #12690)
version 2017.04.09
Extractors
+ [medici] Add support for medici.tv (#3406)
+ [rbmaradio] Add support for redbullradio.com URLs (#12687)
+ [npo:live] Add support for default URL (#12555)
* [mixcloud:playlist] Fix title, description and view count extraction (#12582)
+ [thesun] Add suport for thesun.co.uk (#11298, #12674)
+ [ceskateleveize:porady] Add support for porady (#7411, #12645)
* [ceskateleveize] Improve extraction and remove URL replacement hacks
+ [kaltura] Add support for iframe embeds (#12679)
* [airmozilla] Fix extraction (#12670)
* [wshh] Extract html5 entries and delegate to generic extractor (12676)
+ [raiplay] Extract subtitles
+ [xfileshare] Add support for vidlo.us (#12660)
+ [xfileshare] Add support for vidbom.com (#12661)
+ [aenetworks] Add more video URL regular expressions (#12657)
+ [odnoklassniki] Fix format sorting for 1080p quality
+ [rtl2] Add support for you.rtl2.de (#10257)
+ [vshare] Add support for vshare.io (#12278)
version 2017.04.03
Core
+ [extractor/common] Add censorship check for TransTelekom ISP
* [extractor/common] Move censorship checks to a separate method
Extractors
+ [discoveryvr] Add support for discoveryvr.com (#12578)
+ [tv5mondeplus] Add support for tv5mondeplus.com (#11386)
+ [periscope] Add support for pscp.tv URLs (#12618, #12625)
version 2017.04.02
Core
* [YoutubeDL] Return early when extraction of url_transparent fails
Extractors
* [rai] Fix and improve extraction (#11790)
+ [vrv] Add support for series pages
* [limelight] Improve extraction for audio only formats
* [funimation] Fix extraction (#10696, #11773)
+ [xfileshare] Add support for vidabc.com (#12589)
+ [xfileshare] Improve extraction and extract hls formats
+ [crunchyroll] Pass geo verifcation proxy
+ [cwtv] Extract ISM formats
+ [tvplay] Bypass geo restriction
+ [vrv] Add support for vrv.co
+ [packtpub] Add support for packtpub.com (#12610)
+ [generic] Pass base_url to _parse_jwplayer_data
+ [adn] Add support for animedigitalnetwork.fr (#4866)
+ [allocine] Extract more metadata
* [allocine] Fix extraction (#12592)
* [openload] Fix extraction
version 2017.03.26
Core
* Don't raise an error if JWPlayer config data is not a Javascript object
literal. _find_jwplayer_data now returns a dict rather than an str. (#12307)
* Expand environment variables for options representing paths (#12556)
+ [utils] Introduce expand_path
* [downloader/hls] Delegate downloading to ffmpeg immediately for live streams
Extractors
* [afreecatv] Fix extraction (#12179)
+ [atvat] Add support for atv.at (#5325)
+ [fox] Add metadata extraction (#12391)
+ [atresplayer] Extract DASH formats
+ [atresplayer] Extract HD manifest (#12548)
* [atresplayer] Fix login error detection (#12548)
* [franceculture] Fix extraction (#12547)
* [youtube] Improve URL regular expression (#12538)
* [generic] Do not follow redirects to the same URL
version 2017.03.24

2
Makefile
View File

@ -1,7 +1,7 @@
all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish youtube_dl/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png CONTRIBUTING.md.tmp ISSUE_TEMPLATE.md.tmp youtube-dl youtube-dl.exe
find . -name "*.pyc" -delete
find . -name "*.class" -delete

32
README.md
View File

@ -181,12 +181,15 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
-R, --retries RETRIES Number of retries (default is 10), or
"infinite".
--fragment-retries RETRIES Number of retries for a fragment (default
is 10), or "infinite" (DASH and hlsnative
only)
--skip-unavailable-fragments Skip unavailable fragments (DASH and
hlsnative only)
is 10), or "infinite" (DASH, hlsnative and
ISM)
--skip-unavailable-fragments Skip unavailable fragments (DASH, hlsnative
and ISM)
--abort-on-unavailable-fragment Abort downloading when some fragment is not
available
--keep-fragments Keep downloaded fragments on disk after
downloading is finished; fragments are
erased by default
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer Do not automatically adjust the buffer
@ -397,12 +400,14 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
--add-metadata Write metadata to the video file
--metadata-from-title FORMAT Parse additional metadata like song title /
artist from the video title. The format
syntax is the same as --output, the parsed
parameters replace existing values.
Additional templates: %(album)s,
%(artist)s. Example: --metadata-from-title
"%(artist)s - %(title)s" matches a title
like "Coldplay - Paradise"
syntax is the same as --output. Regular
expression with named capture groups may
also be used. The parsed parameters replace
existing values. Example: --metadata-from-
title "%(artist)s - %(title)s" matches a
title like "Coldplay - Paradise". Example
(regex): --metadata-from-title
"(?P<artist>.+?) - (?P<title>.+)"
--xattrs Write metadata to the video file's xattrs
(using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the
@ -469,7 +474,10 @@ machine twitch login my_twitch_account_name password my_twitch_password
```
To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
On Windows you may also need to setup the `%HOME%` environment variable manually.
On Windows you may also need to setup the `%HOME%` environment variable manually. For example:
```
set HOME=%USERPROFILE%
```
# OUTPUT TEMPLATE
@ -644,7 +652,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
- `acodec`: Name of the audio codec in use
- `vcodec`: Name of the video codec in use
- `container`: Name of the container format
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `m3u8`, or `m3u8_native`)
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
- `format_id`: A short description of the format
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.

57
docs/supportedsites.md
View File

@ -28,6 +28,7 @@
- **acast**
- **acast:channel**
- **AddAnime**
- **ADN**: Anime Digital Network
- **AdobeTV**
- **AdobeTVChannel**
- **AdobeTVShow**
@ -44,6 +45,7 @@
- **anderetijden**: npo.nl and ntr.nl
- **AnimeOnDemand**
- **anitube.se**
- **Anvato**
- **AnySex**
- **Aparat**
- **AppleConnect**
@ -67,6 +69,7 @@
- **arte.tv:playlist**
- **AtresPlayer**
- **ATTTechChannel**
- **ATVAt**
- **AudiMedia**
- **AudioBoom**
- **audiomack**
@ -79,8 +82,6 @@
- **AZMedien**: AZ Medien videos
- **AZMedienPlaylist**: AZ Medien playlists
- **AZMedienShowPlaylist**: AZ Medien show playlists
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
@ -92,7 +93,6 @@
- **bbc.co.uk:article**: BBC articles
- **bbc.co.uk:iplayer:playlist**
- **bbc.co.uk:playlist**
- **Beam:live**
- **Beatport**
- **Beeg**
- **BehindKink**
@ -125,7 +125,7 @@
- **CamWithHer**
- **canalc2.tv**
- **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- **Canvas**
- **Canvas**: canvas.be and een.be
- **CarambaTV**
- **CarambaTVPage**
- **CartoonNetwork**
@ -143,6 +143,7 @@
- **CCTV**: 央视网
- **CDA**
- **CeskaTelevize**
- **CeskaTelevizePorady**
- **channel9**: Channel 9
- **CharlieRose**
- **Chaturbate**
@ -211,8 +212,10 @@
- **DiscoveryGo**
- **DiscoveryGoPlaylist**
- **DiscoveryNetworksDe**
- **DiscoveryVR**
- **Disney**
- **Dotsub**
- **DouyuShow**
- **DouyuTV**: 斗鱼
- **DPlay**
- **DPlayIt**
@ -278,7 +281,8 @@
- **france2.fr:generation-quoi**
- **FranceCulture**
- **FranceInter**
- **francetv**: France 2, 3, 4, 5 and Ô
- **FranceTV**
- **FranceTVEmbed**
- **francetvinfo.fr**
- **Freesound**
- **freespeech.org**
@ -304,6 +308,7 @@
- **Globo**
- **GloboArticle**
- **Go**
- **Go90**
- **GodTube**
- **GodTV**
- **Golem**
@ -428,6 +433,8 @@
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **Medialaan**
- **Mediaset**
- **Medici**
- **Meipai**: 美拍
- **MelonVOD**
- **META**
@ -445,6 +452,8 @@
- **mixcloud:playlist**
- **mixcloud:stream**
- **mixcloud:user**
- **Mixer:live**
- **Mixer:vod**
- **MLB**
- **Mnet**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@ -525,6 +534,8 @@
- **NJPWWorld**: 新日本プロレスワールド
- **NobelPrize**
- **Noco**
- **NonkTube**
- **Noovo**
- **Normalboots**
- **NosVideo**
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
@ -571,6 +582,8 @@
- **orf:iptv**: iptv.ORF.at
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **PacktPub**
- **PacktPubCourse**
- **PandaTV**: 熊猫TV
- **pandora.tv**: 판도라TV
- **parliamentlive.tv**: UK parliament videos
@ -594,7 +607,6 @@
- **pluralsight**
- **pluralsight:course**
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **Pokemon**
- **PolskieRadio**
@ -628,7 +640,7 @@
- **radiofrance**
- **RadioJavan**
- **Rai**
- **RaiTV**
- **RaiPlay**
- **RBMARadio**
- **RDS**: RDS.ca
- **RedBullTV**
@ -653,7 +665,9 @@
- **rte**: Raidió Teilifís Éireann TV
- **rte:radio**: Raidió Teilifís Éireann radio
- **rtl.nl**: rtl.nl and rtlxl.nl
- **RTL2**
- **rtl2**
- **rtl2:you**
- **rtl2:you:series**
- **RTP**
- **RTS**: RTS.ch
- **rtve.es:alacarta**: RTVE a la carta
@ -735,6 +749,7 @@
- **Steam**
- **Stitcher**
- **Streamable**
- **Streamango**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -775,6 +790,7 @@
- **TheScene**
- **TheSixtyOne**
- **TheStar**
- **TheSun**
- **TheWeatherChannel**
- **ThisAmericanLife**
- **ThisAV**
@ -788,16 +804,13 @@
- **ToonGoggles**
- **Tosh**: Tosh.0
- **tou.tv**
- **Toypics**: Toypics user profile
- **Toypics**: Toypics video
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **TruTV**
- **Tube8**
- **TubiTv**
- **tudou**
- **tudou:album**
- **tudou:playlist**
- **Tumblr**
- **tunein:clip**
- **tunein:program**
@ -808,9 +821,11 @@
- **Tutv**
- **tv.dfb.de**
- **TV2**
- **tv2.hu**
- **TV2Article**
- **TV3**
- **TV4**: tv4.se and tv4play.se
- **TV5MondePlus**: TV5MONDE+
- **TVA**
- **TVANouvelles**
- **TVANouvellesArticle**
@ -846,6 +861,8 @@
- **uol.com.br**
- **uplynk**
- **uplynk:preplay**
- **Upskill**
- **UpskillCourse**
- **Urort**: NRK P3 Urørt
- **URPlay**
- **USANetwork**
@ -865,9 +882,10 @@
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **Viafree**
- **Vice**
- **vice**
- **vice:article**
- **vice:show**
- **Viceland**
- **ViceShow**
- **Vidbit**
- **Viddler**
- **Videa**
@ -887,7 +905,7 @@
- **vidme:user**
- **vidme:user:likes**
- **Vidzi**
- **vier**
- **vier**: vier.be and vijf.be
- **vier:videos**
- **ViewLift**
- **ViewLiftEmbed**
@ -924,7 +942,10 @@
- **Vporn**
- **vpro**: npo.nl and ntr.nl
- **Vrak**
- **VRT**
- **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be
- **vrv**
- **vrv:series**
- **VShare**
- **vube**: Vube.com
- **VuClip**
- **VVVVID**
@ -950,9 +971,10 @@
- **wrzuta.pl**
- **wrzuta.pl:playlist**
- **WSJ**: Wall Street Journal
- **WSJArticle**
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo
- **XHamster**
- **XHamsterEmbed**
- **xiami:album**: 虾米音乐 - 专辑
@ -997,6 +1019,7 @@
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **Zaq1**
- **ZDF**
- **ZDFChannel**
- **zingmp3**: mp3.zing.vn

315
test/test_InfoExtractor.py
View File

@ -3,12 +3,13 @@
from __future__ import unicode_literals
# Allow direct execution
import io
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, expect_dict
from test.helper import FakeYDL, expect_dict, expect_value
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
@ -175,6 +176,318 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
}]
})
def test_parse_m3u8_formats(self):
_TEST_CASES = [
(
# https://github.com/rg3/youtube-dl/issues/11507
# http://pluzz.francetv.fr/videos/le_ministere.html
'pluzz_francetv_11507',
'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
[{
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '180',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 180,
'width': 256,
'height': 144,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '303',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 303,
'width': 320,
'height': 180,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '575',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.66.30',
'tbr': 575,
'width': 512,
'height': 288,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'format_id': '831',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.77.30',
'tbr': 831,
'width': 704,
'height': 396,
}, {
'url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0',
'manifest_url': 'http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/master.m3u8?caption=2017%2F16%2F156589847-1492488987.m3u8%3Afra%3AFrancais&audiotrack=0%3Afra%3AFrancais',
'ext': 'mp4',
'protocol': 'm3u8',
'format_id': '1467',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.77.30',
'tbr': 1467,
'width': 1024,
'height': 576,
}]
),
(
# https://github.com/rg3/youtube-dl/issues/11995
# http://teamcoco.com/video/clueless-gamer-super-bowl-for-honor
'teamcoco_11995',
'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
[{
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': 'audio-0-Default',
'protocol': 'm3u8',
'vcodec': 'none',
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': 'audio-1-Default',
'protocol': 'm3u8',
'vcodec': 'none',
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '71',
'protocol': 'm3u8',
'acodec': 'mp4a.40.5',
'vcodec': 'none',
'tbr': 71,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '413',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.42001e',
'tbr': 413,
'width': 400,
'height': 224,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-400k_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '522',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.42001e',
'tbr': 522,
'width': 400,
'height': 224,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-1m_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '1205',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.4d001e',
'tbr': 1205,
'width': 640,
'height': 360,
}, {
'url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/hls/CONAN_020217_Highlight_show-2m_v4.m3u8',
'manifest_url': 'http://ak.storage-w.teamcococdn.com/cdn/2017-02/98599/ed8f/main.m3u8',
'ext': 'mp4',
'format_id': '2374',
'protocol': 'm3u8',
'acodec': 'none',
'vcodec': 'avc1.4d001f',
'tbr': 2374,
'width': 1024,
'height': 576,
}]
),
(
# https://github.com/rg3/youtube-dl/issues/12211
# http://video.toggle.sg/en/series/whoopie-s-world/ep3/478601
'toggle_mobile_12211',
'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
[{
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': 'audio-English',
'protocol': 'm3u8',
'language': 'eng',
'vcodec': 'none',
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': 'audio-Undefined',
'protocol': 'm3u8',
'language': 'und',
'vcodec': 'none',
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '155',
'protocol': 'm3u8',
'tbr': 155.648,
'width': 320,
'height': 180,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '502',
'protocol': 'm3u8',
'tbr': 502.784,
'width': 480,
'height': 270,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '827',
'protocol': 'm3u8',
'tbr': 827.392,
'width': 640,
'height': 360,
}, {
'url': 'http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8',
'manifest_url': 'http://cdnapi.kaltura.com/p/2082311/sp/208231100/playManifest/protocol/http/entryId/0_89q6e8ku/format/applehttp/tags/mobile_sd/f/a.m3u8',
'ext': 'mp4',
'format_id': '1396',
'protocol': 'm3u8',
'tbr': 1396.736,
'width': 854,
'height': 480,
}]
),
(
# http://www.twitch.tv/riotgames/v/6528877
'twitch_vod',
'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
[{
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Audio Only',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'none',
'tbr': 182.725,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Mobile',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C00D',
'tbr': 280.474,
'width': 400,
'height': 226,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Low',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01E',
'tbr': 628.347,
'width': 640,
'height': 360,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Medium',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01E',
'tbr': 893.387,
'width': 852,
'height': 480,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'High',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.42C01F',
'tbr': 1603.789,
'width': 1280,
'height': 720,
}, {
'url': 'https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8',
'manifest_url': 'https://usher.ttvnw.net/vod/6528877?allow_source=true&allow_audio_only=true&allow_spectre=true&player=twitchweb&nauth=%7B%22user_id%22%3Anull%2C%22vod_id%22%3A6528877%2C%22expires%22%3A1492887874%2C%22chansub%22%3A%7B%22restricted_bitrates%22%3A%5B%5D%7D%2C%22privileged%22%3Afalse%2C%22https_required%22%3Afalse%7D&nauthsig=3e29296a6824a0f48f9e731383f77a614fc79bee',
'ext': 'mp4',
'format_id': 'Source',
'protocol': 'm3u8',
'acodec': 'mp4a.40.2',
'vcodec': 'avc1.100.31',
'tbr': 3214.134,
'width': 1280,
'height': 720,
}]
),
(
# http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
# EXT-X-STREAM-INF tag with NAME attribute that is not defined
# in HLS specification
'vidio',
'https://www.vidio.com/videos/165683/playlist.m3u8',
[{
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '270p 3G',
'protocol': 'm3u8',
'tbr': 300,
'width': 480,
'height': 270,
}, {
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '360p SD',
'protocol': 'm3u8',
'tbr': 600,
'width': 640,
'height': 360,
}, {
'url': 'https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8',
'manifest_url': 'https://www.vidio.com/videos/165683/playlist.m3u8',
'ext': 'mp4',
'format_id': '720p HD',
'protocol': 'm3u8',
'tbr': 1200,
'width': 1280,
'height': 720,
}]
)
]
for m3u8_file, m3u8_url, expected_formats in _TEST_CASES:
with io.open('./test/testdata/m3u8/%s.m3u8' % m3u8_file,
mode='r', encoding='utf-8') as f:
formats = self.ie._parse_m3u8_formats(
f.read(), m3u8_url, ext='mp4')
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
if __name__ == '__main__':
unittest.main()

4
test/test_YoutubeDL.py
View File

@ -755,6 +755,7 @@ class TestYoutubeDL(unittest.TestCase):
'_type': 'url_transparent',
'url': 'foo2:',
'ie_key': 'Foo2',
'title': 'foo1 title'
}
class Foo2IE(InfoExtractor):
@ -771,7 +772,7 @@ class TestYoutubeDL(unittest.TestCase):
_VALID_URL = r'foo3:'
def _real_extract(self, url):
return _make_result([{'url': TEST_URL}])
return _make_result([{'url': TEST_URL}], title='foo3 title')
ydl.add_info_extractor(Foo1IE(ydl))
ydl.add_info_extractor(Foo2IE(ydl))
@ -779,6 +780,7 @@ class TestYoutubeDL(unittest.TestCase):
ydl.extract_info('foo1:')
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['url'], TEST_URL)
self.assertEqual(downloaded['title'], 'foo1 title')
if __name__ == '__main__':

18
test/test_download.py
View File

@ -151,7 +151,7 @@ def generator(test_case, tname):
try_num = 1
while True:
try:
