Compare commits

...

113 Commits

Author SHA1 Message Date
Sergey M․
4a01befb34 release 2016.08.07 2016-08-07 21:12:41 +07:00
Sergey M․
845dfcdc40 [ChangeLog] Actualize 2016-08-07 21:10:48 +07:00
Sergey M․
d92cb46305 [discoverygo] Add extractor (Closes #10245) 2016-08-07 20:57:05 +07:00
Sergey M․
a8795327ca [utils] Add support TV Parental Guidelines ratings in parse_age_limit 2016-08-07 20:45:18 +07:00
Sergey M․
d34995a9e3 [flipagram] Make _search_json_ld non fatal 2016-08-07 19:06:55 +07:00
Sergey M․
958849275f [extractor/generic] Make _search_json_ld non fatal 2016-08-07 19:04:22 +07:00
Sergey M․
998f094452 [bbc] Remove proxy from test 2016-08-07 18:13:05 +07:00
Sergey M․
aaa42cf0cf [bbc] PEP 8 2016-08-07 18:05:13 +07:00
Sergey M․
9fb64c04cd [bbc] Add support for morph embeds (Closes #10239) 2016-08-07 18:01:50 +07:00
Remita Amine
f9622868e7 [bbc] preserve format_id backward compatibility 2016-08-07 11:14:15 +01:00
Remita Amine
37768f9242 [common] correctly lower the preference of m3u8 master manifest format 2016-08-07 10:59:09 +01:00
Sergey M․
a1aadd09a4 [tnaflixnetworkbase] Improve title extraction 2016-08-07 16:00:09 +07:00
Sergey M․
b47a75017b [tnaflix] Fix metadata extraction (Closes #10249) 2016-08-07 16:00:03 +07:00
Remita Amine
e37b54b140 [fox] fix theplatform release url query 2016-08-06 20:53:39 +01:00
Yen Chi Hsuan
c1decda58c [openload] Fix extraction (closes #9706) 2016-08-07 02:44:15 +08:00
Yen Chi Hsuan
d3f8e038fe [utils] Add decode_png for openload (#9706) 2016-08-07 02:42:58 +08:00
Remita Amine
ad152e2d95 [bbc] fix test 2016-08-06 19:36:12 +01:00
Remita Amine
b0af12154e [bbc] reduce requests and improve format_id 2016-08-06 19:24:59 +01:00
Remita Amine
d16b3c6677 [common] extract partOfTVSeries info in json-ld 2016-08-06 18:58:38 +01:00
Remita Amine
c57244cdb1 [common] lower the preference of m3u8 master manifest format 2016-08-06 18:55:05 +01:00
Remita Amine
a7e5f27412 [bbc] improve extraction
- extract f4m and dash formats
- improve format sorting and listing
- improve extraction of articles with `otherSettings.playlist`
2016-08-06 18:48:09 +01:00
Remita Amine
089a40955c [pokemon] improve _VALID_URL 2016-08-06 12:08:14 +01:00
Remita Amine
d73ebac100 [pokemon] Add new extractor(closes #10093) 2016-08-06 11:18:14 +01:00
Remita Amine
e563c0d73b [condenast] fallback to loader.js if video.js fail 2016-08-05 21:01:16 +01:00
Sergey M․
491c42e690 release 2016.08.06 2016-08-06 01:23:48 +07:00
Sergey M․
7f2339c617 [ChangeLog] Actualize 2016-08-06 01:19:47 +07:00
Sergey M․
8122e79fef [gamekings] Remove remnants 2016-08-06 00:12:37 +07:00
Sergey M․
fe3ad1d456 [adultswim] Remove superfluous md5 from test 2016-08-06 00:02:05 +07:00
Sergey M․
038a5e1a65 [adultswim] Add support for trailers (Closes #10235) 2016-08-06 00:00:05 +07:00
Sergey M․
84bc23b41b [archiveorg] PEP 8 2016-08-05 23:16:19 +07:00
Sergey M․
46933a15d6 [extractor/common] Support root JSON-LD lists (Closes #10203) 2016-08-05 23:14:32 +07:00
Sergey M․
3859ebeee6 [tvplay] Capture and output native error message 2016-08-05 22:50:42 +07:00
Remita Amine
d50aca41f8 [archiveorg] improve format extraction(closes #10219) 2016-08-05 16:42:15 +01:00
Remita Amine
0ca057b965 [jwplatform] add support for playlist extraction and relative urls and improve audio detection 2016-08-05 16:42:15 +01:00
Sergey M․
5ca968d0a6 [tvplay] Extract series metadata 2016-08-05 22:37:38 +07:00
Sergey M․
f0d31c624e [tvplay] Add support for subtitles (Closes #10194) 2016-08-05 22:17:32 +07:00
Remita Amine
08c655906c [5min] fix _VALID_URL(closes #10228) 2016-08-05 10:22:33 +01:00
Remita Amine
5a993e1692 [natgeo] fix tests(closes #10229) 2016-08-05 10:13:26 +01:00
Remita Amine
a7d2953073 [extractors] add tvp:embed import 2016-08-05 10:11:59 +01:00
Remita Amine
fdd0b8f8e0 [tvp] extract video id from the webpage(fixes #7799) 2016-08-05 09:44:15 +01:00
Remita Amine
f65dc41b72 [naver] extract upload date 2016-08-05 08:12:25 +01:00
Yen Chi Hsuan
962250f7ea [cbslocal] Fix timestamp parsing (closes #10213) 2016-08-05 11:44:50 +08:00
Yen Chi Hsuan
7dc2a74e0a [utils] Fix unified_timestamp for formats parsed by parsedate_tz() 2016-08-05 11:41:55 +08:00
Remita Amine
b02b960c6b [naver] improve extraction(closes #8096) 2016-08-04 21:42:22 +01:00
Remita Amine
4f427c4be8 [condenast] improve extraction 2016-08-04 18:30:56 +01:00
Sergey M․
8a00ea567b [natgeo:episodeguide] Do not shadow url from outer scope 2016-08-04 23:21:04 +07:00
Remita Amine
8895be01fc [5min] fix _VALID_URL 2016-08-04 16:55:12 +01:00
Remita Amine
52e7fcfeb7 [engadget] Relax _VALID_URL 2016-08-04 16:34:47 +01:00
Remita Amine
2396062c74 [5min] delegate extraction to AolIE
recently the 5min SenseHandler request return
HTTP Error 503: Service Unavailable error
2016-08-04 16:21:27 +01:00
Remita Amine
14704aeff6 [kaltura] remove debugging line 2016-08-04 14:54:34 +01:00
Remita Amine
3c2c3af059 [extractors] change imports for national geographic extractors 2016-08-04 12:20:56 +01:00
Remita Amine
1891ea2d76 [nationalgeographic] Add support for National Geographic Episode Guide 2016-08-04 12:18:10 +01:00
Remita Amine
1094074c04 [kaltura] extract subtitles and reduce requests 2016-08-04 09:39:06 +01:00
Remita Amine
217d5ae013 [vodplatform] Add new extractor 2016-08-04 09:39:06 +01:00
Remita Amine
8b40854529 [common] lower proto_preference of rtsp formats
Most of the time the RtspFD fail to download videos but it report
success of the download with this output:
[mpv] 0 bytes
[download] 100% of 0.00B
2016-08-04 09:39:06 +01:00
Yen Chi Hsuan
6bb0fbf9fb Revert "[README.md] Use full paths for all configuration files (#8863)"
This reverts commit 899d2bea63.
2016-08-04 09:54:28 +08:00
Sergey M․
8d3b226b83 [gamekings] Remove extractor
Now covered by generic jwplayer
2016-08-03 22:06:10 +07:00
Remita Amine
42b7a5afe0 [limelight] extract http formats 2016-08-03 13:12:51 +01:00
Yen Chi Hsuan
899d2bea63 [README.md] Use full paths for all configuration files (#8863) 2016-08-03 11:15:27 +08:00
Sergey M․
9cb0e65d7e [ntvru] Fix extraction 2016-08-02 22:56:48 +07:00
Sergey M․
b070564efb [extractor/common] Support multiple properties in _og_search_property 2016-08-02 22:55:14 +07:00
Philipp Hagemeister
ce28252c48 [options] Add test that checks that --password=secret is hidden in verbose output 2016-08-02 17:03:46 +02:00
Philipp Hagemeister
3aa9a73554 [options] Hide --password=secret in verbose output 2016-08-02 17:03:26 +02:00
Philipp Hagemeister
6a9b3b61ea [comedycentral] Re-add shortnames
In cc99d4f826, the shortname feature got deleted by accident. Re-add it as a separate IE.
2016-08-02 14:02:31 +02:00
Sergey M․
45408eb075 release 2016.08.01 2016-08-01 22:59:23 +07:00
Sergey M․
eafc66855d [ChangeLog] Add recent changes 2016-08-01 22:56:01 +07:00
Sergey M․
e03d3e6453 [cwtv] Add support for cwtvpr.com (Closes #10196) 2016-08-01 22:51:01 +07:00
Remita Amine
a70e45f80a [limelight] keep videos marked as previewStream
e382b953f0 (commitcomment-18472915)
2016-08-01 16:25:41 +01:00
Sergey M․
697655a7c0 [safari] Relax url regexes (Closes #10202) 2016-08-01 21:48:48 +07:00
Remita Amine
e382b953f0 [limelight] skip preview and drm protected videos 2016-08-01 00:33:30 +01:00
Yen Chi Hsuan
116e7e0d04 [bloomberg] Support BPlayer() players (closes #10187) 2016-07-31 14:47:19 +08:00
Sergey M․
cf03e34ad3 [yandexmusic:track] Fix extraction (Closes #10193) 2016-07-31 07:56:18 +07:00
Sergey M․
2903137292 release 2016.07.30 2016-07-30 14:45:07 +07:00
Sergey M․
9361f2169c [ChangeLog] Make extractor improvements' descriptions more concrete 2016-07-30 14:43:28 +07:00
Yen Chi Hsuan
35aa6c538f Add ChangeLog 2016-07-30 12:33:09 +08:00
Sergey M․
fa9f1d16b8 [dailymotion:playlist] Carry long line 2016-07-29 22:47:34 +07:00
Dave
485fedf6fd [dailymotion:playlist] Optimize download archive processing 2016-07-29 22:45:41 +07:00
Jaime Marquínez Ferrándiz
da0baba5c8 [rtve] Fix extraction for some videos
For example http://www.rtve.es/alacarta/videos/documentos-tv/documentos-tv-descredito/3574098/.
2016-07-29 17:20:27 +02:00
Jaime Marquínez Ferrándiz
bb9f3bfedf Revert "[rtve] Fix extraction (#10076)"
This reverts commit c39b2ed990.

