Compare commits

..

458 Commits

Author SHA1 Message Date
Philipp Hagemeister
3a0f0c263a release 2015.04.28 2015-04-28 09:11:18 +02:00
Sergey M․
2419a376b9 [moniker] Check not found error (#5541) 2015-04-27 23:46:16 +06:00
Sergey M․
e206740fd7 [moniker] Capture and output error message (#5541) 2015-04-27 23:44:05 +06:00
Sergey M․
290a5a8d85 [escapist] Fix imsVideo regex (#5090) 2015-04-27 22:17:51 +06:00
pulpe
e2dc351d25 [escapist] Fix extractor (fixes #5090) 2015-04-27 17:44:13 +02:00
Sergey M․
c86b61428b [utils] Fix another old python 2.6 kwargs issue (Closes #5539) 2015-04-27 20:00:18 +06:00
Sergey M.
40b96352c9 Merge pull request #5523 from jaimeMF/remove-format-limit
Remove the --max-quality option
2015-04-27 16:44:58 +05:00
Sergey M.
189ba90996 [README] Use youtube-dl test video URL 2015-04-27 16:05:01 +06:00
Sergey M.
c8183e661d [README] Document special characters escaping (#5538) 2015-04-27 16:01:30 +06:00
Sergey M․
053c94f1b3 [README] Clarify youtube-dl version when format selection changed to bestvideo+bestaudio/best 2015-04-27 15:21:51 +06:00
Sergey M․
b9d76a9571 Merge branch 'fstirlitz-philharmoniedeparis' 2015-04-27 03:36:46 +06:00
Sergey M․
a01cfc2951 [philharmoniedeparis] Fix extraction and tests, improve, simplify 2015-04-27 03:36:32 +06:00
Philipp Hagemeister
4eb5c65bee release 2015.04.26 2015-04-26 22:45:20 +02:00
felix
06d07c4000 New extractor: live.philharmoniedeparis.fr 2015-04-26 14:15:29 +02:00
Sergey M․
74f8654a53 [downloader/external] Use encodeArgument 2015-04-26 04:33:43 +06:00
Sergey M․
9e105a858c [downloader/rtmp] Fix arguments encoding and simplify retry logic (Closes #5528) 2015-04-26 04:32:54 +06:00
Sergey M․
cd8a07a764 [downloader/common] Use decodeArgument 2015-04-26 04:30:45 +06:00
Sergey M․
aa49acd15a [utils] Add get_subprocess_encoding and filename/argument decode counterparts 2015-04-26 04:29:41 +06:00
Jaime Marquínez Ferrándiz
642f23bd81 [southpark] Use 'ñ' in the spanish extractor name
IE_NAME can contain unicode characters, so it shouldn't be a problem.
2015-04-25 22:36:11 +02:00
pulpe
2e24e6bd17 Merge branch 'mp3' 2015-04-25 20:41:59 +02:00
pulpe
2a09c1b8ab [postprocessor/embedthumbnail] Fix mp3 embedding with avconv (fixes #5526) 2015-04-25 20:41:15 +02:00
Sergey M․
a5ebf77d87 [mplayer] Rename to RTSP 2015-04-26 00:25:51 +06:00
Sergey M․
b874495b1f [mplayer] Simplify 2015-04-26 00:23:16 +06:00
Sergey M․
b860f5dfd4 [mplayer] Clarify error message 2015-04-26 00:22:13 +06:00
Sergey M.
b19fc36c81 Merge pull request #5521 from mrkrossxdx/mpv
Added support for mpv if mplayer is not available (new version)
2015-04-25 23:19:59 +05:00
Sergey M․
d2d8248f68 [instagram] Modernize 2015-04-25 22:42:15 +06:00
Sergey M․
f54bab4d67 [instagram] Improve _VALID_URL 2015-04-25 22:39:50 +06:00
Yen Chi Hsuan
bf6427d2fb [ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146) 2015-04-25 23:18:27 +08:00
Yen Chi Hsuan
672f1bd849 [cspan] Extract subtitles 2015-04-25 23:18:27 +08:00
Sergey M․
529d26c3e1 [orf:iptv] Update test 2015-04-25 21:06:27 +06:00
Sergey M․
857f00ed94 [southpark] Improve some _VALID_URL's 2015-04-25 20:24:15 +06:00
Sergey M․
e4a5e772f2 [southpark:espanol] Add extractor (Closes #5525) 2015-04-25 20:23:42 +06:00
Sergey M․
a542e372ab [mtv] Stuff lang into info URL when available 2015-04-25 20:22:20 +06:00
Jaime Marquínez Ferrándiz
0d1bd5d62f README: remove --max-quality 2015-04-25 15:14:16 +02:00
Jaime Marquínez Ferrándiz
9f3fa89f7c Remove the --max-quality option
It doesn't work well with 'bestvideo' and 'bestaudio' because they are usually before the max quality.
Format filters should be used instead, they are more flexible and don't require the requested quality to exist for each video.
2015-04-25 11:59:54 +02:00
Jaime Marquínez Ferrándiz
92995e6265 [postprocessor/embedthumbnail] Style fix 2015-04-24 22:08:00 +02:00
Jaime Marquínez Ferrándiz
a4196c3ea5 [ellentv] Remove unused import 2015-04-24 22:06:22 +02:00
mrkrossxdx
db37e0c273 Added support for mpv if mplayer is not available 2015-04-24 20:50:34 +02:00
Sergey M․
d0aefec99a [ellentv:clips] Fix test 2015-04-24 22:10:27 +06:00
Sergey M․
66be4b89d7 [ellentv:clips] Fix extraction 2015-04-24 22:09:54 +06:00
Sergey M․
870744ce8f [ellentv] Fix tests 2015-04-24 22:07:15 +06:00
Sergey M․
2ad978532b [ellentv] Fix extraction 2015-04-24 22:03:14 +06:00
Sergey M․
5090d93f2c [dotsub] Fix extraction 2015-04-24 21:47:13 +06:00
Yen Chi Hsuan
c8ff645766 [gdcvault] Add display_id 2015-04-24 22:43:33 +08:00
Yen Chi Hsuan
25f7d1beba [gdcvault] Extend _VALID_URL (fixes #5236) 2015-04-24 22:33:35 +08:00
pulpe
09aa111918 Merge branch 'embedthumb' 2015-04-24 09:25:44 +02:00
pulpe
10fb7710e8 Forgot to clean the remains of class 2015-04-24 09:17:46 +02:00
pulpe
c0ea8ebb9b [ffmpeg] Remove unneeded class 2015-04-24 09:11:39 +02:00
pulpe
31fd9c7601 [embedthumbnail] use FFmpegPostProcessor for mp3 2015-04-24 09:08:57 +02:00
pulpe
ddbed36455 [embedthumbnail] Add support for mp3 cover embedding 2015-04-24 08:48:49 +02:00
Yen Chi Hsuan
a9b0d4e1f4 [Crunchyroll] Fix extraction on Python 2.6
XPath with recursive children selection not supported
2015-04-24 14:09:35 +08:00
Sergey M․
4d6a3ff411 [README] Finally fix configuration file link 2015-04-24 01:41:36 +06:00
Sergey M․
7fb993e1f4 [README] Fix configuration file link and typo 2015-04-24 01:38:02 +06:00
Sergey M․
02f502f435 [README] Document on how to enable old format selection behavior (#5510, #5511) 2015-04-24 01:34:57 +06:00
Sergey M․
4515cb43ca [xattrpp] Fix typo 2015-04-23 22:11:09 +06:00
Sergey M․
d740333224 [cracked] Modernize 2015-04-23 21:59:18 +06:00
Sergey M․
c610f38ba9 [cracked] Update tests 2015-04-23 21:58:50 +06:00
Sergey M․
6447353f52 [cracked] Add support for youtube embeds 2015-04-23 21:49:54 +06:00
Sergey M․
b46ed49996 [cracked] Fix extraction 2015-04-23 21:44:51 +06:00
Yen Chi Hsuan
cd9fdccde0 [ustream] Try to extract uploader from JSON data (#5128) 2015-04-23 18:33:25 +08:00
Yen Chi Hsuan
2a8137272d [ustream] Add an alternative approach to extract title (fixes #5128) 2015-04-23 18:24:44 +08:00
Yen Chi Hsuan
762155cc90 [ustream] Checking errors 2015-04-23 18:10:18 +08:00
Yen Chi Hsuan
f8610ba1ca [ustream] Fix extraction (closes #3998) 2015-04-23 18:10:18 +08:00
pulpe
c99f4098c4 Merge branch 'master' of github.com:rg3/youtube-dl 2015-04-23 11:43:37 +02:00
pulpe
3eec9fef30 [realvid] Add extractor for realvid.net (closes #5504) 2015-04-23 11:41:21 +02:00
Yen Chi Hsuan
8c8826176d [xattr] Add version detection for python-pyxattr
For more information, see #5498 and changes to convertObj() in
iustin/pyxattr@cc84e466f6
2015-04-23 13:50:44 +08:00
pulpe
14a2d6789f [vimeo] one token overlooked 2015-04-22 23:55:19 +02:00
pulpe
7513f298b0 [vimeo] Fix login token (fixes #5082) 2015-04-22 23:50:11 +02:00
Jaime Marquínez Ferrándiz
c04c3e334c [flickr] Don't use regex for extracting the info from the xml files 2015-04-22 19:58:39 +02:00
Jaime Marquínez Ferrándiz
f8e51f60b3 [flickr] Fix extraction (fixes #5501) 2015-04-22 19:24:14 +02:00
Sergey M․
33b066bda0 [hitbox] Clarify download messages 2015-04-22 21:09:21 +06:00
Sergey M․
14f41bc2fb [hitbox:live] Extract formats before metadata 2015-04-22 21:05:08 +06:00
Sergey M․
008bee0f50 [hitbox] Extract formats before metadata 2015-04-22 21:03:56 +06:00
Sergey M․
29492f3332 [hitbox] Sort formats 2015-04-22 21:01:52 +06:00
Sergey M․
bc94bd510b [hitbox] Extract all formats (Closes #5494) 2015-04-22 21:01:25 +06:00
Sergey M․
9dd8e46a2d [youtube:search] Cancel out _TESTS 2015-04-22 20:28:33 +06:00
Yen Chi Hsuan
8be2bdfabd [YoutubeDL] Remove the redundant assignment to old_filename
Caused by commmit 592e97e855
2015-04-22 15:05:35 +08:00
Jaime Marquínez Ferrándiz
b4c0806963 [youtube:ytsearch] Use the same system as the search webpage (fixes #5483)
The gdata api V2 was deprecated and according to http://youtube-eng.blogspot.com.es/2014/03/committing-to-youtube-data-api-v3_4.html remains available until April 20, 2015.
2015-04-21 19:30:31 +02:00
Sergey M․
cc38fa6cfb [youtube] Remove unused import 2015-04-21 22:55:59 +06:00
Sergey M․
6de5dbafee [youtube:channel] Make extract_videos_from_page static 2015-04-21 22:42:21 +06:00
Sergey M․
60bf45c80d [youtube:channel] Specify first page download message 2015-04-21 22:37:45 +06:00
Sergey M․
eb0f3e7ec0 [youtube:user] Extract in terms of load_more_widget_html 2015-04-21 22:36:41 +06:00
Sergey M․
ed553379df [youtube:ytsearch] Temporary workaround (#5483) 2015-04-21 20:55:05 +06:00
Jaime Marquínez Ferrándiz
5c1e6f69c4 [senate] Simplify
There isn't any problem if the 'formats' field only has one element
2015-04-21 15:04:55 +02:00
Yen Chi Hsuan
757cda0a96 [Cinemassacre] Support Youtube embedded videos (fixes #5131) 2015-04-21 15:21:04 +08:00
Yen Chi Hsuan
e94443de80 [Cinemassacre] Move to a standalone module 2015-04-21 15:10:27 +08:00
Yen Chi Hsuan
0954cd8aa4 [Cinemassacre] Add detection for videos from blip.tv 2015-04-21 13:48:02 +08:00
Yen Chi Hsuan
da55dac047 [CSpan] Removed the md5 sum of CSpan_3 2015-04-21 05:22:23 +08:00
Yen Chi Hsuan
13a11b195f [SenateISVP] Fix tests
Remove md5 sums. They differs from my PC and the travis worker.
2015-04-21 05:13:25 +08:00
Yen Chi Hsuan
92dcba1e1c [CSpan] Fix test cases CSpan_1 and CSpan_2 2015-04-21 03:30:54 +08:00
Yen Chi Hsuan
2fe1b5bd2a [CSpan] Add detection for Senate ISVP. Closes #5302 2015-04-21 03:18:38 +08:00
Yen Chi Hsuan
f91e1a8739 [Senate] Try to capture thumbnails 2015-04-21 02:57:32 +08:00
Yen Chi Hsuan
24e21613b6 [bilibili] Capture the video-not-exist message 2015-04-21 02:32:10 +08:00
Yen Chi Hsuan
c6391cd587 [Senate] Add new extractor (#5302) 2015-04-21 02:29:56 +08:00
Sergey M․
006ce15a0c [bambuser] Add support for authentication (#5478) 2015-04-20 23:00:37 +06:00
Sergey M․
edf4216119 [bambuser] Modernize and extract more metadata 2015-04-20 22:46:01 +06:00
Sergey M․
ae8953409e [bambuser] Capture and output error message (#5478) 2015-04-20 22:35:53 +06:00
Sergey M․
bda44f31a1 [bambuser] Modernize 2015-04-20 22:33:35 +06:00
Sergey M․
6621ca39a3 [ted] Skip hls quality selection format 2015-04-20 22:04:42 +06:00
Sergey M․
14f7abfa71 [ted] Lower preference for direct audio since it's mono 2015-04-20 22:04:17 +06:00
Sergey M․
0f0b5736da [ted] Fix hls audio/video-only formats 2015-04-20 22:01:02 +06:00
Sergey M․
6728187ac0 [YoutubeDL] mp3 is compatible with mp4 2015-04-20 21:58:46 +06:00
Sergey M․
17c8675853 [YoutubeDL] Allow bestvideo+bestaudio/best strategy for ted extractor 2015-04-20 21:58:29 +06:00
Sergey M․
cfbee8a431 [ted] Clarify IE_NAME 2015-04-20 21:42:42 +06:00
Sergey M․
736785ab63 [ted] Clarify audio/video-only formats 2015-04-20 21:42:20 +06:00
Sergey M․
3ded7bac16 [extractor/common] Add ability to specify custom field preference for _sort_formats 2015-04-20 21:13:31 +06:00
Quentin Rameau
b524a001d6 [bandcamp] fix video_id parsing (fixes #4861) 2015-04-20 15:45:57 +02:00
Jaime Marquínez Ferrándiz
7b071e317b README: document bestvideo+bestaudio/best (#5447) 2015-04-19 18:54:05 +02:00
Jaime Marquínez Ferrándiz
a380509259 Move the documentation for the --format option to the manpage
It's too big for beeing embedded in the help message and it's easier to edit in the markdown file.
2015-04-19 18:53:28 +02:00
Sergey M․
c0dea0a782 [YoutubeDL] Respect explicit --merge-format-output for uncompatible formats as well 2015-04-19 22:33:52 +06:00
Sergey M․
70947ea7b1 [parameters.json] Set default format parameter to best 2015-04-19 17:56:06 +02:00
Sergey M․
81cd954a51 [YoutubeDL] Merge incompatible formats into mkv (#5456) 2015-04-19 17:55:42 +02:00
Sergey M․
feccf29c87 [YoutubeDL] Make bestvideo+bestaudio/best default format when merger is available 2015-04-19 17:51:56 +02:00
Jaime Marquínez Ferrándiz
5b5fbc0867 Detect already merged videos
Without the '--keep-video' option the two files would be downloaded again and even using the option, ffmpeg would be run again, which for some videos can take a long time.
We use a temporary file with ffmpeg so that the final file only exists if it success
2015-04-19 17:51:41 +02:00
Yen Chi Hsuan
f158799bbe [Sohu] Fix title extraction 2015-04-19 19:19:44 +08:00