# We're not using .download here sine that is just a shim
# We're not using .download here since that is just a shim
# for outside error handling, and returns the exit code
# instead of the result dict.
res_dict = ydl.extract_info(
@ -199,7 +199,16 @@ def generator(test_case, tname):
self.assertEqual(
test_case['playlist_duration_sum'], got_duration)
for tc in test_cases:
# Generalize both playlists and single videos to unified format for
# simplicity
if 'entries' not in res_dict:
res_dict['entries'] = [res_dict]
for tc_num, tc in enumerate(test_cases):
tc_res_dict = res_dict['entries'][tc_num]
# First, check test cases' data against extracted data alone
expect_info_dict(self, tc_res_dict, tc.get('info_dict', {}))
# Now, check downloaded file consistency
tc_filename = get_tc_filename(tc)
if not test_case.get('params', {}).get('skip_download', False):
self.assertTrue(os.path.exists(tc_filename), msg='Missing file ' + tc_filename)
@ -216,14 +225,15 @@ def generator(test_case, tname):
format_bytes(got_fsize)))
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5'])
self.assertEqual(tc['md5'], md5_for_file)
# Finally, check test cases' data again but this time against
# extracted data from info JSON file written during processing
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
self.assertTrue(
os.path.exists(info_json_fn),
'Missing info file %s' % info_json_fn)
with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
expect_info_dict(self, info_dict, tc.get('info_dict', {}))
finally:
try_rm_tcs_files()

8
test/test_subtitles.py
View File

@ -21,7 +21,7 @@ from youtube_dl.extractor import (
NPOIE,
ComedyCentralIE,
NRKTVIE,
RaiTVIE,
RaiPlayIE,
VikiIE,
ThePlatformIE,
ThePlatformFeedIE,
@ -258,9 +258,9 @@ class TestNRKSubtitles(BaseTestSubtitles):
self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2')
class TestRaiSubtitles(BaseTestSubtitles):
url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiTVIE
class TestRaiPlaySubtitles(BaseTestSubtitles):
url = 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiPlayIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True

62
test/test_utils.py
View File

@ -44,6 +44,7 @@ from youtube_dl.utils import (
limit_length,
mimetype2ext,
month_by_name,
multipart_encode,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
@ -338,6 +339,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@ -619,6 +621,16 @@ class TestUtil(unittest.TestCase):
'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_multipart_encode(self):
self.assertEqual(
multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
self.assertEqual(
multipart_encode({'欄位'.encode('utf-8'): '值'.encode('utf-8')}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
self.assertRaises(
ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
def test_dict_get(self):
FALSE_VALUES = {
'none': None,
@ -666,6 +678,14 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('window.cb && window.cb({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('window.cb && cb({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@ -899,6 +919,7 @@ class TestUtil(unittest.TestCase):
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
self.assertEqual(
@ -1069,6 +1090,47 @@ The first line
'''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
<tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
<head>
<styling>
<style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
<style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
<style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
<style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
</styling>
</head>
<body tts:textAlign="center" style="s0">
<div>
<p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
<p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
<p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
<p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:02,080 --> 00:00:05,839
<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
2
00:00:02,080 --> 00:00:05,839
<b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
</font>part 2</font></b>
3
00:00:05,839 --> 00:00:09,560
<u><font color="lime">line 3
part 3</font></u>
4
00:00:09,560 --> 00:00:12,359
<i><u><font color="yellow"><font color="lime">inner
</font>style</font></u></i>
'''
self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])

268
test/test_youtube_chapters.py Normal file
View File

@ -0,0 +1,268 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import expect_value
from youtube_dl.extractor import YoutubeIE
class TestYoutubeChapters(unittest.TestCase):
_TEST_CASES = [
(
# https://www.youtube.com/watch?v=A22oy8dFjqc
# pattern: 00:00 - <title>
'''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
1477,
[{
'start_time': 36,
'end_time': 162,
'title': 'Bohemian Rhapsody',
}, {
'start_time': 162,
'end_time': 413,
'title': 'Radio Ga Ga',
}, {
'start_time': 413,
'end_time': 454,
'title': 'Ay Oh!',
}, {
'start_time': 454,
'end_time': 728,
'title': 'Hammer To Fall',
}, {
'start_time': 728,
'end_time': 963,
'title': 'Crazy Little Thing Called Love',
}, {
'start_time': 963,
'end_time': 1038,
'title': 'We Will Rock You',
}, {
'start_time': 1038,
'end_time': 1272,
'title': 'We Are The Champions',
}, {
'start_time': 1272,
'end_time': 1477,
'title': 'Is This The World We Created...?',
}]
),
(
# https://www.youtube.com/watch?v=ekYlRhALiRQ
# pattern: <num>. <title> 0:00
'1. Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2. Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3. Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4. The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5. Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6. Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
4009,
[{
'start_time': 0,
'end_time': 707,
'title': '1. Those Beaten Paths of Confusion',
}, {
'start_time': 707,
'end_time': 1590,
'title': '2. Beyond the Shadows of Emptiness & Nothingness',
}, {
'start_time': 1590,
'end_time': 2157,
'title': '3. Poison Yourself...With Thought',
}, {
'start_time': 2157,
'end_time': 2672,
'title': '4. The Agents of Transformation',
}, {
'start_time': 2672,
'end_time': 3187,
'title': '5. Drowning in the Pain of Consciousness',
}, {
'start_time': 3187,
'end_time': 4009,
'title': '6. Deny the Disease of Life',
}]
),
(
# https://www.youtube.com/watch?v=WjL4pSzog9w
# pattern: 00:00 <title>
'<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
2705,
[{
'start_time': 0,
'end_time': 428,
'title': 'Christening Unborn Deformities',
}, {
'start_time': 428,
'end_time': 976,
'title': 'Taste of Purity',
}, {
'start_time': 976,
'end_time': 1485,
'title': 'Sculpting Sins of a Universal Tongue',
}, {
'start_time': 1485,
'end_time': 1884,
'title': 'Birth',
}, {
'start_time': 1884,
'end_time': 2275,
'title': 'Neves',
}, {
'start_time': 2275,
'end_time': 2705,
'title': 'Libations in Limbo',
}]
),
(
# https://www.youtube.com/watch?v=o3r1sn-t3is
# pattern: <title> 00:00 <note>
'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a> (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
5640,
[{
'start_time': 45,
'end_time': 266,
'title': 'I-E-A-I-A-I-O',
}, {
'start_time': 266,
'end_time': 331,
'title': 'Suite-Pee (Incomplete)',
}, {
'start_time': 331,
'end_time': 522,
'title': 'Attack (First live performance since 2011)',
}, {
'start_time': 522,
'end_time': 752,
'title': 'Prison Song',
}, {
'start_time': 752,
'end_time': 932,
'title': 'Know (First live performance since 2011)',
}, {
'start_time': 932,
'end_time': 1153,
'title': 'Aerials',
}, {
'start_time': 1153,
'end_time': 1209,
'title': 'Soldier Side - Intro',
}, {
'start_time': 1209,
'end_time': 1472,
'title': 'B.Y.O.B.',
}, {
'start_time': 1472,
'end_time': 1668,
'title': 'Soil',
}, {
'start_time': 1668,
'end_time': 1838,
'title': 'Darts',
}, {
'start_time': 1838,
'end_time': 2105,
'title': 'Radio/Video',
}, {
'start_time': 2105,
'end_time': 2288,
'title': 'Hypnotize',
}, {
'start_time': 2288,
'end_time': 2460,
'title': 'Temper (First live performance since 1999)',
}, {
'start_time': 2460,
'end_time': 2577,
'title': 'CUBErt',
}, {
'start_time': 2577,
'end_time': 2787,
'title': 'Needles',
}, {
'start_time': 2787,
'end_time': 2978,
'title': 'Deer Dance',
}, {
'start_time': 2978,
'end_time': 3085,
'title': 'Bounce',
}, {
'start_time': 3085,
'end_time': 3232,
'title': 'Suggestions',
}, {
'start_time': 3232,
'end_time': 3493,
'title': 'Psycho',
}, {
'start_time': 3493,
'end_time': 3675,
'title': 'Chop Suey!',
}, {
'start_time': 3675,
'end_time': 3854,
'title': 'Lonely Day',
}, {
'start_time': 3854,
'end_time': 4090,
'title': 'Question!',
}, {
'start_time': 4090,
'end_time': 4420,
'title': 'Lost in Hollywood',
}, {
'start_time': 4420,
'end_time': 4577,
'title': 'Vicinity of Obscenity (First live performance since 2012)',
}, {
'start_time': 4577,
'end_time': 4802,
'title': 'Forest',
}, {
'start_time': 4802,
'end_time': 5037,
'title': 'Cigaro',
}, {
'start_time': 5037,
'end_time': 5273,
'title': 'Toxicity (with Chino Moreno)',
}, {
'start_time': 5273,
'end_time': 5640,
'title': 'Sugar',
}]
),
(
# https://www.youtube.com/watch?v=PkYLQbsqCE8
# pattern: <num> - <title> [<latinized title>] 0:00:00
'''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
1138,
[{
'start_time': 0,
'end_time': 490,
'title': '1 - Во прах [Vo prakh]',
}, {
'start_time': 490,
'end_time': 870,
'title': '2 - Искупление [Iskupleniye]',
}, {
'start_time': 870,
'end_time': 1138,
'title': '3 - Из серпов луны...[Iz serpov luny]',
}]
),
]
def test_youtube_chapters(self):
for description, duration, expected_chapters in self._TEST_CASES:
ie = YoutubeIE()
expect_value(
self, ie._extract_chapters(description, duration),
expected_chapters, None)
if __name__ == '__main__':
unittest.main()

14
test/testdata/m3u8/pluzz_francetv_11507.m3u8 vendored Normal file
View File

@ -0,0 +1,14 @@
#EXTM3U
#EXT-X-VERSION:5
#EXT-X-MEDIA:TYPE=SUBTITLES,GROUP-ID="subs",NAME="Francais",DEFAULT=NO,FORCED=NO,URI="http://replayftv-pmd.francetv.fr/subtitles/2017/16/156589847-1492488987.m3u8",LANGUAGE="fra"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="aac",LANGUAGE="fra",NAME="Francais",DEFAULT=YES, AUTOSELECT=YES
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=180000,RESOLUTION=256x144,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_0_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=303000,RESOLUTION=320x180,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_1_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=575000,RESOLUTION=512x288,CODECS="avc1.66.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_2_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=831000,RESOLUTION=704x396,CODECS="avc1.77.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_3_av.m3u8?null=0
#EXT-X-STREAM-INF:SUBTITLES="subs",AUDIO="aac",PROGRAM-ID=1,BANDWIDTH=1467000,RESOLUTION=1024x576,CODECS="avc1.77.30, mp4a.40.2"
http://replayftv-vh.akamaihd.net/i/streaming-adaptatif_france-dom-tom/2017/S16/J2/156589847-58f59130c1f52-,standard1,standard2,standard3,standard4,standard5,.mp4.csmil/index_4_av.m3u8?null=0

16
test/testdata/m3u8/teamcoco_11995.m3u8 vendored Normal file
View File

@ -0,0 +1,16 @@
#EXTM3U
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-0",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-160k_v4.m3u8"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio-1",NAME="Default",AUTOSELECT=YES,DEFAULT=YES,URI="hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=37862000,CODECS="avc1.4d001f",URI="hls/CONAN_020217_Highlight_show-2m_iframe.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=18750000,CODECS="avc1.4d001e",URI="hls/CONAN_020217_Highlight_show-1m_iframe.m3u8"
#EXT-X-I-FRAME-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=6535000,CODECS="avc1.42001e",URI="hls/CONAN_020217_Highlight_show-400k_iframe.m3u8"
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=2374000,RESOLUTION=1024x576,CODECS="avc1.4d001f,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-2m_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1205000,RESOLUTION=640x360,CODECS="avc1.4d001e,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-1m_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=522000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.2",AUDIO="audio-0"
hls/CONAN_020217_Highlight_show-400k_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=413000,RESOLUTION=400x224,CODECS="avc1.42001e,mp4a.40.5",AUDIO="audio-1"
hls/CONAN_020217_Highlight_show-400k_v4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=71000,CODECS="mp4a.40.5",AUDIO="audio-1"
hls/CONAN_020217_Highlight_show-audio-64k_v4.m3u8

13
test/testdata/m3u8/toggle_mobile_12211.m3u8 vendored Normal file
View File

@ -0,0 +1,13 @@
#EXTM3U
#EXT-X-VERSION:4
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="eng",NAME="English",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_sa2ntrdg/name/a.mp4/index.m3u8"
#EXT-X-MEDIA:TYPE=AUDIO,GROUP-ID="audio",LANGUAGE="und",NAME="Undefined",URI="http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_r7y0nitg/name/a.mp4/index.m3u8"
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=155648,RESOLUTION=320x180,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_qlk9hlzr/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=502784,RESOLUTION=480x270,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/2/pv/1/flavorId/0_oefackmi/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=827392,RESOLUTION=640x360,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_vyg9pj7k/name/a.mp4/index.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1396736,RESOLUTION=854x480,AUDIO="audio"
http://k.toggle.sg/fhls/p/2082311/sp/208231100/serveFlavor/entryId/0_89q6e8ku/v/12/pv/1/flavorId/0_50n4psvx/name/a.mp4/index.m3u8

20
test/testdata/m3u8/twitch_vod.m3u8 vendored Normal file
View File

@ -0,0 +1,20 @@
#EXTM3U
#EXT-X-TWITCH-INFO:ORIGIN="s3",CLUSTER="edgecast_vod",REGION="EU",MANIFEST-CLUSTER="edgecast_vod",USER-IP="109.171.17.81"
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="chunked",NAME="Source",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=3214134,CODECS="avc1.100.31,mp4a.40.2",RESOLUTION="1280x720",VIDEO="chunked"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/chunked/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="high",NAME="High",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1603789,CODECS="avc1.42C01F,mp4a.40.2",RESOLUTION="1280x720",VIDEO="high"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/high/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="medium",NAME="Medium",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=893387,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="852x480",VIDEO="medium"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/medium/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="low",NAME="Low",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=628347,CODECS="avc1.42C01E,mp4a.40.2",RESOLUTION="640x360",VIDEO="low"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/low/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="mobile",NAME="Mobile",AUTOSELECT=YES,DEFAULT=YES
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=280474,CODECS="avc1.42C00D,mp4a.40.2",RESOLUTION="400x226",VIDEO="mobile"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/mobile/index-muted-HM49I092CC.m3u8
#EXT-X-MEDIA:TYPE=VIDEO,GROUP-ID="audio_only",NAME="Audio Only",AUTOSELECT=NO,DEFAULT=NO
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=182725,CODECS="mp4a.40.2",VIDEO="audio_only"
https://vod.edgecast.hls.ttvnw.net/e5da31ab49_riotgames_15001215120_261543898/audio_only/index-muted-HM49I092CC.m3u8

10
test/testdata/m3u8/vidio.m3u8 vendored Normal file
View File

@ -0,0 +1,10 @@
#EXTM3U
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=300000,RESOLUTION=480x270,NAME="270p 3G"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b300.mp4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=600000,RESOLUTION=640x360,NAME="360p SD"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b600.mp4.m3u8
#EXT-X-STREAM-INF:PROGRAM-ID=1,BANDWIDTH=1200000,RESOLUTION=1280x720,NAME="720p HD"
https://cdn1-a.production.vidio.static6.com/uploads/165683/dj_ambred-4383-b1200.mp4.m3u8

26
youtube_dl/YoutubeDL.py
View File

@ -370,10 +370,10 @@ class YoutubeDL(object):
else:
raise
if (sys.version_info >= (3,) and sys.platform != 'win32' and
if (sys.platform != 'win32' and
sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and
not params.get('restrictfilenames', False)):
# On Python 3, the Unicode filesystem API will throw errors (#1474)
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
'cannot encode all characters. '
@ -640,7 +640,7 @@ class YoutubeDL(object):
NUMERIC_FIELDS = set((
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'upload_year', 'upload_month', 'upload_day',
'timestamp', 'upload_year', 'upload_month', 'upload_day',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'average_rating', 'comment_count', 'age_limit',
'start_time', 'end_time',
@ -672,8 +672,7 @@ class YoutubeDL(object):
FORMAT_RE.format(numeric_field),
r'%({0})s'.format(numeric_field), outtmpl)
tmpl = expand_path(outtmpl)
filename = tmpl % template_dict
filename = expand_path(outtmpl % template_dict)
# Temporary fix for #4787
# 'Treat' all problem characters by passing filename through preferredencoding
# to workaround encoding issues with subprocess on python2 @ Windows
@ -837,6 +836,12 @@ class YoutubeDL(object):
ie_result['url'], ie_key=ie_result.get('ie_key'),
extra_info=extra_info, download=False, process=False)
# extract_info may return None when ignoreerrors is enabled and
# extraction failed with an error, don't crash and return early
# in this case
if not info:
return info
force_properties = dict(
(k, v) for k, v in ie_result.items() if v is not None)
for f in ('_type', 'url', 'ie_key'):
@ -845,11 +850,18 @@ class YoutubeDL(object):
new_result = info.copy()
new_result.update(force_properties)
assert new_result.get('_type') != 'url_transparent'
# Extracted info may not be a video result (i.e.
# info.get('_type', 'video') != video) but rather an url or
# url_transparent. In such cases outer metadata (from ie_result)
# should be propagated to inner one (info). For this to happen
# _type of info should be overridden with url_transparent. This
# fixes issue from https://github.com/rg3/youtube-dl/pull/11163.
if new_result.get('_type') == 'url':
new_result['_type'] = 'url_transparent'
return self.process_ie_result(
new_result, download=download, extra_info=extra_info)
elif result_type == 'playlist' or result_type == 'multi_video':
elif result_type in ('playlist', 'multi_video'):
# We process each entry in the playlist
playlist = ie_result.get('title') or ie_result.get('id')
self.to_screen('[download] Downloading playlist: %s' % playlist)

1
youtube_dl/__init__.py
View File

@ -343,6 +343,7 @@ def _real_main(argv=None):
'retries': opts.retries,
'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'keep_fragments': opts.keep_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,

2
youtube_dl/compat.py
View File

@ -2692,7 +2692,7 @@ else:
userhome = pwent.pw_dir
userhome = userhome.rstrip('/')
return (userhome + path[i:]) or '/'
elif compat_os_name == 'nt' or compat_os_name == 'ce':
elif compat_os_name in ('nt', 'ce'):
def compat_expanduser(path):
"""Expand ~ and ~user constructs.

32
youtube_dl/downloader/common.py
View File

@ -187,6 +187,9 @@ class FileDownloader(object):
return filename[:-len('.part')]
return filename
def ytdl_filename(self, filename):
return filename + '.ytdl'
def try_rename(self, old_filename, new_filename):
try:
if old_filename == new_filename:
@ -327,21 +330,22 @@ class FileDownloader(object):
os.path.exists(encodeFilename(filename))
)
continuedl_and_exists = (
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
)
if not hasattr(filename, 'write'):
continuedl_and_exists = (
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
)
# Check file already present
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
'status': 'finished',
'total_bytes': os.path.getsize(encodeFilename(filename)),
})
return True
# Check file already present
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,
'status': 'finished',
'total_bytes': os.path.getsize(encodeFilename(filename)),
})
return True
min_sleep_interval = self.params.get('sleep_interval')
if min_sleep_interval:

43
youtube_dl/downloader/dash.py
View File

@ -1,13 +1,7 @@
from __future__ import unicode_literals
import os
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
class DashSegmentsFD(FragmentFD):
@ -28,31 +22,24 @@ class DashSegmentsFD(FragmentFD):
self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
def process_segment(segment, tmp_filename, num):
segment_url = segment['url']
segment_name = 'Frag%d' % num
target_filename = '%s-%s' % (tmp_filename, segment_name)
frag_index = 0
for i, segment in enumerate(segments):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
# In DASH, the first segment contains necessary headers to
# generate a valid MP4 file, so always abort for the first segment
fatal = num == 0 or not skip_unavailable_fragments
fatal = i == 0 or not skip_unavailable_fragments
count = 0
while count <= fragment_retries:
try:
success = ctx['dl'].download(target_filename, {
'url': segment_url,
'http_headers': info_dict.get('http_headers'),
})
success, frag_content = self._download_fragment(ctx, segment['url'], info_dict)
if not success:
return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
ctx['dest_stream'].write(down.read())
down.close()
segments_filenames.append(target_sanitized)
self._append_fragment(ctx, frag_content)
break
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
@ -63,22 +50,14 @@ class DashSegmentsFD(FragmentFD):
# HTTP error.
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries)
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
if not fatal:
self.report_skip_fragment(segment_name)
return True
self.report_skip_fragment(frag_index)
continue
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
return True
for i, segment in enumerate(segments):
if not process_segment(segment, ctx['tmpfilename'], i):
return False
self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True

17
youtube_dl/downloader/external.py
View File

@ -29,7 +29,17 @@ class ExternalFD(FileDownloader):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
retval = self._call_downloader(tmpfilename, info_dict)
try:
retval = self._call_downloader(tmpfilename, info_dict)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
raise
# Live stream downloading cancellation should be considered as
# correct and expected termination thus all postprocessing
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
@ -202,6 +212,11 @@ class FFmpegFD(ExternalFD):
args = [ffpp.executable, '-y']
for log_level in ('quiet', 'verbose'):
if self.params.get(log_level, False):
args += ['-loglevel', log_level]
break
seekable = info_dict.get('_seekable')
if seekable is not None:
# setting -seekable prevents ffmpeg from guessing if the server

33
youtube_dl/downloader/f4m.py
View File

@ -3,7 +3,6 @@ from __future__ import division, unicode_literals
import base64
import io
import itertools
import os
import time
from .fragment import FragmentFD
@ -16,9 +15,7 @@ from ..compat import (
compat_struct_unpack,
)
from ..utils import (
encodeFilename,
fix_xml_ampersands,
sanitize_open,
xpath_text,
)
@ -366,17 +363,21 @@ class F4mFD(FragmentFD):
dest_stream = ctx['dest_stream']
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
if ctx['complete_frags_downloaded_bytes'] == 0:
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
base_url_parsed = compat_urllib_parse_urlparse(base_url)
self._start_frag_download(ctx)
frags_filenames = []
frag_index = 0
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
query = []
if base_url_parsed.query:
@ -386,17 +387,10 @@ class F4mFD(FragmentFD):
if info_dict.get('extra_param_to_segment_url'):
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {
'url': url_parsed.geturl(),
'http_headers': info_dict.get('http_headers'),
})
success, down_data = self._download_fragment(ctx, url_parsed.geturl(), info_dict)
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
down_data = down.read()
down.close()
reader = FlvReader(down_data)
while True:
try:
@ -411,12 +405,8 @@ class F4mFD(FragmentFD):
break
raise
if box_type == b'mdat':
dest_stream.write(box_data)
self._append_fragment(ctx, box_data)
break
if live:
os.remove(encodeFilename(frag_sanitized))
else:
frags_filenames.append(frag_sanitized)
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
@ -436,7 +426,4 @@ class F4mFD(FragmentFD):
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True

122
youtube_dl/downloader/fragment.py
View File

@ -2,6 +2,7 @@ from __future__ import division, unicode_literals
import os
import time
import json
from .common import FileDownloader
from .http import HttpFD
@ -28,15 +29,37 @@ class FragmentFD(FileDownloader):
and hlsnative only)
skip_unavailable_fragments:
Skip unavailable fragments (DASH and hlsnative only)
keep_fragments: Keep downloaded fragments on disk after downloading is
finished
For each incomplete fragment download youtube-dl keeps on disk a special
bookkeeping file with download state and metadata (in future such files will
be used for any incomplete download handled by youtube-dl). This file is
used to properly handle resuming, check download file consistency and detect
potential errors. The file has a .ytdl extension and represents a standard
JSON file of the following format:
extractor:
Dictionary of extractor related data. TBD.
downloader:
Dictionary of downloader related data. May contain following data:
current_fragment:
Dictionary with current (being downloaded) fragment data:
index: 0-based index of current fragment among all fragments
fragment_count:
Total count of fragments
This feature is experimental and file format may change in future.
"""
def report_retry_fragment(self, err, fragment_name, count, retries):
def report_retry_fragment(self, err, frag_index, count, retries):
self.to_screen(
'[download] Got server HTTP error: %s. Retrying fragment %s (attempt %d of %s)...'
% (error_to_compat_str(err), fragment_name, count, self.format_retries(retries)))
'[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s)...'
% (error_to_compat_str(err), frag_index, count, self.format_retries(retries)))
def report_skip_fragment(self, fragment_name):
self.to_screen('[download] Skipping fragment %s...' % fragment_name)
def report_skip_fragment(self, frag_index):
self.to_screen('[download] Skipping fragment %d...' % frag_index)
def _prepare_url(self, info_dict, url):
headers = info_dict.get('http_headers')
@ -46,6 +69,51 @@ class FragmentFD(FileDownloader):
self._prepare_frag_download(ctx)
self._start_frag_download(ctx)
@staticmethod
def __do_ytdl_file(ctx):
return not ctx['live'] and not ctx['tmpfilename'] == '-'
def _read_ytdl_file(self, ctx):
stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'r')
ctx['fragment_index'] = json.loads(stream.read())['downloader']['current_fragment']['index']
stream.close()
def _write_ytdl_file(self, ctx):
frag_index_stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'w')
downloader = {
'current_fragment': {
'index': ctx['fragment_index'],
},
}
if ctx.get('fragment_count') is not None:
downloader['fragment_count'] = ctx['fragment_count']
frag_index_stream.write(json.dumps({'downloader': downloader}))
frag_index_stream.close()
def _download_fragment(self, ctx, frag_url, info_dict, headers=None):
fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], ctx['fragment_index'])
success = ctx['dl'].download(fragment_filename, {
'url': frag_url,
'http_headers': headers or info_dict.get('http_headers'),
})
if not success:
return False, None
down, frag_sanitized = sanitize_open(fragment_filename, 'rb')
ctx['fragment_filename_sanitized'] = frag_sanitized
frag_content = down.read()
down.close()
return True, frag_content
def _append_fragment(self, ctx, frag_content):
try:
ctx['dest_stream'].write(frag_content)
finally:
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
os.remove(ctx['fragment_filename_sanitized'])
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
@ -66,11 +134,36 @@ class FragmentFD(FileDownloader):
}
)
tmpfilename = self.temp_name(ctx['filename'])
dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb')
open_mode = 'wb'
resume_len = 0
# Establish possible resume length
if os.path.isfile(encodeFilename(tmpfilename)):
open_mode = 'ab'
resume_len = os.path.getsize(encodeFilename(tmpfilename))
# Should be initialized before ytdl file check
ctx.update({
'tmpfilename': tmpfilename,
'fragment_index': 0,
})
if self.__do_ytdl_file(ctx):
if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
self._read_ytdl_file(ctx)
else:
self._write_ytdl_file(ctx)
if ctx['fragment_index'] > 0:
assert resume_len > 0
dest_stream, tmpfilename = sanitize_open(tmpfilename, open_mode)
ctx.update({
'dl': dl,
'dest_stream': dest_stream,
'tmpfilename': tmpfilename,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': resume_len,
})
def _start_frag_download(self, ctx):
@ -79,9 +172,9 @@ class FragmentFD(FileDownloader):
# hook
state = {
'status': 'downloading',
'downloaded_bytes': 0,
'frag_index': 0,
'frag_count': total_frags,
'downloaded_bytes': ctx['complete_frags_downloaded_bytes'],
'fragment_index': ctx['fragment_index'],
'fragment_count': total_frags,
'filename': ctx['filename'],
'tmpfilename': ctx['tmpfilename'],
}
@ -89,8 +182,6 @@ class FragmentFD(FileDownloader):
start = time.time()
ctx.update({
'started': start,
# Total complete fragments downloaded so far in bytes
'complete_frags_downloaded_bytes': 0,
# Amount of fragment's bytes downloaded by the time of the previous
# frag progress hook invocation
'prev_frag_downloaded_bytes': 0,
@ -106,11 +197,12 @@ class FragmentFD(FileDownloader):
if not ctx['live']:
estimated_size = (
(ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags)
(state['fragment_index'] + 1) * total_frags)
state['total_bytes_estimate'] = estimated_size
if s['status'] == 'finished':
state['frag_index'] += 1
state['fragment_index'] += 1
ctx['fragment_index'] = state['fragment_index']
state['downloaded_bytes'] += frag_total_bytes - ctx['prev_frag_downloaded_bytes']
ctx['complete_frags_downloaded_bytes'] = state['downloaded_bytes']
ctx['prev_frag_downloaded_bytes'] = 0
@ -132,6 +224,10 @@ class FragmentFD(FileDownloader):
def _finish_frag_download(self, ctx):
ctx['dest_stream'].close()
if self.__do_ytdl_file(ctx):
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
if os.path.isfile(ytdl_filename):
os.remove(ytdl_filename)
elapsed = time.time() - ctx['started']
self.try_rename(ctx['tmpfilename'], ctx['filename'])
fsize = os.path.getsize(encodeFilename(ctx['filename']))

51
youtube_dl/downloader/hls.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import os.path
import re
import binascii
try:
@ -18,8 +17,6 @@ from ..compat import (
compat_struct_pack,
)
from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes,
update_url_query,
)
@ -34,7 +31,7 @@ class HlsFD(FragmentFD):
def can_download(manifest, info_dict):
UNSUPPORTED_FEATURES = (
r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)', # encrypted streams [1]
r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
# r'#EXT-X-BYTERANGE', # playlists composed of byte ranges of media files [2]
# Live streams heuristic does not always work (e.g. geo restricted to Germany
# http://hls-geo.daserste.de/i/videoportal/Film/c_620000/622873/format,716451,716457,716450,716458,716459,.mp4.csmil/index_4_av.m3u8?null=0)
@ -52,7 +49,9 @@ class HlsFD(FragmentFD):
# 4. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.5
)
check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
check_results.append(can_decrypt_frag or '#EXT-X-KEY:METHOD=AES-128' not in manifest)
is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
check_results.append(can_decrypt_frag or not is_aes128_enc)
check_results.append(not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest))
check_results.append(not info_dict.get('is_live'))
return all(check_results)
@ -100,31 +99,31 @@ class HlsFD(FragmentFD):
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
frags_filenames = []
byte_range = {}
frag_index = 0
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
frag_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
frag_name = 'Frag%d' % i
frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
count = 0
headers = info_dict.get('http_headers', {})
if byte_range:
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'])
while count <= fragment_retries:
try:
success = ctx['dl'].download(frag_filename, {
'url': frag_url,
'http_headers': info_dict.get('http_headers'),
})
success, frag_content = self._download_fragment(
ctx, frag_url, info_dict, headers)
if not success:
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
break
except compat_urllib_error.HTTPError as err:
# Unavailable (possibly temporary) fragments may be served.
@ -133,28 +132,29 @@ class HlsFD(FragmentFD):
# https://github.com/rg3/youtube-dl/issues/10448).
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_name, count, fragment_retries)
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
i += 1
media_sequence += 1
self.report_skip_fragment(frag_name)
self.report_skip_fragment(frag_index)
continue
self.report_error(
'giving up after %s fragment retries' % fragment_retries)
return False
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(decrypt_info['URI']).read()
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
ctx['dest_stream'].write(frag_content)
frags_filenames.append(frag_sanitized)
self._append_fragment(ctx, frag_content)
# We only download the first fragment during the test
if test:
break
i += 1
media_sequence += 1
elif line.startswith('#EXT-X-KEY'):
decrypt_url = decrypt_info.get('URI')
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
@ -164,13 +164,18 @@ class HlsFD(FragmentFD):
man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
elif line.startswith('#EXT-X-BYTERANGE'):
splitted_byte_range = line[17:].split('@')
sub_range_start = int(splitted_byte_range[1]) if len(splitted_byte_range) == 2 else byte_range['end']
byte_range = {
'start': sub_range_start,
'end': sub_range_start + int(splitted_byte_range[0]),
}
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True

34
youtube_dl/downloader/ism.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import os
import time
import struct
import binascii
@ -8,10 +7,6 @@ import io
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import (
sanitize_open,
encodeFilename,
)
u8 = struct.Struct(b'>B')
@ -225,50 +220,39 @@ class IsmFD(FragmentFD):
self._prepare_and_start_frag_download(ctx)
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
track_written = False
frag_index = 0
for i, segment in enumerate(segments):
segment_url = segment['url']
segment_name = 'Frag%d' % i
target_filename = '%s-%s' % (ctx['tmpfilename'], segment_name)
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
count = 0
while count <= fragment_retries:
try:
success = ctx['dl'].download(target_filename, {
'url': segment_url,
'http_headers': info_dict.get('http_headers'),
})
success, frag_content = self._download_fragment(ctx, segment['url'], info_dict)
if not success:
return False
down, target_sanitized = sanitize_open(target_filename, 'rb')
down_data = down.read()
if not track_written:
tfhd_data = extract_box_data(down_data, [b'moof', b'traf', b'tfhd'])
tfhd_data = extract_box_data(frag_content, [b'moof', b'traf', b'tfhd'])
info_dict['_download_params']['track_id'] = u32.unpack(tfhd_data[4:8])[0]
write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
track_written = True
ctx['dest_stream'].write(down_data)
down.close()
segments_filenames.append(target_sanitized)
self._append_fragment(ctx, frag_content)
break
except compat_urllib_error.HTTPError as err:
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, segment_name, count, fragment_retries)
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
self.report_skip_fragment(segment_name)
self.report_skip_fragment(frag_index)
continue
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
self._finish_frag_download(ctx)
for segment_file in segments_filenames:
os.remove(encodeFilename(segment_file))
return True

2
youtube_dl/downloader/rtmp.py
View File

@ -169,7 +169,7 @@ class RtmpFD(FileDownloader):
self.report_error('[rtmpdump] Could not connect to RTMP server.')
