Akkariin/youtube-dl
1
0
Fork 0
mirror of https://github.com/l1ving/youtube-dl synced 2025-01-26 17:22:52 +08:00
Code Issues Releases Wiki Activity

Merge branch 'master' into tvpleextractor

Browse Source
This commit is contained in:
kjy00302 2016-09-04 12:37:20 +09:00
commit f6943b9f4c
207 changed files with 7932 additions and 4066 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 *2016.07.13*. 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 Issues with outdated version will be rejected.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 **2016.07.13**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.03*. 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 Issues with outdated version will be rejected.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 **2016.09.03**
### 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 2016.07.13
[debug] youtube-dl version 2016.09.03
[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: {}

5
AUTHORS
View File

@ -178,3 +178,8 @@ Artur Krysiak
Jakub Adam Wieczorek
Aleksandar Topuzović
Nehal Patel
Rob van Bekkum
Petr Zvoníček
Pratyush Singh
Aleksander Nitecki
Sebastian Blunt

2
CONTRIBUTING.md
View File

@ -46,7 +46,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?

568
ChangeLog Normal file
View File

@ -0,0 +1,568 @@
version <unreleased>
Extractors
* [youjizz] Fix extraction (#10437)
+ [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512)
version 2016.09.03
Core
* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
_extract_m3u8_formats (#10522)
* Handle semicolon in mimetype2ext
Extractors
+ [youtube] Add support for rental videos' previews (#10532)
* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
no playlist is actually served (#10537)
+ [drtv] Add support for dr.dk/nyheder (#10536)
+ [facebook:plugins:video] Add extractor (#10530)
+ [go] Add extractor for *.go.com sites
* [adobepass] Check for authz_token expiration (#10527)
* [nytimes] improve extraction
* [thestar] Fix extraction (#10465)
* [glide] Fix extraction (#10478)
- [exfm] Remove extractor (#10482)
* [youporn] Fix categories and tags extraction (#10521)
+ [curiositystream] Add extractor for app.curiositystream.com
- [thvideo] Remove extractor (#10464)
* [movingimage] Fix for the new site name (#10466)
+ [cbs] Add support for once formats (#10515)
* [limelight] Skip ism snd duplicate manifests
+ [porncom] Extract categories and tags (#10510)
+ [facebook] Extract timestamp (#10508)
+ [yahoo] Extract more formats
version 2016.08.31
Extractors
* [soundcloud] Fix URL regular expression to avoid clashes with sets (#10505)
* [bandcamp:album] Fix title extraction (#10455)
* [pyvideo] Fix extraction (#10468)
+ [ctv] Add support for tsn.ca, bnn.ca and thecomedynetwork.ca (#10016)
* [9c9media] Extract more metadata
* [9c9media] Fix multiple stacks extraction (#10016)
* [adultswim] Improve video info extraction (#10492)
* [vodplatform] Improve embed regular expression
- [played] Remove extractor (#10470)
+ [tbs] Add extractor for tbs.com and tntdrama.com (#10222)
+ [cartoonnetwork] Add extractor for cartoonnetwork.com (#10110)
* [adultswim] Rework in terms of turner extractor
* [cnn] Rework in terms of turner extractor
* [nba] Rework in terms of turner extractor
+ [turner] Add base extractor for Turner Broadcasting System based sites
* [bilibili] Fix extraction (#10375)
* [openload] Fix extraction (#10408)
version 2016.08.28
Core
+ Add warning message that ffmpeg doesn't support SOCKS
* Improve thumbnail sorting
+ Extract formats from #EXT-X-MEDIA tags in _extract_m3u8_formats
* Fill IV with leading zeros for IVs shorter than 16 octets in hlsnative
+ Add ac-3 to the list of audio codecs in parse_codecs
Extractors
* [periscope:user] Fix extraction (#10453)
* [douyutv] Fix extraction (#10153, #10318, #10444)
+ [nhk:vod] Add extractor for www3.nhk.or.jp on demand (#4437, #10424)
- [trutube] Remove extractor (#10438)
+ [usanetwork] Add extractor for usanetwork.com
* [crackle] Fix extraction (#10333)
* [spankbang] Fix description and uploader extraction (#10339)
* [discoverygo] Detect cable provider restricted videos (#10425)
+ [cbc] Add support for watch.cbc.ca
* [kickstarter] Silent the warning for og:description (#10415)
* [mtvservices:embedded] Fix extraction for the new 'edge' player (#10363)
version 2016.08.24.1
Extractors
+ [pluralsight] Add support for subtitles (#9681)
version 2016.08.24
Extractors
* [youtube] Fix authentication (#10392)
* [openload] Fix extraction (#10408)
+ [bravotv] Add support for Adobe Pass (#10407)
* [bravotv] Fix clip info extraction (#10407)
* [eagleplatform] Improve embedded videos detection (#10409)
* [awaan] Fix extraction
* [mtvservices:embedded] Update config URL
+ [abc:iview] Add extractor (#6148)
version 2016.08.22
Core
* Improve formats and subtitles extension auto calculation
+ Recognize full unit names in parse_filesize
+ Add support for m3u8 manifests in HTML5 multimedia tags
* Fix octal/hexadecimal number detection in js_to_json
Extractors
+ [ivi] Add support for 720p and 1080p
+ [charlierose] Add new extractor (#10382)
* [1tv] Fix extraction (#9249)
* [twitch] Renew authentication
* [kaltura] Improve subtitles extension calculation
+ [zingmp3] Add support for video clips
* [zingmp3] Fix extraction (#10041)
* [kaltura] Improve subtitles extraction (#10279)
* [cultureunplugged] Fix extraction (#10330)
+ [cnn] Add support for money.cnn.com (#2797)
* [cbsnews] Fix extraction (#10362)
* [cbs] Fix extraction (#10393)
+ [litv] Support 'promo' URLs (#10385)
* [snotr] Fix extraction (#10338)
* [n-tv.de] Fix extraction (#10331)
* [globo:article] Relax URL and video id regular expressions (#10379)
version 2016.08.19
Core
- Remove output template description from --help
* Recognize lowercase units in parse_filesize
Extractors
+ [porncom] Add extractor for porn.com (#2251, #10251)
+ [generic] Add support for DBTV embeds
* [vk:wallpost] Fix audio extraction for new site layout
* [vk] Fix authentication
+ [hgtvcom:show] Add extractor for hgtv.com shows (#10365)
+ [discoverygo] Add support for another GO network sites
version 2016.08.17
Core
+ Add _get_netrc_login_info
Extractors
* [mofosex] Extract all formats (#10335)
+ [generic] Add support for vbox7 embeds
+ [vbox7] Add support for embed URLs
+ [viafree] Add extractor (#10358)
+ [mtg] Add support for viafree URLs (#10358)
* [theplatform] Extract all subtitles per language
+ [xvideos] Fix HLS extraction (#10356)
+ [amcnetworks] Add extractor
+ [bbc:playlist] Add support for pagination (#10349)
+ [fxnetworks] Add extractor (#9462)
* [cbslocal] Fix extraction for SendtoNews-based videos
* [sendtonews] Fix extraction
* [jwplatform] Extract video id from JWPlayer data
- [zippcast] Remove extractor (#10332)
+ [viceland] Add extractor (#8799)
+ [adobepass] Add base extractor for Adobe Pass Authentication
* [life:embed] Improve extraction
* [vgtv] Detect geo restricted videos (#10348)
+ [uplynk] Add extractor
* [xiami] Fix extraction (#10342)
version 2016.08.13
Core
* Show progress for curl external downloader
* Forward more options to curl external downloader
Extractors
* [pbs] Fix description extraction
* [franceculture] Fix extraction (#10324)
* [pornotube] Fix extraction (#10322)
* [4tube] Fix metadata extraction (#10321)
* [imgur] Fix width and height extraction (#10325)
* [expotv] Improve extraction
+ [vbox7] Fix extraction (#10309)
- [tapely] Remove extractor (#10323)
* [muenchentv] Fix extraction (#10313)
+ [24video] Add support for .me and .xxx TLDs
* [24video] Fix comment count extraction
* [sunporno] Add support for embed URLs
* [sunporno] Fix metadata extraction (#10316)
+ [hgtv] Add extractor for hgtv.ca (#3999)
- [pbs] Remove request to unavailable API
+ [pbs] Add support for high quality HTTP formats
+ [crunchyroll] Add support for HLS formats (#10301)
version 2016.08.12
Core
* Subtitles are now written as is. Newline conversions are disabled. (#10268)
+ Recognize more formats in unified_timestamp
Extractors
- [goldenmoustache] Remove extractor (#10298)
* [drtuber] Improve title extraction
* [drtuber] Make dislike count optional (#10297)
* [chirbit] Fix extraction (#10296)
* [francetvinfo] Relax URL regular expression
* [rtlnl] Relax URL regular expression (#10282)
* [formula1] Relax URL regular expression (#10283)
* [wat] Improve extraction (#10281)
* [ctsnews] Fix extraction
version 2016.08.10
Core
* Make --metadata-from-title non fatal when title does not match the pattern
* Introduce options for randomized sleep before each download
--min-sleep-interval and --max-sleep-interval (#9930)
* Respect default in _search_json_ld
Extractors
+ [uol] Add extractor for uol.com.br (#4263)
* [rbmaradio] Fix extraction and extract all formats (#10242)
+ [sonyliv] Add extractor for sonyliv.com (#10258)
* [aparat] Fix extraction
* [cwtv] Extract HTTP formats
+ [rozhlas] Add extractor for prehravac.rozhlas.cz (#10253)
* [kuwo:singer] Fix extraction
version 2016.08.07
Core
+ Add support for TV Parental Guidelines ratings in parse_age_limit
+ Add decode_png (#9706)
+ Add support for partOfTVSeries in JSON-LD
* Lower master M3U8 manifest preference for better format sorting
Extractors
+ [discoverygo] Add extractor (#10245)
* [flipagram] Make JSON-LD extraction non fatal
* [generic] Make JSON-LD extraction non fatal
+ [bbc] Add support for morph embeds (#10239)
* [tnaflixnetworkbase] Improve title extraction
* [tnaflix] Fix metadata extraction (#10249)
* [fox] Fix theplatform release URL query
* [openload] Fix extraction (#9706)
* [bbc] Skip duplicate manifest URLs
* [bbc] Improve format code
+ [bbc] Add support for DASH and F4M
* [bbc] Improve format sorting and listing
* [bbc] Improve playlist extraction
+ [pokemon] Add extractor (#10093)
+ [condenast] Add fallback scenario for video info extraction
version 2016.08.06
Core
* Add support for JSON-LD root list entries (#10203)
* Improve unified_timestamp
* Lower preference of RTSP formats in generic sorting
+ Add support for multiple properties in _og_search_property
* Improve password hiding from verbose output
Extractors
+ [adultswim] Add support for trailers (#10235)
* [archiveorg] Improve extraction (#10219)
+ [jwplatform] Add support for playlists
+ [jwplatform] Add support for relative URLs
* [jwplatform] Improve audio detection
+ [tvplay] Capture and output native error message
+ [tvplay] Extract series metadata
+ [tvplay] Add support for subtitles (#10194)
* [tvp] Improve extraction (#7799)
* [cbslocal] Fix timestamp parsing (#10213)
+ [naver] Add support for subtitles (#8096)
* [naver] Improve extraction
* [condenast] Improve extraction
* [engadget] Relax URL regular expression
* [5min] Fix extraction
+ [nationalgeographic] Add support for Episode Guide
+ [kaltura] Add support for subtitles
* [kaltura] Optimize network requests
+ [vodplatform] Add extractor for vod-platform.net
- [gamekings] Remove extractor
* [limelight] Extract HTTP formats
* [ntvru] Fix extraction
+ [comedycentral] Re-add :tds and :thedailyshow shortnames
version 2016.08.01
Fixed/improved extractors
- [yandexmusic:track] Adapt to changes in track location JSON (#10193)
- [bloomberg] Support another form of player (#10187)
- [limelight] Skip DRM protected videos
- [safari] Relax regular expressions for URL matching (#10202)
- [cwtv] Add support for cwtvpr.com (#10196)
version 2016.07.30
Fixed/improved extractors
- [twitch:clips] Sort formats
- [tv2] Use m3u8_native
- [tv2:article] Fix video detection (#10188)
- rtve (#10076)
- [dailymotion:playlist] Optimize download archive processing (#10180)
version 2016.07.28
Fixed/improved extractors
- shared (#10170)
- soundcloud (#10179)
- twitch (#9767)
version 2016.07.26.2
Fixed/improved extractors
- smotri
- camdemy
- mtv
- comedycentral
- cmt
- cbc
- mgtv
- orf
version 2016.07.24
New extractors
- arkena (#8682)
- lcp (#8682)
Fixed/improved extractors
- facebook (#10151)
- dailymail
- telegraaf
- dcn
- onet
- tvp
Miscellaneous
- Support $Time$ in DASH manifests
version 2016.07.22
New extractors
- odatv (#9285)
Fixed/improved extractors
- bbc
- youjizz (#10131)
- youtube (#10140)
- pornhub (#10138)
- eporner (#10139)
version 2016.07.17
New extractors
- nintendo (#9986)
- streamable (#9122)
Fixed/improved extractors
- ard (#10095)
- mtv
- comedycentral (#10101)
- viki (#10098)
- spike (#10106)
Miscellaneous
- Improved twitter player detection (#10090)
version 2016.07.16
New extractors
- ninenow (#5181)
Fixed/improved extractors
- rtve (#10076)
- brightcove
- 3qsdn
- syfy (#9087, #3820, #2388)
- youtube (#10083)
Miscellaneous
- Fix subtitle embedding for video-only and audio-only files (#10081)
version 2016.07.13
New extractors
- rudo
Fixed/improved extractors
- biobiochiletv
- tvplay
- dbtv
- brightcove
- tmz
- youtube (#10059)
- shahid (#10062)
- vk
- ellentv (#10067)
version 2016.07.11
New Extractors
- roosterteeth (#9864)
Fixed/improved extractors
- miomio (#9605)
- vuclip
- youtube
- vidzi (#10058)
version 2016.07.09.2
Fixed/improved extractors
- vimeo (#1638)
- facebook (#10048)
- lynda (#10047)
- animeondemand
Fixed/improved features
- Embedding subtitles no longer throws an error with problematic inputs (#9063)
version 2016.07.09.1
Fixed/improved extractors
- youtube
- ard
- srmediatek (#9373)
version 2016.07.09
New extractors
- Flipagram (#9898)
Fixed/improved extractors
- telecinco
- toutv
- radiocanada
- tweakers (#9516)
- lynda
- nick (#7542)
- polskieradio (#10028)
- le
- facebook (#9851)
- mgtv
- animeondemand (#10031)
Fixed/improved features
- `--postprocessor-args` and `--downloader-args` now accepts non-ASCII inputs
on non-Windows systems
version 2016.07.07
New extractors
- kamcord (#10001)
Fixed/improved extractors
- spiegel (#10018)
- metacafe (#8539, #3253)
- onet (#9950)
- francetv (#9955)
- brightcove (#9965)
- daum (#9972)
version 2016.07.06
Fixed/improved extractors
- youtube (#10007, #10009)
- xuite
- stitcher
- spiegel
- slideshare
- sandia
- rtvnh
- prosiebensat1
- onionstudios
version 2016.07.05
Fixed/improved extractors
- brightcove
- yahoo (#9995)
- pornhub (#9997)
- iqiyi
- kaltura (#5557)
- la7
- Changed features
- Rename --cn-verfication-proxy to --geo-verification-proxy
Miscellaneous
- Add script for displaying downloads statistics
version 2016.07.03.1
Fixed/improved extractors
- theplatform
- aenetworks
- nationalgeographic
- hrti (#9482)
- facebook (#5701)
- buzzfeed (#5701)
- rai (#8617, #9157, #9232, #8552, #8551)
- nationalgeographic (#9991)
- iqiyi
version 2016.07.03
New extractors
- hrti (#9482)
Fixed/improved extractors
- vk (#9981)
- facebook (#9938)
- xtube (#9953, #9961)
version 2016.07.02
New extractors
- fusion (#9958)
Fixed/improved extractors
- twitch (#9975)
- vine (#9970)
- periscope (#9967)
- pornhub (#8696)
version 2016.07.01
New extractors
- 9c9media
- ctvnews (#2156)
- ctv (#4077)
Fixed/Improved extractors
- rds
- meta (#8789)
- pornhub (#9964)
- sixplay (#2183)
New features
- Accept quoted strings across multiple lines (#9940)

4
Makefile
View File

@ -94,7 +94,7 @@ _EXTRACTOR_FILES != find youtube_dl/extractor -iname '*.py' -and -not -iname 'la
youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
$(PYTHON) devscripts/make_lazy_extractors.py $@
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog
@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
--exclude '*.DS_Store' \
--exclude '*.kate-swp' \
@ -107,7 +107,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
--exclude 'docs/_build' \
-- \
bin devscripts test youtube_dl docs \
LICENSE README.md README.txt \
ChangeLog LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
youtube-dl.zsh youtube-dl.fish setup.py \
youtube-dl

88
README.md
View File

@ -17,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
To install it right away for all UNIX users (Linux, OS X, etc.), type:
sudo curl -L https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl
sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl
sudo chmod a+rx /usr/local/bin/youtube-dl
If you do not have curl, you can alternatively use a recent wget:
@ -201,32 +201,8 @@ which means you can modify it, redistribute it or use it however you like.
-a, --batch-file FILE File containing URLs to download ('-' for
stdin)
--id Use only video ID in file name
-o, --output TEMPLATE Output filename template. Use %(title)s to
get the title, %(uploader)s for the
uploader name, %(uploader_id)s for the
uploader nickname if different,
%(autonumber)s to get an automatically
incremented number, %(ext)s for the
filename extension, %(format)s for the
format description (like "22 - 1280x720" or
"HD"), %(format_id)s for the unique id of
the format (like YouTube's itags: "137"),
%(upload_date)s for the upload date
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the
video id, %(playlist_title)s,
%(playlist_id)s, or %(playlist)s (=title if
present, ID otherwise) for the playlist the
video is in, %(playlist_index)s for the
position in the playlist. %(height)s and
%(width)s for the width and height of the
video format. %(resolution)s for a textual
description of the resolution of the video
format. %% for a literal percent. Use - to
output to stdout. Can also be used to
download to a different directory, for
example with -o '/my/downloads/%(uploader)s
/%(title)s-%(id)s.%(ext)s' .
-o, --output TEMPLATE Output filename template, see the "OUTPUT
TEMPLATE" for all the info
--autonumber-size NUMBER Specify the number of digits in
%(autonumber)s when it is present in output
filename template or --auto-number option
@ -330,7 +306,15 @@ which means you can modify it, redistribute it or use it however you like.
bidirectional text support. Requires bidiv
or fribidi executable in PATH
--sleep-interval SECONDS Number of seconds to sleep before each
download.
download when used alone or a lower bound
of a range for randomized sleep before each
download (minimum possible number of
seconds to sleep) when used along with
--max-sleep-interval.
--max-sleep-interval SECONDS Upper bound of a range for randomized sleep
before each download (maximum possible
number of seconds to sleep). Must only be
used along with --min-sleep-interval.
## Video Format Options:
-f, --format FORMAT Video format code, see the "FORMAT
@ -428,11 +412,19 @@ You can configure youtube-dl by placing any supported command line option to a c
For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
```
-x
--no-mtime
--proxy 127.0.0.1:3128
-o ~/Movies/%(title)s.%(ext)s
# Lines starting with # are comments
# Always extract audio
-x
# Do not copy the mtime
--no-mtime
# Use this proxy
--proxy 127.0.0.1:3128
# Save all videos under Movies directory in your home directory
-o ~/Movies/%(title)s.%(ext)s
```
Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
@ -661,7 +653,11 @@ $ youtube-dl -f 'best[filesize<50M]'
# Download best format available via direct link over HTTP/HTTPS protocol
$ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]'
# Download the best video format and the best audio format without merging them
$ youtube-dl -f 'bestvideo,bestaudio' -o '%(title)s.f%(format_id)s.%(ext)s'
```
Note that in the last example, an output template is recommended as bestvideo and bestaudio may have the same file name.
# VIDEO SELECTION
@ -742,7 +738,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
### I have downloaded a video but how can I play it?
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org/) or [mplayer](http://www.mplayerhq.hu/).
### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
@ -824,10 +820,32 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
### How do I pass cookies to youtube-dl?
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
### How do I stream directly to media player?
You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](http://www.videolan.org/) can be achieved with:
youtube-dl -o - "http://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
### How do I download only new videos from a playlist?
Use download-archive feature. With this feature you should initially download the complete playlist with `--download-archive /path/to/download/archive/file.txt` that will record identifiers of all the videos in a special file. Each subsequent run with the same `--download-archive` will download only new videos and skip all videos that have been downloaded before. Note that only successful downloads are recorded in the file.
For example, at first,
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and create a file `archive.txt`. Each subsequent run will only download new videos if any:
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
### Can you add support for this anime video site, or site which shows current movies for free?
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
@ -1196,7 +1214,7 @@ Make sure that someone has not already opened the issue you're trying to open. S
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#options). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?

22
devscripts/prepare_manpage.py
View File

@ -54,17 +54,21 @@ def filter_options(readme):
if in_options:
if line.lstrip().startswith('-'):
option, description = re.split(r'\s{2,}', line.lstrip())
split_option = option.split(' ')
split = re.split(r'\s{2,}', line.lstrip())
# Description string may start with `-` as well. If there is
# only one piece then it's a description bit not an option.
if len(split) > 1:
option, description = split
split_option = option.split(' ')
if not split_option[-1].startswith('-'): # metavar
option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
if not split_option[-1].startswith('-'): # metavar
option = ' '.join(split_option[:-1] + ['*%s*' % split_option[-1]])
# Pandoc's definition_lists. See http://pandoc.org/README.html
# for more information.
ret += '\n%s\n: %s\n' % (option, description)
else:
ret += line.lstrip() + '\n'
# Pandoc's definition_lists. See http://pandoc.org/README.html
# for more information.
ret += '\n%s\n: %s\n' % (option, description)
continue
ret += line.lstrip() + '\n'
else:
ret += line + '\n'

5
devscripts/release.sh
View File

@ -71,9 +71,12 @@ fi
/bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
/bin/echo -e "\n### Changing version in ChangeLog..."
sed -i "s/<unreleased>/$version/" ChangeLog
/bin/echo -e "\n### Committing documentation, templates and youtube_dl/version.py..."
make README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md supportedsites
git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py
git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE.md docs/supportedsites.md youtube_dl/version.py ChangeLog
git commit $gpg_sign_commits -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..."

36
devscripts/show-downloads-statistics.py
View File

@ -1,6 +1,7 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import itertools
import json
import os
import re
@ -21,21 +22,26 @@ def format_size(bytes):
total_bytes = 0
releases = json.loads(compat_urllib_request.urlopen(
'https://api.github.com/repos/rg3/youtube-dl/releases').read().decode('utf-8'))
for page in itertools.count(1):
releases = json.loads(compat_urllib_request.urlopen(
'https://api.github.com/repos/rg3/youtube-dl/releases?page=%s' % page
).read().decode('utf-8'))
for release in releases:
compat_print(release['name'])
for asset in release['assets']:
asset_name = asset['name']
total_bytes += asset['download_count'] * asset['size']
if all(not re.match(p, asset_name) for p in (
r'^youtube-dl$',
r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$',
r'^youtube-dl\.exe$')):
continue
compat_print(
' %s size: %s downloads: %d'
% (asset_name, format_size(asset['size']), asset['download_count']))
if not releases:
break
for release in releases:
compat_print(release['name'])
for asset in release['assets']:
asset_name = asset['name']
total_bytes += asset['download_count'] * asset['size']
if all(not re.match(p, asset_name) for p in (
r'^youtube-dl$',
r'^youtube-dl-\d{4}\.\d{2}\.\d{2}(?:\.\d+)?\.tar\.gz$',
r'^youtube-dl\.exe$')):
continue
compat_print(
' %s size: %s downloads: %d'
% (asset_name, format_size(asset['size']), asset['download_count']))
compat_print('total downloads traffic: %s' % format_size(total_bytes))

78
docs/supportedsites.md
View File

@ -13,8 +13,12 @@
- **5min**
- **8tracks**
- **91porn**
- **9c9media**
- **9c9media:stack**
- **9gag**
- **9now.com.au**
- **abc.net.au**
- **abc.net.au:iview**
- **Abc7News**
- **abcnews**
- **abcnews:video**
@ -34,6 +38,7 @@
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **AMCNetworks**
- **AnimeOnDemand**
- **anitube.se**
- **AnySex**
@ -45,6 +50,7 @@
- **archive.org**: archive.org videos
- **ARD**
- **ARD:mediathek**
- **Arkena**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:cinema**
@ -63,6 +69,10 @@
- **audiomack**
- **audiomack:album**
- **auroravid**: AuroraVid
- **AWAAN**
- **awaan:live**
- **awaan:season**
- **awaan:video**
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
@ -107,8 +117,11 @@
- **Canvas**
- **CarambaTV**
- **CarambaTVPage**
- **CBC**
- **CBCPlayer**
- **CartoonNetwork**
- **cbc.ca**
- **cbc.ca:player**
- **cbc.ca:watch**
- **cbc.ca:watch:video**
- **CBS**
- **CBSInteractive**
- **CBSLocal**
@ -118,6 +131,7 @@
- **CDA**
- **CeskaTelevize**
- **channel9**: Channel 9
- **CharlieRose**
- **Chaturbate**
- **Chilloutzone**
- **chirbit**
@ -140,7 +154,8 @@
- **CollegeRama**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralShows**: The Daily Show / The Colbert Report
- **ComedyCentralShortname**
- **ComedyCentralTV**
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **Coub**
- **Cracked**
@ -156,6 +171,8 @@
- **CTVNews**
- **culturebox.francetvinfo.fr**
- **CultureUnplugged**
- **curiositystream**
- **curiositystream:collection**
- **CWTV**
- **DailyMail**
- **dailymotion**
@ -167,10 +184,6 @@
- **daum.net:playlist**
- **daum.net:user**
- **DBTV**
- **DCN**
- **dcn:live**
- **dcn:season**
- **dcn:video**
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
@ -179,6 +192,7 @@
- **DigitallySpeaking**
- **Digiteka**
- **Discovery**
- **DiscoveryGo**
- **Dotsub**
- **DouyuTV**: 斗鱼
- **DPlay**
@ -211,11 +225,11 @@
- **EsriVideo**
- **Europa**
- **EveryonesMixtape**
- **exfm**: ex.fm
- **ExpoTV**
- **ExtremeTube**
- **EyedoTV**
- **facebook**
- **FacebookPluginsVideo**
- **faz.net**
- **fc2**
- **Fczenit**
@ -234,7 +248,6 @@
- **FoxSports**
- **france2.fr:generation-quoi**
- **FranceCulture**
- **FranceCultureEmission**
- **FranceInter**
- **francetv**: France 2, 3, 4, 5 and Ô
- **francetvinfo.fr**
@ -244,8 +257,8 @@
- **Funimation**
- **FunnyOrDie**
- **Fusion**
- **FXNetworks**
- **GameInformer**
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **Gamersyde**
@ -260,9 +273,9 @@
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GloboArticle**
- **Go**
- **GodTube**
- **GodTV**
- **GoldenMoustache**
- **Golem**
- **GoogleDrive**
- **Goshgay**
@ -275,6 +288,8 @@
- **HellPorno**
- **Helsinki**: helsinki.fi
- **HentaiStigma**
- **HGTV**
- **hgtv.com:show**
- **HistoricFilms**
- **history:topic**: History.com Topic
- **hitbox**
@ -335,6 +350,8 @@
- **kuwo:song**: 酷我音乐
- **la7.it**
- **Laola1Tv**
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **Learnr**
- **Lecture2Go**
@ -392,11 +409,12 @@
- **MovieClips**
- **MovieFap**
- **Moviezine**
- **MovingImage**
- **MPORA**
- **MSN**
- **mtg**: MTG services
- **MTV**
- **mtv.de**
- **mtviggy.com**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
@ -412,7 +430,8 @@
- **MyVidster**
- **n-tv.de**
- **natgeo**
- **natgeo:channel**
- **natgeo:episodeguide**
- **natgeo:video**
- **Naver**
- **NBA**
- **NBC**
@ -436,9 +455,9 @@
- **Newstube**
- **NextMedia**: 蘋果日報
- **NextMediaActionNews**: 蘋果日報 - 動新聞
- **nextmovie.com**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **NhkVod**
- **nhl.com**
- **nhl.com:news**: NHL news
- **nhl.com:videocenter**
@ -447,7 +466,7 @@
- **nick.de**
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **NineCNineMedia**
- **Nintendo**
- **njoy**: N-JOY
- **njoy:embed**
- **Noco**
@ -475,6 +494,7 @@
- **NYTimes**
- **NYTimesArticle**
- **ocw.mit.edu**
- **OdaTV**
- **Odnoklassniki**
- **OktoberfestTV**
- **on.aol.com**
@ -503,7 +523,6 @@
- **Pinkbike**
- **Pladform**
- **play.fm**
- **played.to**
- **PlaysTV**
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
- **Playvid**
@ -513,7 +532,9 @@
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **Pokemon**
- **PolskieRadio**
- **PornCom**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
- **PornHubPlaylist**
@ -557,6 +578,7 @@
- **RoosterTeeth**
- **RottenTomatoes**
- **Roxwel**
- **Rozhlas**
- **RTBF**
- **rte**: Raidió Teilifís Éireann TV
- **rte:radio**: Raidió Teilifís Éireann radio
@ -567,6 +589,7 @@
- **rtve.es:alacarta**: RTVE a la carta
- **rtve.es:infantil**: RTVE infantil
- **rtve.es:live**: RTVE.es live streams
- **rtve.es:television**
- **RTVNH**
- **Rudo**
- **RUHD**
@ -613,6 +636,7 @@
- **smotri:user**: Smotri.com user videos
- **Snotr**
- **Sohu**
- **SonyLIV**
- **soundcloud**
- **soundcloud:playlist**
- **soundcloud:search**: Soundcloud search
@ -639,10 +663,10 @@
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
- **Streamable**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -654,8 +678,8 @@
- **SztvHu**
- **Tagesschau**
- **tagesschau:player**
- **Tapely**
- **Tass**
- **TBS**
- **TDSLifeway**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
@ -681,8 +705,6 @@
- **TheStar**
- **ThisAmericanLife**
- **ThisAV**
- **THVideo**
- **THVideoPlaylist**
- **tinypic**: tinypic.com videos
- **tlc.de**
- **TMZ**
@ -690,13 +712,13 @@
- **TNAFlix**
- **TNAFlixNetworkEmbed**
- **toggle**
- **Tosh**: Tosh.0
- **tou.tv**
- **Toypics**: Toypics user profile
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **trollvids**
- **TruTube**
- **Tube8**
- **TubiTv**
- **tudou**
@ -719,9 +741,8 @@
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvland.com**
- **tvp**: Telewizja Polska
- **tvp:embed**: Telewizja Polska
- **tvp:series**
- **TVPlay**: TV3Play and related services
- **tvple**
- **Tweakers**
- **twitch:chapter**
- **twitch:clips**
@ -737,8 +758,12 @@
- **udemy:course**
- **UDNEmbed**: 聯合影音
- **Unistra**
- **uol.com.br**
- **uplynk**
- **uplynk:preplay**
- **Urort**: NRK P3 Urørt
- **URPlay**
- **USANetwork**
- **USAToday**
- **ustream**
- **ustream:channel**
@ -754,7 +779,9 @@
- **VevoPlaylist**
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **Viafree**
- **Vice**
- **Viceland**
- **ViceShow**
- **Vidbit**
- **Viddler**
@ -799,6 +826,7 @@
- **vk:wallpost**
- **vlive**
- **Vodlocker**
- **VODPlatform**
- **VoiceRepublic**
- **VoxMedia**
- **Vporn**
@ -873,6 +901,4 @@
- **Zapiks**
- **ZDF**
- **ZDFChannel**
- **zingmp3:album**: mp3.zing.vn albums
- **zingmp3:song**: mp3.zing.vn songs
- **ZippCast**
- **zingmp3**: mp3.zing.vn

3
test/test_InfoExtractor.py
View File

@ -48,6 +48,9 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
self.assertEqual(ie._og_search_property(('test0', 'test1'), html), 'foo > < bar')
self.assertRaises(RegexNotFoundError, ie._og_search_property, 'test0', html, None, fatal=True)
self.assertRaises(RegexNotFoundError, ie._og_search_property, ('test0', 'test00'), html, None, fatal=True)
def test_html_search_meta(self):
ie = self.ie

34
test/test_YoutubeDL.py
View File

@ -335,6 +335,40 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1['format_id'])
def test_audio_only_extractor_format_selection(self):
# For extractors with incomplete formats (all formats are audio-only or
# video-only) best and worst should fallback to corresponding best/worst
# video-only or audio-only formats (as per
# https://github.com/rg3/youtube-dl/pull/5556)
formats = [
{'format_id': 'low', 'ext': 'mp3', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'high', 'ext': 'mp3', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'best'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'high')
ydl = YDL({'format': 'worst'})
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'low')
def test_format_not_available(self):
formats = [
{'format_id': 'regular', 'ext': 'mp4', 'height': 360, 'url': TEST_URL},
{'format_id': 'video', 'ext': 'mp4', 'height': 720, 'acodec': 'none', 'url': TEST_URL},
]
info_dict = _make_result(formats)