Yen Chi Hsuan
8b0e8990c2 [miomio] Replace the slow test case
MioMio_1 takes about 25~35 seconds on information retrieval
2015-04-19 19:12:23 +08:00
Yen Chi Hsuan
880ee801cf [tests] Allow multi_video to be tested as playlists 2015-04-19 19:08:37 +08:00
Sergey M․
163965d861 [megavideoz] Improve non-existing videos check 2015-04-19 04:14:58 +06:00
Sergey M․
6e218b3f9a [megavideoz] Check non-existing videos 2015-04-19 04:09:01 +06:00
Sergey M․
cc9b9df0b6 [megavideozeu] Rename extractor 2015-04-19 04:08:29 +06:00
Sergey M․
31f224008e [megavideozeu] Simplify (Closes #5454) 2015-04-19 04:07:45 +06:00
Jeff Buchbinder
f32cb5cb14 [megavideoez] Add working test 2015-04-19 04:06:45 +06:00
Jeff Buchbinder
fec2d97ca2 Add megavideoz.eu support. 2015-04-19 04:06:27 +06:00
Sergey M.
f2eeafb061 Merge pull request #5462 from hedii/hedii-patch-1
Update wat.py misspelling 'downloding'
2015-04-18 18:43:03 +05:00
hedii
8f4e8bf280 Update wat.py
line 116, modify 'Downloding' to 'Downloading'.
It looks like nothing, but it is very annoying when youtube-dl command's output is parsed to find progress on a php (or other language) website for example.
2015-04-18 15:40:40 +02:00
Jaime Marquínez Ferrándiz
cc36e2295a [ign] Fix extraction of some videos in articles
Give higher preference to the hero-poster regex because some articles may contain other videos
2015-04-18 13:27:35 +02:00
Jaime Marquínez Ferrándiz
d47aeb2252 FFmpegMergerPP: use the new system for specifying which files can be delete 2015-04-18 11:52:36 +02:00
Jaime Marquínez Ferrándiz
14523ed969 FFmpegEmbedSubtitlePP: remove the subtitle files if '--keep-video' is not given (closes #5435) 2015-04-18 11:44:42 +02:00
Jaime Marquínez Ferrándiz
592e97e855 Postprocessors: use a list for the files that can be deleted
We could only know if we had to delete the original file, but this system allows to specify us more files (like subtitles).
2015-04-18 11:36:42 +02:00
Yen Chi Hsuan
53faa3ca5f [facebook] Extend _VALID_URL take 2 (#5120) 2015-04-18 16:08:24 +08:00
Yen Chi Hsuan
c62566971f [facebook] Extend _VALID_URL 2015-04-18 16:00:33 +08:00
Sergey M․
902be27cf9 Merge branch 'julianrichen-gfycat' 2015-04-18 03:51:38 +06:00
Sergey M․
bf12cbe07c Credit @julianrichen for gfycat (#5440) 2015-04-18 03:51:21 +06:00
Sergey M․
f52e66505a [gfycat] Simplify (Closes #5439, Closes #5394) 2015-04-18 03:50:22 +06:00
Sergey M․
ca75235d3d Merge branch 'gfycat' of https://github.com/julianrichen/youtube-dl into julianrichen-gfycat 2015-04-18 03:49:32 +06:00
Jaime Marquínez Ferrándiz
ecc6bd1341 YoutubeDL.post_process: simplify keep_video handling
Since keep_video started as None we always set it to keep_video_wish unless it was None, so in the end keep_video == keep_video_wish. This should have been changed in f3ff1a3696, but I didn't notice it.
2015-04-17 22:38:14 +02:00
Jaime Marquínez Ferrándiz
ce81b1411d FFmpegExtractAudioPP: Simplify handling of already existing files 2015-04-17 22:37:27 +02:00
Sergey M․
7691a7a3bd [comedycentral] Fix feed uri request (Closes #5449, closes #5455) 2015-04-17 23:41:07 +06:00
Jaime Marquínez Ferrándiz
214e74bf6f [soundcloud] Raise an error instead of calling 'report_error' 2015-04-17 19:24:30 +02:00
Jaime Marquínez Ferrándiz
c5826a491b [mixcloud] Simplify url extraction
On the tracks I tested the server number in the url from the webpage is valid
for the mp3 or the m4a file and any other number is invalid, it's a
waste of time to check them.
2015-04-17 19:02:49 +02:00
Sergey M․
d8e7ef04dc [vimple] Fix extraction (Closes #5448) 2015-04-17 22:56:26 +06:00
Jaime Marquínez Ferrándiz
08f2a92c9c InfoExtractor._search_regex: Suggest updating when the regex is not found (suggested in #5442)
Reuse the same message from ExtractorError
2015-04-17 14:55:24 +02:00
Philipp Hagemeister
3220c50f9a release 2015.04.17 2015-04-17 11:14:25 +02:00
Jaime Marquínez Ferrándiz
024ebb2706 [soundcloud] Handle 'secret_token' for 'w.soundcloud.com/player/?url=*' urls (fixes #5453) 2015-04-17 10:46:25 +02:00
FireDart
954352c4c0 [gfycat] Fixed preferences. 2015-04-16 18:11:30 -04:00
FireDart
4aec95f3c9 [gfycat] Updated tests. 2015-04-16 18:10:53 -04:00
Sergey M․
be531ef1ec [utils] Fix splitunc deprecation warning 2015-04-16 22:12:38 +06:00
Sergey M․
65c1a750f5 [srf] Show display_id when present 2015-04-16 21:48:22 +06:00
Sergey M․
5141249c59 [srf] Extend _VALID_URL 2015-04-16 21:47:42 +06:00
Sergey M․
6225984681 [generic] Update pladform embed test 2015-04-16 21:37:15 +06:00
Sergey M․
5cb91ceaa5 [pladform] Update test 2015-04-16 21:33:01 +06:00
Sergey M․
89c09e2a08 [srf] Update test 2015-04-16 21:30:13 +06:00
Sergey M․
fbbb219409 [srf] Fix direct links ext 2015-04-16 21:28:21 +06:00
Sergey M․
820b064804 [srf] Extract subtitles 2015-04-16 20:48:17 +06:00
Sergey M․
355c524bfa [srf] Extract all formats and prefer direct links over hls and hds 2015-04-16 20:31:02 +06:00
Yen Chi Hsuan
c052ce6cde [Srf] Add new extractor (fixes #981) 2015-04-16 22:00:45 +08:00
Yen Chi Hsuan
c9a779695d [extractor/common] Add the encoding parameter
The QQMusic info extractor need forced encoding for correct working.
2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
a685ae511a [QQMusic] Song extractor: Add lyrics as description
Note: Test fails on python 3 due to encoding issues
2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
5edea45fab [QQMusic] Add album info extractor 2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
8afff9f849 [QQMusic] Add singer info extractor 2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
a2043572aa [QQMusic] Implement the guid algorithm 2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
5d98908b26 [QQMusic] Add new extractor 2015-04-16 17:34:54 +08:00
Yen Chi Hsuan
d6fd958c5f [generic] Extract videos from SMIL manifests (closes #5145 and fixes #5135) 2015-04-16 17:16:11 +08:00
Yen Chi Hsuan
d0eb724e22 [UDNEmbed] Enhance error checking and extend _VALID_URL 2015-04-16 17:04:53 +08:00
FireDart
afe4a8c769 [gfycat] Add new extractor 2015-04-15 22:17:45 -04:00
Yen Chi Hsuan
9fc03aa87c [brightcove] Always return lists from _extract_brightcove_urls
In Python 3, filter() returns an iterable object, which is equivalently
to True even for an empty result set. It causes false positive playlists
in generic extraction logic.
2015-04-16 00:27:39 +08:00
Sergey M․
c798f15b98 [generic] Add test for playwire embed (#5430) 2015-04-15 22:14:29 +06:00
Sergey M․
2dcc114f84 [generic] Add support for playwire embeds (Closes #5430) 2015-04-15 22:10:08 +06:00
Sergey M․
0dfe9bc9d2 [mtv] Capture and output error message (#5420) 2015-04-15 21:02:34 +06:00
Sergey M․
4d1cdb5bfe [spike] Extend _VALID_URL (Closes #5420) 2015-04-15 20:58:48 +06:00
Yen Chi Hsuan
9c5335a027 [teamcoco] Fix "preload" data extraction (fixes #5179) 2015-04-15 19:56:21 +08:00
Yen Chi Hsuan
ae849ca170 [tumblr] Dismiss warnings for optional fields (fixes #5202) 2015-04-15 17:45:28 +08:00
Sergey M․
94c1255782 [brightcove] Handle non well-formed XMLs (#5421) 2015-04-14 17:50:53 +06:00
Sergey M․
476e1095fa [brightcove] Improve brightcove experience regex (Closes #5421) 2015-04-14 17:48:41 +06:00
Yen Chi Hsuan
8da1bb0418 [miomio] Enhance error checking and replace dead test case 2015-04-14 15:27:56 +08:00
Yen Chi Hsuan
01c58f8473 [generic] Fix test generic_51
The website replaced the original video with a new one
2015-04-14 13:10:10 +08:00
Yen Chi Hsuan
edfcf7abe2 [generic] Support another type of Ooyala embedded video 2015-04-14 12:45:43 +08:00
Jaime Marquínez Ferrándiz
37b44fe7c1 [postprocessor/atomicparsley] Don't try to remove the temporary and original files if the format is unsupported (fixes #5419) 2015-04-13 22:50:40 +02:00
Sergey M․
8f02ad4f12 [youtube] Simplify 2015-04-13 20:28:16 +06:00
Yen Chi Hsuan
51f1244600 [vine] flake8 2015-04-13 19:26:15 +08:00
Sergey M․
7bd930368c [youtube] Remove unused variable 2015-04-13 00:08:39 +06:00
Sergey M․
fb69240ca0 [youtube] Extract video titles for channel playlist if possible (Closes #4971) 2015-04-12 23:19:00 +06:00
Sergey M․
830d53bfae [utils] Add video_title for url_result 2015-04-12 23:11:47 +06:00
Sergey M․
c36a959549 [YoutubeDL] Try to download worst audio+video served by a single file first (Closes #5408) 2015-04-12 17:36:29 +06:00
Sergey M․
e91b2d14e3 Credit @snipem for gamersyde (#5352) 2015-04-12 17:17:31 +06:00
Sergey M․
ac58e68bc3 [footyroom] Remove superfluous whitespace 2015-04-12 17:11:11 +06:00
Sergey M․
504c1cedfe [footyroom] Improve 2015-04-12 17:09:52 +06:00
snipem
9a4d8fae82 [FootyTube] Fixed wrong md5 checksum 2015-04-12 17:01:12 +06:00
snipem
7d2ba6394c [FootyRoom] Fixed missing http prefix
For some reason FootyTube is missing the „http:“ prefix on some
Playwire links for some videos
2015-04-12 17:01:03 +06:00
Sergey M․
b04b94da5f [options] Fix file based configurations for python 2 (Closes #5401) 2015-04-12 03:57:56 +06:00
Sergey M․
9933857f67 Merge branch 'fstirlitz-crooksandliars' 2015-04-11 20:27:53 +06:00
Sergey M․
ed5641e249 [crooksandliars] Quotes consistency 2015-04-11 20:27:39 +06:00
Sergey M․
a4257017ef [generic] Add tests for Crooks and Liars embeds 2015-04-11 20:26:42 +06:00
Sergey M․
18153f1b32 [generic] Add support for Crooks and Liars embeds 2015-04-11 20:20:20 +06:00
Sergey M․
7a91d1fc43 [crooksandliars] Improve embed extractor and remove article extractor 2015-04-11 20:03:12 +06:00
Sergey M․
af14ded75e Merge branch 'crooksandliars' of https://github.com/fstirlitz/youtube-dl into fstirlitz-crooksandliars 2015-04-11 19:34:06 +06:00
Sergey M․
65939effb5 [hitbox:live] Fix hls extration (Closes #5315) 2015-04-11 18:52:41 +06:00
Sergey M․
66ee7b3234 [ted] Extract all formats (Closes #5397) 2015-04-10 23:36:28 +06:00
Sergey M․
cd47a628fc [rai] Add test for #5396 2015-04-10 22:44:41 +06:00
Sergey M․
d7c78decb0 [rai] Improve extraction 2015-04-10 22:44:33 +06:00
Sergey M․
8749477ed0 [rai] Fix extraction (Closes #5396) 2015-04-10 22:44:24 +06:00
Naglis Jonaitis
7088f5b5fa [teamcoco] Extract duration 2015-04-10 02:03:38 +03:00
Naglis Jonaitis
5bb6328cb9 [teamcoco] Extract m3u8 URLs 2015-04-09 23:57:51 +03:00
Naglis Jonaitis
ce9f47de99 [teamcoco] Fix extraction 2015-04-09 23:54:53 +03:00
Sergey M․
4c4780c25e [vine] Modernize 2015-04-09 22:41:41 +06:00
Sergey M․
64f1aba8f1 [vine] Extend _VALID_URL 2015-04-09 22:40:18 +06:00
Sergey M․
3359fb661f [vine] Add tests for #5389 2015-04-09 22:37:54 +06:00
Sergey M․
58a9f1b864 [vine] Fix post data regex (Closes #5389) 2015-04-09 22:32:48 +06:00
Sergey M․
6ac41a4ef5 [vine] Zero rate videos is perfectly valid (#5389) 2015-04-09 22:32:22 +06:00
Sergey M․
aa2af7ba74 [dumpert] Add nsfw cookie (Closes #5382) 2015-04-09 19:53:00 +06:00
Jaime Marquínez Ferrándiz
ce73839fe4 [rtve] Detect videos that are no longer available 2015-04-09 14:01:33 +02:00
Philipp Hagemeister
1dc2726f8d release 2015.04.09 2015-04-09 00:21:19 +02:00
Sergey M․
af76e8174d [dailymotion:user] Improve _VALID_URL (Closes #5380) 2015-04-09 02:25:31 +06:00
Sergey M․
402a3efc92 [theplatform] Modernize 2015-04-08 22:29:10 +06:00
Sergey M․
372f08c990 [theplatform] Fix for python 2.6
At least single depth level extraction...
2015-04-08 22:27:25 +06:00
Sergey M․
dd29eb7f81 [postprocessor/common:postprocessor/ffmpeg] Generalize utime 2015-04-08 21:40:31 +06:00
Sergey M.
bca788ab1d Merge pull request #5376 from PeteHemery/ffmpeg-postproc-utime-bug
[ffmpeg] adding exception catching for call to os.utime in run_ffmpeg_multiple_files
2015-04-08 20:27:17 +05:00
Sergey M․
aef8fdba11 [theplatform] Allow <par> without <swtich> at all
Bare `wget` on http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRTl results in an XML without <switch> at all
but with <par> and <video> inside it. Let's handle this possible outcome as well.
2015-04-08 21:03:11 +06:00
Yen Chi Hsuan
0a1603634b [utils] Remove url_infer_protocol 2015-04-08 21:39:34 +08:00
Yen Chi Hsuan
a662163fd5 [theplatform] Rework on <switch> inside <par> 2015-04-08 20:21:34 +08:00
Yen Chi Hsuan
bd7a6478a2 [theplatform] Fix video url extraction (fixes #5340)
In SMIL 2.1, <switch> nodes may be enclosed in <par>. See