return False
while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
while retval in (RD_INCOMPLETE, RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed

13
youtube_dl/extractor/abcnews.py
View File

@ -12,7 +12,15 @@ from ..compat import compat_urlparse
class AbcNewsVideoIE(AMPIE):
IE_NAME = 'abcnews:video'
_VALID_URL = r'https?://abcnews\.go\.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
_VALID_URL = r'''(?x)
https?://
abcnews\.go\.com/
(?:
[^/]+/video/(?P<display_id>[0-9a-z-]+)-|
video/embed\?.*?\bid=
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
@ -29,6 +37,9 @@ class AbcNewsVideoIE(AMPIE):
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abcnews.go.com/video/embed?id=46979033',
'only_matching': True,
}, {
'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
'only_matching': True,

147
youtube_dl/extractor/adn.py Normal file
View File

@ -0,0 +1,147 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import json
import os
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt
from ..compat import compat_ord
from ..utils import (
bytes_to_intlist,
ExtractorError,
float_or_none,
intlist_to_bytes,
srt_subtitles_timecode,
strip_or_none,
urljoin,
)
class ADNIE(InfoExtractor):
IE_DESC = 'Anime Digital Network'
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'md5': 'e497370d847fd79d9d4c74be55575c7a',
'info_dict': {
'id': '7778',
'ext': 'mp4',
'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
}
}
_BASE_URL = 'http://animedigitalnetwork.fr'
def _get_subtitles(self, sub_path, video_id):
if not sub_path:
return None
enc_subtitles = self._download_webpage(
urljoin(self._BASE_URL, sub_path),
video_id, fatal=False, headers={
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
})
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(base64.b64decode(enc_subtitles[24:])),
bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'),
bytes_to_intlist(base64.b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
None, fatal=False)
if not subtitles_json:
return None
subtitles = {}
for sub_lang, sub in subtitles_json.items():
srt = ''
for num, current in enumerate(sub):
start, end, text = (
float_or_none(current.get('startTime')),
float_or_none(current.get('endTime')),
current.get('text'))
if start is None or end is None or text is None:
continue
srt += os.linesep.join(
(
'%d' % num,
'%s --> %s' % (
srt_subtitles_timecode(start),
srt_subtitles_timecode(end)),
text,
os.linesep,
))
if sub_lang == 'vostf':
sub_lang = 'fr'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
}, {
'ext': 'srt',
'data': srt,
}])
return subtitles
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_config = self._parse_json(self._search_regex(
r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
video_info = {}
video_info_str = self._search_regex(
r'videoInfo\s*=\s*({.+});', webpage,
'video info', fatal=False)
if video_info_str:
video_info = self._parse_json(
video_info_str, video_id, fatal=False) or {}
options = player_config.get('options') or {}
metas = options.get('metas') or {}
title = metas.get('title') or video_info['title']
links = player_config.get('links') or {}
if not links:
links_url = player_config['linksurl']
links_data = self._download_json(urljoin(
self._BASE_URL, links_url), video_id)
links = links_data.get('links') or {}
formats = []
for format_id, qualities in links.items():
if not isinstance(qualities, dict):
continue
for load_balancer_url in qualities.values():
load_balancer_data = self._download_json(
load_balancer_url, video_id, fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
continue
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False)
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
formats.extend(m3u8_formats)
error = options.get('error')
if not formats and error:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
'thumbnail': video_info.get('image'),
'formats': formats,
'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
'episode': metas.get('subtitle') or video_info.get('videoTitle'),
'series': video_info.get('playlistTitle'),
}

74
youtube_dl/extractor/adobepass.py
View File

@ -36,11 +36,21 @@ MSO_INFO = {
'username_field': 'Ecom_User_ID',
'password_field': 'Ecom_Password',
},
'Brighthouse': {
'name': 'Bright House Networks | Spectrum',
'username_field': 'j_username',
'password_field': 'j_password',
},
'Charter_Direct': {
'name': 'Charter Spectrum',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
},
'Verizon': {
'name': 'Verizon FiOS',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
},
'thr030': {
'name': '3 Rivers Communications'
},
@ -1303,6 +1313,12 @@ class AdobePassIE(InfoExtractor):
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MVPD_CACHE = 'ap-mvpd'
def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {})
headers.update(self.geo_verification_headers())
kwargs['headers'] = headers
return super(AdobePassIE, self)._download_webpage_handle(*args, **kwargs)
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
@ -1384,40 +1400,72 @@ class AdobePassIE(InfoExtractor):
# Comcast page flow varies by video site and whether you
# are on Comcast's network.
provider_redirect_page, urlh = provider_redirect_page_res
# Check for Comcast auto login
if 'automatically signing you in' in provider_redirect_page:
oauth_redirect_url = self._html_search_regex(
r'window\.location\s*=\s*[\'"]([^\'"]+)',
provider_redirect_page, 'oauth redirect')
# Just need to process the request. No useful data comes back
self._download_webpage(
oauth_redirect_url, video_id, 'Confirming auto login')
else:
if '<form name="signin"' in provider_redirect_page:
# already have the form, just fill it
provider_login_page_res = provider_redirect_page_res
elif 'http-equiv="refresh"' in provider_redirect_page:
# redirects to the login page
oauth_redirect_url = self._html_search_regex(
r'content="0;\s*url=([^\'"]+)',
provider_redirect_page, 'meta refresh redirect')
provider_login_page_res = self._download_webpage_handle(
oauth_redirect_url,
video_id, 'Downloading Provider Login Page')
oauth_redirect_url, video_id,
'Downloading Provider Login Page')
else:
provider_login_page_res = post_form(
provider_redirect_page_res, 'Downloading Provider Login Page')
provider_redirect_page_res,
'Downloading Provider Login Page')
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {
mso_info.get('username_field', 'username'): username,
mso_info.get('password_field', 'password'): password,
})
mvpd_confirm_page_res = post_form(
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
mvpd_confirm_page, urlh = mvpd_confirm_page_res
if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Verizon':
# In general, if you're connecting from a Verizon-assigned IP,
# you will not actually pass your credentials.
provider_redirect_page, urlh = provider_redirect_page_res
if 'Please wait ...' in provider_redirect_page:
saml_redirect_url = self._html_search_regex(
r'self\.parent\.location=(["\'])(?P<url>.+?)\1',
provider_redirect_page,
'SAML Redirect URL', group='url')
saml_login_page = self._download_webpage(
saml_redirect_url, video_id,
'Downloading SAML Login Page')
else:
saml_login_page_res = post_form(
provider_redirect_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
saml_login_page, urlh = saml_login_page_res
if 'Please try again.' in saml_login_page:
raise ExtractorError(
'We\'re sorry, but either the User ID or Password entered is not correct.')
saml_login_url = self._search_regex(
r'xmlHttp\.open\("POST"\s*,\s*(["\'])(?P<url>.+?)\1',
saml_login_page, 'SAML Login URL', group='url')
saml_response_json = self._download_json(
saml_login_url, video_id, 'Downloading SAML Response',
headers={'Content-Type': 'text/xml'})
self._download_webpage(
saml_response_json['targetValue'], video_id,
'Confirming Login', data=urlencode_postdata({
'SAMLResponse': saml_response_json['SAMLResponse'],
'RelayState': saml_response_json['RelayState']
}), headers={
'Content-Type': 'application/x-www-form-urlencoded'
})
else:
# Normal, non-Comcast flow
provider_login_page_res = post_form(
provider_redirect_page_res, 'Downloading Provider Login Page')
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', {

285
youtube_dl/extractor/adultswim.py
View File

@ -5,91 +5,52 @@ import re
from .turner import TurnerBaseIE
from ..utils import (
ExtractorError,
int_or_none,
strip_or_none,
)
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
_TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'playlist': [
{
'md5': '247572debc75c7652f253c8daa51a14d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 1',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
{
'md5': '77b0e037a4b20ec6b98671c4c379f48d',
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
'ext': 'flv',
'title': 'Rick and Morty - Pilot Part 4',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
},
],
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'ext': 'mp4',
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
},
'skip': 'This video is only available for registered users',
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
{
'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog-0',
'ext': 'flv',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}
],
'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'playlist': [
{
'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
}
],
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
'timestamp': 1493267400,
'upload_date': '20170427',
},
'params': {
# m3u8 download
'skip_download': True,
}
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'ext': 'mp4',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
'upload_date': '20080124',
'timestamp': 1201150800,
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
# heroMetadata.trailer
'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
'info_dict': {
'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
'ext': 'mp4',
'title': 'Decker - Inside Decker: A New Hero',
'description': 'md5:c916df071d425d62d70c86d4399d3ee0',
'duration': 249.008,
'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
'timestamp': 1469480460,
'upload_date': '20160725',
},
'params': {
# m3u8 download
@ -97,136 +58,102 @@ class AdultSwimIE(TurnerBaseIE):
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.adultswim.com/videos/toonami/friday-october-14th-2016/',
'url': 'http://www.adultswim.com/videos/attack-on-titan',
'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig',
'title': 'Toonami - Friday, October 14th, 2016',
'description': 'md5:99892c96ffc85e159a428de85c30acde',
'id': 'b7A69dzfRzuaXIECdxW8XQ',
'title': 'Attack on Titan',
'description': 'md5:6c8e003ea0777b47013e894767f5e114',
},
'playlist_mincount': 12,
}, {
'url': 'http://www.adultswim.com/videos/streams/williams-stream',
'info_dict': {
'id': 'd8DEBj7QRfetLsRgFnGEyg',
'ext': 'mp4',
'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'description': 'original programming',
},
'playlist': [{
'md5': '',
'info_dict': {
'id': 'eYiLsKVgQ6qTC6agD67Sig',
'ext': 'mp4',
'title': 'Toonami - Friday, October 14th, 2016',
'description': 'md5:99892c96ffc85e159a428de85c30acde',
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
@staticmethod
def find_video_info(collection, slug):
for video in collection.get('videos'):
if video.get('slug') == slug:
return video
@staticmethod
def find_collection_by_linkURL(collections, linkURL):
for collection in collections:
if collection.get('linkURL') == linkURL:
return collection
@staticmethod
def find_collection_containing_video(collections, slug):
for collection in collections:
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
return None, None
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
show_path = mobj.group('show_path')
episode_path = mobj.group('episode_path')
is_playlist = True if mobj.group('is_playlist') else False
show_path, episode_path = re.match(self._VALID_URL, url).groups()
display_id = episode_path or show_path
webpage = self._download_webpage(url, display_id)
initial_data = self._parse_json(self._search_regex(
r'AS_INITIAL_DATA(?:__)?\s*=\s*({.+?});',
webpage, 'initial data'), display_id)
webpage = self._download_webpage(url, episode_path)
is_stream = show_path == 'streams'
if is_stream:
if not episode_path:
episode_path = 'live-stream'
# Extract the value of `bootstrappedData` from the Javascript in the page.
bootstrapped_data = self._parse_json(self._search_regex(
r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
video_data = next(stream for stream_path, stream in initial_data['streams'].items() if stream_path == episode_path)
video_id = video_data.get('stream')
# Downloading videos from a /videos/playlist/ URL needs to be handled differently.
# NOTE: We are only downloading one video (the current one) not the playlist
if is_playlist:
collections = bootstrapped_data['playlists']['collections']
collection = self.find_collection_by_linkURL(collections, show_path)
video_info = self.find_video_info(collection, episode_path)
show_title = video_info['showTitle']
segment_ids = [video_info['videoPlaybackID']]
if not video_id:
entries = []
for episode in video_data.get('archiveEpisodes', []):
episode_url = episode.get('url')
if not episode_url:
continue
entries.append(self.url_result(
episode_url, 'AdultSwim', episode.get('id')))
return self.playlist_result(
entries, video_data.get('id'), video_data.get('title'),
strip_or_none(video_data.get('description')))
else:
collections = bootstrapped_data['show']['collections']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
# Video wasn't found in the collections, let's try `slugged_video`.
if video_info is None:
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
if not video_info:
video_info = bootstrapped_data.get(
'heroMetadata', {}).get('trailer', {}).get('video')
if not video_info:
video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
if not video_info:
raise ExtractorError('Unable to find video info')
show_data = initial_data['show']
show = bootstrapped_data['show']
show_title = show['title']
stream = video_info.get('stream')
if stream and stream.get('videoPlaybackID'):
segment_ids = [stream['videoPlaybackID']]
elif video_info.get('clips'):
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
elif video_info.get('videoPlaybackID'):
segment_ids = [video_info['videoPlaybackID']]
elif video_info.get('id'):
segment_ids = [video_info['id']]
else:
if video_info.get('auth') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream or clips')
if not episode_path:
entries = []
for video in show_data.get('videos', []):
slug = video.get('slug')
if not slug:
continue
entries.append(self.url_result(
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
'AdultSwim', video.get('id')))
return self.playlist_result(
entries, show_data.get('id'), show_data.get('title'),
strip_or_none(show_data.get('metadata', {}).get('description')))
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info.get('description')
episode_duration = int_or_none(video_info.get('duration'))
view_count = int_or_none(video_info.get('views'))
video_data = show_data['sluggedVideo']
video_id = video_data['id']
entries = []
for part_num, segment_id in enumerate(segment_ids):
segement_info = self._extract_cvp_info(
'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
segment_id, {
'secure': {
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
},
})
segment_title = '%s - %s' % (show_title, episode_title)
if len(segment_ids) > 1:
segment_title += ' Part %d' % (part_num + 1)
segement_info.update({
'id': segment_id,
'title': segment_title,
'description': episode_description,
info = self._extract_cvp_info(
'http://www.adultswim.com/videos/api/v0/assets?platform=desktop&id=' + video_id,
video_id, {
'secure': {
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
},
}, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': video_data.get('auth'),
})
entries.append(segement_info)
return {
'_type': 'playlist',
'id': episode_id,
'display_id': episode_path,
'entries': entries,
'title': '%s - %s' % (show_title, episode_title),
'description': episode_description,
'duration': episode_duration,
'view_count': view_count,
}
info.update({
'id': video_id,
'display_id': display_id,
'description': info.get('description') or strip_or_none(video_data.get('description')),
})
if not is_stream:
info.update({
'duration': info.get('duration') or int_or_none(video_data.get('duration')),
'timestamp': info.get('timestamp') or int_or_none(video_data.get('launch_date')),
'season_number': info.get('season_number') or int_or_none(video_data.get('season_number')),
'episode': info['title'],
'episode_number': info.get('episode_number') or int_or_none(video_data.get('episode_number')),
})
info['series'] = video_data.get('collection_title') or info.get('series')
if info['series'] and info['series'] != info['title']:
info['title'] = '%s - %s' % (info['series'], info['title'])
return info

40
youtube_dl/extractor/aenetworks.py
View File

@ -23,7 +23,19 @@ class AENetworksBaseIE(ThePlatformIE):
class AENetworksIE(AENetworksBaseIE):
IE_NAME = 'aenetworks'
IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:history|aetv|mylifetime|lifetimemovieclub)\.com|fyi\.tv)/(?:shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?)'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?P<domain>
(?:history|aetv|mylifetime|lifetimemovieclub)\.com|
fyi\.tv
)/
(?:
shows/(?P<show_path>[^/]+(?:/[^/]+){0,2})|
movies/(?P<movie_display_id>[^/]+)(?:/full-movie)?|
specials/(?P<special_display_id>[^/]+)/full-special
)
'''
_TESTS = [{
'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
'md5': 'a97a65f7e823ae10e9244bc5433d5fe6',
@ -65,6 +77,9 @@ class AENetworksIE(AENetworksBaseIE):
}, {
'url': 'https://www.lifetimemovieclub.com/movies/a-killer-among-us',
'only_matching': True
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
}]
_DOMAIN_TO_REQUESTOR_ID = {
'history.com': 'HISTORY',
@ -75,8 +90,8 @@ class AENetworksIE(AENetworksBaseIE):
}
def _real_extract(self, url):
domain, show_path, movie_display_id = re.match(self._VALID_URL, url).groups()
display_id = show_path or movie_display_id
domain, show_path, movie_display_id, special_display_id = re.match(self._VALID_URL, url).groups()
display_id = show_path or movie_display_id or special_display_id
webpage = self._download_webpage(url, display_id)
if show_path:
url_parts = show_path.split('/')
@ -86,10 +101,14 @@ class AENetworksIE(AENetworksBaseIE):
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
elif url_parts_len == 2:
if entries:
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
else:
# single season
url_parts_len = 2
if url_parts_len == 2:
entries = []
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item)
@ -97,7 +116,7 @@ class AENetworksIE(AENetworksBaseIE):
url, episode_attributes['data-canonical'])
entries.append(self.url_result(
episode_url, 'AENetworks',
episode_attributes['data-videoid']))
episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage))
@ -107,7 +126,10 @@ class AENetworksIE(AENetworksBaseIE):
}
video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex(
r"media_url\s*=\s*'([^']+)'", webpage, 'video url')
[r"media_url\s*=\s*'(?P<url>[^']+)'",
r'data-media-url=(?P<url>(?:https?:)?//[^\s>]+)',
r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
webpage, 'video url', group='url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)

142
youtube_dl/extractor/afreecatv.py
View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor
from ..compat import compat_xpath
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
xpath_text,
@ -72,13 +73,70 @@ class AfreecaTVIE(InfoExtractor):
'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
'info_dict': {
'id': '18650793',
'ext': 'flv',
'ext': 'mp4',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '윈아디',
'uploader_id': 'badkids',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
'duration': 107,
},
'params': {
'skip_download': True, # requires rtmpdump
'skip_download': True,
},
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/10481652',
'info_dict': {
'id': '10481652',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!'",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'duration': 6492,
},
'playlist_count': 2,
'playlist': [{
'md5': 'd8b7c174568da61d774ef0203159bf97',
'info_dict': {
'id': '20160502_c4c62b9d_174361386_1',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 1)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 3601,
},
}, {
'md5': '58f2ce7f6044e34439ab2d50612ab02b',
'info_dict': {
'id': '20160502_39e739bb_174361386_2',
'ext': 'mp4',
'title': "BJ유트루와 함께하는 '팅커벨 메이크업!' (part 2)",
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160502',
'duration': 2891,
},
}],
'params': {
'skip_download': True,
},
}, {
# non standard key
'url': 'http://vod.afreecatv.com/PLAYER/STATION/20515605',
'info_dict': {
'id': '20170411_BE689A0E_190960999_1_2_h',
'ext': 'mp4',
'title': '혼자사는여자집',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '♥이슬이',
'uploader_id': 'dasl8121',
'upload_date': '20170411',
'duration': 213,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
@ -94,7 +152,7 @@ class AfreecaTVIE(InfoExtractor):
m = re.match(r'^(?P<upload_date>\d{8})_\w+_(?P<part>\d+)$', key)
if m:
video_key['upload_date'] = m.group('upload_date')
video_key['part'] = m.group('part')
video_key['part'] = int(m.group('part'))
return video_key
def _real_extract(self, url):
@ -109,23 +167,64 @@ class AfreecaTVIE(InfoExtractor):
raise ExtractorError('Specified AfreecaTV video does not exist',
expected=True)
video_url_raw = video_element.text
app, playpath = video_url_raw.split('mp4:')
video_url = video_element.text.strip()
title = xpath_text(video_xml, './track/title', 'title', fatal=True)
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(video_xml, './track/duration',
'duration'))
duration = int_or_none(xpath_text(
video_xml, './track/duration', 'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
return {
common_entry = {
'uploader': uploader,
'uploader_id': uploader_id,
'thumbnail': thumbnail,
}
info = common_entry.copy()
info.update({
'id': video_id,
'title': title,
'duration': duration,
})
if not video_url:
entries = []
file_elements = video_element.findall(compat_xpath('./file'))
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = file_element.text
if not file_url:
continue
key = file_element.get('key', '')
upload_date = self._search_regex(
r'^(\d{8})_', key, 'upload date', default=None)
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
file_info = common_entry.copy()
file_info.update({
'id': format_id,
'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date,
'duration': file_duration,
'formats': formats,
})
entries.append(file_info)
entries_info = info.copy()
entries_info.update({
'_type': 'multi_video',
'entries': entries,
})
return entries_info
info = {
'id': video_id,
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
@ -133,6 +232,21 @@ class AfreecaTVIE(InfoExtractor):
'thumbnail': thumbnail,
}
if determine_ext(video_url) == 'm3u8':
info['formats'] = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
app, playpath = video_url.split('mp4:')
info.update({
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
})
return info
class AfreecaTVGlobalIE(AfreecaTVIE):
IE_NAME = 'afreecatv:global'

28
youtube_dl/extractor/airmozilla.py
View File

@ -15,12 +15,12 @@ class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '2e3e7486ba5d180e829d453875b9b8bf',
'md5': '8d02f53ee39cf006009180e21df1f3ba',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': r're:https?://vid\.ly/(?P<id>[0-9a-z-]+)/poster',
'thumbnail': r're:https?://.*/poster\.jpg',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
@ -34,21 +34,13 @@ class AirMozillaIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
metadata = self._parse_json(jwconfig, video_id)
formats = [{
'url': source['file'],
'ext': source['type'],
'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
'format': source['label'],
'height': int(source['label'].rstrip('p')),
} for source in metadata['playlist'][0]['sources']]
self._sort_formats(formats)
jwconfig = self._parse_json(self._search_regex(
r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
info_dict = self._parse_jwplayer_data(jwconfig, video_id)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
@ -58,17 +50,17 @@ class AirMozillaIE(InfoExtractor):
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
return {
info_dict.update({
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'url': self._og_search_url(webpage),
'display_id': display_id,
'thumbnail': metadata['playlist'][0].get('image'),
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
}
})
return info_dict

9
youtube_dl/extractor/aljazeera.py
View File

@ -4,9 +4,9 @@ from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_VALID_URL = r'https?://(?:www\.)?aljazeera\.com/(?:programmes|video)/.*?/(?P<id>[^/]+)\.html'
_TEST = {
_TESTS = [{
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
'info_dict': {
'id': '3792260579001',
@ -19,7 +19,10 @@ class AlJazeeraIE(InfoExtractor):
},
'add_ie': ['BrightcoveNew'],
'skip': 'Not accessible from Travis CI server',
}
}, {
'url': 'http://www.aljazeera.com/video/news/2017/05/sierra-leone-709-carat-diamond-auctioned-170511100111930.html',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/665003303001/default_default/index.html?videoId=%s'
def _real_extract(self, url):

46
youtube_dl/extractor/allocine.py
View File

@ -2,9 +2,13 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
remove_end,
int_or_none,
qualities,
remove_end,
try_get,
unified_timestamp,
url_basename,
)
@ -22,6 +26,10 @@ class AllocineIE(InfoExtractor):
'title': 'Astérix - Le Domaine des Dieux Teaser VF',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
'thumbnail': r're:http://.*\.jpg',
'duration': 39,
'timestamp': 1404273600,
'upload_date': '20140702',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
@ -33,6 +41,10 @@ class AllocineIE(InfoExtractor):
'title': 'Planes 2 Bande-annonce VF',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': r're:http://.*\.jpg',
'duration': 69,
'timestamp': 1385659800,
'upload_date': '20131128',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
@ -44,6 +56,10 @@ class AllocineIE(InfoExtractor):
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
'thumbnail': r're:http://.*\.jpg',
'duration': 144,
'timestamp': 1397589900,
'upload_date': '20140415',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
@ -69,34 +85,37 @@ class AllocineIE(InfoExtractor):
r'data-model="([^"]+)"', webpage, 'data model', default=None)
if model:
model_data = self._parse_json(model, display_id)
for video_url in model_data['sources'].values():
video = model_data['videos'][0]
title = video['title']
for video_url in video['sources'].values():
video_id, format_id = url_basename(video_url).split('_')[:2]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': video_url,
})
title = model_data['title']
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
title = remove_end(
self._html_search_regex(
r'(?s)<title>(.+?)</title>', webpage, 'title').strip(),
' - AlloCiné')
for key, value in media_data['video'].items():
if not key.endswith('Path'):
continue
format_id = key[:-len('Path')]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': value,
})
title = remove_end(self._html_search_regex(
r'(?s)<title>(.+?)</title>', webpage, 'title'
).strip(), ' - AlloCiné')
duration, view_count, timestamp = [None] * 3
self._sort_formats(formats)
@ -104,7 +123,10 @@ class AllocineIE(InfoExtractor):
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'formats': formats,
}

26
youtube_dl/extractor/amp.py
View File

@ -7,15 +7,19 @@ from ..utils import (
parse_iso8601,
mimetype2ext,
determine_ext,
ExtractorError,
)
class AMPIE(InfoExtractor):
# parse Akamai Adaptive Media Player feed
def _extract_feed_info(self, url):
item = self._download_json(
feed = self._download_json(
url, None, 'Downloading Akamai AMP feed',
'Unable to download Akamai AMP feed')['channel']['item']
'Unable to download Akamai AMP feed')
item = feed.get('channel', {}).get('item')
if not item:
raise ExtractorError('%s said: %s' % (self.IE_NAME, feed['error']))
video_id = item['guid']
@ -30,9 +34,12 @@ class AMPIE(InfoExtractor):
if isinstance(media_thumbnail, dict):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data['@attributes']
thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': self._proto_relative_url(thumbnail['url'], 'http:'),
'url': self._proto_relative_url(thumbnail_url, 'http:'),
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
@ -43,9 +50,14 @@ class AMPIE(InfoExtractor):
if isinstance(media_subtitle, dict):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data['@attributes']
lang = subtitle.get('lang') or 'en'
subtitles[lang] = [{'url': subtitle['href']}]
subtitle = subtitle_data.get('@attributes', {})
subtitle_href = subtitle.get('href')
if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
'url': subtitle_href,
'ext': mimetype2ext(subtitle.get('type')) or determine_ext(subtitle_href),
})
formats = []
media_content = get_media_node('content')

66
youtube_dl/extractor/anvato.py
View File

@ -5,6 +5,7 @@ import base64
import hashlib
import json
import random
import re
import time
from .common import InfoExtractor
@ -16,6 +17,7 @@ from ..utils import (
intlist_to_bytes,
int_or_none,
strip_jsonp,
unescapeHTML,
)
@ -26,6 +28,8 @@ def md5_text(s):
class AnvatoIE(InfoExtractor):
_VALID_URL = r'anvato:(?P<access_key_or_mcp>[^:]+):(?P<id>\d+)'
# Copied from anvplayer.min.js
_ANVACK_TABLE = {
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ',
@ -114,6 +118,22 @@ class AnvatoIE(InfoExtractor):
'nbcu_nbcd_desktop_web_prod_93d8ead38ce2024f8f544b78306fbd15895ae5e6_secure': 'NNemUkySjxLyPTKvZRiGntBIjEyK8uqicjMakIaQ'
}
_MCP_TO_ACCESS_KEY_TABLE = {
'qa': 'anvato_mcpqa_demo_web_stage_18b55e00db5a13faa8d03ae6e41f6f5bcb15b922',
'lin': 'anvato_mcp_lin_web_prod_4c36fbfd4d8d8ecae6488656e21ac6d1ac972749',
'univison': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'uni': 'anvato_mcp_univision_web_prod_37fe34850c99a3b5cdb71dab10a417dd5cdecafa',
'dev': 'anvato_mcp_fs2go_web_prod_c7b90a93e171469cdca00a931211a2f556370d0a',
'sps': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'spsstg': 'anvato_mcp_sps_web_prod_54bdc90dd6ba21710e9f7074338365bba28da336',
'anv': 'anvato_mcp_anv_web_prod_791407490f4c1ef2a4bcb21103e0cb1bcb3352b3',
'gray': 'anvato_mcp_gray_web_prod_4c10f067c393ed8fc453d3930f8ab2b159973900',
'hearst': 'anvato_mcp_hearst_web_prod_5356c3de0fc7c90a3727b4863ca7fec3a4524a99',
'cbs': 'anvato_mcp_cbs_web_prod_02f26581ff80e5bda7aad28226a8d369037f2cbe',
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
}
_ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
def __init__(self, *args, **kwargs):
@ -178,12 +198,7 @@ class AnvatoIE(InfoExtractor):