# This must fail since complete video-audio format does not match filter
# and extractor does not provide incomplete only formats (i.e. only
# video-only or audio-only).
ydl = YDL({'format': 'best[height>360]'})
self.assertRaises(ExtractorError, ydl.process_ie_result, info_dict.copy())
def test_invalid_format_specs(self):
def assert_syntax_error(format_spec):
ydl = YDL({'format': format_spec})

2
test/test_all_urls.py
View File

@ -101,8 +101,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch(':ytsubs', ['youtube:subscriptions'])
self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows'])
def test_vimeo_matching(self):
self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])

32
test/test_utils.py
View File

@ -39,9 +39,11 @@ from youtube_dl.utils import (
is_html,
js_to_json,
limit_length,
mimetype2ext,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
parse_age_limit,
parse_duration,
parse_filesize,
parse_count,
@ -308,6 +310,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('25-09-2014'), 1411603200)
self.assertEqual(unified_timestamp('27.02.2016 17:30'), 1456594200)
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@ -431,6 +434,20 @@ class TestUtil(unittest.TestCase):
url_basename('http://media.w3.org/2010/05/sintel/trailer.mp4'),
'trailer.mp4')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
self.assertEqual(parse_age_limit(False), None)
self.assertEqual(parse_age_limit('invalid'), None)
self.assertEqual(parse_age_limit(0), 0)
self.assertEqual(parse_age_limit(18), 18)
self.assertEqual(parse_age_limit(21), 21)
self.assertEqual(parse_age_limit(22), None)
self.assertEqual(parse_age_limit('18'), 18)
self.assertEqual(parse_age_limit('18+'), 18)
self.assertEqual(parse_age_limit('PG-13'), 13)
self.assertEqual(parse_age_limit('TV-14'), 14)
self.assertEqual(parse_age_limit('TV-MA'), 17)
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
@ -609,6 +626,14 @@ class TestUtil(unittest.TestCase):
limit_length('foo bar baz asd', 12).startswith('foo bar'))
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
def test_mimetype2ext(self):
self.assertEqual(mimetype2ext(None), None)
self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
def test_parse_codecs(self):
self.assertEqual(parse_codecs(''), {})
self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
@ -696,6 +721,9 @@ class TestUtil(unittest.TestCase):
inp = '''{"foo":101}'''
self.assertEqual(js_to_json(inp), '''{"foo":101}''')
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@ -801,7 +829,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_filesize('2 MiB'), 2097152)
self.assertEqual(parse_filesize('5 GB'), 5000000000)
self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
self.assertEqual(parse_filesize('1,24 kb'), 1240)
self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
def test_parse_count(self):
self.assertEqual(parse_count(None), None)
@ -952,6 +983,7 @@ The first line
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'), [])
self.assertEqual(cli_option({}, '--proxy', 'proxy'), [])
self.assertEqual(cli_option({'retries': 10}, '--retries', 'retries'), ['--retries', '10'])
def test_cli_valueless_option(self):
self.assertEqual(cli_valueless_option(

70
test/test_verbose_output.py Normal file
View File

@ -0,0 +1,70 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
import unittest
import sys
import os
import subprocess
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
class TestVerboseOutput(unittest.TestCase):
def test_private_info_arg(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'--username', 'johnsmith@gmail.com',
'--password', 'secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'--username' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'--password' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_shortarg(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'-u', 'johnsmith@gmail.com',
'-p', 'secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'-u' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'-p' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_eq(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'--username=johnsmith@gmail.com',
'--password=secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'--username' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'--password' in serr)
self.assertTrue(b'secret' not in serr)
def test_private_info_shortarg_eq(self):
outp = subprocess.Popen(
[
sys.executable, 'youtube_dl/__main__.py', '-v',
'-u=johnsmith@gmail.com',
'-p=secret',
], cwd=rootDir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'-u' in serr)
self.assertTrue(b'johnsmith' not in serr)
self.assertTrue(b'-p' in serr)
self.assertTrue(b'secret' not in serr)
if __name__ == '__main__':
unittest.main()

87
youtube_dl/YoutubeDL.py
View File

@ -5,6 +5,7 @@ from __future__ import absolute_import, unicode_literals
import collections
import contextlib
import copy
import datetime
import errno
import fileinput
@ -248,7 +249,16 @@ class YoutubeDL(object):
source_address: (Experimental) Client-side IP address to bind to.
call_home: Boolean, true iff we are allowed to contact the
youtube-dl servers for debugging.
sleep_interval: Number of seconds to sleep before each download.
sleep_interval: Number of seconds to sleep before each download when
used alone or a lower bound of a range for randomized
sleep before each download (minimum possible number
of seconds to sleep) when used along with
max_sleep_interval.
max_sleep_interval:Upper bound of a range for randomized sleep before each
download (maximum possible number of seconds to sleep).
Must only be used along with sleep_interval.
Actual sleep time will be a random float from range
[sleep_interval; max_sleep_interval].
listformats: Print an overview of available video formats and exit.
list_thumbnails: Print a table of all thumbnails and exit.
match_filter: A function that gets called with the info_dict of
@ -1051,9 +1061,9 @@ class YoutubeDL(object):
if isinstance(selector, list):
fs = [_build_selector_function(s) for s in selector]
def selector_function(formats):
def selector_function(ctx):
for f in fs:
for format in f(formats):
for format in f(ctx):
yield format
return selector_function
elif selector.type == GROUP:
@ -1061,17 +1071,17 @@ class YoutubeDL(object):
elif selector.type == PICKFIRST:
fs = [_build_selector_function(s) for s in selector.selector]
def selector_function(formats):
def selector_function(ctx):
for f in fs:
picked_formats = list(f(formats))
picked_formats = list(f(ctx))
if picked_formats:
return picked_formats
return []
elif selector.type == SINGLE:
format_spec = selector.selector
def selector_function(formats):
formats = list(formats)
def selector_function(ctx):
formats = list(ctx['formats'])
if not formats:
return
if format_spec == 'all':
@ -1084,9 +1094,10 @@ class YoutubeDL(object):
if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
if audiovideo_formats:
yield audiovideo_formats[format_idx]
# for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format
elif (all(f.get('acodec') != 'none' for f in formats) or
all(f.get('vcodec') != 'none' for f in formats)):
# for extractors with incomplete formats (audio only (soundcloud)
# or video only (imgur)) we will fallback to best/worst
# {video,audio}-only format
elif ctx['incomplete_formats']:
yield formats[format_idx]
elif format_spec == 'bestaudio':
audio_formats = [
@ -1160,17 +1171,18 @@ class YoutubeDL(object):
}
video_selector, audio_selector = map(_build_selector_function, selector.selector)
def selector_function(formats):
formats = list(formats)
for pair in itertools.product(video_selector(formats), audio_selector(formats)):
def selector_function(ctx):
for pair in itertools.product(
video_selector(copy.deepcopy(ctx)), audio_selector(copy.deepcopy(ctx))):
yield _merge(pair)
filters = [self._build_format_filter(f) for f in selector.filters]
def final_selector(formats):
def final_selector(ctx):
ctx_copy = copy.deepcopy(ctx)
for _filter in filters:
formats = list(filter(_filter, formats))
return selector_function(formats)
ctx_copy['formats'] = list(filter(_filter, ctx_copy['formats']))
return selector_function(ctx_copy)
return final_selector
stream = io.BytesIO(format_spec.encode('utf-8'))
@ -1244,8 +1256,10 @@ class YoutubeDL(object):
info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
if thumbnails:
thumbnails.sort(key=lambda t: (
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
t.get('preference') if t.get('preference') is not None else -1,
t.get('width') if t.get('width') is not None else -1,
t.get('height') if t.get('height') is not None else -1,
t.get('id') if t.get('id') is not None else '', t.get('url')))
for i, t in enumerate(thumbnails):
t['url'] = sanitize_url(t['url'])
if t.get('width') and t.get('height'):
@ -1287,7 +1301,7 @@ class YoutubeDL(object):
for subtitle_format in subtitle:
if subtitle_format.get('url'):
subtitle_format['url'] = sanitize_url(subtitle_format['url'])
if 'ext' not in subtitle_format:
if subtitle_format.get('ext') is None:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
if self.params.get('listsubtitles', False):
@ -1342,7 +1356,7 @@ class YoutubeDL(object):
note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
)
# Automatically determine file extension if missing
if 'ext' not in format:
if format.get('ext') is None:
format['ext'] = determine_ext(format['url']).lower()
# Automatically determine protocol if missing (useful for format
# selection purposes)
@ -1377,7 +1391,34 @@ class YoutubeDL(object):
req_format_list.append('best')
req_format = '/'.join(req_format_list)
format_selector = self.build_format_selector(req_format)
formats_to_download = list(format_selector(formats))
# While in format selection we may need to have an access to the original
# format set in order to calculate some metrics or do some processing.
# For now we need to be able to guess whether original formats provided
# by extractor are incomplete or not (i.e. whether extractor provides only
# video-only or audio-only formats) for proper formats selection for
# extractors with such incomplete formats (see
# https://github.com/rg3/youtube-dl/pull/5556).
# Since formats may be filtered during format selection and may not match
# the original formats the results may be incorrect. Thus original formats
# or pre-calculated metrics should be passed to format selection routines
# as well.
# We will pass a context object containing all necessary additional data
# instead of just formats.
# This fixes incorrect format selection issue (see
# https://github.com/rg3/youtube-dl/issues/10083).
incomplete_formats = (
# All formats are video-only or
all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or
# all formats are audio-only
all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats))
ctx = {
'formats': formats,
'incomplete_formats': incomplete_formats,
}
formats_to_download = list(format_selector(ctx))
if not formats_to_download:
raise ExtractorError('requested format not available',
expected=True)
@ -1564,7 +1605,9 @@ class YoutubeDL(object):
self.to_screen('[info] Video subtitle %s.%s is already_present' % (sub_lang, sub_format))
else:
self.to_screen('[info] Writing video subtitles to: ' + sub_filename)
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
# Use newline='' to prevent conversion of newline characters
# See https://github.com/rg3/youtube-dl/issues/10268
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8', newline='') as subfile:
subfile.write(sub_data)
except (OSError, IOError):
self.report_error('Cannot write subtitles file ' + sub_filename)

12
youtube_dl/__init__.py
View File

@ -145,6 +145,16 @@ def _real_main(argv=None):
if numeric_limit is None:
parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit
if opts.sleep_interval is not None:
if opts.sleep_interval < 0:
parser.error('sleep interval must be positive or 0')
if opts.max_sleep_interval is not None:
if opts.max_sleep_interval < 0:
parser.error('max sleep interval must be positive or 0')
if opts.max_sleep_interval < opts.sleep_interval:
parser.error('max sleep interval must be greater than or equal to min sleep interval')
else:
opts.max_sleep_interval = opts.sleep_interval
def parse_retries(retries):
if retries in ('inf', 'infinite'):
@ -308,6 +318,7 @@ def _real_main(argv=None):
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,
@ -370,6 +381,7 @@ def _real_main(argv=None):
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval': opts.sleep_interval,
'max_sleep_interval': opts.max_sleep_interval,
'external_downloader': opts.external_downloader,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,

8
youtube_dl/downloader/common.py
View File

@ -4,6 +4,7 @@ import os
import re
import sys
import time
import random
from ..compat import compat_os_name
from ..utils import (
@ -342,8 +343,11 @@ class FileDownloader(object):
})
return True
sleep_interval = self.params.get('sleep_interval')
if sleep_interval:
min_sleep_interval = self.params.get('sleep_interval')
if min_sleep_interval:
max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
print(min_sleep_interval, max_sleep_interval)
sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
time.sleep(sleep_interval)

21
youtube_dl/downloader/dash.py
View File

@ -38,6 +38,7 @@ class DashSegmentsFD(FragmentFD):
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
def append_url_to_file(target_url, tmp_filename, segment_name):
target_filename = '%s-%s' % (tmp_filename, segment_name)
@ -52,26 +53,30 @@ class DashSegmentsFD(FragmentFD):
down.close()
segments_filenames.append(target_sanitized)
break
except (compat_urllib_error.HTTPError, ) as err:
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
# whole download to fail. However if the same fragment is immediately
# retried with the same request data this usually succeeds (1-2 attemps
# is usually enough) thus allowing to download the whole file successfully.
# So, we will retry all fragments that fail with 404 HTTP error for now.
if err.code != 404:
raise
# Retry fragment
# To be future-proof we will retry all fragments that fail with any
# HTTP error.
count += 1
if count <= fragment_retries:
self.report_retry_fragment(segment_name, count, fragment_retries)
self.report_retry_fragment(err, segment_name, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
self.report_skip_fragment(segment_name)
return True
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
return True
if initialization_url:
append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
if not append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init'):
return False
for i, segment_url in enumerate(segment_urls):
append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
if not append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i):
return False
self._finish_frag_download(ctx)

22
youtube_dl/downloader/external.py
View File

@ -96,6 +96,12 @@ class CurlFD(ExternalFD):
cmd = [self.exe, '--location', '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._bool_option('--continue-at', 'continuedl', '-', '0')
cmd += self._valueless_option('--silent', 'noprogress')
cmd += self._valueless_option('--verbose', 'verbose')
cmd += self._option('--limit-rate', 'ratelimit')
cmd += self._option('--retry', 'retries')
cmd += self._option('--max-filesize', 'max_filesize')
cmd += self._option('--interface', 'source_address')
cmd += self._option('--proxy', 'proxy')
cmd += self._valueless_option('--insecure', 'nocheckcertificate')
@ -103,6 +109,16 @@ class CurlFD(ExternalFD):
cmd += ['--', info_dict['url']]
return cmd
def _call_downloader(self, tmpfilename, info_dict):
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
self._debug_cmd(cmd)
# curl writes the progress to stderr so don't capture it.
p = subprocess.Popen(cmd)
p.communicate()
return p.returncode
class AxelFD(ExternalFD):
AVAILABLE_OPT = '-V'
@ -204,6 +220,12 @@ class FFmpegFD(ExternalFD):
if proxy:
if not re.match(r'^[\da-zA-Z]+://', proxy):
proxy = 'http://%s' % proxy
if proxy.startswith('socks'):
self.report_warning(
'%s does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.' % self.get_basename())
# Since December 2015 ffmpeg supports -http_proxy option (see
# http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
# We could switch to the following code if we are able to detect version properly

15
youtube_dl/downloader/fragment.py
View File

@ -6,6 +6,7 @@ import time
from .common import FileDownloader
from .http import HttpFD
from ..utils import (
error_to_compat_str,
encodeFilename,
sanitize_open,
)
@ -22,13 +23,19 @@ class FragmentFD(FileDownloader):
Available options:
fragment_retries: Number of times to retry a fragment for HTTP error (DASH only)
fragment_retries: Number of times to retry a fragment for HTTP error (DASH
and hlsnative only)
skip_unavailable_fragments:
Skip unavailable fragments (DASH and hlsnative only)
"""
def report_retry_fragment(self, fragment_name, count, retries):
def report_retry_fragment(self, err, fragment_name, count, retries):
self.to_screen(
'[download] Got server HTTP error. Retrying fragment %s (attempt %d of %s)...'
% (fragment_name, count, self.format_retries(retries)))
'[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)))
def report_skip_fragment(self, fragment_name):
self.to_screen('[download] Skipping fragment %s...' % fragment_name)
def _prepare_and_start_frag_download(self, ctx):
self._prepare_frag_download(ctx)

52
youtube_dl/downloader/hls.py
View File

@ -13,6 +13,7 @@ from .fragment import FragmentFD
from .external import FFmpegFD
from ..compat import (
compat_urllib_error,
compat_urlparse,
compat_struct_pack,
)
@ -20,6 +21,7 @@ from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes,
update_url_query,
)
@ -82,6 +84,14 @@ class HlsFD(FragmentFD):
self._prepare_and_start_frag_download(ctx)
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
test = self.params.get('test', False)
extra_query = None
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
if extra_param_to_segment_url:
extra_query = compat_urlparse.parse_qs(extra_param_to_segment_url)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
@ -94,13 +104,37 @@ class HlsFD(FragmentFD):
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i)
success = ctx['dl'].download(frag_filename, {'url': frag_url})
if not success:
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
while count <= fragment_retries:
try:
success = ctx['dl'].download(frag_filename, {'url': frag_url})
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.
# First we try to retry then either skip or abort.
# See https://github.com/rg3/youtube-dl/issues/10165,
# https://github.com/rg3/youtube-dl/issues/10448).
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_name, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
i += 1
media_sequence += 1
self.report_skip_fragment(frag_name)
continue
self.report_error(
'giving up after %s fragment retries' % fragment_retries)
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
frag_content = AES.new(
@ -108,7 +142,7 @@ class HlsFD(FragmentFD):
ctx['dest_stream'].write(frag_content)
frags_filenames.append(frag_sanitized)
# We only download the first fragment during the test
if self.params.get('test', False):
if test:
break
i += 1
media_sequence += 1
@ -116,10 +150,12 @@ class HlsFD(FragmentFD):
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:])
decrypt_info['IV'] = binascii.unhexlify(decrypt_info['IV'][2:].zfill(32))
if not re.match(r'^https?://', decrypt_info['URI']):
decrypt_info['URI'] = compat_urlparse.urljoin(
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()
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])

55
youtube_dl/extractor/abc.py
View File

@ -7,6 +7,7 @@ from ..utils import (
ExtractorError,
js_to_json,
int_or_none,
parse_iso8601,
)
@ -93,3 +94,57 @@ class ABCIE(InfoExtractor):
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://iview.abc.net.au/programs/gardening-australia/FA1505V024S00',
'md5': '979d10b2939101f0d27a06b79edad536',
'info_dict': {
'id': 'FA1505V024S00',
'ext': 'mp4',
'title': 'Series 27 Ep 24',
'description': 'md5:b28baeae7504d1148e1d2f0e3ed3c15d',
'upload_date': '20160820',
'uploader_id': 'abc1',
'timestamp': 1471719600,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_params = self._parse_json(self._search_regex(
r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
title = video_params['title']
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
formats = self._extract_akamai_formats(stream['hds-unmetered'], video_id)
self._sort_formats(formats)
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')
if src_vtt:
subtitles['en'] = [{
'url': src_vtt,
'ext': 'vtt',
}]
return {
'id': video_id,
'title': title,
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': video_params.get('seriesTitle'),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage)),
'episode': self._html_search_meta('episode_title', webpage),
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
}

137
youtube_dl/extractor/adobepass.py Normal file
View File

@ -0,0 +1,137 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
import time
import xml.etree.ElementTree as etree
from .common import InfoExtractor
from ..utils import (
unescapeHTML,
urlencode_postdata,
unified_timestamp,
)
class AdobePassIE(InfoExtractor):
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
channel_title = etree.SubElement(channel, 'title')
channel_title.text = provider_id
item = etree.SubElement(channel, 'item')
resource_title = etree.SubElement(item, 'title')
resource_title.text = title
resource_guid = etree.SubElement(item, 'guid')
resource_guid.text = guid
resource_rating = etree.SubElement(item, 'media:rating')
resource_rating.attrib = {'scheme': 'urn:v-chip'}
resource_rating.text = rating
return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
def xml_text(xml_str, tag):
return self._search_regex(
'<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
def is_expired(token, date_ele):
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
return token_expires and token_expires <= int(time.time())
mvpd_headers = {
'ap_42': 'anonymous',
'ap_11': 'Linux i686',
'ap_z': self._USER_AGENT,
'User-Agent': self._USER_AGENT,
}
guid = xml_text(resource, 'guid')
requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
authn_token = None
if not authn_token:
# TODO add support for other TV Providers
mso_id = 'DTV'
username, password = self._get_netrc_login_info(mso_id)
if not username or not password:
return ''
def post_form(form_page, note, data={}):
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
return self._download_webpage(
post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
provider_redirect_page = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
})
provider_login_page = post_form(
provider_redirect_page, 'Downloading Provider Login Page')
mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
'username': username,
'password': password,
})
post_form(mvpd_confirm_page, 'Confirming Login')
session = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
}), headers=mvpd_headers)
if '<pendingLogout' in session:
self._downloader.cache.store('mvpd', requestor_id, {})
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
requestor_info['authn_token'] = authn_token
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
authz_token = requestor_info.get(guid)
if authz_token and is_expired(authz_token, 'simpleTokenTTL'):
authz_token = None
if not authz_token:
authorize = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
'Retrieving Authorization Token', data=urlencode_postdata({
'resource_id': resource,
'requestor_id': requestor_id,
'authentication_token': authn_token,
'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
'userMeta': '1',
}), headers=mvpd_headers)
if '<pendingLogout' in authorize:
self._downloader.cache.store('mvpd', requestor_id, {})
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
requestor_info[guid] = authz_token
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
mvpd_headers.update({
'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
})
short_authorize = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
video_id, 'Retrieving Media Token', data=urlencode_postdata({
'authz_token': authz_token,
'requestor_id': requestor_id,
'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
'hashed_guid': 'false',
}), headers=mvpd_headers)
if '<pendingLogout' in short_authorize:
self._downloader.cache.store('mvpd', requestor_id, {})
return self._extract_mvpd_auth(url, video_id, requestor_id, resource)
return short_authorize

117
youtube_dl/extractor/adultswim.py
View File

@ -3,16 +3,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .turner import TurnerBaseIE
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
xpath_text,
int_or_none,
)
class AdultSwimIE(InfoExtractor):
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TESTS = [{
@ -83,6 +81,21 @@ class AdultSwimIE(InfoExtractor):
# 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,
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
@staticmethod
@ -133,79 +146,56 @@ class AdultSwimIE(InfoExtractor):
if video_info is None:
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
else:
raise ExtractorError('Unable to find video info')
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 = bootstrapped_data['show']
show_title = show['title']
stream = video_info.get('stream')
clips = [stream] if stream else video_info.get('clips')
if not clips:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.'
