Compare commits

...

302 Commits

Author SHA1 Message Date
Sergey M․
cb1e6d8985 release 2017.06.12 2017-06-12 02:23:17 +07:00
Sergey M․
9932ac5c58 [ChangeLog] Actualize 2017-06-12 02:01:15 +07:00
Sergey M․
bf87c36c93 [xfileshare] PEP 8 2017-06-12 02:01:12 +07:00
Sergey M․
b4a3d461e4 [utils] Handle HTMLParseError in extract_attributes (closes #13349) 2017-06-12 01:52:24 +07:00
Sergey M․
72b409559c [compat] Introduce compat_HTMLParseError 2017-06-12 01:50:32 +07:00
Sergey M․
534863e057 [xfileshare] Add support for rapidvideo (closes #13348) 2017-06-12 00:16:47 +07:00
Sergey M․
16bc958287 [xfileshare] Modernize and pass referrer 2017-06-12 00:14:04 +07:00
Sergey M․
624bd0104c [rutv] Add support for testplayer.vgtrk.com (closes #13347) 2017-06-11 21:36:19 +07:00
Sergey M․
28a4d6cce8 [newgrounds] Extract more metadata (closes #13232) 2017-06-11 21:30:06 +07:00
Sergey M․
2ae2ffda5e [utils] Improve unified_timestamp 2017-06-11 21:27:22 +07:00
Sergey M․
70e7967202 [newgrounds:playlist] Add extractor (closes #10611) 2017-06-11 20:50:55 +07:00
Sergey M․
6e999fbc12 [newgrounds] Improve formats and uploader extraction (closes #13346) 2017-06-11 19:44:44 +07:00
Sergey M․
7409af9eb3 [msn] Fix formats extraction 2017-06-11 08:56:53 +07:00
Sergey M․
4e3637034c [extractor/generic] Ensure format id is unicode string 2017-06-10 23:56:20 +07:00
Sergey M․
1afd0b0da7 [extractor/common] Return unicode string from _match_id 2017-06-09 00:40:03 +07:00
Sergey M․
7515830422 [turbo] Ensure format id is string 2017-06-09 00:31:56 +07:00
Sergey M․
f5521ea209 [sexu] Ensure height is int 2017-06-09 00:30:23 +07:00
Sergey M․
34646967ba [jove] Ensure comment count is int 2017-06-09 00:29:20 +07:00
Sergey M․
e4d2e76d8e [golem] Ensure format id is string 2017-06-09 00:27:11 +07:00
Sergey M․
87f5646937 [gfycat] Ensure filesize is int 2017-06-09 00:24:23 +07:00
Sergey M․
cc69a3de1b [foxgay] Ensure height is int 2017-06-09 00:22:14 +07:00
Sergey M․
15aeeb1188 [flickr] Ensure format id is string 2017-06-09 00:20:07 +07:00
Sergey M․
1693bebe4d [sohu] Fix numeric fields 2017-06-09 00:16:42 +07:00
Sergey M․
4244a13a1d [safari] Improve authentication detection (closes #13319) 2017-06-08 23:20:48 +07:00
Sergey M․
931adf8cc1 [liveleak] Ensure height is int (closes #13313) 2017-06-08 22:54:30 +07:00
Sergey M․
c996943418 [YoutubeDL] Sanitize more fields (#13313) 2017-06-08 22:53:14 +07:00
Sergey M․
76e6378358 [README.md] Improve man page formatting 2017-06-08 22:02:42 +07:00
Sergey M․
a355b57f58 [README.md] Clarify output template references (closes #13316) 2017-06-08 21:52:19 +07:00
Sergey M․
1508da30c2 [streamango] Skip download for test (closes #13292) 2017-06-07 21:53:40 +07:00
Luca Steeb
eb703e5380 [streamango] Make title optional 2017-06-07 21:53:33 +07:00
Sergey M․
0a3924e746 [rtlnl] Improve _VALID_URL (closes #13295) 2017-06-06 21:21:44 +07:00
Sergey M․
e1db730d86 [tvplayer] Fix extraction (closes #13291) 2017-06-06 00:13:57 +07:00
Sergey M․
537191826f release 2017.06.05 2017-06-05 00:48:07 +07:00
Sergey M․
130880ba48 [ChangeLog] Actualize 2017-06-05 00:43:38 +07:00
Sergey M․
f8ba3fda4d Credit @jktjkt for dvtv formats (#13063) 2017-06-05 00:38:44 +07:00
Sergey M․
e1b90cc3db Credit @mikf for beam:vod (#13032) 2017-06-05 00:35:41 +07:00
Sergey M․
43e6579558 Credit @adamvoss for bandcamp:weekly (#12758) 2017-06-04 23:22:19 +07:00
Sergey M․
6d923aab35 [bandcamp:weekly] Improve and extract more metadata (closes #12758) 2017-06-04 23:21:30 +07:00
Adam Voss
62bafabc09 [bandcamp:weekly] Add extractor 2017-06-04 23:21:07 +07:00
Sergey M․
9edcdac90c [pornhub:uservideos] Add missing raise 2017-06-04 20:39:55 +07:00
Sergey M․
cd138d8bd4 [pornhub:playlist] Fix extraction (closes #13281) 2017-06-04 15:54:19 +07:00
Sergey M․
cd750b731c [godtv] Remove extractor (closes #13175) 2017-06-03 22:08:12 +07:00
CeruleanSky
4bede0d8f5 [YoutubeDL] Don't emit ANSI escape codes on Windows 2017-06-03 19:14:23 +07:00
Sergey M․
f129c3f349 [safari] Fix typo (closes #13252) 2017-06-02 01:03:51 +07:00
Sergey M․
39d4c1be4d [youtube] Improve chapters extraction (closes #13247) 2017-06-01 23:29:45 +07:00
Sergey M․
f7a747ce59 [1tv] Lower preference for http formats (closes #13246) 2017-06-01 22:19:52 +07:00
Sergey M․
4489d41816 [francetv] Relax _VALID_URL 2017-06-01 00:15:15 +07:00
Sergey M․
87b5184a0d [drbonanza] Fix extraction (closes #13231) 2017-05-31 23:56:32 +07:00
Remita Amine
c56ad5c975 [packtpub] Fix authentication(closes #13240) 2017-05-31 15:44:29 +01:00
Sergey M․
6b7ce85cdc [README.md] Mention http_dash_segments protocol 2017-05-30 23:50:48 +07:00
Yen Chi Hsuan
d10d0e3cf8 [README.md] Add an example for how to use .netrc on Windows
That's a Python bug: http://bugs.python.org/issue28334
Most likely it will be fixed in Python 3.7: https://github.com/python/cpython/pull/123
2017-05-29 14:58:07 +08:00
Sergey M․
941ea38ef5 release 2017.05.29 2017-05-29 00:42:18 +07:00
Sergey M․
99bea8d298 [ChangeLog] Actualize 2017-05-29 00:33:56 +07:00
Yen Chi Hsuan
a49eccdfa7 [youtube] Parse player_url if format URLs are encrypted or DASH MPDs are requested
Fixes #13211
2017-05-28 20:20:20 +08:00
Sergey M․
a846173d93 [xhamster] Simplify (closes #13216) 2017-05-28 07:55:56 +07:00
fiocfun
78e210dea5 [xhamster] Fix author and like/dislike count extraction 2017-05-28 07:55:07 +07:00
Sergey M․
8555204274 [xhamster] Extract categories (closes #11728) 2017-05-28 07:50:15 +07:00
Sergey M․
164fcbfeb7 [abcnews] Improve and remove duplicate test (closes #12851) 2017-05-28 07:06:56 +07:00
Tithen-Firion
bc22df29c4 [abcnews] Add support for embed URLs 2017-05-28 07:06:29 +07:00
Sergey M․
7e688d2f6a [gaskrank] Improve (closes #12493) 2017-05-28 06:47:38 +07:00
motophil
5a6d1da442 [gaskrank] Fix extraction 2017-05-28 06:47:30 +07:00
Sergey M․
703751add4 [medialaan] PEP 8 (closes #12774) 2017-05-28 06:27:57 +07:00
midas02
4050be78e5 [medialaan] Fix videos with missing videoUrl
A rough trick to get around the two different json styles medialaan seems to be using.
Fix for these example videos:
https://vtmkzoom.be/video?aid=45724
https://vtmkzoom.be/video?aid=45425
2017-05-28 06:27:52 +07:00
Sergey M․
4d9fc40100 [dvtv] Improve and fix playlists support (closes #13063) 2017-05-28 06:19:54 +07:00
Jan Kundrát
765522345f [dvtv] Parse adaptive formats as well
The old code hit an error when it attempted to parse the string
"adaptive" for video height. Actually parsing the returned playlists is
a good idea because it adds more output formats, including some
audio-only-ones.
2017-05-28 06:19:46 +07:00
Sergey M․
6bceb36b99 [beam] Improve and add support for mixer.com (closes #13032) 2017-05-28 05:43:04 +07:00
Mike Fährmann
1e0d65f0bd [beam:vod] Add extractor 2017-05-28 05:42:23 +07:00
Sergey M․
03327bc9a6 [cbsinteractive] Relax _VALID_URL (closes #13213) 2017-05-27 22:37:24 +07:00
Yen Chi Hsuan
b407d8533d [utils] Drop an compatibility wrapper for Python < 2.6
addinfourl.getcode is added since Python 2.6a1. As youtube-dl now
requires 2.6+, this is no longer necessary.

See 9b0d46db11
2017-05-27 23:05:02 +08:00
Remita Amine
20e2c9de04 [adn] fix formats extraction 2017-05-26 20:00:44 +01:00
Yen Chi Hsuan
d16c0121b9 [youku] Extract more metadata (closes #10433) 2017-05-27 00:08:37 +08:00
Sergey M․
7f4c3a7439 [cbsnews] Fix extraction (closes #13205) 2017-05-26 22:42:27 +07:00
Sergey M․
28dbde9cc3 release 2017.05.26 2017-05-26 22:29:16 +07:00
Sergey M․
cc304ce588 [ChangeLog] Actualize 2017-05-26 22:27:56 +07:00
Yen Chi Hsuan
98a0618941 [ChangeLog] Update after the fix for #11381 2017-05-26 23:22:54 +08:00
Yen Chi Hsuan
fd545fc6d1 Revert "[youtube] Don't use the DASH manifest from 'get_video_info' if 'use_cipher_signature' is True (#5118)"
This reverts commit 87dc451108.
2017-05-26 23:22:54 +08:00
Sergey M․
97067db2ae [bbc] Add support for authentication 2017-05-26 22:12:24 +07:00
Yen Chi Hsuan
c130f0a37b [tudou] Merge into youku extractor (fixes #12214)
Also, there are no tudou playlists anymore. All playlist URLs points to youku
playlists.
2017-05-26 23:04:42 +08:00
Yen Chi Hsuan
d3d4ba7f24 [youku:show] Fix extraction 2017-05-26 21:59:16 +08:00
Yen Chi Hsuan
5552c9eb0f [utils] Recognize more patterns in strip_jsonp()
Used in Youku Show pages
2017-05-26 21:58:18 +08:00
Yen Chi Hsuan
59ed87cbd9 [youku] Fix extraction (closes #13191) 2017-05-26 19:16:52 +08:00
Sergey M․
b7f8749304 [udemy] Fix extraction for outputs' format entries without URL (closes #13192) 2017-05-25 22:28:26 +07:00
Yen Chi Hsuan
5192ee17e7 [postprocessor/ffmpeg] Fix metadata filename handling on Python 2
Fixes #13182
2017-05-25 22:07:03 +08:00
Sergey M․
e834f04400 [vimeo] Fix formats' sorting (closes #13189) 2017-05-24 22:58:16 +07:00
Remita Amine
884d09f330 [cbsnews] fix extraction for 60 Minutes videos 2017-05-24 09:44:41 +01:00
remitamine
9e35298f97 Merge pull request #12861 from Tithen-Firion/cbsinteractive-fix
[cbsinteractive] update extractor and test cases
2017-05-24 10:21:33 +02:00
Sergey M․
0551f1b07b Credit @gritstub for vevo fix (#12879) 2017-05-23 21:47:40 +07:00
Sergey M․
de53511201 Credit @timendum for rai (#11790) and mediaset (#12964) 2017-05-23 00:41:53 +07:00
Sergey M․
2570e85167 release 2017.05.23 2017-05-23 00:17:48 +07:00
Sergey M․
9dc5ab041f [ChangeLog] Actualize 2017-05-23 00:15:44 +07:00
Sergey M․
01f3c8e290 Credit @fredbourni for noovo (#12792) 2017-05-23 00:08:14 +07:00
Sergey M․
06c1b3ce07 Credit @mphe for streamango (#12643) 2017-05-23 00:07:31 +07:00
Sergey M․
0b75e42dfb Credit @zurfyx for atresplayer improvements (#12548) 2017-05-23 00:00:49 +07:00
Sergey M․
a609e61a90 [downloader/external] Pass -loglevel to ffmpeg downloader (closes #13183) 2017-05-22 23:40:07 +07:00
Ondřej Caletka
afdb387cd8 [streamcz] Add support for subtitles 2017-05-21 15:41:52 +07:00
Sergey M․
dc4e4f90a2 [youtube] Modernize 2017-05-21 01:18:56 +07:00
Protuhj
fdc20f87a6 [youtube] Fix DASH manifest signature decryption (closes #8944) 2017-05-21 01:11:37 +07:00
Sergey M․
35a2d221a3 [toggle] Relax _VALID_URL (closes #13172) 2017-05-20 23:06:30 +07:00
Nii-90
daa4e9ff90 [adobepass] Add support for Brighthouse MSO 2017-05-20 20:50:46 +07:00
Sergey M․
2ca29f1aaf [toypics] Improve and modernize 2017-05-20 01:29:33 +07:00
vobe
77d682da9d [toypics] Fix extraction 2017-05-20 01:18:03 +07:00
Sergey M․
8fffac6927 [njpwworld] Fix extraction (closes #13162) 2017-05-19 23:11:02 +07:00
Sergey M․
5f6fbcea08 [hitbox] Add support for smashcast.tv (closes #13154) 2017-05-19 22:34:00 +07:00
Logan B
00cb0faca8 [mitele] Update app key regex 2017-05-19 21:54:57 +07:00
Sergey M․
bfdf6fcc66 release 2017.05.18.1 2017-05-18 23:00:03 +07:00
Sergey M․
bcaa1dd060 [ChangeLog] Actualize 2017-05-18 22:58:14 +07:00
Sergey M․
0e2d626ddd [jsinterp] Fix typo and cleanup regexes (closes #13134) 2017-05-18 22:57:38 +07:00
Sergey M․
9221d5d7a8 [ChangeLog] Fix typo 2017-05-18 22:37:32 +07:00
Sergey M․
9d63e57d1f release 2017.05.18 2017-05-18 22:30:37 +07:00
Sergey M․
3bc1eea0d8 [ChangeLog] Actualize 2017-05-18 22:29:25 +07:00
Sergey M․
7769f83701 [jsinterp] Add support for quoted names and indexers (closes #13123, closes #13130) 2017-05-18 22:18:33 +07:00
Sergey M․
650bd94716 [vier] Relax regexes and extract more metadata (closes #12539) 2017-05-17 23:39:01 +07:00
mrBliss
36b226d48f [vier] Extract more info
Extract the `episode_number` and `upload_date`. Also extract the real
`description`.
2017-05-17 23:38:50 +07:00
Sergey M․
f2e2f0c777 [extractor/common] Fix rtmp and rtsp formats' URLs in _extract_wowza_formats 2017-05-17 22:20:25 +07:00
Sergey M․
6f76679804 [extractor/common] Add support for schemeless URLs in _extract_wowza_formats (closes #13088, closes #13092) 2017-05-16 22:11:34 +07:00
Sergey M․
7073015a23 [vier] PEP 8 and cleanup 2017-05-15 22:00:53 +07:00
mrBliss
89fd03079b [vier] Improve extraction
+ Add support for authentication
* Bypass authentication when no credentials provded
* Improve extraction robustness
2017-05-15 21:46:55 +07:00
Sergey M․
1c45b7a8a9 [dailymail] Fix sources extraction (closes #13057) 2017-05-14 12:47:19 +07:00
Sergey M․
60f5c9fb19 [utils] Recognize more audio codecs (#13081) 2017-05-14 12:33:33 +07:00
Sergey M․
c360e641e9 [dailymotion] Extend _VALID_URL (closes #13079) 2017-05-14 09:55:40 +07:00
Sergey M․
6f3c632c24 release 2017.05.14 2017-05-14 07:38:40 +07:00
Sergey M․
09b866e171 [ChangeLog] Actualize 2017-05-14 07:37:31 +07:00
Sergey M․
166d12b00c [options] PEP 8 2017-05-14 07:33:24 +07:00
Sergey M․
2b8e6a68f8 [extractor/generic] Add test for mediaset embed 2017-05-14 06:40:19 +07:00
Sergey M․
d105a7edc6 [mediaset] Fix upload date 2017-05-14 06:39:47 +07:00
Sergey M․
5d29af3d15 [extractor/generic] Add support for mediaset embeds 2017-05-14 06:29:16 +07:00
Sergey M․
ca04de463d [mediaset] Add support for shortcut 2017-05-14 06:28:40 +07:00
Sergey M․
946826eec7 [extractor/generic] Remove duplicate limelight code 2017-05-14 06:17:34 +07:00
Sergey M․
76d5a36391 [extractor/common] Respect Width and Height attributes in ISM manifests 2017-05-14 06:11:45 +07:00
Sergey M․
56f9c77f0e [mediaset] Improve extraction (closes #12708, closes #12964) 2017-05-14 05:30:13 +07:00
Timendum
0de136341a [mediaset] Add extractor 2017-05-14 05:30:02 +07:00
Sergey M․
1339ecb2f8 [orf:radio] Cleanup _VALID_URLs (closes #11643) 2017-05-14 04:31:20 +07:00
phaer
efe9316703 [orf:radio] Fix extraction
Since oe1.orf.at has been updated, both ORF radios supported by youtube_dl
use the same API. This commit honors this fact by merging both extractors
into one.
2017-05-14 04:31:14 +07:00
Luca Steeb
851a01aed6 [aljazeera] Extend _VALID_URL 2017-05-14 00:57:02 +07:00
Sergey M․
b845766597 [imdb] Relax _VALID_URL (closes #13056) 2017-05-14 00:32:50 +07:00
Sergey M․
fa26734e07 [postprocessor/metadatafromtitle] Add support regex syntax for --metadata-from-title (closes #13065) 2017-05-14 00:03:15 +07:00
Sergey M․
12f01118b0 [francetv] Add support for mobile.france.tv (closes #13068) 2017-05-13 21:57:00 +07:00
Sergey M․
7fc60f4ee9 [upskill] Add extractor (closes #13043) 2017-05-13 21:52:59 +07:00
Sergey M․
58bb440283 [extractor/generic] Extract wistia embed code into separate method 2017-05-13 21:51:58 +07:00
Remita Amine
7ad4362357 [thescene] fix extraction(closes #13061) 2017-05-12 16:37:09 +01:00
Remita Amine
6c52477f59 [condenast] improve embed support 2017-05-12 16:37:09 +01:00
Yen Chi Hsuan
116283ff64 [liveleak] Fix extraction (#12053) 2017-05-12 19:15:33 +08:00
Yen Chi Hsuan
7274f3d0e9 [douyu] Support Douyu shows (closes #12228) 2017-05-12 18:44:24 +08:00
Sergey M․
3166b1f0ac [myspace] Improve _VALID_URL (closes #13040) 2017-05-10 22:35:46 +07:00
Remita Amine
39ee263819 use platform=desktop in assets url(closes #13041) 2017-05-10 08:50:30 +01:00
Sergey M․
a7ed6b341c release 2017.05.09 2017-05-09 04:20:13 +07:00
Sergey M․
cbd84b5817 [ChangeLog] Actualize 2017-05-09 23:17:22 +07:00
Sergey M․
6d1ded7502 [francetv] Adapt to site redesign (closes #13034) 2017-05-09 23:07:01 +07:00
Remita Amine
5d0968f0af [packtpub] add support for authentication(closes #12622) 2017-05-09 11:15:14 +01:00
Sergey M․
8d65880e24 [drtv] Improve extraction and update tests (closes #13013, closes #13016) 2017-05-09 15:37:09 +07:00
Rasmus Rendal
b972fb037b [drtv] Lower preference for SignLanguage formats (closes #13013) 2017-05-09 15:36:02 +07:00
Remita Amine
5996d21aea [cspan] add support for brightcove live embeds(closes #13028) 2017-05-09 00:51:12 +01:00
Remita Amine
afa0200bf0 [vrv] extract dash formats and subtitles 2017-05-08 20:04:40 +01:00
Sergey M․
e9137224b3 [YoutubeDL] Force restrict filenames when no locale is set for python 2 as well (#13027) 2017-05-09 01:14:02 +07:00
Remita Amine
804181dda9 [funimation] remove codes related to old login method and update test 2017-05-08 18:58:13 +01:00
Remita Amine
8fa17117df [funimation] fix authentication(closes #13021) 2017-05-08 18:13:58 +01:00
Remita Amine
3b859145c2 [adultswim] Fix Extraction(closes #8640)(closes #10950)(closes closes #11042)(closes #12121)
- add support for adobe pass authentication
- add support for live streams
- add support for show pages
2017-05-08 15:07:40 +01:00
Remita Amine
04c09f1961 [turner] extract thumbnail and is_live and strip description 2017-05-08 15:07:40 +01:00
Sergey M․
bf82b87323 [nonktube] Use econfig nuevo URL 2017-05-08 20:13:22 +07:00
Sergey M․
b6eb74e340 [nonktube] Add extractor (closes #8647, closes #13024) 2017-05-08 20:10:39 +07:00
Sergey M․
3d40084b83 [nuevo] Pass headers to _extract_nuevo 2017-05-08 20:03:38 +07:00
Remita Amine
52294cdda7 [nbc] remove unused imports and extract permalink from modified urls 2017-05-07 09:31:14 +01:00
Remita Amine
2eeb588efe [nbc] improve extraction(closes #12364) 2017-05-07 08:59:31 +01:00
Sergey M․
4ac0f573ef release 2017.05.07 2017-05-07 04:51:34 +07:00
Sergey M․
3892a9f4ab [ChangeLog] Actualize 2017-05-07 04:44:54 +07:00
Sergey M․
3995d37da5 [youtube] Fix TFA (#12927) 2017-05-07 04:19:11 +07:00
Sergey M․
e4a75d7932 [test_youtube_chapters] PEP 8 2017-05-07 00:00:11 +07:00
Sergey M․
e00eb564e9 [youtube] Fix authentication (closes #12927) 2017-05-06 23:58:47 +07:00
Yen Chi Hsuan
10c87c151b [utils] Rename try_multipart_encode to _multipart_encode_impl
To state that this is an internal function and people should be careful
when using it outside youtube-dl.
2017-05-06 19:06:18 +08:00
Yen Chi Hsuan
228cd9bb90 [bilibili] Fix video downloading (closes #13001) 2017-05-06 18:58:38 +08:00
Sergey M․
566fbbaefd [rmcdecouverte] Improve (closes #12937) 2017-05-06 17:56:10 +07:00
midas02
74c09c852a [rmcdecouverte] Fix extraction 2017-05-06 17:56:10 +07:00
Remita Amine
fd178b8748 [theplatform] extract chapters 2017-05-06 07:19:07 +01:00
Sergey M․
a57a8e9918 [test_youtube_chapters] Add coding cookie 2017-05-06 05:30:56 +07:00
Tithen-Firion
1f9fefe7f5 [crackle] Update test 2017-05-06 03:39:14 +07:00
Luca Steeb
8b4774dcac [bandcamp] Fix thumbnail extraction 2017-05-06 03:35:42 +07:00
Sergey M․
a99cc4ca16 [pornhub] Extend _VALID_URL (closes #12996) 2017-05-06 02:46:37 +07:00
Sergey M․
9cafc3fd8b [youtube] Extract chapters 2017-05-06 02:27:06 +07:00
Sergey M․
329e3dd5ad [nrk] Extract chapters 2017-05-05 22:59:15 +07:00
Remita Amine
1d9e0a4f40 [vice] update tests and add support for ooyala embeds in article pages 2017-05-05 16:13:12 +01:00
Sergey M․
7ad53cb7ff [laola1tv] PEP 8 2017-05-05 21:59:23 +07:00
Yen Chi Hsuan
b2ad479d17 [utils] Fix multipart_encode for Python < 3.5 2017-05-05 20:51:59 +08:00
Yen Chi Hsuan
4ac6dc3732 [vice] Support Vice articles (closes #12968) 2017-05-05 20:26:51 +08:00
Yen Chi Hsuan
cc7bda4fff [vice] Fix extraction for non en_us videos (closes #12967) 2017-05-05 20:01:02 +08:00
Yen Chi Hsuan
50ad078b7b [gdcvault] Fix extraction for videos with gdc-player.html
Closes #12733
2017-05-05 15:13:40 +08:00
Sergey M․
4947f13cd0 [pbs] Improve multipart video support (closes #12981) 2017-05-04 22:42:49 +07:00
Sergey M․
7f09e523e8 [laola1tv:embed] Fix tests 2017-05-04 22:41:47 +07:00
Remita Amine
4fe14732a2 [laola1tv] fix extraction(closes #12880) 2017-05-04 16:07:08 +01:00
Remita Amine
ff6f9a6704 [extractor/common] fix typo in _extract_akamai_formats 2017-05-04 16:07:08 +01:00
Yen Chi Hsuan
0c26548601 [cda] Implement birthday verification (closes #12789) 2017-05-04 16:26:17 +08:00
Yen Chi Hsuan
5401bea27f [leeco] Fix extraction (closes #12974)
Seems on mobile devices a similar API is used, but I always get an AD
with mimicking that API.
2017-05-04 03:18:56 +08:00
remitamine
7a6d33a9a5 [pbs] extract chapters information 2017-05-02 20:41:48 +01:00
remitamine
fa2a36d9bc [ffmpeg] add support for chapters field postprocessing 2017-05-02 20:41:48 +01:00
remitamine
55949fede6 [common] introduce chapters field 2017-05-02 20:41:48 +01:00
Remita Amine
7fc875195f [amp] imporove thumbnail and subtitle extraction 2017-05-02 00:06:58 +01:00
Tithen-Firion
c6fe5a7e12 [douyutv] Update test 2017-05-02 03:45:27 +08:00
Tithen-Firion
ae21d2fd94 [dotsub] Update test 2017-05-02 02:56:44 +08:00
Tithen-Firion
77481f1386 [democracynow] Update test 2017-05-02 01:38:31 +07:00
Tithen-Firion
d86d169dd5 [dailymotion] Add working test 2017-05-02 01:37:23 +07:00
Tithen-Firion
b9f9f361fa [crunchyroll] Update test 2017-05-02 00:56:51 +07:00
Remita Amine
ab39a25c75 [foxsports] fix extraction(closes #12945) 2017-05-01 09:02:41 +01:00
Tithen-Firion
a146fa1c68 [coub] Update test and remove comment count extraction 2017-05-01 05:54:44 +07:00
Sergey M․
e0c1e9a98c release 2017.05.01 2017-05-01 01:39:52 +07:00
Sergey M․
086041e2f8 [ChangeLog] Actualize 2017-05-01 01:34:51 +07:00
Sergey M․
74da856544 [infoq] Make audio format extraction non fatal (closes #12938) 2017-05-01 01:23:05 +07:00
Sergey M․
9edf47df7b [brightcove] Allow whitespace around attribute names in embedded code 2017-05-01 01:03:47 +07:00
Sergey M․
238cec17ae [extractor/anvato] PEP 8 2017-04-30 22:04:21 +07:00
Sergey M․
50534b7158 [downloader/fragment] PEP 8 2017-04-30 22:04:01 +07:00
Sergey M․
9cd4209724 [zaq1] Improve extraction (closes #12693) 2017-04-30 21:46:05 +07:00
Sergey M․
33a81c2c6f [extractor/common] Extract view count from JSON-LD 2017-04-30 21:45:59 +07:00
Sergey M․
deef31955b [utils] Improve unified_timestamp
Seen at http://zaq1.pl/video/xev0e
2017-04-30 21:45:53 +07:00
slocum
9dac2cec2d [zaq1] Add new extractor 2017-04-30 21:45:47 +07:00
Sergey M․
6ec371cd9e [xvideos] Extract og:duration (closes #12828) 2017-04-30 18:14:01 +07:00
Sander
13081db1f5 [xvideos] Add video duration 2017-04-30 18:10:49 +07:00
Sergey M․
b07ea5eaec [vevo] Modernize 2017-04-30 17:58:22 +07:00
gritstub
5599253009 [vevo] Fix extraction (config.token.key) 2017-04-30 17:56:10 +07:00
Remita Amine
98ce1a3fd3 [utils] add video/mp2t to mimetype2ext 2017-04-30 09:03:10 +01:00
Yen Chi Hsuan
ba5c3caf88 [washingtonpost] Fix invalid escape sequence on Python 3.6 2017-04-30 02:15:28 +08:00
Sergey M․
b5c39537be [noovo] Improve extraction (closes #12792) 2017-04-30 00:24:25 +07:00
Frederic Bournival
1c7c76e4fb [noovo] Add extractor 2017-04-30 00:24:19 +07:00
John Hawkinson
557194591a [washingtonpost] Add support for embeds (closes #12699) 2017-04-29 23:07:26 +07:00
Yen Chi Hsuan
27e70a8f6c Merge pull request #12869 from Tithen-Firion/cbc-update-tests
[cbc] update test cases
2017-04-29 21:34:18 +08:00
Sergey M․
a4c81e4968 [yandexmusic:playlist] Fix extraction for python 3 (closes #12888) 2017-04-29 20:23:26 +07:00
Sergey M․
7986c3abcd [anvato] Improve extraction (closes #12913)
* Promote to regular shortcut based extractor
* Add mcp to access key mapping table
* Add support for embeds extraction
* Add support for anvato embeds in generic extractor
2017-04-29 19:49:04 +07:00
Yen Chi Hsuan
a1ebfd4494 Merge pull request #12854 from Tithen-Firion/appletrailer-test-fix
[appletrailers] update test cases
2017-04-29 19:24:38 +08:00
Yen Chi Hsuan
d19093bd50 Merge pull request #12906 from Tithen-Firion/clean-html-fix
[utils] Fix inconsistent output of clean_html
2017-04-29 15:58:45 +08:00
Yen Chi Hsuan
24eb7c2578 [xtube] Fix extraction with non-standard JSON 'sources'
Closes #12734