}
if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
# Not using _extract_m3u8_formats here as individual media
# playlists are also included in published_urls.
if tbr is None:
formats.append(self._m3u8_meta_format(video_url, ext='mp4', m3u8_id='hls'))
continue
else:
if tbr is not None:
a_format.update({
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4',
@ -222,9 +237,42 @@ class AnvatoIE(InfoExtractor):
'subtitles': subtitles,
}
@staticmethod
def _extract_urls(ie, webpage, video_id):
entries = []
for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
anvplayer_data = ie._parse_json(
mobj.group('anvp'), video_id, transform_source=unescapeHTML,
fatal=False)
if not anvplayer_data:
continue
video = anvplayer_data.get('video')
if not isinstance(video, compat_str) or not video.isdigit():
continue
access_key = anvplayer_data.get('accessKey')
if not access_key:
mcp = anvplayer_data.get('mcp')
if mcp:
access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
mcp.lower())
if not access_key:
continue
entries.append(ie.url_result(
'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
video_id=video))
return entries
def _extract_anvato_videos(self, webpage, video_id):
anvplayer_data = self._parse_json(self._html_search_regex(
r'<script[^>]+data-anvp=\'([^\']+)\'', webpage,
'Anvato player data'), video_id)
anvplayer_data = self._parse_json(
self._html_search_regex(
self._ANVP_RE, webpage, 'Anvato player data', group='anvp'),
video_id)
return self._get_anvato_videos(
anvplayer_data['accessKey'], anvplayer_data['video'])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
access_key, video_id = mobj.group('access_key_or_mcp', 'id')
if access_key not in self._ANVACK_TABLE:
access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key]
return self._get_anvato_videos(access_key, video_id)

4
youtube_dl/extractor/appleconnect.py
View File

@ -12,13 +12,13 @@ class AppleConnectIE(InfoExtractor):
_VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P<id>[\w-]+)'
_TEST = {
'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'md5': '10d0f2799111df4cb1c924520ca78f98',
'md5': 'e7c38568a01ea45402570e6029206723',
'info_dict': {
'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
'ext': 'm4v',
'title': 'Energy',
'uploader': 'Drake',
'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20150710',
'timestamp': 1436545535,
},

5
youtube_dl/extractor/appletrailers.py
View File

@ -70,7 +70,8 @@ class AppleTrailersIE(InfoExtractor):
}, {
'url': 'http://trailers.apple.com/trailers/magnolia/blackthorn/',
'info_dict': {
'id': 'blackthorn',
'id': '4489',
'title': 'Blackthorn',
},
'playlist_mincount': 2,
'expected_warnings': ['Unable to download JSON metadata'],
@ -261,7 +262,7 @@ class AppleTrailersSectionIE(InfoExtractor):
'title': 'Most Popular',
'id': 'mostpopular',
},
'playlist_mincount': 80,
'playlist_mincount': 30,
}, {
'url': 'http://trailers.apple.com/#section=moviestudios',
'info_dict': {

4
youtube_dl/extractor/archiveorg.py
View File

@ -24,12 +24,12 @@ class ArchiveOrgIE(InfoExtractor):
}
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
'md5': '0869000b4ce265e8ca62738b336b268a',
'info_dict': {
'id': 'Cops1922',
'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:b4544662605877edd99df22f9620d858',
'description': 'md5:89e7c77bf5d965dd5c0372cfb49470f6',
}
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',

5
youtube_dl/extractor/arte.py
View File

@ -180,7 +180,7 @@ 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)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
@ -188,6 +188,9 @@ class ArteTVPlus7IE(ArteTVBaseIE):
}, {
'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,
}]
@classmethod

2
youtube_dl/extractor/atresplayer.py
View File

@ -36,7 +36,7 @@ class AtresPlayerIE(InfoExtractor):
},
{
'url': 'http://www.atresplayer.com/television/especial/videoencuentros/temporada-1/capitulo-112-david-bustamante_2014121600375.html',
'md5': '0d0e918533bbd4b263f2de4d197d4aac',
'md5': '6e52cbb513c405e403dbacb7aacf8747',
'info_dict': {
'id': 'capitulo-112-david-bustamante',
'ext': 'flv',

2
youtube_dl/extractor/audioboom.py
View File

@ -16,7 +16,7 @@ class AudioBoomIE(InfoExtractor):
'title': '3/09/2016 Czaban Hour 3',
'description': 'Guest: Nate Davis - NFL free agency, Guest: Stan Gans',
'duration': 2245.72,
'uploader': 'Steve Czaban',
'uploader': 'SB Nation A.M.',
'uploader_url': r're:https?://(?:www\.)?audioboom\.com/channel/steveczabanyahoosportsradio',
}
}, {

140
youtube_dl/extractor/azubu.py
View File

@ -1,140 +0,0 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
)
class AzubuIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/[^/]+#!/play/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.azubu.tv/GSL#!/play/15575/2014-hot6-cup-last-big-match-ro8-day-1',
'md5': 'a88b42fcf844f29ad6035054bd9ecaf4',
'info_dict': {
'id': '15575',
'ext': 'mp4',
'title': '2014 HOT6 CUP LAST BIG MATCH Ro8 Day 1',
'description': 'md5:d06bdea27b8cc4388a90ad35b5c66c01',
'thumbnail': r're:^https?://.*\.jpe?g',
'timestamp': 1417523507.334,
'upload_date': '20141202',
'duration': 9988.7,
'uploader': 'GSL',
'uploader_id': 414310,
'view_count': int,
},
},
{
'url': 'http://www.azubu.tv/FnaticTV#!/play/9344/-fnatic-at-worlds-2014:-toyz---%22i-love-rekkles,-he-has-amazing-mechanics%22-',
'md5': 'b72a871fe1d9f70bd7673769cdb3b925',
'info_dict': {
'id': '9344',
'ext': 'mp4',
'title': 'Fnatic at Worlds 2014: Toyz - "I love Rekkles, he has amazing mechanics"',
'description': 'md5:4a649737b5f6c8b5c5be543e88dc62af',
'thumbnail': r're:^https?://.*\.jpe?g',
'timestamp': 1410530893.320,
'upload_date': '20140912',
'duration': 172.385,
'uploader': 'FnaticTV',
'uploader_id': 272749,
'view_count': int,
},
'skip': 'Channel offline',
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'http://www.azubu.tv/api/video/%s' % video_id, video_id)['data']
title = data['title'].strip()
description = data.get('description')
thumbnail = data.get('thumbnail')
view_count = data.get('view_count')
user = data.get('user', {})
uploader = user.get('username')
uploader_id = user.get('id')
stream_params = json.loads(data['stream_params'])
timestamp = float_or_none(stream_params.get('creationDate'), 1000)
duration = float_or_none(stream_params.get('length'), 1000)
renditions = stream_params.get('renditions') or []
video = stream_params.get('FLVFullLength') or stream_params.get('videoFullLength')
if video:
renditions.append(video)
if not renditions and not user.get('channel', {}).get('is_live', True):
raise ExtractorError('%s said: channel is offline.' % self.IE_NAME, expected=True)
formats = [{
'url': fmt['url'],
'width': fmt['frameWidth'],
'height': fmt['frameHeight'],
'vbr': float_or_none(fmt['encodingRate'], 1000),
'filesize': fmt['size'],
'vcodec': fmt['videoCodec'],
'container': fmt['videoContainer'],
} for fmt in renditions if fmt['url']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'formats': formats,
}
class AzubuLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?azubu\.(?:tv|uol.com.br)/(?P<id>[^/]+)$'
_TESTS = [{
'url': 'http://www.azubu.tv/MarsTVMDLen',
'only_matching': True,
}, {
'url': 'http://azubu.uol.com.br/adolfz',
'only_matching': True,
}]
def _real_extract(self, url):
user = self._match_id(url)
info = self._download_json(
'http://api.azubu.tv/public/modules/last-video/{0}/info'.format(user),
user)['data']
if info['type'] != 'STREAM':
raise ExtractorError('{0} is not streaming live'.format(user), expected=True)
req = sanitized_Request(
'https://edge-elb.api.brightcove.com/playback/v1/accounts/3361910549001/videos/ref:' + info['reference_id'])
req.add_header('Accept', 'application/json;pk=BCpkADawqM1gvI0oGWg8dxQHlgT8HkdE2LnAlWAZkOlznO39bSZX726u4JqnDsK3MDXcO01JxXK2tZtJbgQChxgaFzEVdHRjaDoxaOu8hHOO8NYhwdxw9BzvgkvLUlpbDNUuDoc4E4wxDToV')
bc_info = self._download_json(req, user)
m3u8_url = next(source['src'] for source in bc_info['sources'] if source['container'] == 'M2TS')
formats = self._extract_m3u8_formats(m3u8_url, user, ext='mp4')
self._sort_formats(formats)
return {
'id': info['id'],
'title': self._live_title(info['title']),
'uploader_id': user,
'formats': formats,
'is_live': True,
'thumbnail': bc_info['poster'],
}

12
youtube_dl/extractor/bandcamp.py
View File

@ -34,12 +34,12 @@ class BandcampIE(InfoExtractor):
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}, {
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'md5': '73d0b3171568232574e45652f8720b5c',
'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
'info_dict': {
'id': '2650410135',
'ext': 'mp3',
'title': 'Lanius (Battle)',
'uploader': 'Ben Prunty Music',
'ext': 'aiff',
'title': 'Ben Prunty - Lanius (Battle)',
'uploader': 'Ben Prunty',
},
}]
@ -47,6 +47,7 @@ class BandcampIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
thumbnail = self._html_search_meta('og:image', webpage, default=None)
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@ -75,6 +76,7 @@ class BandcampIE(InfoExtractor):
return {
'id': track_id,
'title': data['title'],
'thumbnail': thumbnail,
'formats': formats,
'duration': float_or_none(data.get('duration')),
}
@ -143,7 +145,7 @@ class BandcampIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'thumbnail': info.get('thumb_url'),
'thumbnail': info.get('thumb_url') or thumbnail,
'uploader': info.get('artist'),
'artist': artist,
'track': track,

50
youtube_dl/extractor/bbc.py
View File

@ -6,14 +6,18 @@ import itertools
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
ExtractorError,
float_or_none,
get_element_by_class,
int_or_none,
parse_duration,
parse_iso8601,
try_get,
unescapeHTML,
urlencode_postdata,
urljoin,
)
from ..compat import (
compat_etree_fromstring,
@ -38,6 +42,9 @@ class BBCCoUkIE(InfoExtractor):
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
_LOGIN_URL = 'https://account.bbc.com/signin'
_NETRC_MACHINE = 'bbc'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g.
@ -227,6 +234,39 @@ class BBCCoUkIE(InfoExtractor):
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading signin page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = urljoin(self._LOGIN_URL, self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url'))
response, urlh = self._download_webpage_handle(
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl():
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
class MediaSelectionError(Exception):
def __init__(self, id):
self.id = id
@ -361,7 +401,7 @@ class BBCCoUkIE(InfoExtractor):
fmt.update({
'width': width,
'height': height,
'vbr': bitrate,
'tbr': bitrate,
'vcodec': encoding,
})
else:
@ -370,7 +410,7 @@ class BBCCoUkIE(InfoExtractor):
'acodec': encoding,
'vcodec': 'none',
})
if protocol == 'http':
if protocol in ('http', 'https'):
# Direct link
fmt.update({
'url': href,
@ -389,6 +429,8 @@ class BBCCoUkIE(InfoExtractor):
'rtmp_live': False,
'ext': 'flv',
})
else:
continue
formats.append(fmt)
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
@ -407,7 +449,7 @@ class BBCCoUkIE(InfoExtractor):
description = smp_config['summary']
for item in smp_config['items']:
kind = item['kind']
if kind != 'programme' and kind != 'radioProgramme':
if kind not in ('programme', 'radioProgramme'):
continue
programme_id = item.get('vpid')
duration = int_or_none(item.get('duration'))
@ -448,7 +490,7 @@ class BBCCoUkIE(InfoExtractor):
for item in self._extract_items(playlist):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
if kind not in ('programme', 'radioProgramme'):
continue
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)

145
youtube_dl/extractor/beampro.py
View File

@ -6,18 +6,33 @@ from ..utils import (
ExtractorError,
clean_html,
compat_str,
float_or_none,
int_or_none,
parse_iso8601,
try_get,
urljoin,
)
class BeamProLiveIE(InfoExtractor):
IE_NAME = 'Beam:live'
_VALID_URL = r'https?://(?:\w+\.)?beam\.pro/(?P<id>[^/?#&]+)'
class BeamProBaseIE(InfoExtractor):
_API_BASE = 'https://mixer.com/api/v1'
_RATINGS = {'family': 0, 'teen': 13, '18+': 18}
def _extract_channel_info(self, chan):
user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
return {
'uploader': chan.get('token') or try_get(
chan, lambda x: x['user']['username'], compat_str),
'uploader_id': compat_str(user_id) if user_id else None,
'age_limit': self._RATINGS.get(chan.get('audience')),
}
class BeamProLiveIE(BeamProBaseIE):
IE_NAME = 'Mixer:live'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.beam.pro/niterhayven',
'url': 'http://mixer.com/niterhayven',
'info_dict': {
'id': '261562',
'ext': 'mp4',
@ -38,11 +53,17 @@ class BeamProLiveIE(InfoExtractor):
},
}
_MANIFEST_URL_TEMPLATE = '%s/channels/%%s/manifest.%%s' % BeamProBaseIE._API_BASE
@classmethod
def suitable(cls, url):
return False if BeamProVodIE.suitable(url) else super(BeamProLiveIE, cls).suitable(url)
def _real_extract(self, url):
channel_name = self._match_id(url)
chan = self._download_json(
'https://beam.pro/api/v1/channels/%s' % channel_name, channel_name)
'%s/channels/%s' % (self._API_BASE, channel_name), channel_name)
if chan.get('online') is False:
raise ExtractorError(
@ -50,24 +71,118 @@ class BeamProLiveIE(InfoExtractor):
channel_id = chan['id']
def manifest_url(kind):
return self._MANIFEST_URL_TEMPLATE % (channel_id, kind)
formats = self._extract_m3u8_formats(
'https://beam.pro/api/v1/channels/%s/manifest.m3u8' % channel_id,
channel_name, ext='mp4', m3u8_id='hls', fatal=False)
manifest_url('m3u8'), channel_name, ext='mp4', m3u8_id='hls',
fatal=False)
formats.extend(self._extract_smil_formats(
manifest_url('smil'), channel_name, fatal=False))
self._sort_formats(formats)
user_id = chan.get('userId') or try_get(chan, lambda x: x['user']['id'])
return {
info = {
'id': compat_str(chan.get('id') or channel_name),
'title': self._live_title(chan.get('name') or channel_name),
'description': clean_html(chan.get('description')),
'thumbnail': try_get(chan, lambda x: x['thumbnail']['url'], compat_str),
'thumbnail': try_get(
chan, lambda x: x['thumbnail']['url'], compat_str),
'timestamp': parse_iso8601(chan.get('updatedAt')),
'uploader': chan.get('token') or try_get(
chan, lambda x: x['user']['username'], compat_str),
'uploader_id': compat_str(user_id) if user_id else None,
'age_limit': self._RATINGS.get(chan.get('audience')),
'is_live': True,
'view_count': int_or_none(chan.get('viewersTotal')),
'formats': formats,
}
info.update(self._extract_channel_info(chan))
return info
class BeamProVodIE(BeamProBaseIE):
IE_NAME = 'Mixer:vod'
_VALID_URL = r'https?://(?:\w+\.)?(?:beam\.pro|mixer\.com)/[^/?#&]+\?.*?\bvod=(?P<id>\d+)'
_TEST = {
'url': 'https://mixer.com/willow8714?vod=2259830',
'md5': 'b2431e6e8347dc92ebafb565d368b76b',
'info_dict': {
'id': '2259830',
'ext': 'mp4',
'title': 'willow8714\'s Channel',
'duration': 6828.15,
'thumbnail': r're:https://.*source\.png$',
'timestamp': 1494046474,
'upload_date': '20170506',
'uploader': 'willow8714',
'uploader_id': '6085379',
'age_limit': 13,
'view_count': int,
},
'params': {
'skip_download': True,
},
}
@staticmethod
def _extract_format(vod, vod_type):
if not vod.get('baseUrl'):
return []
if vod_type == 'hls':
filename, protocol = 'manifest.m3u8', 'm3u8_native'
elif vod_type == 'raw':
filename, protocol = 'source.mp4', 'https'
else:
assert False
data = vod.get('data') if isinstance(vod.get('data'), dict) else {}
format_id = [vod_type]
if isinstance(data.get('Height'), compat_str):
format_id.append('%sp' % data['Height'])
return [{
'url': urljoin(vod['baseUrl'], filename),
'format_id': '-'.join(format_id),
'ext': 'mp4',
'protocol': protocol,
'width': int_or_none(data.get('Width')),
'height': int_or_none(data.get('Height')),
'fps': int_or_none(data.get('Fps')),
'tbr': int_or_none(data.get('Bitrate'), 1000),
}]
def _real_extract(self, url):
vod_id = self._match_id(url)
vod_info = self._download_json(
'%s/recordings/%s' % (self._API_BASE, vod_id), vod_id)
state = vod_info.get('state')
if state != 'AVAILABLE':
raise ExtractorError(
'VOD %s is not available (state: %s)' % (vod_id, state),
expected=True)
formats = []
thumbnail_url = None
for vod in vod_info['vods']:
vod_type = vod.get('format')
if vod_type in ('hls', 'raw'):
formats.extend(self._extract_format(vod, vod_type))
elif vod_type == 'thumbnail':
thumbnail_url = urljoin(vod.get('baseUrl'), 'source.png')
self._sort_formats(formats)
info = {
'id': vod_id,
'title': vod_info.get('name') or vod_id,
'duration': float_or_none(vod_info.get('duration')),
'thumbnail': thumbnail_url,
'timestamp': parse_iso8601(vod_info.get('createdAt')),
'view_count': int_or_none(vod_info.get('viewsTotal')),
'formats': formats,
}
info.update(self._extract_channel_info(vod_info.get('channel') or {}))
return info

2
youtube_dl/extractor/beeg.py
View File

@ -16,7 +16,7 @@ class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://beeg.com/5416503',
'md5': '46c384def73b33dbc581262e5ee67cef',
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': {
'id': '5416503',
'ext': 'mp4',

5
youtube_dl/extractor/bilibili.py
View File

@ -122,6 +122,11 @@ class BiliBiliIE(InfoExtractor):
'preference': -2 if 'hd.mp4' in backup_url else -3,
})
for a_format in formats:
a_format.setdefault('http_headers', {}).update({
'Referer': url,
})
self._sort_formats(formats)
entries.append({

10
youtube_dl/extractor/bleacherreport.py
View File

@ -35,7 +35,7 @@ class BleacherReportIE(InfoExtractor):
'title': 'Aussie Golfers Get Fright of Their Lives After Being Chased by Angry Kangaroo',
'timestamp': 1446839961,
'uploader': 'Sean Fay',
'description': 'md5:825e94e0f3521df52fa83b2ed198fa20',
'description': 'md5:b1601e2314c4d8eec23b6eafe086a757',
'uploader_id': 6466954,
'upload_date': '20151011',
},
@ -90,17 +90,13 @@ class BleacherReportCMSIE(AMPIE):
_VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P<id>[0-9a-f-]{36})'
_TESTS = [{
'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'md5': '8c2c12e3af7805152675446c905d159b',
'md5': '2e4b0a997f9228ffa31fada5c53d1ed1',
'info_dict': {
'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1',
'ext': 'mp4',
'ext': 'flv',
'title': 'Cena vs. Rollins Would Expose the Heavyweight Division',
'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e',
},
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):

2
youtube_dl/extractor/br.py
View File

@ -77,7 +77,7 @@ class BRIE(InfoExtractor):
'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
'duration': 893,
'uploader': 'Eva Maria Steimle',
'upload_date': '20140117',
'upload_date': '20170208',
}
},
]

111
youtube_dl/extractor/brightcove.py
View File

@ -5,6 +5,7 @@ import re
import json
from .common import InfoExtractor
from .adobepass import AdobePassIE
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
@ -17,6 +18,7 @@ from ..compat import (
from ..utils import (
determine_ext,
ExtractorError,
extract_attributes,
find_xpath_attr,
fix_xml_ampersands,
float_or_none,
@ -109,6 +111,7 @@ class BrightcoveLegacyIE(InfoExtractor):
'upload_date': '20140827',
'uploader_id': '710858724001',
},
'skip': 'Video gone',
},
{
# playlist with 'videoList'
@ -129,6 +132,12 @@ class BrightcoveLegacyIE(InfoExtractor):
},
'playlist_mincount': 10,
},
{
# playerID inferred from bcpid
# from http://www.un.org/chinese/News/story.asp?NewsID=27724
'url': 'https://link.brightcove.com/services/player/bcpid1722935254001/?bctid=5360463607001&autoStart=false&secureConnections=true&width=650&height=350',
'only_matching': True, # Tested in GenericIE
}
]
FLV_VCODECS = {
1: 'SORENSON',
@ -264,9 +273,13 @@ class BrightcoveLegacyIE(InfoExtractor):
if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)
if matches:
return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
for custom_bc in matches]))
return [src for _, src in re.findall(
r'<iframe[^>]+src=([\'"])((?:https?:)?//link\.brightcove\.com/services/player/(?!\1).+)\1', webpage)]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
@ -283,6 +296,10 @@ class BrightcoveLegacyIE(InfoExtractor):
if videoPlayer:
# We set the original url as the default 'Referer' header
referer = smuggled_data.get('Referer', url)
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:
@ -432,7 +449,7 @@ class BrightcoveLegacyIE(InfoExtractor):
return info
class BrightcoveNewIE(InfoExtractor):
class BrightcoveNewIE(AdobePassIE):
IE_NAME = 'brightcove:new'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
_TESTS = [{
@ -482,17 +499,18 @@ class BrightcoveNewIE(InfoExtractor):
}]
@staticmethod
def _extract_url(webpage):
urls = BrightcoveNewIE._extract_urls(webpage)
def _extract_url(ie, webpage):
urls = BrightcoveNewIE._extract_urls(ie, webpage)
return urls[0] if urls else None
@staticmethod
def _extract_urls(webpage):
def _extract_urls(ie, webpage):
# Reference:
# 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
# 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript
# 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/embed-in-page.html
# 4. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player
# 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#tag
# 3. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideousingjavascript
# 4. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/in-page-embed-player-implementation.html
# 5. https://support.brightcove.com/en/video-cloud/docs/dynamically-assigning-videos-player
entries = []
@ -501,22 +519,48 @@ class BrightcoveNewIE(InfoExtractor):
r'<iframe[^>]+src=(["\'])((?:https?:)?//players\.brightcove\.net/\d+/[^/]+/index\.html.+?)\1', webpage):
entries.append(url if url.startswith('http') else 'http:' + url)
# Look for embed_in_page embeds [2]
for video_id, account_id, player_id, embed in re.findall(
# According to examples from [3] it's unclear whether video id
# may be optional and what to do when it is
# According to [4] data-video-id may be prefixed with ref:
r'''(?sx)
<video[^>]+
data-video-id=["\'](\d+|ref:[^"\']+)["\'][^>]*>.*?
</video>.*?
<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/
(\d+)/([^/]+)_([^/]+)/index(?:\.min)?\.js
# Look for <video> tags [2] and embed_in_page embeds [3]
# [2] looks like:
for video, script_tag, account_id, player_id, embed in re.findall(
r'''(?isx)
(<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
(?:.*?
(<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/
(\d+)/([^/]+)_([^/]+)/index(?:\.min)?\.js
)
)?