if video_info.get('auth') is True else 'Unable to find stream or clips',
expected=True)
segment_ids = [clip['videoPlaybackID'] for clip in clips]
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']]
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')
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
episode_description = video_info.get('description')
episode_duration = int_or_none(video_info.get('duration'))
view_count = int_or_none(video_info.get('views'))
entries = []
for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
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)
idoc = self._download_xml(
segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information')
segment_duration = float_or_none(
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = []
file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
unique_urls = []
unique_file_els = []
for file_el in file_els:
media_url = file_el.text
if not media_url or determine_ext(media_url) == 'f4m':
continue
if file_el.text not in unique_urls:
unique_urls.append(file_el.text)
unique_file_els.append(file_el)
for file_el in unique_file_els:
bitrate = file_el.attrib.get('bitrate')
ftype = file_el.attrib.get('type')
media_url = file_el.text
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, segment_title, 'mp4', preference=0,
m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text.strip(),
# The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None,
})
self._sort_formats(formats)
entries.append({
segement_info.update({
'id': segment_id,
'title': segment_title,
'formats': formats,
'duration': segment_duration,
'description': episode_description
'description': episode_description,
})
entries.append(segement_info)
return {
'_type': 'playlist',
@ -214,5 +204,6 @@ class AdultSwimIE(InfoExtractor):
'entries': entries,
'title': '%s - %s' % (show_title, episode_title),
'description': episode_description,
'duration': episode_duration
'duration': episode_duration,
'view_count': view_count,
}

5
youtube_dl/extractor/aenetworks.py
View File

@ -109,7 +109,10 @@ class AENetworksIE(AENetworksBaseIE):
info = self._parse_theplatform_metadata(theplatform_metadata)
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]
resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>%s</title><item><title>%s</title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (requestor_id, theplatform_metadata['title'], theplatform_metadata['AETN$PPL_pplProgramId'], theplatform_metadata['ratings'][0]['rating'])
resource = self._get_mvpd_resource(
requestor_id, theplatform_metadata['title'],
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
theplatform_metadata['ratings'][0]['rating'])
query['auth'] = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
info.update(self._search_json_ld(webpage, video_id, fatal=False))

91
youtube_dl/extractor/amcnetworks.py Normal file
View File

@ -0,0 +1,91 @@
# coding: utf-8
from __future__ import unicode_literals
from .theplatform import ThePlatformIE
from ..utils import (
update_url_query,
parse_age_limit,
int_or_none,
)
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?season-\d+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
'info_dict': {
'id': 's3MX01Nl4vPH',
'ext': 'mp4',
'title': 'Maron - Season 4 - Step 1',
'description': 'In denial about his current situation, Marc is reluctantly convinced by his friends to enter rehab. Starring Marc Maron and Constance Zimmer.',
'age_limit': 17,
'upload_date': '20160505',
'timestamp': 1462468831,
'uploader': 'AMCN',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
'only_matching': True,
}, {
'url': 'http://www.amc.com/shows/preacher/full-episodes/season-01/episode-00/pilot',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/million-dollar-matchmaker/season-01/episode-06-the-dumped-dj-and-shallow-hal',
'only_matching': True,
}, {
'url': 'http://www.ifc.com/movies/chaos',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
query = {
'mbr': 'true',
'manifest': 'm3u',
}
media_url = self._search_regex(r'window\.platformLinkURL\s*=\s*[\'"]([^\'"]+)', webpage, 'media url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), display_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
video_id = theplatform_metadata['pid']
title = theplatform_metadata['title']
rating = theplatform_metadata['ratings'][0]['rating']
auth_required = self._search_regex(r'window\.authRequired\s*=\s*(true|false);', webpage, 'auth required')
if auth_required == 'true':
requestor_id = self._search_regex(r'window\.requestor_id\s*=\s*[\'"]([^\'"]+)', webpage, 'requestor id')
resource = self._get_mvpd_resource(requestor_id, title, video_id, rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, requestor_id, resource)
media_url = update_url_query(media_url, query)
formats, subtitles = self._extract_theplatform_smil(media_url, video_id)
self._sort_formats(formats)
info.update({
'id': video_id,
'subtitles': subtitles,
'formats': formats,
'age_limit': parse_age_limit(parse_age_limit(rating)),
})
ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
if ns_keys:
ns = list(ns_keys)[0]
series = theplatform_metadata.get(ns + '$show')
season_number = int_or_none(theplatform_metadata.get(ns + '$season'))
episode = theplatform_metadata.get(ns + '$episodeTitle')
episode_number = int_or_none(theplatform_metadata.get(ns + '$episode'))
if season_number:
title = 'Season %d - %s' % (season_number, title)
if series:
title = '%s - %s' % (series, title)
info.update({
'title': title,
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
})
return info

4
youtube_dl/extractor/aol.py
View File

@ -123,6 +123,10 @@ class AolFeaturesIE(InfoExtractor):
'title': 'What To Watch - February 17, 2016',
},
'add_ie': ['FiveMin'],
'params': {
# encrypted m3u8 download
'skip_download': True,
},
}]
def _real_extract(self, url):

14
youtube_dl/extractor/aparat.py
View File

@ -1,8 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
@ -15,7 +13,7 @@ class AparatIE(InfoExtractor):
_TEST = {
'url': 'http://www.aparat.com/v/wP8On',
'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
@ -31,13 +29,13 @@ class AparatIE(InfoExtractor):
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + '/vt/frame')
embed_url = 'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id
webpage = self._download_webpage(embed_url, video_id)
video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
for i, video_url in enumerate(video_urls):
file_list = self._parse_json(self._search_regex(
r'fileList\s*=\s*JSON\.parse\(\'([^\']+)\'\)', webpage, 'file list'), video_id)
for i, item in enumerate(file_list[0]):
video_url = item['file']
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note='Testing video URL %d' % i, errnote=False)

78
youtube_dl/extractor/archiveorg.py
View File

@ -1,67 +1,65 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
from .jwplatform import JWPlatformBaseIE
from ..utils import (
unified_strdate,
clean_html,
)
class ArchiveOrgIE(InfoExtractor):
class ArchiveOrgIE(JWPlatformBaseIE):
IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos'
_VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_VALID_URL = r'https?://(?:www\.)?archive\.org/(?:details|embed)/(?P<id>[^/?#]+)(?:[?].*)?$'
_TESTS = [{
'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': {
'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'ext': 'ogv',
'ext': 'ogg',
'title': '1968 Demo - FJCC Conference Presentation Reel #1',
'description': 'md5:1780b464abaca9991d8968c877bb53ed',
'description': 'md5:da45c349df039f1cc8075268eb1b5c25',
'upload_date': '19681210',
'uploader': 'SRI International'
}
}, {
'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04',
'md5': 'bc73c8ab3838b5a8fc6c6651fa7b58ba',
'info_dict': {
'id': 'Cops1922',
'ext': 'ogv',
'ext': 'mp4',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3',
'description': 'md5:b4544662605877edd99df22f9620d858',
}
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://archive.org/embed/' + video_id, video_id)
jwplayer_playlist = self._parse_json(self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
webpage, 'jwplayer playlist'), video_id)
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)
json_url = url + ('&' if '?' in url else '?') + 'output=json'
data = self._download_json(json_url, video_id)
def get_optional(metadata, field):
return metadata.get(field, [None])[0]
def get_optional(data_dict, field):
return data_dict['metadata'].get(field, [None])[0]
title = get_optional(data, 'title')
description = get_optional(data, 'description')
uploader = get_optional(data, 'creator')
upload_date = unified_strdate(get_optional(data, 'date'))
formats = [
{
'format': fdata['format'],
'url': 'http://' + data['server'] + data['dir'] + fn,
'file_size': int(fdata['size']),
}
for fn, fdata in data['files'].items()
if 'Video' in fdata['format']]
self._sort_formats(formats)
return {
'_type': 'video',
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'uploader': uploader,
'upload_date': upload_date,
'thumbnail': data.get('misc', {}).get('image'),
}
metadata = self._download_json(
'http://archive.org/details/' + video_id, video_id, query={
'output': 'json',
})['metadata']
info.update({
'title': get_optional(metadata, 'title') or info.get('title'),
'description': clean_html(get_optional(metadata, 'description')),
})
if info.get('_type') != 'playlist':
info.update({
'uploader': get_optional(metadata, 'creator'),
'upload_date': unified_strdate(get_optional(metadata, 'date')),
})
return info

14
youtube_dl/extractor/ard.py
View File

@ -20,7 +20,7 @@ from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
@ -62,6 +62,18 @@ class ARDMediathekIE(InfoExtractor):
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'md5': '4e8f00631aac0395fee17368ac0e9867',
'info_dict': {
'id': '30796318',
'ext': 'mp3',
'title': 'Vor dem Fest',
'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
'duration': 3287,
},
'skip': 'Video is no longer available',
}]
def _extract_media_info(self, media_info_url, webpage, video_id):

115
youtube_dl/extractor/arkena.py Normal file
View File

@ -0,0 +1,115 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
mimetype2ext,
parse_iso8601,
strip_jsonp,
)
class ArkenaIE(InfoExtractor):
_VALID_URL = r'https?://play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)'
_TESTS = [{
'url': 'https://play.arkena.com/embed/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411',
'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
'info_dict': {
'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'description': 'Royalty free test video',
'timestamp': 1432816365,
'upload_date': '20150528',
'is_live': False,
},
}, {
'url': 'https://play.arkena.com/config/avp/v2/player/media/b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe/1/129411/?callbackMethod=jQuery1111023664739129262213_1469227693893',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/config/avp/v1/player/media/327336/darkmatter/131064/?callbackMethod=jQuery1111002221189684892677_1469227595972',
'only_matching': True,
}, {
'url': 'http://play.arkena.com/embed/avp/v1/player/media/327336/darkmatter/131064/',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
# See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
webpage)
if mobj:
return mobj.group('url')
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
account_id = mobj.group('account_id')
playlist = self._download_json(
'https://play.arkena.com/config/avp/v2/player/media/%s/0/%s/?callbackMethod=_'
% (video_id, account_id),
video_id, transform_source=strip_jsonp)['Playlist'][0]
media_info = playlist['MediaInfo']
title = media_info['Title']
media_files = playlist['MediaFiles']
is_live = False
formats = []
for kind_case, kind_formats in media_files.items():
kind = kind_case.lower()
for f in kind_formats:
f_url = f.get('Url')
if not f_url:
continue
is_live = f.get('Live') == 'true'
exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None))
if kind == 'm3u8' or 'm3u8' in exts:
formats.extend(self._extract_m3u8_formats(
f_url, video_id, 'mp4',
entry_protocol='m3u8' if is_live else 'm3u8_native',
m3u8_id=kind, fatal=False, live=is_live))
elif kind == 'flash' or 'f4m' in exts:
formats.extend(self._extract_f4m_formats(
f_url, video_id, f4m_id=kind, fatal=False))
elif kind == 'dash' or 'mpd' in exts:
formats.extend(self._extract_mpd_formats(
f_url, video_id, mpd_id=kind, fatal=False))
elif kind == 'silverlight':
# TODO: process when ism is supported (see
# https://github.com/rg3/youtube-dl/issues/8118)
continue
else:
tbr = float_or_none(f.get('Bitrate'), 1000)
formats.append({
'url': f_url,
'format_id': '%s-%d' % (kind, tbr) if tbr else kind,
'tbr': tbr,
})
self._sort_formats(formats)
description = media_info.get('Description')
video_id = media_info.get('VideoId') or video_id
timestamp = parse_iso8601(media_info.get('PublishDate'))
thumbnails = [{
'url': thumbnail['Url'],
'width': int_or_none(thumbnail.get('Size')),
} for thumbnail in (media_info.get('Poster') or []) if thumbnail.get('Url')]
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'is_live': is_live,
'thumbnails': thumbnails,
'formats': formats,
}

97
youtube_dl/extractor/dcn.py → youtube_dl/extractor/awaan.py
View File

@ -12,46 +12,41 @@ from ..compat import (
from ..utils import (
int_or_none,
parse_iso8601,
sanitized_Request,
smuggle_url,
unsmuggle_url,
urlencode_postdata,
)
class DCNIE(InfoExtractor):
class AWAANIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
def _real_extract(self, url):
show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://www.dcndigital.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'DCNSeason')
'http://awaan.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'AWAANSeason')
else:
return self.url_result(
'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
class DCNBaseIE(InfoExtractor):
def _extract_video_info(self, video_data, video_id, is_live):
class AWAANBaseIE(InfoExtractor):
def _parse_video_data(self, video_data, video_id, is_live):
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
duration = int_or_none(video_data.get('duration'))
description = video_data.get('description_en') or video_data.get('description_ar')
timestamp = parse_iso8601(video_data.get('create_time'), ' ')
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
'is_live': is_live,
}
@ -62,11 +57,9 @@ class DCNBaseIE(InfoExtractor):
r'file\s*:\s*"https?(://[^"]+)/playlist.m3u8',
r'<a[^>]+href="rtsp(://[^"]+)"'
], webpage, 'format url')
# TODO: Current DASH formats are broken - $Time$ pattern in
# <SegmentTemplate> not implemented yet
# formats.extend(self._extract_mpd_formats(
# format_url_base + '/manifest.mpd',
# video_id, mpd_id='dash', fatal=False))
formats.extend(self._extract_mpd_formats(
format_url_base + '/manifest.mpd',
video_id, mpd_id='dash', fatal=False))
formats.extend(self._extract_m3u8_formats(
format_url_base + '/playlist.m3u8', video_id, 'mp4',
m3u8_entry_protocol, m3u8_id='hls', fatal=False))
@ -77,11 +70,12 @@ class DCNBaseIE(InfoExtractor):
return formats
class DCNVideoIE(DCNBaseIE):
IE_NAME = 'dcn:video'
class AWAANVideoIE(AWAANBaseIE):
IE_NAME = 'awaan:video'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
'md5': '5f61c33bfc7794315c671a62d43116aa',
'info_dict':
{
'id': '17375',
@ -92,10 +86,6 @@ class DCNVideoIE(DCNBaseIE):
'timestamp': 1227504126,
'upload_date': '20081124',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
'only_matching': True,
@ -104,11 +94,10 @@ class DCNVideoIE(DCNBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
request = sanitized_Request(
video_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
headers={'Origin': 'http://www.dcndigital.ae'})
video_data = self._download_json(request, video_id)
info = self._extract_video_info(video_data, video_id, False)
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
@ -123,19 +112,31 @@ class DCNVideoIE(DCNBaseIE):
return info
class DCNLiveIE(DCNBaseIE):
IE_NAME = 'dcn:live'
class AWAANLiveIE(AWAANBaseIE):
IE_NAME = 'awaan:live'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
_TEST = {
'url': 'http://awaan.ae/live/6/dubai-tv',
'info_dict': {
'id': '6',
'ext': 'mp4',
'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'upload_date': '20150107',
'timestamp': 1420588800,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
request = sanitized_Request(
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
headers={'Origin': 'http://www.dcndigital.ae'})
channel_data = self._download_json(request, channel_id)
info = self._extract_video_info(channel_data, channel_id, True)
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
@ -150,8 +151,8 @@ class DCNLiveIE(DCNBaseIE):
return info
class DCNSeasonIE(InfoExtractor):
IE_NAME = 'dcn:season'
class AWAANSeasonIE(InfoExtractor):
IE_NAME = 'awaan:season'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
_TEST = {
'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
@ -172,21 +173,17 @@ class DCNSeasonIE(InfoExtractor):
data['season'] = season_id
show_id = smuggled_data.get('show_id')
if show_id is None:
request = sanitized_Request(
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
headers={'Origin': 'http://www.dcndigital.ae'})
season = self._download_json(request, season_id)
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
request = sanitized_Request(
show = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
urlencode_postdata(data),
{
'Origin': 'http://www.dcndigital.ae',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
})
show = self._download_json(request, show_id)
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
@ -197,6 +194,6 @@ class DCNSeasonIE(InfoExtractor):
for video in show['videos']:
video_id = compat_str(video['id'])
entries.append(self.url_result(
'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
return self.playlist_result(entries, season_id, title)

16
youtube_dl/extractor/bandcamp.py
View File

@ -162,6 +162,15 @@ class BandcampAlbumIE(InfoExtractor):
'uploader_id': 'dotscale',
},
'playlist_mincount': 7,
}, {
# with escaped quote in title
'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
'info_dict': {
'title': '"Entropy" EP',
'uploader_id': 'jstrecords',
'id': 'entropy-ep',
},
'playlist_mincount': 3,
}]
def _real_extract(self, url):
@ -176,8 +185,11 @@ class BandcampAlbumIE(InfoExtractor):
entries = [
self.url_result(compat_urlparse.urljoin(url, t_path), ie=BandcampIE.ie_key())
for t_path in tracks_paths]
title = self._search_regex(
r'album_title\s*:\s*"(.*?)"', webpage, 'title', fatal=False)
title = self._html_search_regex(
r'album_title\s*:\s*"((?:\\.|[^"\\])+?)"',
webpage, 'title', fatal=False)
if title:
title = title.replace(r'\"', '"')
return {
'_type': 'playlist',
'uploader_id': uploader_id,

348
youtube_dl/extractor/bbc.py
View File

@ -2,19 +2,23 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import (
dict_get,
ExtractorError,
float_or_none,
int_or_none,
parse_duration,
parse_iso8601,
try_get,
unescapeHTML,
)
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_urlparse,
)
@ -55,11 +59,12 @@ class BBCCoUkIE(InfoExtractor):
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
'info_dict': {
'id': 'b039d07m',
'ext': 'mp4',
'ext': 'flv',
'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
'description': 'The Canadian poet and songwriter reflects on his musical career.',
},
'params': {
# rtmp download
'skip_download': True,
}
},
@ -91,7 +96,7 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'this episode is not currently available',
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
},
{
'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
@ -106,7 +111,7 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'this episode is not currently available',
'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
}, {
'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
'info_dict': {
@ -126,12 +131,13 @@ class BBCCoUkIE(InfoExtractor):
'note': 'Audio',
'info_dict': {
'id': 'p022h44j',
'ext': 'mp4',
'ext': 'flv',
'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
'duration': 227,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
@ -139,12 +145,13 @@ class BBCCoUkIE(InfoExtractor):
'note': 'Video',
'info_dict': {
'id': 'p025c103',
'ext': 'mp4',
'ext': 'flv',
'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
'duration': 226,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
@ -160,7 +167,7 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'this episode is not currently available',
'skip': 'geolocation',
}, {
'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
'info_dict': {
@ -174,7 +181,7 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'this episode is not currently available',
'skip': 'geolocation',
}, {
# iptv-all mediaset fails with geolocation however there is no geo restriction
# for this programme at all
@ -189,17 +196,18 @@ class BBCCoUkIE(InfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'this episode is not currently available on BBC iPlayer Radio',
'skip': 'Now it\'s really geo-restricted',
}, {
# compact player (https://github.com/rg3/youtube-dl/issues/8147)
'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
'info_dict': {
'id': 'p028bfkj',
'ext': 'mp4',
'ext': 'flv',
'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
@ -225,51 +233,6 @@ class BBCCoUkIE(InfoExtractor):
asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
return [ref.get('href') for ref in asx.findall('./Entry/ref')]
def _extract_connection(self, connection, programme_id):
formats = []
kind = connection.get('kind')
protocol = connection.get('protocol')
supplier = connection.get('supplier')
if protocol == 'http':
href = connection.get('href')
transfer_format = connection.get('transferFormat')
# ASX playlist
if supplier == 'asx':
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
formats.append({
'url': ref,
'format_id': 'ref%s_%s' % (i, supplier),
})
# Skip DASH until supported
elif transfer_format == 'dash':
pass
elif transfer_format == 'hls':
formats.extend(self._extract_m3u8_formats(
href, programme_id, 'mp4', 'm3u8_native',
m3u8_id=supplier, fatal=False))
# Direct link
else:
formats.append({
'url': href,
'format_id': supplier or kind or protocol,
})
elif protocol == 'rtmp':
application = connection.get('application', 'ondemand')
auth_string = connection.get('authString')
identifier = connection.get('identifier')
server = connection.get('server')
formats.append({
'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
'play_path': identifier,
'app': '%s?%s' % (application, auth_string),
'page_url': 'http://www.bbc.co.uk',
'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
'rtmp_live': False,
'ext': 'flv',
'format_id': supplier,
})
return formats
def _extract_items(self, playlist):
return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
@ -290,47 +253,6 @@ class BBCCoUkIE(InfoExtractor):
def _extract_connections(self, media):
return self._findall_ns(media, './{%s}connection')
def _extract_video(self, media, programme_id):
formats = []
vbr = int_or_none(media.get('bitrate'))
vcodec = media.get('encoding')
service = media.get('service')
width = int_or_none(media.get('width'))
height = int_or_none(media.get('height'))
file_size = int_or_none(media.get('media_file_size'))
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
if format.get('protocol') != 'm3u8_native':
format.update({
'width': width,
'height': height,
'vbr': vbr,
'vcodec': vcodec,
'filesize': file_size,
})
if service:
format['format_id'] = '%s_%s' % (service, format['format_id'])
formats.extend(conn_formats)
return formats
def _extract_audio(self, media, programme_id):
formats = []
abr = int_or_none(media.get('bitrate'))
acodec = media.get('encoding')
service = media.get('service')
for connection in self._extract_connections(media):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
format.update({
'format_id': '%s_%s' % (service, format['format_id']),
'abr': abr,
'acodec': acodec,
'vcodec': 'none',
})
formats.extend(conn_formats)
return formats
def _get_subtitles(self, media, programme_id):
subtitles = {}
for connection in self._extract_connections(media):
@ -376,13 +298,87 @@ class BBCCoUkIE(InfoExtractor):
def _process_media_selector(self, media_selection, programme_id):
formats = []
subtitles = None
urls = []
for media in self._extract_medias(media_selection):
kind = media.get('kind')
if kind == 'audio':
formats.extend(self._extract_audio(media, programme_id))
elif kind == 'video':
formats.extend(self._extract_video(media, programme_id))
if kind in ('video', 'audio'):
bitrate = int_or_none(media.get('bitrate'))
encoding = media.get('encoding')
service = media.get('service')
width = int_or_none(media.get('width'))
height = int_or_none(media.get('height'))
file_size = int_or_none(media.get('media_file_size'))
for connection in self._extract_connections(media):
href = connection.get('href')
if href in urls:
continue
if href:
urls.append(href)
conn_kind = connection.get('kind')
protocol = connection.get('protocol')
supplier = connection.get('supplier')
transfer_format = connection.get('transferFormat')
format_id = supplier or conn_kind or protocol
if service:
format_id = '%s_%s' % (service, format_id)
# ASX playlist
if supplier == 'asx':
for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
formats.append({
'url': ref,
'format_id': 'ref%s_%s' % (i, format_id),
})
elif transfer_format == 'dash':
formats.extend(self._extract_mpd_formats(
href, programme_id, mpd_id=format_id, fatal=False))
elif transfer_format == 'hls':
formats.extend(self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
elif transfer_format == 'hds':
formats.extend(self._extract_f4m_formats(
href, programme_id, f4m_id=format_id, fatal=False))
else:
if not service and not supplier and bitrate:
format_id += '-%d' % bitrate
fmt = {
'format_id': format_id,
'filesize': file_size,
}
if kind == 'video':
fmt.update({
'width': width,
'height': height,
'vbr': bitrate,
'vcodec': encoding,
})
else:
fmt.update({
'abr': bitrate,
'acodec': encoding,
'vcodec': 'none',
})
if protocol == 'http':
# Direct link
fmt.update({
'url': href,
})
elif protocol == 'rtmp':
application = connection.get('application', 'ondemand')
auth_string = connection.get('authString')
identifier = connection.get('identifier')
server = connection.get('server')
fmt.update({
'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
'play_path': identifier,
'app': '%s?%s' % (application, auth_string),
'page_url': 'http://www.bbc.co.uk',
'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
'rtmp_live': False,
'ext': 'flv',
})
formats.append(fmt)
elif kind == 'captions':
subtitles = self.extract_subtitles(media, programme_id)
return formats, subtitles
@ -587,6 +583,7 @@ class BBCIE(BBCCoUkIE):
'id': '150615_telabyad_kentin_cogu',
'ext': 'mp4',
'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
'timestamp': 1434397334,
'upload_date': '20150615',
},
@ -600,6 +597,7 @@ class BBCIE(BBCCoUkIE):
'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'ext': 'mp4',
'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
'timestamp': 1434713142,
'upload_date': '20150619',
},
@ -649,6 +647,23 @@ class BBCIE(BBCCoUkIE):
# rtmp download
'skip_download': True,
}
}, {
# single video embedded with Morph
'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
'info_dict': {
'id': 'p041vhd0',
'ext': 'mp4',
'title': "Nigeria v Japan - Men's First Round",
'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
'duration': 7980,
'uploader': 'BBC Sport',
'uploader_id': 'bbc_sport',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Georestricted to UK',
}, {
# single video with playlist.sxml URL in playlist param
'url': 'http://www.bbc.com/sport/0/football/33653409',
@ -746,7 +761,7 @@ class BBCIE(BBCCoUkIE):
webpage = self._download_webpage(url, playlist_id)
json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
timestamp = json_ld_info.get('timestamp')
playlist_title = json_ld_info.get('title')
@ -815,8 +830,29 @@ class BBCIE(BBCCoUkIE):
# http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
playlist = data_playable.get('otherSettings', {}).get('playlist', {})
if playlist:
entries.append(self._extract_from_playlist_sxml(
playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
entry = None
for key in ('streaming', 'progressiveDownload'):
playlist_url = playlist.get('%sUrl' % key)
if not playlist_url:
continue
try:
info = self._extract_from_playlist_sxml(
playlist_url, playlist_id, timestamp)
if not entry:
entry = info
else:
entry['title'] = info['title']
entry['formats'].extend(info['formats'])
except Exception as e:
# Some playlist URL may fail with 500, at the same time
# the other one may work fine (e.g.
# http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
continue
raise
if entry:
self._sort_formats(entry['formats'])
entries.append(entry)
if entries:
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
@ -849,6 +885,50 @@ class BBCIE(BBCCoUkIE):
'subtitles': subtitles,
}
# Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
# There are several setPayload calls may be present but the video
# seems to be always related to the first one
morph_payload = self._parse_json(
self._search_regex(
r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
webpage, 'morph payload', default='{}'),
playlist_id, fatal=False)
if morph_payload:
components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
for component in components:
if not isinstance(component, dict):
continue
lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
if not lead_media:
continue
identifiers = lead_media.get('identifiers')
if not identifiers or not isinstance(identifiers, dict):
continue
programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
if not programme_id:
continue
title = lead_media.get('title') or self._og_search_title(webpage)
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
description = lead_media.get('summary')
uploader = lead_media.get('masterBrand')
uploader_id = lead_media.get('mid')
duration = None
duration_d = lead_media.get('duration')
if isinstance(duration_d, dict):
duration = parse_duration(dict_get(
duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
'subtitles': subtitles,
}
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),
@ -866,7 +946,7 @@ class BBCIE(BBCCoUkIE):
r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
if entries:
return self.playlist_result(
[self.url_result(entry, 'BBCCoUk') for entry in entries],
[self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
playlist_id, playlist_title, playlist_description)
# Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
@ -978,27 +1058,43 @@ class BBCCoUkArticleIE(InfoExtractor):
class BBCCoUkPlaylistBaseIE(InfoExtractor):
def _entries(self, webpage, url, playlist_id):
single_page = 'page' in compat_urlparse.parse_qs(
compat_urlparse.urlparse(url).query)
for page_num in itertools.count(2):
for video_id in re.findall(
self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
yield self.url_result(
self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
if single_page:
return
next_page = self._search_regex(
r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
webpage, 'next page url', default=None, group='url')
if not next_page:
break
webpage = self._download_webpage(
compat_urlparse.urljoin(url, next_page), playlist_id,
'Downloading page %d' % page_num, page_num)
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
for video_id in re.findall(
self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
title, description = self._extract_title_and_description(webpage)
return self.playlist_result(entries, playlist_id, title, description)
return self.playlist_result(
self._entries(webpage, url, playlist_id),
playlist_id, title, description)
class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
IE_NAME = 'bbc.co.uk:iplayer:playlist'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
_URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
_VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
_TEST = {
_TESTS = [{
'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
'info_dict': {
'id': 'b05rcz9v',
@ -1006,7 +1102,17 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
'description': 'French thriller serial about a missing teenager.',
},
'playlist_mincount': 6,
}
'skip': 'This programme is not currently available on BBC iPlayer',
}, {
# Available for over a year unlike 30 days for most other programmes
'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
'info_dict': {
'id': 'p02tcc32',
'title': 'Bohemian Icons',
'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
},
'playlist_mincount': 10,
}]
def _extract_title_and_description(self, webpage):
title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
@ -1029,6 +1135,24 @@ class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
'description': 'French thriller serial about a missing teenager.',
},
'playlist_mincount': 7,
}, {
# multipage playlist, explicit page
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Frozen Planet - Clips - BBC One',
'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
},
'playlist_mincount': 24,
}, {
# multipage playlist, all pages
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Frozen Planet - Clips - BBC One',
'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
},
'playlist_mincount': 142,
}, {
'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
'only_matching': True,

5
youtube_dl/extractor/bet.py
View File

@ -2,7 +2,6 @@ from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from ..utils import unified_strdate
from ..compat import compat_urllib_parse_urlencode
class BetIE(MTVServicesInfoExtractor):
@ -53,9 +52,9 @@ class BetIE(MTVServicesInfoExtractor):
_FEED_URL = "http://feeds.mtvnservices.com/od/feed/bet-mrss-player"
def _get_feed_query(self, uri):
return compat_urllib_parse_urlencode({
return {
'uuid': uri,
})
}
def _extract_mgid(self, webpage):
return self._search_regex(r'data-uri="([^"]+)', webpage, 'mgid')

11
youtube_dl/extractor/bigflix.py
View File

@ -11,22 +11,13 @@ from ..compat import compat_urllib_parse_unquote
class BigflixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://www.bigflix.com/Hindi-movies/Action-movies/Singham-Returns/16537',
'md5': 'ec76aa9b1129e2e5b301a474e54fab74',
'info_dict': {
'id': '16537',
'ext': 'mp4',
'title': 'Singham Returns',
'description': 'md5:3d2ba5815f14911d5cc6a501ae0cf65d',
}
}, {
# 2 formats
'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
'info_dict': {
'id': '16070',
'ext': 'mp4',
'title': 'Madarasapatinam',
'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
'formats': 'mincount:2',
},
'params': {

160
youtube_dl/extractor/bilibili.py
View File

@ -1,22 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
import hashlib
import re
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_str,
compat_parse_qs,
compat_xml_parse_error,
)
from ..compat import compat_parse_qs
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
xpath_text,
unified_timestamp,
)
@ -25,13 +18,13 @@ class BiliBiliIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
'info_dict': {
'id': '1554319',
'ext': 'flv',
'id': '1074402',
'ext': 'mp4',
'title': '【金坷垃】金泡沫',
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
'duration': 308.067,
'duration': 308.315,
'timestamp': 1398012660,
'upload_date': '20140420',
'thumbnail': 're:^https?://.+\.jpg',
@ -42,76 +35,42 @@ class BiliBiliIE(InfoExtractor):
'url': 'http://www.bilibili.com/video/av1041170/',
'info_dict': {
'id': '1041170',
'ext': 'mp4',
'title': '【BD1080P】刀语【诸神&异域】',
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦！~',
'duration': 3382.259,
'timestamp': 1396530060,
'upload_date': '20140403',
'thumbnail': 're:^https?://.+\.jpg',
'uploader': '枫叶逝去',
'uploader_id': '520116',
},
'playlist_count': 9,
}, {
'url': 'http://www.bilibili.com/video/av4808130/',
'info_dict': {
'id': '4808130',
'ext': 'mp4',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'duration': 1493.995,
'timestamp': 1464564180,
'upload_date': '20160529',
'thumbnail': 're:^https?://.+\.jpg',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
'playlist': [{
'md5': '55cdadedf3254caaa0d5d27cf20a8f9c',
'info_dict': {
'id': '4808130_part1',
'ext': 'flv',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'timestamp': 1464564180,
'upload_date': '20160529',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
}, {
'md5': '926f9f67d0c482091872fbd8eca7ea3d',
'info_dict': {
'id': '4808130_part2',
'ext': 'flv',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'timestamp': 1464564180,
'upload_date': '20160529',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
}, {
'md5': '4b7b225b968402d7c32348c646f1fd83',
'info_dict': {
'id': '4808130_part3',
'ext': 'flv',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'timestamp': 1464564180,
'upload_date': '20160529',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
}, {
'md5': '7b795e214166501e9141139eea236e91',
'info_dict': {
'id': '4808130_part4',
'ext': 'flv',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉，又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'timestamp': 1464564180,
'upload_date': '20160529',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
}],
}, {
# Missing upload time
'url': 'http://www.bilibili.com/video/av1867637/',
'info_dict': {
'id': '2880301',
'ext': 'flv',
'id': '1867637',
'ext': 'mp4',
'title': '【HDTV】【喜剧】岳父岳母真难当 （2014）【法国票房冠军】',
'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫，老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人，结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
'duration': 5760.0,
'uploader': '黑夜为猫',
'uploader_id': '610729',
'thumbnail': 're:^https?://.+\.jpg',
},
'params': {
# Just to test metadata extraction
@ -120,86 +79,61 @@ class BiliBiliIE(InfoExtractor):
'expected_warnings': ['upload time'],
}]
# BiliBili blocks keys from time to time. The current key is extracted from
# the Android client
# TODO: find the sign algorithm used in the flash player
_APP_KEY = '86385cdc024c0f6c'
_APP_KEY = '6f90a59ac58a4123'
_BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
params = compat_parse_qs(self._search_regex(
cid = compat_parse_qs(self._search_regex(
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
webpage, 'player parameters'))
cid = params['cid'][0]
webpage, 'player parameters'))['cid'][0]
info_xml_str = self._download_webpage(
'http://interface.bilibili.com/v_cdn_play',
cid, query={'appkey': self._APP_KEY, 'cid': cid},
note='Downloading video info page')
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
err_msg = None
durls = None
info_xml = None
try:
info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
except compat_xml_parse_error:
info_json = self._parse_json(info_xml_str, video_id, fatal=False)
err_msg = (info_json or {}).get('error_text')
else:
err_msg = xpath_text(info_xml, './message')
if info_xml is not None:
durls = info_xml.findall('./durl')
if not durls:
if err_msg:
raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
else:
raise ExtractorError('No videos found!')