Apparently outside of Spain using 'auth/resources' is required (#10097).
2016-07-29 17:14:04 +02:00
Sergey M․
dbc0b39b91 [tv2] Improve extraction 2016-07-29 22:01:34 +07:00
Sergey M․
481c5c5137 [tv2:article] Fix extraction (Closes #10188) 2016-07-29 21:43:17 +07:00
Sergey M․
0cacae2807 [twitch:clips] Sort formats 2016-07-29 09:01:53 +07:00
Sergey M․
d9d56deadf release 2016.07.28 2016-07-28 02:42:57 +07:00
Sergey M․
74ba450a81 [twitch:clips] Fix extraction (Closes #9767) 2016-07-28 22:30:09 +07:00
Sergey M․
db19df6ca0 [extractor/generic] Add test for #10179 2016-07-28 22:20:08 +07:00
Sergey M․
fbdf8d15d1 [soundcloud] Add _extract_urls (#10179) 2016-07-28 22:16:05 +07:00
Sergey M․
94aae01548 [extractor/generic] Extract all soundcloud embeds (Closes #10179) 2016-07-28 22:15:15 +07:00
Sergey M․
39eef54cf0 [ard:mediathek] Skip unavailable test 2016-07-28 21:38:23 +07:00
Sergey M․
05c8268c81 [shared] Modernize and make more robust 2016-07-27 23:39:02 +07:00
Sergey M․
289a16b4f3 [shared] Respect redirect URL (Closes #10170) 2016-07-27 23:28:01 +07:00
Sergey M․
7935926baa [devscripts/show-downloads-statistics] Add support for paging 2016-07-27 00:14:40 +07:00
Sergey M․
dcbb07c35a release 2016.07.26.2 2016-07-26 23:56:53 +07:00
Sergey M․
40090e8d51 [extractor/common] Improve is_suitable
In order to fix breakage introduced by a3aa814b77
2016-07-26 23:54:06 +07:00
Sergey M․
3e050d51d4 [orf:oe1] Relax _VALID_URL 2016-07-26 23:14:04 +07:00
Sergey M․
ced70c8640 [cbc] PEP 8 2016-07-26 23:08:08 +07:00
Sergey M․
9a700deea4 [instagram] Remove duplicate field in test 2016-07-26 23:07:16 +07:00
Sergey M․
dc35ba0eba [mgtv] Fix typo 2016-07-26 23:06:21 +07:00
Sergey M․
88bd486b9a [cbc] Improve extraction for videos embedded with clipId 2016-07-26 22:58:50 +07:00
Sergey M․
7f8b92e3cf [bigflix] Update tests 2016-07-26 21:44:53 +07:00
Yen Chi Hsuan
35f6e0ff36 [mtv.de] Skip 2 geo-restricted tests 2016-07-26 13:19:47 +08:00
Yen Chi Hsuan
326fa4e6e5 [generic] Skip an invalid test 2016-07-26 13:16:04 +08:00
Yen Chi Hsuan
c74299a72c [cmt] Detect unavailable videos and update _TESTS 2016-07-26 13:13:14 +08:00
Yen Chi Hsuan
10a1bb3a78 [mtv] Fix for videos with missing bitrates 2016-07-26 13:12:24 +08:00
Yen Chi Hsuan
4d3e543c73 Update extractors.py 2016-07-26 11:17:28 +08:00
Yen Chi Hsuan
05d1e7aaa9 [generic] Fix an MTV test and another test that breaks nosetests 2016-07-26 11:11:36 +08:00
Yen Chi Hsuan
a3aa814b77 Update _TESTS for MTV sites 2016-07-26 11:10:41 +08:00
Yen Chi Hsuan
5c32a77cad [nextmovie] Remove extractor
This domain name now redirects to mtv.com
2016-07-26 11:08:55 +08:00
Yen Chi Hsuan
14a28e705b [test/test_all_urls] Remove *.cc.com tests 2016-07-26 11:08:09 +08:00
Yen Chi Hsuan
cc99d4f826 [comedycentral] Remove IEs for *.cc.com except tosh.cc.com
All other subdomains now redirects to cc.com/* URLs
2016-07-26 11:06:50 +08:00
Yen Chi Hsuan
712c7530ff [mtv] Extract more metadata and more
1. Remove MTVIggyIE. All www.mtviggy.com URLs now redirects to
   www.mtv.com
2. Fix MTVDEIE
3. Return multiple URLs from _transform_rtmp_url. This is for
   tosh.cc.com
2016-07-26 11:03:43 +08:00
Sergey M․
0a147785e8 [camdemy] Extract duration properly 2016-07-25 23:03:58 +07:00
Sergey M․
59eaf69e33 [camdemy] Fix camdemy 2016-07-25 23:03:43 +07:00
Sergey M․
e8be2943a7 [smotri] Modernize, make more robust and fix tests 2016-07-24 18:38:18 +07:00
65 changed files with 2097 additions and 1222 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.07.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.07.24**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.07*. 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 **2016.08.07**
### 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 2016.07.24
[debug] youtube-dl version 2016.08.07
[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: {}

333
ChangeLog Normal file
View File

@@ -0,0 +1,333 @@
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)

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

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..."

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))

View File

@@ -142,7 +142,7 @@
- **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**
@@ -182,6 +182,7 @@
- **DigitallySpeaking**
- **Digiteka**
- **Discovery**
- **DiscoveryGo**
- **Dotsub**
- **DouyuTV**: 斗鱼
- **DPlay**
@@ -248,7 +249,6 @@
- **FunnyOrDie**
- **Fusion**
- **GameInformer**
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **Gamersyde**
@@ -401,7 +401,6 @@
- **MSN**
- **MTV**
- **mtv.de**
- **mtviggy.com**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
@@ -417,7 +416,8 @@
- **MyVidster**
- **n-tv.de**
- **natgeo**
- **natgeo:channel**
- **natgeo:episodeguide**
- **natgeo:video**
- **Naver**
- **NBA**
- **NBC**
@@ -441,7 +441,6 @@
- **Newstube**
- **NextMedia**: 蘋果日報
- **NextMediaActionNews**: 蘋果日報 - 動新聞
- **nextmovie.com**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **nhl.com**
@@ -520,6 +519,7 @@
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **Pokemon**
- **PolskieRadio**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
@@ -699,6 +699,7 @@
- **TNAFlix**
- **TNAFlixNetworkEmbed**
- **toggle**
- **Tosh**: Tosh.0
- **tou.tv**
- **Toypics**: Toypics user profile
- **ToypicsUser**: Toypics user profile
@@ -728,6 +729,7 @@
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvland.com**
- **tvp**: Telewizja Polska
- **tvp:embed**: Telewizja Polska
- **tvp:series**
- **TVPlay**: TV3Play and related services
- **Tweakers**
@@ -807,6 +809,7 @@
- **vk:wallpost**
- **vlive**
- **Vodlocker**
- **VODPlatform**
- **VoiceRepublic**
- **VoxMedia**
- **Vporn**

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

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'])

View File

@@ -42,6 +42,7 @@ from youtube_dl.utils import (
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
parse_age_limit,
parse_duration,
parse_filesize,
parse_count,
@@ -308,6 +309,7 @@ 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 +433,20 @@ 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)

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('--username' in serr)
self.assertTrue('johnsmith' not in serr)
self.assertTrue('--password' in serr)
self.assertTrue('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('-u' in serr)
self.assertTrue('johnsmith' not in serr)
self.assertTrue('-p' in serr)
self.assertTrue('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('--username' in serr)
self.assertTrue('johnsmith' not in serr)
self.assertTrue('--password' in serr)
self.assertTrue('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('-u' in serr)
self.assertTrue('johnsmith' not in serr)
self.assertTrue('-p' in serr)
self.assertTrue('secret' not in serr)
if __name__ == '__main__':
unittest.main()

View File

@@ -83,6 +83,20 @@ 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,
}
}]
@staticmethod
@@ -133,20 +147,26 @@ 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:
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:
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:
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]
episode_id = video_info['id']
episode_title = video_info['title']

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

View File

@@ -73,6 +73,7 @@ class ARDMediathekIE(InfoExtractor):
'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
'duration': 3287,
},
'skip': 'Video is no longer available',
}]
def _extract_media_info(self, media_info_url, webpage, video_id):

View File

@@ -5,11 +5,13 @@ import re
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 (
@@ -229,51 +231,6 @@ 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, ext='mp4', entry_protocol='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)
@@ -294,46 +251,6 @@ 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:
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):
@@ -379,13 +296,87 @@ 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
@@ -589,7 +580,7 @@ class BBCIE(BBCCoUkIE):
'info_dict': {
'id': '150615_telabyad_kentin_cogu',
'ext': 'mp4',
'title': "Tel Abyad'da IŞİD bayrağı indirildi YPG bayrağı çekildi",
'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
'timestamp': 1434397334,
'upload_date': '20150615',
@@ -654,6 +645,23 @@ 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',
@@ -820,13 +828,19 @@ 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:
for key in ('progressiveDownload', 'streaming'):
entry = None
for key in ('streaming', 'progressiveDownload'):
playlist_url = playlist.get('%sUrl' % key)
if not playlist_url:
continue
try:
entries.append(self._extract_from_playlist_sxml(
playlist_url, playlist_id, timestamp))
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.
@@ -834,6 +848,9 @@ class BBCIE(BBCCoUkIE):
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)
@@ -866,6 +883,50 @@ 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),
@@ -883,7 +944,7 @@ 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)

View File

@@ -12,7 +12,7 @@ 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',
'md5': 'dc1b4aebb46e3a7077ecc0d9f43f61e3',
'info_dict': {
'id': '16537',
'ext': 'mp4',
@@ -26,7 +26,7 @@ class BigflixIE(InfoExtractor):
'id': '16070',
'ext': 'mp4',
'title': 'Madarasapatinam',
'description': 'md5:63b9b8ed79189c6f0418c26d9a3452ca',
'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
'formats': 'mincount:2',
},
'params': {

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 Zealands 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(

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,
}

View File

@@ -4,9 +4,11 @@ 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,
)
@@ -27,7 +29,20 @@ class CBCIE(InfoExtractor):
},
'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': {
@@ -83,9 +98,15 @@ 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)]

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):
@@ -71,10 +69,7 @@ class CBSLocalIE(AnvatoIE):
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,

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)

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',
@@ -35,244 +27,43 @@ 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']
_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),
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('shortname'):
return self.url_result('http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes')
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')
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]
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])]
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,
}
@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
class ComedyCentralTVIE(MTVServicesInfoExtractor):
@@ -306,3 +97,22 @@ class ComedyCentralTVIE(MTVServicesInfoExtractor):
webpage, 'mrss url', group='url')
return self._get_videos_info_from_url(mrss_url, video_id)
class ComedyCentralShortnameIE(InfoExtractor):
_VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
_TESTS = [{
'url': ':tds',
'only_matching': True,
}, {
'url': ':thedailyshow',
'only_matching': True,
}]
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])

View File

@@ -727,9 +727,14 @@ 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)
@@ -823,41 +828,47 @@ 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 +922,8 @@ 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 +1140,7 @@ 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',
}
@@ -1786,7 +1798,7 @@ 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)

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 +74,92 @@ 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) 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':

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': {
@@ -51,6 +51,12 @@ class CWTVIE(InfoExtractor):
}, {
'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):

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:

View File

@@ -0,0 +1,98 @@
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,
)
class DiscoveryGoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?discoverygo\.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['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,
}

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)

View File

@@ -159,8 +159,9 @@ from .coub import CoubIE
from .collegerama import CollegeRamaIE
from .comedycentral import (
ComedyCentralIE,
ComedyCentralShowsIE,
ComedyCentralShortnameIE,
ComedyCentralTVIE,
ToshIE,
)
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
@@ -220,6 +221,7 @@ 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 (
@@ -289,7 +291,6 @@ from .funimation import FunimationIE
from .funnyordie import FunnyOrDieIE
from .fusion import FusionIE
from .gameinformer import GameInformerIE
from .gamekings import GamekingsIE
from .gameone import (
GameOneIE,
GameOnePlaylistIE,
@@ -480,7 +481,6 @@ from .msn import MSNIE
from .mtv import (
MTVIE,
MTVServicesEmbeddedIE,
MTVIggyIE,
MTVDEIE,
)
from .muenchentv import MuenchenTVIE
@@ -492,8 +492,9 @@ 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
@@ -530,7 +531,6 @@ from .nextmedia import (
NextMediaActionNewsIE,
AppleDailyIE,
)
from .nextmovie import NextMovieIE
from .nfb import NFBIE
from .nfl import NFLIE
from .nhl import (
@@ -637,6 +637,7 @@ from .pluralsight import (
PluralsightCourseIE,
)
from .podomatic import PodomaticIE
from .pokemon import PokemonIE
from .polskieradio import PolskieRadioIE
from .porn91 import Porn91IE
from .pornhd import PornHdIE
@@ -893,6 +894,7 @@ from .tvc import (
from .tvigle import TvigleIE
from .tvland import TVLandIE
from .tvp import (
TVPEmbedIE,
TVPIE,
TVPSeriesIE,
)
@@ -1006,6 +1008,7 @@ 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

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)

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, fatal=False)
title = json_ld.get('title') or flipagram['captionText']
description = json_ld.get('description') or flipagram.get('captionText')

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,
}

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$',
'uploader_id': 'UCJugRGo4STYMeFr5RoOShtQ',
'uploader': 'Gamekings Vault',
'upload_date': '20151123',
},
'add_ie': ['Youtube'],
}, {
# vimeo video
'url': 'http://www.gamekings.nl/videos/the-legend-of-zelda-majoras-mask/',
'md5': '12bf04dfd238e70058046937657ea68d',
'info_dict': {
'id': 'the-legend-of-zelda-majoras-mask',
'ext': 'mp4',
'title': 'The Legend of Zelda: Majoras Mask',
'description': 'md5:9917825fe0e9f4057601fe1e38860de3',
'thumbnail': 're:^https?://.*\.jpg$',
},
}, {
'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,
}