''', webpage):
entries.append(
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
% (account_id, player_id, embed, video_id))
attrs = extract_attributes(video)
# According to examples from [4] it's unclear whether video id
# may be optional and what to do when it is
video_id = attrs.get('data-video-id')
if not video_id:
continue
account_id = account_id or attrs.get('data-account')
if not account_id:
continue
player_id = player_id or attrs.get('data-player') or 'default'
embed = embed or attrs.get('data-embed') or 'default'
bc_url = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s' % (
account_id, player_id, embed, video_id)
# Some brightcove videos may be embedded with video tag only and
# without script tag or any mentioning of brightcove at all. Such
# embeds are considered ambiguous since they are matched based only
# on data-video-id and data-account attributes and in the wild may
# not be brightcove embeds at all. Let's check reconstructed
# brightcove URLs in case of such embeds and only process valid
# ones. By this we ensure there is indeed a brightcove embed.
if not script_tag and not ie._is_valid_url(
bc_url, video_id, 'possible brightcove video'):
continue
entries.append(bc_url)
return entries
@ -559,6 +603,20 @@ class BrightcoveNewIE(InfoExtractor):
raise ExtractorError(message, expected=True)
raise
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
}, query={
'tveToken': tve_token,
})
title = json_data['name'].strip()
formats = []
@ -624,7 +682,6 @@ class BrightcoveNewIE(InfoExtractor):
})
formats.append(f)
errors = json_data.get('errors')
if not formats and errors:
error = errors[0]
raise ExtractorError(
@ -641,7 +698,7 @@ class BrightcoveNewIE(InfoExtractor):
is_live = False
duration = float_or_none(json_data.get('duration'), 1000)
if duration and duration < 0:
if duration is not None and duration <= 0:
is_live = True
return {

5
youtube_dl/extractor/canalc2.py
View File

@ -16,13 +16,10 @@ class Canalc2IE(InfoExtractor):
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
'ext': 'flv',
'ext': 'mp4',
'title': 'Terrasses du Numérique',
'duration': 122,
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}, {
'url': 'http://archives-canalc2.u-strasbg.fr/video.asp?idVideo=11427&voir=oui',
'only_matching': True,

43
youtube_dl/extractor/canalplus.py
View File

@ -7,8 +7,8 @@ from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
dict_get,
ExtractorError,
HEADRequest,
# ExtractorError,
# HEADRequest,
int_or_none,
qualities,
remove_end,
@ -45,6 +45,9 @@ class CanalplusIE(InfoExtractor):
'itele': 'itele',
}
# Only works for direct mp4 URLs
_GEO_COUNTRIES = ['FR']
_TESTS = [{
'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
'info_dict': {
@ -56,6 +59,7 @@ class CanalplusIE(InfoExtractor):
'upload_date': '20160702',
},
}, {
# geo restricted, bypassed
'url': 'http://www.piwiplus.fr/videos-piwi/pid1405-le-labyrinthe-boing-super-ranger.html?vid=1108190',
'info_dict': {
'id': '1108190',
@ -65,19 +69,20 @@ class CanalplusIE(InfoExtractor):
'description': 'md5:4cea7a37153be42c1ba2c1d3064376ff',
'upload_date': '20140724',
},
'skip': 'Only works from France',
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html',
'md5': '4b47b12b4ee43002626b97fad8fb1de5',
# geo restricted, bypassed
'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',
'info_dict': {
'id': '1420213',
'id': '1443684',
'display_id': 'pid6318-videos-integrales',
'ext': 'mp4',
'title': 'TPMP ! Même le matin - Les 35H de Baba - 14/10/2016',
'description': 'md5:f96736c1b0ffaa96fd5b9e60ad871799',
'upload_date': '20161014',
'title': 'Guess my iep ! - TPMP - 07/04/2017',
'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
'upload_date': '20170407',
},
'skip': 'Only works from France',
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
'info_dict': {
@ -134,15 +139,15 @@ class CanalplusIE(InfoExtractor):
preference = qualities(['MOBILE', 'BAS_DEBIT', 'HAUT_DEBIT', 'HD'])
fmt_url = next(iter(media.get('VIDEOS')))
if '/geo' in fmt_url.lower():
response = self._request_webpage(
HEADRequest(fmt_url), video_id,
'Checking if the video is georestricted')
if '/blocage' in response.geturl():
raise ExtractorError(
'The video is not available in your country',
expected=True)
# _, fmt_url = next(iter(media['VIDEOS'].items()))
# if '/geo' in fmt_url.lower():
# response = self._request_webpage(
# HEADRequest(fmt_url), video_id,
# 'Checking if the video is georestricted')
# if '/blocage' in response.geturl():
# raise ExtractorError(
# 'The video is not available in your country',
# expected=True)
formats = []
for format_id, format_url in media['VIDEOS'].items():

1
youtube_dl/extractor/canvas.py
View File

@ -7,6 +7,7 @@ from ..utils import float_or_none
class CanvasIE(InfoExtractor):
IE_DESC = 'canvas.be and een.be'
_VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',

6
youtube_dl/extractor/cbc.py
View File

@ -96,6 +96,7 @@ class CBCIE(InfoExtractor):
'info_dict': {
'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
'id': 'dog-indoor-exercise-winter-1.3928238',
'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
},
'playlist_mincount': 6,
}]
@ -165,12 +166,11 @@ class CBCPlayerIE(InfoExtractor):
'uploader': 'CBCC-NEW',
},
}, {
# available only when we add `formats=MPEG4,FLV,MP3` to theplatform url
'url': 'http://www.cbc.ca/player/play/2164402062',
'md5': '17a61eb813539abea40618d6323a7f82',
'md5': '33fcd8f6719b9dd60a5e73adcb83b9f6',
'info_dict': {
'id': '2164402062',
'ext': 'flv',
'ext': 'mp4',
'title': 'Cancer survivor four times over',
'description': 'Tim Mayer has beaten three different forms of cancer four times in five years.',
'timestamp': 1320410746,

6
youtube_dl/extractor/cbs.py
View File

@ -49,13 +49,13 @@ class CBSIE(CBSBaseIE):
'only_matching': True,
}]
def _extract_video_info(self, content_id):
def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
items_data = self._download_xml(
'http://can.cbs.com/thunder/player/videoPlayerService.php',
content_id, query={'partner': 'cbs', 'contentId': content_id})
content_id, query={'partner': site, 'contentId': content_id})
video_data = xpath_element(items_data, './/item')
title = xpath_text(video_data, 'videoTitle', 'title', True)
tp_path = 'dJ5BDC/media/guid/2198311517/%s' % content_id
tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
tp_release_url = 'http://link.theplatform.com/s/' + tp_path
asset_types = []

60
youtube_dl/extractor/cbsinteractive.py
View File

@ -3,17 +3,18 @@ from __future__ import unicode_literals
import re
from .theplatform import ThePlatformIE
from .cbs import CBSIE
from ..utils import int_or_none
class CBSInteractiveIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video/share)/(?P<id>[^/?]+)'
class CBSInteractiveIE(CBSIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>cnet|zdnet)\.com/(?:videos|video(?:/share)?)/(?P<id>[^/?]+)'
_TESTS = [{
'url': 'http://www.cnet.com/videos/hands-on-with-microsofts-windows-8-1-update/',
'info_dict': {
'id': '56f4ea68-bd21-4852-b08c-4de5b8354c60',
'ext': 'flv',
'id': 'R49SYt__yAfmlXR85z4f7gNmCBDcN_00',
'display_id': 'hands-on-with-microsofts-windows-8-1-update',
'ext': 'mp4',
'title': 'Hands-on with Microsoft Windows 8.1 Update',
'description': 'The new update to the Windows 8 OS brings improved performance for mouse and keyboard users.',
'uploader_id': '6085384d-619e-11e3-b231-14feb5ca9861',
@ -22,13 +23,19 @@ class CBSInteractiveIE(ThePlatformIE):
'timestamp': 1396479627,
'upload_date': '20140402',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.cnet.com/videos/whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187/',
'md5': 'f11d27b2fa18597fbf92444d2a9ed386',
'info_dict': {
'id': '56527b93-d25d-44e3-b738-f989ce2e49ba',
'ext': 'flv',
'id': 'kjOJd_OoVJqbg_ZD8MZCOk8Wekb9QccK',
'display_id': 'whiny-pothole-tweets-at-local-government-when-hit-by-cars-tomorrow-daily-187',
'ext': 'mp4',
'title': 'Whiny potholes tweet at local government when hit by cars (Tomorrow Daily 187)',
'description': 'Khail and Ashley wonder what other civic woes can be solved by self-tweeting objects, investigate a new kind of VR camera and watch an origami robot self-assemble, walk, climb, dig and dissolve. #TDPothole',
'description': 'md5:d2b9a95a5ffe978ae6fbd4cf944d618f',
'uploader_id': 'b163284d-6b73-44fc-b3e6-3da66c392d40',
'uploader': 'Ashley Esqueda',
'duration': 1482,
@ -38,23 +45,28 @@ class CBSInteractiveIE(ThePlatformIE):
}, {
'url': 'http://www.zdnet.com/video/share/video-keeping-android-smartphones-and-tablets-secure/',
'info_dict': {
'id': 'bc1af9f0-a2b5-4e54-880d-0d95525781c0',
'id': 'k0r4T_ehht4xW_hAOqiVQPuBDPZ8SRjt',
'display_id': 'video-keeping-android-smartphones-and-tablets-secure',
'ext': 'mp4',
'title': 'Video: Keeping Android smartphones and tablets secure',
'description': 'Here\'s the best way to keep Android devices secure, and what you do when they\'ve come to the end of their lives.',
'uploader_id': 'f2d97ea2-8175-11e2-9d12-0018fe8a00b0',
'uploader': 'Adrian Kingsley-Hughes',
'timestamp': 1448961720,
'upload_date': '20151201',
'duration': 731,
'timestamp': 1449129925,
'upload_date': '20151203',
},
'params': {
# m3u8 download
'skip_download': True,
}
},
}, {
'url': 'http://www.zdnet.com/video/huawei-matebook-x-video/',
'only_matching': True,
}]
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/kYEXFC/%s?mbr=true'
MPX_ACCOUNTS = {
'cnet': 2288573011,
'cnet': 2198311517,
'zdnet': 2387448114,
}
@ -68,7 +80,8 @@ class CBSInteractiveIE(ThePlatformIE):
data = self._parse_json(data_json, display_id)
vdata = data.get('video') or data['videos'][0]
video_id = vdata['id']
video_id = vdata['mpxRefId']
title = vdata['title']
author = vdata.get('author')
if author:
@ -78,20 +91,7 @@ class CBSInteractiveIE(ThePlatformIE):
uploader = None
uploader_id = None
media_guid_path = 'media/guid/%d/%s' % (self.MPX_ACCOUNTS[site], vdata['mpxRefId'])
formats, subtitles = [], {}
for (fkey, vid) in vdata['files'].items():
if fkey == 'hls_phone' and 'hls_tablet' in vdata['files']:
continue
release_url = self.TP_RELEASE_URL_TEMPLATE % vid
if fkey == 'hds':
release_url += '&manifest=f4m'
tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % fkey)
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
self._sort_formats(formats)
info = self._extract_theplatform_metadata('kYEXFC/%s' % media_guid_path, video_id)
info = self._extract_video_info(video_id, site, self.MPX_ACCOUNTS[site])
info.update({
'id': video_id,
'display_id': display_id,
@ -99,7 +99,5 @@ class CBSInteractiveIE(ThePlatformIE):
'duration': int_or_none(vdata.get('duration')),
'uploader': uploader,
'uploader_id': uploader_id,
'subtitles': subtitles,
'formats': formats,
})
return info

4
youtube_dl/extractor/cbslocal.py
View File

@ -60,8 +60,8 @@ class CBSLocalIE(AnvatoIE):
'title': 'A Very Blue Anniversary',
'description': 'CBS2’s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*',
'timestamp': 1479962220,
'upload_date': '20161124',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',

14
youtube_dl/extractor/cbsnews.py
View File

@ -61,11 +61,17 @@ class CBSNewsIE(CBSIE):
video_info = self._parse_json(self._html_search_regex(
r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
webpage, 'video JSON info'), video_id)
webpage, 'video JSON info', default='{}'), video_id, fatal=False)
item = video_info['item'] if 'item' in video_info else video_info
guid = item['mpxRefId']
return self._extract_video_info(guid)
if video_info:
item = video_info['item'] if 'item' in video_info else video_info
else:
state = self._parse_json(self._search_regex(
r'data-cbsvideoui-options=(["\'])(?P<json>{.+?})\1', webpage,
'playlist JSON info', group='json'), video_id)['state']
item = state['playlist'][state['pid']]
return self._extract_video_info(item['mpxRefId'], 'cbsnews')
class CBSNewsLiveVideoIE(InfoExtractor):

52
youtube_dl/extractor/cda.py
View File

@ -9,7 +9,10 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
multipart_encode,
parse_duration,
random_birthday,
urljoin,
)
@ -27,7 +30,8 @@ class CDAIE(InfoExtractor):
'description': 'md5:269ccd135d550da90d1662651fcb9772',
'thumbnail': r're:^https?://.*\.jpg$',
'average_rating': float,
'duration': 39
'duration': 39,
'age_limit': 0,
}
}, {
'url': 'http://www.cda.pl/video/57413289',
@ -41,13 +45,41 @@ class CDAIE(InfoExtractor):
'uploader': 'crash404',
'view_count': int,
'average_rating': float,
'duration': 137
'duration': 137,
'age_limit': 0,
}
}, {
# Age-restricted
'url': 'http://www.cda.pl/video/1273454c4',
'info_dict': {
'id': '1273454c4',
'ext': 'mp4',
'title': 'Bronson (2008) napisy HD 1080p',
'description': 'md5:1b6cb18508daf2dc4e0fa4db77fec24c',
'height': 1080,
'uploader': 'boniek61',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 5554,
'age_limit': 18,
'view_count': int,
'average_rating': float,
},
}, {
'url': 'http://ebd.cda.pl/0x0/5749950c',
'only_matching': True,
}]
def _download_age_confirm_page(self, url, video_id, *args, **kwargs):
form_data = random_birthday('rok', 'miesiac', 'dzien')
form_data.update({'return': url, 'module': 'video', 'module_id': video_id})
data, content_type = multipart_encode(form_data)
return self._download_webpage(
urljoin(url, '/a/validatebirth'), video_id, *args,
data=data, headers={
'Referer': url,
'Content-Type': content_type,
}, **kwargs)
def _real_extract(self, url):
video_id = self._match_id(url)
self._set_cookie('cda.pl', 'cda.player', 'html5')
@ -57,6 +89,13 @@ class CDAIE(InfoExtractor):
if 'Ten film jest dostępny dla użytkowników premium' in webpage:
raise ExtractorError('This video is only available for premium users.', expected=True)
need_confirm_age = False
if self._html_search_regex(r'(<form[^>]+action="/a/validatebirth")',
webpage, 'birthday validate form', default=None):
webpage = self._download_age_confirm_page(
url, video_id, note='Confirming age')
need_confirm_age = True
formats = []
uploader = self._search_regex(r'''(?x)
@ -81,6 +120,7 @@ class CDAIE(InfoExtractor):
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
'duration': None,
'age_limit': 18 if need_confirm_age else 0,
}
def extract_format(page, version):
@ -121,7 +161,12 @@ class CDAIE(InfoExtractor):
for href, resolution in re.findall(
r'<a[^>]+data-quality="[^"]+"[^>]+href="([^"]+)"[^>]+class="quality-btn"[^>]*>([0-9]+p)',
webpage):
webpage = self._download_webpage(
if need_confirm_age:
handler = self._download_age_confirm_page
else:
handler = self._download_webpage
webpage = handler(
self._BASE_URL + href, video_id,
'Downloading %s version information' % resolution, fatal=False)
if not webpage:
@ -129,6 +174,7 @@ class CDAIE(InfoExtractor):
# invalid version is requested.
self.report_warning('Unable to download %s version information' % resolution)
continue
extract_format(webpage, resolution)
self._sort_formats(formats)

106
youtube_dl/extractor/ceskatelevize.py
View File

@ -12,13 +12,14 @@ from ..utils import (
ExtractorError,
float_or_none,
sanitized_Request,
unescapeHTML,
urlencode_postdata,
USER_AGENTS,
)
class CeskaTelevizeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/(porady|ivysilani)/(?:[^/]+/)*(?P<id>[^/#?]+)/*(?:[#?].*)?$'
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/ivysilani/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
'url': 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220',
'info_dict': {
@ -62,40 +63,12 @@ class CeskaTelevizeIE(InfoExtractor):
},
'skip': 'Georestricted to Czech Republic',
}, {
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Queer: Bogotart',
'description': 'Alternativní průvodce současným queer světem',
},
'playlist': [{
'info_dict': {
'id': '61924494876844842',
'ext': 'mp4',
'title': 'Queer: Bogotart (Varování 18+)',
'duration': 10.2,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Queer: Bogotart (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
'url': 'http://www.ceskatelevize.cz/ivysilani/embed/iFramePlayer.php?hash=d6a3e1370d2e4fa76296b90bad4dfc19673b641e&IDEC=217 562 22150/0004&channelID=1&width=100%25',
'only_matching': True,
}]
def _real_extract(self, url):
url = url.replace('/porady/', '/ivysilani/').replace('/video/', '')
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
@ -103,13 +76,28 @@ class CeskaTelevizeIE(InfoExtractor):
if '%s</p>' % NOT_AVAILABLE_STRING in webpage:
raise ExtractorError(NOT_AVAILABLE_STRING, expected=True)
typ = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],', webpage, 'type')
episode_id = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],', webpage, 'episode_id')
type_ = None
episode_id = None
playlist = self._parse_json(
self._search_regex(
r'getPlaylistUrl\(\[({.+?})\]', webpage, 'playlist',
default='{}'), playlist_id)
if playlist:
type_ = playlist.get('type')
episode_id = playlist.get('id')
if not type_:
type_ = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":"(.+?)","id":".+?"\}\],',
webpage, 'type')
if not episode_id:
episode_id = self._html_search_regex(
r'getPlaylistUrl\(\[\{"type":".+?","id":"(.+?)"\}\],',
webpage, 'episode_id')
data = {
'playlist[0][type]': typ,
'playlist[0][type]': type_,
'playlist[0][id]': episode_id,
'requestUrl': compat_urllib_parse_urlparse(url).path,
'requestSource': 'iVysilani',
@ -245,3 +233,47 @@ class CeskaTelevizeIE(InfoExtractor):
yield line
return '\r\n'.join(_fix_subtitle(subtitles))
class CeskaTelevizePoradyIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ceskatelevize\.cz/porady/(?:[^/?#&]+/)*(?P<id>[^/#?]+)'
_TESTS = [{
# video with 18+ caution trailer
'url': 'http://www.ceskatelevize.cz/porady/10520528904-queer/215562210900007-bogotart/',
'info_dict': {
'id': '215562210900007-bogotart',
'title': 'Queer: Bogotart',
'description': 'Alternativní průvodce současným queer světem',
},
'playlist': [{
'info_dict': {
'id': '61924494876844842',
'ext': 'mp4',
'title': 'Queer: Bogotart (Varování 18+)',
'duration': 10.2,
},
}, {
'info_dict': {
'id': '61924494877068022',
'ext': 'mp4',
'title': 'Queer: Bogotart (Queer)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 1558.3,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
data_url = unescapeHTML(self._search_regex(
r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'iframe player url', group='url'))
return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

16
youtube_dl/extractor/chaturbate.py
View File

@ -33,10 +33,17 @@ class ChaturbateIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
m3u8_formats = [(m.group('id').lower(), m.group('url')) for m in re.finditer(
r'hlsSource(?P<id>.+?)\s*=\s*(?P<q>["\'])(?P<url>http.+?)(?P=q)', webpage)]
m3u8_urls = []
if not m3u8_formats:
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 m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
if m3u8_url not in m3u8_urls:
m3u8_urls.append(m3u8_url)
if not m3u8_urls:
error = self._search_regex(
[r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
@ -50,7 +57,8 @@ class ChaturbateIE(InfoExtractor):
raise ExtractorError('Unable to find stream URL')
formats = []
for m3u8_id, m3u8_url in m3u8_formats:
for m3u8_url in m3u8_urls:
m3u8_id = 'fast' if '_fast' in m3u8_url else 'slow'
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4',
# ffmpeg skips segments for fast m3u8

2
youtube_dl/extractor/clipfish.py
View File

@ -12,7 +12,7 @@ class ClipfishIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.clipfish.de/special/ugly-americans/video/4343170/s01-e01-ugly-americans-date-in-der-hoelle/',
'md5': '720563e467b86374c194bdead08d207d',
'md5': 'b9a5dc46294154c1193e2d10e0c95693',
'info_dict': {
'id': '4343170',
'ext': 'mp4',

3
youtube_dl/extractor/collegerama.py
View File

@ -21,7 +21,7 @@ class CollegeRamaIE(InfoExtractor):
'ext': 'mp4',
'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.',
'description': '',
'thumbnail': r're:^https?://.*\.jpg$',
'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
'duration': 7713.088,
'timestamp': 1413309600,
'upload_date': '20141014',
@ -35,6 +35,7 @@ class CollegeRamaIE(InfoExtractor):
'ext': 'wmv',
'title': '64ste Vakantiecursus: Afvalwater',
'description': 'md5:7fd774865cc69d972f542b157c328305',
'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$',
'duration': 10853,
'timestamp': 1326446400,
'upload_date': '20120113',

304
youtube_dl/extractor/common.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
@ -244,6 +245,10 @@ class InfoExtractor(object):
specified in the URL.
end_time: Time in seconds where the reproduction should end, as
specified in the URL.
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
* "title" (optional, string)
The following fields should only be used when the video belongs to some logical
chapter or section:
@ -547,6 +552,34 @@ class InfoExtractor(object):
return encoding
def __check_blocked(self, content):
first_block = content[:512]
if ('<title>Access to this site is blocked</title>' in content and
'Websense' in first_block):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
'Websense information URL', default=None)
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
if '<title>The URL you requested has been blocked</title>' in first_block:
msg = (
'Access to this webpage has been blocked by Indian censorship. '
'Use a VPN or proxy server (with --proxy) to route around it.')
block_msg = self._html_search_regex(
r'</h1><p>(.*?)</p>',
content, 'block message', default=None)
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
if ('<title>TTK :: Доступ к ресурсу ограничен</title>' in content and
'blocklist.rkn.gov.ru' in content):
raise ExtractorError(
'Access to this webpage has been blocked by decision of the Russian government. '
'Visit http://blocklist.rkn.gov.ru/ for a block reason.',
expected=True)
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
@ -588,25 +621,7 @@ class InfoExtractor(object):
except LookupError:
content = webpage_bytes.decode('utf-8', 'replace')
if ('<title>Access to this site is blocked</title>' in content and
'Websense' in content[:512]):
msg = 'Access to this webpage has been blocked by Websense filtering software in your network.'
blocked_iframe = self._html_search_regex(
r'<iframe src="([^"]+)"', content,
'Websense information URL', default=None)
if blocked_iframe:
msg += ' Visit %s for more details' % blocked_iframe
raise ExtractorError(msg, expected=True)
if '<title>The URL you requested has been blocked</title>' in content[:512]:
msg = (
'Access to this webpage has been blocked by Indian censorship. '
'Use a VPN or proxy server (with --proxy) to route around it.')
block_msg = self._html_search_regex(
r'</h1><p>(.*?)</p>',
content, 'block message', default=None)
if block_msg:
msg += ' (Message: "%s")' % block_msg.replace('\n', ' ')
raise ExtractorError(msg, expected=True)
self.__check_blocked(content)
return content
@ -965,6 +980,23 @@ class InfoExtractor(object):
return info
if isinstance(json_ld, dict):
json_ld = [json_ld]
def extract_video_object(e):
assert e['@type'] == 'VideoObject'
info.update({
'url': e.get('contentUrl'),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
'view_count': int_or_none(e.get('interactionCount')),
})
for e in json_ld:
if e.get('@context') == 'http://schema.org':
item_type = e.get('@type')
@ -989,18 +1021,11 @@ class InfoExtractor(object):
'description': unescapeHTML(e.get('articleBody')),
})
elif item_type == 'VideoObject':
info.update({
'url': e.get('contentUrl'),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
})
extract_video_object(e)
elif item_type == 'WebPage':
video = e.get('video')
if isinstance(video, dict) and video.get('@type') == 'VideoObject':
extract_video_object(video)
break
return dict((k, v) for k, v in info.items() if v is not None)
@ -1292,40 +1317,50 @@ class InfoExtractor(object):
entry_protocol='m3u8', preference=None,
m3u8_id=None, note=None, errnote=None,
fatal=True, live=False):
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)
if res is False:
return []
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
return self._parse_m3u8_formats(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
preference=preference, m3u8_id=m3u8_id, live=live)
def _parse_m3u8_formats(self, m3u8_doc, m3u8_url, ext=None,
entry_protocol='m3u8', preference=None,
m3u8_id=None, live=False):
if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access
return []
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
formats = []
format_url = lambda u: (
u
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
# We should try extracting formats only from master playlists [1], i.e.
# playlists that describe available qualities. On the other hand media
# playlists [2] should be returned as is since they contain just the media
# without qualities renditions.
# References:
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21
# 2. https://github.com/rg3/youtube-dl/issues/12211
# We should try extracting formats only from master playlists [1, 4.3.4],
# i.e. playlists that describe available qualities. On the other hand
# media playlists [1, 4.3.3] should be returned as is since they contain
# just the media without qualities renditions.
# Fortunately, master playlist can be easily distinguished from media
# playlist based on particular tags availability. As of [1, 2] master
# playlist tags MUST NOT appear in a media playist and vice versa.
# As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist
# and MUST NOT appear in master playlist thus we can clearly detect media
# playlist with this criterion.
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
# playlist based on particular tags availability. As of [1, 4.3.3, 4.3.4]
# master playlist tags MUST NOT appear in a media playist and vice versa.
# As of [1, 4.3.3.1] #EXT-X-TARGETDURATION tag is REQUIRED for every
# media playlist and MUST NOT appear in master playlist thus we can
# clearly detect media playlist with this criterion.
if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is
return [{
'url': m3u8_url,
@ -1334,52 +1369,72 @@ class InfoExtractor(object):
'protocol': entry_protocol,
'preference': preference,
}]
audio_in_video_stream = {}
last_info = {}
last_media = {}
groups = {}
last_stream_inf = {}
def extract_media(x_media_line):
media = parse_m3u8_attributes(x_media_line)
# As per [1, 4.3.4.1] TYPE, GROUP-ID and NAME are REQUIRED
media_type, group_id, name = media.get('TYPE'), media.get('GROUP-ID'), media.get('NAME')
if not (media_type and group_id and name):
return
groups.setdefault(group_id, []).append(media)
if media_type not in ('VIDEO', 'AUDIO'):
return
media_url = media.get('URI')
if media_url:
format_id = []
for v in (group_id, name):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'manifest_url': m3u8_url,
'language': media.get('LANGUAGE'),
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
}
if media_type == 'AUDIO':
f['vcodec'] = 'none'
formats.append(f)
def build_stream_name():
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF tag it still sometimes may be present (see [1]
# or vidio test in TestInfoExtractor.test_parse_m3u8_formats)
# 1. http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
stream_name = last_stream_inf.get('NAME')
if stream_name:
return stream_name
# If there is no NAME in EXT-X-STREAM-INF it will be obtained
# from corresponding rendition group
stream_group_id = last_stream_inf.get('VIDEO')
if not stream_group_id:
return
stream_group = groups.get(stream_group_id)
if not stream_group:
return stream_group_id
rendition = stream_group[0]
return rendition.get('NAME') or stream_group_id
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_info = parse_m3u8_attributes(line)
last_stream_inf = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
media = parse_m3u8_attributes(line)
media_type = media.get('TYPE')
if media_type in ('VIDEO', 'AUDIO'):
group_id = media.get('GROUP-ID')
media_url = media.get('URI')
if media_url:
format_id = []
for v in (group_id, media.get('NAME')):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'language': media.get('LANGUAGE'),
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
}
if media_type == 'AUDIO':
f['vcodec'] = 'none'
if group_id and not audio_in_video_stream.get(group_id):
audio_in_video_stream[group_id] = False
formats.append(f)
else:
# When there is no URI in EXT-X-MEDIA let this tag's
# data be used by regular URI lines below
last_media = media
if media_type == 'AUDIO' and group_id:
audio_in_video_stream[group_id] = True
extract_media(line)
elif line.startswith('#') or not line.strip():
continue
else:
tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
tbr = float_or_none(
last_stream_inf.get('AVERAGE-BANDWIDTH') or
last_stream_inf.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF it still sometimes may be present
stream_name = last_info.get('NAME') or last_media.get('NAME')
stream_name = build_stream_name()
# Bandwidth of live streams may differ over time thus making
# format_id unpredictable. So it's better to keep provided
# format_id intact.
@ -1389,14 +1444,14 @@ class InfoExtractor(object):
f = {
'format_id': '-'.join(format_id),
'url': manifest_url,
'manifest_url': manifest_url,
'manifest_url': m3u8_url,
'tbr': tbr,
'ext': ext,
'fps': float_or_none(last_info.get('FRAME-RATE')),
'fps': float_or_none(last_stream_inf.get('FRAME-RATE')),
'protocol': entry_protocol,
'preference': preference,
}
resolution = last_info.get('RESOLUTION')
resolution = last_stream_inf.get('RESOLUTION')
if resolution:
mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
if mobj:
@ -1412,13 +1467,26 @@ class InfoExtractor(object):
'vbr': vbr,
'abr': abr,
})
f.update(parse_codecs(last_info.get('CODECS')))
if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none':
# TODO: update acodec for audio only formats with the same GROUP-ID
f['acodec'] = 'none'
codecs = parse_codecs(last_stream_inf.get('CODECS'))
f.update(codecs)
audio_group_id = last_stream_inf.get('AUDIO')
# As per [1, 4.3.4.1.1] any EXT-X-STREAM-INF tag which
# references a rendition group MUST have a CODECS attribute.
# However, this is not always respected, for example, [2]
# contains EXT-X-STREAM-INF tag which references AUDIO
# rendition group but does not have CODECS and despite
# referencing audio group an audio group, it represents
# a complete (with audio and video) format. So, for such cases
# we will ignore references to rendition groups and treat them
# as complete formats.
if audio_group_id and codecs and f.get('vcodec') != 'none':
audio_group = groups.get(audio_group_id)
if audio_group and audio_group[0].get('URI'):
# TODO: update acodec for audio only formats with
# the same GROUP-ID
f['acodec'] = 'none'
formats.append(f)
last_info = {}
last_media = {}
last_stream_inf = {}
return formats
@staticmethod
@ -1768,7 +1836,7 @@ class InfoExtractor(object):
if content_type == 'text':
# TODO implement WebVTT downloading
pass
elif content_type == 'video' or content_type == 'audio':
elif content_type in ('video', 'audio'):
base_url = ''
for element in (representation, adaptation_set, period, mpd_doc):
base_url_e = element.find(_add_ns('BaseURL'))
@ -1792,7 +1860,7 @@ class InfoExtractor(object):
'ext': mimetype2ext(mime_type),
'width': int_or_none(representation_attrib.get('width')),
'height': int_or_none(representation_attrib.get('height')),
'tbr': int_or_none(bandwidth, 1000),
'tbr': float_or_none(bandwidth, 1000),
'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
'fps': int_or_none(representation_attrib.get('frameRate')),
'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
@ -1933,6 +2001,12 @@ class InfoExtractor(object):
compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id)
def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
"""
Parse formats from ISM manifest.