video_info = self._download_json(
'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page')
entries = []
for durl in durls:
size = xpath_text(durl, ['./filesize', './size'])
for idx, durl in enumerate(video_info['durl']):
formats = [{
'url': durl.find('./url').text,
'filesize': int_or_none(size),
'url': durl['url'],
'filesize': int_or_none(durl['size']),
}]
for backup_url in durl.findall('./backup_url/url'):
for backup_url in durl['backup_url']:
formats.append({
'url': backup_url.text,
'url': backup_url,
# backup URLs have lower priorities
'preference': -2 if 'hd.mp4' in backup_url.text else -3,
'preference': -2 if 'hd.mp4' in backup_url else -3,
})
self._sort_formats(formats)
entries.append({
'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
'duration': int_or_none(xpath_text(durl, './length'), 1000),
'id': '%s_part%s' % (video_id, idx),
'duration': float_or_none(durl.get('length'), 1000),
'formats': formats,
})
title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
description = self._html_search_meta('description', webpage)
datetime_str = self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
timestamp = None
if datetime_str:
timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
# TODO 'view_count' requires deobfuscating Javascript
info = {
'id': compat_str(cid),
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
'duration': float_or_none(video_info.get('timelength'), scale=1000),
}
uploader_mobj = re.search(

3
youtube_dl/extractor/biqle.py
View File

@ -24,7 +24,8 @@ class BIQLEIE(InfoExtractor):
'ext': 'mp4',
'title': 'Ребенок в шоке от автоматической мойки',
'uploader': 'Dmitry Kotov',
}
},
'skip': ' This video was marked as adult. Embedding adult videos on external sites is prohibited.',
}]
def _real_extract(self, url):

19
youtube_dl/extractor/bloomberg.py
View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -20,6 +21,18 @@ class BloombergIE(InfoExtractor):
'params': {
'format': 'best[format_id^=hds]',
},
}, {
# video ID in BPlayer(...)
'url': 'http://www.bloomberg.com/features/2016-hello-world-new-zealand/',
'info_dict': {
'id': '938c7e72-3f25-4ddb-8b85-a9be731baa74',
'ext': 'flv',
'title': 'Meet the Real-Life Tech Wizards of Middle Earth',
'description': 'Hello World, Episode 1: New Zealand’s freaky AI babies, robot exoskeletons, and a virtual you.',
},
'params': {
'format': 'best[format_id^=hds]',
},
}, {
'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
'only_matching': True,
@ -33,7 +46,11 @@ class BloombergIE(InfoExtractor):
webpage = self._download_webpage(url, name)
video_id = self._search_regex(
r'["\']bmmrId["\']\s*:\s*(["\'])(?P<url>.+?)\1',
webpage, 'id', group='url')
webpage, 'id', group='url', default=None)
if not video_id:
bplayer_data = self._parse_json(self._search_regex(
r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)
video_id = bplayer_data['id']
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(

81
youtube_dl/extractor/bravotv.py
View File

@ -1,31 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
from .adobepass import AdobePassIE
from ..utils import (
smuggle_url,
update_url_query,
int_or_none,
)
class BravoTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+videos/(?P<id>[^/?]+)'
_TEST = {
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.bravotv.com/last-chance-kitchen/season-5/videos/lck-ep-12-fishy-finale',
'md5': 'd60cdf68904e854fac669bd26cccf801',
'md5': '9086d0b7ef0ea2aabc4781d75f4e5863',
'info_dict': {
'id': 'LitrBdX64qLn',
'id': 'zHyk1_HU_mPy',
'ext': 'mp4',
'title': 'Last Chance Kitchen Returns',
'description': 'S13: Last Chance Kitchen Returns for Top Chef Season 13',
'timestamp': 1448926740,
'upload_date': '20151130',
'title': 'LCK Ep 12: Fishy Finale',
'description': 'S13/E12: Two eliminated chefs have just 12 minutes to cook up a delicious fish dish.',
'uploader': 'NBCU-BRAV',
'upload_date': '20160302',
'timestamp': 1456945320,
}
}
}, {
'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
account_pid = self._search_regex(r'"account_pid"\s*:\s*"([^"]+)"', webpage, 'account pid')
release_pid = self._search_regex(r'"release_pid"\s*:\s*"([^"]+)"', webpage, 'release pid')
return self.url_result(smuggle_url(
'http://link.theplatform.com/s/%s/%s?mbr=true&switch=progressive' % (account_pid, release_pid),
{'force_smil_url': True}), 'ThePlatform', release_pid)
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
settings = self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
display_id)
info = {}
query = {
'mbr': 'true',
}
account_pid, release_pid = [None] * 2
tve = settings.get('sharedTVE')
if tve:
query['manifest'] = 'm3u'
account_pid = 'HNK2IC'
release_pid = tve['release_pid']
if tve.get('entitlement') == 'auth':
adobe_pass = settings.get('adobePass', {})
resource = self._get_mvpd_resource(
adobe_pass.get('adobePassResourceId', 'bravo'),
tve['title'], release_pid, tve.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource)
else:
shared_playlist = settings['shared_playlist']
account_pid = shared_playlist['account_pid']
metadata = shared_playlist['video_metadata'][shared_playlist['default_clip']]
release_pid = metadata['release_pid']
info.update({
'title': metadata['title'],
'description': metadata.get('description'),
'season_number': int_or_none(metadata.get('season_num')),
'episode_number': int_or_none(metadata.get('episode_num')),
})
query['switch'] = 'progressive'
info.update({
'_type': 'url_transparent',
'id': release_pid,
'url': smuggle_url(update_url_query(
'http://link.theplatform.com/s/%s/%s' % (account_pid, release_pid),
query), {'force_smil_url': True}),
'ie_key': 'ThePlatform',
})
return info

64
youtube_dl/extractor/camdemy.py
View File

@ -1,7 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import re
from .common import InfoExtractor
@ -10,8 +9,10 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
parse_iso8601,
clean_html,
parse_duration,
str_to_int,
unified_strdate,
)
@ -26,14 +27,14 @@ class CamdemyIE(InfoExtractor):
'ext': 'mp4',
'title': 'Ch1-1 Introduction, Signals (02-23-2012)',
'thumbnail': 're:^https?://.*\.jpg$',
'description': '',
'creator': 'ss11spring',
'duration': 1591,
'upload_date': '20130114',
'timestamp': 1358154556,
'view_count': int,
}
}, {
# With non-empty description
# webpage returns "No permission or not login"
'url': 'http://www.camdemy.com/media/13885',
'md5': '4576a3bb2581f86c61044822adbd1249',
'info_dict': {
@ -41,64 +42,71 @@ class CamdemyIE(InfoExtractor):
'ext': 'mp4',
'title': 'EverCam + Camdemy QuickStart',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'md5:050b62f71ed62928f8a35f1a41e186c9',
'description': 'md5:2a9f989c2b153a2342acee579c6e7db6',
'creator': 'evercam',
'upload_date': '20140620',
'timestamp': 1403271569,
'duration': 318,
}
}, {
# External source
# External source (YouTube)
'url': 'http://www.camdemy.com/media/14842',
'md5': '50e1c3c3aa233d3d7b7daa2fa10b1cf7',
'info_dict': {
'id': '2vsYQzNIsJo',
'ext': 'mp4',
'title': 'Excel 2013 Tutorial - How to add Password Protection',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'upload_date': '20130211',
'uploader': 'Hun Kim',
'description': 'Excel 2013 Tutorial for Beginners - How to add Password Protection',
'uploader_id': 'hunkimtutorials',
'title': 'Excel 2013 Tutorial - How to add Password Protection',
}
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
webpage = self._download_webpage(url, video_id)
src_from = self._html_search_regex(
r"<div class='srcFrom'>Source: <a title='([^']+)'", page,
'external source', default=None)
r"class=['\"]srcFrom['\"][^>]*>Sources?(?:\s+from)?\s*:\s*<a[^>]+(?:href|title)=(['\"])(?P<url>(?:(?!\1).)+)\1",
webpage, 'external source', default=None, group='url')
if src_from:
return self.url_result(src_from)
oembed_obj = self._download_json(
'http://www.camdemy.com/oembed/?format=json&url=' + url, video_id)
title = oembed_obj['title']
thumb_url = oembed_obj['thumbnail_url']
video_folder = compat_urlparse.urljoin(thumb_url, 'video/')
file_list_doc = self._download_xml(
compat_urlparse.urljoin(video_folder, 'fileList.xml'),
video_id, 'Filelist XML')
video_id, 'Downloading filelist XML')
file_name = file_list_doc.find('./video/item/fileName').text
video_url = compat_urlparse.urljoin(video_folder, file_name)
timestamp = parse_iso8601(self._html_search_regex(
r"<div class='title'>Posted\s*:</div>\s*<div class='value'>([^<>]+)<",
page, 'creation time', fatal=False),
delimiter=' ', timezone=datetime.timedelta(hours=8))
view_count = str_to_int(self._html_search_regex(
r"<div class='title'>Views\s*:</div>\s*<div class='value'>([^<>]+)<",
page, 'view count', fatal=False))
# Some URLs return "No permission or not login" in a webpage despite being
# freely available via oembed JSON URL (e.g. http://www.camdemy.com/media/13885)
upload_date = unified_strdate(self._search_regex(
r'>published on ([^<]+)<', webpage,
'upload date', default=None))
view_count = str_to_int(self._search_regex(
r'role=["\']viewCnt["\'][^>]*>([\d,.]+) views',
webpage, 'view count', default=None))
description = self._html_search_meta(
'description', webpage, default=None) or clean_html(
oembed_obj.get('description'))
return {
'id': video_id,
'url': video_url,
'title': oembed_obj['title'],
'title': title,
'thumbnail': thumb_url,
'description': self._html_search_meta('description', page),
'creator': oembed_obj['author_name'],
'duration': oembed_obj['duration'],
'timestamp': timestamp,
'description': description,
'creator': oembed_obj.get('author_name'),
'duration': parse_duration(oembed_obj.get('duration')),
'upload_date': upload_date,
'view_count': view_count,
}

36
youtube_dl/extractor/cartoonnetwork.py Normal file
View File

@ -0,0 +1,36 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .turner import TurnerBaseIE
class CartoonNetworkIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
_TEST = {
'url': 'http://www.cartoonnetwork.com/video/teen-titans-go/starfire-the-cat-lady-clip.html',
'info_dict': {
'id': '8a250ab04ed07e6c014ef3f1e2f9016c',
'ext': 'mp4',
'title': 'Starfire the Cat Lady',
'description': 'Robin decides to become a cat so that Starfire will finally love him.',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
id_type, video_id = re.search(r"_cnglobal\.cvp(Video|Title)Id\s*=\s*'([^']+)';", webpage).groups()
query = ('id' if id_type == 'Video' else 'titleId') + '=' + video_id
return self._extract_cvp_info(
'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
'secure': {
'media_src': 'http://apple-secure.cdn.turner.com/toon/big',
'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
},
})

204
youtube_dl/extractor/cbc.py
View File

@ -4,13 +4,24 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
js_to_json,
smuggle_url,
try_get,
xpath_text,
xpath_element,
xpath_with_ns,
find_xpath_attr,
parse_iso8601,
parse_age_limit,
int_or_none,
ExtractorError,
)
class CBCIE(InfoExtractor):
IE_NAME = 'cbc.ca'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# with mediaId
@ -25,8 +36,22 @@ class CBCIE(InfoExtractor):
'upload_date': '20160203',
'uploader': 'CBCC-NEW',
},
'skip': 'Geo-restricted to Canada',
}, {
# with clipId
# with clipId, feed available via tpfeed.cbc.ca and feed.theplatform.com
'url': 'http://www.cbc.ca/22minutes/videos/22-minutes-update/22-minutes-update-episode-4',
'md5': '162adfa070274b144f4fdc3c3b8207db',
'info_dict': {
'id': '2414435309',
'ext': 'mp4',
'title': '22 Minutes Update: What Not To Wear Quebec',
'description': "This week's latest Canadian top political story is What Not To Wear Quebec.",
'upload_date': '20131025',
'uploader': 'CBCC-NEW',
'timestamp': 1382717907,
},
}, {
# with clipId, feed only available via tpfeed.cbc.ca
'url': 'http://www.cbc.ca/archives/entry/1978-robin-williams-freestyles-on-90-minutes-live',
'md5': '0274a90b51a9b4971fe005c63f592f12',
'info_dict': {
@ -64,6 +89,7 @@ class CBCIE(InfoExtractor):
'uploader': 'CBCC-NEW',
},
}],
'skip': 'Geo-restricted to Canada',
}]
@classmethod
@ -81,9 +107,15 @@ class CBCIE(InfoExtractor):
media_id = player_info.get('mediaId')
if not media_id:
clip_id = player_info['clipId']
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
feed = self._download_json(
'http://tpfeed.cbc.ca/f/ExhSPC/vms_5akSXx4Ng_Zn?byCustomValue={:mpsReleases}{%s}' % clip_id,
clip_id, fatal=False)
if feed:
media_id = try_get(feed, lambda x: x['entries'][0]['guid'], compat_str)
if not media_id:
media_id = self._download_json(
'http://feed.theplatform.com/f/h9dtGB/punlNGjMlc1F?fields=id&byContent=byReleases%3DbyId%253D' + clip_id,
clip_id)['entries'][0]['id'].split('/')[-1]
return self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
else:
entries = [self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id) for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)]
@ -91,6 +123,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
@ -104,6 +137,7 @@ class CBCPlayerIE(InfoExtractor):
'upload_date': '20160210',
'uploader': 'CBCC-NEW',
},
'skip': 'Geo-restricted to Canada',
}, {
# Redirected from http://www.cbc.ca/player/AudioMobile/All%20in%20a%20Weekend%20Montreal/ID/2657632011/
'url': 'http://www.cbc.ca/player/play/2657631896',
@ -143,3 +177,165 @@ class CBCPlayerIE(InfoExtractor):
}),
'id': video_id,
}
class CBCWatchBaseIE(InfoExtractor):
_device_id = None
_device_token = None
_API_BASE_URL = 'https://api-cbc.cloud.clearleap.com/cloffice/client/'
_NS_MAP = {
'media': 'http://search.yahoo.com/mrss/',
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
result = self._download_xml(url, video_id, headers={
'X-Clearleap-DeviceId': self._device_id,
'X-Clearleap-DeviceToken': self._device_token,
})
error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage')
if error_message:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message))
return result
def _real_initialize(self):
if not self._device_id or not self._device_token:
device = self._downloader.cache.load('cbcwatch', 'device') or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if not self._device_id or not self._device_token:
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
'cbcwatch', 'device', {
'id': self._device_id,
'token': self._device_token,
})
def _parse_rss_feed(self, rss):
channel = xpath_element(rss, 'channel', fatal=True)
def _add_ns(path):
return xpath_with_ns(path, self._NS_MAP)
entries = []
for item in channel.findall('item'):
guid = xpath_text(item, 'guid', fatal=True)
title = xpath_text(item, 'title', fatal=True)
media_group = xpath_element(item, _add_ns('media:group'), fatal=True)
content = xpath_element(media_group, _add_ns('media:content'), fatal=True)
content_url = content.attrib['url']
thumbnails = []
for thumbnail in media_group.findall(_add_ns('media:thumbnail')):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'id': thumbnail.get('profile'),
'url': thumbnail_url,
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
timestamp = None
release_date = find_xpath_attr(
item, _add_ns('media:credit'), 'role', 'releaseDate')
if release_date is not None:
timestamp = parse_iso8601(release_date.text)
entries.append({
'_type': 'url_transparent',
'url': content_url,
'id': guid,
'title': title,
'description': xpath_text(item, 'description'),
'timestamp': timestamp,
'duration': int_or_none(content.get('duration')),
'age_limit': parse_age_limit(xpath_text(item, _add_ns('media:rating'))),
'episode': xpath_text(item, _add_ns('clearleap:episode')),
'episode_number': int_or_none(xpath_text(item, _add_ns('clearleap:episodeInSeason'))),
'series': xpath_text(item, _add_ns('clearleap:series')),
'season_number': int_or_none(xpath_text(item, _add_ns('clearleap:season'))),
'thumbnails': thumbnails,
'ie_key': 'CBCWatchVideo',
})
return self.playlist_result(
entries, xpath_text(channel, 'guid'),
xpath_text(channel, 'title'),
xpath_text(channel, 'description'))
class CBCWatchVideoIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch:video'
_VALID_URL = r'https?://api-cbc\.cloud\.clearleap\.com/cloffice/client/web/play/?\?.*?\bcontentId=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
def _real_extract(self, url):
video_id = self._match_id(url)
result = self._call_api(url, video_id)
m3u8_url = xpath_text(result, 'url', fatal=True)
formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
if len(formats) < 2:
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
# Despite metadata in m3u8 all video+audio formats are
# actually video-only (no audio)
for f in formats:
if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
f['acodec'] = 'none'
self._sort_formats(formats)
info = {
'id': video_id,
'title': video_id,
'formats': formats,
}
rss = xpath_element(result, 'rss')
if rss:
info.update(self._parse_rss_feed(rss)['entries'][0])
del info['url']
del info['_type']
del info['ie_key']
return info
class CBCWatchIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch'
_VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
_TESTS = [{
'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
'info_dict': {
'id': '38e815a-009e3ab12e4',
'ext': 'mp4',
'title': 'Customer (Dis)Service',
'description': 'md5:8bdd6913a0fe03d4b2a17ebe169c7c87',
'upload_date': '20160219',
'timestamp': 1455840000,
},
'params': {
# m3u8 download
'skip_download': True,
'format': 'bestvideo',
},
'skip': 'Geo-restricted to Canada',
}, {
'url': 'http://watch.cbc.ca/arthur/all/1ed4b385-cd84-49cf-95f0-80f004680057',
'info_dict': {
'id': '1ed4b385-cd84-49cf-95f0-80f004680057',
'title': 'Arthur',
'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
},
'playlist_mincount': 30,
'skip': 'Geo-restricted to Canada',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
rss = self._call_api('web/browse/' + video_id, video_id)
return self._parse_rss_feed(rss)

47
youtube_dl/extractor/cbs.py
View File

@ -4,6 +4,7 @@ from .theplatform import ThePlatformFeedIE
from ..utils import (
int_or_none,
find_xpath_attr,
ExtractorError,
)
@ -17,19 +18,6 @@ class CBSBaseIE(ThePlatformFeedIE):
}]
} if closed_caption_e is not None and closed_caption_e.attrib.get('value') else []
def _extract_video_info(self, filter_query, video_id):
return self._extract_feed_info(
'dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id, lambda entry: {
'series': entry.get('cbs$SeriesTitle'),
'season_number': int_or_none(entry.get('cbs$SeasonNumber')),
'episode': entry.get('cbs$EpisodeTitle'),
'episode_number': int_or_none(entry.get('cbs$EpisodeNumber')),
}, {
'StreamPack': {
'manifest': 'm3u',
}
})
class CBSIE(CBSBaseIE):
_VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
@ -38,7 +26,6 @@ class CBSIE(CBSBaseIE):
'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
'info_dict': {
'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
'display_id': 'connect-chat-feat-garth-brooks',
'ext': 'mp4',
'title': 'Connect Chat feat. Garth Brooks',
'description': 'Connect with country music singer Garth Brooks, as he chats with fans on Wednesday November 27, 2013. Be sure to tune in to Garth Brooks: Live from Las Vegas, Friday November 29, at 9/8c on CBS!',
@ -47,7 +34,10 @@ class CBSIE(CBSBaseIE):
'upload_date': '20131127',
'uploader': 'CBSI-NEW',
},
'expected_warnings': ['Failed to download m3u8 information'],
'params': {
# m3u8 download
'skip_download': True,
},
'_skip': 'Blocked outside the US',
}, {
'url': 'http://colbertlateshow.com/video/8GmB0oY0McANFvp2aEffk9jZZZ2YyXxy/the-colbeard/',
@ -56,8 +46,31 @@ class CBSIE(CBSBaseIE):
'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
'only_matching': True,
}]
TP_RELEASE_URL_TEMPLATE = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true'
def _extract_video_info(self, guid):
path = 'dJ5BDC/media/guid/2198311517/' + guid
smil_url = 'http://link.theplatform.com/s/%s?mbr=true' % path
formats, subtitles = self._extract_theplatform_smil(smil_url + '&manifest=m3u', guid)
for r in ('OnceURL&formats=M3U', 'HLS&formats=M3U', 'RTMP', 'WIFI', '3G'):
try:
tp_formats, _ = self._extract_theplatform_smil(smil_url + '&assetTypes=' + r, guid, 'Downloading %s SMIL data' % r.split('&')[0])
formats.extend(tp_formats)
except ExtractorError:
continue
self._sort_formats(formats)
metadata = self._download_theplatform_metadata(path, guid)
info = self._parse_theplatform_metadata(metadata)
info.update({
'id': guid,
'formats': formats,
'subtitles': subtitles,
'series': metadata.get('cbs$SeriesTitle'),
'season_number': int_or_none(metadata.get('cbs$SeasonNumber')),
'episode': metadata.get('cbs$EpisodeTitle'),
'episode_number': int_or_none(metadata.get('cbs$EpisodeNumber')),
})
return info
def _real_extract(self, url):
content_id = self._match_id(url)
return self._extract_video_info('byGuid=%s' % content_id, content_id)
return self._extract_video_info(content_id)

27
youtube_dl/extractor/cbslocal.py
View File

@ -1,12 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
from .anvato import AnvatoIE
from .sendtonews import SendtoNewsIE
from ..compat import compat_urlparse
from ..utils import unified_timestamp
class CBSLocalIE(AnvatoIE):
@ -43,13 +41,8 @@ class CBSLocalIE(AnvatoIE):
'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
'info_dict': {
'id': 'GxfCe0Zo7D-175909-5588',
'ext': 'mp4',
'title': 'Recap: CLE 15, CIN 6',
'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
'upload_date': '20160516',
'timestamp': 1463433840,
'duration': 49,
},
'playlist_count': 9,
'params': {
# m3u8 download
'skip_download': True,
@ -62,19 +55,15 @@ class CBSLocalIE(AnvatoIE):
sendtonews_url = SendtoNewsIE._extract_url(webpage)
if sendtonews_url:
info_dict = {
'_type': 'url_transparent',
'url': compat_urlparse.urljoin(url, sendtonews_url),
}
else:
info_dict = self._extract_anvato_videos(webpage, display_id)
return self.url_result(
compat_urlparse.urljoin(url, sendtonews_url),
ie=SendtoNewsIE.ie_key())
info_dict = self._extract_anvato_videos(webpage, display_id)
time_str = self._html_search_regex(
r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)
timestamp = None
if time_str:
timestamp = calendar.timegm(datetime.datetime.strptime(
time_str, '%b %d, %Y %I:%M %p').timetuple())
timestamp = unified_timestamp(time_str)
info_dict.update({
'display_id': display_id,

12
youtube_dl/extractor/cbsnews.py
View File

@ -2,13 +2,13 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .cbs import CBSBaseIE
from .cbs import CBSIE
from ..utils import (
parse_duration,
)
class CBSNewsIE(CBSBaseIE):
class CBSNewsIE(CBSIE):
IE_DESC = 'CBS News'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
@ -26,6 +26,7 @@ class CBSNewsIE(CBSBaseIE):
# rtmp download
'skip_download': True,
},
'skip': 'Subscribers only',
},
{
'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
@ -34,7 +35,8 @@ class CBSNewsIE(CBSBaseIE):
'ext': 'mp4',
'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
'upload_date': '19700101',
'upload_date': '20140404',
'timestamp': 1396650660,
'uploader': 'CBSI-NEW',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 205,
@ -62,13 +64,14 @@ class CBSNewsIE(CBSBaseIE):
item = video_info['item'] if 'item' in video_info else video_info
guid = item['mpxRefId']
return self._extract_video_info('byGuid=%s' % guid, guid)
return self._extract_video_info(guid)
class CBSNewsLiveVideoIE(InfoExtractor):
IE_DESC = 'CBS News Live Videos'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
# Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
_TEST = {
'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
'info_dict': {
@ -77,6 +80,7 @@ class CBSNewsLiveVideoIE(InfoExtractor):
'title': 'Clinton, Sanders Prepare To Face Off In NH',
'duration': 334,
},
'skip': 'Video gone',
}
def _real_extract(self, url):

3
youtube_dl/extractor/cbssports.py
View File

@ -23,6 +23,9 @@ class CBSSportsIE(CBSBaseIE):
}
}]
def _extract_video_info(self, filter_query, video_id):
return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video_info('byId=%s' % video_id, video_id)

51
youtube_dl/extractor/charlierose.py Normal file
View File

@ -0,0 +1,51 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import remove_end
class CharlieRoseIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?charlierose\.com/video(?:s|/player)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://charlierose.com/videos/27996',
'md5': 'fda41d49e67d4ce7c2411fd2c4702e09',
'info_dict': {
'id': '27996',
'ext': 'mp4',
'title': 'Remembering Zaha Hadid',
'thumbnail': 're:^https?://.*\.jpg\?\d+',
'description': 'We revisit past conversations with Zaha Hadid, in memory of the world renowned Iraqi architect.',
'subtitles': {
'en': [{
'ext': 'vtt',
}],
},
},
}, {
'url': 'https://charlierose.com/videos/27996',
'only_matching': True,
}]
_PLAYER_BASE = 'https://charlierose.com/video/player/%s'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(self._PLAYER_BASE % video_id, video_id)
title = remove_end(self._og_search_title(webpage), ' - Charlie Rose')
info_dict = self._parse_html5_media_entries(
self._PLAYER_BASE % video_id, webpage, video_id,
m3u8_entry_protocol='m3u8_native')[0]
self._sort_formats(info_dict['formats'])
self._remove_duplicate_formats(info_dict['formats'])
info_dict.update({
'id': video_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
})
return info_dict

3
youtube_dl/extractor/chaturbate.py
View File

@ -17,7 +17,8 @@ class ChaturbateIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
'skip': 'Room is offline',
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,

54
youtube_dl/extractor/chirbit.py
View File

@ -1,30 +1,33 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..utils import (
parse_duration,
int_or_none,
)
from ..utils import parse_duration
class ChirbitIE(InfoExtractor):
IE_NAME = 'chirbit'
_VALID_URL = r'https?://(?:www\.)?chirb\.it/(?:(?:wp|pl)/|fb_chirbit_player\.swf\?key=)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'http://chirb.it/PrIPv5',
'md5': '9847b0dad6ac3e074568bf2cfb197de8',
'url': 'http://chirb.it/be2abG',
'info_dict': {
'id': 'PrIPv5',
'id': 'be2abG',
'ext': 'mp3',
'title': 'Фасадстрой',
'duration': 52,
'view_count': int,
'comment_count': int,
'title': 'md5:f542ea253f5255240be4da375c6a5d7e',
'description': 'md5:f24a4e22a71763e32da5fed59e47c770',
'duration': 306,
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://chirb.it/fb_chirbit_player.swf?key=PrIPv5',
'only_matching': True,
}, {
'url': 'https://chirb.it/wp/MN58c2',
'only_matching': True,
}]
def _real_extract(self, url):
@ -33,27 +36,30 @@ class ChirbitIE(InfoExtractor):
webpage = self._download_webpage(
'http://chirb.it/%s' % audio_id, audio_id)
audio_url = self._search_regex(
r'"setFile"\s*,\s*"([^"]+)"', webpage, 'audio url')
data_fd = self._search_regex(
r'data-fd=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'data fd', group='url')
# Reverse engineered from https://chirb.it/js/chirbit.player.js (look
# for soundURL)
audio_url = base64.b64decode(
data_fd[::-1].encode('ascii')).decode('utf-8')
title = self._search_regex(
r'itemprop="name">([^<]+)', webpage, 'title')
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'itemprop="playCount"\s*>(\d+)', webpage,
'listen count', fatal=False))
comment_count = int_or_none(self._search_regex(
r'>(\d+) Comments?:', webpage,
'comment count', fatal=False))
r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')
description = self._search_regex(
r'<h3>Description</h3>\s*<pre[^>]*>([^<]+)</pre>',
webpage, 'description', default=None)
duration = parse_duration(self._search_regex(
r'class=["\']c-length["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
return {
'id': audio_id,
'url': audio_url,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'comment_count': comment_count,
}

17
youtube_dl/extractor/cliphunter.py
View File

@ -23,7 +23,7 @@ class CliphunterIE(InfoExtractor):
(?P<id>[0-9]+)/
(?P<seo>.+?)(?:$|[#\?])
'''
_TEST = {
_TESTS = [{
'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
'info_dict': {
@ -32,8 +32,19 @@ class CliphunterIE(InfoExtractor):
'title': 'Fun Jynx Maze solo',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
}
}
},
'skip': 'Video gone',
}, {
'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
'info_dict': {
'id': '2019449',
'ext': 'mp4',
'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
'thumbnail': 're:^https?://.*\.jpg$',
'age_limit': 18,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)

48
youtube_dl/extractor/cloudy.py
View File

@ -6,7 +6,6 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlencode,
compat_HTTPError,
)
from ..utils import (
@ -17,37 +16,26 @@ from ..utils import (
class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec and videoraj.ch'
_IE_DESC = 'cloudy.ec'
_VALID_URL = r'''(?x)
https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/
https?://(?:www\.)?cloudy\.ec/
(?:v/|embed\.php\?id=)
(?P<id>[A-Za-z0-9]+)
'''
_EMBED_URL = 'http://www.%s/embed.php?id=%s'
_API_URL = 'http://www.%s/api/player.api.php?%s'
_EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
_API_URL = 'http://www.cloudy.ec/api/player.api.php'
_MAX_TRIES = 2
_TESTS = [
{
'url': 'https://www.cloudy.ec/v/af511e2527aac',
'md5': '5cb253ace826a42f35b4740539bedf07',
'info_dict': {
'id': 'af511e2527aac',
'ext': 'flv',
'title': 'Funny Cats and Animals Compilation june 2013',
}
},
{
'url': 'http://www.videoraj.to/v/47f399fd8bb60',
'md5': '7d0f8799d91efd4eda26587421c3c3b0',
'info_dict': {
'id': '47f399fd8bb60',
'ext': 'flv',
'title': 'Burning a New iPhone 5 with Gasoline - Will it Survive?',
}
_TEST = {
'url': 'https://www.cloudy.ec/v/af511e2527aac',
'md5': '5cb253ace826a42f35b4740539bedf07',
'info_dict': {
'id': 'af511e2527aac',
'ext': 'flv',
'title': 'Funny Cats and Animals Compilation june 2013',
}
]
}
def _extract_video(self, video_host, video_id, file_key, error_url=None, try_num=0):
def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
if try_num > self._MAX_TRIES - 1:
raise ExtractorError('Unable to extract video URL', expected=True)
@ -64,9 +52,8 @@ class CloudyIE(InfoExtractor):
'errorUrl': error_url,
})
data_url = self._API_URL % (video_host, compat_urllib_parse_urlencode(form))
player_data = self._download_webpage(
data_url, video_id, 'Downloading player data')
self._API_URL, video_id, 'Downloading player data', query=form)
data = compat_parse_qs(player_data)
try_num += 1
@ -88,7 +75,7 @@ class CloudyIE(InfoExtractor):
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
self.report_warning('Invalid video URL, requesting another', video_id)
return self._extract_video(video_host, video_id, file_key, video_url, try_num)
return self._extract_video(video_id, file_key, video_url, try_num)
return {
'id': video_id,
@ -98,14 +85,13 @@ class CloudyIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_host = mobj.group('host')
video_id = mobj.group('id')
url = self._EMBED_URL % (video_host, video_id)
url = self._EMBED_URL % video_id
webpage = self._download_webpage(url, video_id)
file_key = self._search_regex(
[r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
webpage, 'file_key')
return self._extract_video(video_host, video_id, file_key)
return self._extract_video(video_id, file_key)

22
youtube_dl/extractor/cmt.py
View File

@ -1,5 +1,7 @@
from __future__ import unicode_literals
from .mtv import MTVIE
from ..utils import ExtractorError
class CMTIE(MTVIE):
@ -16,7 +18,27 @@ class CMTIE(MTVIE):
'title': 'Garth Brooks - "The Call (featuring Trisha Yearwood)"',
'description': 'Blame It All On My Roots',
},
'skip': 'Video not available',
}, {
'url': 'http://www.cmt.com/videos/misc/1504699/still-the-king-ep-109-in-3-minutes.jhtml#id=1739908',
'md5': 'e61a801ca4a183a466c08bd98dccbb1c',
'info_dict': {
'id': '1504699',
'ext': 'mp4',
'title': 'Still The King Ep. 109 in 3 Minutes',
'description': 'Relive or catch up with Still The King by watching this recap of season 1, episode 9. New episodes Sundays 9/8c.',
'timestamp': 1469421000.0,
'upload_date': '20160725',
},
}, {
'url': 'http://www.cmt.com/shows/party-down-south/party-down-south-ep-407-gone-girl/1738172/playlist/#id=1738172',
'only_matching': True,
}]
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
if 'error_not_available.swf' in rtmp_video_url:
raise ExtractorError(
'%s said: video is not available' % cls.IE_NAME, expected=True)
return super(CMTIE, cls)._transform_rtmp_url(rtmp_video_url)

132
youtube_dl/extractor/cnn.py
View File

@ -3,15 +3,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
url_basename,
)
from .turner import TurnerBaseIE
from ..utils import url_basename
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
class CNNIE(TurnerBaseIE):
_VALID_URL = r'''(?x)https?://(?:(?P<sub_domain>edition|www|money)\.)?cnn\.com/(?:video/(?:data/.+?|\?)/)?videos?/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))'''
_TESTS = [{
@ -25,6 +22,7 @@ class CNNIE(InfoExtractor):
'duration': 135,
'upload_date': '20130609',
},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29',
'md5': 'b5cc60c60a3477d185af8f19a2a26f4e',
@ -34,7 +32,8 @@ class CNNIE(InfoExtractor):
'title': "Student's epic speech stuns new freshmen",
'description': "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
'upload_date': '20130821',
}
},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
'md5': 'f14d02ebd264df951feb2400e2c25a1b',
@ -44,80 +43,61 @@ class CNNIE(InfoExtractor):
'title': 'Nashville Ep. 1: Hand crafted skateboards',
'description': 'md5:e7223a503315c9f150acac52e76de086',
'upload_date': '20141222',
}
},
'expected_warnings': ['Failed to download m3u8 information'],
}, {
'url': 'http://money.cnn.com/video/news/2016/08/19/netflix-stunning-stats.cnnmoney/index.html',
'md5': '52a515dc1b0f001cd82e4ceda32be9d1',
'info_dict': {
'id': '/video/news/2016/08/19/netflix-stunning-stats.cnnmoney',
'ext': 'mp4',
'title': '5 stunning stats about Netflix',
'description': 'Did you know that Netflix has more than 80 million members? Here are five facts about the online video distributor that you probably didn\'t know.',
'upload_date': '20160819',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
'only_matching': True,
}, {
'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
'only_matching': True,
}, {
'url': 'http://edition.cnn.com/videos/arts/2016/04/21/olympic-games-cultural-a-z-brazil.cnn',
'only_matching': True,
}]
_CONFIG = {
# http://edition.cnn.com/.element/apps/cvp/3.0/cfg/spider/cnn/expansion/config.xml
'edition': {
'data_src': 'http://edition.cnn.com/video/data/3.0/video/%s/index.xml',
'media_src': 'http://pmd.cdn.turner.com/cnn/big',
},
# http://money.cnn.com/.element/apps/cvp2/cfg/config.xml
'money': {
'data_src': 'http://money.cnn.com/video/data/4.0/video/%s.xml',
'media_src': 'http://ht3.cdn.turner.com/money/big',
},
}
def _extract_timestamp(self, video_data):
# TODO: fix timestamp extraction
return None
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
path = mobj.group('path')
page_title = mobj.group('title')
info_url = 'http://edition.cnn.com/video/data/3.0/%s/index.xml' % path
info = self._download_xml(info_url, page_title)
formats = []
rex = re.compile(r'''(?x)
(?P<width>[0-9]+)x(?P<height>[0-9]+)
(?:_(?P<bitrate>[0-9]+)k)?