Thanks @paulguy for the fix!
2017-04-29 15:55:08 +08:00
Sergey M․
e7db6759e4 [downloader/external] Properly handle live stream downloading cancellation (closes #8932) 2017-04-29 04:33:35 +07:00
Sergey M․
b364c87c42 [tvplayer] Fix extraction (closes #12908) 2017-04-29 03:46:08 +07:00
Tithen-Firion
9222d94510 [test_utils] Add one more clean_html test 2017-04-28 18:05:14 +02:00
Tithen-Firion
edd9221cd2 [utils] Fix inconsistent output of clean_html
`\s` in Python 2.x doesn't match unicode whitespace characters by
default
2017-04-28 17:34:27 +02:00
Sergey M․
bc8a2ea071 release 2017.04.28 2017-04-28 18:30:03 +07:00
Sergey M․
7527923371 [ChangeLog] Actualize 2017-04-28 18:27:29 +07:00
Remita Amine
20783b8b50 [aenetworks] fix extraction for shows with single season 2017-04-28 12:04:56 +01:00
Remita Amine
bf2a5555c0 [go] add support for Disney, DisneyJunior and DisneyXD show pages 2017-04-28 09:48:52 +01:00
Remita Amine
fb8e8b2d16 [adobepass] use geo verification headers for all requests 2017-04-28 09:48:52 +01:00
Yen Chi Hsuan
b62985a9a5 [youtube] Recognize another HTML5 player URL (#12885) 2017-04-28 16:25:04 +08:00
Yen Chi Hsuan
e31fed95b4 [youtube] Recognize new locale-based player URLs (fixes #12885) 2017-04-28 15:48:30 +08:00
Tithen-Firion
3fd0f70f6a [cbslocal] Update test 2017-04-28 04:26:59 +07:00
Tithen-Firion
33c62efc32 [collegerama] Update tests 2017-04-28 04:00:49 +07:00
Tithen-Firion
6b4ddd336c [afreecatv] Fix title extraction 2017-04-28 04:00:15 +07:00
Tithen-Firion
c12b4b80f8 [archiveorg] Update test 2017-04-28 03:48:32 +07:00
Tithen-Firion
064fafe932 [appleconnect] Update test 2017-04-28 03:47:25 +07:00
Tithen-Firion
ac1a5b9a12 [audioboom] Update test 2017-04-28 03:36:28 +07:00
Tithen-Firion
a15777491a [atresplayer] Update test 2017-04-28 03:32:25 +07:00
Tithen-Firion
d8571dd6bf [bleacherreport] Update tests 2017-04-28 03:28:26 +07:00
Sergey M․
c0fa4245ce [downloader/fragment] Remove assert for resume_len when no fragments downloaded
This may be incorrect due some header (e.g. flv header in f4m downloader)
2017-04-28 03:26:19 +07:00
Tithen-Firion
8814ae42bc [beeg] Update test 2017-04-28 03:14:11 +07:00
Tithen-Firion
0f63dc2402 [bandcamp] Update test 2017-04-28 03:13:12 +07:00
Tithen-Firion
dde97ea8da [canalc2] Update test 2017-04-28 03:07:42 +07:00
Sergey M․
30bb6ce1a4 [test_InfoExtractor] Fix test_parse_m3u8_formats 2017-04-28 03:01:43 +07:00
Sergey M․
c89b49f743 [extractor/common] Add manifest_url for explicit group rendition formats 2017-04-28 03:00:14 +07:00
Tithen-Firion
6f4a888416 [br] Update test 2017-04-28 02:53:11 +07:00
Tithen-Firion
f5edd7ae51 [clipfish] Update test 2017-04-28 02:51:30 +07:00
Tithen-Firion
96820c1c6b [cbsinteractive] extract formats with CBSIE 2017-04-27 20:23:52 +02:00
Tithen-Firion
c95e2b5911 [cbc] update test cases 2017-04-27 18:07:07 +02:00
Tithen-Firion
374560f018 [test_download] Fix order when testing file's md5 2017-04-27 22:27:34 +07:00
Sergey M․
ff99fe529e Don't list master m3u8 playlists in format list (closes #12832) 2017-04-27 21:53:17 +07:00
Tithen-Firion
e095109da1 [cbsinteractive] update test cases 2017-04-27 15:40:17 +02:00
Tithen-Firion
d68afc5bc9 [cbsinteractive] fix extractor 2017-04-27 15:27:01 +02:00
Tithen-Firion
76c1951036 [appletrailers] update test cases 2017-04-27 10:04:21 +02:00
Lucas M
e8bfe2a946 [streamable] Add support for new embedded URL schema 2017-04-26 23:39:53 +07:00
Sergey M․
3dc8b61b7f [arte:+7] Relax _VALID_URL (closes #12837) 2017-04-26 01:55:29 +07:00
Sergey M․
a82f41841d release 2017.04.26 2017-04-26 00:06:12 +07:00
Sergey M․
30a4ab191a [ChangeLog] Actualize 2017-04-26 00:03:13 +07:00
Sergey M․
ac9c69ace7 [extractor/common] Improve jwplayer regex 2017-04-25 23:46:05 +07:00
Sergey M․
85f6de25e4 [downloader/fragment] Clarify current_fragment's index and mark as experimental 2017-04-25 23:33:35 +07:00
Sergey M․
538eee7b6a Add missing test m3u8 file 2017-04-25 22:26:30 +07:00
Yen Chi Hsuan
9f54ae2873 Ignore and clean *.ytdl files 2017-04-25 22:42:55 +08:00
Yen Chi Hsuan
01cb57016f [iqiyi] Fix extraction of Yule videos 2017-04-25 22:23:57 +08:00
Sergey M․
290f64dbaa [downloader/fragment] Improve .ytdl format and start documenting 2017-04-24 23:50:20 +07:00
Sergey M․
adb4b03cd5 [downloader/fragment] Don't process ytdl file when it's not needed yet 2017-04-24 23:05:56 +07:00
Sergey M․
0eee52f34b Introduce --keep-fragments 2017-04-24 03:09:08 +07:00
Sergey M․
d3f0687cf7 [downloader/fragment] Use temp file for current fragment 2017-04-24 02:54:17 +07:00
Sergey M․
a4d6cf970c [YoutubeDL] Fix output template for missing timestamp (closes #12796) 2017-04-24 00:50:39 +07:00
Sergey M․
3019cb0c99 [extractor/common] Rephrase comment 2017-04-23 11:52:07 +07:00
Sergey M․
ddd258f922 [test_InfoExtractor] Add m3u8 parsing test for NAME attribute in EXT-X-STREAM-INF tag 2017-04-23 11:49:57 +07:00
Sergey M․
07ad0cf34f [vidio] Improve and sort formats 2017-04-23 11:48:51 +07:00
Sergey M․
9c99bef704 [extractor/common] Use float for scaled tbr 2017-04-23 11:33:49 +07:00
Remita Amine
ffbc8386b9 [brightcove] match only video elements with data-video-id attribute 2017-04-22 22:26:20 +01:00
Remita Amine
4abdba643c [downloader/fragment] remove unused code 2017-04-22 18:19:47 +01:00
Remita Amine
3e0304fe6e [downloader/fragment] use the documented names for fragment progress_hooks fields 2017-04-22 16:42:24 +01:00
Yen Chi Hsuan
fbf56be213 [iqiyi] Fix playlist detection (#12504) 2017-04-22 22:11:37 +08:00
Yen Chi Hsuan
54f54fcca7 [socks] Report errors elegantly when credentails are required but missing
In some non-standard implementations, the server may respond AUTH_USER_PASS
even if's not listed in available authentication methods. (it should
respond AUTH_NO_ACCEPTABLE per standards)
2017-04-22 21:48:41 +08:00
Yen Chi Hsuan
facfd79f9a [azubu] Remove extractor as the site is gone (closes #12813) 2017-04-22 21:20:25 +08:00
Yen Chi Hsuan
3110bb937d [porn91] Fix extraction (closes #12814) 2017-04-22 21:16:36 +08:00
Sergey M․
cb2520802d [extractor/common] Improve m3u8 extraction (closes #12211)
* Extract m3u8 parsing to separate method
* Improve rendition groups extraction
* Build stream name according stream GROUP-ID
* Ignore reference to AUDIO group without URI when stream has no CODECS
+ Add test coverage for parsing m3u8 from #11507, #11995, #12211 and twitch vod
2017-04-22 07:01:00 +07:00
Sergey M․
f779958250 [vidzi] Fix extraction (closes #12793) 2017-04-21 23:37:06 +07:00
Remita Amine
8abc7dca39 [amp] extract error message(closes #12795) 2017-04-20 05:16:41 +01:00
Remita Amine
ea0c2f219c [downloader/fragment] use a general file to store fragment download context 2017-04-19 18:53:15 +01:00
Sergey M․
481ef51e23 [brightcove] PEP 8 2017-04-19 21:47:03 +07:00
Remita Amine
5b995f713b [utils] add support for ttml styles 2017-04-19 14:38:40 +01:00
Remita Amine
75a2485407 [fragment,hls,f4m,dash,ism] improve fragment downloading
- resume immediately
- no need to concatenate segments and decrypt them on every resume
- no need to save temp files for segments

and for hls downloader:
- no need to download keys for segments that already downloaded
2017-04-19 11:46:07 +01:00
Remita Amine
58f6ab72ed [odnoklassniki] update tests 2017-04-19 00:16:55 +01:00
Sergey M․
2dc48df5bc [xfileshare] Add support for gorillavid.com and daclips.com (closes #12776) 2017-04-18 23:58:37 +07:00
Sergey M․
18848d226a [instagram] Fix extraction (closes #12777) 2017-04-18 22:40:26 +07:00
Sergey M․
a32a9a7ef5 [extractor/common] Add support multiple getters in try_get 2017-04-18 22:39:58 +07:00
Sergey M․
bae1404893 [extractor/common] Add support for video of WebPage context in _json_ld (closes #12778) 2017-04-18 22:21:38 +07:00
Yen Chi Hsuan
06d0ad9a4e [brightcove] Support URLs with bcpid instead of playerID
Fixes #12482
2017-04-18 23:04:22 +08:00
Sergey M․
f631b55791 [brightcove] Fix _extract_url (closes #12782) 2017-04-18 21:46:25 +07:00
Remita Amine
bf1b87cd91 [common] Relax JWPlayer regex and remove duplicate urls(#12768) 2017-04-17 08:48:24 +01:00
Remita Amine
1c35b3da44 [odnoklassniki] extract m3u8 formats 2017-04-16 21:27:08 +01:00
168 changed files with 5234 additions and 2528 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.04.17*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.04.17**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.06.12*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.06.12**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.04.17
[debug] youtube-dl version 2017.06.12
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