View File

@@ -71,6 +71,7 @@ from .vessel import VesselIE
from .kaltura import KalturaIE
from .eagleplatform import EaglePlatformIE
from .facebook import FacebookIE
from .soundcloud import SoundcloudIE
class GenericIE(InfoExtractor):
@@ -474,7 +475,7 @@ 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': {
@@ -641,6 +642,8 @@ 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="">
@@ -782,6 +785,15 @@ 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',
@@ -857,6 +869,7 @@ 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
{
@@ -1996,12 +2009,9 @@ 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)
@@ -2197,6 +2207,14 @@ 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=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
# Look for Instagram embeds
instagram_embed_url = InstagramIE._extract_embed_url(webpage)
if instagram_embed_url is not None:
@@ -2223,7 +2241,7 @@ class GenericIE(InfoExtractor):
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default=None, expected_type='VideoObject')
webpage, video_id, fatal=False, expected_type='VideoObject')
if json_ld and json_ld.get('url'):
info_dict.update({
'title': video_title or info_dict['title'],

View File

@@ -36,7 +36,6 @@ class InstagramIE(InfoExtractor):
'info_dict': {
'id': 'BA-pQFBG8HZ',
'ext': 'mp4',
'uploader_id': 'britneyspears',
'title': 'Video by britneyspears',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1453760977,

View File

@@ -4,10 +4,12 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
mimetype2ext,
)
@@ -28,74 +30,84 @@ class JWPlatformBaseIE(InfoExtractor):
return self._parse_jwplayer_data(
jwplayer_data, video_id, *args, **kwargs)
def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None):
def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
# JWPlayer backward compatibility: flattened playlists
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
if 'playlist' not in jwplayer_data:
jwplayer_data = {'playlist': [jwplayer_data]}
video_data = jwplayer_data['playlist'][0]
entries = []
for video_data in jwplayer_data['playlist']:
# JWPlayer backward compatibility: flattened sources
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
if 'sources' not in video_data:
video_data['sources'] = [video_data]
# JWPlayer backward compatibility: flattened sources
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/playlist/item.js#L29-L35
if 'sources' not in video_data:
video_data['sources'] = [video_data]
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
source_type = source.get('type') or ''
if source_type in ('application/vnd.apple.mpegurl', 'hls') or determine_ext(source_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
elif source_type.startswith('audio'):
formats.append({
'url': source_url,
'vcodec': 'none',
})
else:
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv',
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
rtmp_url_parts = re.split(
r'((?:mp4|mp3|flv):)', source_url, 1)
if len(rtmp_url_parts) == 3:
rtmp_url, prefix, play_path = rtmp_url_parts
a_format.update({
'url': rtmp_url,
'play_path': prefix + play_path,
})
if rtmp_params:
a_format.update(rtmp_params)
formats.append(a_format)
self._sort_formats(formats)
subtitles = {}
tracks = video_data.get('tracks')
if tracks and isinstance(tracks, list):
for track in tracks:
if track.get('file') and track.get('kind') == 'captions':
subtitles.setdefault(track.get('label') or 'en', []).append({
'url': self._proto_relative_url(track['file'])
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
# https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
formats.append({
'url': source_url,
'vcodec': 'none',
'ext': ext,
})
else:
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
'height': int_or_none(source.get('height')),
'ext': ext,
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv',
return {
'id': video_id,
'title': video_data['title'] if require_title else video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': self._proto_relative_url(video_data.get('image')),
'timestamp': int_or_none(video_data.get('pubdate')),
'duration': float_or_none(jwplayer_data.get('duration')),
'subtitles': subtitles,
'formats': formats,
}
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
rtmp_url_parts = re.split(
r'((?:mp4|mp3|flv):)', source_url, 1)
if len(rtmp_url_parts) == 3:
rtmp_url, prefix, play_path = rtmp_url_parts
a_format.update({
'url': rtmp_url,
'play_path': prefix + play_path,
})
if rtmp_params:
a_format.update(rtmp_params)
formats.append(a_format)
self._sort_formats(formats)
subtitles = {}
tracks = video_data.get('tracks')
if tracks and isinstance(tracks, list):
for track in tracks:
if track.get('file') and track.get('kind') == 'captions':
subtitles.setdefault(track.get('label') or 'en', []).append({
'url': self._proto_relative_url(track['file'])
})
entries.append({
'id': video_id,
'title': video_data['title'] if require_title else video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': self._proto_relative_url(video_data.get('image')),
'timestamp': int_or_none(video_data.get('pubdate')),
'duration': float_or_none(jwplayer_data.get('duration')),
'subtitles': subtitles,
'formats': formats,
})
if len(entries) == 1:
return entries[0]
else:
return self.playlist_result(entries)
class JWPlatformIE(JWPlatformBaseIE):

View File

@@ -62,6 +62,11 @@ class KalturaIE(InfoExtractor):
{
'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342',
'only_matching': True,
},
{
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
}
]
@@ -130,7 +135,6 @@ class KalturaIE(InfoExtractor):
video_id, actions, service_url, note='Downloading Kaltura signature')['ks']
def _get_video_info(self, video_id, partner_id, service_url=None):
signature = self._get_kaltura_signature(video_id, partner_id, service_url)
actions = [
{
'action': 'null',
@@ -138,18 +142,30 @@ class KalturaIE(InfoExtractor):
'clientTag': 'kdp:v3.8.5',
'format': 1, # JSON, 2 = XML, 3 = PHP
'service': 'multirequest',
'ks': signature,
},
{
'expiry': 86400,
'service': 'session',
'action': 'startWidgetSession',
'widgetId': '_%s' % partner_id,
},
{
'action': 'get',
'entryId': video_id,
'service': 'baseentry',
'version': '-1',
'ks': '{1:result:ks}',
},
{
'action': 'getbyentryid',
'entryId': video_id,
'service': 'flavorAsset',
'ks': '{1:result:ks}',
},
{
'action': 'list',
'filter:entryIdEqual': video_id,
'service': 'caption_captionasset',
'ks': '{1:result:ks}',
},
]
return self._kaltura_api_call(
@@ -161,8 +177,9 @@ class KalturaIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
partner_id, entry_id = mobj.group('partner_id', 'id')
ks = None
captions = None
if partner_id and entry_id:
info, flavor_assets = self._get_video_info(entry_id, partner_id, smuggled_data.get('service_url'))
_, info, flavor_assets, captions = self._get_video_info(entry_id, partner_id, smuggled_data.get('service_url'))
else:
path, query = mobj.group('path', 'query')
if not path and not query:
@@ -181,7 +198,7 @@ class KalturaIE(InfoExtractor):
raise ExtractorError('Invalid URL', expected=True)
if 'entry_id' in params:
entry_id = params['entry_id'][0]
info, flavor_assets = self._get_video_info(entry_id, partner_id)
_, info, flavor_assets, captions = self._get_video_info(entry_id, partner_id)
elif 'uiconf_id' in params and 'flashvars[referenceId]' in params:
reference_id = params['flashvars[referenceId]'][0]
webpage = self._download_webpage(url, reference_id)
@@ -217,7 +234,7 @@ class KalturaIE(InfoExtractor):
formats = []
for f in flavor_assets:
# Continue if asset is not ready
if f['status'] != 2:
if f.get('status') != 2:
continue
video_url = sign_url(
'%s/flavorId/%s' % (data_url, f['id']))
@@ -240,13 +257,24 @@ class KalturaIE(InfoExtractor):
m3u8_url, entry_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
self._check_formats(formats, entry_id)
self._sort_formats(formats)
subtitles = {}
if captions:
for caption in captions.get('objects', []):
# Continue if caption is not ready
if f.get('status') != 2:
continue
subtitles.setdefault(caption.get('languageCode') or caption.get('language'), []).append({
'url': '%s/api_v3/service/caption_captionasset/action/serve/captionAssetId/%s' % (self._SERVICE_URL, caption['id']),
'ext': caption.get('fileExt'),
})
return {
'id': entry_id,
'title': info['name'],
'formats': formats,
'subtitles': subtitles,
'description': clean_html(info.get('description')),
'thumbnail': info.get('thumbnailUrl'),
'duration': info.get('duration'),

View File

@@ -37,11 +37,12 @@ class LimelightBaseIE(InfoExtractor):
for stream in streams:
stream_url = stream.get('url')
if not stream_url:
if not stream_url or stream.get('drmProtected'):
continue
if '.f4m' in stream_url:
ext = determine_ext(stream_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
stream_url, video_id, fatal=False))
stream_url, video_id, f4m_id='hds', fatal=False))
else:
fmt = {
'url': stream_url,
@@ -50,13 +51,19 @@ class LimelightBaseIE(InfoExtractor):
'fps': float_or_none(stream.get('videoFrameRate')),
'width': int_or_none(stream.get('videoWidthInPixels')),
'height': int_or_none(stream.get('videoHeightInPixels')),
'ext': determine_ext(stream_url)
'ext': ext,
}
rtmp = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
if rtmp:
format_id = 'rtmp'
if stream.get('videoBitRate'):
format_id += '-%d' % int_or_none(stream['videoBitRate'])
http_fmt = fmt.copy()
http_fmt.update({
'url': 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:]),
'format_id': format_id.replace('rtmp', 'http'),
})
formats.append(http_fmt)
fmt.update({
'url': rtmp.group('url'),
'play_path': rtmp.group('playpath'),
@@ -68,18 +75,23 @@ class LimelightBaseIE(InfoExtractor):
for mobile_url in mobile_urls:
media_url = mobile_url.get('mobileUrl')
if not media_url:
continue
format_id = mobile_url.get('targetMediaPlatform')
if determine_ext(media_url) == 'm3u8':
if not media_url or format_id == 'Widevine':
continue
ext = determine_ext(media_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
stream_url, video_id, f4m_id=format_id, fatal=False))
else:
formats.append({
'url': media_url,
'format_id': format_id,
'preference': -1,
'ext': ext,
})
self._sort_formats(formats)
@@ -145,7 +157,7 @@ class LimelightMediaIE(LimelightBaseIE):
'url': 'http://link.videoplatform.limelight.com/media/?mediaId=3ffd040b522b4485b6d84effc750cd86',
'info_dict': {
'id': '3ffd040b522b4485b6d84effc750cd86',
'ext': 'flv',
'ext': 'mp4',
'title': 'HaP and the HB Prince Trailer',
'description': 'md5:8005b944181778e313d95c1237ddb640',
'thumbnail': 're:^https?://.*\.jpeg$',
@@ -154,27 +166,23 @@ class LimelightMediaIE(LimelightBaseIE):
'upload_date': '20090604',
},
'params': {
# rtmp download
# m3u8 download
'skip_download': True,
},
}, {
# video with subtitles
'url': 'limelight:media:a3e00274d4564ec4a9b29b9466432335',
'md5': '2fa3bad9ac321e23860ca23bc2c69e3d',
'info_dict': {
'id': 'a3e00274d4564ec4a9b29b9466432335',
'ext': 'flv',
'ext': 'mp4',
'title': '3Play Media Overview Video',
'description': '',
'thumbnail': 're:^https?://.*\.jpeg$',
'duration': 78.101,
'timestamp': 1338929955,
'upload_date': '20120605',
'subtitles': 'mincount:9',
},
'params': {
# rtmp download
'skip_download': True,
},
}, {
'url': 'https://assets.delvenetworks.com/player/loader.swf?mediaId=8018a574f08d416e95ceaccae4ba0452',
'only_matching': True,

View File

@@ -9,7 +9,7 @@ class MGTVIE(InfoExtractor):
_VALID_URL = r'https?://www\.mgtv\.com/v/(?:[^/]+/)*(?P<id>\d+)\.html'
IE_DESC = '芒果TV'
_TEST = {
_TESTS = [{
'url': 'http://www.mgtv.com/v/1/290525/f/3116640.html',
'md5': '1bdadcf760a0b90946ca68ee9a2db41a',
'info_dict': {
@@ -20,7 +20,11 @@ class MGTVIE(InfoExtractor):
'duration': 7461,
'thumbnail': 're:^https?://.*\.jpg$',
},
}
}, {
# no tbr extracted from stream_url
'url': 'http://www.mgtv.com/v/1/1/f/3324755.html',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -41,7 +45,8 @@ class MGTVIE(InfoExtractor):
def extract_format(stream_url, format_id, idx, query={}):
format_info = self._download_json(
stream_url, video_id,
note='Download video info for format %s' % format_id or '#%d' % idx, query=query)
note='Download video info for format %s' % (format_id or '#%d' % idx),
query=query)
return {
'format_id': format_id,
'url': format_info['info'],