''')
for f in info.findall('files/file'):
video_url = 'http://ht.cdn.turner.com/cnn/big%s' % (f.text.strip())
fdct = {
'format_id': f.attrib['bitrate'],
'url': video_url,
}
mf = rex.match(f.attrib['bitrate'])
if mf:
fdct['width'] = int(mf.group('width'))
fdct['height'] = int(mf.group('height'))
fdct['tbr'] = int_or_none(mf.group('bitrate'))
else:
mf = rex.search(f.text)
if mf:
fdct['width'] = int(mf.group('width'))
fdct['height'] = int(mf.group('height'))
fdct['tbr'] = int_or_none(mf.group('bitrate'))
else:
mi = re.match(r'ios_(audio|[0-9]+)$', f.attrib['bitrate'])
if mi:
if mi.group(1) == 'audio':
fdct['vcodec'] = 'none'
fdct['ext'] = 'm4a'
else:
fdct['tbr'] = int(mi.group(1))
formats.append(fdct)
self._sort_formats(formats)
thumbnails = [{
'height': int(t.attrib['height']),
'width': int(t.attrib['width']),
'url': t.text,
} for t in info.findall('images/image')]
metas_el = info.find('metas')
upload_date = (
metas_el.attrib.get('version') if metas_el is not None else None)
duration_el = info.find('length')
duration = parse_duration(duration_el.text)
return {
'id': info.attrib['id'],
'title': info.find('headline').text,
'formats': formats,
'thumbnails': thumbnails,
'description': info.find('description').text,
'duration': duration,
'upload_date': upload_date,
}
sub_domain, path, page_title = re.match(self._VALID_URL, url).groups()
if sub_domain not in ('money', 'edition'):
sub_domain = 'edition'
config = self._CONFIG[sub_domain]
return self._extract_cvp_info(
config['data_src'] % path, page_title, {
'default': {
'media_src': config['media_src'],
}
})
class CNNBlogsIE(InfoExtractor):
@ -132,6 +112,7 @@ class CNNBlogsIE(InfoExtractor):
'description': 'Glenn Greenwald responds to comments made this week on Capitol Hill that journalists could be criminal accessories.',
'upload_date': '20140209',
},
'expected_warnings': ['Failed to download m3u8 information'],
'add_ie': ['CNN'],
}
@ -146,7 +127,7 @@ class CNNBlogsIE(InfoExtractor):
class CNNArticleIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
_VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!videos?/)'
_TEST = {
'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
'md5': '689034c2a3d9c6dc4aa72d65a81efd01',
@ -154,9 +135,10 @@ class CNNArticleIE(InfoExtractor):
'id': 'bestoftv/2014/12/21/ip-north-korea-obama.cnn',
'ext': 'mp4',
'title': 'Obama: Cyberattack not an act of war',
'description': 'md5:51ce6750450603795cad0cdfbd7d05c5',
'description': 'md5:0a802a40d2376f60e6b04c8d5bcebc4b',
'upload_date': '20141221',
},
'expected_warnings': ['Failed to download m3u8 information'],
'add_ie': ['CNN'],
}

313
youtube_dl/extractor/comedycentral.py
View File

@ -1,17 +1,7 @@
from __future__ import unicode_literals
import re
from .mtv import MTVServicesInfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
float_or_none,
unified_strdate,
)
from .common import InfoExtractor
class ComedyCentralIE(MTVServicesInfoExtractor):
@ -26,8 +16,10 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
'info_dict': {
'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
'ext': 'mp4',
'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
'description': 'After a certain point, breastfeeding becomes c**kblocking.',
'timestamp': 1376798400,
'upload_date': '20130818',
},
}, {
'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
@ -35,241 +27,92 @@ class ComedyCentralIE(MTVServicesInfoExtractor):
}]
class ComedyCentralShowsIE(MTVServicesInfoExtractor):
IE_DESC = 'The Daily Show / The Colbert Report'
# urls can be abbreviations like :thedailyshow
# urls for episodes like:
# or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
# or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
# or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport|tosh)\.(?:cc\.)?com/
((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
(?P<clip>
(?:(?:guests/[^/]+|videos|video-(?:clips|playlists)|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
|(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
(?P<interview>
extended-interviews/(?P<interID>[0-9a-z]+)/
(?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
(?:/[^/?#]?|[?#]|$))))
'''
class ToshIE(MTVServicesInfoExtractor):
IE_DESC = 'Tosh.0'
_VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
_FEED_URL = 'http://tosh.cc.com/feeds/mrss'
_TESTS = [{
'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
'info_dict': {
'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
'ext': 'mp4',
'upload_date': '20121213',
'description': 'Kristen Stewart learns to let loose in "On the Road."',
'uploader': 'thedailyshow',
'title': 'thedailyshow kristen-stewart part 1',
}
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
'info_dict': {
'id': 'sarah-chayes-extended-interview',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'title': 'thedailyshow Sarah Chayes Extended Interview',
},
'playlist': [
{
'info_dict': {
'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
'ext': 'mp4',
'upload_date': '20150129',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'uploader': 'thedailyshow',
'title': 'thedailyshow sarah-chayes-extended-interview part 1',
},
},
{
'info_dict': {
'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
'ext': 'mp4',
'upload_date': '20150129',
'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
'uploader': 'thedailyshow',
'title': 'thedailyshow sarah-chayes-extended-interview part 2',
},
},
],
'params': {
'skip_download': True,
},
}, {
'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
'only_matching': True,
}, {
'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
'only_matching': True,
}, {
'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
'only_matching': True,
}, {
'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
'only_matching': True,
}, {
'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
'only_matching': True,
}, {
'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
'info_dict': {
'description': 'Tosh asked fans to share their summer plans.',
'title': 'Twitter Users Share Summer Plans',
},
'playlist': [{
'md5': 'f269e88114c1805bb6d7653fecea9e06',
'info_dict': {
'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
'ext': 'mp4',
'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
'description': 'Tosh asked fans to share their summer plans.',
'thumbnail': 're:^https?://.*\.jpg',
# It's really reported to be published on year 2077
'upload_date': '20770610',
'timestamp': 3390510600,
'subtitles': {
'en': 'mincount:3',
},
},
}]
}, {
'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
'only_matching': True,
}]
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
return new_urls
_video_extensions = {
'3500': 'mp4',
'2200': 'mp4',
'1700': 'mp4',
'1200': 'mp4',
'750': 'mp4',
'400': 'mp4',
}
_video_dimensions = {
'3500': (1280, 720),
'2200': (960, 540),
'1700': (768, 432),
'1200': (640, 360),
'750': (512, 288),
'400': (384, 216),
}
class ComedyCentralTVIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
'info_dict': {
'id': 'local_playlist-f99b626bdfe13568579a',
'ext': 'flv',
'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
'only_matching': True,
}, {
'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = self._match_id(url)
if mobj.group('shortname'):
return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')
webpage = self._download_webpage(url, video_id)
if mobj.group('clip'):
if mobj.group('videotitle'):
epTitle = mobj.group('videotitle')
elif mobj.group('showname') == 'thedailyshow':
epTitle = mobj.group('tdstitle')
else:
epTitle = mobj.group('cntitle')
dlNewest = False
elif mobj.group('interview'):
epTitle = mobj.group('interview_title')
dlNewest = False
else:
dlNewest = not mobj.group('episode')
if dlNewest:
epTitle = mobj.group('showname')
else:
epTitle = mobj.group('episode')
show_name = mobj.group('showname')
mrss_url = self._search_regex(
r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'mrss url', group='url')
webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
if dlNewest:
url = htmlHandle.geturl()
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
if mobj is None:
raise ExtractorError('Invalid redirected URL: ' + url)
if mobj.group('episode') == '':
raise ExtractorError('Redirected URL is still not specific: ' + url)
epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
return self._get_videos_info_from_url(mrss_url, video_id)
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference
# and then add the URL prefix manually.
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
if len(altMovieParams) == 0:
raise ExtractorError('unable to find Flash URL in webpage ' + url)
else:
mMovieParams = [('http://media.mtvnservices.com/' + altMovieParams[0], altMovieParams[0])]
class ComedyCentralShortnameIE(InfoExtractor):
_VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
_TESTS = [{
'url': ':tds',
'only_matching': True,
}, {
'url': ':thedailyshow',
'only_matching': True,
}]
uri = mMovieParams[0][1]
# Correct cc.com in uri
uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse_urlencode({'uri': uri}))
idoc = self._download_xml(
index_url, epTitle,
'Downloading show index', 'Unable to download episode index')
title = idoc.find('./channel/title').text
description = idoc.find('./channel/description').text
entries = []
item_els = idoc.findall('.//item')
for part_num, itemEl in enumerate(item_els):
upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
duration = float_or_none(content.attrib.get('duration'))
mediagen_url = content.attrib['url']
guid = itemEl.find('./guid').text.rpartition(':')[-1]
cdoc = self._download_xml(
mediagen_url, epTitle,
'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
turls = []
for rendition in cdoc.findall('.//rendition'):
finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
turls.append(finfo)
formats = []
for format, rtmp_video_url in turls:
w, h = self._video_dimensions.get(format, (None, None))
formats.append({
'format_id': 'vhttp-%s' % format,
'url': self._transform_rtmp_url(rtmp_video_url),
'ext': self._video_extensions.get(format, 'mp4'),
'height': h,
'width': w,
})
formats.append({
'format_id': 'rtmp-%s' % format,
'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
'ext': self._video_extensions.get(format, 'mp4'),
'height': h,
'width': w,
})
self._sort_formats(formats)
subtitles = self._extract_subtitles(cdoc, guid)
virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
entries.append({
'id': guid,
'title': virtual_id,
'formats': formats,
'uploader': show_name,
'upload_date': upload_date,
'duration': duration,
'thumbnail': thumbnail,
'description': description,
'subtitles': subtitles,
})
return {
'_type': 'playlist',
'id': epTitle,
'entries': entries,
'title': show_name + ' ' + title,
'description': description,
def _real_extract(self, url):
video_id = self._match_id(url)
shortcut_map = {
'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
}
return self.url_result(shortcut_map[video_id])

281
youtube_dl/extractor/common.py
View File

@ -662,6 +662,24 @@ class InfoExtractor(object):
else:
return res
def _get_netrc_login_info(self, netrc_machine=None):
username = None
password = None
netrc_machine = netrc_machine or self._NETRC_MACHINE
if self._downloader.params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(netrc_machine)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
except (IOError, netrc.NetrcParseError) as err:
self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
return (username, password)
def _get_login_info(self):
"""
Get the login info as (username, password)
@ -679,16 +697,8 @@ class InfoExtractor(object):
if downloader_params.get('username') is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
else:
username, password = self._get_netrc_login_info()
return (username, password)
@ -727,9 +737,14 @@ class InfoExtractor(object):
[^>]+?content=(["\'])(?P<content>.*?)\2''' % re.escape(prop)
def _og_search_property(self, prop, html, name=None, **kargs):
if not isinstance(prop, (list, tuple)):
prop = [prop]
if name is None:
name = 'OpenGraph %s' % prop
escaped = self._search_regex(self._og_regexes(prop), html, name, flags=re.DOTALL, **kargs)
name = 'OpenGraph %s' % prop[0]
og_regexes = []
for p in prop:
og_regexes.extend(self._og_regexes(p))
escaped = self._search_regex(og_regexes, html, name, flags=re.DOTALL, **kargs)
if escaped is None:
return None
return unescapeHTML(escaped)
@ -811,11 +826,14 @@ class InfoExtractor(object):
json_ld = self._search_regex(
r'(?s)<script[^>]+type=(["\'])application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
html, 'JSON-LD', group='json_ld', **kwargs)
default = kwargs.get('default', NO_DEFAULT)
if not json_ld:
return {}
return self._json_ld(
json_ld, video_id, fatal=kwargs.get('fatal', True),
expected_type=expected_type)
return default if default is not NO_DEFAULT else {}
# JSON-LD may be malformed and thus `fatal` should be respected.
# At the same time `default` may be passed that assumes `fatal=False`
# for _search_regex. Let's simulate the same behavior here as well.
fatal = kwargs.get('fatal', True) if default == NO_DEFAULT else False
return self._json_ld(json_ld, video_id, fatal=fatal, expected_type=expected_type)
def _json_ld(self, json_ld, video_id, fatal=True, expected_type=None):
if isinstance(json_ld, compat_str):
@ -823,41 +841,47 @@ class InfoExtractor(object):
if not json_ld:
return {}
info = {}
if json_ld.get('@context') == 'http://schema.org':
item_type = json_ld.get('@type')
if expected_type is not None and expected_type != item_type:
return info
if item_type == 'TVEpisode':
info.update({
'episode': unescapeHTML(json_ld.get('name')),
'episode_number': int_or_none(json_ld.get('episodeNumber')),
'description': unescapeHTML(json_ld.get('description')),
})
part_of_season = json_ld.get('partOfSeason')
if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
part_of_series = json_ld.get('partOfSeries')
if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
info['series'] = unescapeHTML(part_of_series.get('name'))
elif item_type == 'Article':
info.update({
'timestamp': parse_iso8601(json_ld.get('datePublished')),
'title': unescapeHTML(json_ld.get('headline')),
'description': unescapeHTML(json_ld.get('articleBody')),
})
elif item_type == 'VideoObject':
info.update({
'url': json_ld.get('contentUrl'),
'title': unescapeHTML(json_ld.get('name')),
'description': unescapeHTML(json_ld.get('description')),
'thumbnail': json_ld.get('thumbnailUrl'),
'duration': parse_duration(json_ld.get('duration')),
'timestamp': unified_timestamp(json_ld.get('uploadDate')),
'filesize': float_or_none(json_ld.get('contentSize')),
'tbr': int_or_none(json_ld.get('bitrate')),
'width': int_or_none(json_ld.get('width')),
'height': int_or_none(json_ld.get('height')),
})
if not isinstance(json_ld, (list, tuple, dict)):
return info
if isinstance(json_ld, dict):
json_ld = [json_ld]
for e in json_ld:
if e.get('@context') == 'http://schema.org':
item_type = e.get('@type')
if expected_type is not None and expected_type != item_type:
return info
if item_type == 'TVEpisode':
info.update({
'episode': unescapeHTML(e.get('name')),
'episode_number': int_or_none(e.get('episodeNumber')),
'description': unescapeHTML(e.get('description')),
})
part_of_season = e.get('partOfSeason')
if isinstance(part_of_season, dict) and part_of_season.get('@type') == 'TVSeason':
info['season_number'] = int_or_none(part_of_season.get('seasonNumber'))
part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
if isinstance(part_of_series, dict) and part_of_series.get('@type') == 'TVSeries':
info['series'] = unescapeHTML(part_of_series.get('name'))
elif item_type == 'Article':
info.update({
'timestamp': parse_iso8601(e.get('datePublished')),
'title': unescapeHTML(e.get('headline')),
'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'),
'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')),
})
break
return dict((k, v) for k, v in info.items() if v is not None)
@staticmethod
@ -911,7 +935,8 @@ class InfoExtractor(object):
if f.get('ext') in ['f4f', 'f4m']: # Not yet supported
preference -= 0.5
proto_preference = 0 if determine_protocol(f) in ['http', 'https'] else -0.1
protocol = f.get('protocol') or determine_protocol(f)
proto_preference = 0 if protocol in ['http', 'https'] else (-0.5 if protocol == 'rtsp' else -0.1)
if f.get('vcodec') == 'none': # audio only
preference -= 50
@ -1128,7 +1153,7 @@ class InfoExtractor(object):
'url': m3u8_url,
'ext': ext,
'protocol': 'm3u8',
'preference': preference - 1 if preference else -1,
'preference': preference - 100 if preference else -100,
'resolution': 'multiple',
'format_note': 'Quality selection URL',
}
@ -1176,27 +1201,44 @@ class InfoExtractor(object):
'protocol': entry_protocol,
'preference': preference,
}]
last_info = None
last_media = None
last_info = {}
last_media = {}
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_info = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
last_media = parse_m3u8_attributes(line)
media = parse_m3u8_attributes(line)
media_type = media.get('TYPE')
if media_type in ('VIDEO', 'AUDIO'):
media_url = media.get('URI')
if media_url:
format_id = []
for v in (media.get('GROUP-ID'), media.get('NAME')):
if v:
format_id.append(v)
formats.append({
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'language': media.get('LANGUAGE'),
'vcodec': 'none' if media_type == 'AUDIO' else None,
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
})
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
elif line.startswith('#') or not line.strip():
continue
else:
if last_info is None:
formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None
# 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_name
stream_name = last_info.get('NAME') or last_media.get('NAME')
# Bandwidth of live streams may differ over time thus making
# format_id unpredictable. So it's better to keep provided
# format_id intact.
@ -1227,11 +1269,9 @@ class InfoExtractor(object):
'abr': abr,
})
f.update(parse_codecs(last_info.get('CODECS')))
if last_media is not None:
f['m3u8_media'] = last_media
last_media = None
formats.append(f)
last_info = {}
last_media = {}
return formats
@staticmethod
@ -1481,6 +1521,13 @@ class InfoExtractor(object):
compat_etree_fromstring(mpd.encode('utf-8')), mpd_id, mpd_base_url, formats_dict=formats_dict)
def _parse_mpd_formats(self, mpd_doc, mpd_id=None, mpd_base_url='', formats_dict={}):
"""
Parse formats from MPD manifest.
References:
1. MPEG-DASH Standard, ISO/IEC 23009-1:2014(E),
http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip
2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP
"""
if mpd_doc.get('type') == 'dynamic':
return []
@ -1513,8 +1560,16 @@ class InfoExtractor(object):
s_e = segment_timeline.findall(_add_ns('S'))
if s_e:
ms_info['total_number'] = 0
ms_info['s'] = []
for s in s_e:
ms_info['total_number'] += 1 + int(s.get('r', '0'))
r = int(s.get('r', 0))
ms_info['total_number'] += 1 + r
ms_info['s'].append({
't': int(s.get('t', 0)),
# @d is mandatory (see [1, 5.3.9.6.2, Table 17, page 60])
'd': int(s.attrib['d']),
'r': r,
})
else:
timescale = segment_template.get('timescale')
if timescale:
@ -1551,7 +1606,7 @@ class InfoExtractor(object):
continue
representation_attrib = adaptation_set.attrib.copy()
representation_attrib.update(representation.attrib)
# According to page 41 of ISO/IEC 29001-1:2014, @mimeType is mandatory
# According to [1, 5.3.7.2, Table 9, page 41], @mimeType is mandatory
mime_type = representation_attrib['mimeType']
content_type = mime_type.split('/')[0]
if content_type == 'text':
@ -1595,16 +1650,40 @@ class InfoExtractor(object):
representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
media_template = representation_ms_info['media_template']
media_template = media_template.replace('$RepresentationID$', representation_id)
media_template = re.sub(r'\$(Number|Bandwidth)\$', r'%(\1)d', media_template)
media_template = re.sub(r'\$(Number|Bandwidth)%([^$]+)\$', r'%(\1)\2', media_template)
media_template = re.sub(r'\$(Number|Bandwidth|Time)\$', r'%(\1)d', media_template)
media_template = re.sub(r'\$(Number|Bandwidth|Time)%([^$]+)\$', r'%(\1)\2', media_template)
media_template.replace('$$', '$')
representation_ms_info['segment_urls'] = [
media_template % {
'Number': segment_number,
'Bandwidth': representation_attrib.get('bandwidth')}
for segment_number in range(
representation_ms_info['start_number'],
representation_ms_info['total_number'] + representation_ms_info['start_number'])]
# As per [1, 5.3.9.4.4, Table 16, page 55] $Number$ and $Time$
# can't be used at the same time
if '%(Number' in media_template:
representation_ms_info['segment_urls'] = [
media_template % {
'Number': segment_number,
'Bandwidth': representation_attrib.get('bandwidth'),
}
for segment_number in range(
representation_ms_info['start_number'],
representation_ms_info['total_number'] + representation_ms_info['start_number'])]
else:
representation_ms_info['segment_urls'] = []
segment_time = 0
def add_segment_url():
representation_ms_info['segment_urls'].append(
media_template % {
'Time': segment_time,
'Bandwidth': representation_attrib.get('bandwidth'),
}
)
for num, s in enumerate(representation_ms_info['s']):
segment_time = s.get('t') or segment_time
add_segment_url()
for r in range(s.get('r', 0)):
segment_time += s['d']
add_segment_url()
segment_time += s['d']
if 'segment_urls' in representation_ms_info:
f.update({
'segment_urls': representation_ms_info['segment_urls'],
@ -1631,7 +1710,7 @@ class InfoExtractor(object):
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _parse_html5_media_entries(self, base_url, webpage):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
def absolute_url(video_url):
return compat_urlparse.urljoin(base_url, video_url)
@ -1646,6 +1725,21 @@ class InfoExtractor(object):
return f
return {}
def _media_formats(src, cur_media_type):
full_url = absolute_url(src)
if determine_ext(full_url) == 'm3u8':
is_plain_url = False
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
else:
is_plain_url = True
formats = [{
'url': full_url,
'vcodec': 'none' if cur_media_type == 'audio' else None,
}]
return is_plain_url, formats
entries = []
for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
media_info = {
@ -1655,10 +1749,8 @@ class InfoExtractor(object):
media_attributes = extract_attributes(media_tag)
src = media_attributes.get('src')
if src:
media_info['formats'].append({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
_, formats = _media_formats(src, media_type)
media_info['formats'].extend(formats)
media_info['thumbnail'] = media_attributes.get('poster')
if media_content:
for source_tag in re.findall(r'<source[^>]+>', media_content):
@ -1666,12 +1758,13 @@ class InfoExtractor(object):
src = source_attributes.get('src')
if not src:
continue
f = parse_content_type(source_attributes.get('type'))
f.update({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
media_info['formats'].append(f)
is_plain_url, formats = _media_formats(src, media_type)
if is_plain_url:
f = parse_content_type(source_attributes.get('type'))
f.update(formats[0])
media_info['formats'].append(f)
else:
media_info['formats'].extend(formats)
for track_tag in re.findall(r'<track[^>]+>', media_content):
track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind')
@ -1687,6 +1780,18 @@ class InfoExtractor(object):
entries.append(media_info)
return entries
def _extract_akamai_formats(self, manifest_url, video_id):
formats = []
f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
formats.extend(self._extract_f4m_formats(
update_url_query(f4m_url, {'hdcore': '3.7.0'}),
video_id, f4m_id='hds', fatal=False))
m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()
@ -1747,7 +1852,7 @@ class InfoExtractor(object):
any_restricted = False
for tc in self.get_testcases(include_onlymatching=False):
if 'playlist' in tc:
if tc.get('playlist', []):
tc = tc['playlist'][0]
is_restricted = age_restricted(
tc.get('info_dict', {}).get('age_limit'), age_limit)

120
youtube_dl/extractor/condenast.py
View File

@ -5,13 +5,17 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
orderedSet,
remove_end,
extract_attributes,
mimetype2ext,
determine_ext,
int_or_none,
parse_iso8601,
)
@ -58,6 +62,9 @@ class CondeNastIE(InfoExtractor):
'ext': 'mp4',
'title': '3D Printed Speakers Lit With LED',
'description': 'Check out these beautiful 3D printed LED speakers. You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
'uploader': 'wired',
'upload_date': '20130314',
'timestamp': 1363219200,
}
}, {
# JS embed
@ -67,70 +74,93 @@ class CondeNastIE(InfoExtractor):
'id': '55f9cf8b61646d1acf00000c',
'ext': 'mp4',
'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
'uploader': 'arstechnica',
'upload_date': '20150916',
'timestamp': 1442434955,
}
}]
def _extract_series(self, url, webpage):
title = self._html_search_regex(r'<div class="cne-series-info">.*?<h1>(.+?)</h1>',
webpage, 'series title', flags=re.DOTALL)
title = self._html_search_regex(
r'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
webpage, 'series title')
url_object = compat_urllib_parse_urlparse(url)
base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
m_paths = re.finditer(r'<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]',
webpage, flags=re.DOTALL)
m_paths = re.finditer(
r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
paths = orderedSet(m.group(1) for m in m_paths)
build_url = lambda path: compat_urlparse.urljoin(base_url, path)
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):
if url_type != 'embed':
description = self._html_search_regex(
[
r'<div class="cne-video-description">(.+?)</div>',
r'<div class="video-post-content">(.+?)</div>',
],
webpage, 'description', fatal=False, flags=re.DOTALL)
query = {}
params = self._search_regex(
r'(?s)var params = {(.+?)}[;,]', webpage, 'player params', default=None)
if params:
query.update({
'videoId': self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id'),
'playerId': self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id'),
'target': self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target'),
})
else:
description = None
params = self._search_regex(r'var params = {(.+?)}[;,]', webpage,
'player params', flags=re.DOTALL)
video_id = self._search_regex(r'videoId: [\'"](.+?)[\'"]', params, 'video id')
player_id = self._search_regex(r'playerId: [\'"](.+?)[\'"]', params, 'player id')
target = self._search_regex(r'target: [\'"](.+?)[\'"]', params, 'target')
data = compat_urllib_parse_urlencode({'videoId': video_id,
'playerId': player_id,
'target': target,
})
base_info_url = self._search_regex(r'url = [\'"](.+?)[\'"][,;]',
webpage, 'base info url',
default='http://player.cnevids.com/player/loader.js?')