http://www.w3.org/TR/SMIL2/smil-timing.html#edef-par
2015-04-08 19:20:34 +08:00
Yen Chi Hsuan
4a20c9f628 [livestream] Extend _VALID_URL (fixes #5375) 2015-04-08 17:42:26 +08:00
Yen Chi Hsuan
418c5cc3fc [udn] Add new extractor 2015-04-08 17:26:51 +08:00
Pete Hemery
cc55d08832 [ffmpeg] adding exception catching for call to os.utime in run_ffmpeg_multiple_files 2015-04-07 22:33:18 +01:00
Yen Chi Hsuan
de5c545648 [youtube] Skip WebVTT in DASH manifest (#5297) 2015-04-08 03:47:27 +08:00
Sergey M․
a35099bd33 [addanime] Add test for #5372 2015-04-07 21:01:35 +06:00
Sergey M․
5f4b5cf044 [addanime] Extend _VALID_URL (Closes #5372) 2015-04-07 21:00:52 +06:00
Sergey M․
beb10f843f [addanime] Add format quality (Closes #5371) 2015-04-07 21:00:22 +06:00
Philipp Hagemeister
29713e4268 [cnn] Match more affilliates 2015-04-07 14:59:13 +02:00
Jaime Marquínez Ferrándiz
8e4b83b96b Remove check for ssl certs
When it uses a capath instead of a cafile, 'get_ca_certs' or 'cert_store_stats' only returns certificates already used in a connection.
(see #5364)
2015-04-06 22:18:08 +02:00
Sergey M․
ae603b500e Merge branch 'newtonelectron-spankbang.com' 2015-04-06 21:24:45 +06:00
Sergey M․
d97aae7572 [spankbang] Improve and simplify 2015-04-06 21:24:17 +06:00
Sergey M․
a55e2f04a0 Merge branch 'spankbang.com' of https://github.com/newtonelectron/youtube-dl into newtonelectron-spankbang.com 2015-04-06 20:46:40 +06:00
felix
6e53c91608 [crooksandliars] resolve protocol-relative URLs 2015-04-06 10:12:43 +02:00
felix
d2272fcf6e crooksandliars.com extractor 2015-04-06 09:54:19 +02:00
newtonelectron
c7ac5dce8c [SpankBang] Remove regexp type prefix from _TEST url. 2015-04-05 14:02:05 -07:00
newtonelectron
5c1d459ae9 [SpankBang] Add test 2015-04-05 13:57:59 -07:00
newtonelectron
2e7daef502 [SpankBang] Use python2.6 compatible string formatting spec 2015-04-05 13:43:21 -07:00
newtonelectron
6410229681 [SpankBang] Add new extractor 2015-04-05 12:50:21 -07:00
Sergey M․
e40bd5f06b [youtube] Simplify url_encoded_fmt_stream_map check 2015-04-06 00:45:57 +06:00
Sergey M․
06b491eb7b [youtube] Add test for #5361 2015-04-06 00:35:55 +06:00
Yen Chi Hsuan
3a9fadd6df [youtube] Enhance url_encoded_fmt_stream_map checking (fix #5361) 2015-04-05 22:29:06 +08:00
Sergey M․
0de9312a7e [ellentv] Replace test 2015-04-05 00:01:55 +06:00
Sergey M․
27fe5e3473 [ellentv] Make video url extraction fatal 2015-04-05 00:00:04 +06:00
Sergey M․
f67dcc09f5 [eagleplatform] Skip georestricted test 2015-04-04 23:36:45 +06:00
Sergey M․
fefc9d121d [dump] Fix title extraction 2015-04-04 23:33:07 +06:00
Sergey M․
a319c33d8b [dreisat] Update test 2015-04-04 23:30:38 +06:00
Sergey M․
218d6bcc05 [dreisat] Capture status errors 2015-04-04 23:28:47 +06:00
Sergey M․
7d25463972 [drtv] Update test 2015-04-04 23:19:28 +06:00
Sergey M․
aff84bec07 [drtv] Check for unavailable videos 2015-04-04 23:17:09 +06:00
Sergey M․
ac651e974e [culturebox] Fix test 2015-04-04 23:06:16 +06:00
Sergey M․
e21a55abcc [extractor/common] Remove f4m section
It's now provided by `f4m_id`
2015-04-04 23:05:25 +06:00
Sergey M․
bc03228ab5 [francetv] Improve formats extraction 2015-04-04 23:02:04 +06:00
Sergey M․
f05d0e73c6 [francetv] Fix duration 2015-04-04 22:52:25 +06:00
Sergey M․
aed2d4b31e [culturebox] Replace test 2015-04-04 22:50:13 +06:00
Sergey M․
184a197441 [culturebox] Check for unavailable videos 2015-04-04 22:43:34 +06:00
Sergey M․
ed676e8c0a [bliptv] Check format URLs
Some formats are now 404
2015-04-04 22:27:25 +06:00
Sergey M․
8e1f937473 [aftonbladet] Modernize 2015-04-04 22:19:34 +06:00
Sergey M․
1a68d39211 [aftonbladet] Fix extraction 2015-04-04 22:15:59 +06:00
Sergey M․
4ba7d5b14c Merge branch 'tuexss-patch-1' 2015-04-04 20:09:36 +06:00
Sergey M․
1a48181a9f [options] Fix load info help string 2015-04-04 20:09:11 +06:00
Sergey M․
6b70a4eb7d [options] Number is a verb here 2015-04-04 20:02:29 +06:00
Sergey M․
f01855813b [options] extractor is lowercase 2015-04-04 20:01:24 +06:00
Sergey M․
4a3cdf81af [options] Restore some strings 2015-04-04 20:00:23 +06:00
Sergey M․
f777397aca Merge branch 'patch-1' of https://github.com/tuexss/youtube-dl into tuexss-patch-1 2015-04-04 19:50:47 +06:00
Sergey M․
8fb2e5a4f5 [radiojavan] Sort formats 2015-04-04 19:25:08 +06:00
Sergey M․
4e8cc1e973 [radiojavan] Fix height 2015-04-04 19:24:37 +06:00
Sergey M․
ff02a228e3 [test_execution] Fix test under python 2 @ windows 2015-04-04 19:21:50 +06:00
Sergey M․
424266abb1 Credit @Roman2K for pornovoisines (#5264) 2015-04-04 19:16:18 +06:00
Sergey M․
3fde134791 Merge branch 'Roman2K-pornovoisines' 2015-04-04 19:14:01 +06:00
Sergey M․
7c39a65543 [pornovoisines] Simplify 2015-04-04 19:13:37 +06:00
Sergey M․
8cf70de428 [test_utils] Add test for unified_strdate 2015-04-04 19:11:01 +06:00
Sergey M․
15ac8413c7 [utils] Avoid treating *-%Y date template as UTC offset 2015-04-04 19:08:48 +06:00
Sergey M․
79c21abba7 [utils] Add one more template to unified_strdate 2015-04-04 18:45:46 +06:00
Sergey M․
d5c418f29f Merge branch 'pornovoisines' of https://github.com/Roman2K/youtube-dl into Roman2K-pornovoisines 2015-04-04 18:08:20 +06:00
Sergey M․
536b94e56f Merge branch 'snipem-gamersyde' 2015-04-04 17:54:02 +06:00
Sergey M․
5c29dbd0c7 [gamersyde] Simplify 2015-04-04 17:53:22 +06:00
Sergey M․
ba9e68f402 [utils] Drop trailing comma before closing brace 2015-04-04 17:48:55 +06:00
Jaime Marquínez Ferrándiz
e9f65f8749 [rtve] Extract a better quality video 2015-04-04 13:11:55 +02:00
Sergey M․
ae0dd4b298 Merge branch 'gamersyde' of https://github.com/snipem/youtube-dl into snipem-gamersyde 2015-04-04 16:59:39 +06:00
Sergey M․
f1ce35af1a Merge branch 'mtp1376-radiojavan' 2015-04-04 16:47:24 +06:00
Sergey M․
6e617ed0b6 Credit @mtp1376 for varzesh3 and radiojavan 2015-04-04 16:47:09 +06:00
Sergey M․
7cf97daf77 [radiojavan] Simplify and extract upload date 2015-04-04 16:45:41 +06:00
snipem
3d24d997ae Fixed intendation of test cases
Leaded to error on Linux machine
2015-04-04 12:42:14 +02:00
snipem
115c281672 [Gamersyde] Improved robustness, added duration and tests
Fix for Json syntax is now less error prone for Json syntax inside of
values. Extractor is now also using native Json handling. Added tests
for several videos that were producing errors in the first place.
2015-04-04 12:31:48 +02:00
Sergey M․
cce23e43a9 Merge branch 'radiojavan' of https://github.com/mtp1376/youtube-dl into mtp1376-radiojavan 2015-04-04 16:10:17 +06:00
Sergey M․
ff556f5c09 Do not encode outtmpl twice (Closes #5288) 2015-04-04 00:30:37 +06:00
Sergey M․
16fa01291b [prosiebensat1] Fix test 2015-04-03 23:44:13 +06:00
Sergey M․
01534bf54f [prosiebensat1] Fix bitrate (Closes #5350 closes #5351) 2015-04-03 23:42:53 +06:00
Jaime Marquínez Ferrándiz
cd341b6e06 [mixcloud] Fix extraction of like count (reported in #5231) 2015-04-03 19:37:35 +02:00
Mohammad Teimori Pabandi
185a7e25e7 [RadioJavan] Add new extractor 2015-04-03 20:55:39 +04:30
snipem
e81a474603 [Gamersyde] Add new extractor 2015-04-03 15:34:49 +02:00
Jaime Marquínez Ferrándiz
ff2be6e180 [bloomberg] Adapt to website changes (fixes #5347) 2015-04-03 15:01:17 +02:00
Jaime Marquínez Ferrándiz
3da4b31359 [postprocessor/ffmpeg] Fix crash when ffprobe/avprobe are not installed (closes #5349)
'self.probe_basename' was None, so 'probe_executable' raised a KeyError exception
2015-04-03 14:09:50 +02:00
Jaime Marquínez Ferrándiz
4bbeb19fc7 [miomio] pep8: remove whitespaces in empty line 2015-04-03 14:09:07 +02:00
Philipp Hagemeister
a9cbab1735 release 2015.04.03 2015-04-03 10:22:25 +02:00
Sergey M․
6b7556a554 Credit @tiktok7 for miomio.tv (#5265) 2015-04-03 01:47:18 +06:00
Sergey M․
a3c7019e06 [YoutubeDL] Check for get_ca_certs availability
`get_ca_certs` is not available in python <3.4
2015-04-02 22:50:10 +06:00
Sergey M․
416b9c29f7 Merge branch 'tiktok7-MiomioTv' 2015-04-02 22:34:53 +06:00
Sergey M․
2ec8e04cac [miomio] Fix alphabetic order 2015-04-02 22:34:08 +06:00
Sergey M․
e03bfb30ce [miomio] Rename extractor 2015-04-02 22:33:30 +06:00
Sergey M․
f5b669113f [miomio] Simplify and fix python 2.6 issue 2015-04-02 22:32:16 +06:00
Sergey M․
d08225edf4 Merge branch 'MiomioTv' of https://github.com/tiktok7/youtube-dl into tiktok7-MiomioTv 2015-04-02 21:12:47 +06:00
Sergey M․
8075d4f99d [playfm] Adapt to v2api (Closes #5344) 2015-04-02 20:26:05 +06:00
Jaime Marquínez Ferrándiz
1a944d8a2a Print a warning if no ssl certificates are loaded 2015-04-02 14:09:55 +02:00
Sergey M․
7cf02b6619 Merge branch 'mtp1376-varzesh3' 2015-04-01 22:03:35 +06:00
Sergey M․
55cde6ef3c [varzesh3] Simplify 2015-04-01 22:02:55 +06:00
Sergey M․
69c3af567d Merge branch 'varzesh3' of https://github.com/mtp1376/youtube-dl into mtp1376-varzesh3 2015-04-01 20:25:46 +06:00
Sergey M․
60e1fe0079 Merge branch 'master' of github.com:rg3/youtube-dl 2015-04-01 20:25:11 +06:00
Sergey M.
4669393070 Merge pull request #5311 from yan12125/fix_douyu
[douyutv] Fix extractor and improve error handling
2015-04-01 20:22:11 +06:00
Sergey M․
ce3bfe5d57 Merge branch 'fix_douyu' of https://github.com/yan12125/youtube-dl 2015-04-01 19:54:00 +06:00
Sergey M․
2a0c2ca2b8 [dailymotion] Fix ff cookie and use it for embed page (Closes #5330) 2015-03-31 20:55:21 +06:00
Sergey M․
c89fbfb385 [nbc] Remove redundant note
This is already supposed by `only_matching`
2015-03-31 20:14:37 +06:00
Sergey M․
facecb84a1 [generic] Add working NBC Sports vplayer test 2015-03-31 20:11:14 +06:00
Sergey M.
ed06e9949b Merge pull request #5328 from yan12125/fix_5226
[Yahoo/NBCSports] Fix 5226 and add support for NBC sports
2015-03-31 20:00:47 +06:00
Yen Chi Hsuan
e15307a612 [NBCSports/Yahoo] Comment out some MD5 checksums
They seems to change constantly
2015-03-31 13:13:29 +08:00
Yen Chi Hsuan
5cbb2699ee [NBCSports] Add a test case for extended _VALID_URL 2015-03-31 03:38:45 +08:00
Yen Chi Hsuan
a2edf2e7ff [NBC/ThePlatform/Generic] Add a generic detector for NBCSportsVPlayer and enhance error detection in ThePlatformIE 2015-03-31 03:36:09 +08:00
Yen Chi Hsuan
1d31e7a2fc [NBCSports] Move imports alphabetically 2015-03-31 02:51:11 +08:00
Yen Chi Hsuan
a2a4d5fa31 [Yahoo/NBCSports] Generalize NBC sports info extractor 2015-03-31 02:47:18 +08:00
Yen Chi Hsuan
a28ccbabc6 [Yahoo/NBCSports] Fix #5226 2015-03-31 02:21:27 +08:00
Naglis Jonaitis
edd7344820 [phoenix] Extend _VALID_URL (#5322) 2015-03-30 18:16:51 +03:00
Sergey M․
c808ef81bb [soundcloud:set:user] Support mobile URLs (Closes #5323) 2015-03-30 21:03:38 +06:00
Sergey M․
fd203fe357 Credit @jorams or dumpert.nl (#5319) 2015-03-30 20:12:55 +06:00
Sergey M․
5bb7ab9928 Merge branch 'jorams-dumpert' 2015-03-30 20:12:09 +06:00
Sergey M․
87270c8416 [dumpert] Simplify and fix python 3.2 2015-03-30 20:11:51 +06:00
Sergey M․
ebc2f7a2db Merge branch 'dumpert' of https://github.com/jorams/youtube-dl into jorams-dumpert 2015-03-30 19:47:11 +06:00
Sergey M․
7700207ec7 [pornhub] Fix comment count extraction (Closes #5320) 2015-03-30 19:41:04 +06:00
Joram Schrijver
4d5d14f5cf [Dumpert] Add new extractor
Add support for the Dutch video site Dumpert. http://www.dumpert.nl/
2015-03-29 23:41:06 +02:00
Sergey M.
72b249bf1f Merge pull request #5313 from yan12125/fix_xuite_python32
[Xuite] Fix extraction on python 3.2
2015-03-30 01:28:30 +06:00
Yen Chi Hsuan
9b4774b21b [Xuite] Fix extraction on python 3.2
base64.b64decode() accept only binary types in Python 3.2
2015-03-29 20:51:33 +08:00
Yen Chi Hsuan
2ddf083588 [douyutv] Simplify usage of isinstance 2015-03-29 18:17:48 +08:00
Yen Chi Hsuan
8343a03357 [douyutv] Fix extractor and improve error handling 2015-03-29 14:26:28 +08:00
Naglis Jonaitis
ad320e9b83 [generic] Add support for 5min embeds (#5310) 2015-03-29 04:57:37 +03:00
Philipp Hagemeister
ecb750a446 [cnn] Match more URLs 2015-03-28 23:39:41 +01:00
Philipp Hagemeister
5f88e02818 [ultimedia] PEP8 2015-03-28 23:35:55 +01:00
Sergey M․
616af2f4b9 Unduplicate @ossi96 2015-03-29 00:03:59 +06:00
Sergey M․
5a3b315b5f [dhm] Improve _VALID_URL and add test 2015-03-28 23:55:15 +06:00
Sergey M․
b7a2268e7b Credit @ossi96 for dhm (#5305) 2015-03-28 23:43:15 +06:00
Sergey M․
20d729228c Merge branch 'ossi96-dhm' 2015-03-28 22:30:27 +06:00
Sergey M․