View File

@@ -16,6 +16,7 @@ from ..utils import (
HEADRequest,
sanitized_Request,
strip_or_none,
timeconvert,
unescapeHTML,
url_basename,
RegexNotFoundError,
@@ -36,13 +37,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
return uri.split(':')[-1]
# This was originally implemented for ComedyCentral, but it also works here
@staticmethod
def _transform_rtmp_url(rtmp_video_url):
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
m = re.match(r'^rtmpe?://.*?/(?P<finalid>gsp\..+?/.*)$', rtmp_video_url)
if not m:
return rtmp_video_url
return {'rtmp': rtmp_video_url}
base = 'http://viacommtvstrmfs.fplive.net/'
return base + m.group('finalid')
return {'http': base + m.group('finalid')}
def _get_feed_url(self, uri):
return self._FEED_URL
@@ -86,14 +87,14 @@ class MTVServicesInfoExtractor(InfoExtractor):
rtmp_video_url = rendition.find('./src').text
if rtmp_video_url.endswith('siteunavail.png'):
continue
new_url = self._transform_rtmp_url(rtmp_video_url)
formats.append({
new_urls = self._transform_rtmp_url(rtmp_video_url)
formats.extend([{
'ext': 'flv' if new_url.startswith('rtmp') else ext,
'url': new_url,
'format_id': rendition.get('bitrate'),
'format_id': '-'.join(filter(None, [kind, rendition.get('bitrate')])),
'width': int(rendition.get('width')),
'height': int(rendition.get('height')),
})
} for kind, new_url in new_urls.items()])
except (KeyError, TypeError):
raise ExtractorError('Invalid rendition field.')
self._sort_formats(formats)
@@ -136,6 +137,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
description = strip_or_none(xpath_text(itemdoc, 'description'))
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
title_el = None
if title_el is None:
title_el = find_xpath_attr(
@@ -168,6 +171,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
'thumbnail': self._get_thumbnail_url(uri, itemdoc),
'description': description,
'duration': float_or_none(content_el.attrib.get('duration')),
'timestamp': timestamp,
}
def _get_feed_query(self, uri):
@@ -186,8 +190,13 @@ class MTVServicesInfoExtractor(InfoExtractor):
idoc = self._download_xml(
url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
title = xpath_text(idoc, './channel/title')
description = xpath_text(idoc, './channel/description')
return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')])
[self._get_video_info(item) for item in idoc.findall('.//item')],
playlist_title=title, playlist_description=description)
def _extract_mgid(self, webpage):
try:
@@ -233,6 +242,8 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
'ext': 'mp4',
'title': 'Peter Dinklage Sums Up \'Game Of Thrones\' In 45 Seconds',
'description': '"Sexy sexy sexy, stabby stabby stabby, beautiful language," says Peter Dinklage as he tries summarizing "Game of Thrones" in under a minute.',
'timestamp': 1400126400,
'upload_date': '20140515',
},
}
@@ -275,6 +286,8 @@ class MTVIE(MTVServicesInfoExtractor):
'ext': 'mp4',
'title': 'Taylor Swift - "Ours (VH1 Storytellers)"',
'description': 'Album: Taylor Swift performs "Ours" for VH1 Storytellers at Harvey Mudd College.',
'timestamp': 1352610000,
'upload_date': '20121111',
},
},
]
@@ -301,20 +314,6 @@ class MTVIE(MTVServicesInfoExtractor):
return self._get_videos_info(uri)
class MTVIggyIE(MTVServicesInfoExtractor):
IE_NAME = 'mtviggy.com'
_VALID_URL = r'https?://www\.mtviggy\.com/videos/.+'
_TEST = {
'url': 'http://www.mtviggy.com/videos/arcade-fire-behind-the-scenes-at-the-biggest-music-experiment-yet/',
'info_dict': {
'id': '984696',
'ext': 'mp4',
'title': 'Arcade Fire: Behind the Scenes at the Biggest Music Experiment Yet',
}
}
_FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/'
class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de'
_VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
@@ -322,7 +321,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
'info_dict': {
'id': 'music_video-a50bc5f0b3aa4b3190aa',
'ext': 'mp4',
'ext': 'flv',
'title': 'MusicVideo_cro-traum',
'description': 'Cro - Traum',
},
@@ -330,20 +329,21 @@ class MTVDEIE(MTVServicesInfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'Blocked at Travis CI',
}, {
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
'info_dict': {
'id': 'local_playlist-f5ae778b9832cc837189',
'ext': 'mp4',
'ext': 'flv',
'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
},
'params': {
# rtmp download
'skip_download': True,
},
'skip': 'Blocked at Travis CI',
}, {
# single video in pagePlaylist with different id
'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344',
@@ -355,6 +355,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
# rtmp download
'skip_download': True,
},
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
}]
def _real_extract(self, url):
@@ -367,11 +368,14 @@ class MTVDEIE(MTVServicesInfoExtractor):
r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
video_id)
def _mrss_url(item):
return item['mrss'] + item.get('mrssvars', '')
# news pages contain single video in playlist with different id
if len(playlist) == 1:
return self._get_videos_info_from_url(playlist[0]['mrss'], video_id)
return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
for item in playlist:
item_id = item.get('id')
if item_id and compat_str(item_id) == video_id:
return self._get_videos_info_from_url(item['mrss'], video_id)
return self._get_videos_info_from_url(_mrss_url(item), video_id)

View File

@@ -1,16 +1,19 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .theplatform import ThePlatformIE
from ..utils import (
smuggle_url,
url_basename,
update_url_query,
get_element_by_class,
)
class NationalGeographicIE(InfoExtractor):
IE_NAME = 'natgeo'
class NationalGeographicVideoIE(InfoExtractor):
IE_NAME = 'natgeo:video'
_VALID_URL = r'https?://video\.nationalgeographic\.com/.*?'
_TESTS = [
@@ -62,16 +65,16 @@ class NationalGeographicIE(InfoExtractor):
}
class NationalGeographicChannelIE(ThePlatformIE):
IE_NAME = 'natgeo:channel'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/videos/(?P<id>[^/?]+)'
class NationalGeographicIE(ThePlatformIE):
IE_NAME = 'natgeo'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
_TESTS = [
{
'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/videos/uncovering-a-universal-knowledge/',
'md5': '518c9aa655686cf81493af5cc21e2a04',
'info_dict': {
'id': 'nB5vIAfmyllm',
'id': 'vKInpacll2pC',
'ext': 'mp4',
'title': 'Uncovering a Universal Knowledge',
'description': 'md5:1a89148475bf931b3661fcd6ddb2ae3a',
@@ -85,7 +88,7 @@ class NationalGeographicChannelIE(ThePlatformIE):
'url': 'http://channel.nationalgeographic.com/wild/destination-wild/videos/the-stunning-red-bird-of-paradise/',
'md5': 'c4912f656b4cbe58f3e000c489360989',
'info_dict': {
'id': '3TmMv9OvGwIR',
'id': 'Pok5lWCkiEFA',
'ext': 'mp4',
'title': 'The Stunning Red Bird of Paradise',
'description': 'md5:7bc8cd1da29686be4d17ad1230f0140c',
@@ -95,6 +98,10 @@ class NationalGeographicChannelIE(ThePlatformIE):
},
'add_ie': ['ThePlatform'],
},
{
'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episodes/the-power-of-miracles/',
'only_matching': True,
}
]
def _real_extract(self, url):
@@ -122,3 +129,40 @@ class NationalGeographicChannelIE(ThePlatformIE):
{'force_smil_url': True}),
'display_id': display_id,
}
class NationalGeographicEpisodeGuideIE(ThePlatformIE):
IE_NAME = 'natgeo:episodeguide'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
_TESTS = [
{
'url': 'http://channel.nationalgeographic.com/the-story-of-god-with-morgan-freeman/episode-guide/',
'info_dict': {
'id': 'the-story-of-god-with-morgan-freeman-season-1',
'title': 'The Story of God with Morgan Freeman - Season 1',
},
'playlist_mincount': 6,
},
{
'url': 'http://channel.nationalgeographic.com/underworld-inc/episode-guide/?s=2',
'info_dict': {
'id': 'underworld-inc-season-2',
'title': 'Underworld, Inc. - Season 2',
},
'playlist_mincount': 7,
},
]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
show = get_element_by_class('show', webpage)
selected_season = self._search_regex(
r'<div[^>]+class="select-seasons[^"]*".*?<a[^>]*>(.*?)</a>',
webpage, 'selected season')
entries = [
self.url_result(self._proto_relative_url(entry_url), 'NationalGeographic')
for entry_url in re.findall('(?s)<div[^>]+class="col-inner"[^>]*?>.*?<a[^>]+href="([^"]+)"', webpage)]
return self.playlist_result(
entries, '%s-%s' % (display_id, selected_season.lower().replace(' ', '-')),
'%s - %s' % (show, selected_season))

View File

@@ -4,12 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
ExtractorError,
int_or_none,
update_url_query,
)
@@ -51,48 +49,74 @@ class NaverIE(InfoExtractor):
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('couldn\'t extract vid and key')
vid = m_id.group(1)
key = m_id.group(2)
query = compat_urllib_parse_urlencode({'vid': vid, 'inKey': key, })
query_urls = compat_urllib_parse_urlencode({
'masterVid': vid,
'protocol': 'p2p',
'inKey': key,
})
info = self._download_xml(
'http://serviceapi.rmcnmv.naver.com/flash/videoInfo.nhn?' + query,
video_id, 'Downloading video info')
urls = self._download_xml(
'http://serviceapi.rmcnmv.naver.com/flash/playableEncodingOption.nhn?' + query_urls,
video_id, 'Downloading video formats info')
video_data = self._download_json(
'http://play.rmcnmv.naver.com/vod/play/v2.0/' + m_id.group(1),
video_id, query={
'key': m_id.group(2),
})
meta = video_data['meta']
title = meta['subject']
formats = []
for format_el in urls.findall('EncodingOptions/EncodingOption'):
domain = format_el.find('Domain').text
uri = format_el.find('uri').text
f = {
'url': compat_urlparse.urljoin(domain, uri),
'ext': 'mp4',
'width': int(format_el.find('width').text),
'height': int(format_el.find('height').text),
}
if domain.startswith('rtmp'):
# urlparse does not support custom schemes
# https://bugs.python.org/issue18828
f.update({
'url': domain + uri,
'ext': 'flv',
'rtmp_protocol': '1', # rtmpt
def extract_formats(streams, stream_type, query={}):
for stream in streams:
stream_url = stream.get('source')
if not stream_url:
continue
stream_url = update_url_query(stream_url, query)
encoding_option = stream.get('encodingOption', {})
bitrate = stream.get('bitrate', {})
formats.append({
'format_id': '%s_%s' % (stream.get('type') or stream_type, encoding_option.get('id') or encoding_option.get('name')),
'url': stream_url,
'width': int_or_none(encoding_option.get('width')),
'height': int_or_none(encoding_option.get('height')),
'vbr': int_or_none(bitrate.get('video')),
'abr': int_or_none(bitrate.get('audio')),
'filesize': int_or_none(stream.get('size')),
'protocol': 'm3u8_native' if stream_type == 'HLS' else None,
})
formats.append(f)
extract_formats(video_data.get('videos', {}).get('list', []), 'H264')
for stream_set in video_data.get('streams', []):
query = {}
for param in stream_set.get('keys', []):
query[param['name']] = param['value']
stream_type = stream_set.get('type')
videos = stream_set.get('videos')
if videos:
extract_formats(videos, stream_type, query)
elif stream_type == 'HLS':
stream_url = stream_set.get('source')
if not stream_url:
continue
formats.extend(self._extract_m3u8_formats(
update_url_query(stream_url, query), video_id,
'mp4', 'm3u8_native', m3u8_id=stream_type, fatal=False))
self._sort_formats(formats)
subtitles = {}
for caption in video_data.get('captions', {}).get('list', []):
caption_url = caption.get('source')
if not caption_url:
continue
subtitles.setdefault(caption.get('language') or caption.get('locale'), []).append({
'url': caption_url,
})
upload_date = self._search_regex(
r'<span[^>]+class="date".*?(\d{4}\.\d{2}\.\d{2})',
webpage, 'upload date', fatal=False)
if upload_date:
upload_date = upload_date.replace('.', '')
return {
'id': video_id,
'title': info.find('Subject').text,
'title': title,
'formats': formats,
'subtitles': subtitles,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'upload_date': info.find('WriteDate').text.replace('.', ''),
'view_count': int(info.find('PlayCount').text),
'thumbnail': meta.get('cover', {}).get('source') or self._og_search_thumbnail(webpage),
'view_count': int_or_none(meta.get('count')),
'upload_date': upload_date,
}