2
.gitignore vendored
View File

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

View File

@@ -212,3 +212,11 @@ Xiao Di Guan
Thomas Winant
Daniel Twardowski
Jeremie Jarosh
Gerard Rovira
Marvin Ewald
Frédéric Bournival
Timendum
gritstub
Adam Voss
Mike Fährmann
Jan Kundrát

293
ChangeLog
View File

@@ -1,3 +1,296 @@
version 2017.06.12
Core
* [utils] Handle compat_HTMLParseError in extract_attributes (#13349)
+ [compat] Introduce compat_HTMLParseError
* [utils] Improve unified_timestamp
* [extractor/generic] Ensure format id is unicode string
* [extractor/common] Return unicode string from _match_id
+ [YoutubeDL] Sanitize more fields (#13313)
Extractors
+ [xfileshare] Add support for rapidvideo.tv (#13348)
* [xfileshare] Modernize and pass Referer
+ [rutv] Add support for testplayer.vgtrk.com (#13347)
+ [newgrounds] Extract more metadata (#13232)
+ [newgrounds:playlist] Add support for playlists (#10611)
* [newgrounds] Improve formats and uploader extraction (#13346)
* [msn] Fix formats extraction
* [turbo] Ensure format id is string
* [sexu] Ensure height is int
* [jove] Ensure comment count is int
* [golem] Ensure format id is string
* [gfycat] Ensure filesize is int
* [foxgay] Ensure height is int
* [flickr] Ensure format id is string
* [sohu] Fix numeric fields
* [safari] Improve authentication detection (#13319)
* [liveleak] Ensure height is int (#13313)
* [streamango] Make title optional (#13292)
* [rtlnl] Improve URL regular expression (#13295)
* [tvplayer] Fix extraction (#13291)
version 2017.06.05
Core
* [YoutubeDL] Don't emit ANSI escape codes on Windows (#13270)
Extractors
+ [bandcamp:weekly] Add support for bandcamp weekly (#12758)
* [pornhub:playlist] Fix extraction (#13281)
- [godtv] Remove extractor (#13175)
* [safari] Fix typo (#13252)
* [youtube] Improve chapters extraction (#13247)
* [1tv] Lower preference for HTTP formats (#13246)
* [francetv] Relax URL regular expression
* [drbonanza] Fix extraction (#13231)
* [packtpub] Fix authentication (#13240)
version 2017.05.29
Extractors
* [youtube] Fix DASH MPD extraction for videos with non-encrypted format URLs
(#13211)
* [xhamster] Fix uploader and like/dislike count extraction (#13216))
+ [xhamster] Extract categories (#11728)
+ [abcnews] Add support for embed URLs (#12851)
* [gaskrank] Fix extraction (#12493)
* [medialaan] Fix videos with missing videoUrl (#12774)
* [dvtv] Fix playlist support
+ [dvtv] Add support for DASH and HLS formats (#3063)
+ [beam:vod] Add support for beam.pro/mixer.com VODs (#13032))
* [cbsinteractive] Relax URL regular expression (#13213)
* [adn] Fix formats extraction
+ [youku] Extract more metadata (#10433)
* [cbsnews] Fix extraction (#13205)
version 2017.05.26
Core
+ [utils] strip_jsonp() can recognize more patterns
* [postprocessor/ffmpeg] Fix metadata filename handling on Python 2 (#13182)
Extractors
+ [youtube] DASH MPDs with cipher signatures are recognized now (#11381)
+ [bbc] Add support for authentication
* [tudou] Merge into youku extractor (#12214)
* [youku:show] Fix extraction
* [youku] Fix extraction (#13191)
* [udemy] Fix extraction for outputs' format entries without URL (#13192)
* [vimeo] Fix formats' sorting (#13189)
* [cbsnews] Fix extraction for 60 Minutes videos (#12861)
version 2017.05.23
Core
+ [downloader/external] Pass -loglevel to ffmpeg downloader (#13183)
+ [adobepass] Add support for Bright House Networks (#13149)
Extractors
+ [streamcz] Add support for subtitles (#13174)
* [youtube] Fix DASH manifest signature decryption (#8944, #13156)
* [toggle] Relax URL regular expression (#13172)
* [toypics] Fix extraction (#13077)
* [njpwworld] Fix extraction (#13162, #13169)
+ [hitbox] Add support for smashcast.tv (#13154)
* [mitele] Update app key regular expression (#13158)
version 2017.05.18.1
Core
* [jsinterp] Fix typo and cleanup regular expressions (#13134)
version 2017.05.18
Core
+ [jsinterp] Add support for quoted names and indexers (#13123, #13124, #13125,
#13126, #13128, #13129, #13130, #13131, #13132)
+ [extractor/common] Add support for schemeless URLs in _extract_wowza_formats
(#13088, #13092)
+ [utils] Recognize more audio codecs (#13081)
Extractors
+ [vier] Extract more metadata (#12539)
* [vier] Improve extraction (#12801)
+ Add support for authentication
* Bypass authentication when no credentials provided
* Improve extraction robustness
* [dailymail] Fix sources extraction (#13057)
* [dailymotion] Extend URL regular expression (#13079)
version 2017.05.14
Core
+ [extractor/common] Respect Width and Height attributes in ISM manifests
+ [postprocessor/metadatafromtitle] Add support regular expression syntax for
--metadata-from-title (#13065)
Extractors
+ [mediaset] Add support for video.mediaset.it (#12708, #12964)
* [orf:radio] Fix extraction (#11643, #12926)
* [aljazeera] Extend URL regular expression (#13053)
* [imdb] Relax URL regular expression (#13056)
+ [francetv] Add support for mobile.france.tv (#13068)
+ [upskill] Add support for upskillcourses.com (#13043)
* [thescene] Fix extraction (#13061)
* [condenast] Improve embed support
* [liveleak] Fix extraction (#12053)
+ [douyu] Support Douyu shows (#12228)
* [myspace] Improve URL regular expression (#13040)
* [adultswim] Use desktop platform in assets URL (#13041)
version 2017.05.09
Core
* [YoutubeDL] Force --restrict-filenames when no locale is set on all python
versions (#13027)
Extractors
* [francetv] Adapt to site redesign (#13034)
+ [packtpub] Add support for authentication (#12622)
* [drtv] Lower preference for SignLanguage formats (#13013, #13016)
+ [cspan] Add support for brightcove live embeds (#13028)
* [vrv] Extract DASH formats and subtitles
* [funimation] Fix authentication (#13021)
* [adultswim] Fix extraction (#8640, #10950, #11042, #12121)
+ Add support for Adobe Pass authentication
+ Add support for live streams
+ Add support for show pages
* [turner] Extract thumbnail, is_live and strip description
+ [nonktube] Add support for nonktube.com (#8647, #13024)
+ [nuevo] Pass headers to _extract_nuevo
* [nbc] Improve extraction (#12364)
version 2017.05.07
Common
* [extractor/common] Fix typo in _extract_akamai_formats
+ [postprocessor/ffmpeg] Embed chapters into media file with --add-metadata
+ [extractor/common] Introduce chapters meta field
Extractors
* [youtube] Fix authentication (#12820, #12927, #12973, #12992, #12993, #12995,
#13003)
* [bilibili] Fix video downloading (#13001)
* [rmcdecouverte] Fix extraction (#12937)
* [theplatform] Extract chapters
* [bandcamp] Fix thumbnail extraction (#12980)
* [pornhub] Extend URL regular expression (#12996)
+ [youtube] Extract chapters
+ [nrk] Extract chapters
+ [vice] Add support for ooyala embeds in article pages
+ [vice] Support vice articles (#12968)
* [vice] Fix extraction for non en_us videos (#12967)
* [gdcvault] Fix extraction for some videos (#12733)
* [pbs] Improve multipart video support (#12981)
* [laola1tv] Fix extraction (#12880)
+ [cda] Support birthday verification (#12789)
* [leeco] Fix extraction (#12974)
+ [pbs] Extract chapters
* [amp] Imporove thumbnail and subtitles extraction
* [foxsports] Fix extraction (#12945)
- [coub] Remove comment count extraction (#12941)
version 2017.05.01
Core
+ [extractor/common] Extract view count from JSON-LD
* [utils] Improve unified_timestamp
+ [utils] Add video/mp2t to mimetype2ext
* [downloader/external] Properly handle live stream downloading cancellation
(#8932)
+ [utils] Add support for unicode whitespace in clean_html on python 2 (#12906)
Extractors
* [infoq] Make audio format extraction non fatal (#12938)
* [brightcove] Allow whitespace around attribute names in embedded code
+ [zaq1] Add support for zaq1.pl (#12693)
+ [xvideos] Extract duration (#12828)
* [vevo] Fix extraction (#12879)
+ [noovo] Add support for noovo.ca (#12792)
+ [washingtonpost] Add support for embeds (#12699)
* [yandexmusic:playlist] Fix extraction for python 3 (#12888)
* [anvato] Improve extraction (#12913)
* Promote to regular shortcut based extractor
* Add mcp to access key mapping table
* Add support for embeds extraction
* Add support for anvato embeds in generic extractor
* [xtube] Fix extraction for older FLV videos (#12734)
* [tvplayer] Fix extraction (#12908)
version 2017.04.28
Core
+ [adobepass] Use geo verification headers for all requests
- [downloader/fragment] Remove assert for resume_len when no fragments
downloaded
+ [extractor/common] Add manifest_url for explicit group rendition formats
* [extractor/common] Fix manifest_url for m3u8 formats
- [extractor/common] Don't list master m3u8 playlists in format list (#12832)
Extractor
* [aenetworks] Fix extraction for shows with single season
+ [go] Add support for Disney, DisneyJunior and DisneyXD show pages
* [youtube] Recognize new locale-based player URLs (#12885)
+ [streamable] Add support for new embedded URL schema (#12844)
* [arte:+7] Relax URL regular expression (#12837)
version 2017.04.26
Core
* Introduce --keep-fragments for keeping fragments of fragmented download
on disk after download is finished
* [YoutubeDL] Fix output template for missing timestamp (#12796)
* [socks] Handle cases where credentials are required but missing
* [extractor/common] Improve HLS extraction (#12211)
* Extract m3u8 parsing to separate method
* Improve rendition groups extraction
* Build stream name according stream GROUP-ID
* Ignore reference to AUDIO group without URI when stream has no CODECS
* Use float for scaled tbr in _parse_m3u8_formats
* [utils] Add support for TTML styles in dfxp2srt
* [downloader/hls] No need to download keys for fragments that have been
already downloaded
* [downloader/fragment] Improve fragment downloading
* Resume immediately
* Don't concatenate fragments and decrypt them on every resume
* Optimize disk storage usage, don't store intermediate fragments on disk
* Store bookkeeping download state file
+ [extractor/common] Add support for multiple getters in try_get
+ [extractor/common] Add support for video of WebPage context in _json_ld
(#12778)
+ [extractor/common] Relax JWPlayer regular expression and remove
duplicate URLs (#12768)
Extractors
* [iqiyi] Fix extraction of Yule videos
* [vidio] Improve extraction and sort formats
+ [brightcove] Match only video elements with data-video-id attribute
* [iqiyi] Fix playlist detection (#12504)
- [azubu] Remove extractor (#12813)
* [porn91] Fix extraction (#12814)
* [vidzi] Fix extraction (#12793)
+ [amp] Extract error message (#12795)
+ [xfileshare] Add support for gorillavid.com and daclips.com (#12776)
* [instagram] Fix extraction (#12777)
+ [generic] Support Brightcove videos in <iframe> (#12482)
+ [brightcove] Support URLs with bcpid instead of playerID (#12482)
* [brightcove] Fix _extract_url (#12782)
+ [odnoklassniki] Extract HLS formats
version 2017.04.17
Extractors