af8c93086c [dhm] Simplify 2015-03-28 22:30:13 +06:00
Sergey M․
79fd11ab8e Merge branch 'dhm' of https://github.com/ossi96/youtube-dl into ossi96-dhm 2015-03-28 22:09:05 +06:00
Jaime Marquínez Ferrándiz
cb88671e37 [nbc] Recognize https urls (fixes #5300) 2015-03-28 14:18:11 +01:00
Oskar Jauch
ff79552f13 [DHM] Add extractor description 2015-03-28 10:42:35 +01:00
Oskar Jauch
643fe72717 [DHM] Add new extractor 2015-03-28 10:38:52 +01:00
Philipp Hagemeister
4747e2183a release 2015.03.28 2015-03-28 08:12:05 +01:00
Philipp Hagemeister
c59e701e35 Default to continuedl=True
We already do this in the CLI interface, so it should be just fine.
2015-03-28 08:11:39 +01:00
Jaime Marquínez Ferrándiz
8e678af4ba Makefile: fix 'find' command
It worked with the GNU version, but not with the BSD version.
2015-03-27 14:21:53 +01:00
Jaime Marquínez Ferrándiz
70a1165b32 Don't use bare 'except:'
They catch any exception, including KeyboardInterrupt, we don't want to catch it.
2015-03-27 13:02:20 +01:00
Naglis Jonaitis
af14000215 [eroprofile] Add login support (#5269) 2015-03-26 23:24:28 +02:00
Sergey M․
998e6cdba0 [vimeo] Capture and output error message (#5294) 2015-03-27 03:05:08 +06:00
Mohammad Teimori Pabandi
2315fb5e5f unicde :( 2015-03-26 23:53:57 +04:30
Jaime Marquínez Ferrándiz
157e9e5aa5 [youtube:watchlater] Remove unused properties and fix tests 2015-03-26 20:03:31 +01:00
Jaime Marquínez Ferrándiz
c496ec0848 [vessel] Fix pep8 issue 2015-03-26 19:51:40 +01:00
Sergey M․
15b67a268a Merge branch 'zx8-master' 2015-03-26 23:57:56 +06:00
Sergey M․
31c4809827 [safari] Improve and simplify 2015-03-26 23:57:46 +06:00
Sergey M․
ac0df2350a Merge branch 'master' of https://github.com/zx8/youtube-dl into zx8-master 2015-03-26 23:57:13 +06:00
Naglis Jonaitis
223b27f46c [vessel] Add new extractor (Closes #5275) 2015-03-26 19:48:22 +02:00
Naglis Jonaitis
425142be60 [slideshare] Fix extraction (#5279) 2015-03-26 17:47:25 +02:00
Sergey M․
7e17ec8c71 [youtube] Clarify some IE_NAMEs 2015-03-26 21:42:28 +06:00
Sergey M․
448830ce7b [youtube:watchlater] Extract watchlater as playlist (Closes #5280) 2015-03-26 21:41:09 +06:00
Mohammad Teimori Pabandi
8896b614a9 removing unicode literal because it is imported :)) 2015-03-26 20:06:50 +04:30
Mohammad Teimori Pabandi
a7fce980ad removed one of tests that made problem with testing server 2015-03-26 19:47:34 +04:30
Naglis Jonaitis
91757b0f37 [utils] Escape all HTML entities written in hexadecimal form 2015-03-26 17:15:27 +02:00
Naglis Jonaitis
fbfcc2972b [teamcoco] Fix extraction 2015-03-26 16:13:53 +02:00
Mohammad Teimori Pabandi
db40364b87 [Varzesh3] Add new extractor 2015-03-26 18:17:21 +04:30
Sergey M․
094ce39c45 Credit @amishb for 22tracks (#5276) 2015-03-25 22:27:20 +06:00
Sergey M․
ae67d082fe [22tracks] Improve and simplify 2015-03-25 22:26:02 +06:00
Amish Bhadeshia
8f76df7f37 Updated init to add 22tracks 2015-03-25 21:11:31 +06:00
Amish Bhadeshia
5c19d18cbf [22Tracks] Add new extractor
Conflicts:
	youtube_dl/extractor/__init__.py
2015-03-25 21:10:54 +06:00
Sergey M․
838b93405b [redtube] Fix test 2015-03-25 20:09:01 +06:00
Sergey M․
2676caf344 [redtube] Capture and output removed video message (#5281) 2015-03-25 20:08:35 +06:00
testbonn
17941321ab Clean up of --help output
For consistency and readability
2015-03-25 11:02:55 +01:00
Philipp Hagemeister
48c971e073 release 2015.03.24 2015-03-24 16:39:53 +01:00
Philipp Hagemeister
f5e2efbbf0 [options] Handle special characters in argv (Fixes #5157) 2015-03-24 16:39:46 +01:00
tiktok
5d1f0e607b [MiomioTv] updated based on feedback to merge request:
1) added comment to explain extra xml link download
    2) changed {} entries to {0}, {1} etc
    3) removed redundant language header (the others are required)
    4) checked out the old version of the supported sites md (the change was
    not required)
2015-03-23 23:16:50 +01:00
Sergey M․
b0872c19ea [npo] Skip broken URL links (Closes #5266) 2015-03-23 22:15:01 +06:00
Sergey M․
9f790b9901 [mlb] Improve _VALID_URL (Closes #5260) 2015-03-23 21:23:57 +06:00
tiktok
c41a2ec4af [MiomioTv] Add new extractor 2015-03-23 01:42:17 +01:00
Roman Le Négrate
575dad3c98 [pornovoisines] Add extractor 2015-03-22 20:27:45 +01:00
zx8
32d687f55e [safari] Add safaribooksonline extractor 2015-03-22 18:04:50 +00:00
Jaime Marquínez Ferrándiz
93f787070f [twitch] Only match digits for the video id
Urls can also contain contain a query (for example a timestamp '?t=foo')
2015-03-22 15:39:35 +01:00
Jaime Marquínez Ferrándiz
f9544f6e8f [test/aes] Test aes_decrypt_text with 256 bit 2015-03-22 12:09:58 +01:00
Jaime Marquínez Ferrándiz
336d19044c [lybsyn] pep8: add space around operator 2015-03-22 11:03:52 +01:00
Sergey M․
7866c9e173 Merge branch 'fstirlitz-the-daily-show-podcast' 2015-03-22 08:24:26 +06:00
Sergey M․
1a4123de04 [comedycentral] Remove unused import 2015-03-22 08:23:38 +06:00
Sergey M․
cf2e2eb1c0 [comedycentral] Drop thedailyshow podcast extractor
Generic extractor is just fine for Libsyn embeds
2015-03-22 08:23:20 +06:00
Sergey M․
2051acdeb2 [extractor/generic] Add test for Libsyn embed 2015-03-22 08:20:27 +06:00
Sergey M․
cefdf970cc [extractor/generic] Support Libsyn embeds 2015-03-22 08:18:13 +06:00
Sergey M․
a1d0aa7b88 [libsyn] Fix extractor alphabetic order 2015-03-22 08:11:47 +06:00
Sergey M․
49aeedb8cb [libsyn] Improve and simplify 2015-03-22 08:11:10 +06:00
Sergey M․
ef249a2cd7 Merge branch 'the-daily-show-podcast' of https://github.com/fstirlitz/youtube-dl into fstirlitz-the-daily-show-podcast 2015-03-22 07:44:28 +06:00
Sergey M․
a09141548a [nrk:playlist] Relax video id regex and improve _VALID_URL 2015-03-21 20:42:48 +06:00
Jaime Marquínez Ferrándiz
5379a2d40d [test/utils] Test xpath_text 2015-03-21 14:12:43 +01:00
Jaime Marquínez Ferrándiz
c9450c7ab1 [nrk:playlist] Restrict _VALID_URL
It would also match /videos/PS... urls
2015-03-21 14:00:37 +01:00
Sergey M․
faa1b5c292 [nrk:playlist] Add extractor (Closes #5245) 2015-03-21 18:22:08 +06:00
Sergey M․
393d9fc6d2 [nrk] Extract duration 2015-03-21 18:21:19 +06:00
Sergey M․
4e6a228689 [nrk] Adapt to new URL format 2015-03-21 18:20:49 +06:00
Jaime Marquínez Ferrándiz
179d6678b1 Remove the 'stitle' field
A warning has been printed for more than 2 years (since 97cd3afc75)
2015-03-21 12:34:44 +01:00
Jaime Marquínez Ferrándiz
85698c5086 [crunchyroll] Remove unused class 2015-03-21 12:18:33 +01:00
Jaime Marquínez Ferrándiz
a7d9ded45d [test] Add tests for aes 2015-03-21 12:07:23 +01:00
Jaime Marquínez Ferrándiz
531980d89c [test/YoutubeDL] test match_filter 2015-03-20 17:05:28 +01:00
Sergey M․
1887ecd4d6 [twitch] Fix login 2015-03-20 21:45:09 +06:00
Sergey M․
cd32c2caba Merge branch 'ndac-todoroki-niconico_nm' 2015-03-20 20:53:27 +06:00
Sergey M․
1c9a1457fc [niconico] Add nm video test 2015-03-20 20:53:14 +06:00
Sergey M․
038b0eb1da Merge branch 'niconico_nm' of https://github.com/ndac-todoroki/youtube-dl into ndac-todoroki-niconico_nm 2015-03-20 20:52:56 +06:00
Jaime Marquínez Ferrándiz
f20bf146e2 [test/YoutubeDL] split in two classes
The name was misleading
2015-03-20 15:14:25 +01:00
Jaime Marquínez Ferrándiz
01218f919b [test/http] Add test for proxy support 2015-03-20 14:59:38 +01:00
Naglis Jonaitis
2684871bc1 [vine] Fix formats extraction (Closes #5239) 2015-03-20 01:50:36 +02:00
Naglis Jonaitis
ccf3960eec [nytimes] Improve _VALID_URL (Fixes #5238) 2015-03-19 20:55:05 +02:00
Naglis Jonaitis
eecc0685c9 [videomega] Fix extraction and update test (Fixes #5235) 2015-03-19 19:38:03 +02:00
Sergey M․
2ed849eccf Merge branch 'master' of github.com:rg3/youtube-dl 2015-03-19 21:27:38 +06:00
Sergey M․
3378d67a18 [generic] Add support for nytimes embeds (Closes #5234) 2015-03-19 21:26:57 +06:00
Sergey M․
f3c0c667a6 [nytimes] Modernize 2015-03-19 21:23:52 +06:00
Sergey M․
0ae8bbac2d [nytimes] Support embed URL 2015-03-19 21:17:04 +06:00
Philipp Hagemeister
cbc3cfcab4 release 2015.03.18 2015-03-18 22:02:39 +01:00
Sergey M․
b30ef07c6c [ultimedia] Handle youtube embeds 2015-03-19 01:06:39 +06:00
Sergey M․
73900846b1 [ultimedia] Capture and output unavailable video message 2015-03-19 00:53:26 +06:00
Sergey M․
d1dc7e3991 [ultimedia] Fix alphabetic order 2015-03-18 23:11:48 +06:00
Sergey M․
3073a6d5e9 [ultimedia] Add extractor
Sponsored by thankyoumotion.com
2015-03-18 23:08:18 +06:00
Roman Le Négrate
aae53774f2 [mixcloud] Try preview server first, then further numbers 2015-03-18 17:08:22 +01:00
Jaime Marquínez Ferrándiz
7a757b7194 [mixcloud] Fix extraction of some metadata
The second test had some wrong info.
I couldn't find the timestamp, so I have removed it.
2015-03-18 17:08:19 +01:00
Roman Le Négrate
fa8ce26904 [mixcloud] Fix extraction like-count 2015-03-18 16:30:29 +01:00
Sergey M․
2c2c06e359 [krasview] Fix extraction (Closes #5228) 2015-03-18 20:28:00 +06:00
Todoroki
ee580538fa fix nm video DL issue when logged in 2015-03-18 22:24:17 +09:00
Todoroki
c3c5c31517 fix nm video DL issue when logged in 2015-03-18 22:19:55 +09:00
Sergey M․
ed9a25dd61 [generic] Generalize redirect regex 2015-03-18 00:05:40 +06:00
felix
9ef4f12b53 testcases for libsyn and The Daily Show Podcast extractors 2015-03-17 18:54:36 +01:00
Sergey M․
84f8101606 [generic] Follow redirects specified by Refresh HTTP header 2015-03-17 23:51:40 +06:00
Sergey M․
b1337948eb [grooveshark] Fix extraction 2015-03-17 23:13:43 +06:00
Sergey M․
98f02fdde2 Credit @jbuchbinder for primesharetv (#5123) 2015-03-17 22:33:05 +06:00
Sergey M․
048fdc2292 Merge branch 'bonfy-douyutv' 2015-03-17 22:27:46 +06:00
Sergey M․
2ca1c5aa9f [douyutv] Improve and extract all formats 2015-03-17 22:27:33 +06:00
Sergey M․
674fb0fcc5 Merge branch 'douyutv' of https://github.com/bonfy/youtube-dl into bonfy-douyutv 2015-03-17 21:41:25 +06:00
Sergey M․
00bfe40e4d Merge branch 'yan12125-sohu_fix' 2015-03-17 21:39:45 +06:00
Sergey M․
cd459b1d49 [sohu] Fix test's note info 2015-03-17 21:39:31 +06:00
Sergey M․
92a4793b3c [utils] Place sanitize url function near other sanitizing functions 2015-03-17 21:34:22 +06:00
Sergey M․
dc03a42537 Merge branch 'sohu_fix' of https://github.com/yan12125/youtube-dl into yan12125-sohu_fix 2015-03-17 21:18:36 +06:00
Sergey M․
219da6bb68 [megavideoeu] Remove extractor 2015-03-17 21:13:42 +06:00
Sergey M․
0499cd866e [primesharetv] Clean up 2015-03-17 21:06:38 +06:00
Jeff Buchbinder
13047f4135 [Primesharetv] Handle file not existing properly. 2015-03-17 20:33:32 +06:00
Jeff Buchbinder
af69cab21d [Primesharetv] Add public domain example video 2015-03-17 20:33:24 +06:00
Jeff Buchbinder
d41a3fa1b4 [Primesharetv] Add primeshare.tv extractor, still need test data 2015-03-17 20:33:16 +06:00
Jeff Buchbinder
733be371af Add megavideoz.eu support. 2015-03-17 20:33:03 +06:00
Sergey M․
576904bce6 [letv] Clarify download message 2015-03-17 20:01:31 +06:00
Sergey M.
cf47794f09 Merge pull request #5116 from yan12125/letv_fix
[Letv] Fix test_Letv and test_Letv_1 failures in python 3
2015-03-17 19:58:34 +06:00
Sergey M․
c06a9f8730 [arte+7] Check formats (Closes #5224) 2015-03-17 19:42:50 +06:00
felix
2e90dff2c2 The Daily Show Podcast support 2015-03-16 20:05:02 +01:00
Jaime Marquínez Ferrándiz
90183a46d8 Credit @eferro for the rtve.es:infantil extractor (#5214) 2015-03-15 22:49:03 +01:00
Jaime Marquínez Ferrándiz
b68eedba23 [rtve.es:infantil] Minor fixes (closes #5214) 2015-03-15 22:18:41 +01:00
Eduardo Ferro
d5b559393b [rtve] Add new extractor for rtve infantil 2015-03-15 22:14:36 +01:00
Yen Chi Hsuan
2cb434e53e [Sohu] Fix title extraction 2015-03-15 01:05:01 +08:00
Yen Chi Hsuan
cd65491c30 [Sohu] Add a multiplart video test case 2015-03-15 00:59:49 +08:00
bonfy
a172d96292 [douyutv] Add new extractor 2015-03-07 14:05:56 +08:00
Yen Chi Hsuan
55969016e9 [utils] Add a function to sanitize consecutive slashes in URLs 2015-03-06 12:43:49 +08:00
Yen Chi Hsuan
5c7495a194 [sohu] Correct wrong imports 2015-03-06 02:48:27 +08:00
Yen Chi Hsuan
5ee6fc974e [sohu] Fix info extractor and add tests 2015-03-06 02:43:39 +08:00
Yen Chi Hsuan
63fc800057 [Letv] Fix test_Letv and test_Letv_1 failures in python 3 2015-03-03 23:20:55 +08:00
139 changed files with 4986 additions and 1464 deletions