View File

@@ -1,30 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from ..compat import compat_urllib_parse_urlencode
class NextMovieIE(MTVServicesInfoExtractor):
IE_NAME = 'nextmovie.com'
_VALID_URL = r'https?://(?:www\.)?nextmovie\.com/shows/[^/]+/\d{4}-\d{2}-\d{2}/(?P<id>[^/?#]+)'
_FEED_URL = 'http://lite.dextr.mtvi.com/service1/dispatch.htm'
_TESTS = [{
'url': 'http://www.nextmovie.com/shows/exclusives/2013-03-10/mgid:uma:videolist:nextmovie.com:1715019/',
'md5': '09a9199f2f11f10107d04fcb153218aa',
'info_dict': {
'id': '961726',
'ext': 'mp4',
'title': 'The Muppets\' Gravity',
},
}]
def _get_feed_query(self, uri):
return compat_urllib_parse_urlencode({
'feed': '1505',
'mgid': uri,
})
def _real_extract(self, url):
mgid = self._match_id(url)
return self._get_videos_info(mgid)

View File

@@ -7,6 +7,7 @@ from ..utils import update_url_query
class NickIE(MTVServicesInfoExtractor):
# None of videos on the website are still alive?
IE_NAME = 'nick.com'
_VALID_URL = r'https?://(?:www\.)?nick(?:jr)?\.com/(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'

View File

@@ -11,70 +11,64 @@ from ..utils import (
class NTVRuIE(InfoExtractor):
IE_NAME = 'ntv.ru'
_VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?P<id>.+)'
_VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [
{
'url': 'http://www.ntv.ru/novosti/863142/',
'md5': 'ba7ea172a91cb83eb734cad18c10e723',
'info_dict': {
'id': '746000',
'ext': 'mp4',
'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
'thumbnail': 're:^http://.*\.jpg',
'duration': 136,
},
_TESTS = [{
'url': 'http://www.ntv.ru/novosti/863142/',
'md5': 'ba7ea172a91cb83eb734cad18c10e723',
'info_dict': {
'id': '746000',
'ext': 'mp4',
'title': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
'description': 'Командующий Черноморским флотом провел переговоры в штабе ВМС Украины',
'thumbnail': 're:^http://.*\.jpg',
'duration': 136,
},
{
'url': 'http://www.ntv.ru/video/novosti/750370/',
'md5': 'adecff79691b4d71e25220a191477124',
'info_dict': {
'id': '750370',
'ext': 'mp4',
'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'thumbnail': 're:^http://.*\.jpg',
'duration': 172,
},
}, {
'url': 'http://www.ntv.ru/video/novosti/750370/',
'md5': 'adecff79691b4d71e25220a191477124',
'info_dict': {
'id': '750370',
'ext': 'mp4',
'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'thumbnail': 're:^http://.*\.jpg',
'duration': 172,
},
{
'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
'md5': '82dbd49b38e3af1d00df16acbeab260c',
'info_dict': {
'id': '747480',
'ext': 'mp4',
'title': '«Сегодня». 21 марта 2014 года. 16:00',
'description': '«Сегодня». 21 марта 2014 года. 16:00',
'thumbnail': 're:^http://.*\.jpg',
'duration': 1496,
},
}, {
'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
'md5': '82dbd49b38e3af1d00df16acbeab260c',
'info_dict': {
'id': '747480',
'ext': 'mp4',
'title': '«Сегодня». 21 марта 2014 года. 16:00',
'description': '«Сегодня». 21 марта 2014 года. 16:00',
'thumbnail': 're:^http://.*\.jpg',
'duration': 1496,
},
{
'url': 'http://www.ntv.ru/kino/Koma_film',
'md5': 'f825770930937aa7e5aca0dc0d29319a',
'info_dict': {
'id': '1007609',
'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»',
'thumbnail': 're:^http://.*\.jpg',
'duration': 5592,
},
}, {
'url': 'http://www.ntv.ru/kino/Koma_film',
'md5': 'f825770930937aa7e5aca0dc0d29319a',
'info_dict': {
'id': '1007609',
'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»',
'thumbnail': 're:^http://.*\.jpg',
'duration': 5592,
},
{
'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
'md5': '9320cd0e23f3ea59c330dc744e06ff3b',
'info_dict': {
'id': '751482',
'ext': 'mp4',
'title': '«Дело врачей»: «Деревце жизни»',
'description': '«Дело врачей»: «Деревце жизни»',
'thumbnail': 're:^http://.*\.jpg',
'duration': 2590,
},
}, {
'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
'md5': '9320cd0e23f3ea59c330dc744e06ff3b',
'info_dict': {
'id': '751482',
'ext': 'mp4',
'title': '«Дело врачей»: «Деревце жизни»',
'description': '«Дело врачей»: «Деревце жизни»',
'thumbnail': 're:^http://.*\.jpg',
'duration': 2590,
},
]
}]
_VIDEO_ID_REGEXES = [
r'<meta property="og:url" content="http://www\.ntv\.ru/video/(\d+)',
@@ -87,11 +81,21 @@ class NTVRuIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_id = self._html_search_regex(self._VIDEO_ID_REGEXES, webpage, 'video id')
video_url = self._og_search_property(
('video', 'video:iframe'), webpage, default=None)
if video_url:
video_id = self._search_regex(
r'https?://(?:www\.)?ntv\.ru/video/(?:embed/)?(\d+)',
video_url, 'video id', default=None)
if not video_id:
video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id')
player = self._download_xml(
'http://www.ntv.ru/vi%s/' % video_id,
video_id, 'Downloading video XML')
title = clean_html(xpath_text(player, './data/title', 'title', fatal=True))
description = clean_html(xpath_text(player, './data/description', 'description'))

View File

@@ -1,15 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
from __future__ import unicode_literals, division
import re
import math
from .common import InfoExtractor
from ..compat import compat_chr
from ..utils import (
decode_png,
determine_ext,
encode_base_n,
ExtractorError,
mimetype2ext,
)
@@ -41,60 +40,6 @@ class OpenloadIE(InfoExtractor):
'only_matching': True,
}]
@staticmethod
def openload_level2_debase(m):
radix, num = int(m.group(1)) + 27, int(m.group(2))
return '"' + encode_base_n(num, radix) + '"'
@classmethod
def openload_level2(cls, txt):
# The function name is ǃ \u01c3
# Using escaped unicode literals does not work in Python 3.2
return re.sub(r'ǃ\((\d+),(\d+)\)', cls.openload_level2_debase, txt, re.UNICODE).replace('"+"', '')
# Openload uses a variant of aadecode
# openload_decode and related functions are originally written by
# vitas@matfyz.cz and released with public domain
# See https://github.com/rg3/youtube-dl/issues/8489
@classmethod
def openload_decode(cls, txt):
symbol_table = [
('_', '(゚Д゚) [゚Θ゚]'),
('a', '(゚Д゚) [゚ω゚ノ]'),
('b', '(゚Д゚) [゚Θ゚ノ]'),
('c', '(゚Д゚) [\'c\']'),
('d', '(゚Д゚) [゚ー゚ノ]'),
('e', '(゚Д゚) [゚Д゚ノ]'),
('f', '(゚Д゚) [1]'),
('o', '(゚Д゚) [\'o\']'),
('u', '(o゚ー゚o)'),
('c', '(゚Д゚) [\'c\']'),
('7', '((゚ー゚) + (o^_^o))'),
('6', '((o^_^o) +(o^_^o) +(c^_^o))'),
('5', '((゚ー゚) + (゚Θ゚))'),
('4', '(-~3)'),
('3', '(-~-~1)'),
('2', '(-~1)'),
('1', '(-~0)'),
('0', '((c^_^o)-(c^_^o))'),
]
delim = '(゚Д゚)[゚ε゚]+'
ret = ''
for aachar in txt.split(delim):
for val, pat in symbol_table:
aachar = aachar.replace(pat, val)
aachar = aachar.replace('+ ', '')
m = re.match(r'^\d+', aachar)
if m:
ret += compat_chr(int(m.group(0), 8))
else:
m = re.match(r'^u([\da-f]+)', aachar)
if m:
ret += compat_chr(int(m.group(1), 16))
return cls.openload_level2(ret)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
@@ -102,29 +47,77 @@ class OpenloadIE(InfoExtractor):
if 'File not found' in webpage:
raise ExtractorError('File not found', expected=True)
code = self._search_regex(
r'</video>\s*</div>\s*<script[^>]+>[^>]+</script>\s*<script[^>]+>([^<]+)</script>',
webpage, 'JS code')
# The following extraction logic is proposed by @Belderak and @gdkchan
# and declared to be used freely in youtube-dl
# See https://github.com/rg3/youtube-dl/issues/9706
decoded = self.openload_decode(code)
numbers_js = self._download_webpage(
'https://openload.co/assets/js/obfuscator/n.js', video_id,
note='Downloading signature numbers')
signums = self._search_regex(
r'window\.signatureNumbers\s*=\s*[\'"](?P<data>[a-z]+)[\'"]',
numbers_js, 'signature numbers', group='data')
video_url = self._search_regex(
r'return\s+"(https?://[^"]+)"', decoded, 'video URL')
linkimg_uri = self._search_regex(
r'<img[^>]+id="linkimg"[^>]+src="([^"]+)"', webpage, 'link image')
linkimg = self._request_webpage(
linkimg_uri, video_id, note=False).read()
width, height, pixels = decode_png(linkimg)
output = ''
for y in range(height):
for x in range(width):
r, g, b = pixels[y][3 * x:3 * x + 3]
if r == 0 and g == 0 and b == 0:
break
else:
output += compat_chr(r)
output += compat_chr(g)
output += compat_chr(b)
img_str_length = len(output) // 200
img_str = [[0 for x in range(img_str_length)] for y in range(10)]
sig_str_length = len(signums) // 260
sig_str = [[0 for x in range(sig_str_length)] for y in range(10)]
for i in range(10):
for j in range(img_str_length):
begin = i * img_str_length * 20 + j * 20
img_str[i][j] = output[begin:begin + 20]
for j in range(sig_str_length):
begin = i * sig_str_length * 26 + j * 26
sig_str[i][j] = signums[begin:begin + 26]
parts = []
# TODO: find better names for str_, chr_ and sum_
str_ = ''
for i in [2, 3, 5, 7]:
str_ = ''
sum_ = float(99)
for j in range(len(sig_str[i])):
for chr_idx in range(len(img_str[i][j])):
if sum_ > float(122):
sum_ = float(98)
chr_ = compat_chr(int(math.floor(sum_)))
if sig_str[i][j][chr_idx] == chr_ and j >= len(str_):
sum_ += float(2.5)
str_ += img_str[i][j][chr_idx]
parts.append(str_.replace(',', ''))
video_url = 'https://openload.co/stream/%s~%s~%s~%s' % (parts[3], parts[1], parts[2], parts[0])
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
'title', default=None) or self._html_search_meta(
'description', webpage, 'title', fatal=True)
ext = mimetype2ext(self._search_regex(
r'window\.vt\s*=\s*(["\'])(?P<mimetype>.+?)\1', decoded,
'mimetype', default=None, group='mimetype')) or determine_ext(
video_url, 'mp4')
return {
'id': video_id,
'title': title,
'ext': ext,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'url': video_url,
# Seems all videos have extensions in their titles
'ext': determine_ext(title),
}