References:
1. [MS-SSTR]: Smooth Streaming Protocol,
https://msdn.microsoft.com/en-us/library/ff469518.aspx
"""
if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
return []
@ -1954,8 +2028,11 @@ class InfoExtractor(object):
self.report_warning('%s is not a supported codec' % fourcc)
continue
tbr = int(track.attrib['Bitrate']) // 1000
width = int_or_none(track.get('MaxWidth'))
height = int_or_none(track.get('MaxHeight'))
# [1] does not mention Width and Height attributes. However,
# they're often present while MaxWidth and MaxHeight are
# missing, so should be used as fallbacks
width = int_or_none(track.get('MaxWidth') or track.get('Width'))
height = int_or_none(track.get('MaxHeight') or track.get('Height'))
sampling_rate = int_or_none(track.get('SamplingRate'))
track_url_pattern = re.sub(r'{[Bb]itrate}', track.attrib['Bitrate'], url_pattern)
@ -2106,7 +2183,7 @@ class InfoExtractor(object):
def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
formats = []
hdcore_sign = 'hdcore=3.7.0'
f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
f4m_url = re.sub(r'(https?://[^/]+)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
hds_host = hosts.get('hds')
if hds_host:
f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)
@ -2128,8 +2205,9 @@ class InfoExtractor(object):
def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
url_base = self._search_regex(r'(?:https?|rtmp|rtsp)(://[^?]+)', url, 'format url')
http_base_url = 'http' + url_base
url_base = self._search_regex(
r'(?:(?:https?|rtmp|rtsp):)?(//[^?]+)', url, 'format url')
http_base_url = '%s:%s' % ('http', url_base)
formats = []
if 'm3u8' not in skip_protocols:
formats.extend(self._extract_m3u8_formats(
@ -2163,24 +2241,30 @@ class InfoExtractor(object):
for protocol in ('rtmp', 'rtsp'):
if protocol not in skip_protocols:
formats.append({
'url': protocol + url_base,
'url': '%s:%s' % (protocol, url_base),
'format_id': protocol,
'protocol': protocol,
})
return formats
@staticmethod
def _find_jwplayer_data(webpage):
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
webpage)
if mobj:
return mobj.group('options')
try:
jwplayer_data = self._parse_json(mobj.group('options'),
video_id=video_id,
transform_source=transform_source)
except ExtractorError:
pass
else:
if isinstance(jwplayer_data, dict):
return jwplayer_data
def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
jwplayer_data = self._parse_json(
self._find_jwplayer_data(webpage), video_id,
transform_source=js_to_json)
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
return self._parse_jwplayer_data(
jwplayer_data, video_id, *args, **kwargs)
@ -2241,11 +2325,17 @@ class InfoExtractor(object):
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
urls = []
formats = []
for source in jwplayer_sources_data:
source_url = self._proto_relative_url(source['file'])
source_url = self._proto_relative_url(source.get('file'))
if not source_url:
continue
if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url)
if source_url in urls:
continue
urls.append(source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':

81
youtube_dl/extractor/condenast.py
View File

@ -16,7 +16,6 @@ from ..utils import (
mimetype2ext,
orderedSet,
parse_iso8601,
remove_end,
)
@ -50,10 +49,17 @@ class CondeNastIE(InfoExtractor):
'wmagazine': 'W Magazine',
}
_VALID_URL = r'https?://(?:video|www|player)\.(?P<site>%s)\.com/(?P<type>watch|series|video|embed(?:js)?)/(?P<id>[^/?#]+)' % '|'.join(_SITES.keys())
_VALID_URL = r'''(?x)https?://(?:video|www|player(?:-backend)?)\.(?:%s)\.com/
(?:
(?:
embed(?:js)?|
(?:script|inline)/video
)/(?P<id>[0-9a-f]{24})(?:/(?P<player_id>[0-9a-f]{24}))?(?:.+?\btarget=(?P<target>[^&]+))?|
(?P<type>watch|series|video)/(?P<display_id>[^/?#]+)
)''' % '|'.join(_SITES.keys())
IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
EMBED_URL = r'(?:https?:)?//player\.(?P<site>%s)\.com/(?P<type>embed(?:js)?)/.+?' % '|'.join(_SITES.keys())
EMBED_URL = r'(?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?' % '|'.join(_SITES.keys())
_TESTS = [{
'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
@ -89,6 +95,12 @@ class CondeNastIE(InfoExtractor):
'upload_date': '20150916',
'timestamp': 1442434955,
}
}, {
'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
'only_matching': True,
}, {
'url': 'http://player-backend.cnevids.com/script/video/59138decb57ac36b83000005.js',
'only_matching': True,
}]
def _extract_series(self, url, webpage):
@ -104,7 +116,7 @@ class CondeNastIE(InfoExtractor):
entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
return self.playlist_result(entries, playlist_title=title)
def _extract_video(self, webpage, url_type):
def _extract_video_params(self, webpage):
query = {}
params = self._search_regex(
r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
@ -123,17 +135,30 @@ class CondeNastIE(InfoExtractor):
'playerId': params['data-player'],
'target': params['id'],
})
video_id = query['videoId']
return query
def _extract_video(self, params):
video_id = params['videoId']
video_info = None
info_page = self._download_json(
'http://player.cnevids.com/player/video.js',
video_id, 'Downloading video info', fatal=False, query=query)
if info_page:
video_info = info_page.get('video')
if not video_info:
if params.get('playerId'):
info_page = self._download_json(
'http://player.cnevids.com/player/video.js',
video_id, 'Downloading video info', fatal=False, query=params)
if info_page:
video_info = info_page.get('video')
if not video_info:
info_page = self._download_webpage(
'http://player.cnevids.com/player/loader.js',
video_id, 'Downloading loader info', query=params)
else:
info_page = self._download_webpage(
'http://player.cnevids.com/player/loader.js',
video_id, 'Downloading loader info', query=query)
'https://player.cnevids.com/inline/video/%s.js' % video_id,
video_id, 'Downloading inline info', query={
'target': params.get('target', 'embedplayer')
})
if not video_info:
video_info = self._parse_json(
self._search_regex(
r'(?s)var\s+config\s*=\s*({.+?});', info_page, 'config'),
@ -161,9 +186,7 @@ class CondeNastIE(InfoExtractor):
})
self._sort_formats(formats)
info = self._search_json_ld(
webpage, video_id, fatal=False) if url_type != 'embed' else {}
info.update({
return {
'id': video_id,
'formats': formats,
'title': title,
@ -174,22 +197,26 @@ class CondeNastIE(InfoExtractor):
'series': video_info.get('series_title'),
'season': video_info.get('season_title'),
'timestamp': parse_iso8601(video_info.get('premiere_date')),
})
return info
'categories': video_info.get('categories'),
}
def _real_extract(self, url):
site, url_type, item_id = re.match(self._VALID_URL, url).groups()
video_id, player_id, target, url_type, display_id = re.match(self._VALID_URL, url).groups()
# Convert JS embed to regular embed
if url_type == 'embedjs':
parsed_url = compat_urlparse.urlparse(url)
url = compat_urlparse.urlunparse(parsed_url._replace(
path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/')))
url_type = 'embed'
if video_id:
return self._extract_video({
'videoId': video_id,
'playerId': player_id,
'target': target,
})
webpage = self._download_webpage(url, item_id)
webpage = self._download_webpage(url, display_id)
if url_type == 'series':
return self._extract_series(url, webpage)
else:
return self._extract_video(webpage, url_type)
params = self._extract_video_params(webpage)
info = self._search_json_ld(
webpage, display_id, fatal=False)
info.update(self._extract_video(params))
return info

5
youtube_dl/extractor/coub.py
View File

@ -24,12 +24,11 @@ class CoubIE(InfoExtractor):
'duration': 4.6,
'timestamp': 1428527772,
'upload_date': '20150408',
'uploader': 'Артём Лоскутников',
'uploader': 'Artyom Loskutnikov',
'uploader_id': 'artyom.loskutnikov',
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
'age_limit': 0,
},
}, {
@ -118,7 +117,6 @@ class CoubIE(InfoExtractor):
view_count = int_or_none(coub.get('views_count') or coub.get('views_increase_count'))
like_count = int_or_none(coub.get('likes_count'))
repost_count = int_or_none(coub.get('recoubs_count'))
comment_count = int_or_none(coub.get('comments_count'))
age_restricted = coub.get('age_restricted', coub.get('age_restricted_by_admin'))
if age_restricted is not None:
@ -137,7 +135,6 @@ class CoubIE(InfoExtractor):
'view_count': view_count,
'like_count': like_count,
'repost_count': repost_count,
'comment_count': comment_count,
'age_limit': age_limit,
'formats': formats,
}

7
youtube_dl/extractor/crackle.py
View File

@ -21,9 +21,10 @@ class CrackleIE(InfoExtractor):
'season_number': 8,
'episode_number': 4,
'subtitles': {
'en-US': [{
'ext': 'ttml',
}]
'en-US': [
{'ext': 'vtt'},
{'ext': 'tt'},
]
},
},
'params': {

12
youtube_dl/extractor/crunchyroll.py
View File

@ -171,7 +171,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'info_dict': {
'id': '727589',
'ext': 'mp4',
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance from this Judicial Injustice!",
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 – Give Me Deliverance From This Judicial Injustice!",
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Kadokawa Pictures Inc.',
@ -179,7 +179,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2,
'episode': 'Give Me Deliverance from this Judicial Injustice!',
'episode': 'Give Me Deliverance From This Judicial Injustice!',
'episode_number': 1,
},
'params': {
@ -390,7 +390,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
else:
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
webpage = self._download_webpage(
self._add_skip_wall(webpage_url), video_id,
headers=self.geo_verification_headers())
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
@ -565,7 +567,9 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
webpage = self._download_webpage(
self._add_skip_wall(url), show_id,
headers=self.geo_verification_headers())
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')

15
youtube_dl/extractor/cspan.py
View File

@ -10,6 +10,7 @@ from ..utils import (
smuggle_url,
determine_ext,
ExtractorError,
extract_attributes,
)
from .senateisvp import SenateISVPIE
from .ustream import UstreamIE
@ -68,6 +69,7 @@ class CSpanIE(InfoExtractor):
'uploader_id': '12987475',
},
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
@ -78,6 +80,19 @@ class CSpanIE(InfoExtractor):
if ustream_url:
return self.url_result(ustream_url, UstreamIE.ie_key())
if '&vod' not in url:
bc = self._search_regex(
r"(<[^>]+id='brightcove-player-embed'[^>]+>)",
webpage, 'brightcove embed', default=None)
if bc:
bc_attr = extract_attributes(bc)
bc_url = self.BRIGHTCOVE_URL_TEMPLATE % (
bc_attr.get('data-bcaccountid', '3162030207001'),
bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'),
bc_attr.get('data-newbcplayerid', 'default'),
bc_attr['data-bcid'])
return self.url_result(smuggle_url(bc_url, {'source_url': url}))
# We first look for clipid, because clipprog always appears before
patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
results = list(filter(None, (re.search(p, webpage) for p in patterns)))

55
youtube_dl/extractor/curiositystream.py
View File

@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
@ -46,9 +48,50 @@ class CuriosityStreamBaseIE(InfoExtractor):
def _extract_media_info(self, media):
video_id = compat_str(media['id'])
limelight_media_id = media['limelight_media_id']
title = media['title']
formats = []
for encoding in media.get('encodings', []):
m3u8_url = encoding.get('master_playlist_url')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
encoding_url = encoding.get('url')
file_url = encoding.get('file_url')
if not encoding_url and not file_url:
continue
f = {
'width': int_or_none(encoding.get('width')),
'height': int_or_none(encoding.get('height')),
'vbr': int_or_none(encoding.get('video_bitrate')),
'abr': int_or_none(encoding.get('audio_bitrate')),
'filesize': int_or_none(encoding.get('size_in_bytes')),
'vcodec': encoding.get('video_codec'),
'acodec': encoding.get('audio_codec'),
'container': encoding.get('container_type'),
}
for f_url in (encoding_url, file_url):
if not f_url:
continue
fmt = f.copy()
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
if rtmp:
fmt.update({
'url': rtmp.group('url'),
'play_path': rtmp.group('playpath'),
'app': rtmp.group('app'),
'ext': 'flv',
'format_id': 'rtmp',
})
else:
fmt.update({
'url': f_url,
'format_id': 'http',
})
formats.append(fmt)
self._sort_formats(formats)
subtitles = {}
for closed_caption in media.get('closed_captions', []):
sub_url = closed_caption.get('file')
@ -60,16 +103,14 @@ class CuriosityStreamBaseIE(InfoExtractor):
})
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'limelight:media:' + limelight_media_id,
'formats': formats,
'title': title,
'description': media.get('description'),
'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
'duration': int_or_none(media.get('duration')),
'tags': media.get('tags'),
'subtitles': subtitles,
'ie_key': 'LimelightMedia',
}
@ -78,14 +119,12 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
_VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
_TEST = {
'url': 'https://app.curiositystream.com/video/2',
'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
'md5': '262bb2f257ff301115f1973540de8983',
'info_dict': {
'id': '2',
'ext': 'mp4',
'title': 'How Did You Develop The Internet?',
'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
'timestamp': 1448388615,
'upload_date': '20151124',
}
}
@ -105,7 +144,7 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
'title': 'Curious Minds: The Internet',
'description': 'How is the internet shaping our lives in the 21st Century?',
},
'playlist_mincount': 17,
'playlist_mincount': 12,
}
def _real_extract(self, url):

7
youtube_dl/extractor/cwtv.py
View File

@ -82,6 +82,11 @@ class CWTVIE(InfoExtractor):
'url': quality_url,
'tbr': tbr,
})
video_metadata = video_data['assetFields']
ism_url = video_metadata.get('smoothStreamingUrl')
if ism_url:
formats.extend(self._extract_ism_formats(
ism_url, video_id, ism_id='mss', fatal=False))
self._sort_formats(formats)
thumbnails = [{
@ -90,8 +95,6 @@ class CWTVIE(InfoExtractor):
'height': image.get('height'),
} for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
video_metadata = video_data['assetFields']
subtitles = {
'en': [{
'url': video_metadata['UnicornCcUrl'],

12
youtube_dl/extractor/dailymail.py
View File

@ -2,9 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
determine_protocol,
try_get,
unescapeHTML,
)
@ -28,8 +30,14 @@ class DailyMailIE(InfoExtractor):
video_data = self._parse_json(self._search_regex(
r"data-opts='({.+?})'", webpage, 'video data'), video_id)
title = unescapeHTML(video_data['title'])
video_sources = self._download_json(video_data.get(
'sources', {}).get('url') or 'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id, video_id)
sources_url = (try_get(
video_data,
(lambda x: x['plugins']['sources']['url'],
lambda x: x['sources']['url']), compat_str) or
'http://www.dailymail.co.uk/api/player/%s/video-sources.json' % video_id)
video_sources = self._download_json(sources_url, video_id)
formats = []
for rendition in video_sources['renditions']:

126
youtube_dl/extractor/dailymotion.py
View File

@ -38,7 +38,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor):
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
_VALID_URL = r'(?i)https?://(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|#)/)?video|swf)/(?P<id>[^/?_]+)'
IE_NAME = 'dailymotion'
_FORMATS = [
@ -49,68 +49,82 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
('stream_h264_hd1080_url', 'hd180'),
]
_TESTS = [
{
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
'md5': '2137c41a8e78554bb09225b8eb322406',
'info_dict': {
'id': 'x2iuewm',
'ext': 'mp4',
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
'description': 'Several come bundled with the Steam Controller.',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 74,
'timestamp': 1425657362,
'upload_date': '20150306',
'uploader': 'IGN',
'uploader_id': 'xijv66',
'age_limit': 0,
'view_count': int,
}
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'info_dict': {
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review – Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 187,
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
'uploader_id': 'x1xm8ri',
'age_limit': 0,
'view_count': int,
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
'md5': '2137c41a8e78554bb09225b8eb322406',
'info_dict': {
'id': 'x2iuewm',
'ext': 'mp4',
'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News',
'description': 'Several come bundled with the Steam Controller.',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 74,
'timestamp': 1425657362,
'upload_date': '20150306',
'uploader': 'IGN',
'uploader_id': 'xijv66',
'age_limit': 0,
'view_count': int,
},
'skip': 'video gone',
}, {
# Vevo video
{
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
'info_dict': {
'title': 'Roar (Official)',
'id': 'USUV71301934',
'ext': 'mp4',
'uploader': 'Katy Perry',
'upload_date': '20130905',
},
'params': {
'skip_download': True,
},
'skip': 'VEVO is only available in some countries',
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
'info_dict': {
'title': 'Roar (Official)',
'id': 'USUV71301934',
'ext': 'mp4',
'uploader': 'Katy Perry',
'upload_date': '20130905',
},
'params': {
'skip_download': True,
},
'skip': 'VEVO is only available in some countries',
}, {
# age-restricted video
{
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
'md5': '0d667a7b9cebecc3c89ee93099c4159d',
'info_dict': {
'id': 'xyh2zz',
'ext': 'mp4',
'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
'uploader': 'HotWaves1012',
'age_limit': 18,
},
'skip': 'video gone',
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
'md5': '0d667a7b9cebecc3c89ee93099c4159d',
'info_dict': {
'id': 'xyh2zz',
'ext': 'mp4',
'title': 'Leanna Decker - Cyber Girl Of The Year Desires Nude [Playboy Plus]',
'uploader': 'HotWaves1012',
'age_limit': 18,
},
'skip': 'video gone',
}, {
# geo-restricted, player v5
{
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
},
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
}, {
# with subtitles
{
'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
'only_matching': True,
},
{
'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
'only_matching': True,
}
]
'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
'only_matching': True,
}, {
'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
'only_matching': True,
}, {
'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):

3
youtube_dl/extractor/democracynow.py
View File

@ -21,7 +21,8 @@ class DemocracynowIE(InfoExtractor):
'info_dict': {
'id': '2015-0703-001',
'ext': 'mp4',
'title': 'Daily Show',
'title': 'Daily Show for July 03, 2015',
'description': 'md5:80eb927244d6749900de6072c7cc2c86',
},
}, {
'url': 'http://www.democracynow.org/2015/7/3/this_flag_comes_down_today_bree',

59
youtube_dl/extractor/discoveryvr.py Normal file
View File

@ -0,0 +1,59 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import parse_duration
class DiscoveryVRIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?discoveryvr\.com/watch/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.discoveryvr.com/watch/discovery-vr-an-introduction',
'md5': '32b1929798c464a54356378b7912eca4',
'info_dict': {
'id': 'discovery-vr-an-introduction',
'ext': 'mp4',
'title': 'Discovery VR - An Introduction',
'description': 'md5:80d418a10efb8899d9403e61d8790f06',
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
bootstrap_data = self._search_regex(
r'root\.DVR\.bootstrapData\s+=\s+"({.+?})";',
webpage, 'bootstrap data')
bootstrap_data = self._parse_json(
bootstrap_data.encode('utf-8').decode('unicode_escape'),
display_id)
videos = self._parse_json(bootstrap_data['videos'], display_id)['allVideos']
video_data = next(video for video in videos if video.get('slug') == display_id)
series = video_data.get('showTitle')
title = episode = video_data.get('title') or series
if series and series != title:
title = '%s - %s' % (series, title)
formats = []
for f, format_id in (('cdnUriM3U8', 'mobi'), ('webVideoUrlSd', 'sd'), ('webVideoUrlHd', 'hd')):
f_url = video_data.get(f)
if not f_url:
continue
formats.append({
'format_id': format_id,
'url': f_url,
})
return {
'id': display_id,
'display_id': display_id,
'title': title,
'description': video_data.get('description'),
'thumbnail': video_data.get('thumbnail'),
'duration': parse_duration(video_data.get('runTime')),
'formats': formats,
'episode': episode,
'series': series,
}

2
youtube_dl/extractor/dotsub.py
View File

@ -35,7 +35,7 @@ class DotsubIE(InfoExtractor):
'thumbnail': 're:^https?://dotsub.com/media/747bcf58-bd59-45b7-8c8c-ac312d084ee6/p',
'duration': 290,
'timestamp': 1476767794.2809999,
'upload_date': '20160525',
'upload_date': '20161018',
'uploader': 'parthivi001',
'uploader_id': 'user52596202',
'view_count': int,

86
youtube_dl/extractor/douyutv.py
View File

@ -3,11 +3,14 @@ from __future__ import unicode_literals
import time
import hashlib
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unescapeHTML,
unified_strdate,
urljoin,
)
@ -20,7 +23,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732',
'display_id': 'iseven',
'ext': 'flv',
'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅',
@ -51,7 +54,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732',
'display_id': '17732',
'ext': 'flv',
'title': 're:^清晨醒脑！T-ARA根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^清晨醒脑！根本停不下来！ [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅',
@ -117,3 +120,82 @@ class DouyuTVIE(InfoExtractor):
'uploader': uploader,
'is_live': True,
}
class DouyuShowIE(InfoExtractor):
_VALID_URL = r'https?://v(?:mobile)?\.douyu\.com/show/(?P<id>[0-9a-zA-Z]+)'
_TESTS = [{
'url': 'https://v.douyu.com/show/rjNBdvnVXNzvE2yw',
'md5': '0c2cfd068ee2afe657801269b2d86214',
'info_dict': {
'id': 'rjNBdvnVXNzvE2yw',
'ext': 'mp4',
'title': '陈一发儿：砒霜 我有个室友系列！04-01 22点场',
'duration': 7150.08,
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '陈一发儿',
'uploader_id': 'XrZwYelr5wbK',
'uploader_url': 'https://v.douyu.com/author/XrZwYelr5wbK',
'upload_date': '20170402',
},
}, {
'url': 'https://vmobile.douyu.com/show/rjNBdvnVXNzvE2yw',
'only_matching': True,
}]
def _real_extract(self, url):
url = url.replace('vmobile.', 'v.')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
room_info = self._parse_json(self._search_regex(
r'var\s+\$ROOM\s*=\s*({.+});', webpage, 'room info'), video_id)
video_info = None
for trial in range(5):
# Sometimes Douyu rejects our request. Let's try it more times
try:
video_info = self._download_json(
'https://vmobile.douyu.com/video/getInfo', video_id,
query={'vid': video_id},
headers={
'Referer': url,
'x-requested-with': 'XMLHttpRequest',
})
break
except ExtractorError:
self._sleep(1, video_id)
if not video_info:
raise ExtractorError('Can\'t fetch video info')
formats = self._extract_m3u8_formats(
video_info['data']['video_url'], video_id,
entry_protocol='m3u8_native', ext='mp4')
upload_date = unified_strdate(self._html_search_regex(
r'<em>上传时间：</em><span>([^<]+)</span>', webpage,
'upload date', fatal=False))
uploader = uploader_id = uploader_url = None
mobj = re.search(
r'(?m)<a[^>]+href="/author/([0-9a-zA-Z]+)".+?<strong[^>]+title="([^"]+)"',
webpage)
if mobj:
uploader_id, uploader = mobj.groups()
uploader_url = urljoin(url, '/author/' + uploader_id)
return {
'id': video_id,
'title': room_info['name'],
'formats': formats,
'duration': room_info.get('duration'),
'thumbnail': room_info.get('pic'),
'upload_date': upload_date,
'uploader': uploader,
'uploader_id': uploader_id,
'uploader_url': uploader_url,
}

146
youtube_dl/extractor/drbonanza.py
View File

@ -1,135 +1,59 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
js_to_json,
parse_duration,
unescapeHTML,
)
class DRBonanzaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P<id>\d+))?(?:[#&]|$)'
_TESTS = [{
'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517',
_VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
_TEST = {
'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-',
'info_dict': {
'id': '65517',
'id': '40312',
'display_id': 'matador---0824-komme-fremmede-',
'ext': 'mp4',
'title': 'Talkshowet - Leonard Cohen',
'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca',
'title': 'MATADOR - 08:24. "Komme fremmede".',
'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84',
'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
'timestamp': 1295537932,
'upload_date': '20110120',
'duration': 3664,
'duration': 4613,
},
'params': {
'skip_download': True, # requires rtmp
},
}, {
'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410',
'md5': '6dfe039417e76795fb783c52da3de11d',
'info_dict': {
'id': '59410',
'ext': 'mp3',
'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission',
'description': 'md5:501e5a195749480552e214fbbed16c4e',
'thumbnail': r're:^https?://.*\.(?:gif|jpg)$',
'timestamp': 1223274900,
'upload_date': '20081006',
'duration': 7369,
},
}]
}
def _real_extract(self, url):
url_id = self._match_id(url)
webpage = self._download_webpage(url, url_id)
mobj = re.match(self._VALID_URL, url)
video_id, display_id = mobj.group('id', 'display_id')
if url_id:
info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json'))
else:
# Just fetch the first video on that page
info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json'))
webpage = self._download_webpage(url, display_id)
asset_id = str(info['AssetId'])
title = info['Title'].rstrip(' \'\"-,.:;!?')