View File

@@ -115,3 +115,12 @@ Leslie P. Polzer
Duncan Keall
Alexander Mamay
Devin J. Pohly
Eduardo Ferro Aldama
Jeff Buchbinder
Amish Bhadeshia
Joram Schrijver
Will W.
Mohammad Teimori Pabandi
Roman Le Négrate
Matthias Küch
Julian Richen

View File

@@ -2,7 +2,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas
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 *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
find -name "*.pyc" -delete
find . -name "*.pyc" -delete
PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin

234
README.md
View File

@@ -5,6 +5,7 @@ youtube-dl - download videos from youtube.com or other video platforms
- [OPTIONS](#options)
- [CONFIGURATION](#configuration)
- [OUTPUT TEMPLATE](#output-template)
- [FORMAT SELECTION](#format-selection)
- [VIDEO SELECTION](#video-selection)
- [FAQ](#faq)
- [DEVELOPER INSTRUCTIONS](#developer-instructions)
@@ -45,21 +46,21 @@ which means you can modify it, redistribute it or use it however you like.
youtube-dl [OPTIONS] URL [URL...]
# OPTIONS
-h, --help print this help text and exit
--version print program version and exit
-U, --update update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-i, --ignore-errors continue on download errors, for example to skip unavailable videos in a playlist
-h, --help Print this help text and exit
--version Print program version and exit
-U, --update Update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
-i, --ignore-errors Continue on download errors, for example to skip unavailable videos in a playlist
--abort-on-error Abort downloading of further videos (in the playlist or the command line) if an error occurs
--dump-user-agent display the current browser identification
--dump-user-agent Display the current browser identification
--list-extractors List all supported extractors and the URLs they would handle
--extractor-descriptions Output descriptions of all supported extractors
--default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
--default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
--ignore-config Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
--flat-playlist Do not extract the videos of a playlist, only list them.
--no-color Do not emit color codes in output.
--no-color Do not emit color codes in output
## Network Options:
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
@@ -71,70 +72,70 @@ which means you can modify it, redistribute it or use it however you like.
not present) is used for the actual downloading. (experimental)
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--playlist-items ITEM_SPEC playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
--playlist-start NUMBER Playlist video to start at (default is 1)
--playlist-end NUMBER Playlist video to end at (default is last)
--playlist-items ITEM_SPEC Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
--match-title REGEX download only matching titles (regex or caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or caseless sub-string)
--match-title REGEX Download only matching titles (regex or caseless sub-string)
--reject-title REGEX Skip download for matching titles (regex or caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m)
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded on or before this date (i.e. inclusive)
--dateafter DATE download only videos uploaded on or after this date (i.e. inclusive)
--date DATE Download only videos uploaded in this date
--datebefore DATE Download only videos uploaded on or before this date (i.e. inclusive)
--dateafter DATE Download only videos uploaded on or after this date (i.e. inclusive)
--min-views COUNT Do not download any videos with less than COUNT views
--max-views COUNT Do not download any videos with more than COUNT views
--match-filter FILTER (Experimental) Generic video filter. Specify any key (see help for -o for a list of available keys) to match if the key is present,
--match-filter FILTER Generic video filter (experimental). 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, 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 service), but who also have a description, use --match-filter "like_count > 100 &
dislike_count <? 50 & description" .
--no-playlist If the URL refers to a video and a playlist, download only the video.
--yes-playlist If the URL refers to a video and a playlist, download the playlist.
--age-limit YEARS download only videos suitable for the given age
--no-playlist Download only the video, if the URL refers to a video and a playlist.
--yes-playlist Download the playlist, if the URL refers to a video and a playlist.
--age-limit YEARS Download only videos suitable for the given age
--download-archive FILE Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
--include-ads Download advertisements as well (experimental)
## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second (e.g. 50K or 4.2M)
-R, --retries RETRIES number of retries (default is 10), or "infinite".
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K) (default is 1024)
--no-resize-buffer do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
-r, --rate-limit LIMIT Maximum download rate in bytes per second (e.g. 50K or 4.2M)
-R, --retries RETRIES Number of retries (default is 10), or "infinite".
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K) (default is 1024)
--no-resize-buffer Do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
--playlist-reverse Download playlist videos in reverse order
--xattr-set-filesize (experimental) set file xattribute ytdl.filesize with expected filesize
--hls-prefer-native (experimental) Use the native HLS downloader instead of ffmpeg.
--xattr-set-filesize Set file xattribute ytdl.filesize with expected filesize (experimental)
--hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental)
--external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,wget
--external-downloader-args ARGS Give these arguments to the external downloader.
--external-downloader-args ARGS Give these arguments to the external downloader
## Filesystem Options:
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
--id use only video ID in file name
-o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
-a, --batch-file FILE File containing URLs to download ('-' for stdin)
--id Use only video ID in file name
-o, --output TEMPLATE Output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube's itags: "137"),
the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like YouTube's itags: "137"),
%(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
%(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
%(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
%(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
--autonumber-size NUMBER Specify the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
--restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
-A, --auto-number [deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000
-t, --title [deprecated] use title in file name (default)
-l, --literal [deprecated] alias of --title
-w, --no-overwrites do not overwrite files
-c, --continue force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
--no-continue do not resume partially downloaded files (restart from beginning)
--no-part do not use .part files - write directly into output file
--no-mtime do not use the Last-modified header to set the file modification time
--write-description write video description to a .description file
--write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation file
--load-info FILE json file containing the video information (created with the "--write-json" option)
--cookies FILE file to read cookies from and dump cookie jar in
-A, --auto-number [deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] Number downloaded files starting from 00000
-t, --title [deprecated] Use title in file name (default)
-l, --literal [deprecated] Alias of --title
-w, --no-overwrites Do not overwrite files
-c, --continue Force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
--no-continue Do not resume partially downloaded files (restart from beginning)
--no-part Do not use .part files - write directly into output file
--no-mtime Do not use the Last-modified header to set the file modification time
--write-description Write video description to a .description file
--write-info-json Write video metadata to a .info.json file
--write-annotations Write video annotations to a .annotation file
--load-info FILE JSON file containing the video information (created with the "--write-info-json" option)
--cookies FILE File to read cookies from and dump cookie jar in
--cache-dir DIR Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
change.
@@ -142,96 +143,86 @@ which means you can modify it, redistribute it or use it however you like.
--rm-cache-dir Delete all filesystem cache files
## Thumbnail images:
--write-thumbnail write thumbnail image to disk
--write-all-thumbnails write all thumbnail image formats to disk
--write-thumbnail Write thumbnail image to disk
--write-all-thumbnails Write all thumbnail image formats to disk
--list-thumbnails Simulate and list all available thumbnail formats
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
-q, --quiet Activate quiet mode
--no-warnings Ignore warnings
-s, --simulate do not download the video and do not write anything to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title
--get-id simulate, quiet but print id
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
--get-duration simulate, quiet but print video length
--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.
-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 playlist
-s, --simulate Do not download the video and do not write anything to disk
--skip-download Do not download the video
-g, --get-url Simulate, quiet but print URL
-e, --get-title Simulate, quiet but print title
--get-id Simulate, quiet but print id
--get-thumbnail Simulate, quiet but print thumbnail URL
--get-description Simulate, quiet but print video description
--get-duration Simulate, quiet but print video length
--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.
-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 playlist
information in a single line.
--print-json Be quiet and print the video information as JSON (video is still being downloaded).
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
--dump-pages print downloaded pages to debug problems (very verbose)
--newline Output progress bar as new lines
--no-progress Do not print progress bar
--console-title Display progress in console titlebar
-v, --verbose Print various debugging information
--dump-pages Print downloaded pages to debug problems (very verbose)
--write-pages Write downloaded intermediary pages to files in the current directory to debug problems
--print-traffic Display sent and read HTTP traffic
-C, --call-home Contact the youtube-dl server for debugging.
--no-call-home Do NOT contact the youtube-dl server for debugging.
-C, --call-home Contact the youtube-dl server for debugging
--no-call-home Do NOT contact the youtube-dl server for debugging
## Workarounds:
--encoding ENCODING Force the specified encoding (experimental)
--no-check-certificate Suppress HTTPS certificate validation.
--no-check-certificate Suppress HTTPS certificate validation
--prefer-insecure Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
--user-agent UA specify a custom user agent
--referer URL specify a custom referer, use if the video access is restricted to one domain
--add-header FIELD:VALUE specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
--user-agent UA Specify a custom user agent
--referer URL Specify a custom referer, use if the video access is restricted to one domain
--add-header FIELD:VALUE Specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
--bidi-workaround Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
--sleep-interval SECONDS Number of seconds to sleep before each download.
## Video Format Options:
-f, --format FORMAT video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by
extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio",
"worst". You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]").
This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec,
vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a
question mark (?) after the operator. You can combine format filters, so -f "[height <=? 720][tbr>500]" selects up to 720p videos
(or videos where the height is not known) with a bitrate of at least 500 KBit/s. By default, youtube-dl will pick the best quality.
Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio
of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f
bestvideo+bestaudio.
--all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific one is requested
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats
-f, --format FORMAT Video format code, see the "FORMAT SELECTION" for all the info
--all-formats Download all available video formats
--prefer-free-formats Prefer free video formats unless a specific one is requested
-F, --list-formats List all available formats
--youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos
--merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
merge is required
## Subtitle Options:
--write-sub write subtitle file
--write-auto-sub write automatic subtitle file (youtube only)
--all-subs downloads all the available subtitles of the video
--list-subs lists all available subtitles for the video
--sub-format FORMAT subtitle format, accepts formats preference, for example: "ass/srt/best"
--sub-lang LANGS languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
--write-sub Write subtitle file
--write-auto-sub Write automatic subtitle file (YouTube only)
--all-subs Download all the available subtitles of the video
--list-subs List all available subtitles for the video
--sub-format FORMAT Subtitle format, accepts formats preference, for example: "srt" or "ass/srt/best"
--sub-lang LANGS Languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
## Authentication Options:
-u, --username USERNAME login with this account ID
-p, --password PASSWORD account password. If this option is left out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri)
-u, --username USERNAME Login with this account ID
-p, --password PASSWORD Account password. If this option is left out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR Two-factor auth code
-n, --netrc Use .netrc authentication data
--video-password PASSWORD Video password (vimeo, smotri)
## Post-processing Options:
-x, --extract-audio convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
--audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K
(default 5)
-x, --extract-audio Convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default
5)
--recode-video FORMAT Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
-k, --keep-video keeps the video file on disk after the post-processing; the video is erased by default
--no-post-overwrites do not overwrite post-processed files; the post-processed files are overwritten by default
--embed-subs embed subtitles in the video (only for mp4 videos)
--embed-thumbnail embed thumbnail in the audio as cover art
--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
-k, --keep-video Keep the video file on disk after the post-processing; the video is erased by default
--no-post-overwrites Do not overwrite post-processed files; the post-processed files are overwritten by default
--embed-subs Embed subtitles in the video (only for mp4 videos)
--embed-thumbnail Embed thumbnail in the audio as cover art
--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), %(artist). Example: --metadata-from-title "%(artist)s -
%(title)s" matches a title like "Coldplay - Paradise"
--xattrs write metadata to the video file's xattrs (using dublin core and xdg standards)
--xattrs Write metadata to the video file's xattrs (using dublin core and xdg standards)
--fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
fix file if we can, warn otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default)
@@ -271,6 +262,17 @@ $ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filena
youtube-dl_test_video_.mp4 # A simple file name
```
# FORMAT SELECTION
By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`.
Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file.
If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
# VIDEO SELECTION
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
@@ -321,9 +323,9 @@ YouTube changed their playlist format in March 2014 and later on, so you'll need
If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
### Do I always have to pass `-citw`?
By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
### Can you please put the -b option back?
@@ -355,6 +357,22 @@ YouTube has switched to a new video info format in July 2011 which is not suppor
YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
```youtube-dl 'https://www.youtube.com/watch?t=4&v=BaW_jenozKc'```
or
```youtube-dl https://www.youtube.com/watch?t=4\&v=BaW_jenozKc```
For Windows you have to use the double quotes:
```youtube-dl "https://www.youtube.com/watch?t=4&v=BaW_jenozKc"```
### ExtractorError: Could not find JS function u'OF'
In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.