View File

@@ -137,13 +137,16 @@ class ORFTVthekIE(InfoExtractor):
class ORFOE1IE(InfoExtractor):
IE_NAME = 'orf:oe1'
IE_DESC = 'Radio Österreich 1'
_VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole.*?#\?track_id=)(?P<id>[0-9]+)'
_VALID_URL = r'https?://oe1\.orf\.at/(?:programm/|konsole\?.*?\btrack_id=)(?P<id>[0-9]+)'
# Audios on ORF radio are only available for 7 days, so we can't add tests.
_TEST = {
_TESTS = [{
'url': 'http://oe1.orf.at/konsole?show=on_demand#?track_id=394211',
'only_matching': True,
}
}, {
'url': 'http://oe1.orf.at/konsole?show=ondemand&track_id=443608&load_day=/programm/konsole/tag/20160726',
'only_matching': True,
}]
def _real_extract(self, url):
show_id = self._match_id(url)

View File

@@ -0,0 +1,58 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
int_or_none,
)
class PokemonIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pokemon\.com/[a-z]{2}(?:.*?play=(?P<id>[a-z0-9]{32})|/[^/]+/\d+_\d+-(?P<display_id>[^/?#]+))'
_TESTS = [{
'url': 'http://www.pokemon.com/us/pokemon-episodes/19_01-from-a-to-z/?play=true',
'md5': '9fb209ae3a569aac25de0f5afc4ee08f',
'info_dict': {
'id': 'd0436c00c3ce4071ac6cee8130ac54a1',
'ext': 'mp4',
'title': 'From A to Z!',
'description': 'Bonnie makes a new friend, Ash runs into an old friend, and a terrifying premonition begins to unfold!',
'timestamp': 1460478136,
'upload_date': '20160412',
},
'add_id': ['LimelightMedia']
}, {
'url': 'http://www.pokemon.com/uk/pokemon-episodes/?play=2e8b5c761f1d4a9286165d7748c1ece2',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/fr/episodes-pokemon/18_09-un-hiver-inattendu/',
'only_matching': True,
}, {
'url': 'http://www.pokemon.com/de/pokemon-folgen/01_20-bye-bye-smettbo/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, video_id or display_id)
video_data = extract_attributes(self._search_regex(
r'(<[^>]+data-video-id="%s"[^>]*>)' % (video_id if video_id else '[a-z0-9]{32}'),
webpage, 'video data element'))
video_id = video_data['data-video-id']
title = video_data['data-video-title']
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'limelight:media:%s' % video_id,
'title': title,
'description': video_data.get('data-video-summary'),
'thumbnail': video_data.get('data-video-poster'),
'series': 'Pokémon',
'season_number': int_or_none(video_data.get('data-video-season')),
'episode': title,
'episode_number': int_or_none(video_data.get('data-video-episode')),
'ie_key': 'LimelightMedia',
}

View File

@@ -113,6 +113,8 @@ class RTVEALaCartaIE(InfoExtractor):
png = self._download_webpage(png_request, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):
if '?' not in video_url:
video_url = video_url.replace('resources/', 'auth/resources/')
video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
subtitles = None

View File

@@ -75,7 +75,7 @@ class SafariBaseIE(InfoExtractor):
class SafariIE(SafariBaseIE):
IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>part\d+)\.html'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?#&]+)\.html'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
@@ -92,6 +92,9 @@ class SafariIE(SafariBaseIE):
# non-digits in course id
'url': 'https://www.safaribooksonline.com/library/view/create-a-nodejs/100000006A0210/part00.html',
'only_matching': True,
}, {
'url': 'https://www.safaribooksonline.com/library/view/learning-path-red/9780134664057/RHCE_Introduction.html',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -132,12 +135,15 @@ class SafariIE(SafariBaseIE):
class SafariApiIE(SafariBaseIE):
IE_NAME = 'safari:api'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>part\d+)\.html'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html'
_TEST = {
_TESTS = [{
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True,
}
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780134664057/chapter/RHCE_Introduction.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

View File

@@ -6,7 +6,6 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
urlencode_postdata,
)
@@ -37,28 +36,33 @@ class SharedIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage, urlh = self._download_webpage_handle(url, video_id)
if '>File does not exist<' in webpage:
raise ExtractorError(
'Video %s does not exist' % video_id, expected=True)
download_form = self._hidden_inputs(webpage)
request = sanitized_Request(
url, urlencode_postdata(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
video_page = self._download_webpage(
request, video_id, 'Downloading video page')
urlh.geturl(), video_id, 'Downloading video page',
data=urlencode_postdata(download_form),
headers={
'Content-Type': 'application/x-www-form-urlencoded',
'Referer': urlh.geturl(),
})
video_url = self._html_search_regex(
r'data-url="([^"]+)"', video_page, 'video URL')
r'data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'video URL', group='url')
title = base64.b64decode(self._html_search_meta(
'full:title', webpage, 'title').encode('utf-8')).decode('utf-8')
filesize = int_or_none(self._html_search_meta(
'full:size', webpage, 'file size', fatal=False))
thumbnail = self._html_search_regex(
r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
r'data-poster=(["\'])(?P<url>(?:(?!\1).)+)\1',
video_page, 'thumbnail', default=None, group='url')
return {
'id': video_id,

View File

@@ -13,20 +13,21 @@ from ..utils import (
sanitized_Request,
unified_strdate,
urlencode_postdata,
xpath_text,
)
class SmotriIE(InfoExtractor):
IE_DESC = 'Smotri.com'
IE_NAME = 'smotri'
_VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
_VALID_URL = r'https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?P<id>v(?P<realvideoid>[0-9]+)[a-z0-9]{4})'
_NETRC_MACHINE = 'smotri'
_TESTS = [
# real video id 2610366
{
'url': 'http://smotri.com/video/view/?id=v261036632ab',
'md5': '2a7b08249e6f5636557579c368040eb9',
'md5': '02c0dfab2102984e9c5bb585cc7cc321',
'info_dict': {
'id': 'v261036632ab',
'ext': 'mp4',
@@ -174,11 +175,11 @@ class SmotriIE(InfoExtractor):
if video_password:
video_form['pass'] = hashlib.md5(video_password.encode('utf-8')).hexdigest()
request = sanitized_Request(
'http://smotri.com/video/view/url/bot/', urlencode_postdata(video_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
video = self._download_json(request, video_id, 'Downloading video JSON')
video = self._download_json(
'http://smotri.com/video/view/url/bot/',
video_id, 'Downloading video JSON',
data=urlencode_postdata(video_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
video_url = video.get('_vidURL') or video.get('_vidURL_mp4')
@@ -196,11 +197,11 @@ class SmotriIE(InfoExtractor):
raise ExtractorError(msg, expected=True)
title = video['title']
thumbnail = video['_imgURL']
upload_date = unified_strdate(video['added'])
uploader = video['userNick']
uploader_id = video['userLogin']
duration = int_or_none(video['duration'])
thumbnail = video.get('_imgURL')
upload_date = unified_strdate(video.get('added'))
uploader = video.get('userNick')
uploader_id = video.get('userLogin')
duration = int_or_none(video.get('duration'))
# Video JSON does not provide enough meta data
# We will extract some from the video web page instead
@@ -209,7 +210,7 @@ class SmotriIE(InfoExtractor):
# Warning if video is unavailable
warning = self._html_search_regex(
r'<div class="videoUnModer">(.*?)</div>', webpage,
r'<div[^>]+class="videoUnModer"[^>]*>(.+?)</div>', webpage,
'warning message', default=None)
if warning is not None:
self._downloader.report_warning(
@@ -217,20 +218,22 @@ class SmotriIE(InfoExtractor):
(video_id, warning))
# Adult content
if re.search('EroConfirmText">', webpage) is not None:
if 'EroConfirmText">' in webpage:
self.report_age_confirmation()
confirm_string = self._html_search_regex(
r'<a href="/video/view/\?id=%s&confirm=([^"]+)" title="[^"]+">' % video_id,
r'<a[^>]+href="/video/view/\?id=%s&confirm=([^"]+)"' % video_id,
webpage, 'confirm string')
confirm_url = webpage_url + '&confirm=%s' % confirm_string
webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)')
webpage = self._download_webpage(
confirm_url, video_id,
'Downloading video page (age confirmed)')
adult_content = True
else:
adult_content = False
view_count = self._html_search_regex(
'Общее количество просмотров.*?<span class="Number">(\\d+)</span>',
webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL)
r'(?s)Общее количество просмотров.*?<span class="Number">(\d+)</span>',
webpage, 'view count', fatal=False)
return {
'id': video_id,
@@ -249,37 +252,33 @@ class SmotriIE(InfoExtractor):
class SmotriCommunityIE(InfoExtractor):
IE_DESC = 'Smotri.com community videos'
IE_NAME = 'smotri:community'
_VALID_URL = r'^https?://(?:www\.)?smotri\.com/community/video/(?P<communityid>[0-9A-Za-z_\'-]+)'
_VALID_URL = r'https?://(?:www\.)?smotri\.com/community/video/(?P<id>[0-9A-Za-z_\'-]+)'
_TEST = {
'url': 'http://smotri.com/community/video/kommuna',
'info_dict': {
'id': 'kommuna',
'title': 'КПРФ',
},
'playlist_mincount': 4,
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
community_id = mobj.group('communityid')
community_id = self._match_id(url)
url = 'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id
rss = self._download_xml(url, community_id, 'Downloading community RSS')
rss = self._download_xml(
'http://smotri.com/export/rss/video/by/community/-/%s/video.xml' % community_id,
community_id, 'Downloading community RSS')
entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')]
entries = [
self.url_result(video_url.text, SmotriIE.ie_key())
for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text
community_title = self._html_search_regex(
'^Видео сообщества "([^"]+)"$', description_text, 'community title')
return self.playlist_result(entries, community_id, community_title)
return self.playlist_result(entries, community_id)
class SmotriUserIE(InfoExtractor):
IE_DESC = 'Smotri.com user videos'
IE_NAME = 'smotri:user'
_VALID_URL = r'^https?://(?:www\.)?smotri\.com/user/(?P<userid>[0-9A-Za-z_\'-]+)'
_VALID_URL = r'https?://(?:www\.)?smotri\.com/user/(?P<id>[0-9A-Za-z_\'-]+)'
_TESTS = [{
'url': 'http://smotri.com/user/inspector',
'info_dict': {
@@ -290,19 +289,19 @@ class SmotriUserIE(InfoExtractor):
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('userid')
user_id = self._match_id(url)
url = 'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id
rss = self._download_xml(url, user_id, 'Downloading user RSS')
rss = self._download_xml(
'http://smotri.com/export/rss/user/video/-/%s/video.xml' % user_id,
user_id, 'Downloading user RSS')
entries = [self.url_result(video_url.text, 'Smotri')
for video_url in rss.findall('./channel/item/link')]
description_text = rss.find('./channel/description').text
user_nickname = self._html_search_regex(
'^Видео режиссера (.*)$', description_text,
'user nickname')
description_text = xpath_text(rss, './channel/description') or ''
user_nickname = self._search_regex(
'^Видео режиссера (.+)$', description_text,
'user nickname', fatal=False)
return self.playlist_result(entries, user_id, user_nickname)
@@ -310,11 +309,11 @@ class SmotriUserIE(InfoExtractor):
class SmotriBroadcastIE(InfoExtractor):
IE_DESC = 'Smotri.com broadcasts'
IE_NAME = 'smotri:broadcast'
_VALID_URL = r'^https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<broadcastid>[^/]+))/?.*'
_VALID_URL = r'https?://(?:www\.)?(?P<url>smotri\.com/live/(?P<id>[^/]+))/?.*'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
broadcast_id = mobj.group('broadcastid')
broadcast_id = mobj.group('id')
broadcast_url = 'http://' + mobj.group('url')
broadcast_page = self._download_webpage(broadcast_url, broadcast_id, 'Downloading broadcast page')
@@ -328,7 +327,8 @@ class SmotriBroadcastIE(InfoExtractor):
(username, password) = self._get_login_info()
if username is None:
self.raise_login_required('Erotic broadcasts allowed only for registered users')
self.raise_login_required(
'Erotic broadcasts allowed only for registered users')
login_form = {
'login-hint53': '1',
@@ -343,8 +343,9 @@ class SmotriBroadcastIE(InfoExtractor):
broadcast_page = self._download_webpage(
request, broadcast_id, 'Logging in and confirming age')
if re.search('>Неверный логин или пароль<', broadcast_page) is not None:
raise ExtractorError('Unable to log in: bad username or password', expected=True)
if '>Неверный логин или пароль<' in broadcast_page:
raise ExtractorError(
'Unable to log in: bad username or password', expected=True)
adult_content = True
else:
@@ -383,11 +384,11 @@ class SmotriBroadcastIE(InfoExtractor):
broadcast_playpath = broadcast_json['_streamName']
broadcast_app = '%s/%s' % (mobj.group('app'), broadcast_json['_vidURL'])
broadcast_thumbnail = broadcast_json['_imgURL']
broadcast_thumbnail = broadcast_json.get('_imgURL')
broadcast_title = self._live_title(broadcast_json['title'])
broadcast_description = broadcast_json['description']
broadcaster_nick = broadcast_json['nick']
broadcaster_login = broadcast_json['login']
broadcast_description = broadcast_json.get('description')
broadcaster_nick = broadcast_json.get('nick')
broadcaster_login = broadcast_json.get('login')
rtmp_conn = 'S:%s' % uuid.uuid4().hex
except KeyError:
if protected_broadcast:

View File

@@ -119,6 +119,12 @@ class SoundcloudIE(InfoExtractor):
_CLIENT_ID = '02gUJC0hH2ct1EGOcYXQIzRFU91c72Ea'
_IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@staticmethod
def _extract_urls(webpage):
return [m.group('url') for m in re.finditer(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
webpage)]
def report_resolve(self, video_id):
"""Report information extraction."""
self.to_screen('%s: Resolving id' % video_id)

View File

@@ -17,6 +17,8 @@ class SouthParkIE(MTVServicesInfoExtractor):
'ext': 'mp4',
'title': 'South Park|Bat Daded',
'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.',
'timestamp': 1112760000,
'upload_date': '20050406',
},
}]
@@ -28,6 +30,10 @@ class SouthParkEsIE(SouthParkIE):
_TESTS = [{
'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
'info_dict': {
'title': 'Cartman Consigue Una Sonda Anal',
'description': 'Cartman Consigue Una Sonda Anal',
},
'playlist_count': 4,
}]
@@ -42,17 +48,27 @@ class SouthParkDeIE(SouthParkIE):
'info_dict': {
'id': '85487c96-b3b9-4e39-9127-ad88583d9bf2',
'ext': 'mp4',
'title': 'The Government Won\'t Respect My Privacy',
'title': 'South Park|The Government Won\'t Respect My Privacy',
'description': 'Cartman explains the benefits of "Shitter" to Stan, Kyle and Craig.',
'timestamp': 1380160800,
'upload_date': '20130926',
},
}, {
# non-ASCII characters in initial URL
'url': 'http://www.southpark.de/alle-episoden/s18e09-hashtag-aufwärmen',
'playlist_count': 4,
'info_dict': {
'title': 'Hashtag „Aufwärmen“',
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
},
'playlist_count': 3,
}, {
# non-ASCII characters in redirect URL
'url': 'http://www.southpark.de/alle-episoden/s18e09',
'playlist_count': 4,
'info_dict': {
'title': 'Hashtag „Aufwärmen“',
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
},
'playlist_count': 3,
}]
@@ -63,7 +79,11 @@ class SouthParkNlIE(SouthParkIE):
_TESTS = [{
'url': 'http://www.southpark.nl/full-episodes/s18e06-freemium-isnt-free',
'playlist_count': 4,
'info_dict': {
'title': 'Freemium Isn\'t Free',
'description': 'Stan is addicted to the new Terrance and Phillip mobile game.',
},
'playlist_mincount': 3,
}]
@@ -74,5 +94,9 @@ class SouthParkDkIE(SouthParkIE):
_TESTS = [{
'url': 'http://www.southparkstudios.dk/full-episodes/s18e07-grounded-vindaloop',
'playlist_count': 4,
'info_dict': {
'title': 'Grounded Vindaloop',
'description': 'Butters is convinced he\'s living in a virtual reality.',
},
'playlist_mincount': 3,
}]

View File

@@ -11,8 +11,10 @@ class SpikeIE(MTVServicesInfoExtractor):
'info_dict': {
'id': 'b9c8221a-4e50-479a-b86d-3333323e38ba',
'ext': 'mp4',
'title': 'Auction Hunters|Can Allen Ride A Hundred Year-Old Motorcycle?',
'title': 'Auction Hunters|December 27, 2013|4|414|Can Allen Ride A Hundred Year-Old Motorcycle?',
'description': 'md5:fbed7e82ed5fad493615b3094a9499cb',
'timestamp': 1388120400,
'upload_date': '20131227',
},
}, {
'url': 'http://www.spike.com/video-clips/lhtu8m/',

View File

@@ -118,8 +118,12 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
xpath_text(cfg_xml, './startThumb', 'thumbnail'), 'http:')
thumbnails = self._extract_thumbnails(cfg_xml)
title = self._html_search_regex(
self._TITLE_REGEX, webpage, 'title') if self._TITLE_REGEX else self._og_search_title(webpage)
title = None
if self._TITLE_REGEX:
title = self._html_search_regex(
self._TITLE_REGEX, webpage, 'title', default=None)
if not title:
title = self._og_search_title(webpage)
age_limit = self._rta_search(webpage) or 18
@@ -189,9 +193,9 @@ class TNAFlixNetworkEmbedIE(TNAFlixNetworkBaseIE):
class TNAFlixIE(TNAFlixNetworkBaseIE):
_VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)'
_TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>'
_DESCRIPTION_REGEX = r'<meta[^>]+name="description"[^>]+content="([^"]+)"'
_UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h1>(.+?)</h1>'
_TITLE_REGEX = r'<title>(.+?) - (?:TNAFlix Porn Videos|TNAFlix\.com)</title>'
_DESCRIPTION_REGEX = r'(?s)>Description:</[^>]+>(.+?)<'
_UPLOADER_REGEX = r'<i>\s*Verified Member\s*</i>\s*<h\d+>(.+?)<'
_CATEGORIES_REGEX = r'(?s)<span[^>]*>Categories:</span>(.+?)</div>'
_TESTS = [{

View File

@@ -8,6 +8,7 @@ from ..utils import (
determine_ext,
int_or_none,
float_or_none,
js_to_json,
parse_iso8601,
remove_end,
)
@@ -54,10 +55,11 @@ class TV2IE(InfoExtractor):
ext = determine_ext(video_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id=format_id))
video_url, video_id, f4m_id=format_id, fatal=False))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id=format_id))
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
pass
else:
@@ -105,7 +107,7 @@ class TV2ArticleIE(InfoExtractor):
'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542',
'info_dict': {
'id': '6930542',
'title': 'Russen hetses etter pingvintyveri innrømmer å ha åpnet luken på buret',
'title': 'Russen hetses etter pingvintyveri - innrømmer å ha åpnet luken på buret',
'description': 'md5:339573779d3eea3542ffe12006190954',
},
'playlist_count': 2,
@@ -119,9 +121,23 @@ class TV2ArticleIE(InfoExtractor):
webpage = self._download_webpage(url, playlist_id)
# Old embed pattern (looks unused nowadays)
assets = re.findall(r'data-assetid=["\'](\d+)', webpage)
if not assets:
# New embed pattern
for v in re.findall('TV2ContentboxVideo\(({.+?})\)', webpage):
video = self._parse_json(
v, playlist_id, transform_source=js_to_json, fatal=False)
if not video:
continue
asset = video.get('assetId')
if asset:
assets.append(asset)
entries = [
self.url_result('http://www.tv2.no/v/%s' % video_id, 'TV2')
for video_id in re.findall(r'data-assetid="(\d+)"', webpage)]
self.url_result('http://www.tv2.no/v/%s' % asset_id, 'TV2')
for asset_id in assets]
title = remove_end(self._og_search_title(webpage), ' - TV2.no')
description = remove_end(self._og_search_description(webpage), ' - TV2.no')

View File

@@ -9,56 +9,23 @@ class TVLandIE(MTVServicesInfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tvland\.com/(?:video-clips|episodes)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://www.tvland.com/feeds/mrss/'
_TESTS = [{
# Geo-restricted. Without a proxy metadata are still there. With a
# proxy it redirects to http://m.tvland.com/app/
'url': 'http://www.tvland.com/episodes/hqhps2/everybody-loves-raymond-the-invasion-ep-048',
'playlist': [
{
'md5': '227e9723b9669c05bf51098b10287aa7',
'info_dict': {
'id': 'bcbd3a83-3aca-4dca-809b-f78a87dcccdd',
'ext': 'mp4',
'title': 'Everybody Loves Raymond|Everybody Loves Raymond 048 HD, Part 1 of 5',
}
},
{
'md5': '9fa2b764ec0e8194fb3ebb01a83df88b',
'info_dict': {
'id': 'f4279548-6e13-40dd-92e8-860d27289197',
'ext': 'mp4',
'title': 'Everybody Loves Raymond|Everybody Loves Raymond 048 HD, Part 2 of 5',
}
},
{
'md5': 'fde4c3bccd7cc7e3576b338734153cec',
'info_dict': {
'id': '664e4a38-53ef-4115-9bc9-d0f789ec6334',
'ext': 'mp4',
'title': 'Everybody Loves Raymond|Everybody Loves Raymond 048 HD, Part 3 of 5',
}
},
{
'md5': '247f6780cda6891f2e49b8ae2b10e017',
'info_dict': {
'id': '9146ecf5-b15a-4d78-879c-6679b77f4960',
'ext': 'mp4',
'title': 'Everybody Loves Raymond|Everybody Loves Raymond 048 HD, Part 4 of 5',
}
},
{
'md5': 'fd269f33256e47bad5eb6c40de089ff6',
'info_dict': {
'id': '04334a2e-9a47-4214-a8c2-ae5792e2fab7',
'ext': 'mp4',
'title': 'Everybody Loves Raymond|Everybody Loves Raymond 048 HD, Part 5 of 5',
}
}
],
'info_dict': {
'description': 'md5:80973e81b916a324e05c14a3fb506d29',
'title': 'The Invasion',
},
'playlist': [],
}, {
'url': 'http://www.tvland.com/video-clips/zea2ev/younger-younger--hilary-duff---little-lies',
'md5': 'e2c6389401cf485df26c79c247b08713',
'info_dict': {
'id': 'b8697515-4bbe-4e01-83d5-fa705ce5fa88',
'ext': 'mp4',
'title': 'Younger|Younger: Hilary Duff - Little Lies',
'description': 'md5:7d192f56ca8d958645c83f0de8ef0269'
'title': 'Younger|December 28, 2015|2|NO-EPISODE#|Younger: Hilary Duff - Little Lies',
'description': 'md5:7d192f56ca8d958645c83f0de8ef0269',
'upload_date': '20151228',
'timestamp': 1451289600,
},
}]