info_url = base_info_url + data
info_page = self._download_webpage(info_url, video_id,
'Downloading video info')
video_info = self._search_regex(r'var\s+video\s*=\s*({.+?});', info_page, 'video info')
video_info = self._parse_json(video_info, video_id)
params = extract_attributes(self._search_regex(
r'(<[^>]+data-js="video-player"[^>]+>)',
webpage, 'player params element'))
query.update({
'videoId': params['data-video'],
'playerId': params['data-player'],
'target': params['id'],
})
video_id = query['videoId']
video_info = None
info_page = self._download_webpage(
'http://player.cnevids.com/player/video.js',
video_id, 'Downloading video info', query=query, fatal=False)
if info_page:
video_info = self._parse_json(self._search_regex(
r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
else:
info_page = self._download_webpage(
'http://player.cnevids.com/player/loader.js',
video_id, 'Downloading loader info', query=query)
video_info = self._parse_json(self._search_regex(
r'var\s+video\s*=\s*({.+?});', info_page, 'video info'), video_id)
title = video_info['title']
formats = [{
'format_id': '%s-%s' % (fdata['type'].split('/')[-1], fdata['quality']),
'url': fdata['src'],
'ext': fdata['type'].split('/')[-1],
'quality': 1 if fdata['quality'] == 'high' else 0,
} for fdata in video_info['sources'][0]]
formats = []
for fdata in video_info.get('sources', [{}])[0]:
src = fdata.get('src')
if not src:
continue
ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
quality = fdata.get('quality')
formats.append({
'format_id': ext + ('-%s' % quality if quality else ''),
'url': src,
'ext': ext,
'quality': 1 if quality == 'high' else 0,
})
self._sort_formats(formats)
return {
info = self._search_json_ld(
webpage, video_id, fatal=False) if url_type != 'embed' else {}
info.update({
'id': video_id,
'formats': formats,
'title': video_info['title'],
'thumbnail': video_info['poster_frame'],
'description': description,
}
'title': title,
'thumbnail': video_info.get('poster_frame'),
'uploader': video_info.get('brand'),
'duration': int_or_none(video_info.get('duration')),
'tags': video_info.get('tags'),
'series': video_info.get('series_title'),
'season': video_info.get('season_title'),
'timestamp': parse_iso8601(video_info.get('premiere_date')),
})
return info
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site = mobj.group('site')
url_type = mobj.group('type')
item_id = mobj.group('id')
site, url_type, item_id = re.match(self._VALID_URL, url).groups()
# Convert JS embed to regular embed
if url_type == 'embedjs':

39
youtube_dl/extractor/crackle.py
View File

@ -1,5 +1,5 @@
# coding: utf-8
from __future__ import unicode_literals
from __future__ import unicode_literals, division
from .common import InfoExtractor
from ..utils import int_or_none
@ -8,12 +8,22 @@ from ..utils import int_or_none
class CrackleIE(InfoExtractor):
_VALID_URL = r'(?:crackle:|https?://(?:www\.)?crackle\.com/(?:playlist/\d+/|(?:[^/]+/)+))(?P<id>\d+)'
_TEST = {
'url': 'http://www.crackle.com/the-art-of-more/2496419',
'url': 'http://www.crackle.com/comedians-in-cars-getting-coffee/2498934',
'info_dict': {
'id': '2496419',
'id': '2498934',
'ext': 'mp4',
'title': 'Heavy Lies the Head',
'description': 'md5:bb56aa0708fe7b9a4861535f15c3abca',
'title': 'Everybody Respects A Bloody Nose',
'description': 'Jerry is kaffeeklatsching in L.A. with funnyman J.B. Smoove (Saturday Night Live, Real Husbands of Hollywood). They’re headed for brew at 10 Speed Coffee in a 1964 Studebaker Avanti.',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 906,
'series': 'Comedians In Cars Getting Coffee',
'season_number': 8,
'episode_number': 4,
'subtitles': {
'en-US': [{
'ext': 'ttml',
}]
},
},
'params': {
# m3u8 download
@ -21,12 +31,8 @@ class CrackleIE(InfoExtractor):
}
}
# extracted from http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx
_SUBTITLE_SERVER = 'http://web-us-az.crackle.com'
_UPLYNK_OWNER_ID = 'e8773f7770a44dbd886eee4fca16a66b'
_THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
# extracted from http://legacyweb-us.crackle.com/flash/ReferrerRedirect.ashx
_THUMBNAIL_TEMPLATE = 'http://images-us-am.crackle.com/%stnl_1920x1080.jpg?ts=20140107233116?c=635333335057637614'
_MEDIA_FILE_SLOTS = {
'c544.flv': {
'width': 544,
@ -48,16 +54,21 @@ class CrackleIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
config_doc = self._download_xml(
'http://legacyweb-us.crackle.com/flash/QueryReferrer.ashx?site=16',
video_id, 'Downloading config')
item = self._download_xml(
'http://legacyweb-us.crackle.com/app/revamp/vidwallcache.aspx?flags=-1&fm=%s' % video_id,
video_id).find('i')
title = item.attrib['t']
thumbnail = None
subtitles = {}
formats = self._extract_m3u8_formats(
'http://content.uplynk.com/ext/%s/%s.m3u8' % (self._UPLYNK_OWNER_ID, video_id),
'http://content.uplynk.com/ext/%s/%s.m3u8' % (config_doc.attrib['strUplynkOwnerId'], video_id),
video_id, 'mp4', m3u8_id='hls', fatal=None)
thumbnail = None
path = item.attrib.get('p')
if path:
thumbnail = self._THUMBNAIL_TEMPLATE % path
@ -76,7 +87,7 @@ class CrackleIE(InfoExtractor):
if locale not in subtitles:
subtitles[locale] = []
subtitles[locale] = [{
'url': '%s/%s%s_%s.xml' % (self._SUBTITLE_SERVER, path, locale, v),
'url': '%s/%s%s_%s.xml' % (config_doc.attrib['strSubtitleServer'], path, locale, v),
'ext': 'ttml',
}]
self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
@ -85,7 +96,7 @@ class CrackleIE(InfoExtractor):
'id': video_id,
'title': title,
'description': item.attrib.get('d'),
'duration': int(item.attrib.get('r'), 16) if item.attrib.get('r') else None,
'duration': int(item.attrib.get('r'), 16) / 1000 if item.attrib.get('r') else None,
'series': item.attrib.get('sn'),
'season_number': int_or_none(item.attrib.get('se')),
'episode_number': int_or_none(item.attrib.get('ep')),

32
youtube_dl/extractor/crunchyroll.py
View File

@ -114,6 +114,21 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# rtmp
'skip_download': True,
},
}, {
'url': 'http://www.crunchyroll.com/rezero-starting-life-in-another-world-/episode-5-the-morning-of-our-promise-is-still-distant-702409',
'info_dict': {
'id': '702409',
'ext': 'mp4',
'title': 'Re:ZERO -Starting Life in Another World- Episode 5 – The Morning of Our Promise Is Still Distant',
'description': 'md5:97664de1ab24bbf77a9c01918cb7dca9',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'TV TOKYO',
'upload_date': '20160508',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
@ -336,9 +351,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
if video_encode_id in video_encode_ids:
continue
video_encode_ids.append(video_encode_id)
video_file = xpath_text(stream_info, './file')
if not video_file:
continue
if video_file.startswith('http'):
formats.extend(self._extract_m3u8_formats(
video_file, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
video_url = xpath_text(stream_info, './host')
video_play_path = xpath_text(stream_info, './file')
if not video_url or not video_play_path:
if not video_url:
continue
metadata = stream_info.find('./metadata')
format_info = {
@ -353,7 +377,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
parsed_video_url = compat_urlparse.urlparse(video_url)
direct_video_url = compat_urlparse.urlunparse(parsed_video_url._replace(
netloc='v.lvlt.crcdn.net',
path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1])))
path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_file.split(':')[-1])))
if self._is_valid_url(direct_video_url, video_id, video_format):
format_info.update({
'url': direct_video_url,
@ -363,7 +387,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
format_info.update({
'url': video_url,
'play_path': video_play_path,
'play_path': video_file,
'ext': 'flv',
})
formats.append(format_info)

49
youtube_dl/extractor/ctsnews.py
View File

@ -1,13 +1,12 @@
# -*- coding: utf-8 -*-
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import parse_iso8601, ExtractorError
from ..utils import unified_timestamp
class CtsNewsIE(InfoExtractor):
IE_DESC = '華視新聞'
# https connection failed (Connection reset)
_VALID_URL = r'https?://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P<id>\d+)\.html'
_TESTS = [{
'url': 'http://news.cts.com.tw/cts/international/201501/201501291578109.html',
@ -16,7 +15,7 @@ class CtsNewsIE(InfoExtractor):
'id': '201501291578109',
'ext': 'mp4',
'title': '以色列.真主黨交火 3人死亡',
'description': 'md5:95e9b295c898b7ff294f09d450178d7d',
'description': '以色列和黎巴嫩真主黨，爆發五年最嚴重衝突，雙方砲轟交火，兩名以軍死亡，還有一名西班牙籍的聯合國維和人...',
'timestamp': 1422528540,
'upload_date': '20150129',
}
@ -28,7 +27,7 @@ class CtsNewsIE(InfoExtractor):
'id': '201309031304098',
'ext': 'mp4',
'title': '韓國31歲童顏男 貌如十多歲小孩',
'description': 'md5:f183feeba3752b683827aab71adad584',
'description': '越有年紀的人，越希望看起來年輕一點，而南韓卻有一位31歲的男子，看起來像是11、12歲的小孩，身...',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1378205880,
'upload_date': '20130903',
@ -36,8 +35,7 @@ class CtsNewsIE(InfoExtractor):
}, {
# With Youtube embedded video
'url': 'http://news.cts.com.tw/cts/money/201501/201501291578003.html',
'md5': '1d842c771dc94c8c3bca5af2cc1db9c5',
'add_ie': ['Youtube'],
'md5': 'e4726b2ccd70ba2c319865e28f0a91d1',
'info_dict': {
'id': 'OVbfO7d0_hQ',
'ext': 'mp4',
@ -47,42 +45,37 @@ class CtsNewsIE(InfoExtractor):
'upload_date': '20150128',
'uploader_id': 'TBSCTS',
'uploader': '中華電視公司',
}
},
'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
news_id = self._match_id(url)
page = self._download_webpage(url, news_id)
if self._search_regex(r'(CTSPlayer2)', page, 'CTSPlayer2 identifier', default=None):
feed_url = self._html_search_regex(
r'(http://news\.cts\.com\.tw/action/mp4feed\.php\?news_id=\d+)',
page, 'feed url')
video_url = self._download_webpage(
feed_url, news_id, note='Fetching feed')
news_id = self._hidden_inputs(page).get('get_id')
if news_id:
mp4_feed = self._download_json(
'http://news.cts.com.tw/action/test_mp4feed.php',
news_id, note='Fetching feed', query={'news_id': news_id})
video_url = mp4_feed['source_url']
else:
self.to_screen('Not CTSPlayer video, trying Youtube...')
youtube_url = self._search_regex(
r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url',
default=None)
if not youtube_url:
raise ExtractorError('The news includes no videos!', expected=True)
r'src="(//www\.youtube\.com/embed/[^"]+)"', page, 'youtube url')
return {
'_type': 'url',
'url': youtube_url,
'ie_key': 'Youtube',
}
return self.url_result(youtube_url, ie='Youtube')
description = self._html_search_meta('description', page)
title = self._html_search_meta('title', page)
title = self._html_search_meta('title', page, fatal=True)
thumbnail = self._html_search_meta('image', page)
datetime_str = self._html_search_regex(
r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time')
# Transform into ISO 8601 format with timezone info
datetime_str = datetime_str.replace('/', '-') + ':00+0800'
timestamp = parse_iso8601(datetime_str, delimiter=' ')
r'(\d{4}/\d{2}/\d{2} \d{2}:\d{2})', page, 'date and time', fatal=False)
timestamp = None
if datetime_str:
timestamp = unified_timestamp(datetime_str) - 8 * 3600
return {
'id': news_id,

22
youtube_dl/extractor/ctv.py
View File

@ -1,11 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class CTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ctv\.ca/video/player\?vid=(?P<id>[0-9.]+)'
_VALID_URL = r'https?://(?:www\.)?(?P<domain>ctv|tsn|bnn|thecomedynetwork)\.ca/.*?(?:\bvid=|-vid|~|%7E)(?P<id>[0-9.]+)'
_TESTS = [{
'url': 'http://www.ctv.ca/video/player?vid=706966',
'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@ -18,13 +20,27 @@ class CTVIE(InfoExtractor):
'timestamp': 1442624700,
},
'expected_warnings': ['HTTP Error 404'],
}, {
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
'only_matching': True,
}, {
'url': 'http://www.tsn.ca/video/expectations-high-for-milos-raonic-at-us-open~939549',
'only_matching': True,
}, {
'url': 'http://www.bnn.ca/video/berman-s-call-part-two-viewer-questions~939654',
'only_matching': True,
}, {
'url': 'http://www.ctv.ca/YourMorning/Video/S1E6-Monday-August-29-2016-vid938009',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
domain, video_id = re.match(self._VALID_URL, url).groups()
if domain == 'thecomedynetwork':
domain = 'comedy'
return {
'_type': 'url_transparent',
'id': video_id,
'url': '9c9media:ctv_web:%s' % video_id,
'url': '9c9media:%s_web:%s' % (domain, video_id),
'ie_key': 'NineCNineMedia',
}

9
youtube_dl/extractor/cultureunplugged.py
View File

@ -1,9 +1,13 @@
from __future__ import unicode_literals
import re
import time
from .common import InfoExtractor
from ..utils import int_or_none
from ..utils import (
int_or_none,
HEADRequest,
)
class CultureUnpluggedIE(InfoExtractor):
@ -32,6 +36,9 @@ class CultureUnpluggedIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
# request setClientTimezone.php to get PHPSESSID cookie which is need to get valid json data in the next request
self._request_webpage(HEADRequest(
'http://www.cultureunplugged.com/setClientTimezone.php?timeOffset=%d' % -(time.timezone / 3600)), display_id)
movie_data = self._download_json(
'http://www.cultureunplugged.com/movie-data/cu-%s.json' % video_id, display_id)

120
youtube_dl/extractor/curiositystream.py Normal file
View File

@ -0,0 +1,120 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
urlencode_postdata,
compat_str,
ExtractorError,
)
class CuriosityStreamBaseIE(InfoExtractor):
_NETRC_MACHINE = 'curiositystream'
_auth_token = None
_API_BASE_URL = 'https://api.curiositystream.com/v1/'
def _handle_errors(self, result):
error = result.get('error', {}).get('message')
if error:
if isinstance(error, dict):
error = ', '.join(error.values())
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
def _call_api(self, path, video_id):
headers = {}
if self._auth_token:
headers['X-Auth-Token'] = self._auth_token
result = self._download_json(
self._API_BASE_URL + path, video_id, headers=headers)
self._handle_errors(result)
return result['data']
def _real_initialize(self):
(email, password) = self._get_login_info()
if email is None:
return
result = self._download_json(
self._API_BASE_URL + 'login', None, data=urlencode_postdata({
'email': email,
'password': password,
}))
self._handle_errors(result)
self._auth_token = result['message']['auth_token']
def _extract_media_info(self, media):
video_id = compat_str(media['id'])
limelight_media_id = media['limelight_media_id']
title = media['title']
subtitles = {}
for closed_caption in media.get('closed_captions', []):
sub_url = closed_caption.get('file')
if not sub_url:
continue
lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
subtitles.setdefault(lang, []).append({
'url': sub_url,
})
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'limelight:media:' + limelight_media_id,
'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',
}
class CuriosityStreamIE(CuriosityStreamBaseIE):
IE_NAME = 'curiositystream'
_VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
_TEST = {
'url': 'https://app.curiositystream.com/video/2',
'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
'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',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
media = self._call_api('media/' + video_id, video_id)
return self._extract_media_info(media)
class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
IE_NAME = 'curiositystream:collection'
_VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
_TEST = {
'url': 'https://app.curiositystream.com/collection/2',
'info_dict': {
'id': '2',
'title': 'Curious Minds: The Internet',
'description': 'How is the internet shaping our lives in the 21st Century?',
},
'playlist_mincount': 17,
}
def _real_extract(self, url):
collection_id = self._match_id(url)
collection = self._call_api(
'collections/' + collection_id, collection_id)
entries = []
for media in collection.get('media', []):
entries.append(self._extract_media_info(media))
return self.playlist_result(
entries, collection_id,
collection.get('title'), collection.get('description'))

44
youtube_dl/extractor/cwtv.py
View File

@ -9,7 +9,7 @@ from ..utils import (
class CWTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
_VALID_URL = r'https?://(?:www\.)?cw(?:tv(?:pr)?|seed)\.com/(?:shows/)?(?:[^/]+/)+[^?]*\?.*\b(?:play|watch)=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
_TESTS = [{
'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
'info_dict': {
@ -28,7 +28,8 @@ class CWTVIE(InfoExtractor):
'params': {
# m3u8 download
'skip_download': True,
}
},
'skip': 'redirect to http://cwtv.com/shows/arrow/',
}, {
'url': 'http://www.cwseed.com/shows/whose-line-is-it-anyway/jeff-davis-4/?play=24282b12-ead2-42f2-95ad-26770c2c6088',
'info_dict': {
@ -44,22 +45,43 @@ class CWTVIE(InfoExtractor):
'upload_date': '20151006',
'timestamp': 1444107300,
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
'only_matching': True,
}, {
'url': 'http://cwtvpr.com/the-cw/video?watch=9eee3f60-ef4e-440b-b3b2-49428ac9c54e',
'only_matching': True,
}, {
'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?watch=6b15e985-9345-4f60-baf8-56e96be57c63',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/132?format=json' % video_id, video_id)
formats = self._extract_m3u8_formats(
video_data['videos']['variantplaylist']['uri'], video_id, 'mp4')
video_data = None
formats = []
for partner in (154, 213):
vdata = self._download_json(
'http://metaframe.digitalsmiths.tv/v2/CWtv/assets/%s/partner/%d?format=json' % (video_id, partner), video_id, fatal=False)
if not vdata:
continue
video_data = vdata
for quality, quality_data in vdata.get('videos', {}).items():
quality_url = quality_data.get('uri')
if not quality_url:
continue
if quality == 'variantplaylist':
formats.extend(self._extract_m3u8_formats(
quality_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
tbr = int_or_none(quality_data.get('bitrate'))
format_id = 'http' + ('-%d' % tbr if tbr else '')
if self._is_valid_url(quality_url, video_id, format_id):
formats.append({
'format_id': format_id,
'url': quality_url,
'tbr': tbr,
})
self._sort_formats(formats)
thumbnails = [{

15
youtube_dl/extractor/dailymail.py
View File

@ -5,19 +5,20 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
determine_protocol,
unescapeHTML,
)
class DailyMailIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dailymail\.co\.uk/video/[^/]+/video-(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.dailymail.co.uk/video/sciencetech/video-1288527/Turn-video-impressionist-masterpiece.html',
'md5': '2f639d446394f53f3a33658b518b6615',
'url': 'http://www.dailymail.co.uk/video/tvshowbiz/video-1295863/The-Mountain-appears-sparkling-water-ad-Heavy-Bubbles.html',
'md5': 'f6129624562251f628296c3a9ffde124',
'info_dict': {
'id': '1288527',
'id': '1295863',
'ext': 'mp4',
'title': 'Turn any video into an impressionist masterpiece',
'description': 'md5:88ddbcb504367987b2708bb38677c9d2',
'title': 'The Mountain appears in sparkling water ad for \'Heavy Bubbles\'',
'description': 'md5:a93d74b6da172dd5dc4d973e0b766a84',
}
}
@ -26,7 +27,7 @@ class DailyMailIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_data = self._parse_json(self._search_regex(
r"data-opts='({.+?})'", webpage, 'video data'), video_id)
title = video_data['title']
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)
@ -55,7 +56,7 @@ class DailyMailIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'description': video_data.get('descr'),
'description': unescapeHTML(video_data.get('descr')),
'thumbnail': video_data.get('poster') or video_data.get('thumbnail'),
'formats': formats,
}

4
youtube_dl/extractor/dailymotion.py
View File

@ -331,7 +331,9 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
for video_id in re.findall(r'data-xid="(.+?)"', webpage):
if video_id not in video_ids:
yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion')
yield self.url_result(
'http://www.dailymotion.com/video/%s' % video_id,
DailymotionIE.ie_key(), video_id)
video_ids.add(video_id)
if re.search(self._MORE_PAGES_INDICATOR, webpage) is None:

6
youtube_dl/extractor/dbtv.py
View File

@ -38,6 +38,12 @@ class DBTVIE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [url for _, url in re.findall(
r'<iframe[^>]+src=(["\'])((?:https?:)?//(?:www\.)?dbtv\.no/(?:lazy)?player/\d+.*?)\1',
webpage)]
def _real_extract(self, url):
video_id, display_id = re.match(self._VALID_URL, url).groups()

116
youtube_dl/extractor/discoverygo.py Normal file
View File

@ -0,0 +1,116 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
extract_attributes,
int_or_none,
parse_age_limit,
unescapeHTML,
ExtractorError,
)
class DiscoveryGoIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc|
velocitychannel
)go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
_TEST = {
'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
'info_dict': {
'id': '57a33c536b66d1cd0345eeb1',
'ext': 'mp4',
'title': 'Kiss First, Ask Questions Later!',
'description': 'md5:fe923ba34050eae468bffae10831cb22',
'duration': 2579,
'series': 'Love at First Kiss',
'season_number': 1,
'episode_number': 1,
'age_limit': 14,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
container = extract_attributes(
self._search_regex(
r'(<div[^>]+class=["\']video-player-container[^>]+>)',
webpage, 'video container'))
video = self._parse_json(
unescapeHTML(container.get('data-video') or container.get('data-json')),
display_id)
title = video['name']
stream = video.get('stream')
if not stream:
if video.get('authenticated') 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')
STREAM_URL_SUFFIX = 'streamUrl'
formats = []
for stream_kind in ('', 'hds'):
suffix = STREAM_URL_SUFFIX.capitalize() if stream_kind else STREAM_URL_SUFFIX
stream_url = stream.get('%s%s' % (stream_kind, suffix))
if not stream_url:
continue
if stream_kind == '':
formats.extend(self._extract_m3u8_formats(
stream_url, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
elif stream_kind == 'hds':
formats.extend(self._extract_f4m_formats(
stream_url, display_id, f4m_id=stream_kind, fatal=False))
self._sort_formats(formats)
video_id = video.get('id') or display_id
description = video.get('description', {}).get('detailed')
duration = int_or_none(video.get('duration'))
series = video.get('show', {}).get('name')
season_number = int_or_none(video.get('season', {}).get('number'))
episode_number = int_or_none(video.get('episodeNumber'))
tags = video.get('tags')
age_limit = parse_age_limit(video.get('parental', {}).get('rating'))
subtitles = {}
captions = stream.get('captions')
if isinstance(captions, list):
for caption in captions:
subtitle_url = caption.get('fileUrl')
if (not subtitle_url or not isinstance(subtitle_url, compat_str) or
not subtitle_url.startswith('http')):
continue
lang = caption.get('fileLang', 'en')
subtitles.setdefault(lang, []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'duration': duration,
'series': series,
'season_number': season_number,
'episode_number': episode_number,
'tags': tags,
'age_limit': age_limit,
'formats': formats,
'subtitles': subtitles,
}

20
youtube_dl/extractor/dotsub.py
View File

@ -10,18 +10,18 @@ from ..utils import (
class DotsubIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dotsub\.com/view/(?P<id>[^/]+)'
_TEST = {
'url': 'http://dotsub.com/view/aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'md5': '0914d4d69605090f623b7ac329fea66e',
'url': 'https://dotsub.com/view/9c63db2a-fa95-4838-8e6e-13deafe47f09',
'md5': '21c7ff600f545358134fea762a6d42b6',
'info_dict': {
'id': 'aed3b8b2-1889-4df5-ae63-ad85f5572f27',
'id': '9c63db2a-fa95-4838-8e6e-13deafe47f09',
'ext': 'flv',
'title': 'Pyramids of Waste (2010), AKA The Lightbulb Conspiracy - Planned obsolescence documentary',
'description': 'md5:699a0f7f50aeec6042cb3b1db2d0d074',
'thumbnail': 're:^https?://dotsub.com/media/aed3b8b2-1889-4df5-ae63-ad85f5572f27/p',
'duration': 3169,
'uploader': '4v4l0n42',
'timestamp': 1292248482.625,
'upload_date': '20101213',
'title': 'MOTIVATION - "It\'s Possible" Best Inspirational Video Ever',
'description': 'md5:41af1e273edbbdfe4e216a78b9d34ac6',
'thumbnail': 're:^https?://dotsub.com/media/9c63db2a-fa95-4838-8e6e-13deafe47f09/p',
'duration': 198,
'uploader': 'liuxt',
'timestamp': 1385778501.104,
'upload_date': '20131130',
'view_count': int,
}
}

111
youtube_dl/extractor/douyutv.py
View File

@ -3,9 +3,17 @@ from __future__ import unicode_literals
import hashlib
import time
import uuid
from .common import InfoExtractor
from ..utils import (ExtractorError, unescapeHTML)
from ..compat import (compat_str, compat_basestring)
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
unescapeHTML,
)
class DouyuTVIE(InfoExtractor):
@ -21,7 +29,6 @@ class DouyuTVIE(InfoExtractor):
'description': 're:.*m7show@163\.com.*',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
'is_live': True,
},
'params': {
@ -37,7 +44,6 @@ class DouyuTVIE(InfoExtractor):
'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'douyu小漠',
'uploader_id': '3769985',
'is_live': True,
},
'params': {
@ -54,7 +60,6 @@ class DouyuTVIE(InfoExtractor):
'description': 're:.*m7show@163\.com.*',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
'is_live': True,
},
'params': {
@ -65,6 +70,10 @@ class DouyuTVIE(InfoExtractor):
'only_matching': True,
}]
# Decompile core.swf in webpage by ffdec "Search SWFs in memory". core.swf
# is encrypted originally, but ffdec can dump memory to get the decrypted one.
_API_KEY = 'A12Svb&%1UUmf@hC'
def _real_extract(self, url):
video_id = self._match_id(url)
@ -75,74 +84,56 @@ class DouyuTVIE(InfoExtractor):
room_id = self._html_search_regex(
r'"room_id"\s*:\s*(\d+),', page, 'room id')
config = None
# Douyu API sometimes returns error "Unable to load the requested class: eticket_redis_cache"
# Retry with different parameters - same parameters cause same errors
for i in range(5):
prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
room_id, int(time.time()))
auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
room = self._download_json(
'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
note='Downloading room info')['data']
config_page = self._download_webpage(
'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
video_id)
try:
config = self._parse_json(config_page, video_id, fatal=False)
except ExtractorError:
# Wait some time before retrying to get a different time() value
self._sleep(1, video_id, msg_template='%(video_id)s: Error occurs. '
'Waiting for %(timeout)s seconds before retrying')
continue
else:
break
if config is None:
raise ExtractorError('Unable to fetch API result')
data = config['data']
error_code = config.get('error', 0)
if error_code is not 0:
error_desc = 'Server reported error %i' % error_code
if isinstance(data, (compat_str, compat_basestring)):
error_desc += ': ' + data
raise ExtractorError(error_desc, expected=True)
show_status = data.get('show_status')
# 1 = live, 2 = offline
if show_status == '2':
if room.get('show_status') == '2':
raise ExtractorError('Live stream is offline', expected=True)
tt = compat_str(int(time.time() / 60))
did = uuid.uuid4().hex.upper()
sign_content = ''.join((room_id, did, self._API_KEY, tt))
sign = hashlib.md5((sign_content).encode('utf-8')).hexdigest()
flv_data = compat_urllib_parse_urlencode({
'cdn': 'ws',
'rate': '0',
'tt': tt,
'did': did,
'sign': sign,
})
video_info = self._download_json(
'http://www.douyu.com/lapi/live/getPlay/%s' % room_id, video_id,
data=flv_data, note='Downloading video info',
headers={'Content-Type': 'application/x-www-form-urlencoded'})
error_code = video_info.get('error', 0)
if error_code is not 0:
raise ExtractorError(
'Live stream is offline', expected=True)
'%s reported error %i' % (self.IE_NAME, error_code),
expected=True)
base_url = data['rtmp_url']
live_path = data['rtmp_live']
base_url = video_info['data']['rtmp_url']
live_path = video_info['data']['rtmp_live']
title = self._live_title(unescapeHTML(data['room_name']))
description = data.get('show_details')
thumbnail = data.get('room_src')
video_url = '%s/%s' % (base_url, live_path)
uploader = data.get('nickname')
uploader_id = data.get('owner_uid')
multi_formats = data.get('rtmp_multi_bitrate')
if not isinstance(multi_formats, dict):
multi_formats = {}
multi_formats['live'] = live_path
formats = [{
'url': '%s/%s' % (base_url, format_path),
'format_id': format_id,
'preference': 1 if format_id == 'live' else 0,
} for format_id, format_path in multi_formats.items()]
self._sort_formats(formats)
title = self._live_title(unescapeHTML(room['room_name']))
description = room.get('notice')
thumbnail = room.get('room_src')
uploader = room.get('nickname')
return {
'id': room_id,
'display_id': video_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
'is_live': True,
}

22
youtube_dl/extractor/drtuber.py
View File

@ -3,7 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import str_to_int
from ..utils import (
NO_DEFAULT,
str_to_int,
)
class DrTuberIE(InfoExtractor):
@ -17,7 +20,6 @@ class DrTuberIE(InfoExtractor):
'ext': 'mp4',
'title': 'hot perky blonde naked golf',
'like_count': int,
'dislike_count': int,
'comment_count': int,
'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'],
'thumbnail': 're:https?://.*\.jpg$',
@ -36,25 +38,29 @@ class DrTuberIE(InfoExtractor):
r'<source src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
[r'<p[^>]+class="title_substrate">([^<]+)</p>', r'<title>([^<]+) - \d+'],
(r'class="title_watch"[^>]*><p>([^<]+)<',
r'<p[^>]+class="title_substrate">([^<]+)</p>',
r'<title>([^<]+) - \d+'),
webpage, 'title')
thumbnail = self._html_search_regex(
r'poster="([^"]+)"',
webpage, 'thumbnail', fatal=False)
def extract_count(id_, name):
def extract_count(id_, name, default=NO_DEFAULT):
return str_to_int(self._html_search_regex(
r'<span[^>]+(?:class|id)="%s"[^>]*>([\d,\.]+)</span>' % id_,
webpage, '%s count' % name, fatal=False))
webpage, '%s count' % name, default=default, fatal=False))
like_count = extract_count('rate_likes', 'like')
dislike_count = extract_count('rate_dislikes', 'dislike')
dislike_count = extract_count('rate_dislikes', 'dislike', default=None)
comment_count = extract_count('comments_count', 'comment')
cats_str = self._search_regex(
r'<div[^>]+class="categories_list">(.+?)</div>', webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str)
r'<div[^>]+class="categories_list">(.+?)</div>',
webpage, 'categories', fatal=False)
categories = [] if not cats_str else re.findall(
r'<a title="([^"]+)"', cats_str)
return {
'id': video_id,

95
youtube_dl/extractor/drtv.py
View File

@ -4,26 +4,45 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
mimetype2ext,
parse_iso8601,
remove_end,
)
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
_TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
'md5': '25e659cccc9a2ed956110a299fdf5983',
'info_dict': {
'id': 'panisk-paske-5',
'id': 'klassen-darlig-taber-10',
'ext': 'mp4',
'title': 'Panisk Påske (5)',
'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
'timestamp': 1426984612,
'upload_date': '20150322',
'duration': 1455,
'title': 'Klassen - Dårlig taber (10)',
'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
'timestamp': 1471991907,
'upload_date': '20160823',
'duration': 606.84,
},
}
'params': {
'skip_download': True,
},
}, {
'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.',
'timestamp': 1472800279,
'upload_date': '20160902',
'duration': 131.4,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
'Video %s is not available' % video_id, expected=True)
video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
(r'data-(?:material-identifier|episode-slug)="([^"]+)"',
r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
webpage, 'video id')
programcard = self._download_json(
@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
video_id, 'Downloading video JSON')
data = programcard['Data'][0]
title = data['Title']
description = data['Description']
timestamp = parse_iso8601(data['CreatedTime'])
title = remove_end(self._og_search_title(
webpage, default=None), ' | TV | DR') or data['Title']
description = self._og_search_description(
webpage, default=None) or data.get('Description')
timestamp = parse_iso8601(data.get('CreatedTime'))
thumbnail = None
duration = None
@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
subtitles = {}
for asset in data['Assets']:
if asset['Kind'] == 'Image':
thumbnail = asset['Uri']
elif asset['Kind'] == 'VideoResource':
duration = asset['DurationInMilliseconds'] / 1000.0
restricted_to_denmark = asset['RestrictedToDenmark']
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
uri = link['Uri']
target = link['Target']
format_id = target
if asset.get('Kind') == 'Image':
thumbnail = asset.get('Uri')
elif asset.get('Kind') == 'VideoResource':
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
restricted_to_denmark = asset.get('RestrictedToDenmark')
spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
for link in asset.get('Links', []):
uri = link.get('Uri')
if not uri:
continue
target = link.get('Target')
format_id = target or ''
preference = None
if spoken_subtitles:
preference = -1
@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
video_id, preference, f4m_id=format_id))
elif target == 'HLS':
formats.extend(self._extract_m3u8_formats(
uri, video_id, 'mp4', preference=preference,
m3u8_id=format_id))
uri, video_id, 'mp4', entry_protocol='m3u8_native',
preference=preference, m3u8_id=format_id))
else:
bitrate = link.get('Bitrate')
if bitrate:
@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
formats.append({
'url': uri,
'format_id': format_id,
'tbr': bitrate,
'tbr': int_or_none(bitrate),
'ext': link.get('FileFormat'),
})
subtitles_list = asset.get('SubtitlesList')
@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
'Danish': 'da',
}
for subs in subtitles_list:
lang = subs['Language']
subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
if not subs.get('Uri'):
continue
lang = subs.get('Language') or 'da'
subtitles.setdefault(LANGS.get(lang, lang), []).append({
'url': subs['Uri'],
'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
})
if not formats and restricted_to_denmark:
raise ExtractorError(
'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
self.raise_geo_restricted(
'Unfortunately, DR is not allowed to show this program outside Denmark.',
expected=True)
self._sort_formats(formats)

13
youtube_dl/extractor/eagleplatform.py
View File

@ -52,11 +52,24 @@ class EaglePlatformIE(InfoExtractor):
@staticmethod
def _extract_url(webpage):
# Regular iframe embedding
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1',
webpage)
if mobj is not None:
return mobj.group('url')
# Basic usage embedding (see http://dultonmedia.github.io/eplayer/)
mobj = re.search(
r'''(?xs)
<script[^>]+
src=(?P<q1>["\'])(?:https?:)?//(?P<host>.+?\.media\.eagleplatform\.com)/player/player\.js(?P=q1)
.+?