View File

@@ -28,7 +28,7 @@ for test in get_testcases():
if METHOD == 'EURISTIC':
try:
webpage = compat_urllib_request.urlopen(test['url'], timeout=10).read()
except:
except Exception:
print('\nFail: {0}'.format(test['name']))
continue

View File

@@ -0,0 +1,42 @@
from __future__ import unicode_literals
import codecs
import subprocess
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import intlist_to_bytes
from youtube_dl.aes import aes_encrypt, key_expansion
secret_msg = b'Secret message goes here'
def hex_str(int_list):
return codecs.encode(intlist_to_bytes(int_list), 'hex')
def openssl_encode(algo, key, iv):
cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
out, _ = prog.communicate(secret_msg)
return out
iv = key = [0x20, 0x15] + 14 * [0]
r = openssl_encode('aes-128-cbc', key, iv)
print('aes_cbc_decrypt')
print(repr(r))
password = key
new_key = aes_encrypt(password, key_expansion(password))
r = openssl_encode('aes-128-ctr', new_key, iv)
print('aes_decrypt_text 16')
print(repr(r))
password = key + 16 * [0]
new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
r = openssl_encode('aes-256-ctr', new_key, iv)
print('aes_decrypt_text 32')
print(repr(r))

View File

@@ -2,6 +2,8 @@
- **1tv**: Первый канал
- **1up.com**
- **220.ro**
- **22tracks:genre**
- **22tracks:track**
- **24video**
- **3sat**
- **4tube**
@@ -96,6 +98,7 @@
- **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
- **Cracked**
- **Criterion**
- **CrooksAndLiars**
- **Crunchyroll**
- **crunchyroll:playlist**
- **CSpan**: C-SPAN
@@ -109,14 +112,17 @@
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **DHM**: Filmarchiv - Deutsches Historisches Museum
- **Discovery**
- **divxstage**: DivxStage
- **Dotsub**
- **DouyuTV**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
- **DRTV**
- **Dump**
- **Dumpert**
- **dvtv**: http://video.aktualne.cz/
- **EaglePlatform**
- **EbaumsWorld**
@@ -161,12 +167,14 @@
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **Gamersyde**
- **GameSpot**
- **GameStar**
- **Gametrailers**
- **Gazeta**
- **GDCVault**
- **generic**: Generic downloader that works on some sites
- **Gfycat**
- **GiantBomb**
- **Giga**
- **Glide**: Glide mobile video messages (glide.me)
@@ -174,7 +182,7 @@
- **GodTube**
- **GoldenMoustache**
- **Golem**
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net
- **Goshgay**
- **Grooveshark**
- **Groupon**
@@ -230,6 +238,7 @@
- **Letv**
- **LetvPlaylist**
- **LetvTv**
- **Libsyn**
- **lifenews**: LIFE | NEWS
- **LiveLeak**
- **livestream**
@@ -244,11 +253,13 @@
- **Malemotion**
- **MDR**
- **media.ccc.de**
- **MegaVideoz**
- **metacafe**
- **Metacritic**
- **Mgoon**
- **Minhateca**
- **MinistryGrid**
- **miomio.tv**
- **mitele.es**
- **mixcloud**
- **MLB**
@@ -282,6 +293,8 @@
- **NBA**
- **NBC**
- **NBCNews**
- **NBCSports**
- **NBCSportsVPlayer**
- **ndr**: NDR.de - Mediathek
- **NDTV**
- **NerdCubedFeed**
@@ -309,6 +322,7 @@
- **npo.nl:radio**
- **npo.nl:radio:fragment**
- **NRK**
- **NRKPlaylist**
- **NRKTV**
- **ntv.ru**
- **Nuvid**
@@ -326,6 +340,7 @@
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **PBS**
- **PhilharmonieDeParis**: Philharmonie de Paris
- **Phoenix**
- **Photobucket**
- **Pladform**
@@ -341,16 +356,22 @@
- **PornHub**
- **PornHubPlaylist**
- **Pornotube**
- **PornoVoisines**
- **PornoXO**
- **PrimeShareTV**
- **PromptFile**
- **prosiebensat1**: ProSiebenSat.1 Digital
- **Puls4**
- **Pyvideo**
- **QQMusic**
- **QQMusicAlbum**
- **QQMusicSinger**
- **QuickVid**
- **R7**
- **radio.de**
- **radiobremen**
- **radiofrance**
- **RadioJavan**
- **Rai**
- **RBMARadio**
- **RedTube**
@@ -367,6 +388,7 @@
- **RTP**
- **RTS**: RTS.ch
- **rtve.es:alacarta**: RTVE a la carta
- **rtve.es:infantil**: RTVE infantil
- **rtve.es:live**: RTVE.es live streams
- **RUHD**
- **rutube**: Rutube videos
@@ -375,6 +397,8 @@
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **RUTV**: RUTV.RU
- **safari**: safaribooksonline.com online video
- **safari:course**: safaribooksonline.com online courses
- **Sandia**: Sandia National Laboratories
- **Sapo**: SAPO Vídeos
- **savefrom.net**
@@ -384,6 +408,7 @@
- **Screencast**
- **ScreencastOMatic**
- **ScreenwaveMedia**
- **SenateISVP**
- **ServingSys**
- **Sexu**
- **SexyKarma**: Sexy Karma and Watch Indian Porn
@@ -406,8 +431,10 @@
- **soundgasm**
- **soundgasm:profile**
- **southpark.cc.com**
- **southpark.cc.com:español**
- **southpark.de**
- **Space**
- **SpankBang**
- **Spankwire**
- **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
@@ -416,6 +443,7 @@
- **Sport5**
- **SportBox**
- **SportDeutschland**
- **Srf**
- **SRMediathek**: Saarländischer Rundfunk
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
@@ -438,7 +466,7 @@
- **TeamFour**
- **TechTalks**
- **techtv.mit.edu**
- **TED**
- **ted**
- **tegenlicht.vpro.nl**
- **TeleBruxelles**
- **telecinco.es**
@@ -487,13 +515,17 @@
- **Ubu**
- **udemy**
- **udemy:course**
- **UDNEmbed**
- **Ultimedia**
- **Unistra**
- **Urort**: NRK P3 Urørt
- **ustream**
- **ustream:channel**
- **Varzesh3**
- **Vbox7**
- **VeeHD**
- **Veoh**
- **Vessel**
- **Vesti**: Вести.Ru
- **Vevo**
- **VGTV**
@@ -524,7 +556,7 @@
- **vimeo:review**: Review pages on vimeo
- **vimeo:user**
- **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- **Vimple**: Vimple.ru
- **Vimple**: Vimple - one-click video hosting
- **Vine**
- **vine:user**
- **vk.com**
@@ -582,7 +614,7 @@
- **youtube:show**: YouTube.com (multi-season) shows
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **ZDF**
- **ZDFChannel**

View File

@@ -150,7 +150,7 @@ def expect_info_dict(self, got_dict, expected_dict):
'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
# Check for the presence of mandatory fields
if got_dict.get('_type') != 'playlist':
if got_dict.get('_type') not in ('playlist', 'multi_video'):
for key in ('id', 'url', 'title', 'ext'):
self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
# Check for mandatory fields that are automatically set by YoutubeDL

View File

@@ -7,8 +7,7 @@
"forcethumbnail": false,
"forcetitle": false,
"forceurl": false,
"format": null,
"format_limit": null,
"format": "best",
"ignoreerrors": false,
"listformats": null,
"logtostderr": false,

View File

@@ -14,6 +14,7 @@ from test.helper import FakeYDL, assertRegexpMatches
from youtube_dl import YoutubeDL
from youtube_dl.extractor import YoutubeIE
from youtube_dl.postprocessor.common import PostProcessor
from youtube_dl.utils import match_filter_func
TEST_URL = 'http://localhost/sample.mp4'
@@ -100,39 +101,6 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['ext'], 'flv')
def test_format_limit(self):
formats = [
{'format_id': 'meh', 'url': 'http://example.com/meh', 'preference': 1},
{'format_id': 'good', 'url': 'http://example.com/good', 'preference': 2},
{'format_id': 'great', 'url': 'http://example.com/great', 'preference': 3},
{'format_id': 'excellent', 'url': 'http://example.com/exc', 'preference': 4},
]
info_dict = _make_result(formats)
ydl = YDL()
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
ydl = YDL({'format_limit': 'good'})
assert ydl.params['format_limit'] == 'good'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'good')
ydl = YDL({'format_limit': 'great', 'format': 'all'})
ydl.process_ie_result(info_dict.copy())
self.assertEqual(ydl.downloaded_info_dicts[0]['format_id'], 'meh')
self.assertEqual(ydl.downloaded_info_dicts[1]['format_id'], 'good')
self.assertEqual(ydl.downloaded_info_dicts[2]['format_id'], 'great')
self.assertTrue('3' in ydl.msgs[0])
ydl = YDL()
ydl.params['format_limit'] = 'excellent'
ydl.process_ie_result(info_dict.copy())
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'excellent')
def test_format_selection(self):
formats = [
{'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
@@ -339,6 +307,8 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
class TestYoutubeDL(unittest.TestCase):
def test_subtitles(self):
def s_formats(lang, autocaption=False):
return [{
@@ -440,27 +410,103 @@ class TestFormatSelection(unittest.TestCase):
def run(self, info):
with open(audiofile, 'wt') as f:
f.write('EXAMPLE')
info['filepath']
return False, info
return [info['filepath']], info
def run_pp(params):
def run_pp(params, PP):
with open(filename, 'wt') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(SimplePP())
ydl.add_post_processor(PP())
ydl.post_process(filename, {'filepath': filename})
run_pp({'keepvideo': True})
run_pp({'keepvideo': True}, SimplePP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(filename)
os.unlink(audiofile)
run_pp({'keepvideo': False})
run_pp({'keepvideo': False}, SimplePP)
self.assertFalse(os.path.exists(filename), '%s exists' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(audiofile)
class ModifierPP(PostProcessor):
def run(self, info):
with open(info['filepath'], 'wt') as f:
f.write('MODIFIED')
return [], info
run_pp({'keepvideo': False}, ModifierPP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
os.unlink(filename)
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete):
res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict)
return res
first = {
'id': '1',
'url': TEST_URL,
'title': 'one',
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
}
second = {
'id': '2',
'url': TEST_URL,
'title': 'two',
'extractor': 'TEST',
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
}
videos = [first, second]
def get_videos(filter_=None):
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
res = get_videos()
self.assertEqual(res, ['1', '2'])
def f(v):
if v['id'] == '1':
return None
else:
return 'Video id is not 1'
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('duration < 30')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description = foo')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description =? foo')
res = get_videos(f)
self.assertEqual(res, ['1', '2'])
f = match_filter_func('filesize > 5KiB')
res = get_videos(f)
self.assertEqual(res, ['1'])
if __name__ == '__main__':
unittest.main()

55
test/test_aes.py Normal file
View File

@@ -0,0 +1,55 @@
#!/usr/bin/env python
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 youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
import base64
# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
class TestAES(unittest.TestCase):
def setUp(self):
self.key = self.iv = [0x20, 0x15] + 14 * [0]
self.secret_msg = b'Secret message goes here'
def test_encrypt(self):
msg = b'message'
key = list(range(16))
encrypted = aes_encrypt(bytes_to_intlist(msg), key)
decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
self.assertEqual(decrypted, msg)
def test_cbc_decrypt(self):
data = bytes_to_intlist(
b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
)
decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
)
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
)
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
if __name__ == '__main__':
unittest.main()

View File

@@ -59,7 +59,7 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
def test_youtube_feeds(self):
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])

View File

@@ -153,7 +153,7 @@ def generator(test_case):
break
if is_playlist:
self.assertEqual(res_dict['_type'], 'playlist')
self.assertTrue(res_dict['_type'] in ['playlist', 'multi_video'])
self.assertTrue('entries' in res_dict)
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))