duration = int_or_none(info.get('Duration'), scale=1000)
# First published online. "FirstPublished" contains the date for original airing.
timestamp = parse_iso8601(
re.sub(r'\.\d+$', '', info['Created']))
info = self._parse_html5_media_entries(
url, webpage, display_id, m3u8_id='hls',
m3u8_entry_protocol='m3u8_native')[0]
self._sort_formats(info['formats'])
def parse_filename_info(url):
match = re.search(r'/\d+_(?P<width>\d+)x(?P<height>\d+)x(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
if match:
return {
'width': int(match.group('width')),
'height': int(match.group('height')),
'vbr': int(match.group('bitrate')),
'ext': match.group('ext')
}
match = re.search(r'/\d+_(?P<bitrate>\d+)K\.(?P<ext>\w+)$', url)
if match:
return {
'vbr': int(match.group('bitrate')),
'ext': match.group(2)
}
return {}
asset = self._parse_json(
self._search_regex(
r'(?s)currentAsset\s*=\s*({.+?})\s*</script', webpage, 'asset'),
display_id, transform_source=js_to_json)
video_types = ['VideoHigh', 'VideoMid', 'VideoLow']
preferencemap = {
'VideoHigh': -1,
'VideoMid': -2,
'VideoLow': -3,
'Audio': -4,
}
title = unescapeHTML(asset['AssetTitle']).strip()
formats = []
for file in info['Files']:
if info['Type'] == 'Video':
if file['Type'] in video_types:
format = parse_filename_info(file['Location'])
format.update({
'url': file['Location'],
'format_id': file['Type'].replace('Video', ''),
'preference': preferencemap.get(file['Type'], -10),
})
if format['url'].startswith('rtmp'):
rtmp_url = format['url']
format['rtmp_live'] = True # --resume does not work
if '/bonanza/' in rtmp_url:
format['play_path'] = rtmp_url.split('/bonanza/')[1]
formats.append(format)
elif file['Type'] == 'Thumb':
thumbnail = file['Location']
elif info['Type'] == 'Audio':
if file['Type'] == 'Audio':
format = parse_filename_info(file['Location'])
format.update({
'url': file['Location'],
'format_id': file['Type'],
'vcodec': 'none',
})
formats.append(format)
elif file['Type'] == 'Thumb':
thumbnail = file['Location']
def extract(field):
return self._search_regex(
r'<div[^>]+>\s*<p>%s:<p>\s*</div>\s*<div[^>]+>\s*<p>([^<]+)</p>' % field,
webpage, field, default=None)
description = '%s\n%s\n%s\n' % (
info['Description'], info['Actors'], info['Colophon'])
self._sort_formats(formats)
display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id
display_id = re.sub(r'-+', '-', display_id)
return {
'id': asset_id,
info.update({
'id': asset.get('AssetId') or video_id,
'display_id': display_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
}
'description': extract('Programinfo'),
'duration': parse_duration(extract('Tid')),
'thumbnail': asset.get('AssetImageUrl'),
})
return info

34
youtube_dl/extractor/drtv.py
View File

@ -20,7 +20,7 @@ class DRTVIE(InfoExtractor):
IE_NAME = 'drtv'
_TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
'md5': '25e659cccc9a2ed956110a299fdf5983',
'md5': '7ae17b4e18eb5d29212f424a7511c184',
'info_dict': {
'id': 'klassen-darlig-taber-10',
'ext': 'mp4',
@ -30,21 +30,37 @@ class DRTVIE(InfoExtractor):
'upload_date': '20160823',
'duration': 606.84,
},
'params': {
'skip_download': True,
},
}, {
# embed
'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
'md5': '2c37175c718155930f939ef59952474a',
'info_dict': {
'id': 'christiania-pusher-street-ryddes-drdkrjpo',
'ext': 'mp4',
'title': 'LIVE Christianias rydning af Pusher Street er i gang',
'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
'timestamp': 1472800279,
'upload_date': '20160902',
'duration': 131.4,
},
'params': {
'skip_download': True,
},
}, {
# with SignLanguage formats
'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
'info_dict': {
'id': 'historien-om-danmark-stenalder',
'ext': 'mp4',
'title': 'Historien om Danmark: Stenalder (1)',
'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
'timestamp': 1490401996,
'upload_date': '20170325',
'duration': 3502.04,
'formats': 'mincount:20',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -88,7 +104,7 @@ class DRTVIE(InfoExtractor):
elif kind in ('VideoResource', 'AudioResource'):
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
restricted_to_denmark = asset.get('RestrictedToDenmark')
spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
asset_target = asset.get('Target')
for link in asset.get('Links', []):
uri = link.get('Uri')
if not uri:
@ -96,9 +112,9 @@ class DRTVIE(InfoExtractor):
target = link.get('Target')
format_id = target or ''
preference = None
if spoken_subtitles:
if asset_target in ('SpokenSubtitles', 'SignLanguage'):
preference = -1
format_id += '-spoken-subtitles'
format_id += '-%s' % asset_target
if target == 'HDS':
f4m_formats = self._extract_f4m_formats(
uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',

101
youtube_dl/extractor/dvtv.py
View File

@ -5,9 +5,12 @@ import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
unescapeHTML,
determine_ext,
ExtractorError,
int_or_none,
js_to_json,
mimetype2ext,
unescapeHTML,
)
@ -24,14 +27,7 @@ class DVTVIE(InfoExtractor):
'id': 'dc0768de855511e49e4b0025900fea04',
'ext': 'mp4',
'title': 'Vondra o Českém století: Při pohledu na Havla mi bylo trapně',
}
}, {
'url': 'http://video.aktualne.cz/dvtv/stropnicky-policie-vrbetice-preventivne-nekontrolovala/r~82ed4322849211e4a10c0025900fea04/',
'md5': '6388f1941b48537dbd28791f712af8bf',
'info_dict': {
'id': '72c02230849211e49f60002590604f2e',
'ext': 'mp4',
'title': 'Stropnický: Policie Vrbětice preventivně nekontrolovala',
'duration': 1484,
}
}, {
'url': 'http://video.aktualne.cz/dvtv/dvtv-16-12-2014-utok-talibanu-boj-o-kliniku-uprchlici/r~973eb3bc854e11e498be002590604f2e/',
@ -44,55 +40,100 @@ class DVTVIE(InfoExtractor):
'info_dict': {
'id': 'b0b40906854d11e4bdad0025900fea04',
'ext': 'mp4',
'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne'
'title': 'Drtinová Veselovský TV 16. 12. 2014: Témata dne',
'description': 'md5:0916925dea8e30fe84222582280b47a0',
'timestamp': 1418760010,
'upload_date': '20141216',
}
}, {
'md5': '5f7652a08b05009c1292317b449ffea2',
'info_dict': {
'id': '420ad9ec854a11e4bdad0025900fea04',
'ext': 'mp4',
'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka'
'title': 'Školní masakr možná změní boj s Talibanem, říká novinářka',
'description': 'md5:ff2f9f6de73c73d7cef4f756c1c1af42',
'timestamp': 1418760010,
'upload_date': '20141216',
}
}, {
'md5': '498eb9dfa97169f409126c617e2a3d64',
'info_dict': {
'id': '95d35580846a11e4b6d20025900fea04',
'ext': 'mp4',
'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?'
'title': 'Boj o kliniku: Veřejný zájem, nebo právo na majetek?',
'description': 'md5:889fe610a70fee5511dc3326a089188e',
'timestamp': 1418760010,
'upload_date': '20141216',
}
}, {
'md5': 'b8dc6b744844032dab6ba3781a7274b9',
'info_dict': {
'id': '6fe14d66853511e4833a0025900fea04',
'ext': 'mp4',
'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády'
'title': 'Pánek: Odmítání syrských uprchlíků je ostudou české vlády',
'description': 'md5:544f86de6d20c4815bea11bf2ac3004f',
'timestamp': 1418760010,
'upload_date': '20141216',
}
}],
}, {
'url': 'https://video.aktualne.cz/dvtv/zeman-si-jen-leci-mindraky-sobotku-nenavidi-a-babis-se-mu-te/r~960cdb3a365a11e7a83b0025900fea04/',
'md5': 'f8efe9656017da948369aa099788c8ea',
'info_dict': {
'id': '3c496fec365911e7a6500025900fea04',
'ext': 'mp4',
'title': 'Zeman si jen léčí mindráky, Sobotku nenávidí a Babiš se mu teď hodí, tvrdí Kmenta',
'duration': 1103,
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://video.aktualne.cz/v-cechach-poprve-zazni-zelenkova-zrestaurovana-mse/r~45b4b00483ec11e4883b002590604f2e/',
'only_matching': True,
}]
def _parse_video_metadata(self, js, video_id):
metadata = self._parse_json(js, video_id, transform_source=js_to_json)
data = self._parse_json(js, video_id, transform_source=js_to_json)
title = unescapeHTML(data['title'])
formats = []
for video in metadata['sources']:
ext = video['type'][6:]
formats.append({
'url': video['file'],
'ext': ext,
'format_id': '%s-%s' % (ext, video['label']),
'height': int(video['label'].rstrip('p')),
'fps': 25,
})
for video in data['sources']:
video_url = video.get('file')
if not video_url:
continue
video_type = video.get('type')
ext = determine_ext(video_url, mimetype2ext(video_type))
if video_type == 'application/vnd.apple.mpegurl' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif video_type == 'application/dash+xml' or ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))
else:
label = video.get('label')
height = self._search_regex(
r'^(\d+)[pP]', label or '', 'height', default=None)
format_id = ['http']
for f in (ext, label):
if f:
format_id.append(f)
formats.append({
'url': video_url,
'format_id': '-'.join(format_id),
'height': int_or_none(height),
})
self._sort_formats(formats)
return {
'id': metadata['mediaid'],
'title': unescapeHTML(metadata['title']),
'thumbnail': self._proto_relative_url(metadata['image'], 'http:'),
'id': data.get('mediaid') or video_id,
'title': title,
'description': data.get('description'),
'thumbnail': data.get('image'),
'duration': int_or_none(data.get('duration')),
'timestamp': int_or_none(data.get('pubtime')),
'formats': formats
}
@ -103,7 +144,7 @@ class DVTVIE(InfoExtractor):
# single video
item = self._search_regex(
r"(?s)embedData[0-9a-f]{32}\['asset'\]\s*=\s*(\{.+?\});",
r'(?s)embedData[0-9a-f]{32}\[["\']asset["\']\]\s*=\s*(\{.+?\});',
webpage, 'video', default=None, fatal=False)
if item:
@ -113,6 +154,8 @@ class DVTVIE(InfoExtractor):
items = re.findall(
r"(?s)BBX\.context\.assets\['[0-9a-f]{32}'\]\.push\(({.+?})\);",
webpage)
if not items:
items = re.findall(r'(?s)var\s+asset\s*=\s*({.+?});\n', webpage)
if items:
return {

67
youtube_dl/extractor/extractors.py
View File

@ -19,6 +19,7 @@ from .acast import (
ACastChannelIE,
)
from .addanime import AddAnimeIE
from .adn import ADNIE
from .adobetv import (
AdobeTVIE,
AdobeTVShowIE,
@ -40,6 +41,7 @@ from .alphaporno import AlphaPornoIE
from .amcnetworks import AMCNetworksIE
from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE
from .anvato import AnvatoIE
from .anysex import AnySexIE
from .aol import AolIE
from .allocine import AllocineIE
@ -86,7 +88,6 @@ from .azmedien import (
AZMedienPlaylistIE,
AZMedienShowPlaylistIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
@ -97,7 +98,10 @@ from .bbc import (
BBCCoUkPlaylistIE,
BBCIE,
)
from .beampro import BeamProLiveIE
from .beampro import (
BeamProLiveIE,
BeamProVodIE,
)
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
@ -164,7 +168,10 @@ from .ccc import CCCIE
from .ccma import CCMAIE
from .cctv import CCTVIE
from .cda import CDAIE
from .ceskatelevize import CeskaTelevizeIE
from .ceskatelevize import (
CeskaTelevizeIE,
CeskaTelevizePoradyIE,
)
from .channel9 import Channel9IE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
@ -247,7 +254,10 @@ from .democracynow import DemocracynowIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .douyutv import (
DouyuShowIE,
DouyuTVIE,
)
from .dplay import (
DPlayIE,
DPlayItIE,
@ -272,6 +282,7 @@ from .discoverygo import (
DiscoveryGoPlaylistIE,
)
from .discoverynetworks import DiscoveryNetworksDeIE
from .discoveryvr import DiscoveryVRIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .dropbox import DropboxIE
@ -345,9 +356,9 @@ from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,
FranceTvInfoIE,
FranceTVIE,
FranceTVEmbedIE,
FranceTVInfoIE,
GenerationQuoiIE,
CultureboxIE,
)
@ -379,6 +390,7 @@ from .globo import (
GloboArticleIE,
)
from .go import GoIE
from .go90 import Go90IE
from .godtube import GodTubeIE
from .godtv import GodTVIE
from .golem import GolemIE
@ -536,6 +548,8 @@ from .mangomolo import (
)
from .matchtv import MatchTVIE
from .mdr import MDRIE
from .mediaset import MediasetIE
from .medici import MediciIE
from .meipai import MeipaiIE
from .melonvod import MelonVODIE
from .meta import METAIE
@ -656,6 +670,8 @@ from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE
from .noco import NocoIE
from .nonktube import NonkTubeIE
from .noovo import NoovoIE
from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
from .nova import NovaIE
@ -724,10 +740,14 @@ from .openload import OpenloadIE
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
ORFFM4IE,
ORFOE1IE,
ORFIPTVIE,
)
from .packtpub import (
PacktPubIE,
PacktPubCourseIE,
)
from .pandatv import PandaTVIE
from .pandoratv import PandoraTVIE
from .parliamentliveuk import ParliamentLiveUKIE
@ -797,7 +817,7 @@ from .radiojavan import RadioJavanIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import (
RaiTVIE,
RaiPlayIE,
RaiIE,
)
from .rbmaradio import RBMARadioIE
@ -828,7 +848,11 @@ from .rozhlas import RozhlasIE
from .rtbf import RTBFIE
from .rte import RteIE, RteRadioIE
from .rtlnl import RtlNlIE
from .rtl2 import RTL2IE
from .rtl2 import (
RTL2IE,
RTL2YouIE,
RTL2YouSeriesIE,
)
from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
@ -924,6 +948,7 @@ 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
@ -970,6 +995,7 @@ from .theplatform import (
from .thescene import TheSceneIE
from .thesixtyone import TheSixtyOneIE
from .thestar import TheStarIE
from .thesun import TheSunIE
from .theweatherchannel import TheWeatherChannelIE
from .thisamericanlife import ThisAmericanLifeIE
from .thisav import ThisAVIE
@ -996,11 +1022,6 @@ from .trilulilu import TriluliluIE
from .trutv import TruTVIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
from .tudou import (
TudouIE,
TudouPlaylistIE,
TudouAlbumIE,
)
from .tumblr import TumblrIE
from .tunein import (
TuneInClipIE,
@ -1016,8 +1037,10 @@ from .tv2 import (
TV2IE,
TV2ArticleIE,
)
from .tv2hu import TV2HuIE
from .tv3 import TV3IE
from .tv4 import TV4IE
from .tv5mondeplus import TV5MondePlusIE
from .tva import TVAIE
from .tvanouvelles import (
TVANouvellesIE,
@ -1078,6 +1101,10 @@ from .uplynk import (
UplynkIE,
UplynkPreplayIE,
)
from .upskill import (
UpskillIE,
UpskillCourseIE,
)
from .urort import UrortIE
from .urplay import URPlayIE
from .usanetwork import USANetworkIE
@ -1105,6 +1132,7 @@ from .vgtv import (
from .vh1 import VH1IE
from .vice import (
ViceIE,
ViceArticleIE,
ViceShowIE,
)
from .viceland import VicelandIE
@ -1177,6 +1205,11 @@ from .voxmedia import VoxMediaIE
from .vporn import VpornIE
from .vrt import VRTIE
from .vrak import VrakIE
from .vrv import (
VRVIE,
VRVSeriesIE,
)
from .vshare import VShareIE
from .medialaan import MedialaanIE
from .vube import VubeIE
from .vuclip import VuClipIE
@ -1210,7 +1243,10 @@ from .wrzuta import (
WrzutaIE,
WrzutaPlaylistIE,
)
from .wsj import WSJIE
from .wsj import (
WSJIE,
WSJArticleIE,
)
from .xbef import XBefIE
from .xboxclips import XboxClipsIE
from .xfileshare import XFileShareIE
@ -1272,5 +1308,6 @@ from .youtube import (
YoutubeWatchLaterIE,
)
from .zapiks import ZapiksIE
from .zaq1 import Zaq1IE
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import ZingMp3IE

9
youtube_dl/extractor/foxsports.py
View File

@ -11,10 +11,10 @@ class FoxSportsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?foxsports\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.foxsports.com/video?vid=432609859715',
'url': 'http://www.foxsports.com/tennessee/video/432609859715',
'md5': 'b49050e955bebe32c301972e4012ac17',
'info_dict': {
'id': 'i0qKWsk3qJaM',
'id': 'bwduI3X_TgUB',
'ext': 'mp4',
'title': 'Courtney Lee on going up 2-0 in series vs. Blazers',
'description': 'Courtney Lee talks about Memphis being focused.',
@ -31,8 +31,9 @@ class FoxSportsIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
config = self._parse_json(
self._search_regex(
r"data-player-config='([^']+)'", webpage, 'data player config'),
self._html_search_regex(
r"""class="[^"]*(?:fs-player|platformPlayer-wrapper)[^"]*".+?data-player-config='([^']+)'""",
webpage, 'data player config'),
video_id)
return self.url_result(smuggle_url(update_url_query(

223
youtube_dl/extractor/francetv.py
View File

@ -21,11 +21,13 @@ from .dailymotion import (
class FranceTVBaseInfoExtractor(InfoExtractor):
def _extract_video(self, video_id, catalogue):
def _extract_video(self, video_id, catalogue=None):
info = self._download_json(
'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
% (video_id, catalogue),
video_id, 'Downloading video JSON')
'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
video_id, 'Downloading video JSON', query={
'idDiffusion': video_id,
'catalogue': catalogue or '',
})
if info.get('status') == 'NOK':
raise ExtractorError(
@ -109,27 +111,100 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
}
class PluzzIE(FranceTVBaseInfoExtractor):
IE_NAME = 'pluzz.francetv.fr'
_VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
class FranceTVIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?france\.tv|mobile\.france\.tv)/(?:[^/]+/)*(?P<id>[^/]+)\.html'
# Can't use tests, videos expire in 7 days
_TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': {
'id': '157550144',
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
'timestamp': 1494156300,
'upload_date': '20170507',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
}, {
# france3
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
'only_matching': True,
}, {
# france4
'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
'only_matching': True,
}, {
# france5
'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
'only_matching': True,
}, {
# franceo
'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
'only_matching': True,
}, {
# france2 live
'url': 'https://www.france.tv/france-2/direct.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
'only_matching': True,
}, {
'url': 'https://mobile.france.tv/france-5/c-dans-l-air/137347-emission-du-vendredi-12-mai-2017.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/142749-rouge-sang.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_meta(
'id_video', webpage, 'video id', default=None)
catalogue = None
video_id = self._search_regex(
r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'video id', default=None, group='id')
if not video_id:
video_id = self._search_regex(
r'data-diffusion=["\'](\d+)', webpage, 'video id')
return self._extract_video(video_id, 'Pluzz')
video_id, catalogue = self._html_search_regex(
r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._extract_video(video_id, catalogue)
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'
_TEST = {
'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
'info_dict': {
'id': 'NI_983319',
'ext': 'mp4',
'title': 'Le Pen Reims',
'upload_date': '20170505',
'timestamp': 1493981780,
'duration': 16,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
video_id)
return self._extract_video(video['video_id'], video.get('catalog'))
class FranceTVInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
@ -233,124 +308,6 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
return self._extract_video(video_id, catalogue)
class FranceTVIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetv'
IE_DESC = 'France 2, 3, 4, 5 and Ô'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?france[2345o]\.fr/
(?:
emissions/[^/]+/(?:videos|diffusions)|
emission/[^/]+|
videos|
jt
)
/|
embed\.francetv\.fr/\?ue=
)
(?P<id>[^/?]+)
'''
_TESTS = [
# france2
{
'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
'md5': 'c03fc87cb85429ffd55df32b9fc05523',
'info_dict': {
'id': '109169362',
'ext': 'flv',
'title': '13h15, le dimanche...',
'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
'upload_date': '20140914',
'timestamp': 1410693600,
},
},
# france3
{
'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
'md5': '679bb8f8921f8623bd658fa2f8364da0',
'info_dict': {
'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
'ext': 'mp4',
'title': 'Le scandale du prix des médicaments',
'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
'upload_date': '20131113',
'timestamp': 1384380000,
},
},
# france4
{
'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
'info_dict': {
'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
'ext': 'mp4',
'title': 'Hero Corp Making of - Extrait 1',
'description': 'md5:c87d54871b1790679aec1197e73d650a',
'upload_date': '20131106',
'timestamp': 1383766500,
},
},
# france5
{
'url': 'http://www.france5.fr/emissions/c-a-dire/videos/quels_sont_les_enjeux_de_cette_rentree_politique__31-08-2015_908948?onglet=tous&page=1',
'md5': 'f6c577df3806e26471b3d21631241fd0',
'info_dict': {
'id': '123327454',
'ext': 'flv',
'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
'upload_date': '20150831',
'timestamp': 1441035120,
},
},
# franceo
{
'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
'md5': '47d5816d3b24351cdce512ad7ab31da8',
'info_dict': {
'id': '125377621',
'ext': 'flv',
'title': 'Infô soir',
'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
'upload_date': '20150718',
'timestamp': 1437241200,
'duration': 414,
},
},
{
# francetv embed
'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
'info_dict': {
'id': 'EV_30231',
'ext': 'flv',
'title': 'Alcaline, le concert avec Calogero',
'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
'upload_date': '20150226',
'timestamp': 1424989860,
'duration': 5400,
},
},
{
'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
'only_matching': True,
},
{
'url': 'http://www.franceo.fr/videos/125377617',
'only_matching': True,
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id, catalogue = self._html_search_regex(
r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._extract_video(video_id, catalogue)
class GenerationQuoiIE(InfoExtractor):
IE_NAME = 'france2.fr:generation-quoi'
_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'

275
youtube_dl/extractor/funimation.py
View File

@ -2,231 +2,148 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse_unquote_plus,
)
from ..compat import compat_HTTPError
from ..utils import (
clean_html,
determine_ext,
int_or_none,
sanitized_Request,
js_to_json,
ExtractorError,
urlencode_postdata
)
class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
_NETRC_MACHINE = 'funimation'
_TOKEN = None
_TESTS = [{
'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
'info_dict': {
'id': '658',
'display_id': 'breeze',
'ext': 'mp4',
'title': 'Air - 1 - Breeze',
'description': 'md5:1769f43cd5fc130ace8fd87232207892',
'thumbnail': r're:https?://.*\.jpg',
},
'skip': 'Access without user interaction is forbidden by CloudFlare, and video removed',
}, {
'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
'info_dict': {
'id': '31128',
'id': '91144',
'display_id': 'role-play',
'ext': 'mp4',
'title': '.hack//SIGN - 1 - Role Play',
'title': '.hack//SIGN - Role Play',
'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
'thumbnail': r're:https?://.*\.jpg',
},
'skip': 'Access without user interaction is forbidden by CloudFlare',
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
'info_dict': {
'id': '9635',
'id': '210051',
'display_id': 'broadcast-dub-preview',
'ext': 'mp4',
'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
'skip': 'Access without user interaction is forbidden by CloudFlare',
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
}]
_LOGIN_URL = 'http://www.funimation.com/login'
def _download_webpage(self, *args, **kwargs):
try:
return super(FunimationIE, self)._download_webpage(*args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
response = ee.cause.read()
if b'>Please complete the security check to access<' in response:
raise ExtractorError(
'Access to funimation.com is blocked by CloudFlare. '
'Please browse to http://www.funimation.com/, solve '
'the reCAPTCHA, export browser cookies to a text file,'
' and then try again with --cookies YOUR_COOKIE_FILE.',
expected=True)
raise
def _extract_cloudflare_session_ua(self, url):
ci_session_cookie = self._get_cookies(url).get('ci_session')
if ci_session_cookie:
ci_session = compat_urllib_parse_unquote_plus(ci_session_cookie.value)
# ci_session is a string serialized by PHP function serialize()
# This case is simple enough to use regular expressions only
return self._search_regex(
r'"user_agent";s:\d+:"([^"]+)"', ci_session, 'user agent',
default=None)
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
data = urlencode_postdata({
'email_field': username,
'password_field': password,
})
user_agent = self._extract_cloudflare_session_ua(self._LOGIN_URL)
if not user_agent:
user_agent = 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'
login_request = sanitized_Request(self._LOGIN_URL, data, headers={
'User-Agent': user_agent,
'Content-Type': 'application/x-www-form-urlencoded'
})
login_page = self._download_webpage(
login_request, None, 'Logging in as %s' % username)
if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
return
error = self._html_search_regex(
r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
login_page, 'error messages', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
try:
data = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
None, 'Logging in as %s' % username, data=urlencode_postdata({
'username': username,
'password': password,
}))
self._TOKEN = data['token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
error = self._parse_json(e.cause.read().decode(), None)['error']
raise ExtractorError(error, expected=True)
raise
def _real_initialize(self):
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def _search_kane(name):
return self._search_regex(
r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
webpage, name, default=None)
title_data = self._parse_json(self._search_regex(
r'TITLE_DATA\s*=\s*({[^}]+})',
webpage, 'title data', default=''),
display_id, js_to_json, fatal=False) or {}
video_id = title_data.get('id') or self._search_regex([
r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
r'<iframe[^>]+src="/player/(\d+)"',
], webpage, 'video_id', default=None)
if not video_id:
player_url = self._html_search_meta([
'al:web:url',
'og:video:url',
'og:video:secure_url',
], webpage, fatal=True)
video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
series = _search_kane('showName')
if series:
title = '%s - %s' % (series, title)
description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
try:
headers = {}
if self._TOKEN:
headers['Authorization'] = 'Token %s' % self._TOKEN
sources = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
video_id, headers=headers)['items']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read(), video_id)['errors'][0]
raise ExtractorError('%s said: %s' % (
self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
raise
errors = []
formats = []