View File

@@ -24,6 +24,7 @@ class TVPIE(InfoExtractor):
'id': '194536',
'ext': 'mp4',
'title': 'Czas honoru, I seria odc. 13',
'description': 'md5:76649d2014f65c99477be17f23a4dead',
},
}, {
'url': 'http://www.tvp.pl/there-can-be-anything-so-i-shortened-it/17916176',
@@ -32,6 +33,16 @@ class TVPIE(InfoExtractor):
'id': '17916176',
'ext': 'mp4',
'title': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
'description': 'TVP Gorzów pokaże filmy studentów z podroży dookoła świata',
},
}, {
# page id is not the same as video id(#7799)
'url': 'http://vod.tvp.pl/22704887/08122015-1500',
'md5': 'cf6a4705dfd1489aef8deb168d6ba742',
'info_dict': {
'id': '22680786',
'ext': 'mp4',
'title': 'Wiadomości, 08.12.2015, 15:00',
},
}, {
'url': 'http://vod.tvp.pl/seriale/obyczajowe/na-sygnale/sezon-2-27-/odc-39/17834272',
@@ -53,6 +64,39 @@ class TVPIE(InfoExtractor):
'only_matching': True,
}]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
video_id = self._search_regex([
r'<iframe[^>]+src="[^"]*?object_id=(\d+)',
"object_id\s*:\s*'(\d+)'"], webpage, 'video id')
return {
'_type': 'url_transparent',
'url': 'tvp:' + video_id,
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage),
'ie_key': 'TVPEmbed',
}
class TVPEmbedIE(InfoExtractor):
IE_NAME = 'tvp:embed'
IE_DESC = 'Telewizja Polska'
_VALID_URL = r'(?:tvp:|https?://[^/]+\.tvp\.(?:pl|info)/sess/tvplayer\.php\?.*?object_id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.tvp.pl/sess/tvplayer.php?object_id=22670268',
'md5': '8c9cd59d16edabf39331f93bf8a766c7',
'info_dict': {
'id': '22670268',
'ext': 'mp4',
'title': 'Panorama, 07.12.2015, 15:40',
},
}, {
'url': 'tvp:22670268',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -4,13 +4,18 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_HTTPError,
compat_str,
compat_urlparse,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_iso8601,
qualities,
determine_ext,
update_url_query,
int_or_none,
)
@@ -34,6 +39,9 @@ class TVPlayIE(InfoExtractor):
'ext': 'mp4',
'title': 'Kādi ir īri? - Viņas melo labāk',
'description': 'Baiba apsmej īrus, kādi tie ir un ko viņi dara.',
'series': 'Viņas melo labāk',
'season': '2.sezona',
'season_number': 2,
'duration': 25,
'timestamp': 1406097056,
'upload_date': '20140723',
@@ -46,6 +54,10 @@ class TVPlayIE(InfoExtractor):
'ext': 'flv',
'title': 'Moterys meluoja geriau',
'description': 'md5:9aec0fc68e2cbc992d2a140bd41fa89e',
'series': 'Moterys meluoja geriau',
'episode_number': 47,
'season': '1 sezonas',
'season_number': 1,
'duration': 1330,
'timestamp': 1403769181,
'upload_date': '20140626',
@@ -196,12 +208,15 @@ class TVPlayIE(InfoExtractor):
title = video['title']
if video.get('is_geo_blocked'):
self.report_warning(
'This content might not be available in your country due to copyright reasons')
streams = self._download_json(
'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id, video_id, 'Downloading streams JSON')
try:
streams = self._download_json(
'http://playapi.mtgx.tv/v1/videos/stream/%s' % video_id,
video_id, 'Downloading streams JSON')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
msg = self._parse_json(e.cause.read().decode('utf-8'), video_id)
raise ExtractorError(msg['msg'], expected=True)
raise
quality = qualities(['hls', 'medium', 'high'])
formats = []
@@ -226,7 +241,8 @@ class TVPlayIE(InfoExtractor):
'ext': ext,
}
if video_url.startswith('rtmp'):
m = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
m = re.search(
r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url)
if not m:
continue
fmt.update({
@@ -240,15 +256,41 @@ class TVPlayIE(InfoExtractor):
'url': video_url,
})
formats.append(fmt)
if not formats and video.get('is_geo_blocked'):
self.raise_geo_restricted(
'This content might not be available in your country due to copyright reasons')
self._sort_formats(formats)
# TODO: webvtt in m3u8
subtitles = {}
sami_path = video.get('sami_path')
if sami_path:
lang = self._search_regex(
r'_([a-z]{2})\.xml', sami_path, 'lang',
default=compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1])
subtitles[lang] = [{
'url': sami_path,
}]
series = video.get('format_title')
episode_number = int_or_none(video.get('format_position', {}).get('episode'))
season = video.get('_embedded', {}).get('season', {}).get('title')
season_number = int_or_none(video.get('format_position', {}).get('season'))
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'series': series,
'episode_number': episode_number,
'season': season,
'season_number': season_number,
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('created_at')),
'view_count': int_or_none(video.get('views', {}).get('total')),
'age_limit': int_or_none(video.get('age_limit', 0)),
'formats': formats,
'subtitles': subtitles,
}

View File

@@ -461,7 +461,7 @@ class TwitchClipsIE(InfoExtractor):
IE_NAME = 'twitch:clips'
_VALID_URL = r'https?://clips\.twitch\.tv/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TEST = {
_TESTS = [{
'url': 'https://clips.twitch.tv/ea/AggressiveCobraPoooound',
'md5': '761769e1eafce0ffebfb4089cb3847cd',
'info_dict': {
@@ -473,7 +473,11 @@ class TwitchClipsIE(InfoExtractor):
'uploader': 'stereotype_',
'uploader_id': 'stereotype_',
},
}
}, {
# multiple formats
'url': 'https://clips.twitch.tv/rflegendary/UninterestedBeeDAESuppy',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -485,15 +489,27 @@ class TwitchClipsIE(InfoExtractor):
r'(?s)clipInfo\s*=\s*({.+?});', webpage, 'clip info'),
video_id, transform_source=js_to_json)
video_url = clip['clip_video_url']
title = clip['channel_title']
title = clip.get('channel_title') or self._og_search_title(webpage)
formats = [{
'url': option['source'],
'format_id': option.get('quality'),
'height': int_or_none(option.get('quality')),
} for option in clip.get('quality_options', []) if option.get('source')]
if not formats:
formats = [{
'url': clip['clip_video_url'],
}]
self._sort_formats(formats)
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'creator': clip.get('broadcaster_display_name') or clip.get('broadcaster_login'),
'uploader': clip.get('curator_login'),
'uploader_id': clip.get('curator_display_name'),
'formats': formats,
}

View File

@@ -0,0 +1,58 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import unescapeHTML
class VODPlatformIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vod-platform\.net/embed/(?P<id>[^/?#]+)'
_TEST = {
# from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar
'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw',
'md5': '1db2b7249ce383d6be96499006e951fc',
'info_dict': {
'id': 'RufMcytHDolTH1MuKHY9Fw',
'ext': 'mp4',
'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = unescapeHTML(self._og_search_title(webpage))
hidden_inputs = self._hidden_inputs(webpage)
base_url = self._search_regex(
'(.*/)(?:playlist.m3u8|manifest.mpd)',
hidden_inputs.get('HiddenmyhHlsLink') or hidden_inputs['HiddenmyDashLink'],
'base url')
formats = self._extract_m3u8_formats(
base_url + 'playlist.m3u8', video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False)
formats.extend(self._extract_mpd_formats(
base_url + 'manifest.mpd', video_id,
mpd_id='dash', fatal=False))
rtmp_formats = self._extract_smil_formats(
base_url + 'jwplayer.smil', video_id, fatal=False)
for rtmp_format in rtmp_formats:
rtsp_format = rtmp_format.copy()
rtsp_format['url'] = '%s/%s' % (rtmp_format['url'], rtmp_format['play_path'])
del rtsp_format['play_path']
del rtsp_format['ext']
rtsp_format.update({
'url': rtsp_format['url'].replace('rtmp://', 'rtsp://'),
'format_id': rtmp_format['format_id'].replace('rtmp', 'rtsp'),
'protocol': 'rtsp',
})
formats.extend([rtmp_format, rtsp_format])
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'thumbnail': hidden_inputs.get('HiddenThumbnail') or self._og_search_thumbnail(webpage),
'formats': formats,
}

View File

@@ -75,6 +75,12 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
% storage_dir,
track_id, 'Downloading track location JSON')
# Each string is now wrapped in a list, this is probably only temporarily thus
# supporting both scenarios (see https://github.com/rg3/youtube-dl/issues/10193)
for k, v in data.items():
if v and isinstance(v, list):
data[k] = v[0]
key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).hexdigest()
storage = storage_dir.split('.')

View File

@@ -2,6 +2,7 @@ from __future__ import unicode_literals
import os.path
import optparse
import re
import sys
from .downloader.external import list_external_downloaders
@@ -93,8 +94,18 @@ def parseOpts(overrideArguments=None):
setattr(parser.values, option.dest, value.split(','))
def _hide_login_info(opts):
opts = list(opts)
for private_opt in ['-p', '--password', '-u', '--username', '--video-password']:
PRIVATE_OPTS = ['-p', '--password', '-u', '--username', '--video-password']
eqre = re.compile('^(?P<key>' + ('|'.join(re.escape(po) for po in PRIVATE_OPTS)) + ')=.+$')
def _scrub_eq(o):
m = eqre.match(o)
if m:
return m.group('key') + '=PRIVATE'
else:
return o
opts = list(map(_scrub_eq, opts))
for private_opt in PRIVATE_OPTS:
try:
i = opts.index(private_opt)
opts[i + 1] = 'PRIVATE'

View File

@@ -47,6 +47,7 @@ from .compat import (
compat_socket_create_connection,
compat_str,
compat_struct_pack,
compat_struct_unpack,
compat_urllib_error,
compat_urllib_parse,
compat_urllib_parse_urlencode,
@@ -1101,7 +1102,7 @@ def unified_timestamp(date_str, day_first=True):
date_str = date_str.replace(',', ' ')
pm_delta = datetime.timedelta(hours=12 if re.search(r'(?i)PM', date_str) else 0)
pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
timezone, date_str = extract_timezone(date_str)
# Remove AM/PM + timezone
@@ -1109,13 +1110,13 @@ def unified_timestamp(date_str, day_first=True):
for expression in date_formats(day_first):
try:
dt = datetime.datetime.strptime(date_str, expression) - timezone + pm_delta
dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
return calendar.timegm(dt.timetuple())
except ValueError:
pass
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
return calendar.timegm(timetuple.timetuple())
return calendar.timegm(timetuple) + pm_delta * 3600
def determine_ext(url, default_ext='unknown_video'):
@@ -1983,11 +1984,27 @@ US_RATINGS = {
}
TV_PARENTAL_GUIDELINES = {
'TV-Y': 0,
'TV-Y7': 7,
'TV-G': 0,
'TV-PG': 0,
'TV-14': 14,
'TV-MA': 17,
}
def parse_age_limit(s):
if s is None:
if type(s) == int:
return s if 0 <= s <= 21 else None
if not isinstance(s, compat_basestring):
return None
m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
return int(m.group('age')) if m else US_RATINGS.get(s)
if m:
return int(m.group('age'))
if s in US_RATINGS:
return US_RATINGS[s]
return TV_PARENTAL_GUIDELINES.get(s)
def strip_jsonp(code):
@@ -2969,3 +2986,110 @@ def parse_m3u8_attributes(attrib):
def urshift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n
# Based on png2str() written by @gdkchan and improved by @yokrysty
# Originally posted at https://github.com/rg3/youtube-dl/issues/9706
def decode_png(png_data):
# Reference: https://www.w3.org/TR/PNG/
header = png_data[8:]
if png_data[:8] != b'\x89PNG\x0d\x0a\x1a\x0a' or header[4:8] != b'IHDR':
raise IOError('Not a valid PNG file.')
int_map = {1: '>B', 2: '>H', 4: '>I'}
unpack_integer = lambda x: compat_struct_unpack(int_map[len(x)], x)[0]
chunks = []
while header:
length = unpack_integer(header[:4])
header = header[4:]
chunk_type = header[:4]
header = header[4:]
chunk_data = header[:length]
header = header[length:]
header = header[4:] # Skip CRC
chunks.append({
'type': chunk_type,
'length': length,
'data': chunk_data
})
ihdr = chunks[0]['data']
width = unpack_integer(ihdr[:4])
height = unpack_integer(ihdr[4:8])
idat = b''
for chunk in chunks:
if chunk['type'] == b'IDAT':
idat += chunk['data']
if not idat:
raise IOError('Unable to read PNG data.')
decompressed_data = bytearray(zlib.decompress(idat))
stride = width * 3
pixels = []
def _get_pixel(idx):
x = idx % stride
y = idx // stride
return pixels[y][x]
for y in range(height):
basePos = y * (1 + stride)
filter_type = decompressed_data[basePos]
current_row = []
pixels.append(current_row)
for x in range(stride):
color = decompressed_data[1 + basePos + x]
basex = y * stride + x
left = 0
up = 0
if x > 2:
left = _get_pixel(basex - 3)
if y > 0:
up = _get_pixel(basex - stride)
if filter_type == 1: # Sub
color = (color + left) & 0xff
elif filter_type == 2: # Up
color = (color + up) & 0xff
elif filter_type == 3: # Average
color = (color + ((left + up) >> 1)) & 0xff
elif filter_type == 4: # Paeth
a = left
b = up
c = 0
if x > 2 and y > 0:
c = _get_pixel(basex - stride - 3)
p = a + b - c
pa = abs(p - a)
pb = abs(p - b)
pc = abs(p - c)
if pa <= pb and pa <= pc:
color = (color + a) & 0xff
elif pb <= pc:
color = (color + b) & 0xff
else:
color = (color + c) & 0xff
current_row.append(color)
return width, height, pixels

View File

@@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2016.07.24'
__version__ = '2016.08.07'