View File

@@ -1,4 +1,6 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
import unittest
@@ -6,6 +8,9 @@ import unittest
import sys
import os
import subprocess
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import encodeArgument
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
@@ -27,5 +32,12 @@ class TestExecution(unittest.TestCase):
def test_main_exec(self):
subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_cmdline_umlauts(self):
p = subprocess.Popen(
[sys.executable, 'youtube_dl/__main__.py', encodeArgument('ä'), '--version'],
cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
_, stderr = p.communicate()
self.assertFalse(stderr)
if __name__ == '__main__':
unittest.main()

View File

@@ -8,7 +8,7 @@ import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_http_server
from youtube_dl.compat import compat_http_server, compat_urllib_request
import ssl
import threading
@@ -68,5 +68,52 @@ class TestHTTP(unittest.TestCase):
r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
self.assertEqual(r['url'], 'https://localhost:%d/vid.mp4' % self.port)
def _build_proxy_handler(name):
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
proxy_name = name
def log_message(self, format, *args):
pass
def do_GET(self):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
return HTTPTestRequestHandler
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('normal'))
self.port = self.proxy.socket.getsockname()[1]
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.cn_proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('cn'))
self.cn_port = self.cn_proxy.socket.getsockname()[1]
self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
self.cn_proxy_thread.daemon = True
self.cn_proxy_thread.start()
def test_proxy(self):
cn_proxy = 'localhost:{0}'.format(self.cn_port)
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
'cn_verification_proxy': cn_proxy,
})
url = 'http://foo.com/bar'
response = ydl.urlopen(url).read().decode('utf-8')
self.assertEqual(response, 'normal: {0}'.format(url))
req = compat_urllib_request.Request(url)
req.add_header('Ytdl-request-proxy', cn_proxy)
response = ydl.urlopen(req).read().decode('utf-8')
self.assertEqual(response, 'cn: {0}'.format(url))
if __name__ == '__main__':
unittest.main()

View File

@@ -24,6 +24,7 @@ from youtube_dl.utils import (
encodeFilename,
escape_rfc3986,
escape_url,
ExtractorError,
find_xpath_attr,
fix_xml_ampersands,
InAdvancePagedList,
@@ -39,6 +40,7 @@ from youtube_dl.utils import (
read_batch_urls,
sanitize_filename,
sanitize_path,
sanitize_url_path_consecutive_slashes,
shell_quote,
smuggle_url,
str_to_int,
@@ -53,8 +55,11 @@ from youtube_dl.utils import (
urlencode_postdata,
version_tuple,
xpath_with_ns,
xpath_text,
render_table,
match_str,
parse_dfxp_time_expr,
dfxp2srt,
)
@@ -168,6 +173,26 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
def test_sanitize_url_path_consecutive_slashes(self):
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname//'),
'http://hostname/')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/'),
'http://hostname/')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
'http://hostname/abc/')
def test_ordered_set(self):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), [])
@@ -177,6 +202,8 @@ class TestUtil(unittest.TestCase):
def test_unescape_html(self):
self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual(unescapeHTML('&#x2F;'), '/')
self.assertEqual(unescapeHTML('&#47;'), '/')
self.assertEqual(
unescapeHTML('&eacute;'), 'é')
@@ -202,6 +229,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
self.assertEqual(unified_strdate('25-09-2014'), '20140925')
def test_find_xpath_attr(self):
testxml = '''<root>
@@ -229,6 +257,17 @@ class TestUtil(unittest.TestCase):
self.assertEqual(find('media:song/media:author').text, 'The Author')
self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
def test_xpath_text(self):
testxml = '''<root>
<div>
<p>Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a'
@@ -434,6 +473,12 @@ class TestUtil(unittest.TestCase):
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
on = js_to_json('["abc", "def",]')
self.assertEqual(json.loads(on), ['abc', 'def'])
on = js_to_json('{"abc": "def",}')
self.assertEqual(json.loads(on), {'abc': 'def'})
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
@@ -538,6 +583,42 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
def test_parse_dfxp_time_expr(self):
self.assertEqual(parse_dfxp_time_expr(None), 0.0)
self.assertEqual(parse_dfxp_time_expr(''), 0.0)
self.assertEqual(parse_dfxp_time_expr('0.1'), 0.1)
self.assertEqual(parse_dfxp_time_expr('0.1s'), 0.1)
self.assertEqual(parse_dfxp_time_expr('00:00:01'), 1.0)
self.assertEqual(parse_dfxp_time_expr('00:00:01.100'), 1.1)
def test_dfxp2srt(self):
dfxp_data = '''<?xml version="1.0" encoding="UTF-8"?>
<tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
<body>
<div xml:lang="en">
<p begin="0" end="1">The following line contains Chinese characters and special symbols</p>
<p begin="1" end="2">第二行<br/>♪♪</p>
<p begin="2" end="3"><span>Third<br/>Line</span></p>
</div>
</body>
</tt>'''
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The following line contains Chinese characters and special symbols
2
00:00:01,000 --> 00:00:02,000
第二行
♪♪
3
00:00:02,000 --> 00:00:03,000
Third
Line
'''
self.assertEqual(dfxp2srt(dfxp_data), srt_data)
if __name__ == '__main__':
unittest.main()

View File

@@ -64,7 +64,6 @@ from .utils import (
sanitize_path,
std_headers,
subtitles_filename,
takewhile_inclusive,
UnavailableVideoError,
url_basename,
version_tuple,
@@ -135,7 +134,6 @@ class YoutubeDL(object):
(or video) as a single JSON line.
simulate: Do not download the video files.
format: Video format code. See options.py for more information.
format_limit: Highest quality format to try.
outtmpl: Template for output names.
restrictfilenames: Do not allow "&" and spaces in file names
ignoreerrors: Do not stop on download errors.
@@ -328,9 +326,6 @@ class YoutubeDL(object):
'Parameter outtmpl is bytes, but should be a unicode string. '
'Put from __future__ import unicode_literals at the top of your code file or consider switching to Python 3.x.')
if '%(stitle)s' in self.params.get('outtmpl', ''):
self.report_warning('%(stitle)s is deprecated. Use the %(title)s and the --restrict-filenames flag(which also secures %(uploader)s et al) instead.')
self._setup_opener()
if auto_init:
@@ -922,6 +917,11 @@ class YoutubeDL(object):
if format_spec == 'best' or format_spec is None:
return available_formats[-1]
elif format_spec == 'worst':
audiovideo_formats = [
f for f in available_formats
if f.get('vcodec') != 'none' and f.get('acodec') != 'none']
if audiovideo_formats:
return audiovideo_formats[0]
return available_formats[0]
elif format_spec == 'bestaudio':
audio_formats = [
@@ -1066,12 +1066,6 @@ class YoutubeDL(object):
full_format_info.update(format)
format['http_headers'] = self._calc_headers(full_format_info)
format_limit = self.params.get('format_limit', None)
if format_limit:
formats = list(takewhile_inclusive(
lambda f: f['format_id'] != format_limit, formats
))
# TODO Central sorting goes here
if formats[0] is not info_dict:
@@ -1089,7 +1083,11 @@ class YoutubeDL(object):
req_format = self.params.get('format')
if req_format is None:
req_format = 'best'
req_format_list = []
if info_dict['extractor'] in ['youtube', 'ted'] and FFmpegMergerPP(self).available:
req_format_list.append('bestvideo+bestaudio')
req_format_list.append('best')
req_format = '/'.join(req_format_list)
formats_to_download = []
if req_format == 'all':
formats_to_download = formats
@@ -1218,9 +1216,6 @@ class YoutubeDL(object):
if len(info_dict['title']) > 200:
info_dict['title'] = info_dict['title'][:197] + '...'
# Keep for backwards compatibility
info_dict['stitle'] = info_dict['title']
if 'format' not in info_dict:
info_dict['format'] = info_dict['ext']
@@ -1362,7 +1357,7 @@ class YoutubeDL(object):
if info_dict.get('requested_formats') is not None:
downloaded = []
success = True
merger = FFmpegMergerPP(self, not self.params.get('keepvideo'))
merger = FFmpegMergerPP(self)
if not merger.available:
postprocessors = []
self.report_warning('You have requested multiple '
@@ -1370,16 +1365,42 @@ class YoutubeDL(object):
' The formats won\'t be merged')
else:
postprocessors = [merger]
for f in info_dict['requested_formats']:
new_info = dict(info_dict)
new_info.update(f)
fname = self.prepare_filename(new_info)
fname = prepend_extension(fname, 'f%s' % f['format_id'])
downloaded.append(fname)
partial_success = dl(fname, new_info)
success = success and partial_success
info_dict['__postprocessors'] = postprocessors
info_dict['__files_to_merge'] = downloaded
def compatible_formats(formats):
video, audio = formats
# Check extension
video_ext, audio_ext = audio.get('ext'), video.get('ext')
if video_ext and audio_ext:
COMPATIBLE_EXTS = (
('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v'),
('webm')
)
for exts in COMPATIBLE_EXTS:
if video_ext in exts and audio_ext in exts:
return True
# TODO: Check acodec/vcodec
return False
requested_formats = info_dict['requested_formats']
if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats):
filename = os.path.splitext(filename)[0] + '.mkv'
self.report_warning('You have requested formats uncompatible for merge. '
'The formats will be merged into mkv')
if os.path.exists(encodeFilename(filename)):
self.to_screen(
'[download] %s has already been downloaded and '
'merged' % filename)
else:
for f in requested_formats:
new_info = dict(info_dict)
new_info.update(f)
fname = self.prepare_filename(new_info)
fname = prepend_extension(fname, 'f%s' % f['format_id'])
downloaded.append(fname)
partial_success = dl(fname, new_info)
success = success and partial_success
info_dict['__postprocessors'] = postprocessors
info_dict['__files_to_merge'] = downloaded
else:
# Just a single file
success = dl(filename, info_dict)
@@ -1487,24 +1508,17 @@ class YoutubeDL(object):
pps_chain.extend(ie_info['__postprocessors'])
pps_chain.extend(self._pps)
for pp in pps_chain:
keep_video = None
old_filename = info['filepath']
try:
keep_video_wish, info = pp.run(info)
if keep_video_wish is not None:
if keep_video_wish:
keep_video = keep_video_wish
elif keep_video is None:
# No clear decision yet, let IE decide
keep_video = keep_video_wish
files_to_delete, info = pp.run(info)
except PostProcessingError as e:
self.report_error(e.msg)
if keep_video is False and not self.params.get('keepvideo', False):
try:
if files_to_delete and not self.params.get('keepvideo', False):
for old_filename in files_to_delete:
self.to_screen('Deleting original file %s (pass -k to keep)' % old_filename)
os.remove(encodeFilename(old_filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded video file')
try:
os.remove(encodeFilename(old_filename))
except (IOError, OSError):
self.report_warning('Unable to remove downloaded original file')
def _make_archive_id(self, info_dict):
# Future-proof against any change in case
@@ -1707,10 +1721,10 @@ class YoutubeDL(object):
out = out.decode().strip()
if re.match('[0-9a-f]+', out):
self._write_string('[debug] Git HEAD: ' + out + '\n')
except:
except Exception:
try:
sys.exc_clear()
except:
except Exception:
pass
self._write_string('[debug] Python version %s - %s\n' % (
platform.python_version(), platform_name()))

View File

@@ -189,10 +189,6 @@ def _real_main(argv=None):
if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True
if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
(opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
(opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
@@ -244,9 +240,7 @@ def _real_main(argv=None):
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.embedthumbnail:
if not opts.addmetadata:
postprocessors.append({'key': 'FFmpegAudioFix'})
postprocessors.append({'key': 'AtomicParsley'})
postprocessors.append({'key': 'EmbedThumbnail'})
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
@@ -289,7 +283,6 @@ def _real_main(argv=None):
'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
'outtmpl': outtmpl,
'autonumber_size': opts.autonumber_size,

View File

@@ -389,7 +389,7 @@ else:
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = sp.communicate()
lines, columns = map(int, out.split())
except:
except Exception:
pass
return _terminal_size(columns, lines)

View File

@@ -6,7 +6,7 @@ from .f4m import F4mFD
from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD
from .mplayer import MplayerFD
from .rtsp import RtspFD
from .rtmp import RtmpFD
from ..utils import (
@@ -17,8 +17,8 @@ PROTOCOL_MAP = {
'rtmp': RtmpFD,
'm3u8_native': NativeHlsFD,
'm3u8': HlsFD,
'mms': MplayerFD,
'rtsp': MplayerFD,
'mms': RtspFD,
'rtsp': RtspFD,
'f4m': F4mFD,
}

View File

@@ -8,6 +8,7 @@ import time
from ..compat import compat_str
from ..utils import (
encodeFilename,
decodeArgument,
format_bytes,
timeconvert,
)
@@ -204,7 +205,7 @@ class FileDownloader(object):
return
try:
os.utime(filename, (time.time(), filetime))
except:
except Exception:
pass
return filetime
@@ -318,7 +319,7 @@ class FileDownloader(object):
)
continuedl_and_exists = (
self.params.get('continuedl', False) and
self.params.get('continuedl', True) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
)
@@ -353,19 +354,15 @@ class FileDownloader(object):
# this interface
self._progress_hooks.append(ph)
def _debug_cmd(self, args, subprocess_encoding, exe=None):
def _debug_cmd(self, args, exe=None):
if not self.params.get('verbose', False):
return
if exe is None:
exe = os.path.basename(args[0])
str_args = [decodeArgument(a) for a in args]
if exe is None:
exe = os.path.basename(str_args[0])
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))

View File

@@ -2,11 +2,11 @@ from __future__ import unicode_literals
import os.path
import subprocess
import sys
from .common import FileDownloader
from ..utils import (
encodeFilename,
encodeArgument,
)
@@ -60,17 +60,9 @@ class ExternalFD(FileDownloader):
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = self._make_cmd(tmpfilename, info_dict)
cmd = [encodeArgument(a) for a in self._make_cmd(tmpfilename, info_dict)]
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
else:
subprocess_encoding = None
self._debug_cmd(cmd, subprocess_encoding)
self._debug_cmd(cmd)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)

View File

@@ -389,6 +389,8 @@ class F4mFD(FileDownloader):
url = base_url + name
if akamai_pv:
url += '?' + akamai_pv.strip(';')
if info_dict.get('extra_param_to_segment_url'):
url += info_dict.get('extra_param_to_segment_url')
frag_filename = '%s-%s' % (tmpfilename, name)
try:
success = http_dl.download(frag_filename, {'url': url})

View File

@@ -49,7 +49,7 @@ class HttpFD(FileDownloader):
open_mode = 'wb'
if resume_len != 0:
if self.params.get('continuedl', False):
if self.params.get('continuedl', True):
self.report_resuming_byte(resume_len)
request.add_header('Range', 'bytes=%d-' % resume_len)
open_mode = 'ab'