ERRORS_MAP = {
'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
'ERROR_VIDEO_EXPIRED': 'videoExpired',
'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
}
USER_AGENTS = (
# PC UA is served with m3u8 that provides some bonus lower quality formats
('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
# Mobile UA allows to extract direct links and also does not fail when
# PC UA fails with hulu error (e.g.
# http://www.funimation.com/shows/hacksign/videos/official/role-play)
('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
)
user_agent = self._extract_cloudflare_session_ua(url)
if user_agent:
USER_AGENTS = ((None, user_agent),)
for kind, user_agent in USER_AGENTS:
request = sanitized_Request(url)
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(
request, display_id,
'Downloading %s webpage' % kind if kind else 'Downloading webpage')
playlist = self._parse_json(
self._search_regex(
r'var\s+playersData\s*=\s*(\[.+?\]);\n',
webpage, 'players data'),
display_id)[0]['playlist']
items = next(item['items'] for item in playlist if item.get('items'))
item = next(item for item in items if item.get('itemAK') == display_id)
error_messages = {}
video_error_messages = self._search_regex(
r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
webpage, 'error messages', default=None)
if video_error_messages:
error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
if error_messages_json:
for _, error in error_messages_json.items():
type_ = error.get('type')
description = error.get('description')
content = error.get('content')
if type_ == 'text' and description and content:
error_message = ERRORS_MAP.get(description)
if error_message:
error_messages[error_message] = content
for video in item.get('videoSet', []):
auth_token = video.get('authToken')
if not auth_token:
continue
funimation_id = video.get('FUNImationID') or video.get('videoId')
preference = 1 if video.get('languageMode') == 'dub' else 0
if not auth_token.startswith('?'):
auth_token = '?%s' % auth_token
for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
format_url = video.get('%sUrl' % quality)
if not format_url:
continue
if not format_url.startswith(('http', '//')):
errors.append(format_url)
continue
if determine_ext(format_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
else:
tbr = int_or_none(self._search_regex(
r'-(\d+)[Kk]', format_url, 'tbr', default=None))
formats.append({
'url': format_url + auth_token,
'format_id': '%s-http-%dp' % (funimation_id, height),
'height': height,
'tbr': tbr,
'preference': preference,
})
if not formats and errors:
raise ExtractorError(
'%s returned error: %s'
% (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
expected=True)
for source in sources:
source_url = source.get('src')
if not source_url:
continue
source_type = source.get('videoType') or determine_ext(source_url)
if source_type == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4',
m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': source_type,
'url': source_url,
})
self._sort_formats(formats)
title = item['title']
artist = item.get('artist')
if artist:
title = '%s - %s' % (artist, title)
description = self._og_search_description(webpage) or item.get('description')
thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
video_id = item.get('itemId') or display_id
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
'episode_number': int_or_none(title_data.get('episodeNum')),
'episode': episode,
'season_id': title_data.get('seriesId'),
'formats': formats,
}

3
youtube_dl/extractor/funnyordie.py
View File

@ -58,8 +58,7 @@ class FunnyOrDieIE(InfoExtractor):
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
source_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
m3u8_formats))
lambda f: f.get('vcodec') != 'none', m3u8_formats))
bitrates = [int(bitrate) for bitrate in re.findall(r'[,/]v(\d+)(?=[,/])', m3u8_url)]
bitrates.sort()

3
youtube_dl/extractor/gamespot.py
View File

@ -78,8 +78,7 @@ class GameSpotIE(OnceIE):
if m3u8_formats:
self._sort_formats(m3u8_formats)
m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
m3u8_formats))
lambda f: f.get('vcodec') != 'none', m3u8_formats))
if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy()

106
youtube_dl/extractor/gaskrank.py
View File

@ -6,62 +6,52 @@ from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
js_to_json,
unified_strdate,
)
class GaskrankIE(InfoExtractor):
"""InfoExtractor for gaskrank.tv"""
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.html?'
_TESTS = [
{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
'id': '201601/26955',
'ext': 'mp4',
'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['motorrad-fun'],
'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
'uploader_id': 'Bikefun',
'upload_date': '20170110',
'uploader_url': None,
}
},
{
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
'id': '201106/15920',
'ext': 'mp4',
'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20160506',
'uploader_url': 'www.iomtt.com',
}
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.htm'
_TESTS = [{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
'id': '201601/26955',
'ext': 'mp4',
'title': 'Strike! Einparken können nur Männer - Flurschaden hält sich in Grenzen *lol*',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['motorrad-fun'],
'display_id': 'strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden',
'uploader_id': 'Bikefun',
'upload_date': '20170110',
'uploader_url': None,
}
]
}, {
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
'id': '201106/15920',
'ext': 'mp4',
'title': 'Isle of Man - Michael Dunlop vs Guy Martin - schwindelig kucken',
'thumbnail': r're:^https?://.*\.jpg$',
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20170523',
'uploader_url': 'www.iomtt.com',
}
}]
def _real_extract(self, url):
"""extract information from gaskrank.tv"""
def fix_json(code):
"""Removes trailing comma in json: {{},} --> {{}}"""
return re.sub(r',\s*}', r'}', js_to_json(code))
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, fatal=True)
categories = [re.match(self._VALID_URL, url).group('categories')]
title = self._search_regex(
r'movieName\s*:\s*\'([^\']*)\'',
webpage, 'title')
thumbnail = self._search_regex(
r'poster\s*:\s*\'([^\']*)\'',
webpage, 'thumbnail', default=None)
mobj = re.search(
r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])',
@ -89,29 +79,14 @@ class GaskrankIE(InfoExtractor):
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
playlist = self._parse_json(
self._search_regex(
r'playlist\s*:\s*\[([^\]]*)\]',
webpage, 'playlist', default='{}'),
display_id, transform_source=fix_json, fatal=False)
video_id = self._search_regex(
r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
playlist.get('0').get('src'), 'video id')
webpage, 'video id', default=display_id)
formats = []
for key in playlist:
formats.append({
'url': playlist[key]['src'],
'format_id': key,
'quality': playlist[key].get('quality')})
self._sort_formats(formats, field_preference=['format_id'])
return {
entry = self._parse_html5_media_entries(url, webpage, video_id)[0]
entry.update({
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'categories': categories,
'display_id': display_id,
'uploader_id': uploader_id,
@ -120,4 +95,7 @@ class GaskrankIE(InfoExtractor):
'tags': tags,
'view_count': view_count,
'average_rating': average_rating,
}
})
self._sort_formats(entry['formats'])
return entry

15
youtube_dl/extractor/gdcvault.py
View File

@ -75,6 +75,19 @@ class GDCVaultIE(InfoExtractor):
'format': 'jp', # The japanese audio
}
},
{
# gdc-player.html
'url': 'http://www.gdcvault.com/play/1435/An-American-engine-in-Tokyo',
'info_dict': {
'id': '1435',
'display_id': 'An-American-engine-in-Tokyo',
'ext': 'flv',
'title': 'An American Engine in Tokyo:/nThe collaboration of Epic Games and Square Enix/nFor THE LAST REMINANT',
},
'params': {
'skip_download': True, # Requires rtmpdump
},
},
]
def _login(self, webpage_url, display_id):
@ -128,7 +141,7 @@ class GDCVaultIE(InfoExtractor):
'title': title,
}
PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/player.*?\.html.*?".*?</iframe>'
PLAYER_REGEX = r'<iframe src="(?P<xml_root>.+?)/(?:gdc-)?player.*?\.html.*?".*?</iframe>'
xml_root = self._html_search_regex(
PLAYER_REGEX, start_page, 'xml root', default=None)

294
youtube_dl/extractor/generic.py
View File

@ -85,6 +85,11 @@ from .ustream import UstreamIE
from .openload import OpenloadIE
from .videopress import VideoPressIE
from .rutube import RutubeIE
from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
from .wistia import WistiaIE
from .mediaset import MediasetIE
class GenericIE(InfoExtractor):
@ -429,6 +434,22 @@ class GenericIE(InfoExtractor):
'skip_download': True, # m3u8 download
},
},
{
# Brightcove video in <iframe>
'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
'md5': '36d74ef5e37c8b4a2ce92880d208b968',
'info_dict': {
'id': '5360463607001',
'ext': 'mp4',
'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼（Zade Dirani）在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》（HEARTBEAT），为受到六年冲突影响的叙利亚儿童发出强烈呐喊，呼吁世界做出共同努力，使叙利亚儿童重新获得享有正常童年生活的权利。',
'uploader': 'United Nations',
'uploader_id': '1362235914001',
'timestamp': 1489593889,
'upload_date': '20170315',
},
'add_ie': ['BrightcoveLegacy'],
},
{
# Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
@ -449,6 +470,59 @@ class GenericIE(InfoExtractor):
},
}],
},
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
'info_dict': {
'id': '5255815316001',
'ext': 'mp4',
'title': 'Sprocket Video - China',
'description': 'Sprocket Video - China',
'uploader': 'HP-Video Gallery',
'timestamp': 1482263210,
'upload_date': '20161220',
'uploader_id': '1107601872001',
},
'params': {
'skip_download': True, # m3u8 download
},
'skip': 'video rotates...weekly?',
},
{
# Brightcove:new type [2].
'url': 'http://www.delawaresportszone.com/video-st-thomas-more-earns-first-trip-to-basketball-semis',
'md5': '2b35148fcf48da41c9fb4591650784f3',
'info_dict': {
'id': '5348741021001',
'ext': 'mp4',
'upload_date': '20170306',
'uploader_id': '4191638492001',
'timestamp': 1488769918,
'title': 'VIDEO: St. Thomas More earns first trip to basketball semis',
},
},
{
# Alternative brightcove <video> attributes
'url': 'http://www.programme-tv.net/videos/extraits/81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche/',
'info_dict': {
'id': '81095-guillaume-canet-evoque-les-rumeurs-d-infidelite-de-marion-cotillard-avec-brad-pitt-dans-vivement-dimanche',
'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche, Extraits : toutes les vidéos avec Télé-Loisirs",
},
'playlist': [{
'md5': '732d22ba3d33f2f3fc253c39f8f36523',
'info_dict': {
'id': '5311302538001',
'ext': 'mp4',
'title': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche",
'description': "Guillaume Canet évoque les rumeurs d'infidélité de Marion Cotillard avec Brad Pitt dans Vivement Dimanche (France 2, 5 février 2017)",
'timestamp': 1486321708,
'upload_date': '20170205',
'uploader_id': '800000640001',
},
'only_matching': True,
}],
},
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
@ -730,6 +804,21 @@ class GenericIE(InfoExtractor):
'skip_download': True,
}
},
# YouTube <object> embed
{
'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
'md5': '516718101ec834f74318df76259fb3cc',
'info_dict': {
'id': 'msN87y-iEx0',
'ext': 'webm',
'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
'upload_date': '20080526',
'description': 'md5:0ffc78ea3f01b2e2c247d5f8d1d3c18d',
'uploader': 'Christopher Sykes',
'uploader_id': 'ChristopherJSykes',
},
'add_ie': ['Youtube'],
},
# Camtasia studio
{
'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
@ -991,6 +1080,20 @@ class GenericIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
# JWPlayer config passed as variable
'url': 'http://www.txxx.com/videos/3326530/ariele/',
'info_dict': {
'id': '3326530_hq',
'ext': 'mp4',
'title': 'ARIELE | Tube Cup',
'uploader': 'www.txxx.com',
'age_limit': 18,
},
'params': {
'skip_download': True,
}
},
# rtl.nl embed
{
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@ -1066,6 +1169,21 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Kaltura'],
},
{
# Kaltura iframe embed
'url': 'http://www.gsd.harvard.edu/event/i-m-pei-a-centennial-celebration/',
'md5': 'ae5ace8eb09dc1a35d03b579a9c2cc44',
'info_dict': {
'id': '0_f2cfbpwy',
'ext': 'mp4',
'title': 'I. M. Pei: A Centennial Celebration',
'description': 'md5:1db8f40c69edc46ca180ba30c567f37c',
'upload_date': '20170403',
'uploader_id': 'batchUser',
'timestamp': 1491232186,
},
'add_ie': ['Kaltura'],
},
# Eagle.Platform embed (generic URL)
{
'url': 'http://lenta.ru/news/2015/03/06/navalny/',
@ -1313,6 +1431,22 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
{
# Brightcove embed with whitespace around attribute names
'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
'info_dict': {
'id': '3167554373001',
'ext': 'mp4',
'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
'description': 'md5:57bacb0e0f29349de4972bfda3191713',
'uploader_id': '1079349493',
'upload_date': '20140207',
'timestamp': 1391810548,
},
'params': {
'skip_download': True,
},
},
# Another form of arte.tv embed
{
'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
@ -1554,6 +1688,51 @@ class GenericIE(InfoExtractor):
},
'add_ie': [SenateISVPIE.ie_key()],
},
{
# Limelight embeds (1 channel embed + 4 media embeds)
'url': 'http://www.sedona.com/FacilitatorTraining2017',
'info_dict': {
'id': 'FacilitatorTraining2017',
'title': 'Facilitator Training 2017',
},
'playlist_mincount': 5,
},
{
'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
'info_dict': {
'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
'title': 'Standoff with Walnut Creek murder suspect ends',
'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
},
'playlist_mincount': 4,
},
{
# WashingtonPost embed
'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
'info_dict': {
'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
'ext': 'mp4',
'title': "No one has seen the drama series based on Trump's life \u2014 until now",
'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
'timestamp': 1455216756,
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
'add_ie': [WashingtonPostIE.ie_key()],
},
{
# Mediaset embed
'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
'info_dict': {
'id': '720642',
'ext': 'mp4',
'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
},
'params': {
'skip_download': True,
},
'add_ie': [MediasetIE.ie_key()],
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -1596,7 +1775,7 @@ class GenericIE(InfoExtractor):
continue
entries.append({
'_type': 'url',
'_type': 'url_transparent',
'url': next_url,
'title': it.find('title').text,
})
@ -1856,7 +2035,6 @@ class GenericIE(InfoExtractor):
# Look for Brightcove Legacy Studio embeds
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
self.to_screen('Brightcove video detected.')
entries = [{
'_type': 'url',
'url': smuggle_url(bc_url, {'Referer': url}),
@ -1871,7 +2049,7 @@ class GenericIE(InfoExtractor):
}
# Look for Brightcove New Studio embeds
bc_urls = BrightcoveNewIE._extract_urls(webpage)
bc_urls = BrightcoveNewIE._extract_urls(self, webpage)
if bc_urls:
return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
@ -1909,6 +2087,7 @@ class GenericIE(InfoExtractor):
data-video-url=|
<embed[^>]+?src=|
embedSWF\(?:\s*|
<object[^>]+data=|
new\s+SWFObject\(
)
(["\'])
@ -1947,57 +2126,20 @@ class GenericIE(InfoExtractor):
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for embedded Wistia player
match = re.search(
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
if match:
embed_url = self._proto_relative_url(
unescapeHTML(match.group('url')))
wistia_url = WistiaIE._extract_url(webpage)
if wistia_url:
return {
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'Wistia',
'url': self._proto_relative_url(wistia_url),
'ie_key': WistiaIE.ie_key(),
'uploader': video_uploader,
}
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return {
'_type': 'url_transparent',
'url': 'wistia:%s' % match.group('id'),
'ie_key': 'Wistia',
'uploader': video_uploader,
}
match = re.search(
r'''(?sx)
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
''', webpage)
if match:
return self.url_result(self._proto_relative_url(
'wistia:%s' % match.group('id')), 'Wistia')
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
if svt_url:
return self.url_result(svt_url, 'SVT')
# Look for embedded condenast player
matches = re.findall(
r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
webpage)
if matches:
return {
'_type': 'playlist',
'entries': [{
'_type': 'url',
'ie_key': 'CondeNast',
'url': ma,
} for ma in matches],
'title': video_title,
'id': video_id,
}
# Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
if mobj is not None:
@ -2386,28 +2528,16 @@ class GenericIE(InfoExtractor):
return self.url_result(piksel_url, PikselIE.ie_key())
# Look for Limelight embeds
mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
if mobj:
lm = {
'Media': 'media',
'Channel': 'channel',
'ChannelList': 'channel_list',
}
return self.url_result(smuggle_url('limelight:%s:%s' % (
lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
'Limelight%s' % mobj.group(1), mobj.group(2))
limelight_urls = LimelightBaseIE._extract_urls(webpage, url)
if limelight_urls:
return self.playlist_result(
limelight_urls, video_id, video_title, video_description)
mobj = re.search(
r'''(?sx)
<object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
<param[^>]+
name=(["\'])flashVars\2[^>]+
value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
''', webpage)
if mobj:
return self.url_result(smuggle_url(
'limelight:media:%s' % mobj.group('id'),
{'source_url': url}), 'LimelightMedia', mobj.group('id'))
# Look for Anvato embeds
anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
if anvato_urls:
return self.playlist_result(
anvato_urls, video_id, video_title, video_description)
# Look for AdobeTVVideo embeds
mobj = re.search(
@ -2526,6 +2656,18 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
# Look for Mediaset embeds
mediaset_urls = MediasetIE._extract_urls(webpage)
if mediaset_urls:
return self.playlist_from_matches(
mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
@ -2550,18 +2692,14 @@ class GenericIE(InfoExtractor):
self._sort_formats(entry['formats'])
return self.playlist_result(entries)
jwplayer_data_str = self._find_jwplayer_data(webpage)
if jwplayer_data_str:
try:
jwplayer_data = self._parse_json(
jwplayer_data_str, video_id, transform_source=js_to_json)
info = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False)
if not info.get('title'):
info['title'] = video_title
return info
except ExtractorError:
pass
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
if jwplayer_data:
info = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False, base_url=url)
if not info.get('title'):
info['title'] = video_title
return info
def check_video(vurl):
if YoutubeIE.suitable(vurl):
@ -2570,7 +2708,7 @@ class GenericIE(InfoExtractor):
return True
vpath = compat_urlparse.urlparse(vurl).path
vext = determine_ext(vpath)
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js')
return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml', 'js', 'xml')
def filter_video(urls):
return list(filter(check_video, urls))

49
youtube_dl/extractor/go.py
View File

@ -36,22 +36,26 @@ class GoIE(AdobePassIE):
'requestor_id': 'DisneyXD',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': {
'id': '0_g86w5onx',
'id': 'VDKA3807643',
'ext': 'mp4',
'title': 'Sneak Peek: Language Arts',
'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
'only_matching': True,
'url': 'http://watchdisneyxd.go.com/doraemon',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
@ -60,19 +64,36 @@ class GoIE(AdobePassIE):
'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id = video_id if video_id != '-1' else show_id
return self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
display_id)['video']
def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
if not video_id:
webpage = self._download_webpage(url, display_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')
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
video_data = self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
video_id)['video'][0]
r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
formats = []
@ -105,7 +126,7 @@ class GoIE(AdobePassIE):
self._initialize_geo_bypass(['US'])
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
for error in errors:

126
youtube_dl/extractor/go90.py Normal file
View File

@ -0,0 +1,126 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
parse_iso8601,
)
class Go90IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?go90\.com/videos/(?P<id>[0-9a-zA-Z]+)'
_TEST = {
'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',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'https://www.go90.com/api/view/items/' + video_id,
video_id, headers={
'Content-Type': 'application/json; charset=utf-8',
}, data=b'{"client":"web","device_type":"pc"}')
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,
}

16
youtube_dl/extractor/hbo.py
View File

@ -92,12 +92,14 @@ class HBOBaseIE(InfoExtractor):
video_url.replace('.tar', '/base_index_w8.m3u8'),
video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
elif source.tag == 'hls':
# #EXT-X-BYTERANGE is not supported by native hls downloader
# and ffmpeg (#10955)
# formats.extend(self._extract_m3u8_formats(
# video_url.replace('.tar', '/base_index.m3u8'),
# video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
continue
m3u8_formats = self._extract_m3u8_formats(
video_url.replace('.tar', '/base_index.m3u8'),
video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
for f in m3u8_formats:
if f.get('vcodec') == 'none' and not f.get('tbr'):
f['tbr'] = int_or_none(self._search_regex(
r'-(\d+)k/', f['url'], 'tbr', default=None))
formats.extend(m3u8_formats)
elif source.tag == 'dash':
formats.extend(self._extract_mpd_formats(
video_url.replace('.tar', '/manifest.mpd'),
@ -110,7 +112,7 @@ class HBOBaseIE(InfoExtractor):
'width': format_info.get('width'),
'height': format_info.get('height'),
})
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
self._sort_formats(formats)
thumbnails = []
card_sizes = xpath_element(video_data, 'titleCardSizes')

52
youtube_dl/extractor/hitbox.py
View File

@ -16,8 +16,8 @@ from ..utils import (
class HitboxIE(InfoExtractor):
IE_NAME = 'hitbox'
_VALID_URL = r'https?://(?:www\.)?hitbox\.tv/video/(?P<id>[0-9]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?:[^/]+/)*videos?/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.hitbox.tv/video/203213',
'info_dict': {
'id': '203213',
@ -38,13 +38,15 @@ class HitboxIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
}
}, {
'url': 'https://www.smashcast.tv/hitboxlive/videos/203213',
'only_matching': True,
}]
def _extract_metadata(self, url, video_id):
thumb_base = 'https://edge.sf.hitbox.tv'
metadata = self._download_json(
'%s/%s' % (url, video_id), video_id,
'Downloading metadata JSON')
'%s/%s' % (url, video_id), video_id, 'Downloading metadata JSON')
date = 'media_live_since'
media_type = 'livestream'
@ -63,14 +65,15 @@ class HitboxIE(InfoExtractor):
views = int_or_none(video_meta.get('media_views'))
timestamp = parse_iso8601(video_meta.get(date), ' ')
categories = [video_meta.get('category_name')]
thumbs = [
{'url': thumb_base + video_meta.get('media_thumbnail'),
'width': 320,
'height': 180},
{'url': thumb_base + video_meta.get('media_thumbnail_large'),
'width': 768,
'height': 432},
]
thumbs = [{
'url': thumb_base + video_meta.get('media_thumbnail'),
'width': 320,
'height': 180
}, {
'url': thumb_base + video_meta.get('media_thumbnail_large'),
'width': 768,
'height': 432
}]
return {
'id': video_id,
@ -90,7 +93,7 @@ class HitboxIE(InfoExtractor):
video_id = self._match_id(url)
player_config = self._download_json(
'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
'https://www.smashcast.tv/api/player/config/video/%s' % video_id,
video_id, 'Downloading video JSON')
formats = []
@ -121,8 +124,7 @@ class HitboxIE(InfoExtractor):
self._sort_formats(formats)
metadata = self._extract_metadata(
'https://www.hitbox.tv/api/media/video',
video_id)
'https://www.smashcast.tv/api/media/video', video_id)
metadata['formats'] = formats
return metadata
@ -130,8 +132,8 @@ class HitboxIE(InfoExtractor):
class HitboxLiveIE(HitboxIE):
IE_NAME = 'hitbox:live'
_VALID_URL = r'https?://(?:www\.)?hitbox\.tv/(?!video)(?P<id>.+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?(?:hitbox|smashcast)\.tv/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.hitbox.tv/dimak',
'info_dict': {
'id': 'dimak',
@ -146,13 +148,20 @@ class HitboxLiveIE(HitboxIE):
# live
'skip_download': True,
},
}
}, {
'url': 'https://www.smashcast.tv/dimak',
'only_matching': True,
}]
@classmethod
def suitable(cls, url):
return False if HitboxIE.suitable(url) else super(HitboxLiveIE, cls).suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
player_config = self._download_json(
'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
'https://www.smashcast.tv/api/player/config/live/%s' % video_id,
video_id)
formats = []
@ -197,8 +206,7 @@ class HitboxLiveIE(HitboxIE):
self._sort_formats(formats)
metadata = self._extract_metadata(
'https://www.hitbox.tv/api/media/live',
video_id)
'https://www.smashcast.tv/api/media/live', video_id)
metadata['formats'] = formats
metadata['is_live'] = True
metadata['title'] = self._live_title(metadata.get('title'))

5
youtube_dl/extractor/imdb.py
View File

@ -13,7 +13,7 @@ from ..utils import (
class ImdbIE(InfoExtractor):
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video/[^/]+/|title/tt\d+.*?#lb-|videoplayer/)vi(?P<id>\d+)'
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title).+?[/-]vi(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
@ -35,6 +35,9 @@ class ImdbIE(InfoExtractor):
}, {
'url': 'http://www.imdb.com/videoplayer/vi1562949145',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
'only_matching': True,
}]
def _real_extract(self, url):

4
youtube_dl/extractor/infoq.py
View File

@ -87,8 +87,8 @@ class InfoQIE(BokeCCBaseIE):
def _extract_http_audio(self, webpage, video_id):
fields = self._hidden_inputs(webpage)
http_audio_url = fields['filename']
if http_audio_url is None:
http_audio_url = fields.get('filename')
if not http_audio_url:
return []
cookies_header = {'Cookie': self._extract_cookies(webpage)}

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