View File

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

View File

@@ -145,18 +145,18 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
--max-views COUNT Do not download any videos with more than
COUNT views
--match-filter FILTER Generic video filter. Specify any key (see
help for -o for a list of available keys)
to match if the key is present, !key to
check if the key is not present, key >
NUMBER (like "comment_count > 12", also
works with >=, <, <=, !=, =) to compare
against a number, key = 'LITERAL' (like
"uploader = 'Mike Smith'", also works with
!=) to match against a string literal and &
to require multiple matches. Values which
are not known are excluded unless you put a
question mark (?) after the operator. For
example, to only match videos that have
the "OUTPUT TEMPLATE" for a list of
available keys) to match if the key is
present, !key to check if the key is not
present, key > NUMBER (like "comment_count
> 12", also works with >=, <, <=, !=, =) to
compare against a number, key = 'LITERAL'
(like "uploader = 'Mike Smith'", also works
with !=) to match against a string literal
and & to require multiple matches. Values
which are not known are excluded unless you
put a question mark (?) after the operator.
For example, to only match videos that have
been liked more than 100 times and disliked
less than 50 times (or the dislike
functionality is not available at the given
@@ -187,6 +187,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
and ISM)
--abort-on-unavailable-fragment Abort downloading when some fragment is not
available
--keep-fragments Keep downloaded fragments on disk after
downloading is finished; fragments are
erased by default
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer Do not automatically adjust the buffer
@@ -274,8 +277,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
--get-filename Simulate, quiet but print output filename
--get-format Simulate, quiet but print output format
-j, --dump-json Simulate, quiet but print JSON information.
See --output for a description of available
keys.
See the "OUTPUT TEMPLATE" for a description
of available keys.
-J, --dump-single-json Simulate, quiet but print JSON information
for each command-line argument. If the URL
refers to a playlist, dump the whole
@@ -397,12 +400,14 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
--add-metadata Write metadata to the video file
--metadata-from-title FORMAT Parse additional metadata like song title /
artist from the video title. The format
syntax is the same as --output, the parsed
parameters replace existing values.
Additional templates: %(album)s,
%(artist)s. Example: --metadata-from-title
"%(artist)s - %(title)s" matches a title
like "Coldplay - Paradise"
syntax is the same as --output. Regular
expression with named capture groups may
also be used. The parsed parameters replace
existing values. Example: --metadata-from-
title "%(artist)s - %(title)s" matches a
title like "Coldplay - Paradise". Example
(regex): --metadata-from-title
"(?P<artist>.+?) - (?P<title>.+)"
--xattrs Write metadata to the video file's xattrs
(using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the
@@ -469,7 +474,10 @@ machine twitch login my_twitch_account_name password my_twitch_password
```
To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
On Windows you may also need to setup the `%HOME%` environment variable manually.
On Windows you may also need to setup the `%HOME%` environment variable manually. For example:
```
set HOME=%USERPROFILE%
```
# OUTPUT TEMPLATE
@@ -527,13 +535,14 @@ The basic usage is not to set any template arguments when downloading a single f
- `playlist_id` (string): Playlist identifier
- `playlist_title` (string): Playlist title
Available for the video that belongs to some logical chapter or section:
- `chapter` (string): Name or title of the chapter the video belongs to
- `chapter_number` (numeric): Number of the chapter the video belongs to
- `chapter_id` (string): Id of the chapter the video belongs to
Available for the video that is an episode of some series or programme:
- `series` (string): Title of the series or programme the video episode belongs to
- `season` (string): Title of the season the video episode belongs to
- `season_number` (numeric): Number of the season the video episode belongs to
@@ -543,6 +552,7 @@ Available for the video that is an episode of some series or programme:
- `episode_id` (string): Id of the video episode
Available for the media that is a track or a part of a music album:
- `track` (string): Title of the track
- `track_number` (numeric): Number of the track within an album or a disc
- `track_id` (string): Id of the track
@@ -644,7 +654,7 @@ Also filtering work for comparisons `=` (equals), `!=` (not equals), `^=` (begin
- `acodec`: Name of the audio codec in use
- `vcodec`: Name of the video codec in use
- `container`: Name of the container format
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `m3u8`, or `m3u8_native`)
- `protocol`: The protocol that will be used for the actual download, lower-case (`http`, `https`, `rtsp`, `rtmp`, `rtmpe`, `mms`, `f4m`, `ism`, `http_dash_segments`, `m3u8`, or `m3u8_native`)
- `format_id`: A short description of the format
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the video hoster.

View File

@@ -45,6 +45,7 @@
- **anderetijden**: npo.nl and ntr.nl
- **AnimeOnDemand**
- **anitube.se**
- **Anvato**
- **AnySex**
- **Aparat**
- **AppleConnect**
@@ -81,20 +82,18 @@
- **AZMedien**: AZ Medien videos
- **AZMedienPlaylist**: AZ Medien playlists
- **AZMedienShowPlaylist**: AZ Medien show playlists
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
- **bambuser**
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **Bandcamp:weekly**
- **bangumi.bilibili.com**: BiliBili番剧
- **bbc**: BBC
- **bbc.co.uk**: BBC iPlayer
- **bbc.co.uk:article**: BBC articles
- **bbc.co.uk:iplayer:playlist**
- **bbc.co.uk:playlist**
- **Beam:live**
- **Beatport**
- **Beeg**
- **BehindKink**
@@ -217,6 +216,7 @@
- **DiscoveryVR**
- **Disney**
- **Dotsub**
- **DouyuShow**
- **DouyuTV**: 斗鱼
- **DPlay**
- **DPlayIt**
@@ -282,7 +282,8 @@
- **france2.fr:generation-quoi**
- **FranceCulture**
- **FranceInter**
- **francetv**: France 2, 3, 4, 5 and Ô
- **FranceTV**
- **FranceTVEmbed**
- **francetvinfo.fr**
- **Freesound**
- **freespeech.org**
@@ -310,7 +311,6 @@
- **Go**
- **Go90**
- **GodTube**
- **GodTV**
- **Golem**
- **GoogleDrive**
- **Goshgay**
@@ -433,6 +433,7 @@
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **Medialaan**
- **Mediaset**
- **Medici**
- **Meipai**: 美拍
- **MelonVOD**
@@ -451,6 +452,8 @@
- **mixcloud:playlist**
- **mixcloud:stream**
- **mixcloud:user**
- **Mixer:live**
- **Mixer:vod**
- **MLB**
- **Mnet**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
@@ -509,6 +512,7 @@
- **netease:song**: 网易云音乐
- **Netzkino**
- **Newgrounds**
- **NewgroundsPlaylist**
- **Newstube**
- **NextMedia**: 蘋果日報
- **NextMediaActionNews**: 蘋果日報 - 動新聞
@@ -531,6 +535,8 @@
- **NJPWWorld**: 新日本プロレスワールド
- **NobelPrize**
- **Noco**
- **NonkTube**
- **Noovo**
- **Normalboots**
- **NosVideo**
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
@@ -602,7 +608,6 @@
- **pluralsight**
- **pluralsight:course**
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **Pokemon**
- **PolskieRadio**
@@ -800,16 +805,13 @@
- **ToonGoggles**
- **Tosh**: Tosh.0
- **tou.tv**
- **Toypics**: Toypics user profile
- **Toypics**: Toypics video
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **TruTV**
- **Tube8**
- **TubiTv**
- **tudou**
- **tudou:album**
- **tudou:playlist**
- **Tumblr**
- **tunein:clip**
- **tunein:program**
@@ -860,6 +862,8 @@
- **uol.com.br**
- **uplynk**
- **uplynk:preplay**
- **Upskill**
- **UpskillCourse**
- **Urort**: NRK P3 Urørt
- **URPlay**
- **USANetwork**
@@ -879,9 +883,10 @@
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **Viafree**
- **Vice**
- **vice**
- **vice:article**
- **vice:show**
- **Viceland**
- **ViceShow**
- **Vidbit**
- **Viddler**
- **Videa**
@@ -970,7 +975,7 @@
- **WSJArticle**
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC, VidBom, vidlo, RapidVideo.TV
- **XHamster**
- **XHamsterEmbed**
- **xiami:album**: 虾米音乐 - 专辑
@@ -1015,6 +1020,7 @@
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **Zaq1**
- **ZDF**
- **ZDFChannel**
- **zingmp3**: mp3.zing.vn

View File

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

View File

@@ -225,7 +225,7 @@ def generator(test_case, tname):
format_bytes(got_fsize)))
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5'])
self.assertEqual(tc['md5'], md5_for_file)
# Finally, check test cases' data again but this time against
# extracted data from info JSON file written during processing
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'

View File

@@ -44,6 +44,7 @@ from youtube_dl.utils import (
limit_length,
mimetype2ext,
month_by_name,
multipart_encode,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
@@ -338,6 +339,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('UNKNOWN DATE FORMAT'), None)
self.assertEqual(unified_timestamp('May 16, 2016 11:15 PM'), 1463440500)
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@@ -619,6 +622,16 @@ class TestUtil(unittest.TestCase):
'http://example.com/path', {'test': '第二行тест'})),
query_dict('http://example.com/path?test=%E7%AC%AC%E4%BA%8C%E8%A1%8C%D1%82%D0%B5%D1%81%D1%82'))
def test_multipart_encode(self):
self.assertEqual(
multipart_encode({b'field': b'value'}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="field"\r\n\r\nvalue\r\n--AAAAAA--\r\n')
self.assertEqual(
multipart_encode({'欄位'.encode('utf-8'): ''.encode('utf-8')}, boundary='AAAAAA')[0],
b'--AAAAAA\r\nContent-Disposition: form-data; name="\xe6\xac\x84\xe4\xbd\x8d"\r\n\r\n\xe5\x80\xbc\r\n--AAAAAA--\r\n')
self.assertRaises(
ValueError, multipart_encode, {b'field': b'value'}, boundary='value')
def test_dict_get(self):
FALSE_VALUES = {
'none': None,
@@ -666,6 +679,14 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('window.cb && window.cb({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('window.cb && cb({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape(''), '')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@@ -895,10 +916,13 @@ class TestUtil(unittest.TestCase):
supports_outside_bmp = False
if supports_outside_bmp:
self.assertEqual(extract_attributes('<e x="Smile &#128512;!">'), {'x': 'Smile \U0001f600!'})
# Malformed HTML should not break attributes extraction on older Python
self.assertEqual(extract_attributes('<mal"formed/>'), {})
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
self.assertEqual(
@@ -1069,6 +1093,47 @@ The first line
'''
self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data)
dfxp_data_with_style = '''<?xml version="1.0" encoding="utf-8"?>
<tt xmlns="http://www.w3.org/2006/10/ttaf1" xmlns:ttp="http://www.w3.org/2006/10/ttaf1#parameter" ttp:timeBase="media" xmlns:tts="http://www.w3.org/2006/10/ttaf1#style" xml:lang="en" xmlns:ttm="http://www.w3.org/2006/10/ttaf1#metadata">
<head>
<styling>
<style id="s2" style="s0" tts:color="cyan" tts:fontWeight="bold" />
<style id="s1" style="s0" tts:color="yellow" tts:fontStyle="italic" />
<style id="s3" style="s0" tts:color="lime" tts:textDecoration="underline" />
<style id="s0" tts:backgroundColor="black" tts:fontStyle="normal" tts:fontSize="16" tts:fontFamily="sansSerif" tts:color="white" />
</styling>
</head>
<body tts:textAlign="center" style="s0">
<div>
<p begin="00:00:02.08" id="p0" end="00:00:05.84">default style<span tts:color="red">custom style</span></p>
<p style="s2" begin="00:00:02.08" id="p0" end="00:00:05.84"><span tts:color="lime">part 1<br /></span><span tts:color="cyan">part 2</span></p>
<p style="s3" begin="00:00:05.84" id="p1" end="00:00:09.56">line 3<br />part 3</p>
<p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:02,080 --> 00:00:05,839
<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
2
00:00:02,080 --> 00:00:05,839
<b><font color="cyan" face="sansSerif" size="16"><font color="lime">part 1
</font>part 2</font></b>
3
00:00:05,839 --> 00:00:09,560
<u><font color="lime">line 3
part 3</font></u>
4
00:00:09,560 --> 00:00:12,359
<i><u><font color="yellow"><font color="lime">inner
</font>style</font></u></i>
'''
self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])

View File

@@ -0,0 +1,275 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import expect_value
from youtube_dl.extractor import YoutubeIE
class TestYoutubeChapters(unittest.TestCase):
_TEST_CASES = [
(
# https://www.youtube.com/watch?v=A22oy8dFjqc
# pattern: 00:00 - <title>
'''This is the absolute ULTIMATE experience of Queen's set at LIVE AID, this is the best video mixed to the absolutely superior stereo radio broadcast. This vastly superior audio mix takes a huge dump on all of the official mixes. Best viewed in 1080p. ENJOY! ***MAKE SURE TO READ THE DESCRIPTION***<br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+36);return false;">00:36</a> - Bohemian Rhapsody<br /><a href="#" onclick="yt.www.watch.player.seekTo(02*60+42);return false;">02:42</a> - Radio Ga Ga<br /><a href="#" onclick="yt.www.watch.player.seekTo(06*60+53);return false;">06:53</a> - Ay Oh!<br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+34);return false;">07:34</a> - Hammer To Fall<br /><a href="#" onclick="yt.www.watch.player.seekTo(12*60+08);return false;">12:08</a> - Crazy Little Thing Called Love<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+03);return false;">16:03</a> - We Will Rock You<br /><a href="#" onclick="yt.www.watch.player.seekTo(17*60+18);return false;">17:18</a> - We Are The Champions<br /><a href="#" onclick="yt.www.watch.player.seekTo(21*60+12);return false;">21:12</a> - Is This The World We Created...?<br /><br />Short song analysis:<br /><br />- "Bohemian Rhapsody": Although it's a short medley version, it's one of the best performances of the ballad section, with Freddie nailing the Bb4s with the correct studio phrasing (for the first time ever!).<br /><br />- "Radio Ga Ga": Although it's missing one chorus, this is one of - if not the best - the best versions ever, Freddie nails all the Bb4s and sounds very clean! Spike Edney's Roland Jupiter 8 also really shines through on this mix, compared to the DVD releases!<br /><br />- "Audience Improv": A great improv, Freddie sounds strong and confident. You gotta love when he sustains that A4 for 4 seconds!<br /><br />- "Hammer To Fall": Despite missing a verse and a chorus, it's a strong version (possibly the best ever). Freddie sings the song amazingly, and even ad-libs a C#5 and a C5! Also notice how heavy Brian's guitar sounds compared to the thin DVD mixes - it roars!<br /><br />- "Crazy Little Thing Called Love": A great version, the crowd loves the song, the jam is great as well! Only downside to this is the slight feedback issues.<br /><br />- "We Will Rock You": Although cut down to the 1st verse and chorus, Freddie sounds strong. He nails the A4, and the solo from Dr. May is brilliant!<br /><br />- "We Are the Champions": Perhaps the high-light of the performance - Freddie is very daring on this version, he sustains the pre-chorus Bb4s, nails the 1st C5, belts great A4s, but most importantly: He nails the chorus Bb4s, in all 3 choruses! This is the only time he has ever done so! It has to be said though, the last one sounds a bit rough, but that's a side effect of belting high notes for the past 18 minutes, with nodules AND laryngitis!<br /><br />- "Is This The World We Created... ?": Freddie and Brian perform a beautiful version of this, and it is one of the best versions ever. It's both sad and hilarious that a couple of BBC engineers are talking over the song, one of them being completely oblivious of the fact that he is interrupting the performance, on live television... Which was being televised to almost 2 billion homes.<br /><br /><br />All rights go to their respective owners!<br />-----Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for fair use for purposes such as criticism, comment, news reporting, teaching, scholarship, and research. Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use''',
1477,
[{
'start_time': 36,
'end_time': 162,
'title': 'Bohemian Rhapsody',
}, {
'start_time': 162,
'end_time': 413,
'title': 'Radio Ga Ga',
}, {
'start_time': 413,
'end_time': 454,
'title': 'Ay Oh!',
}, {
'start_time': 454,
'end_time': 728,
'title': 'Hammer To Fall',
}, {
'start_time': 728,
'end_time': 963,
'title': 'Crazy Little Thing Called Love',
}, {
'start_time': 963,
'end_time': 1038,
'title': 'We Will Rock You',
}, {
'start_time': 1038,
'end_time': 1272,
'title': 'We Are The Champions',
}, {
'start_time': 1272,
'end_time': 1477,
'title': 'Is This The World We Created...?',
}]
),
(
# https://www.youtube.com/watch?v=ekYlRhALiRQ
# pattern: <num>. <title> 0:00
'1. Those Beaten Paths of Confusion <a href="#" onclick="yt.www.watch.player.seekTo(0*60+00);return false;">0:00</a><br />2. Beyond the Shadows of Emptiness & Nothingness <a href="#" onclick="yt.www.watch.player.seekTo(11*60+47);return false;">11:47</a><br />3. Poison Yourself...With Thought <a href="#" onclick="yt.www.watch.player.seekTo(26*60+30);return false;">26:30</a><br />4. The Agents of Transformation <a href="#" onclick="yt.www.watch.player.seekTo(35*60+57);return false;">35:57</a><br />5. Drowning in the Pain of Consciousness <a href="#" onclick="yt.www.watch.player.seekTo(44*60+32);return false;">44:32</a><br />6. Deny the Disease of Life <a href="#" onclick="yt.www.watch.player.seekTo(53*60+07);return false;">53:07</a><br /><br />More info/Buy: http://crepusculonegro.storenvy.com/products/257645-cn-03-arizmenda-within-the-vacuum-of-infinity<br /><br />No copyright is intended. The rights to this video are assumed by the owner and its affiliates.',
4009,
[{
'start_time': 0,
'end_time': 707,
'title': '1. Those Beaten Paths of Confusion',
}, {
'start_time': 707,
'end_time': 1590,
'title': '2. Beyond the Shadows of Emptiness & Nothingness',
}, {
'start_time': 1590,
'end_time': 2157,
'title': '3. Poison Yourself...With Thought',
}, {
'start_time': 2157,
'end_time': 2672,
'title': '4. The Agents of Transformation',
}, {
'start_time': 2672,
'end_time': 3187,
'title': '5. Drowning in the Pain of Consciousness',
}, {
'start_time': 3187,
'end_time': 4009,
'title': '6. Deny the Disease of Life',
}]
),
(
# https://www.youtube.com/watch?v=WjL4pSzog9w
# pattern: 00:00 <title>
'<a href="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" class="yt-uix-servicelink " data-target-new-window="True" data-servicelink="CDAQ6TgYACITCNf1raqT2dMCFdRjGAod_o0CBSj4HQ" data-url="https://arizmenda.bandcamp.com/merch/despairs-depths-descended-cd" rel="nofollow noopener" target="_blank">https://arizmenda.bandcamp.com/merch/...</a><br /><br /><a href="#" onclick="yt.www.watch.player.seekTo(00*60+00);return false;">00:00</a> Christening Unborn Deformities <br /><a href="#" onclick="yt.www.watch.player.seekTo(07*60+08);return false;">07:08</a> Taste of Purity<br /><a href="#" onclick="yt.www.watch.player.seekTo(16*60+16);return false;">16:16</a> Sculpting Sins of a Universal Tongue<br /><a href="#" onclick="yt.www.watch.player.seekTo(24*60+45);return false;">24:45</a> Birth<br /><a href="#" onclick="yt.www.watch.player.seekTo(31*60+24);return false;">31:24</a> Neves<br /><a href="#" onclick="yt.www.watch.player.seekTo(37*60+55);return false;">37:55</a> Libations in Limbo',
2705,
[{
'start_time': 0,
'end_time': 428,
'title': 'Christening Unborn Deformities',
}, {
'start_time': 428,
'end_time': 976,
'title': 'Taste of Purity',
}, {
'start_time': 976,
'end_time': 1485,
'title': 'Sculpting Sins of a Universal Tongue',
}, {
'start_time': 1485,
'end_time': 1884,
'title': 'Birth',
}, {
'start_time': 1884,
'end_time': 2275,
'title': 'Neves',
}, {
'start_time': 2275,
'end_time': 2705,
'title': 'Libations in Limbo',
}]
),
(