<div[^>]+
class=(?P<q2>["\'])eagleplayer(?P=q2)[^>]+
data-id=["\'](?P<id>\d+)
''', webpage)
if mobj is not None:
return 'eagleplatform:%(host)s:%(id)s' % mobj.groupdict()
@staticmethod
def _handle_error(response):

13
youtube_dl/extractor/engadget.py
View File

@ -4,9 +4,10 @@ from .common import InfoExtractor
class EngadgetIE(InfoExtractor):
_VALID_URL = r'https?://www.engadget.com/video/(?P<id>\d+)'
_VALID_URL = r'https?://www.engadget.com/video/(?P<id>[^/?#]+)'
_TEST = {
_TESTS = [{
# video with 5min ID
'url': 'http://www.engadget.com/video/518153925/',
'md5': 'c6820d4828a5064447a4d9fc73f312c9',
'info_dict': {
@ -15,8 +16,12 @@ class EngadgetIE(InfoExtractor):
'title': 'Samsung Galaxy Tab Pro 8.4 Review',
},
'add_ie': ['FiveMin'],
}
}, {
# video with vidible ID
'url': 'https://www.engadget.com/video/57a28462134aa15a39f0421a/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result('5min:%s' % video_id)
return self.url_result('aol-video:%s' % video_id)

82
youtube_dl/extractor/eporner.py
View File

@ -4,19 +4,23 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
encode_base_n,
ExtractorError,
int_or_none,
parse_duration,
str_to_int,
)
class EpornerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)/(?P<display_id>[\w-]+)'
_VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
_TESTS = [{
'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
'md5': '39d486f046212d8e1b911c52ab4691f8',
'info_dict': {
'id': '95008',
'id': 'qlDUmNsj6VS',
'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
'ext': 'mp4',
'title': 'Infamous Tiffany Teen Strip Tease Video',
@ -28,34 +32,72 @@ class EpornerIE(InfoExtractor):
# New (May 2016) URL layout
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
'only_matching': True,
}, {
'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
title = self._html_search_regex(
r'<title>(.*?) - EPORNER', webpage, 'title')
webpage, urlh = self._download_webpage_handle(url, display_id)
redirect_url = 'http://www.eporner.com/config5/%s' % video_id
player_code = self._download_webpage(
redirect_url, display_id, note='Downloading player config')
video_id = self._match_id(compat_str(urlh.geturl()))
sources = self._search_regex(
r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources')
hash = self._search_regex(
r'hash\s*:\s*["\']([\da-f]{32})', webpage, 'hash')
title = self._og_search_title(webpage, default=None) or self._html_search_regex(
r'<title>(.+?) - EPORNER', webpage, 'title')
# Reverse engineered from vjs.js
def calc_hash(s):
return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
video = self._download_json(
'http://www.eporner.com/xhr/video/%s' % video_id,
display_id, note='Downloading video JSON',
query={
'hash': calc_hash(hash),
'device': 'generic',
'domain': 'www.eporner.com',
'fallback': 'false',
})
if video.get('available') is False:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, video['message']), expected=True)
sources = video['sources']
formats = []
for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources):
fmt = {
'url': video_url,
'format_id': format_id,
}
m = re.search(r'^(\d+)', format_id)
if m:
fmt['height'] = int(m.group(1))
formats.append(fmt)
for kind, formats_dict in sources.items():
if not isinstance(formats_dict, dict):
continue
for format_id, format_dict in formats_dict.items():
if not isinstance(format_dict, dict):
continue
src = format_dict.get('src')
if not isinstance(src, compat_str) or not src.startswith('http'):
continue
if kind == 'hls':
formats.extend(self._extract_m3u8_formats(
src, display_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=kind, fatal=False))
else:
height = int_or_none(self._search_regex(
r'(\d+)[pP]', format_id, 'height', default=None))
fps = int_or_none(self._search_regex(
r'(\d+)fps', format_id, 'fps', default=None))
formats.append({
'url': src,
'format_id': format_id,
'height': height,
'fps': fps,
})
self._sort_formats(formats)
duration = parse_duration(self._html_search_meta('duration', webpage))

5
youtube_dl/extractor/espn.py
View File

@ -5,7 +5,7 @@ from ..utils import remove_end
class ESPNIE(InfoExtractor):
_VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://espn.go.com/video/clip?id=10365079',
'md5': '60e5d097a523e767d06479335d1bdc58',
@ -47,6 +47,9 @@ class ESPNIE(InfoExtractor):
}, {
'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return',
'only_matching': True,
}, {
'url': 'http://www.espn.com/video/clip?id=10365079',
'only_matching': True,
}]
def _real_extract(self, url):

58
youtube_dl/extractor/exfm.py
View File

@ -1,58 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class ExfmIE(InfoExtractor):
IE_NAME = 'exfm'
IE_DESC = 'ex.fm'
_VALID_URL = r'https?://(?:www\.)?ex\.fm/song/(?P<id>[^/]+)'
_SOUNDCLOUD_URL = r'http://(?:www\.)?api\.soundcloud\.com/tracks/([^/]+)/stream'
_TESTS = [
{
'url': 'http://ex.fm/song/eh359',
'md5': 'e45513df5631e6d760970b14cc0c11e7',
'info_dict': {
'id': '44216187',
'ext': 'mp3',
'title': 'Test House "Love Is Not Enough" (Extended Mix) DeadJournalist Exclusive',
'uploader': 'deadjournalist',
'upload_date': '20120424',
'description': 'Test House \"Love Is Not Enough\" (Extended Mix) DeadJournalist Exclusive',
},
'note': 'Soundcloud song',
'skip': 'The site is down too often',
},
{
'url': 'http://ex.fm/song/wddt8',
'md5': '966bd70741ac5b8570d8e45bfaed3643',
'info_dict': {
'id': 'wddt8',
'ext': 'mp3',
'title': 'Safe and Sound',
'uploader': 'Capital Cities',
},
'skip': 'The site is down too often',
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
song_id = mobj.group('id')
info_url = 'http://ex.fm/api/v3/song/%s' % song_id
info = self._download_json(info_url, song_id)['song']
song_url = info['url']
if re.match(self._SOUNDCLOUD_URL, song_url) is not None:
self.to_screen('Soundcloud song detected')
return self.url_result(song_url.replace('/stream', ''), 'Soundcloud')
return {
'id': song_id,
'url': song_url,
'ext': 'mp3',
'title': info['title'],
'thumbnail': info['image']['large'],
'uploader': info['artist'],
'view_count': info['loved_count'],
}

23
youtube_dl/extractor/expotv.py
View File

@ -1,7 +1,5 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
@ -12,23 +10,22 @@ from ..utils import (
class ExpoTVIE(InfoExtractor):
_VALID_URL = r'https?://www\.expotv\.com/videos/[^?#]*/(?P<id>[0-9]+)($|[?#])'
_TEST = {
'url': 'http://www.expotv.com/videos/reviews/1/24/LinneCardscom/17561',
'md5': '2985e6d7a392b2f7a05e0ca350fe41d0',
'url': 'http://www.expotv.com/videos/reviews/3/40/NYX-Butter-lipstick/667916',
'md5': 'fe1d728c3a813ff78f595bc8b7a707a8',
'info_dict': {
'id': '17561',
'id': '667916',
'ext': 'mp4',
'upload_date': '20060212',
'title': 'My Favorite Online Scrapbook Store',
'view_count': int,
'description': 'You\'ll find most everything you need at this virtual store front.',
'uploader': 'Anna T.',
'title': 'NYX Butter Lipstick Little Susie',
'description': 'Goes on like butter, but looks better!',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'Stephanie S.',
'upload_date': '20150520',
'view_count': int,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_key = self._search_regex(
@ -66,7 +63,7 @@ class ExpoTVIE(InfoExtractor):
fatal=False)
upload_date = unified_strdate(self._search_regex(
r'<h5>Reviewed on ([0-9/.]+)</h5>', webpage, 'upload date',
fatal=False))
fatal=False), day_first=False)
return {
'id': video_id,

116
youtube_dl/extractor/extractors.py
View File

@ -1,7 +1,10 @@
# flake8: noqa
from __future__ import unicode_literals
from .abc import ABCIE
from .abc import (
ABCIE,
ABCIViewIE,
)
from .abc7news import Abc7NewsIE
from .abcnews import (
AbcNewsIE,
@ -29,6 +32,7 @@ from .aftonbladet import AftonbladetIE
from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .amcnetworks import AMCNetworksIE
from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE
from .anysex import AnySexIE
@ -44,6 +48,7 @@ from .appletrailers import (
AppleTrailersSectionIE,
)
from .archiveorg import ArchiveOrgIE
from .arkena import ArkenaIE
from .ard import (
ARDIE,
ARDMediathekIE,
@ -66,6 +71,12 @@ from .atttechchannel import ATTTechChannelIE
from .audimedia import AudiMediaIE
from .audioboom import AudioBoomIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .awaan import (
AWAANIE,
AWAANVideoIE,
AWAANLiveIE,
AWAANSeasonIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
@ -116,9 +127,12 @@ from .carambatv import (
CarambaTVIE,
CarambaTVPageIE,
)
from .cartoonnetwork import CartoonNetworkIE
from .cbc import (
CBCIE,
CBCPlayerIE,
CBCWatchVideoIE,
CBCWatchIE,
)
from .cbs import CBSIE
from .cbslocal import CBSLocalIE
@ -132,6 +146,7 @@ from .ccc import CCCIE
from .cda import CDAIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
from .chilloutzone import ChilloutzoneIE
from .chirbit import (
@ -156,7 +171,12 @@ from .cnn import (
)
from .coub import CoubIE
from .collegerama import CollegeRamaIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .comedycentral import (
ComedyCentralIE,
ComedyCentralShortnameIE,
ComedyCentralTVIE,
ToshIE,
)
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .commonprotocols import RtmpIE
@ -174,6 +194,10 @@ from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .curiositystream import (
CuriosityStreamIE,
CuriosityStreamCollectionIE,
)
from .cwtv import CWTVIE
from .dailymail import DailyMailIE
from .dailymotion import (
@ -189,12 +213,6 @@ from .daum import (
DaumUserIE,
)
from .dbtv import DBTVIE
from .dcn import (
DCNIE,
DCNVideoIE,
DCNLiveIE,
DCNSeasonIE,
)
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE
@ -215,6 +233,7 @@ from .dvtv import DVTVIE
from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .discoverygo import DiscoveryGoIE
from .dispeak import DigitallySpeakingIE
from .dropbox import DropboxIE
from .dw import (
@ -242,13 +261,18 @@ from .espn import ESPNIE
from .esri import EsriVideoIE
from .europa import EuropaIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE
from .eyedotv import EyedoTVIE
from .facebook import FacebookIE
from .facebook import (
FacebookIE,
FacebookPluginsVideoIE,
)
from .faz import FazIE
from .fc2 import FC2IE
from .fc2 import (
FC2IE,
FC2EmbedIE,
)
from .fczenit import FczenitIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
@ -263,12 +287,12 @@ from .formula1 import Formula1IE
from .fourtube import FourTubeIE
from .fox import FOXIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .foxsports import FoxSportsIE
from .franceculture import (
FranceCultureIE,
FranceCultureEmissionIE,
from .foxnews import (
FoxNewsIE,
FoxNewsInsiderIE,
)
from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,
@ -283,8 +307,8 @@ from .freevideo import FreeVideoIE
from .funimation import FunimationIE
from .funnyordie import FunnyOrDieIE
from .fusion import FusionIE
from .fxnetworks import FXNetworksIE
from .gameinformer import GameInformerIE
from .gamekings import GamekingsIE
from .gameone import (
GameOneIE,
GameOnePlaylistIE,
@ -303,9 +327,9 @@ from .globo import (
GloboIE,
GloboArticleIE,
)
from .go import GoIE
from .godtube import GodTubeIE
from .godtv import GodTVIE
from .goldenmoustache import GoldenMoustacheIE
from .golem import GolemIE
from .googledrive import GoogleDriveIE
from .googleplus import GooglePlusIE
@ -320,6 +344,10 @@ from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .hgtv import (
HGTVIE,
HGTVComShowIE,
)
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE
@ -393,6 +421,10 @@ from .kuwo import (
)
from .la7 import LA7IE
from .laola1tv import Laola1TvIE
from .lcp import (
LcpPlayIE,
LcpIE,
)
from .learnr import LearnrIE
from .lecture2go import Lecture2GoIE
from .lemonde import LemondeIE
@ -467,11 +499,11 @@ from .motherless import MotherlessIE
from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE
from .moviezine import MoviezineIE
from .movingimage import MovingImageIE
from .msn import MSNIE
from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
MTVIggyIE,
MTVDEIE,
)
from .muenchentv import MuenchenTVIE
@ -483,8 +515,9 @@ from .myvi import MyviIE
from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .nationalgeographic import (
NationalGeographicVideoIE,
NationalGeographicIE,
NationalGeographicChannelIE,
NationalGeographicEpisodeGuideIE,
)
from .naver import NaverIE
from .nba import NBAIE
@ -521,9 +554,9 @@ from .nextmedia import (
NextMediaActionNewsIE,
AppleDailyIE,
)
from .nextmovie import NextMovieIE
from .nfb import NFBIE
from .nfl import NFLIE
from .nhk import NhkVodIE
from .nhl import (
NHLVideocenterIE,
NHLNewsIE,
@ -535,9 +568,13 @@ from .nick import (
NickDeIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninecninemedia import NineCNineMediaIE
from .ninecninemedia import (
NineCNineMediaStackIE,
NineCNineMediaIE,
)
from .ninegag import NineGagIE
from .ninenow import NineNowIE
from .nintendo import NintendoIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
@ -582,6 +619,7 @@ from .nytimes import (
NYTimesArticleIE,
)
from .nuvid import NuvidIE
from .odatv import OdaTVIE
from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
from .onet import (
@ -615,7 +653,6 @@ from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .pinkbike import PinkbikeIE
from .pladform import PladformIE
from .played import PlayedIE
from .playfm import PlayFMIE
from .plays import PlaysTVIE
from .playtvak import PlaytvakIE
@ -626,8 +663,10 @@ from .pluralsight import (
PluralsightCourseIE,
)
from .podomatic import PodomaticIE
from .pokemon import PokemonIE
from .polskieradio import PolskieRadioIE
from .porn91 import Porn91IE
from .porncom import PornComIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
@ -684,6 +723,7 @@ from .rockstargames import RockstarGamesIE
from .roosterteeth import RoosterTeethIE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rozhlas import RozhlasIE
from .rtbf import RTBFIE
from .rte import RteIE, RteRadioIE
from .rtlnl import RtlNlIE
@ -743,6 +783,7 @@ from .smotri import (
)
from .snotr import SnotrIE
from .sohu import SohuIE
from .sonyliv import SonyLIVIE
from .soundcloud import (
SoundcloudIE,
SoundcloudSetIE,
@ -779,9 +820,9 @@ from .srgssr import (
SRGSSRPlayIE,
)
from .srmediathek import SRMediathekIE
from .ssa import SSAIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamable import StreamableIE
from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
@ -797,8 +838,8 @@ from .tagesschau import (
TagesschauPlayerIE,
TagesschauIE,
)
from .tapely import TapelyIE
from .tass import TassIE
from .tbs import TBSIE
from .tdslifeway import TDSLifewayIE
from .teachertube import (
TeacherTubeIE,
@ -841,16 +882,11 @@ from .tnaflix import (
MovieFapIE,
)
from .toggle import ToggleIE
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
)
from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trollvids import TrollvidsIE
from .trutube import TruTubeIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
from .tudou import (
@ -881,10 +917,14 @@ from .tvc import (
from .tvigle import TvigleIE
from .tvland import TVLandIE
from .tvp import (
TVPEmbedIE,
TVPIE,
TVPSeriesIE,
)
from .tvplay import TVPlayIE
from .tvplay import (
TVPlayIE,
ViafreeIE,
)
from .tvple import TvpleIE
from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
@ -914,8 +954,14 @@ from .udemy import (
from .udn import UDNEmbedIE
from .digiteka import DigitekaIE
from .unistra import UnistraIE
from .uol import UOLIE
from .uplynk import (
UplynkIE,
UplynkPreplayIE,
)
from .urort import UrortIE
from .urplay import URPlayIE
from .usanetwork import USANetworkIE
from .usatoday import USATodayIE
from .ustream import UstreamIE, UstreamChannelIE
from .ustudio import (
@ -942,6 +988,7 @@ from .vice import (
ViceIE,
ViceShowIE,
)
from .viceland import VicelandIE
from .vidbit import VidbitIE
from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE
@ -995,6 +1042,7 @@ from .vk import (
)
from .vlive import VLiveIE
from .vodlocker import VodlockerIE
from .vodplatform import VODPlatformIE
from .voicerepublic import VoiceRepublicIE
from .voxmedia import VoxMediaIE
from .vporn import VpornIE
@ -1087,8 +1135,4 @@ from .youtube import (
)
from .zapiks import ZapiksIE
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
)
from .zippcast import ZippCastIE
from .zingmp3 import ZingMp3IE

68
youtube_dl/extractor/extremetube.py
View File

@ -1,20 +1,14 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
sanitized_Request,
str_to_int,
)
from ..utils import str_to_int
from .keezmovies import KeezMoviesIE
class ExtremeTubeIE(InfoExtractor):
class ExtremeTubeIE(KeezMoviesIE):
_VALID_URL = r'https?://(?:www\.)?extremetube\.com/(?:[^/]+/)?video/(?P<id>[^/#?&]+)'
_TESTS = [{
'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
'info_dict': {
'id': 'music-video-14-british-euro-brit-european-cumshots-swallow-652431',
'ext': 'mp4',
@ -35,58 +29,22 @@ class ExtremeTubeIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage, info = self._extract_info(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
if not info['title']:
info['title'] = self._search_regex(
r'<h1[^>]+title="([^"]+)"[^>]*>', webpage, 'title')
video_title = self._html_search_regex(
r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
uploader = self._html_search_regex(
r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
webpage, 'uploader', fatal=False)
view_count = str_to_int(self._html_search_regex(
view_count = str_to_int(self._search_regex(
r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
webpage, 'view count', fatal=False))
flash_vars = self._parse_json(
self._search_regex(
r'var\s+flashvars\s*=\s*({.+?});', webpage, 'flash vars'),
video_id)
formats = []
for quality_key, video_url in flash_vars.items():
height = int_or_none(self._search_regex(
r'quality_(\d+)[pP]$', quality_key, 'height', default=None))
if not height:
continue
f = {
'url': video_url,
}
mobj = re.search(
r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+', video_url)
if mobj:
height = int(mobj.group('height'))
bitrate = int(mobj.group('bitrate'))
f.update({
'format_id': '%dp-%dk' % (height, bitrate),
'height': height,
'tbr': bitrate,
})
else:
f.update({
'format_id': '%dp' % height,
'height': height,
})
formats.append(f)
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
'formats': formats,
info.update({
'uploader': uploader,
'view_count': view_count,
'age_limit': 18,
}
})
return info

47
youtube_dl/extractor/facebook.py
View File

@ -15,6 +15,7 @@ from ..compat import (
from ..utils import (
error_to_compat_str,
ExtractorError,
int_or_none,
limit_length,
sanitized_Request,
urlencode_postdata,
@ -27,7 +28,7 @@ class FacebookIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:
https?://
(?:\w+\.)?facebook\.com/
(?:[\w-]+\.)?facebook\.com/
(?:[^#]*?\#!/)?