# https://www.youtube.com/watch?v=o3r1sn-t3is
# pattern: <title> 00:00 <note>
'Download this show in MP3: <a href="http://sh.st/njZKK" class="yt-uix-servicelink " data-url="http://sh.st/njZKK" data-target-new-window="True" data-servicelink="CDAQ6TgYACITCK3j8_6o2dMCFVDCGAoduVAKKij4HQ" rel="nofollow noopener" target="_blank">http://sh.st/njZKK</a><br /><br />Setlist:<br />I-E-A-I-A-I-O <a href="#" onclick="yt.www.watch.player.seekTo(00*60+45);return false;">00:45</a><br />Suite-Pee <a href="#" onclick="yt.www.watch.player.seekTo(4*60+26);return false;">4:26</a> (Incomplete)<br />Attack <a href="#" onclick="yt.www.watch.player.seekTo(5*60+31);return false;">5:31</a> (First live performance since 2011)<br />Prison Song <a href="#" onclick="yt.www.watch.player.seekTo(8*60+42);return false;">8:42</a><br />Know <a href="#" onclick="yt.www.watch.player.seekTo(12*60+32);return false;">12:32</a> (First live performance since 2011)<br />Aerials <a href="#" onclick="yt.www.watch.player.seekTo(15*60+32);return false;">15:32</a><br />Soldier Side - Intro <a href="#" onclick="yt.www.watch.player.seekTo(19*60+13);return false;">19:13</a><br />B.Y.O.B. <a href="#" onclick="yt.www.watch.player.seekTo(20*60+09);return false;">20:09</a><br />Soil <a href="#" onclick="yt.www.watch.player.seekTo(24*60+32);return false;">24:32</a><br />Darts <a href="#" onclick="yt.www.watch.player.seekTo(27*60+48);return false;">27:48</a><br />Radio/Video <a href="#" onclick="yt.www.watch.player.seekTo(30*60+38);return false;">30:38</a><br />Hypnotize <a href="#" onclick="yt.www.watch.player.seekTo(35*60+05);return false;">35:05</a><br />Temper <a href="#" onclick="yt.www.watch.player.seekTo(38*60+08);return false;">38:08</a> (First live performance since 1999)<br />CUBErt <a href="#" onclick="yt.www.watch.player.seekTo(41*60+00);return false;">41:00</a><br />Needles <a href="#" onclick="yt.www.watch.player.seekTo(42*60+57);return false;">42:57</a><br />Deer Dance <a href="#" onclick="yt.www.watch.player.seekTo(46*60+27);return false;">46:27</a><br />Bounce <a href="#" onclick="yt.www.watch.player.seekTo(49*60+38);return false;">49:38</a><br />Suggestions <a href="#" onclick="yt.www.watch.player.seekTo(51*60+25);return false;">51:25</a><br />Psycho <a href="#" onclick="yt.www.watch.player.seekTo(53*60+52);return false;">53:52</a><br />Chop Suey! <a href="#" onclick="yt.www.watch.player.seekTo(58*60+13);return false;">58:13</a><br />Lonely Day <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+01*60+15);return false;">1:01:15</a><br />Question! <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+04*60+14);return false;">1:04:14</a><br />Lost in Hollywood <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+08*60+10);return false;">1:08:10</a><br />Vicinity of Obscenity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+13*60+40);return false;">1:13:40</a>(First live performance since 2012)<br />Forest <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+16*60+17);return false;">1:16:17</a><br />Cigaro <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+20*60+02);return false;">1:20:02</a><br />Toxicity <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+23*60+57);return false;">1:23:57</a>(with Chino Moreno)<br />Sugar <a href="#" onclick="yt.www.watch.player.seekTo(1*3600+27*60+53);return false;">1:27:53</a>',
5640,
[{
'start_time': 45,
'end_time': 266,
'title': 'I-E-A-I-A-I-O',
}, {
'start_time': 266,
'end_time': 331,
'title': 'Suite-Pee (Incomplete)',
}, {
'start_time': 331,
'end_time': 522,
'title': 'Attack (First live performance since 2011)',
}, {
'start_time': 522,
'end_time': 752,
'title': 'Prison Song',
}, {
'start_time': 752,
'end_time': 932,
'title': 'Know (First live performance since 2011)',
}, {
'start_time': 932,
'end_time': 1153,
'title': 'Aerials',
}, {
'start_time': 1153,
'end_time': 1209,
'title': 'Soldier Side - Intro',
}, {
'start_time': 1209,
'end_time': 1472,
'title': 'B.Y.O.B.',
}, {
'start_time': 1472,
'end_time': 1668,
'title': 'Soil',
}, {
'start_time': 1668,
'end_time': 1838,
'title': 'Darts',
}, {
'start_time': 1838,
'end_time': 2105,
'title': 'Radio/Video',
}, {
'start_time': 2105,
'end_time': 2288,
'title': 'Hypnotize',
}, {
'start_time': 2288,
'end_time': 2460,
'title': 'Temper (First live performance since 1999)',
}, {
'start_time': 2460,
'end_time': 2577,
'title': 'CUBErt',
}, {
'start_time': 2577,
'end_time': 2787,
'title': 'Needles',
}, {
'start_time': 2787,
'end_time': 2978,
'title': 'Deer Dance',
}, {
'start_time': 2978,
'end_time': 3085,
'title': 'Bounce',
}, {
'start_time': 3085,
'end_time': 3232,
'title': 'Suggestions',
}, {
'start_time': 3232,
'end_time': 3493,
'title': 'Psycho',
}, {
'start_time': 3493,
'end_time': 3675,
'title': 'Chop Suey!',
}, {
'start_time': 3675,
'end_time': 3854,
'title': 'Lonely Day',
}, {
'start_time': 3854,
'end_time': 4090,
'title': 'Question!',
}, {
'start_time': 4090,
'end_time': 4420,
'title': 'Lost in Hollywood',
}, {
'start_time': 4420,
'end_time': 4577,
'title': 'Vicinity of Obscenity (First live performance since 2012)',
}, {
'start_time': 4577,
'end_time': 4802,
'title': 'Forest',
}, {
'start_time': 4802,
'end_time': 5037,
'title': 'Cigaro',
}, {
'start_time': 5037,
'end_time': 5273,
'title': 'Toxicity (with Chino Moreno)',
}, {
'start_time': 5273,
'end_time': 5640,
'title': 'Sugar',
}]
),
(
# https://www.youtube.com/watch?v=PkYLQbsqCE8
# pattern: <num> - <title> [<latinized title>] 0:00:00
'''Затемно (Zatemno) is an Obscure Black Metal Band from Russia.<br /><br />"Во прах (Vo prakh)'' Into The Ashes", Debut mini-album released may 6, 2016, by Death Knell Productions<br />Released on 6 panel digipak CD, limited to 100 copies only<br />And digital format on Bandcamp<br /><br />Tracklist<br /><br />1 - Во прах [Vo prakh] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+00*60+00);return false;">0:00:00</a><br />2 - Искупление [Iskupleniye] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+08*60+10);return false;">0:08:10</a><br />3 - Из серпов луны...[Iz serpov luny] <a href="#" onclick="yt.www.watch.player.seekTo(0*3600+14*60+30);return false;">0:14:30</a><br /><br />Links:<br /><a href="https://deathknellprod.bandcamp.com/album/--2" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://deathknellprod.bandcamp.com/album/--2" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://deathknellprod.bandcamp.com/a...</a><br /><a href="https://www.facebook.com/DeathKnellProd/" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://www.facebook.com/DeathKnellProd/" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://www.facebook.com/DeathKnellProd/</a><br /><br /><br />I don't have any right about this artifact, my only intention is to spread the music of the band, all rights are reserved to the Затемно (Zatemno) and his producers, Death Knell Productions.<br /><br />------------------------------------------------------------------<br /><br />Subscribe for more videos like this.<br />My link: <a href="https://web.facebook.com/AttackOfTheDragons" class="yt-uix-servicelink " data-target-new-window="True" data-url="https://web.facebook.com/AttackOfTheDragons" data-servicelink="CC8Q6TgYACITCNP234Kr2dMCFcNxGAodQqsIwSj4HQ" target="_blank" rel="nofollow noopener">https://web.facebook.com/AttackOfTheD...</a>''',
1138,
[{
'start_time': 0,
'end_time': 490,
'title': '1 - Во прах [Vo prakh]',
}, {
'start_time': 490,
'end_time': 870,
'title': '2 - Искупление [Iskupleniye]',
}, {
'start_time': 870,
'end_time': 1138,
'title': '3 - Из серпов луны...[Iz serpov luny]',
}]
),
(
# https://www.youtube.com/watch?v=xZW70zEasOk
# time point more than duration
'''● LCS Spring finals: Saturday and Sunday from <a href="#" onclick="yt.www.watch.player.seekTo(13*60+30);return false;">13:30</a> outside the venue! <br />● PAX East: Fri, Sat & Sun - more info in tomorrows video on the main channel!''',
283,
[]
),
]
def test_youtube_chapters(self):
for description, duration, expected_chapters in self._TEST_CASES:
ie = YoutubeIE()
expect_value(
self, ie._extract_chapters(description, duration),
expected_chapters, None)
if __name__ == '__main__':
unittest.main()

View File

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

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

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

View File

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

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

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

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

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

View File

@@ -58,6 +58,7 @@ from .utils import (
format_bytes,
formatSeconds,
GeoRestrictedError,
int_or_none,
ISO3166Utils,
locked_file,
make_HTTPS_handler,
@@ -302,6 +303,17 @@ class YoutubeDL(object):
postprocessor.
"""
_NUMERIC_FIELDS = set((
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'timestamp', 'upload_year', 'upload_month', 'upload_day',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'average_rating', 'comment_count', 'age_limit',
'start_time', 'end_time',
'chapter_number', 'season_number', 'episode_number',
'track_number', 'disc_number', 'release_year',
'playlist_index',
))
params = None
_ies = []
_pps = []
@@ -370,10 +382,10 @@ class YoutubeDL(object):
else:
raise
if (sys.version_info >= (3,) and sys.platform != 'win32' and
if (sys.platform != 'win32' and
sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and
not params.get('restrictfilenames', False)):
# On Python 3, the Unicode filesystem API will throw errors (#1474)
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
'cannot encode all characters. '
@@ -498,7 +510,8 @@ class YoutubeDL(object):
def to_console_title(self, message):
if not self.params.get('consoletitle', False):
return
if compat_os_name == 'nt' and ctypes.windll.kernel32.GetConsoleWindow():
if compat_os_name == 'nt':
if ctypes.windll.kernel32.GetConsoleWindow():
# c_wchar_p() might not be necessary if `message` is
# already of type unicode()
ctypes.windll.kernel32.SetConsoleTitleW(ctypes.c_wchar_p(message))
@@ -508,14 +521,14 @@ class YoutubeDL(object):
def save_console_title(self):
if not self.params.get('consoletitle', False):
return
if 'TERM' in os.environ:
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Save the title on stack
self._write_string('\033[22;0t', self._screen_file)
def restore_console_title(self):
if not self.params.get('consoletitle', False):
return
if 'TERM' in os.environ:
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Restore the title from stack
self._write_string('\033[23;0t', self._screen_file)
@@ -638,22 +651,11 @@ class YoutubeDL(object):
r'%%(\1)0%dd' % field_size_compat_map[mobj.group('field')],
outtmpl)
NUMERIC_FIELDS = set((
'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
'upload_year', 'upload_month', 'upload_day',
'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
'average_rating', 'comment_count', 'age_limit',
'start_time', 'end_time',
'chapter_number', 'season_number', 'episode_number',
'track_number', 'disc_number', 'release_year',
'playlist_index',
))
# Missing numeric fields used together with integer presentation types
# in format specification will break the argument substitution since
# string 'NA' is returned for missing fields. We will patch output
# template for missing fields to meet string presentation type.
for numeric_field in NUMERIC_FIELDS:
for numeric_field in self._NUMERIC_FIELDS:
if numeric_field not in template_dict:
# As of [1] format syntax is:
# %[mapping_key][conversion_flags][minimum_width][.precision][length_modifier]type
@@ -1344,9 +1346,28 @@ class YoutubeDL(object):
if 'title' not in info_dict:
raise ExtractorError('Missing "title" field in extractor result')
if not isinstance(info_dict['id'], compat_str):
self.report_warning('"id" field is not a string - forcing string conversion')
info_dict['id'] = compat_str(info_dict['id'])
def report_force_conversion(field, field_not, conversion):
self.report_warning(
'"%s" field is not %s - forcing %s conversion, there is an error in extractor'
% (field, field_not, conversion))
def sanitize_string_field(info, string_field):
field = info.get(string_field)
if field is None or isinstance(field, compat_str):
return
report_force_conversion(string_field, 'a string', 'string')
info[string_field] = compat_str(field)
def sanitize_numeric_fields(info):
for numeric_field in self._NUMERIC_FIELDS:
field = info.get(numeric_field)
if field is None or isinstance(field, compat_numeric_types):
continue
report_force_conversion(numeric_field, 'numeric', 'int')
info[numeric_field] = int_or_none(field)
sanitize_string_field(info_dict, 'id')
sanitize_numeric_fields(info_dict)
if 'playlist' not in info_dict:
# It isn't part of a playlist
@@ -1434,6 +1455,8 @@ class YoutubeDL(object):
if 'url' not in format:
raise ExtractorError('Missing "url" key in result (index %d)' % i)
sanitize_string_field(format, 'format_id')
sanitize_numeric_fields(format)
format['url'] = sanitize_url(format['url'])
if format.get('format_id') is None:

View File

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

View File

@@ -2322,6 +2322,19 @@ try:
except ImportError: # Python 2
from HTMLParser import HTMLParser as compat_HTMLParser
try: # Python 2
from HTMLParser import HTMLParseError as compat_HTMLParseError
except ImportError: # Python <3.4
try:
from html.parser import HTMLParseError as compat_HTMLParseError
except ImportError: # Python >3.4
# HTMLParseError has been deprecated in Python 3.3 and removed in
# Python 3.5. Introducing dummy exception for Python >3.5 for compatible
# and uniform cross-version exceptiong handling
class compat_HTMLParseError(Exception):
pass
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL

View File

@@ -187,6 +187,9 @@ class FileDownloader(object):
return filename[:-len('.part')]
return filename
def ytdl_filename(self, filename):
return filename + '.ytdl'
def try_rename(self, old_filename, new_filename):
try:
if old_filename == new_filename:
@@ -327,6 +330,7 @@ class FileDownloader(object):
os.path.exists(encodeFilename(filename))
)
if not hasattr(filename, 'write'):
continuedl_and_exists = (
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and

View File

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

View File

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

View File

@@ -3,7 +3,6 @@ from __future__ import division, unicode_literals
import base64
import io
import itertools
import os
import time
from .fragment import FragmentFD
@@ -16,9 +15,7 @@ from ..compat import (
compat_struct_unpack,
)
from ..utils import (
encodeFilename,
fix_xml_ampersands,
sanitize_open,
xpath_text,
)
@@ -366,6 +363,7 @@ class F4mFD(FragmentFD):
dest_stream = ctx['dest_stream']
if ctx['complete_frags_downloaded_bytes'] == 0:
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
@@ -374,9 +372,12 @@ class F4mFD(FragmentFD):
self._start_frag_download(ctx)
frags_filenames = []
frag_index = 0
while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
name = 'Seg%d-Frag%d' % (seg_i, frag_i)
query = []
if base_url_parsed.query:
@@ -386,17 +387,10 @@ class F4mFD(FragmentFD):
if info_dict.get('extra_param_to_segment_url'):
query.append(info_dict['extra_param_to_segment_url'])
url_parsed = base_url_parsed._replace(path=base_url_parsed.path + name, query='&'.join(query))
frag_filename = '%s-%s' % (ctx['tmpfilename'], name)
try:
success = ctx['dl'].download(frag_filename, {
'url': url_parsed.geturl(),
'http_headers': info_dict.get('http_headers'),
})
success, down_data = self._download_fragment(ctx, url_parsed.geturl(), info_dict)
if not success:
return False
(down, frag_sanitized) = sanitize_open(frag_filename, 'rb')
down_data = down.read()
down.close()
reader = FlvReader(down_data)
while True:
try:
@@ -411,12 +405,8 @@ class F4mFD(FragmentFD):
break
raise
if box_type == b'mdat':
dest_stream.write(box_data)
self._append_fragment(ctx, box_data)
break
if live:
os.remove(encodeFilename(frag_sanitized))
else:
frags_filenames.append(frag_sanitized)
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
@@ -436,7 +426,4 @@ class F4mFD(FragmentFD):
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True

View File

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

View File

@@ -1,6 +1,5 @@
from __future__ import unicode_literals
import os.path
import re
import binascii
try:
@@ -18,8 +17,6 @@ from ..compat import (
compat_struct_pack,
)
from ..utils import (
encodeFilename,
sanitize_open,
parse_m3u8_attributes,
update_url_query,
)
@@ -103,17 +100,18 @@ class HlsFD(FragmentFD):
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
byte_range = {}
frags_filenames = []
frag_index = 0
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
frag_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(man_url, line))
frag_name = 'Frag%d' % i
frag_filename = '%s-%s' % (ctx['tmpfilename'], frag_name)
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
count = 0
@@ -122,15 +120,10 @@ class HlsFD(FragmentFD):
headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'])
while count <= fragment_retries:
try:
success = ctx['dl'].download(frag_filename, {
'url': frag_url,
'http_headers': headers,
})
success, frag_content = self._download_fragment(
ctx, frag_url, info_dict, headers)
if not success:
return False
down, frag_sanitized = sanitize_open(frag_filename, 'rb')
frag_content = down.read()
down.close()
break
except compat_urllib_error.HTTPError as err:
# Unavailable (possibly temporary) fragments may be served.
@@ -139,28 +132,29 @@ class HlsFD(FragmentFD):
# https://github.com/rg3/youtube-dl/issues/10448).
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_name, count, fragment_retries)
self.report_retry_fragment(err, frag_index, count, fragment_retries)
if count > fragment_retries:
if skip_unavailable_fragments:
i += 1
media_sequence += 1
self.report_skip_fragment(frag_name)
self.report_skip_fragment(frag_index)
continue
self.report_error(
'giving up after %s fragment retries' % fragment_retries)
return False
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(decrypt_info['URI']).read()
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
ctx['dest_stream'].write(frag_content)
frags_filenames.append(frag_sanitized)
self._append_fragment(ctx, frag_content)
# We only download the first fragment during the test
if test:
break
i += 1
media_sequence += 1
elif line.startswith('#EXT-X-KEY'):
decrypt_url = decrypt_info.get('URI')
decrypt_info = parse_m3u8_attributes(line[11:])
if decrypt_info['METHOD'] == 'AES-128':
if 'IV' in decrypt_info:
@@ -170,7 +164,8 @@ class HlsFD(FragmentFD):
man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
decrypt_info['KEY'] = self.ydl.urlopen(decrypt_info['URI']).read()
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
media_sequence = int(line[22:])
elif line.startswith('#EXT-X-BYTERANGE'):
@@ -183,7 +178,4 @@ class HlsFD(FragmentFD):
self._finish_frag_download(ctx)
for frag_file in frags_filenames:
os.remove(encodeFilename(frag_file))
return True

View File

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

View File

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

View File

@@ -15,6 +15,7 @@ from ..utils import (
intlist_to_bytes,
srt_subtitles_timecode,
strip_or_none,
urljoin,
)
@@ -31,25 +32,28 @@ class ADNIE(InfoExtractor):
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
}
}
_BASE_URL = 'http://animedigitalnetwork.fr'
def _get_subtitles(self, sub_path, video_id):
if not sub_path:
return None
enc_subtitles = self._download_webpage(
'http://animedigitalnetwork.fr/' + sub_path,
video_id, fatal=False)
urljoin(self._BASE_URL, sub_path),
video_id, fatal=False, headers={
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
})
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(base64.b64decode(enc_subtitles[24:])),
bytes_to_intlist(b'\nd\xaf\xd2J\xd0\xfc\xe1\xfc\xdf\xb61\xe8\xe1\xf0\xcc'),
bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'),
bytes_to_intlist(base64.b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
dec_subtitles[:-compat_ord(dec_subtitles[-1])],
dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
None, fatal=False)
if not subtitles_json:
return None
@@ -103,9 +107,16 @@ class ADNIE(InfoExtractor):
metas = options.get('metas') or {}
title = metas.get('title') or video_info['title']
links = player_config.get('links') or {}
if not links:
links_url = player_config['linksurl']
links_data = self._download_json(urljoin(
self._BASE_URL, links_url), video_id)
links = links_data.get('links') or {}
formats = []
for format_id, qualities in links.items():
if not isinstance(qualities, dict):
continue
for load_balancer_url in qualities.values():
load_balancer_data = self._download_json(
load_balancer_url, video_id, fatal=False) or {}

View File

@@ -36,6 +36,11 @@ MSO_INFO = {
'username_field': 'Ecom_User_ID',
'password_field': 'Ecom_Password',
},
'Brighthouse': {
'name': 'Bright House Networks | Spectrum',
'username_field': 'j_username',
'password_field': 'j_password',
},
'Charter_Direct': {
'name': 'Charter Spectrum',
'username_field': 'IDToken1',
@@ -1308,6 +1313,12 @@ class AdobePassIE(InfoExtractor):
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MVPD_CACHE = 'ap-mvpd'
def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {})
headers.update(self.geo_verification_headers())
kwargs['headers'] = headers
return super(AdobePassIE, self)._download_webpage_handle(*args, **kwargs)
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')

View File

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

View File

@@ -101,10 +101,14 @@ class AENetworksIE(AENetworksBaseIE):
for season_url_path in re.findall(r'(?s)<li[^>]+data-href="(/shows/%s/season-\d+)"' % url_parts[0], webpage):
entries.append(self.url_result(
compat_urlparse.urljoin(url, season_url_path), 'AENetworks'))
if entries:
return self.playlist_result(
entries, self._html_search_meta('aetn:SeriesId', webpage),
self._html_search_meta('aetn:SeriesTitle', webpage))
elif url_parts_len == 2:
else:
# single season
url_parts_len = 2
if url_parts_len == 2:
entries = []
for episode_item in re.findall(r'(?s)<[^>]+class="[^"]*(?:episode|program)-item[^"]*"[^>]*>', webpage):
episode_attributes = extract_attributes(episode_item)
@@ -112,7 +116,7 @@ class AENetworksIE(AENetworksBaseIE):
url, episode_attributes['data-canonical'])
entries.append(self.url_result(
episode_url, 'AENetworks',
episode_attributes['data-videoid']))
episode_attributes.get('data-videoid') or episode_attributes.get('data-video-id')))
return self.playlist_result(
entries, self._html_search_meta('aetn:SeasonId', webpage))

View File

@@ -207,11 +207,10 @@ class AfreecaTVIE(InfoExtractor):
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
title = title if one else '%s (part %d)' % (title, file_num)
file_info = common_entry.copy()
file_info.update({
'id': format_id,
'title': title,
'title': title if one else '%s (part %d)' % (title, file_num),
'upload_date': upload_date,
'duration': file_duration,
'formats': formats,

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -180,7 +180,7 @@ class ArteTVBaseIE(InfoExtractor):
class ArteTVPlus7IE(ArteTVBaseIE):
IE_NAME = 'arte.tv:+7'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/[^/]+/(?P<lang>fr|de|en|es)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?:www|sites)\.)?arte\.tv/(?:[^/]+/)?(?P<lang>fr|de|en|es)/(?:videos/)?(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.arte.tv/guide/de/sendungen/XEN/xenius/?vid=055918-015_PLUS7-D',
@@ -188,6 +188,9 @@ class ArteTVPlus7IE(ArteTVBaseIE):
}, {
'url': 'http://sites.arte.tv/karambolage/de/video/karambolage-22',
'only_matching': True,
}, {
'url': 'http://www.arte.tv/de/videos/048696-000-A/der-kluge-bauch-unser-zweites-gehirn',
'only_matching': True,
}]
@classmethod

View File

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

View File

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

View File

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

View File

@@ -14,14 +14,16 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
unescapeHTML,
update_url_query,
unified_strdate,
)
class BandcampIE(InfoExtractor):
_VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>.*)'
_VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'md5': 'c557841d5e50261777a6585648adf439',
@@ -34,12 +36,12 @@ class BandcampIE(InfoExtractor):
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}, {
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'md5': '73d0b3171568232574e45652f8720b5c',
'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
'info_dict': {
'id': '2650410135',
'ext': 'mp3',
'title': 'Lanius (Battle)',
'uploader': 'Ben Prunty Music',
'ext': 'aiff',
'title': 'Ben Prunty - Lanius (Battle)',
'uploader': 'Ben Prunty',
},
}]
@@ -47,6 +49,7 @@ class BandcampIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
thumbnail = self._html_search_meta('og:image', webpage, default=None)
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
@@ -75,6 +78,7 @@ class BandcampIE(InfoExtractor):
return {
'id': track_id,
'title': data['title'],
'thumbnail': thumbnail,
'formats': formats,
'duration': float_or_none(data.get('duration')),
}
@@ -143,7 +147,7 @@ class BandcampIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'thumbnail': info.get('thumb_url'),
'thumbnail': info.get('thumb_url') or thumbnail,
'uploader': info.get('artist'),
'artist': artist,
'track': track,
@@ -153,7 +157,7 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(InfoExtractor):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^?#]+)|/?(?:$|[?#]))'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?:/album/(?P<album_id>[^/?#&]+))?'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -220,6 +224,12 @@ class BandcampAlbumIE(InfoExtractor):
'playlist_count': 2,
}]
@classmethod
def suitable(cls, url):
return (False
if BandcampWeeklyIE.suitable(url) or BandcampIE.suitable(url)
else super(BandcampAlbumIE, cls).suitable(url))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
uploader_id = mobj.group('subdomain')
@@ -248,3 +258,92 @@ class BandcampAlbumIE(InfoExtractor):
'title': title,
'entries': entries,
}
class BandcampWeeklyIE(InfoExtractor):
IE_NAME = 'Bandcamp:weekly'
_VALID_URL = r'https?://(?:www\.)?bandcamp\.com/?\?(?:.*?&)?show=(?P<id>\d+)'
_TESTS = [{
'url': 'https://bandcamp.com/?show=224',
'md5': 'b00df799c733cf7e0c567ed187dea0fd',
'info_dict': {
'id': '224',
'ext': 'opus',
'title': 'BC Weekly April 4th 2017 - Magic Moments',
'description': 'md5:5d48150916e8e02d030623a48512c874',
'duration': 5829.77,
'release_date': '20170404',
'series': 'Bandcamp Weekly',
'episode': 'Magic Moments',
'episode_number': 208,
'episode_id': '224',
}
}, {
'url': 'https://bandcamp.com/?blah/blah@&show=228',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
blob = self._parse_json(
self._search_regex(
r'data-blob=(["\'])(?P<blob>{.+?})\1', webpage,
'blob', group='blob'),
video_id, transform_source=unescapeHTML)
show = blob['bcw_show']
# This is desired because any invalid show id redirects to `bandcamp.com`
# which happens to expose the latest Bandcamp Weekly episode.
show_id = int_or_none(show.get('show_id')) or int_or_none(video_id)
formats = []
for format_id, format_url in show['audio_stream'].items():
if not isinstance(format_url, compat_str):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:
ext = known_ext
break
else:
ext = None
formats.append({
'format_id': format_id,
'url': format_url,
'ext': ext,
'vcodec': 'none',
})
self._sort_formats(formats)
title = show.get('audio_title') or 'Bandcamp Weekly'
subtitle = show.get('subtitle')
if subtitle:
title += ' - %s' % subtitle
episode_number = None
seq = blob.get('bcw_seq')
if seq and isinstance(seq, list):
try:
episode_number = next(
int_or_none(e.get('episode_number'))
for e in seq
if isinstance(e, dict) and int_or_none(e.get('id')) == show_id)
except StopIteration:
pass
return {
'id': video_id,
'title': title,
'description': show.get('desc') or show.get('short_desc'),
'duration': float_or_none(show.get('audio_duration')),
'is_live': False,
'release_date': unified_strdate(show.get('published_date')),
'series': 'Bandcamp Weekly',
'episode': show.get('subtitle'),
'episode_number': episode_number,
'episode_id': compat_str(video_id),
'formats': formats
}

View File

@@ -6,14 +6,18 @@ import itertools
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
ExtractorError,
float_or_none,
get_element_by_class,
int_or_none,
parse_duration,
parse_iso8601,
try_get,
unescapeHTML,
urlencode_postdata,
urljoin,
)
from ..compat import (
compat_etree_fromstring,
@@ -38,6 +42,9 @@ class BBCCoUkIE(InfoExtractor):
(?P<id>%s)(?!/(?:episodes|broadcasts|clips))
''' % _ID_REGEX
_LOGIN_URL = 'https://account.bbc.com/signin'
_NETRC_MACHINE = 'bbc'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
# with geolocation in some cases when it's even not geo restricted at all (e.g.
@@ -227,6 +234,39 @@ class BBCCoUkIE(InfoExtractor):
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading signin page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
post_url = urljoin(self._LOGIN_URL, self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_URL, group='url'))
response, urlh = self._download_webpage_handle(
post_url, None, 'Logging in', data=urlencode_postdata(login_form),
headers={'Referer': self._LOGIN_URL})
if self._LOGIN_URL in urlh.geturl():
error = clean_html(get_element_by_class('form-message', response))
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
class MediaSelectionError(Exception):
def __init__(self, id):
self.id = id

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -5,6 +5,7 @@ import re
import json
from .common import InfoExtractor
from .adobepass import AdobePassIE
from ..compat import (
compat_etree_fromstring,
compat_parse_qs,
@@ -131,6 +132,12 @@ class BrightcoveLegacyIE(InfoExtractor):
},
'playlist_mincount': 10,
},
{
# playerID inferred from bcpid
# from http://www.un.org/chinese/News/story.asp?NewsID=27724
'url': 'https://link.brightcove.com/services/player/bcpid1722935254001/?bctid=5360463607001&autoStart=false&secureConnections=true&width=650&height=350',
'only_matching': True, # Tested in GenericIE
}
]
FLV_VCODECS = {
1: 'SORENSON',
@@ -266,9 +273,13 @@ class BrightcoveLegacyIE(InfoExtractor):
if matches:
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
matches = re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)
if matches:
return list(filter(None, [
cls._build_brighcove_url_from_js(custom_bc)
for custom_bc in re.findall(r'(customBC\.createVideo\(.+?\);)', webpage)]))
for custom_bc in matches]))
return [src for _, src in re.findall(
r'<iframe[^>]+src=([\'"])((?:https?:)?//link\.brightcove\.com/services/player/(?!\1).+)\1', webpage)]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
@@ -285,6 +296,10 @@ class BrightcoveLegacyIE(InfoExtractor):
if videoPlayer:
# We set the original url as the default 'Referer' header
referer = smuggled_data.get('Referer', url)
if 'playerID' not in query:
mobj = re.search(r'/bcpid(\d+)', url)
if mobj is not None:
query['playerID'] = [mobj.group(1)]
return self._get_video_info(
videoPlayer[0], query, referer=referer)
elif 'playerKey' in query:
@@ -434,7 +449,7 @@ class BrightcoveLegacyIE(InfoExtractor):
return info
class BrightcoveNewIE(InfoExtractor):
class BrightcoveNewIE(AdobePassIE):
IE_NAME = 'brightcove:new'
_VALID_URL = r'https?://players\.brightcove\.net/(?P<account_id>\d+)/(?P<player_id>[^/]+)_(?P<embed>[^/]+)/index\.html\?.*videoId=(?P<video_id>\d+|ref:[^&]+)'
_TESTS = [{
@@ -484,8 +499,8 @@ class BrightcoveNewIE(InfoExtractor):
}]
@staticmethod
def _extract_url(webpage):
urls = BrightcoveNewIE._extract_urls(webpage)
def _extract_url(ie, webpage):
urls = BrightcoveNewIE._extract_urls(ie, webpage)
return urls[0] if urls else None
@staticmethod
@@ -508,7 +523,7 @@ class BrightcoveNewIE(InfoExtractor):
# [2] looks like:
for video, script_tag, account_id, player_id, embed in re.findall(
r'''(?isx)
(<video\s+[^>]+>)
(<video\s+[^>]*\bdata-video-id\s*=\s*['"]?[^>]+>)
(?:.*?
(<script[^>]+
src=["\'](?:https?:)?//players\.brightcove\.net/
@@ -588,6 +603,20 @@ class BrightcoveNewIE(InfoExtractor):
raise ExtractorError(message, expected=True)
raise
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
}, query={
'tveToken': tve_token,
})
title = json_data['name'].strip()
formats = []
@@ -653,7 +682,6 @@ class BrightcoveNewIE(InfoExtractor):
})
formats.append(f)
errors = json_data.get('errors')
if not formats and errors:
error = errors[0]
raise ExtractorError(
@@ -670,7 +698,7 @@ class BrightcoveNewIE(InfoExtractor):
is_live = False
duration = float_or_none(json_data.get('duration'), 1000)
if duration and duration < 0:
if duration is not None and duration <= 0:
is_live = True
return {

View File

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

View File

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

View File

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

View File

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

View File

@@ -60,8 +60,8 @@ class CBSLocalIE(AnvatoIE):
'title': 'A Very Blue Anniversary',
'description': 'CBS2s Cindy Hsu has more.',
'thumbnail': 're:^https?://.*',
'timestamp': 1479962220,
'upload_date': '20161124',
'timestamp': int,
'upload_date': r're:^\d{8}$',
'uploader': 'CBS',
'subtitles': {
'en': 'mincount:5',

View File

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

View File

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

View File

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

View File

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

View File

@@ -245,6 +245,10 @@ class InfoExtractor(object):
specified in the URL.
end_time: Time in seconds where the reproduction should end, as
specified in the URL.
chapters: A list of dictionaries, with the following entries:
* "start_time" - The start time of the chapter in seconds
* "end_time" - The end time of the chapter in seconds
* "title" (optional, string)
The following fields should only be used when the video belongs to some logical
chapter or section:
@@ -372,7 +376,7 @@ class InfoExtractor(object):
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
m = cls._VALID_URL_RE.match(url)
assert m
return m.group('id')
return compat_str(m.group('id'))
@classmethod
def working(cls):
@@ -976,6 +980,23 @@ class InfoExtractor(object):
return info
if isinstance(json_ld, dict):
json_ld = [json_ld]
def extract_video_object(e):
assert e['@type'] == 'VideoObject'
info.update({
'url': e.get('contentUrl'),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
'view_count': int_or_none(e.get('interactionCount')),
})
for e in json_ld:
if e.get('@context') == 'http://schema.org':
item_type = e.get('@type')
@@ -1000,18 +1021,11 @@ class InfoExtractor(object):
'description': unescapeHTML(e.get('articleBody')),
})
elif item_type == 'VideoObject':
info.update({
'url': e.get('contentUrl'),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
'filesize': float_or_none(e.get('contentSize')),
'tbr': int_or_none(e.get('bitrate')),
'width': int_or_none(e.get('width')),
'height': int_or_none(e.get('height')),
})
extract_video_object(e)
elif item_type == 'WebPage':
video = e.get('video')
if isinstance(video, dict) and video.get('@type') == 'VideoObject':
extract_video_object(video)
break
return dict((k, v) for k, v in info.items() if v is not None)
@@ -1303,40 +1317,50 @@ class InfoExtractor(object):
entry_protocol='m3u8', preference=None,
m3u8_id=None, note=None, errnote=None,
fatal=True, live=False):
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
errnote=errnote or 'Failed to download m3u8 information',
fatal=fatal)
if res is False:
return []
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
return self._parse_m3u8_formats(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
preference=preference, m3u8_id=m3u8_id, live=live)
def _parse_m3u8_formats(self, m3u8_doc, m3u8_url, ext=None,
entry_protocol='m3u8', preference=None,
m3u8_id=None, live=False):
if '#EXT-X-FAXS-CM:' in m3u8_doc: # Adobe Flash Access
return []
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
formats = []
format_url = lambda u: (
u
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
# We should try extracting formats only from master playlists [1], i.e.
# playlists that describe available qualities. On the other hand media
# playlists [2] should be returned as is since they contain just the media
# without qualities renditions.
# References:
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-21
# 2. https://github.com/rg3/youtube-dl/issues/12211
# We should try extracting formats only from master playlists [1, 4.3.4],
# i.e. playlists that describe available qualities. On the other hand
# media playlists [1, 4.3.3] should be returned as is since they contain
# just the media without qualities renditions.
# Fortunately, master playlist can be easily distinguished from media
# playlist based on particular tags availability. As of [1, 2] master
# playlist tags MUST NOT appear in a media playist and vice versa.
# As of [3] #EXT-X-TARGETDURATION tag is REQUIRED for every media playlist
# and MUST NOT appear in master playlist thus we can clearly detect media
# playlist with this criterion.
# 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.4
# 2. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3
# 3. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.3.1
# playlist based on particular tags availability. As of [1, 4.3.3, 4.3.4]
# master playlist tags MUST NOT appear in a media playist and vice versa.
# As of [1, 4.3.3.1] #EXT-X-TARGETDURATION tag is REQUIRED for every
# media playlist and MUST NOT appear in master playlist thus we can
# clearly detect media playlist with this criterion.
if '#EXT-X-TARGETDURATION' in m3u8_doc: # media playlist, return as is
return [{
'url': m3u8_url,
@@ -1345,26 +1369,29 @@ class InfoExtractor(object):
'protocol': entry_protocol,
'preference': preference,
}]
audio_in_video_stream = {}
last_info = {}
last_media = {}
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_info = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
media = parse_m3u8_attributes(line)
media_type = media.get('TYPE')
if media_type in ('VIDEO', 'AUDIO'):
group_id = media.get('GROUP-ID')
groups = {}
last_stream_inf = {}
def extract_media(x_media_line):
media = parse_m3u8_attributes(x_media_line)
# As per [1, 4.3.4.1] TYPE, GROUP-ID and NAME are REQUIRED
media_type, group_id, name = media.get('TYPE'), media.get('GROUP-ID'), media.get('NAME')
if not (media_type and group_id and name):
return
groups.setdefault(group_id, []).append(media)
if media_type not in ('VIDEO', 'AUDIO'):
return
media_url = media.get('URI')
if media_url:
format_id = []
for v in (group_id, media.get('NAME')):
for v in (group_id, name):
if v:
format_id.append(v)
f = {
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'manifest_url': m3u8_url,
'language': media.get('LANGUAGE'),
'ext': ext,
'protocol': entry_protocol,
@@ -1372,25 +1399,42 @@ class InfoExtractor(object):
}
if media_type == 'AUDIO':
f['vcodec'] = 'none'
if group_id and not audio_in_video_stream.get(group_id):
audio_in_video_stream[group_id] = False
formats.append(f)
else:
# When there is no URI in EXT-X-MEDIA let this tag's
# data be used by regular URI lines below
last_media = media
if media_type == 'AUDIO' and group_id:
audio_in_video_stream[group_id] = True
def build_stream_name():
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF tag it still sometimes may be present (see [1]
# or vidio test in TestInfoExtractor.test_parse_m3u8_formats)
# 1. http://www.vidio.com/watch/165683-dj_ambred-booyah-live-2015
stream_name = last_stream_inf.get('NAME')
if stream_name:
return stream_name
# If there is no NAME in EXT-X-STREAM-INF it will be obtained
# from corresponding rendition group
stream_group_id = last_stream_inf.get('VIDEO')
if not stream_group_id:
return
stream_group = groups.get(stream_group_id)
if not stream_group:
return stream_group_id
rendition = stream_group[0]
return rendition.get('NAME') or stream_group_id
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_stream_inf = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
extract_media(line)
elif line.startswith('#') or not line.strip():
continue
else:
tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
tbr = float_or_none(
last_stream_inf.get('AVERAGE-BANDWIDTH') or
last_stream_inf.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF it still sometimes may be present
stream_name = last_info.get('NAME') or last_media.get('NAME')
stream_name = build_stream_name()
# Bandwidth of live streams may differ over time thus making
# format_id unpredictable. So it's better to keep provided
# format_id intact.
@@ -1400,14 +1444,14 @@ class InfoExtractor(object):
f = {
'format_id': '-'.join(format_id),
'url': manifest_url,
'manifest_url': manifest_url,
'manifest_url': m3u8_url,
'tbr': tbr,
'ext': ext,
'fps': float_or_none(last_info.get('FRAME-RATE')),
'fps': float_or_none(last_stream_inf.get('FRAME-RATE')),
'protocol': entry_protocol,
'preference': preference,
}
resolution = last_info.get('RESOLUTION')
resolution = last_stream_inf.get('RESOLUTION')
if resolution:
mobj = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', resolution)
if mobj:
@@ -1423,13 +1467,26 @@ class InfoExtractor(object):
'vbr': vbr,
'abr': abr,
})
f.update(parse_codecs(last_info.get('CODECS')))
if audio_in_video_stream.get(last_info.get('AUDIO')) is False and f['vcodec'] != 'none':
# TODO: update acodec for audio only formats with the same GROUP-ID
codecs = parse_codecs(last_stream_inf.get('CODECS'))
f.update(codecs)
audio_group_id = last_stream_inf.get('AUDIO')
# As per [1, 4.3.4.1.1] any EXT-X-STREAM-INF tag which
# references a rendition group MUST have a CODECS attribute.
# However, this is not always respected, for example, [2]
# contains EXT-X-STREAM-INF tag which references AUDIO
# rendition group but does not have CODECS and despite
# referencing audio group an audio group, it represents
# a complete (with audio and video) format. So, for such cases
# we will ignore references to rendition groups and treat them
# as complete formats.
if audio_group_id and codecs and f.get('vcodec') != 'none':
audio_group = groups.get(audio_group_id)
if audio_group and audio_group[0].get('URI'):
# TODO: update acodec for audio only formats with
# the same GROUP-ID
f['acodec'] = 'none'
formats.append(f)
last_info = {}
last_media = {}
last_stream_inf = {}
return formats
@staticmethod
@@ -1803,7 +1860,7 @@ class InfoExtractor(object):
'ext': mimetype2ext(mime_type),
'width': int_or_none(representation_attrib.get('width')),
'height': int_or_none(representation_attrib.get('height')),
'tbr': int_or_none(bandwidth, 1000),
'tbr': float_or_none(bandwidth, 1000),
'asr': int_or_none(representation_attrib.get('audioSamplingRate')),
'fps': int_or_none(representation_attrib.get('frameRate')),
'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None,
@@ -1944,6 +2001,12 @@ class InfoExtractor(object):
compat_etree_fromstring(ism.encode('utf-8')), urlh.geturl(), ism_id)
def _parse_ism_formats(self, ism_doc, ism_url, ism_id=None):
"""
Parse formats from ISM manifest.
References:
1. [MS-SSTR]: Smooth Streaming Protocol,
https://msdn.microsoft.com/en-us/library/ff469518.aspx
"""
if ism_doc.get('IsLive') == 'TRUE' or ism_doc.find('Protection') is not None:
return []
@@ -1965,8 +2028,11 @@ class InfoExtractor(object):
self.report_warning('%s is not a supported codec' % fourcc)
continue
tbr = int(track.attrib['Bitrate']) // 1000
width = int_or_none(track.get('MaxWidth'))
height = int_or_none(track.get('MaxHeight'))
# [1] does not mention Width and Height attributes. However,
# they're often present while MaxWidth and MaxHeight are
# missing, so should be used as fallbacks
width = int_or_none(track.get('MaxWidth') or track.get('Width'))
height = int_or_none(track.get('MaxHeight') or track.get('Height'))
sampling_rate = int_or_none(track.get('SamplingRate'))
track_url_pattern = re.sub(r'{[Bb]itrate}', track.attrib['Bitrate'], url_pattern)
@@ -2117,7 +2183,7 @@ class InfoExtractor(object):