(?:
(?:
@ -62,6 +63,8 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
'uploader': 'Tennis on Facebook',
'upload_date': '20140908',
'timestamp': 1410199200,
}
}, {
'note': 'Video without discernible title',
@ -71,6 +74,8 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'Facebook video #274175099429670',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
},
'expected_warnings': [
'title'
@ -78,12 +83,14 @@ class FacebookIE(InfoExtractor):
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
'md5': '54706e4db4f5ad58fbad82dde1f1213f',
'md5': 'b2c28d528273b323abe5c6ab59f0f030',
'info_dict': {
'id': '957955867617029',
'ext': 'mp4',
'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
'uploader': 'Demy de Zeeuw',
'upload_date': '20160110',
'timestamp': 1452431627,
},
}, {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
@ -127,6 +134,9 @@ class FacebookIE(InfoExtractor):
}, {
'url': 'https://www.facebook.com/groups/164828000315060/permalink/764967300301124/',
'only_matching': True,
}, {
'url': 'https://zh-hk.facebook.com/peoplespower/videos/1135894589806027/',
'only_matching': True,
}]
@staticmethod
@ -303,12 +313,16 @@ class FacebookIE(InfoExtractor):
if not video_title:
video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))
info_dict = {
'id': video_id,
'title': video_title,
'formats': formats,
'uploader': uploader,
'timestamp': timestamp,
}
return webpage, info_dict
@ -337,3 +351,32 @@ class FacebookIE(InfoExtractor):
self._VIDEO_PAGE_TEMPLATE % video_id,
video_id, fatal_if_no_video=True)
return info_dict
class FacebookPluginsVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
_TESTS = [{
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
'info_dict': {
'id': '10154383743583686',
'ext': 'mp4',
'title': 'What to do during the haze?',
'uploader': 'Gov.sg',
'upload_date': '20160826',
'timestamp': 1472184808,
},
'add_ie': [FacebookIE.ie_key()],
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560',
'only_matching': True,
}]
def _real_extract(self, url):
return self.url_result(
compat_urllib_parse_unquote(self._match_id(url)),
FacebookIE.ie_key())

59
youtube_dl/extractor/fc2.py
View File

@ -1,10 +1,12 @@
#! -*- coding: utf-8 -*-
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_request,
compat_urlparse,
)
@ -16,7 +18,7 @@ from ..utils import (
class FC2IE(InfoExtractor):
_VALID_URL = r'^https?://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)'
_VALID_URL = r'^(?:https?://video\.fc2\.com/(?:[^/]+/)*content/|fc2:)(?P<id>[^/]+)'
IE_NAME = 'fc2'
_NETRC_MACHINE = 'fc2'
_TESTS = [{
@ -75,12 +77,17 @@ class FC2IE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
self._login()
webpage = self._download_webpage(url, video_id)
self._downloader.cookiejar.clear_session_cookies() # must clear
self._login()
webpage = None
if not url.startswith('fc2:'):
webpage = self._download_webpage(url, video_id)
self._downloader.cookiejar.clear_session_cookies() # must clear
self._login()
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
title = 'FC2 video %s' % video_id
thumbnail = None
if webpage is not None:
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
@ -113,3 +120,41 @@ class FC2IE(InfoExtractor):
'ext': 'flv',
'thumbnail': thumbnail,
}
class FC2EmbedIE(InfoExtractor):
_VALID_URL = r'https?://video\.fc2\.com/flv2\.swf\?(?P<query>.+)'
IE_NAME = 'fc2:embed'
_TEST = {
'url': 'http://video.fc2.com/flv2.swf?t=201404182936758512407645&i=20130316kwishtfitaknmcgd76kjd864hso93htfjcnaogz629mcgfs6rbfk0hsycma7shkf85937cbchfygd74&i=201403223kCqB3Ez&d=2625&sj=11&lang=ja&rel=1&from=11&cmt=1&tk=TlRBM09EQTNNekU9&tl=プリズン･ブレイク%20S1-01%20マイケル%20【吹替】',
'md5': 'b8aae5334cb691bdb1193a88a6ab5d5a',
'info_dict': {
'id': '201403223kCqB3Ez',
'ext': 'flv',
'title': 'プリズン･ブレイク S1-01 マイケル 【吹替】',
'thumbnail': 're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
query = compat_parse_qs(mobj.group('query'))
video_id = query['i'][-1]
title = query.get('tl', ['FC2 video %s' % video_id])[0]
sj = query.get('sj', [None])[0]
thumbnail = None
if sj:
# See thumbnailImagePath() in ServerConst.as of flv2.swf
thumbnail = 'http://video%s-thumbnail.fc2.com/up/pic/%s.jpg' % (
sj, '/'.join((video_id[:6], video_id[6:8], video_id[-2], video_id[-1], video_id)))
return {
'_type': 'url_transparent',
'ie_key': FC2IE.ie_key(),
'url': 'fc2:%s' % video_id,
'title': title,
'thumbnail': thumbnail,
}

125
youtube_dl/extractor/firsttv.py
View File

@ -2,44 +2,40 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_xpath
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
qualities,
unified_strdate,
xpath_attr,
xpath_element,
xpath_text,
xpath_with_ns,
)
class FirstTVIE(InfoExtractor):
IE_NAME = '1tv'
IE_DESC = 'Первый канал'
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+p?(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# single format via video_materials.json API
'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
'md5': '82a2777648acae812d58b3f5bd42882b',
# single format
'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
'info_dict': {
'id': '35930',
'id': '40049',
'ext': 'mp4',
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
'description': 'md5:357933adeede13b202c7c21f91b871b2',
'description': 'md5:36a39c1d19618fec57d12efe212a8370',
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
'upload_date': '20150212',
'duration': 2694,
},
}, {
# multiple formats via video_materials.json API
'url': 'http://www.1tv.ru/video_archive/projects/dobroeutro/p113641',
# multiple formats
'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
'info_dict': {
'id': '113641',
'id': '364746',
'ext': 'mp4',
'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
'description': 'md5:8dcebb3dded0ff20fade39087fd1fee2',
'description': 'md5:a242eea0031fd180a4497d52640a9572',
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
'upload_date': '20160407',
'duration': 179,
@ -48,84 +44,47 @@ class FirstTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# single format only available via ONE_ONLINE_VIDEOS.archive_single_xml API
'url': 'http://www.1tv.ru/video_archive/series/f7552/p47038',
'md5': '519d306c5b5669761fd8906c39dbee23',
'info_dict': {
'id': '47038',
'ext': 'mp4',
'title': '"Побег". Второй сезон. 3 серия',
'description': 'md5:3abf8f6b9bce88201c33e9a3d794a00b',
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
'upload_date': '20120516',
'duration': 3080,
},
}, {
'url': 'http://www.1tv.ru/videoarchive/9967',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = self._match_id(url)
# Videos with multiple formats only available via this API
video = self._download_json(
'http://www.1tv.ru/video_materials.json?legacy_id=%s' % video_id,
video_id, fatal=False)
description, thumbnail, upload_date, duration = [None] * 4
if video:
item = video[0]
title = item['title']
quality = qualities(('ld', 'sd', 'hd', ))
formats = [{
'url': f['src'],
'format_id': f.get('name'),
'quality': quality(f.get('name')),
} for f in item['mbr'] if f.get('src')]
thumbnail = item.get('poster')
else:
# Some videos are not available via video_materials.json
video = self._download_xml(
'http://www.1tv.ru/owa/win/ONE_ONLINE_VIDEOS.archive_single_xml?pid=%s' % video_id,
video_id)
NS_MAP = {
'media': 'http://search.yahoo.com/mrss/',
}
item = xpath_element(video, './channel/item', fatal=True)
title = xpath_text(item, './title', fatal=True)
formats = [{
'url': content.attrib['url'],
} for content in item.findall(
compat_xpath(xpath_with_ns('./media:content', NS_MAP))) if content.attrib.get('url')]
thumbnail = xpath_attr(
item, xpath_with_ns('./media:thumbnail', NS_MAP), 'url')
webpage = self._download_webpage(url, display_id)
playlist_url = compat_urlparse.urljoin(url, self._search_regex(
r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
item = self._download_json(playlist_url, display_id)[0]
video_id = item['id']
quality = qualities(('ld', 'sd', 'hd', ))
formats = []
for f in item.get('mbr', []):
src = f.get('src')
if not src:
continue
fname = f.get('name')
formats.append({
'url': src,
'format_id': fname,
'quality': quality(fname),
})
self._sort_formats(formats)
webpage = self._download_webpage(url, video_id, 'Downloading page', fatal=False)
if webpage:
title = self._html_search_regex(
(r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
r"'title'\s*:\s*'([^']+)'"),
webpage, 'title', default=None) or title
description = self._html_search_regex(
r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
webpage, 'description', default=None) or self._html_search_meta(
'description', webpage, 'description')
thumbnail = thumbnail or self._og_search_thumbnail(webpage)
duration = int_or_none(self._html_search_meta(
'video:duration', webpage, 'video duration', fatal=False))
upload_date = unified_strdate(self._html_search_meta(
'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
title = self._html_search_regex(
(r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
r"'title'\s*:\s*'([^']+)'"),
webpage, 'title', default=None) or item['title']
description = self._html_search_regex(
r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
webpage, 'description', default=None) or self._html_search_meta(
'description', webpage, 'description')
duration = int_or_none(self._html_search_meta(
'video:duration', webpage, 'video duration', fatal=False))
upload_date = unified_strdate(self._html_search_meta(
'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
return {
'id': video_id,
'thumbnail': thumbnail,
'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
'title': title,
'description': description,
'upload_date': upload_date,

135
youtube_dl/extractor/fivemin.py
View File

@ -1,24 +1,11 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
replace_extension,
)
class FiveMinIE(InfoExtractor):
IE_NAME = '5min'
_VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
_VALID_URL = r'(?:5min:|https?://(?:[^/]*?5min\.com/|delivery\.vidible\.tv/aol)(?:(?:Scripts/PlayerSeed\.js|playerseed/?)?\?.*?playList=)?)(?P<id>\d+)'
_TESTS = [
{
@ -29,8 +16,16 @@ class FiveMinIE(InfoExtractor):
'id': '518013791',
'ext': 'mp4',
'title': 'iPad Mini with Retina Display Review',
'description': 'iPad mini with Retina Display review',
'duration': 177,
'uploader': 'engadget',
'upload_date': '20131115',
'timestamp': 1384515288,
},
'params': {
# m3u8 download
'skip_download': True,
}
},
{
# From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
@ -44,108 +39,16 @@ class FiveMinIE(InfoExtractor):
},
'skip': 'no longer available',
},
{
'url': 'http://embed.5min.com/518726732/',
'only_matching': True,
},
{
'url': 'http://delivery.vidible.tv/aol?playList=518013791',
'only_matching': True,
}
]
_ERRORS = {
'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
}
_QUALITIES = {
1: {
'width': 640,
'height': 360,
},
2: {
'width': 854,
'height': 480,
},
4: {
'width': 1280,
'height': 720,
},
8: {
'width': 1920,
'height': 1080,
},
16: {
'width': 640,
'height': 360,
},
32: {
'width': 854,
'height': 480,
},
64: {
'width': 1280,
'height': 720,
},
128: {
'width': 640,
'height': 360,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
sid = mobj.group('sid')
if mobj.group('query'):
qs = compat_parse_qs(mobj.group('query'))
if not qs.get('playList'):
raise ExtractorError('Invalid URL', expected=True)
video_id = qs['playList'][0]
if qs.get('sid'):
sid = qs['sid'][0]
embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
if not sid:
embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed page')
sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
response = self._download_json(
'https://syn.5min.com/handlers/SenseHandler.ashx?' +
compat_urllib_parse_urlencode({
'func': 'GetResults',
'playlist': video_id,
'sid': sid,
'isPlayerSeed': 'true',
'url': embed_url,
}),
video_id)
if not response['success']:
raise ExtractorError(
'%s said: %s' % (
self.IE_NAME,
self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
expected=True)
info = response['binding'][0]
formats = []
parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
for rendition in info['Renditions']:
if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
continue
else:
rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
quality = self._QUALITIES.get(rendition['ID'], {})
formats.append({
'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
'url': rendition_url,
'width': quality.get('width'),
'height': quality.get('height'),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info['Title'],
'thumbnail': info.get('ThumbURL'),
'duration': parse_duration(info.get('Duration')),
'formats': formats,
}
video_id = self._match_id(url)
return self.url_result('aol-video:%s' % video_id)

2
youtube_dl/extractor/flipagram.py
View File

@ -48,7 +48,7 @@ class FlipagramIE(InfoExtractor):
flipagram = video_data['flipagram']
video = flipagram['video']
json_ld = self._search_json_ld(webpage, video_id, default=False)
json_ld = self._search_json_ld(webpage, video_id, default={})
title = json_ld.get('title') or flipagram['captionText']
description = json_ld.get('description') or flipagram.get('captionText')

9
youtube_dl/extractor/formula1.py
View File

@ -5,8 +5,8 @@ from .common import InfoExtractor
class Formula1IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?formula1\.com/content/fom-website/en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?formula1\.com/(?:content/fom-website/)?en/video/\d{4}/\d{1,2}/(?P<id>.+?)\.html'
_TESTS = [{
'url': 'http://www.formula1.com/content/fom-website/en/video/2016/5/Race_highlights_-_Spain_2016.html',
'md5': '8c79e54be72078b26b89e0e111c0502b',
'info_dict': {
@ -15,7 +15,10 @@ class Formula1IE(InfoExtractor):
'title': 'Race highlights - Spain 2016',
},
'add_ie': ['Ooyala'],
}
}, {
'url': 'http://www.formula1.com/en/video/2016/5/Race_highlights_-_Spain_2016.html',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)

10
youtube_dl/extractor/fourtube.py
View File

@ -43,14 +43,14 @@ class FourTubeIE(InfoExtractor):
'uploadDate', webpage))
thumbnail = self._html_search_meta('thumbnailUrl', webpage)
uploader_id = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
r'<a class="item-to-subscribe" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
webpage, 'uploader id', fatal=False)
uploader = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
r'<a class="item-to-subscribe" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
webpage, 'uploader', fatal=False)
categories_html = self._search_regex(
r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="[^"]*?list[^"]*?">(.*?)</ul>',
webpage, 'categories', fatal=False)
categories = None
if categories_html:
@ -59,10 +59,10 @@ class FourTubeIE(InfoExtractor):
r'(?s)<li><a.*?>(.*?)</a>', categories_html)]
view_count = str_to_int(self._search_regex(
r'<meta itemprop="interactionCount" content="UserPlays:([0-9,]+)">',
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserPlays:([0-9,]+)">',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
r'<meta itemprop="interactionCount" content="UserLikes:([0-9,]+)">',
r'<meta[^>]+itemprop="interactionCount"[^>]+content="UserLikes:([0-9,]+)">',
webpage, 'like count', fatal=False))
duration = parse_duration(self._html_search_meta('duration', webpage))

10
youtube_dl/extractor/fox.py
View File

@ -2,7 +2,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import smuggle_url
from ..utils import (
smuggle_url,
update_url_query,
)
class FOXIE(InfoExtractor):
@ -29,11 +32,12 @@ class FOXIE(InfoExtractor):
release_url = self._parse_json(self._search_regex(
r'"fox_pdk_player"\s*:\s*({[^}]+?})', webpage, 'fox_pdk_player'),
video_id)['release_url'] + '&switch=http'
video_id)['release_url']
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(release_url, {'force_smil_url': True}),
'url': smuggle_url(update_url_query(
release_url, {'switch': 'http'}), {'force_smil_url': True}),
'id': video_id,
}

48
youtube_dl/extractor/foxnews.py
View File

@ -3,11 +3,12 @@ from __future__ import unicode_literals
import re
from .amp import AMPIE
from .common import InfoExtractor
class FoxNewsIE(AMPIE):
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
@ -49,6 +50,11 @@ class FoxNewsIE(AMPIE):
'url': 'http://video.foxbusiness.com/v/4442309889001',
'only_matching': True,
},
{
# From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
'only_matching': True,
},
]
def _real_extract(self, url):
@ -58,3 +64,43 @@ class FoxNewsIE(AMPIE):
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
info['id'] = video_id
return info
class FoxNewsInsiderIE(InfoExtractor):
_VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
IE_NAME = 'foxnews:insider'
_TEST = {
'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
'md5': 'a10c755e582d28120c62749b4feb4c0c',
'info_dict': {
'id': '5099377331001',
'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
'ext': 'mp4',
'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
'description': 'Is campus censorship getting out of control?',
'timestamp': 1472168725,
'upload_date': '20160825',
'thumbnail': 're:^https?://.*\.jpg$',
},
'add_ie': [FoxNewsIE.ie_key()],
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
return {
'_type': 'url_transparent',
'ie_key': FoxNewsIE.ie_key(),
'url': embed_url,
'display_id': display_id,
'title': title,
'description': description,
}

98
youtube_dl/extractor/franceculture.py
View File

@ -2,104 +2,56 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
)
from ..utils import (
determine_ext,
int_or_none,
ExtractorError,
unified_strdate,
)
class FranceCultureIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/player/reecouter\?play=(?P<id>[0-9]+)'
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emissions/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.franceculture.fr/player/reecouter?play=4795174',
'url': 'http://www.franceculture.fr/emissions/carnet-nomade/rendez-vous-au-pays-des-geeks',
'info_dict': {
'id': '4795174',
'id': 'rendez-vous-au-pays-des-geeks',
'display_id': 'rendez-vous-au-pays-des-geeks',
'ext': 'mp3',
'title': 'Rendez-vous au pays des geeks',
'alt_title': 'Carnet nomade | 13-14',
'vcodec': 'none',
'thumbnail': 're:^https?://.*\\.jpg$',
'upload_date': '20140301',
'thumbnail': r're:^http://static\.franceculture\.fr/.*/images/player/Carnet-nomade\.jpg$',
'description': 'startswith:Avec :Jean-Baptiste Péretié pour son documentaire sur Arte "La revanche',
'timestamp': 1393700400,
'vcodec': 'none',
}
}
def _extract_from_player(self, url, video_id):
webpage = self._download_webpage(url, video_id)
def _real_extract(self, url):
display_id = self._match_id(url)
video_path = self._search_regex(
r'<a id="player".*?href="([^"]+)"', webpage, 'video path')
video_url = compat_urlparse.urljoin(url, video_path)
timestamp = int_or_none(self._search_regex(
r'<a id="player".*?data-date="([0-9]+)"',
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<a[^>]+href="([^"]+)"',
webpage, 'video path')
title = self._og_search_title(webpage)
upload_date = unified_strdate(self._search_regex(
'(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
webpage, 'upload date', fatal=False))
thumbnail = self._search_regex(
r'<a id="player".*?>\s+<img src="([^"]+)"',
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-pagespeed-(?:lazy|high-res)-src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
display_id = self._search_regex(
r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
title = self._html_search_regex(
r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
alt_title = self._html_search_regex(
r'<span class="title">(.*?)</span>',
webpage, 'alt_title', fatal=False)
description = self._html_search_regex(
r'<span class="description">(.*?)</span>',
webpage, 'description', fatal=False)
uploader = self._html_search_regex(
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
webpage, 'uploader', default=None)
vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
return {
'id': video_id,
'id': display_id,
'display_id': display_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'vcodec': vcodec,
'uploader': uploader,
'timestamp': timestamp,
'title': title,
'alt_title': alt_title,
'thumbnail': thumbnail,
'description': description,
'display_id': display_id,
'upload_date': upload_date,
}
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_from_player(url, video_id)
class FranceCultureEmissionIE(FranceCultureIE):
_VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
_TEST = {
'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
'info_dict': {
'title': 'Jean-Gabriel Périot, cinéaste',
'alt_title': 'Les Carnets de la création',
'id': '5093239',
'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
'ext': 'mp3',
'timestamp': 1444762500,
'upload_date': '20151013',
'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_path = self._html_search_regex(
r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
if video_path == 'no_path_player':
raise ExtractorError('no player : no sound in this page.', expected=True)
new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
video_url = compat_urlparse.urljoin(url, video_path)
return self._extract_from_player(video_url, new_id)

5
youtube_dl/extractor/francetv.py
View File

@ -131,7 +131,7 @@ class PluzzIE(FranceTVBaseInfoExtractor):
class FranceTvInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
_VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
_TESTS = [{
'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
@ -206,6 +206,9 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
'uploader_id': 'x2q2ez',
},
'add_ie': ['Dailymotion'],
}, {
'url': 'http://france3-regions.francetvinfo.fr/limousin/emissions/jt-1213-limousin',
'only_matching': True,
}]
def _real_extract(self, url):

70
youtube_dl/extractor/fxnetworks.py Normal file
View File

@ -0,0 +1,70 @@
# coding: utf-8
from __future__ import unicode_literals
from .adobepass import AdobePassIE
from ..utils import (
update_url_query,
extract_attributes,
parse_age_limit,
smuggle_url,
)
class FXNetworksIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?:fxnetworks|simpsonsworld)\.com/video/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.fxnetworks.com/video/719841347694',
'md5': '1447d4722e42ebca19e5232ab93abb22',
'info_dict': {
'id': '719841347694',
'ext': 'mp4',
'title': 'Vanpage',
'description': 'F*ck settling down. You\'re the Worst returns for an all new season August 31st on FXX.',
'age_limit': 14,
'uploader': 'NEWA-FNG-FX',
'upload_date': '20160706',
'timestamp': 1467844741,
},
'add_ie': ['ThePlatform'],
}, {
'url': 'http://www.simpsonsworld.com/video/716094019682',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if 'The content you are trying to access is not available in your region.' in webpage:
self.raise_geo_restricted()
video_data = extract_attributes(self._search_regex(
r'(<a.+?rel="http://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
release_url = video_data['rel']
title = video_data['data-title']
rating = video_data.get('data-rating')
query = {
'mbr': 'true',
}
if player_type == 'movies':
query.update({
'manifest': 'm3u',
})
else:
query.update({
'switch': 'http',
})
if video_data.get('data-req-auth') == '1':
resource = self._get_mvpd_resource(
video_data['data-channel'], title,
video_data.get('data-guid'), rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, 'fx', resource)
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
'thumbnail': video_data.get('data-large-thumb'),
'age_limit': parse_age_limit(rating),
'ie_key': 'ThePlatform',
}

76
youtube_dl/extractor/gamekings.py
View File

@ -1,76 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
xpath_text,
xpath_with_ns,
)
from .youtube import YoutubeIE
class GamekingsIE(InfoExtractor):
_VALID_URL = r'https?://www\.gamekings\.nl/(?:videos|nieuws)/(?P<id>[^/]+)'
_TESTS = [{
# YouTube embed video
'url': 'http://www.gamekings.nl/videos/phoenix-wright-ace-attorney-dual-destinies-review/',
'md5': '5208d3a17adeaef829a7861887cb9029',
'info_dict': {
'id': 'HkSQKetlGOU',
'ext': 'mp4',
'title': 'Phoenix Wright: Ace Attorney - Dual Destinies Review',
'description': 'md5:db88c0e7f47e9ea50df3271b9dc72e1d',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader_id': 'UCJugRGo4STYMeFr5RoOShtQ',
'uploader': 'Gamekings Vault',
'upload_date': '20151123',
},
'add_ie': ['Youtube'],
}, {
# vimeo video
'url': 'http://www.gamekings.nl/videos/the-legend-of-zelda-majoras-mask/',
'md5': '12bf04dfd238e70058046937657ea68d',
'info_dict': {
'id': 'the-legend-of-zelda-majoras-mask',
'ext': 'mp4',
'title': 'The Legend of Zelda: Majora’s Mask',
'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
'thumbnail': 're:^https?://.*\.jpg$',
},
}, {
'url': 'http://www.gamekings.nl/nieuws/gamekings-extra-shelly-en-david-bereiden-zich-voor-op-de-livestream/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist_id = self._search_regex(
r'gogoVideo\([^,]+,\s*"([^"]+)', webpage, 'playlist id')
# Check if a YouTube embed is used
if YoutubeIE.suitable(playlist_id):
return self.url_result(playlist_id, ie='Youtube')
playlist = self._download_xml(
'http://www.gamekings.tv/wp-content/themes/gk2010/rss_playlist.php?id=%s' % playlist_id,
video_id)
NS_MAP = {
'jwplayer': 'http://rss.jwpcdn.com/'
}
item = playlist.find('./channel/item')
thumbnail = xpath_text(item, xpath_with_ns('./jwplayer:image', NS_MAP), 'thumbnail')
video_url = item.find(xpath_with_ns('./jwplayer:source', NS_MAP)).get('file')
return {
'id': video_id,
'url': video_url,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': thumbnail,
}

140
youtube_dl/extractor/generic.py
View File

@ -62,6 +62,7 @@ from .videomore import VideomoreIE
from .googledrive import GoogleDriveIE
from .jwplatform import JWPlatformIE
from .digiteka import DigitekaIE
from .arkena import ArkenaIE
from .instagram import InstagramIE
from .liveleak import LiveLeakIE
from .threeqsdn import ThreeQSDNIE
@ -70,6 +71,9 @@ from .vessel import VesselIE
from .kaltura import KalturaIE
from .eagleplatform import EaglePlatformIE
from .facebook import FacebookIE
from .soundcloud import SoundcloudIE
from .vbox7 import Vbox7IE
from .dbtv import DBTVIE
class GenericIE(InfoExtractor):
@ -100,7 +104,8 @@ class GenericIE(InfoExtractor):
},
'expected_warnings': [
'URL could be a direct video link, returning it as such.'
]
],
'skip': 'URL invalid',
},
# Direct download with broken HEAD
{
@ -264,7 +269,8 @@ class GenericIE(InfoExtractor):
'params': {
# m3u8 downloads
'skip_download': True,
}
},
'skip': 'video gone',
},
# m3u8 served with Content-Type: text/plain
{
@ -279,7 +285,8 @@ class GenericIE(InfoExtractor):
'params': {
# m3u8 downloads
'skip_download': True,
}
},
'skip': 'video gone',
},
# google redirect
{
@ -364,6 +371,7 @@ class GenericIE(InfoExtractor):
'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
},
'add_ie': ['BrightcoveLegacy'],
'skip': 'video gone',
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
@ -417,6 +425,7 @@ class GenericIE(InfoExtractor):
'params': {
'skip_download': True,
},
'skip': 'movie expired',
},
# embed.ly video
{
@ -444,6 +453,8 @@ class GenericIE(InfoExtractor):
'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
},
# HEAD requests lead to endless 301, while GET is OK
'expected_warnings': ['301'],
},
# RUTV embed
{
@ -473,7 +484,7 @@ class GenericIE(InfoExtractor):
'url': 'http://www.vestifinance.ru/articles/25753',
'info_dict': {
'id': '25753',
'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
'title': 'Прямые трансляции с Форума-выставки "Госзаказ-2013"',
},
'playlist': [{
'info_dict': {
@ -518,6 +529,9 @@ class GenericIE(InfoExtractor):
'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
},
'playlist_mincount': 7,
# This forum does not allow <iframe> syntaxes anymore
# Now HTML tags are displayed as-is
'skip': 'No videos on this page',
},
# Embedded TED video
{
@ -566,7 +580,8 @@ class GenericIE(InfoExtractor):
},
'params': {
'skip_download': 'Requires rtmpdump'
}
},
'skip': 'video gone',
},
# francetv embed
{
@ -640,6 +655,8 @@ class GenericIE(InfoExtractor):
'ext': 'mp4',
'title': 'Key and Peele|October 10, 2012|2|203|Liam Neesons - Uncensored',
'description': 'Two valets share their love for movie star Liam Neesons.',
'timestamp': 1349922600,
'upload_date': '20121011',
},
},
# YouTube embed via <data-embed-url="">
@ -781,6 +798,15 @@ class GenericIE(InfoExtractor):
'upload_date': '20141029',
}
},
# Soundcloud multiple embeds
{
'url': 'http://www.guitarplayer.com/lessons/1014/legato-workout-one-hour-to-more-fluid-performance---tab/52809',
'info_dict': {
'id': '52809',
'title': 'Guitar Essentials: Legato Workout—One-Hour to Fluid Performance | TAB + AUDIO',
},
'playlist_mincount': 7,
},
# Livestream embed
{
'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast',
@ -856,6 +882,7 @@ class GenericIE(InfoExtractor):
'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220',
},
'skip': 'All The Daily Show URLs now redirect to http://www.cc.com/shows/',
},
# jwplayer YouTube
{
@ -1249,6 +1276,20 @@ class GenericIE(InfoExtractor):
'uploader': 'www.hudl.com',
},
},
# twitter:player:stream embed
{
'url': 'http://www.rtl.be/info/video/589263.aspx?CategoryID=288',
'info_dict': {
'id': 'master',
'ext': 'mp4',
'title': 'Une nouvelle espèce de dinosaure découverte en Argentine',
'uploader': 'www.rtl.be',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
},
# twitter:player embed
{
'url': 'http://www.theatlantic.com/video/index/484130/what-do-black-holes-sound-like/',
@ -1328,6 +1369,44 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Vimeo'],
},
{
'url': 'https://support.arkena.com/display/PLAY/Ways+to+embed+your+video',
'md5': 'b96f2f71b359a8ecd05ce4e1daa72365',
'info_dict': {
'id': 'b41dda37-d8e7-4d3f-b1b5-9a9db578bdfe',
'ext': 'mp4',
'title': 'Big Buck Bunny',
'description': 'Royalty free test video',
'timestamp': 1432816365,
'upload_date': '20150528',
'is_live': False,
},
'params': {
'skip_download': True,
},
'add_ie': [ArkenaIE.ie_key()],
},
{
'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
'info_dict': {
'id': '1c7141f46c',
'ext': 'mp4',
'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
},
'params': {
'skip_download': True,
},
'add_ie': [Vbox7IE.ie_key()],
},
{
# DBTV embeds
'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
'info_dict': {
'id': '43254897',
'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
},
'playlist_mincount': 3,
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -1964,12 +2043,9 @@ class GenericIE(InfoExtractor):
return self.url_result(myvi_url)
# Look for embedded soundcloud player
mobj = re.search(
r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"',
webpage)
if mobj is not None:
url = unescapeHTML(mobj.group('url'))
return self.url_result(url)
soundcloud_urls = SoundcloudIE._extract_urls(webpage)
if soundcloud_urls:
return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
# Look for embedded mtvservices player
mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
@ -2132,6 +2208,11 @@ class GenericIE(InfoExtractor):
if digiteka_url:
return self.url_result(self._proto_relative_url(digiteka_url), DigitekaIE.ie_key())
# Look for Arkena embeds
arkena_url = ArkenaIE._extract_url(webpage)
if arkena_url:
return self.url_result(arkena_url, ArkenaIE.ie_key())
# Look for Limelight embeds
mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
if mobj:
@ -2160,6 +2241,14 @@ class GenericIE(InfoExtractor):
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group(1))), 'Vine')
# Look for VODPlatform embeds
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
# Look for Instagram embeds
instagram_embed_url = InstagramIE._extract_embed_url(webpage)
if instagram_embed_url is not None:
@ -2184,15 +2273,20 @@ class GenericIE(InfoExtractor):
'uploader': video_uploader,
}
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser
embed_url = self._html_search_meta('twitter:player', webpage, default=None)
if embed_url:
return self.url_result(embed_url)
# Look for VBOX7 embeds
vbox7_url = Vbox7IE._extract_url(webpage)
if vbox7_url:
return self.url_result(vbox7_url, Vbox7IE.ie_key())
# Look for DBTV embeds
dbtv_urls = DBTVIE._extract_urls(webpage)
if dbtv_urls:
return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default=None, expected_type='VideoObject')
if json_ld and json_ld.get('url'):
webpage, video_id, default={}, expected_type='VideoObject')
if json_ld.get('url'):
info_dict.update({
'title': video_title or info_dict['title'],
'description': video_description,
@ -2245,6 +2339,9 @@ class GenericIE(InfoExtractor):
r"cinerama\.embedPlayer\(\s*\'[^']+\',\s*'([^']+)'", webpage)
if not found:
# Try to find twitter cards info
# twitter:player:stream should be checked before twitter:player since
# it is expected to contain a raw stream (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
found = filter_video(re.findall(
r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage))
if not found:
@ -2278,6 +2375,15 @@ class GenericIE(InfoExtractor):
'_type': 'url',
'url': new_url,
}
if not found:
# twitter:player is a https URL to iframe player that may or may not
# be supported by youtube-dl thus this is checked the very last (see
# https://dev.twitter.com/cards/types/player#On_twitter.com_via_desktop_browser)
embed_url = self._html_search_meta('twitter:player', webpage, default=None)
if embed_url:
return self.url_result(embed_url)
if not found:
raise UnsupportedError(url)

16
youtube_dl/extractor/glide.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unified_strdate
class GlideIE(InfoExtractor):
@ -14,10 +13,8 @@ class GlideIE(InfoExtractor):
'info_dict': {
'id': 'UZF8zlmuQbe4mr+7dCiQ0w==',
'ext': 'mp4',
'title': 'Damon Timm\'s Glide message',
'title': "Damon's Glide message",
'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$',
'uploader': 'Damon Timm',
'upload_date': '20140919',
}
}
@ -27,7 +24,8 @@ class GlideIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<title>(.+?)</title>', webpage, 'title')
r'<title>(.+?)</title>', webpage,
'title', default=None) or self._og_search_title(webpage)
video_url = self._proto_relative_url(self._search_regex(
r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'video URL', default=None,
@ -36,18 +34,10 @@ class GlideIE(InfoExtractor):
r'<img[^>]+id=["\']video-thumbnail["\'][^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'thumbnail url', default=None,
group='url')) or self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'<div[^>]+class=["\']info-name["\'][^>]*>([^<]+)',
webpage, 'uploader', fatal=False)
upload_date = unified_strdate(self._search_regex(
r'<div[^>]+class="info-date"[^>]*>([^<]+)',
webpage, 'upload date', fatal=False))
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumbnail,
'uploader': uploader,
'upload_date': upload_date,
}

7
youtube_dl/extractor/globo.py
View File

@ -396,12 +396,12 @@ class GloboIE(InfoExtractor):
class GloboArticleIE(InfoExtractor):
_VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)\.html'
_VALID_URL = 'https?://.+?\.globo\.com/(?:[^/]+/)*(?P<id>[^/]+)(?:\.html)?'
_VIDEOID_REGEXES = [
r'\bdata-video-id=["\'](\d{7,})',
r'\bdata-player-videosids=["\'](\d{7,})',
r'\bvideosIDs\s*:\s*["\'](\d{7,})',
r'\bvideosIDs\s*:\s*["\']?(\d{7,})',
r'\bdata-id=["\'](\d{7,})',
r'<div[^>]+\bid=["\'](\d{7,})',
]
@ -423,6 +423,9 @@ class GloboArticleIE(InfoExtractor):
}, {
'url': 'http://gshow.globo.com/programas/tv-xuxa/O-Programa/noticia/2014/01/xuxa-e-junno-namoram-muuuito-em-luau-de-zeze-di-camargo-e-luciano.html',
'only_matching': True,
}, {
'url': 'http://oglobo.globo.com/rio/a-amizade-entre-um-entregador-de-farmacia-um-piano-19946271',
'only_matching': True,
}]
@classmethod

101
youtube_dl/extractor/go.py Normal file
View File

@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
determine_ext,
parse_age_limit,
)
class GoIE(InfoExtractor):
_BRANDS = {
'abc': '001',
'freeform': '002',
'watchdisneychannel': '004',
'watchdisneyjunior': '008',
'watchdisneyxd': '009',
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/.*?vdka(?P<id>\w+)' % '|'.join(_BRANDS.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'info_dict': {
'id': '0_g86w5onx',
'ext': 'mp4',
'title': 'Sneak Peek: Language Arts',
'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
'only_matching': True,
}]
def _real_extract(self, url):
sub_domain, video_id = re.match(self._VALID_URL, url).groups()
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' % (self._BRANDS[sub_domain], video_id),
video_id)['video'][0]
title = video_data['title']
formats = []
for asset in video_data.get('assets', {}).get('asset', []):
asset_url = asset.get('value')
if not asset_url:
continue
format_id = asset.get('format')
ext = determine_ext(asset_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
else:
formats.append({
'format_id': format_id,
'url': asset_url,
'ext': ext,
})
self._sort_formats(formats)
subtitles = {}
for cc in video_data.get('closedcaption', {}).get('src', []):
cc_url = cc.get('value')
if not cc_url:
continue
ext = determine_ext(cc_url)
if ext == 'xml':
ext = 'ttml'
subtitles.setdefault(cc.get('lang'), []).append({
'url': cc_url,
'ext': ext,
})
thumbnails = []
for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
thumbnail_url = thumbnail.get('value')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
return {
'id': video_id,
'title': title,
'description': video_data.get('longdescription') or video_data.get('description'),
'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
'episode_number': int_or_none(video_data.get('episodenumber')),
'series': video_data.get('show', {}).get('title'),
'season_number': int_or_none(video_data.get('season', {}).get('num')),
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles,
}

48
youtube_dl/extractor/goldenmoustache.py
View File

@ -1,48 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
class GoldenMoustacheIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P<display_id>[\w-]+)-(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/',
'md5': '0f904432fa07da5054d6c8beb5efb51a',
'info_dict': {
'id': '3700',
'ext': 'mp4',
'title': 'Suricate - Le Poker',
'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/',
'md5': '27f0c50fb4dd5f01dc9082fc67cd5700',
'info_dict': {
'id': '55249',
'ext': 'mp4',
'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)',
'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a',
'thumbnail': 're:^https?://.*\.(?:png|jpg)$',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_regex(
r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL')
title = self._html_search_regex(
r'<title>(.*?)(?: - Golden Moustache)?</title>', webpage, 'title')
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
return {
'id': video_id,
'url': video_url,
'ext': 'mp4',
'title': title,
'description': description,
'thumbnail': thumbnail,
}

79
youtube_dl/extractor/hgtv.py Normal file
View File

@ -0,0 +1,79 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
js_to_json,
smuggle_url,
)
class HGTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hgtv\.ca/[^/]+/video/(?P<id>[^/]+)/video.html'
_TEST = {
'url': 'http://www.hgtv.ca/homefree/video/overnight-success/video.html?v=738081859718&p=1&s=da#video',
'md5': '',
'info_dict': {
'id': 'aFH__I_5FBOX',
'ext': 'mp4',
'title': 'Overnight Success',
'description': 'After weeks of hard work, high stakes, breakdowns and pep talks, the final 2 contestants compete to win the ultimate dream.',
'uploader': 'SHWM-NEW',
'timestamp': 1470320034,
'upload_date': '20160804',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
embed_vars = self._parse_json(self._search_regex(
r'(?s)embed_vars\s*=\s*({.*?});',
webpage, 'embed vars'), display_id, js_to_json)
return {
'_type': 'url_transparent',
'url': smuggle_url(
'http://link.theplatform.com/s/dtjsEC/%s?mbr=true&manifest=m3u' % embed_vars['pid'], {
'force_smil_url': True
}),
'series': embed_vars.get('show'),
'season_number': int_or_none(embed_vars.get('season')),
'episode_number': int_or_none(embed_vars.get('episode')),
'ie_key': 'ThePlatform',
}
class HGTVComShowIE(InfoExtractor):
IE_NAME = 'hgtv.com:show'
_VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
'info_dict': {
'id': 'flip-or-flop-full-episodes-videos',
'title': 'Flip or Flop Full Episodes',
},
'playlist_mincount': 15,
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
config = self._parse_json(
self._search_regex(
r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
webpage, 'video config'),
display_id)['channels'][0]
entries = [
self.url_result(video['releaseUrl'])
for video in config['videos'] if video.get('releaseUrl')]
return self.playlist_result(
entries, display_id, config.get('title'), config.get('description'))

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