def _extract_akamai_formats(self, manifest_url, video_id, hosts={}):
formats = []
hdcore_sign = 'hdcore=3.7.0'
f4m_url = re.sub(r'(https?://[^/+])/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
f4m_url = re.sub(r'(https?://[^/]+)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
hds_host = hosts.get('hds')
if hds_host:
f4m_url = re.sub(r'(https?://)[^/]+', r'\1' + hds_host, f4m_url)
@@ -2139,8 +2205,9 @@ class InfoExtractor(object):
def _extract_wowza_formats(self, url, video_id, m3u8_entry_protocol='m3u8_native', skip_protocols=[]):
url = re.sub(r'/(?:manifest|playlist|jwplayer)\.(?:m3u8|f4m|mpd|smil)', '', url)
url_base = self._search_regex(r'(?:https?|rtmp|rtsp)(://[^?]+)', url, 'format url')
http_base_url = 'http' + url_base
url_base = self._search_regex(
r'(?:(?:https?|rtmp|rtsp):)?(//[^?]+)', url, 'format url')
http_base_url = '%s:%s' % ('http', url_base)
formats = []
if 'm3u8' not in skip_protocols:
formats.extend(self._extract_m3u8_formats(
@@ -2174,7 +2241,7 @@ class InfoExtractor(object):
for protocol in ('rtmp', 'rtsp'):
if protocol not in skip_protocols:
formats.append({
'url': protocol + url_base,
'url': '%s:%s' % (protocol, url_base),
'format_id': protocol,
'protocol': protocol,
})
@@ -2182,7 +2249,7 @@ class InfoExtractor(object):
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
r'(?s)jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)(?!</script>).*?\.setup\s*\((?P<options>[^)]+)\)',
webpage)
if mobj:
try:
@@ -2258,11 +2325,17 @@ class InfoExtractor(object):
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
urls = []
formats = []
for source in jwplayer_sources_data:
source_url = self._proto_relative_url(source['file'])
source_url = self._proto_relative_url(source.get('file'))
if not source_url:
continue
if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url)
if source_url in urls:
continue
urls.append(source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':

View File

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

View File

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

View File

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

View File

@@ -171,7 +171,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'info_dict': {
'id': '727589',
'ext': 'mp4',
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 Give Me Deliverance from this Judicial Injustice!",
'title': "KONOSUBA -God's blessing on this wonderful world! 2 Episode 1 Give Me Deliverance From This Judicial Injustice!",
'description': 'md5:cbcf05e528124b0f3a0a419fc805ea7d',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Kadokawa Pictures Inc.',
@@ -179,7 +179,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2,
'episode': 'Give Me Deliverance from this Judicial Injustice!',
'episode': 'Give Me Deliverance From This Judicial Injustice!',
'episode_number': 1,
},
'params': {

View File

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

View File

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

View File

@@ -38,7 +38,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
class DailymotionIE(DailymotionBaseInfoExtractor):
_VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:embed|swf|#)/)?video/(?P<id>[^/?_]+)'
_VALID_URL = r'(?i)https?://(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:embed|swf|#)/)?video|swf)/(?P<id>[^/?_]+)'
IE_NAME = 'dailymotion'
_FORMATS = [
@@ -49,8 +49,24 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
('stream_h264_hd1080_url', 'hd180'),
]
_TESTS = [
{
_TESTS = [{
'url': 'http://www.dailymotion.com/video/x5kesuj_office-christmas-party-review-jason-bateman-olivia-munn-t-j-miller_news',
'md5': '074b95bdee76b9e3654137aee9c79dfe',
'info_dict': {
'id': 'x5kesuj',
'ext': 'mp4',
'title': 'Office Christmas Party Review Jason Bateman, Olivia Munn, T.J. Miller',
'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
'thumbnail': r're:^https?:.*\.(?:jpg|png)$',
'duration': 187,
'timestamp': 1493651285,
'upload_date': '20170501',
'uploader': 'Deadline',
'uploader_id': 'x1xm8ri',
'age_limit': 0,
'view_count': int,
},
}, {
'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
'md5': '2137c41a8e78554bb09225b8eb322406',
'info_dict': {
@@ -66,10 +82,10 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader_id': 'xijv66',
'age_limit': 0,
'view_count': int,
}
},
'skip': 'video gone',
}, {
# Vevo video
{
'url': 'http://www.dailymotion.com/video/x149uew_katy-perry-roar-official_musi',
'info_dict': {
'title': 'Roar (Official)',
@@ -82,9 +98,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'skip_download': True,
},
'skip': 'VEVO is only available in some countries',
},
}, {
# age-restricted video
{
'url': 'http://www.dailymotion.com/video/xyh2zz_leanna-decker-cyber-girl-of-the-year-desires-nude-playboy-plus_redband',
'md5': '0d667a7b9cebecc3c89ee93099c4159d',
'info_dict': {
@@ -95,22 +110,21 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'age_limit': 18,
},
'skip': 'video gone',
},
}, {
# geo-restricted, player v5
{
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
},
}, {
# with subtitles
{
'url': 'http://www.dailymotion.com/video/x20su5f_the-power-of-nightmares-1-the-rise-of-the-politics-of-fear-bbc-2004_news',
'only_matching': True,
},
{
}, {
'url': 'http://www.dailymotion.com/swf/video/x3n92nf',
'only_matching': True,
}
]
}, {
'url': 'http://www.dailymotion.com/swf/x3ss1m_funny-magic-trick-barry-and-stuart_fun',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -41,6 +41,7 @@ from .alphaporno import AlphaPornoIE
from .amcnetworks import AMCNetworksIE
from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE
from .anvato import AnvatoIE
from .anysex import AnySexIE
from .aol import AolIE
from .allocine import AllocineIE
@@ -87,10 +88,9 @@ from .azmedien import (
AZMedienPlaylistIE,
AZMedienShowPlaylistIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
from .bbc import (
BBCCoUkIE,
BBCCoUkArticleIE,
@@ -98,7 +98,10 @@ from .bbc import (
BBCCoUkPlaylistIE,
BBCIE,
)
from .beampro import BeamProLiveIE
from .beampro import (
BeamProLiveIE,
BeamProVodIE,
)
from .beeg import BeegIE
from .behindkink import BehindKinkIE
from .bellmedia import BellMediaIE
@@ -251,7 +254,10 @@ from .democracynow import DemocracynowIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .douyutv import (
DouyuShowIE,
DouyuTVIE,
)
from .dplay import (
DPlayIE,
DPlayItIE,
@@ -350,9 +356,9 @@ from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
PluzzIE,
FranceTvInfoIE,
FranceTVIE,
FranceTVEmbedIE,
FranceTVInfoIE,
GenerationQuoiIE,
CultureboxIE,
)
@@ -386,7 +392,6 @@ from .globo import (
from .go import GoIE
from .go90 import Go90IE
from .godtube import GodTubeIE
from .godtv import GodTVIE
from .golem import GolemIE
from .googledrive import GoogleDriveIE
from .googleplus import GooglePlusIE
@@ -542,6 +547,7 @@ from .mangomolo import (
)
from .matchtv import MatchTVIE
from .mdr import MDRIE
from .mediaset import MediasetIE
from .medici import MediciIE
from .meipai import MeipaiIE
from .melonvod import MelonVODIE
@@ -630,7 +636,10 @@ from .neteasemusic import (
NetEaseMusicProgramIE,
NetEaseMusicDjRadioIE,
)
from .newgrounds import NewgroundsIE
from .newgrounds import (
NewgroundsIE,
NewgroundsPlaylistIE,
)
from .newstube import NewstubeIE
from .nextmedia import (
NextMediaIE,
@@ -663,6 +672,8 @@ from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE
from .noco import NocoIE
from .nonktube import NonkTubeIE
from .noovo import NoovoIE
from .normalboots import NormalbootsIE
from .nosvideo import NosVideoIE
from .nova import NovaIE
@@ -731,8 +742,8 @@ from .openload import OpenloadIE
from .ora import OraTVIE
from .orf import (
ORFTVthekIE,
ORFOE1IE,
ORFFM4IE,
ORFOE1IE,
ORFIPTVIE,
)
from .packtpub import (
@@ -1013,11 +1024,6 @@ from .trilulilu import TriluliluIE
from .trutv import TruTVIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
from .tudou import (
TudouIE,
TudouPlaylistIE,
TudouAlbumIE,
)
from .tumblr import TumblrIE
from .tunein import (
TuneInClipIE,
@@ -1097,6 +1103,10 @@ from .uplynk import (
UplynkIE,
UplynkPreplayIE,
)
from .upskill import (
UpskillIE,
UpskillCourseIE,
)
from .urort import UrortIE
from .urplay import URPlayIE
from .usanetwork import USANetworkIE
@@ -1124,6 +1134,7 @@ from .vgtv import (
from .vh1 import VH1IE
from .vice import (
ViceIE,
ViceArticleIE,
ViceShowIE,
)
from .viceland import VicelandIE
@@ -1299,5 +1310,6 @@ from .youtube import (
YoutubeWatchLaterIE,
)
from .zapiks import ZapiksIE
from .zaq1 import Zaq1IE
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import ZingMp3IE

View File

@@ -102,6 +102,8 @@ class FirstTVIE(InfoExtractor):
'format_id': f.get('name'),
'tbr': tbr,
'source_preference': quality(f.get('name')),
# quality metadata of http formats may be incorrect
'preference': -1,
})
# m3u8 URL format is reverse engineered from [1] (search for
# master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)

View File

@@ -1,7 +1,10 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
int_or_none,
@@ -81,7 +84,7 @@ class FlickrIE(InfoExtractor):
formats = []
for stream in streams['stream']:
stream_type = str(stream.get('type'))
stream_type = compat_str(stream.get('type'))
formats.append({
'format_id': stream_type,
'url': stream['_content'],

View File

@@ -5,6 +5,7 @@ import itertools
from .common import InfoExtractor
from ..utils import (
get_element_by_id,
int_or_none,
remove_end,
)
@@ -46,7 +47,7 @@ class FoxgayIE(InfoExtractor):
formats = [{
'url': source,
'height': resolution,
'height': int_or_none(resolution),
} for source, resolution in zip(
video_data['sources'], video_data.get('resolutions', itertools.repeat(None)))]

View File

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

View File

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

View File

@@ -2,15 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse_unquote_plus,
)
from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
sanitized_Request,
ExtractorError,
urlencode_postdata
)
@@ -20,6 +16,7 @@ class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
_NETRC_MACHINE = 'funimation'
_TOKEN = None
_TESTS = [{
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
@@ -38,56 +35,38 @@ class FunimationIE(InfoExtractor):
}, {
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
'info_dict': {
'id': '9635',
'id': '210051',
'display_id': 'broadcast-dub-preview',
'ext': 'mp4',
'title': 'Attack on Titan: Junior High - Broadcast Dub Preview',
'description': 'md5:f8ec49c0aff702a7832cd81b8a44f803',
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
'skip': 'Access without user interaction is forbidden by CloudFlare',
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
}]
_LOGIN_URL = 'http://www.funimation.com/login'
def _extract_cloudflare_session_ua(self, url):
ci_session_cookie = self._get_cookies(url).get('ci_session')
if ci_session_cookie:
ci_session = compat_urllib_parse_unquote_plus(ci_session_cookie.value)
# ci_session is a string serialized by PHP function serialize()
# This case is simple enough to use regular expressions only
return self._search_regex(
r'"user_agent";s:\d+:"([^"]+)"', ci_session, 'user agent',
default=None)
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
data = urlencode_postdata({
'email_field': username,
'password_field': password,
})
user_agent = self._extract_cloudflare_session_ua(self._LOGIN_URL)
if not user_agent:
user_agent = 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'
login_request = sanitized_Request(self._LOGIN_URL, data, headers={
'User-Agent': user_agent,
'Content-Type': 'application/x-www-form-urlencoded'
})
login_page = self._download_webpage(
login_request, None, 'Logging in as %s' % username)
if any(p in login_page for p in ('funimation.com/logout', '>Log Out<')):
return
error = self._html_search_regex(
r'(?s)<div[^>]+id=["\']errorMessages["\'][^>]*>(.+?)</div>',
login_page, 'error messages', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
try:
data = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/auth/login/',
None, 'Logging in as %s' % username, data=urlencode_postdata({
'username': username,
'password': password,
}))
self._TOKEN = data['token']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
error = self._parse_json(e.cause.read().decode(), None)['error']
raise ExtractorError(error, expected=True)
raise
def _real_initialize(self):
self._login()
@@ -125,9 +104,12 @@ class FunimationIE(InfoExtractor):
description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
try:
headers = {}
if self._TOKEN:
headers['Authorization'] = 'Token %s' % self._TOKEN
sources = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
video_id)['items']
video_id, headers=headers)['items']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read(), video_id)['errors'][0]

View File

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

View File

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

View File

@@ -6,16 +6,13 @@ from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
js_to_json,
unified_strdate,
)
class GaskrankIE(InfoExtractor):
"""InfoExtractor for gaskrank.tv"""
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.html?'
_TESTS = [
{
_VALID_URL = r'https?://(?:www\.)?gaskrank\.tv/tv/(?P<categories>[^/]+)/(?P<id>[^/]+)\.htm'
_TESTS = [{
'url': 'http://www.gaskrank.tv/tv/motorrad-fun/strike-einparken-durch-anfaenger-crash-mit-groesserem-flurschaden.htm',
'md5': '1ae88dbac97887d85ebd1157a95fc4f9',
'info_dict': {
@@ -29,8 +26,7 @@ class GaskrankIE(InfoExtractor):
'upload_date': '20170110',
'uploader_url': None,
}
},
{
}, {
'url': 'http://www.gaskrank.tv/tv/racing/isle-of-man-tt-2011-michael-du-15920.htm',
'md5': 'c33ee32c711bc6c8224bfcbe62b23095',
'info_dict': {
@@ -41,27 +37,21 @@ class GaskrankIE(InfoExtractor):
'categories': ['racing'],
'display_id': 'isle-of-man-tt-2011-michael-du-15920',
'uploader_id': 'IOM',
'upload_date': '20160506',
'upload_date': '20170523',
'uploader_url': 'www.iomtt.com',
}
}
]
}]
def _real_extract(self, url):
"""extract information from gaskrank.tv"""
def fix_json(code):
"""Removes trailing comma in json: {{},} --> {{}}"""
return re.sub(r',\s*}', r'}', js_to_json(code))
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, fatal=True)
categories = [re.match(self._VALID_URL, url).group('categories')]
title = self._search_regex(
r'movieName\s*:\s*\'([^\']*)\'',
webpage, 'title')
thumbnail = self._search_regex(
r'poster\s*:\s*\'([^\']*)\'',
webpage, 'thumbnail', default=None)
mobj = re.search(
r'Video von:\s*(?P<uploader_id>[^|]*?)\s*\|\s*vom:\s*(?P<upload_date>[0-9][0-9]\.[0-9][0-9]\.[0-9][0-9][0-9][0-9])',
@@ -89,29 +79,14 @@ class GaskrankIE(InfoExtractor):
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
playlist = self._parse_json(
self._search_regex(
r'playlist\s*:\s*\[([^\]]*)\]',
webpage, 'playlist', default='{}'),
display_id, transform_source=fix_json, fatal=False)
video_id = self._search_regex(
r'https?://movies\.gaskrank\.tv/([^-]*?)(-[^\.]*)?\.mp4',
playlist.get('0').get('src'), 'video id')
webpage, 'video id', default=display_id)
formats = []
for key in playlist:
formats.append({
'url': playlist[key]['src'],
'format_id': key,
'quality': playlist[key].get('quality')})
self._sort_formats(formats, field_preference=['format_id'])
return {
entry = self._parse_html5_media_entries(url, webpage, video_id)[0]
entry.update({
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'categories': categories,
'display_id': display_id,
'uploader_id': uploader_id,
@@ -120,4 +95,7 @@ class GaskrankIE(InfoExtractor):
'tags': tags,
'view_count': view_count,
'average_rating': average_rating,
}
})
self._sort_formats(entry['formats'])
return entry

View File

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

View File

@@ -10,6 +10,7 @@ from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import (
compat_etree_fromstring,
compat_str,
compat_urllib_parse_unquote,
compat_urlparse,
compat_xml_parse_error,
@@ -86,6 +87,10 @@ from .openload import OpenloadIE
from .videopress import VideoPressIE
from .rutube import RutubeIE
from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
from .wistia import WistiaIE
from .mediaset import MediasetIE
class GenericIE(InfoExtractor):
@@ -430,6 +435,22 @@ class GenericIE(InfoExtractor):
'skip_download': True, # m3u8 download
},
},
{
# Brightcove video in <iframe>
'url': 'http://www.un.org/chinese/News/story.asp?NewsID=27724',
'md5': '36d74ef5e37c8b4a2ce92880d208b968',
'info_dict': {
'id': '5360463607001',
'ext': 'mp4',
'title': '叙利亚失明儿童在废墟上演唱《心跳》 呼吁获得正常童年生活',
'description': '联合国儿童基金会中东和北非区域大使、作曲家扎德·迪拉尼Zade Dirani在3月15日叙利亚冲突爆发7周年纪念日之际发布了为叙利亚谱写的歌曲《心跳》HEARTBEAT为受到六年冲突影响的叙利亚儿童发出强烈呐喊呼吁世界做出共同努力使叙利亚儿童重新获得享有正常童年生活的权利。',
'uploader': 'United Nations',
'uploader_id': '1362235914001',
'timestamp': 1489593889,
'upload_date': '20170315',
},
'add_ie': ['BrightcoveLegacy'],
},
{
# Brightcove with alternative playerID key
'url': 'http://www.nature.com/nmeth/journal/v9/n7/fig_tab/nmeth.2062_SV1.html',
@@ -1411,6 +1432,22 @@ class GenericIE(InfoExtractor):
'skip_download': True,
},
},
{
# Brightcove embed with whitespace around attribute names
'url': 'http://www.stack.com/video/3167554373001/learn-to-hit-open-three-pointers-with-damian-lillard-s-baseline-drift-drill',
'info_dict': {
'id': '3167554373001',
'ext': 'mp4',
'title': "Learn to Hit Open Three-Pointers With Damian Lillard's Baseline Drift Drill",
'description': 'md5:57bacb0e0f29349de4972bfda3191713',
'uploader_id': '1079349493',
'upload_date': '20140207',
'timestamp': 1391810548,
},
'params': {
'skip_download': True,
},
},
# Another form of arte.tv embed
{
'url': 'http://www.tv-replay.fr/redirection/09-04-16/arte-reportage-arte-11508975.html',
@@ -1661,6 +1698,42 @@ class GenericIE(InfoExtractor):
},
'playlist_mincount': 5,
},
{
'url': 'http://kron4.com/2017/04/28/standoff-with-walnut-creek-murder-suspect-ends-with-arrest/',
'info_dict': {
'id': 'standoff-with-walnut-creek-murder-suspect-ends-with-arrest',
'title': 'Standoff with Walnut Creek murder suspect ends',
'description': 'md5:3ccc48a60fc9441eeccfc9c469ebf788',
},
'playlist_mincount': 4,
},
{
# WashingtonPost embed
'url': 'http://www.vanityfair.com/hollywood/2017/04/donald-trump-tv-pitches',
'info_dict': {
'id': '8caf6e88-d0ec-11e5-90d3-34c2c42653ac',
'ext': 'mp4',
'title': "No one has seen the drama series based on Trump's life \u2014 until now",
'description': 'Donald Trump wanted a weekly TV drama based on his life. It never aired. But The Washington Post recently obtained a scene from the pilot script — and enlisted actors.',
'timestamp': 1455216756,
'uploader': 'The Washington Post',
'upload_date': '20160211',
},
'add_ie': [WashingtonPostIE.ie_key()],
},
{
# Mediaset embed
'url': 'http://www.tgcom24.mediaset.it/politica/serracchiani-voglio-vivere-in-una-societa-aperta-reazioni-sproporzionate-_3071354-201702a.shtml',
'info_dict': {
'id': '720642',
'ext': 'mp4',
'title': 'Serracchiani: "Voglio vivere in una società aperta, con tutela del patto di fiducia"',
},
'params': {
'skip_download': True,
},
'add_ie': [MediasetIE.ie_key()],
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@@ -1835,14 +1908,14 @@ class GenericIE(InfoExtractor):
content_type = head_response.headers.get('Content-Type', '').lower()
m = re.match(r'^(?P<type>audio|video|application(?=/(?:ogg$|(?:vnd\.apple\.|x-)?mpegurl)))/(?P<format_id>[^;\s]+)', content_type)
if m:
format_id = m.group('format_id')
format_id = compat_str(m.group('format_id'))
if format_id.endswith('mpegurl'):
formats = self._extract_m3u8_formats(url, video_id, 'mp4')
elif format_id == 'f4m':
formats = self._extract_f4m_formats(url, video_id)
else:
formats = [{
'format_id': m.group('format_id'),
'format_id': format_id,
'url': url,
'vcodec': 'none' if m.group('type') == 'audio' else None
}]
@@ -2054,57 +2127,20 @@ class GenericIE(InfoExtractor):
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for embedded Wistia player
match = re.search(
r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage)
if match:
embed_url = self._proto_relative_url(
unescapeHTML(match.group('url')))
wistia_url = WistiaIE._extract_url(webpage)
if wistia_url:
return {
'_type': 'url_transparent',
'url': embed_url,
'ie_key': 'Wistia',
'url': self._proto_relative_url(wistia_url),
'ie_key': WistiaIE.ie_key(),
'uploader': video_uploader,
}
match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage)
if match:
return {
'_type': 'url_transparent',
'url': 'wistia:%s' % match.group('id'),
'ie_key': 'Wistia',
'uploader': video_uploader,
}
match = re.search(
r'''(?sx)
<script[^>]+src=(["'])(?:https?:)?//fast\.wistia\.com/assets/external/E-v1\.js\1[^>]*>.*?
<div[^>]+class=(["']).*?\bwistia_async_(?P<id>[a-z0-9]+)\b.*?\2
''', webpage)
if match:
return self.url_result(self._proto_relative_url(
'wistia:%s' % match.group('id')), 'Wistia')
# Look for SVT player
svt_url = SVTIE._extract_url(webpage)
if svt_url:
return self.url_result(svt_url, 'SVT')
# Look for embedded condenast player
matches = re.findall(
r'<iframe\s+(?:[a-zA-Z-]+="[^"]+"\s+)*?src="(https?://player\.cnevids\.com/embed/[^"]+")',
webpage)
if matches:
return {
'_type': 'playlist',
'entries': [{
'_type': 'url',
'ie_key': 'CondeNast',
'url': ma,
} for ma in matches],
'title': video_title,
'id': video_id,
}
# Look for Bandcamp pages with custom domain
mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
if mobj is not None:
@@ -2498,28 +2534,11 @@ class GenericIE(InfoExtractor):
return self.playlist_result(
limelight_urls, video_id, video_title, video_description)
mobj = re.search(r'LimelightPlayer\.doLoad(Media|Channel|ChannelList)\(["\'](?P<id>[a-z0-9]{32})', webpage)
if mobj:
lm = {
'Media': 'media',
'Channel': 'channel',
'ChannelList': 'channel_list',
}
return self.url_result(smuggle_url('limelight:%s:%s' % (
lm[mobj.group(1)], mobj.group(2)), {'source_url': url}),
'Limelight%s' % mobj.group(1), mobj.group(2))
mobj = re.search(
r'''(?sx)
<object[^>]+class=(["\'])LimelightEmbeddedPlayerFlash\1[^>]*>.*?
<param[^>]+
name=(["\'])flashVars\2[^>]+
value=(["\'])(?:(?!\3).)*mediaId=(?P<id>[a-z0-9]{32})
''', webpage)
if mobj:
return self.url_result(smuggle_url(
'limelight:media:%s' % mobj.group('id'),
{'source_url': url}), 'LimelightMedia', mobj.group('id'))
# Look for Anvato embeds
anvato_urls = AnvatoIE._extract_urls(self, webpage, video_id)
if anvato_urls:
return self.playlist_result(
anvato_urls, video_id, video_title, video_description)
# Look for AdobeTVVideo embeds
mobj = re.search(
@@ -2638,6 +2657,18 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
# Look for Mediaset embeds
mediaset_urls = MediasetIE._extract_urls(webpage)
if mediaset_urls:
return self.playlist_from_matches(
mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')

View File

@@ -82,7 +82,7 @@ class GfycatIE(InfoExtractor):
video_url = gfy.get('%sUrl' % format_id)
if not video_url:
continue
filesize = gfy.get('%sSize' % format_id)
filesize = int_or_none(gfy.get('%sSize' % format_id))
formats.append({
'url': video_url,
'format_id': format_id,

View File

@@ -36,22 +36,26 @@ class GoIE(AdobePassIE):
'requestor_id': 'DisneyXD',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:(?:[^/]+/)*(?P<id>vdka\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'info_dict': {
'id': '0_g86w5onx',
'id': 'VDKA3807643',
'ext': 'mp4',
'title': 'Sneak Peek: Language Arts',
'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
'only_matching': True,
'url': 'http://watchdisneyxd.go.com/doraemon',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
@@ -60,19 +64,36 @@ class GoIE(AdobePassIE):
'only_matching': True,
}]
def _extract_videos(self, brand, video_id='-1', show_id='-1'):
display_id = video_id if video_id != '-1' else show_id
return self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/%s/-1/%s/-1/-1.json' % (brand, show_id, video_id),
display_id)['video']
def _real_extract(self, url):
sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups()
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
if not video_id:
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id')
site_info = self._SITE_INFO[sub_domain]
brand = site_info['brand']
video_data = self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),
video_id)['video'][0]
r'data-video-id=["\']*(VDKA\w+)', webpage, 'video id', default=None)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
formats = []
@@ -105,7 +126,7 @@ class GoIE(AdobePassIE):
self._initialize_geo_bypass(['US'])
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
video_id, data=urlencode_postdata(data), headers=self.geo_verification_headers())
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
for error in errors:

View File

@@ -1,66 +0,0 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..utils import js_to_json
class GodTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?god\.tv(?:/[^/]+)*/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://god.tv/jesus-image/video/jesus-conference-2016/randy-needham',
'info_dict': {
'id': 'lpd3g2MzE6D1g8zFAKz8AGpxWcpu6o_3',
'ext': 'mp4',
'title': 'Randy Needham',
'duration': 3615.08,
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://god.tv/playlist/bible-study',
'info_dict': {
'id': 'bible-study',
},
'playlist_mincount': 37,
}, {
'url': 'http://god.tv/node/15097',
'only_matching': True,
}, {
'url': 'http://god.tv/live/africa',
'only_matching': True,
}, {
'url': 'http://god.tv/liveevents',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
settings = self._parse_json(
self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'settings', default='{}'),
display_id, transform_source=js_to_json, fatal=False)
ooyala_id = None
if settings:
playlist = settings.get('playlist')
if playlist and isinstance(playlist, list):
entries = [
OoyalaIE._build_url_result(video['content_id'])
for video in playlist if video.get('content_id')]
if entries:
return self.playlist_result(entries, display_id)
ooyala_id = settings.get('ooyala', {}).get('content_id')
if not ooyala_id:
ooyala_id = self._search_regex(
r'["\']content_id["\']\s*:\s*(["\'])(?P<id>[\w-]+)\1',
webpage, 'ooyala id', group='id')
return OoyalaIE._build_url_result(ooyala_id)

View File

@@ -3,6 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
@@ -46,7 +47,7 @@ class GolemIE(InfoExtractor):
continue
formats.append({
'format_id': e.tag,
'format_id': compat_str(e.tag),
'url': compat_urlparse.urljoin(self._PREFIX, url),
'height': self._int(e.get('height'), 'height'),
'width': self._int(e.get('width'), 'width'),

View File

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

View File

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

View File

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

View File

@@ -112,7 +112,8 @@ class InstagramIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
(video_url, description, thumbnail, timestamp, uploader,
uploader_id, like_count, comment_count, height, width) = [None] * 10
uploader_id, like_count, comment_count, comments, height,
width) = [None] * 11
shared_data = self._parse_json(
self._search_regex(
@@ -121,7 +122,10 @@ class InstagramIE(InfoExtractor):
video_id, fatal=False)
if shared_data:
media = try_get(
shared_data, lambda x: x['entry_data']['PostPage'][0]['media'], dict)
shared_data,
(lambda x: x['entry_data']['PostPage'][0]['graphql']['shortcode_media'],
lambda x: x['entry_data']['PostPage'][0]['media']),
dict)
if media:
video_url = media.get('video_url')
height = int_or_none(media.get('dimensions', {}).get('height'))

View File

@@ -189,7 +189,11 @@ class IqiyiIE(InfoExtractor):
'only_matching': True,
}, {
'url': 'http://yule.iqiyi.com/pcb.html',
'only_matching': True,
'info_dict': {
'id': '4a0af228fddb55ec96398a364248ed7f',
'ext': 'mp4',
'title': '第2017-04-21期 女艺人频遭极端粉丝骚扰',
},
}, {
# VIP-only video. The first 2 parts (6 minutes) are available without login
# MD5 sums omitted as values are different on Travis CI and my machine
@@ -337,15 +341,18 @@ class IqiyiIE(InfoExtractor):
url, 'temp_id', note='download video page')
# There's no simple way to determine whether an URL is a playlist or not
# So detect it
# Sometimes there are playlist links in individual videos, so treat it
# as a single video first
tvid = self._search_regex(
r'data-(?:player|shareplattrigger)-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid', default=None)
if tvid is None:
playlist_result = self._extract_playlist(webpage)
if playlist_result:
return playlist_result
raise ExtractorError('Can\'t find any video')
tvid = self._search_regex(
r'data-player-tvid\s*=\s*[\'"](\d+)', webpage, 'tvid')
video_id = self._search_regex(
r'data-player-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
r'data-(?:player|shareplattrigger)-videoid\s*=\s*[\'"]([a-f\d]+)', webpage, 'video_id')
formats = []
for _ in range(5):
@@ -377,7 +384,8 @@ class IqiyiIE(InfoExtractor):
self._sort_formats(formats)
title = (get_element_by_id('widget-videotitle', webpage) or
clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage)))
clean_html(get_element_by_attribute('class', 'mod-play-tit', webpage)) or
self._html_search_regex(r'<span[^>]+data-videochanged-title="word"[^>]*>([^<]+)</span>', webpage, 'title'))
return {
'id': video_id,

View File

@@ -65,9 +65,9 @@ class JoveIE(InfoExtractor):
webpage, 'description', fatal=False)
publish_date = unified_strdate(self._html_search_meta(
'citation_publication_date', webpage, 'publish date', fatal=False))
comment_count = self._html_search_regex(
comment_count = int(self._html_search_regex(
r'<meta name="num_comments" content="(\d+) Comments?"',
webpage, 'comment count', fatal=False)
webpage, 'comment count', fatal=False))
return {
'id': video_id,

View File

@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
@@ -8,15 +10,15 @@ from ..utils import (
urlencode_postdata,
xpath_element,
xpath_text,
urljoin,
update_url_query,
js_to_json,
)
class Laola1TvEmbedIE(InfoExtractor):
IE_NAME = 'laola1tv:embed'
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/titanplayer\.php\?.*?\bvideoid=(?P<id>\d+)'
_TEST = {
_TESTS = [{
# flashvars.premium = "false";
'url': 'https://www.laola1.tv/titanplayer.php?videoid=708065&type=V&lang=en&portal=int&customer=1024',
'info_dict': {
@@ -26,7 +28,30 @@ class Laola1TvEmbedIE(InfoExtractor):
'uploader': 'ITTF - International Table Tennis Federation',
'upload_date': '20161211',
},
}
}]
def _extract_token_url(self, stream_access_url, video_id, data):
return self._download_json(
stream_access_url, video_id, headers={
'Content-Type': 'application/json',
}, data=json.dumps(data).encode())['data']['stream-access'][0]
def _extract_formats(self, token_url, video_id):
token_doc = self._download_xml(
token_url, video_id, 'Downloading token',
headers=self.geo_verification_headers())
token_attrib = xpath_element(token_doc, './/token').attrib
if token_attrib['status'] != '0':
raise ExtractorError(
'Token error: %s' % token_attrib['comment'], expected=True)
formats = self._extract_akamai_formats(
'%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
video_id)
self._sort_formats(formats)
return formats
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -68,29 +93,16 @@ class Laola1TvEmbedIE(InfoExtractor):
else:
data_abo = urlencode_postdata(
dict((i, v) for i, v in enumerate(_v('req_liga_abos').split(','))))
token_url = self._download_json(
'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access',
video_id, query={
stream_access_url = update_url_query(
'https://club.laola1.tv/sp/laola1/api/v3/user/session/premium/player/stream-access', {
'videoId': _v('id'),
'target': self._search_regex(r'vs_target = (\d+);', webpage, 'vs target'),
'label': _v('label'),
'area': _v('area'),
}, data=data_abo)['data']['stream-access'][0]
})
token_url = self._extract_token_url(stream_access_url, video_id, data_abo)
token_doc = self._download_xml(
token_url, video_id, 'Downloading token',
headers=self.geo_verification_headers())
token_attrib = xpath_element(token_doc, './/token').attrib
if token_attrib['status'] != '0':
raise ExtractorError(
'Token error: %s' % token_attrib['comment'], expected=True)
formats = self._extract_akamai_formats(
'%s?hdnea=%s' % (token_attrib['url'], token_attrib['auth']),
video_id)
self._sort_formats(formats)
formats = self._extract_formats(token_url, video_id)
categories_str = _v('meta_sports')
categories = categories_str.split(',') if categories_str else []
@@ -107,7 +119,7 @@ class Laola1TvEmbedIE(InfoExtractor):
}
class Laola1TvIE(InfoExtractor):
class Laola1TvIE(Laola1TvEmbedIE):
IE_NAME = 'laola1tv'
_VALID_URL = r'https?://(?:www\.)?laola1\.tv/[a-z]+-[a-z]+/[^/]+/(?P<id>[^/?#&]+)'
_TESTS = [{
@@ -164,13 +176,42 @@ class Laola1TvIE(InfoExtractor):
if 'Dieser Livestream ist bereits beendet.' in webpage:
raise ExtractorError('This live stream has already finished.', expected=True)
iframe_url = urljoin(url, self._search_regex(
r'<iframe[^>]*?id="videoplayer"[^>]*?src="([^"]+)"',
webpage, 'iframe url'))
conf = self._parse_json(self._search_regex(
r'(?s)conf\s*=\s*({.+?});', webpage, 'conf'),
display_id, js_to_json)
video_id = conf['videoid']
config = self._download_json(conf['configUrl'], video_id, query={
'videoid': video_id,
'partnerid': conf['partnerid'],
'language': conf.get('language', ''),
'portal': conf.get('portalid', ''),
})
error = config.get('error')
if error:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
video_data = config['video']
title = video_data['title']
is_live = video_data.get('isLivestream') and video_data.get('isLive')
meta = video_data.get('metaInformation')
sports = meta.get('sports')
categories = sports.split(',') if sports else []
token_url = self._extract_token_url(
video_data['streamAccess'], video_id,
video_data['abo']['required'])
formats = self._extract_formats(token_url, video_id)
return {
'_type': 'url',
'id': video_id,
'display_id': display_id,
'url': iframe_url,
'ie_key': 'Laola1TvEmbed',
'title': self._live_title(title) if is_live else title,
'description': video_data.get('description'),
'thumbnail': video_data.get('image'),
'categories': categories,
'formats': formats,
'is_live': is_live,
}

View File

@@ -23,7 +23,6 @@ from ..utils import (
str_or_none,
url_basename,
urshift,
update_url_query,
)
@@ -51,7 +50,7 @@ class LeIE(InfoExtractor):
'id': '1415246',
'ext': 'mp4',
'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
'description': 'md5:28942e650e82ed4fcc8e4de919ee854d',
},
'params': {
'hls_prefer_native': True,
@@ -69,7 +68,6 @@ class LeIE(InfoExtractor):
'params': {
'hls_prefer_native': True,
},
'skip': 'Only available in China',
}, {
'url': 'http://sports.le.com/video/25737697.html',
'only_matching': True,
@@ -81,7 +79,7 @@ class LeIE(InfoExtractor):
'only_matching': True,
}]
# ror() and calc_time_key() are reversed from a embedded swf file in KLetvPlayer.swf
# ror() and calc_time_key() are reversed from a embedded swf file in LetvPlayer.swf
def ror(self, param1, param2):
_loc3_ = 0
while _loc3_ < param2:
@@ -90,15 +88,8 @@ class LeIE(InfoExtractor):
return param1
def calc_time_key(self, param1):
_loc2_ = 773625421
_loc3_ = self.ror(param1, _loc2_ % 13)
_loc3_ = _loc3_ ^ _loc2_
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# reversed from http://jstatic.letvcdn.com/sdk/player.js
def get_mms_key(self, time):
return self.ror(time, 8) ^ 185025305
_loc2_ = 185025305
return self.ror(param1, _loc2_ % 17) ^ _loc2_
# see M3U8Encryption class in KLetvPlayer.swf
@staticmethod
@@ -122,7 +113,7 @@ class LeIE(InfoExtractor):
def _check_errors(self, play_json):
# Check for errors
playstatus = play_json['playstatus']
playstatus = play_json['msgs']['playstatus']
if playstatus['status'] == 0:
flag = playstatus['flag']
if flag == 1:
@@ -134,59 +125,32 @@ class LeIE(InfoExtractor):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
play_json_h5 = self._download_json(
'http://api.le.com/mms/out/video/playJsonH5',
media_id, 'Downloading html5 playJson data', query={
'id': media_id,
'platid': 3,
'splatid': 304,
'format': 1,
'tkey': self.get_mms_key(int(time.time())),
'domain': 'www.le.com',
'tss': 'no',
},
headers=self.geo_verification_headers())
self._check_errors(play_json_h5)
play_json_flash = self._download_json(
'http://api.le.com/mms/out/video/playJson',
'http://player-pc.le.com/mms/out/video/playJson',
media_id, 'Downloading flash playJson data', query={
'id': media_id,
'platid': 1,
'splatid': 101,
'format': 1,
'source': 1000,
'tkey': self.calc_time_key(int(time.time())),
'domain': 'www.le.com',
'region': 'cn',
},
headers=self.geo_verification_headers())
self._check_errors(play_json_flash)
def get_h5_urls(media_url, format_id):
location = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id, query={
'format': 1,
'expect': 3,
'tss': 'no',
})['location']
return {
'http': update_url_query(location, {'tss': 'no'}),
'hls': update_url_query(location, {'tss': 'ios'}),
}
def get_flash_urls(media_url, format_id):
media_url += '&' + compat_urllib_parse_urlencode({
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id,
query={
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
'tss': 'ios',
})
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id)
req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id,
note='Downloading m3u8 information for format %s' % format_id)
@@ -199,8 +163,7 @@ class LeIE(InfoExtractor):
extracted_formats = []
formats = []
for play_json, get_urls in ((play_json_h5, get_h5_urls), (play_json_flash, get_flash_urls)):
playurl = play_json['playurl']
playurl = play_json_flash['msgs']['playurl']
play_domain = playurl['domain'][0]
for format_id, format_data in playurl.get('dispatch', []).items():
@@ -209,7 +172,7 @@ class LeIE(InfoExtractor):
extracted_formats.append(format_id)
media_url = play_domain + format_data[0]
for protocol, format_url in get_urls(media_url, format_id).items():
for protocol, format_url in get_flash_urls(media_url, format_id).items():
f = {
'url': format_url,
'ext': determine_ext(format_data[1]),

View File

@@ -86,7 +86,7 @@ class LEGOIE(InfoExtractor):
formats = self._extract_akamai_formats(
'%si/s/public/%s_,%s,.mp4.csmil/master.m3u8' % (streaming_base, path, streaming_path), video_id)
m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
lambda f: f.get('protocol') == 'm3u8_native' and f.get('vcodec') != 'none',
formats))
if len(m3u8_formats) == len(self._BITRATES):
self._sort_formats(m3u8_formats)

View File

@@ -1,6 +1,5 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
@@ -11,10 +10,10 @@ class LiveLeakIE(InfoExtractor):
_VALID_URL = r'https?://(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<id>[\w_]+)(?:.*)'
_TESTS = [{
'url': 'http://www.liveleak.com/view?i=757_1364311680',
'md5': '50f79e05ba149149c1b4ea961223d5b3',
'md5': '0813c2430bea7a46bf13acf3406992f4',
'info_dict': {
'id': '757_1364311680',
'ext': 'flv',
'ext': 'mp4',
'description': 'extremely bad day for this guy..!',
'uploader': 'ljfriel2',
'title': 'Most unlucky car accident',
@@ -22,7 +21,7 @@ class LiveLeakIE(InfoExtractor):
}
}, {
'url': 'http://www.liveleak.com/view?i=f93_1390833151',
'md5': 'b13a29626183c9d33944e6a04f41aafc',
'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
'info_dict': {
'id': 'f93_1390833151',
'ext': 'mp4',
@@ -32,6 +31,7 @@ class LiveLeakIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$'
}
}, {
# Prochan embed
'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
'md5': '42c6d97d54f1db107958760788c5f48f',
'info_dict': {
@@ -41,11 +41,13 @@ class LiveLeakIE(InfoExtractor):
'uploader': 'CapObveus',
'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
'age_limit': 18,
}
},
'skip': 'Video is dead',
}, {
# Covers https://github.com/rg3/youtube-dl/pull/5983
# Multiple resolutions
'url': 'http://www.liveleak.com/view?i=801_1409392012',
'md5': '0b3bec2d888c20728ca2ad3642f0ef15',
'md5': 'c3a449dbaca5c0d1825caecd52a57d7b',
'info_dict': {
'id': '801_1409392012',
'ext': 'mp4',
@@ -93,17 +95,11 @@ class LiveLeakIE(InfoExtractor):
webpage, 'age limit', default=None))
video_thumbnail = self._og_search_thumbnail(webpage)
sources_raw = self._search_regex(
r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
if sources_raw is None:
alt_source = self._search_regex(
r'(file: ".*?"),', webpage, 'video URL', default=None)
if alt_source:
sources_raw = '[{ %s}]' % alt_source
else:
entries = self._parse_html5_media_entries(url, webpage, video_id)
if not entries:
# Maybe an embed?
embed_url = self._search_regex(
r'<iframe[^>]+src="(https?://(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?(?:prochan|youtube)\.com/embed[^"]+)"',
webpage, 'embed URL')
return {
'_type': 'url_transparent',
@@ -115,35 +111,23 @@ class LiveLeakIE(InfoExtractor):
'age_limit': age_limit,
}
sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
sources = json.loads(sources_json)
info_dict = entries[0]
formats = [{
'format_id': '%s' % i,
'format_note': s.get('label'),
'url': s['file'],
} for i, s in enumerate(sources)]
for a_format in info_dict['formats']:
if not a_format.get('height'):
a_format['height'] = int_or_none(self._search_regex(
r'([0-9]+)p\.mp4', a_format['url'], 'height label',
default=None))
for i, s in enumerate(sources):
# Removing '.h264_*.mp4' gives the raw video, which is essentially
# the same video without the LiveLeak logo at the top (see
# https://github.com/rg3/youtube-dl/pull/4768)
orig_url = re.sub(r'\.h264_.+?\.mp4', '', s['file'])
if s['file'] != orig_url:
formats.append({
'format_id': 'original-%s' % i,
'format_note': s.get('label'),
'url': orig_url,
'preference': 1,
})
self._sort_formats(formats)
self._sort_formats(info_dict['formats'])
return {
info_dict.update({
'id': video_id,
'title': video_title,
'description': video_description,
'uploader': video_uploader,
'formats': formats,
'age_limit': age_limit,
'thumbnail': video_thumbnail,
}
})
return info_dict

View File

@@ -17,7 +17,7 @@ from ..utils import (
class MedialaanIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:www\.|nieuws\.)?
(?:
(?P<site_id>vtm|q2|vtmkzoom)\.be/
(?:
@@ -85,6 +85,22 @@ class MedialaanIE(InfoExtractor):
# clip
'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
'only_matching': True,
}, {
# http/s redirect
'url': 'https://vtmkzoom.be/video?aid=45724',
'info_dict': {
'id': '257136373657000',
'ext': 'mp4',
'title': 'K3 Dansstudio Ushuaia afl.6',
},
'params': {
'skip_download': True,
},
'skip': 'Requires account credentials',
}, {
# nieuws.vtm.be
'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma',
'only_matching': True,
}]
def _real_initialize(self):
@@ -146,6 +162,8 @@ class MedialaanIE(InfoExtractor):
video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
if player:
video = player[-1]
if video['videoUrl'] in ('http', 'https'):
return self.url_result(video['url'], MedialaanIE.ie_key())
info = {
'id': video_id,
'url': video['videoUrl'],

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