View File

@@ -3,7 +3,6 @@ from __future__ import unicode_literals
import os
import re
import subprocess
import sys
import time
from .common import FileDownloader
@@ -11,6 +10,7 @@ from ..compat import compat_str
from ..utils import (
check_executable,
encodeFilename,
encodeArgument,
get_exe_version,
)
@@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
protocol = info_dict.get('rtmp_protocol', None)
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = info_dict.get('continuedl', False)
continue_dl = info_dict.get('continuedl', True)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
@@ -121,7 +121,7 @@ class RtmpFD(FileDownloader):
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = [
'rtmpdump', '--verbose', '-r', url,
'-o', encodeFilename(tmpfilename, True)]
'-o', tmpfilename]
if player_url is not None:
basic_args += ['--swfVfy', player_url]
if page_url is not None:
@@ -154,16 +154,9 @@ class RtmpFD(FileDownloader):
if not live and continue_dl:
args += ['--skip', '1']
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
args = [a.encode(subprocess_encoding, 'ignore') for a in args]
else:
subprocess_encoding = None
args = [encodeArgument(a) for a in args]
self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
self._debug_cmd(args, exe='rtmpdump')
RD_SUCCESS = 0
RD_FAILED = 1
@@ -180,7 +173,11 @@ class RtmpFD(FileDownloader):
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
args = basic_args + ['--resume']
if retval == RD_FAILED:
args += ['--skip', '1']
args = [encodeArgument(a) for a in args]
retval = run_rtmpdump(args)
cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED:
break

View File

@@ -10,21 +10,23 @@ from ..utils import (
)
class MplayerFD(FileDownloader):
class RtspFD(FileDownloader):
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
# Check for mplayer first
if not check_executable('mplayer', ['-h']):
self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
if check_executable('mplayer', ['-h']):
args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
elif check_executable('mpv', ['-h']):
args = [
'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
else:
self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
return False
# Download using mplayer.
retval = subprocess.call(args)
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
@@ -39,5 +41,5 @@ class MplayerFD(FileDownloader):
return True
else:
self.to_stderr('\n')
self.report_error('mplayer exited with code %d' % retval)
self.report_error('%s exited with code %d' % (args[0], retval))
return False

View File

@@ -70,6 +70,7 @@ from .chirbit import (
ChirbitProfileIE,
)
from .cinchcast import CinchcastIE
from .cinemassacre import CinemassacreIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE
@@ -90,6 +91,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE
from .cracked import CrackedIE
from .criterion import CriterionIE
from .crooksandliars import CrooksAndLiarsIE
from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
@@ -106,13 +108,16 @@ from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE
from .drtv import DRTVIE
from .dvtv import DVTVIE
from .dump import DumpIE
from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .divxstage import DivxStageIE
@@ -174,12 +179,14 @@ from .gameone import (
GameOneIE,
GameOnePlaylistIE,
)
from .gamersyde import GamersydeIE
from .gamespot import GameSpotIE
from .gamestar import GameStarIE
from .gametrailers import GametrailersIE
from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE
from .generic import GenericIE
from .gfycat import GfycatIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
@@ -249,6 +256,7 @@ from .letv import (
LetvTvIE,
LetvPlaylistIE
)
from .libsyn import LibsynIE
from .lifenews import LifeNewsIE
from .liveleak import LiveLeakIE
from .livestream import (
@@ -267,11 +275,13 @@ from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .malemotion import MalemotionIE
from .mdr import MDRIE
from .megavideoz import MegaVideozIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mgoon import MgoonIE
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE
from .miomio import MioMioIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE
from .mixcloud import MixcloudIE
@@ -307,6 +317,8 @@ from .nba import NBAIE
from .nbc import (
NBCIE,
NBCNewsIE,
NBCSportsIE,
NBCSportsVPlayerIE,
)
from .ndr import NDRIE
from .ndtv import NDTVIE
@@ -345,6 +357,7 @@ from .npo import (
)
from .nrk import (
NRKIE,
NRKPlaylistIE,
NRKTVIE,
)
from .ntvde import NTVDeIE
@@ -364,6 +377,7 @@ from .orf import (
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
@@ -379,14 +393,22 @@ from .pornhub import (
PornHubPlaylistIE,
)
from .pornotube import PornotubeIE
from .pornovoisines import PornoVoisinesIE
from .pornoxo import PornoXOIE
from .primesharetv import PrimeShareTVIE
from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE
from .pyvideo import PyvideoIE
from .qqmusic import (
QQMusicIE,
QQMusicSingerIE,
QQMusicAlbumIE,
)
from .quickvid import QuickVidIE
from .r7 import R7IE
from .radiode import RadioDeIE
from .radiojavan import RadioJavanIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import RaiIE
@@ -405,7 +427,7 @@ from .rtlnow import RTLnowIE
from .rtl2 import RTL2IE
from .rtp import RTPIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
from .ruhd import RUHDIE
from .rutube import (
RutubeIE,
@@ -416,13 +438,18 @@ from .rutube import (
)
from .rutv import RUTVIE
from .sandia import SandiaIE
from .safari import (
SafariIE,
SafariCourseIE,
)
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
from .senateisvp import SenateISVPIE
from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
@@ -452,9 +479,11 @@ from .soundgasm import (
)
from .southpark import (
SouthParkIE,
SouthParkEsIE,
SouthparkDeIE,
)
from .space import SpaceIE
from .spankbang import SpankBangIE
from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
@@ -462,6 +491,7 @@ from .spike import SpikeIE
from .sport5 import Sport5IE
from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE
from .srf import SrfIE
from .srmediathek import SRMediathekIE
from .ssa import SSAIE
from .stanfordoc import StanfordOpenClassroomIE
@@ -522,6 +552,10 @@ from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE
from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
from .twentytwotracks import (
TwentyTwoTracksIE,
TwentyTwoTracksGenreIE
)
from .twitch import (
TwitchVideoIE,
TwitchChapterIE,
@@ -536,12 +570,16 @@ from .udemy import (
UdemyIE,
UdemyCourseIE
)
from .udn import UDNEmbedIE
from .ultimedia import UltimediaIE
from .unistra import UnistraIE
from .urort import UrortIE
from .ustream import UstreamIE, UstreamChannelIE
from .varzesh3 import Varzesh3IE
from .vbox7 import Vbox7IE
from .veehd import VeeHDIE
from .veoh import VeohIE
from .vessel import VesselIE
from .vesti import VestiIE
from .vevo import VevoIE
from .vgtv import VGTVIE

View File

@@ -11,12 +11,13 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
qualities,
)
class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
_TEST = {
_VALID_URL = r'http://(?:\w+\.)?add-anime\.net/(?:watch_video\.php\?(?:.*?)v=|video/)(?P<id>[\w_]+)'
_TESTS = [{
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0',
'info_dict': {
@@ -25,7 +26,10 @@ class AddAnimeIE(InfoExtractor):
'description': 'One Piece 606',
'title': 'One Piece 606',
}
}
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -63,8 +67,10 @@ class AddAnimeIE(InfoExtractor):
note='Confirming after redirect')
webpage = self._download_webpage(url, video_id)
FORMATS = ('normal', 'hq')
quality = qualities(FORMATS)
formats = []
for format_id in ('normal', 'hq'):
for format_id in FORMATS:
rex = r"var %s_video_file = '(.*?)';" % re.escape(format_id)
video_url = self._search_regex(rex, webpage, 'video file URLx',
fatal=False)
@@ -73,6 +79,7 @@ class AddAnimeIE(InfoExtractor):
formats.append({
'format_id': format_id,
'url': video_url,
'quality': quality(format_id),
})
self._sort_formats(formats)
video_title = self._og_search_title(webpage)

View File

@@ -2,10 +2,11 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
class AftonbladetIE(InfoExtractor):
_VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
_VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?P<id>article[0-9]+)\.ab(?:$|[?#])'
_TEST = {
'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
'info_dict': {
@@ -43,9 +44,9 @@ class AftonbladetIE(InfoExtractor):
formats.append({
'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
'ext': 'mp4',
'width': fmt['width'],
'height': fmt['height'],
'tbr': fmt['bitrate'],
'width': int_or_none(fmt.get('width')),
'height': int_or_none(fmt.get('height')),
'tbr': int_or_none(fmt.get('bitrate')),
'protocol': 'http',
})
self._sort_formats(formats)
@@ -54,9 +55,9 @@ class AftonbladetIE(InfoExtractor):
'id': video_id,
'title': internal_meta_json['title'],
'formats': formats,
'thumbnail': internal_meta_json['imageUrl'],
'description': internal_meta_json['shortPreamble'],
'timestamp': internal_meta_json['timePublished'],
'duration': internal_meta_json['duration'],
'view_count': internal_meta_json['views'],
'thumbnail': internal_meta_json.get('imageUrl'),
'description': internal_meta_json.get('shortPreamble'),
'timestamp': int_or_none(internal_meta_json.get('timePublished')),
'duration': int_or_none(internal_meta_json.get('duration')),
'view_count': int_or_none(internal_meta_json.get('views')),
}

View File

@@ -146,6 +146,7 @@ class ArteTVPlus7IE(InfoExtractor):
formats.append(format)
self._check_formats(formats, video_id)
self._sort_formats(formats)
info_dict['formats'] = formats

View File

@@ -1,12 +1,18 @@
from __future__ import unicode_literals
import re
import json
import itertools
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_str,
)
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
)
@@ -14,6 +20,8 @@ class BambuserIE(InfoExtractor):
IE_NAME = 'bambuser'
_VALID_URL = r'https?://bambuser\.com/v/(?P<id>\d+)'
_API_KEY = '005f64509e19a868399060af746a00aa'
_LOGIN_URL = 'https://bambuser.com/user'
_NETRC_MACHINE = 'bambuser'
_TEST = {
'url': 'http://bambuser.com/v/4050584',
@@ -26,6 +34,9 @@ class BambuserIE(InfoExtractor):
'duration': 3741,
'uploader': 'pixelversity',
'uploader_id': '344706',
'timestamp': 1382976692,
'upload_date': '20131028',
'view_count': int,
},
'params': {
# It doesn't respect the 'Range' header, it would download the whole video
@@ -34,23 +45,60 @@ class BambuserIE(InfoExtractor):
},
}
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'form_id': 'user_login',
'op': 'Log in',
'name': username,
'pass': password,
}
request = compat_urllib_request.Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
login_error = self._html_search_regex(
r'(?s)<div class="messages error">(.+?)</div>',
response, 'login error', default=None)
if login_error:
raise ExtractorError(
'Unable to login: %s' % login_error, expected=True)
def _real_initialize(self):
self._login()
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info_url = ('http://player-c.api.bambuser.com/getVideo.json?'
'&api_key=%s&vid=%s' % (self._API_KEY, video_id))
info_json = self._download_webpage(info_url, video_id)
info = json.loads(info_json)['result']
video_id = self._match_id(url)
info = self._download_json(
'http://player-c.api.bambuser.com/getVideo.json?api_key=%s&vid=%s'
% (self._API_KEY, video_id), video_id)
error = info.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
result = info['result']
return {
'id': video_id,
'title': info['title'],
'url': info['url'],
'thumbnail': info.get('preview'),
'duration': int(info['length']),
'view_count': int(info['views_total']),
'uploader': info['username'],
'uploader_id': info['owner']['uid'],
'title': result['title'],
'url': result['url'],
'thumbnail': result.get('preview'),
'duration': int_or_none(result.get('length')),
'uploader': result.get('username'),
'uploader_id': compat_str(result.get('owner', {}).get('uid')),
'timestamp': int_or_none(result.get('created')),
'fps': float_or_none(result.get('framerate')),
'view_count': int_or_none(result.get('views_total')),
'comment_count': int_or_none(result.get('comment_count')),
}

View File

@@ -72,7 +72,7 @@ class BandcampIE(InfoExtractor):
download_link = m_download.group(1)
video_id = self._search_regex(
r'(?ms)var TralbumData = {.*?id: (?P<id>\d+),?$',
r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
webpage, 'video id')
download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page')

View File

@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
ExtractorError,
)
@@ -30,6 +31,8 @@ class BiliBiliIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None):
raise ExtractorError('The video does not exist or was deleted', expected=True)
video_code = self._search_regex(
r'(?s)<div itemprop="video".*?>(.*?)</div>', webpage, 'video code')

View File

@@ -102,6 +102,15 @@ class BlipTVIE(InfoExtractor):
},
]
@staticmethod
def _extract_url(webpage):
mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
if mobj:
return 'http://blip.tv/a/a-' + mobj.group(1)
mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
if mobj:
return mobj.group(1)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
lookup_id = mobj.group('lookup_id')
@@ -172,6 +181,7 @@ class BlipTVIE(InfoExtractor):
'width': int_or_none(media_content.get('width')),
'height': int_or_none(media_content.get('height')),
})
self._check_formats(formats, video_id)
self._sort_formats(formats)
subtitles = self.extract_subtitles(video_id, subtitles_urls)

View File

@@ -6,32 +6,39 @@ from .common import InfoExtractor
class BloombergIE(InfoExtractor):
_VALID_URL = r'https?://www\.bloomberg\.com/video/(?P<id>.+?)\.html'
_VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html',
'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2',
# The md5 checksum changes
'info_dict': {
'id': 'qurhIVlJSB6hzkVi229d8g',
'ext': 'flv',
'title': 'Shah\'s Presentation on Foreign-Exchange Strategies',
'description': 'md5:0681e0d30dcdfc6abf34594961d8ea88',
'description': 'md5:a8ba0302912d03d246979735c17d2761',
},
}
def _real_extract(self, url):
name = self._match_id(url)
webpage = self._download_webpage(url, name)
f4m_url = self._search_regex(
r'<source src="(https?://[^"]+\.f4m.*?)"', webpage,
'f4m url')
video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id')
title = re.sub(': Video$', '', self._og_search_title(webpage))
embed_info = self._download_json(
'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id)
formats = []
for stream in embed_info['streams']:
if stream["muxing_format"] == "TS":
formats.extend(self._extract_m3u8_formats(stream['url'], video_id))
else:
formats.extend(self._extract_f4m_formats(stream['url'], video_id))
self._sort_formats(formats)
return {
'id': name.split('-')[-1],
'id': video_id,
'title': title,
'formats': self._extract_f4m_formats(f4m_url, name),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
}

View File

@@ -117,7 +117,10 @@ class BrightcoveIE(InfoExtractor):
object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
object_str = fix_xml_ampersands(object_str)
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
except xml.etree.ElementTree.ParseError:
return
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
if fv_el is not None:
@@ -183,9 +186,9 @@ class BrightcoveIE(InfoExtractor):
(?:
[^>]+?class=[\'"][^>]*?BrightcoveExperience.*?[\'"] |
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?</object>''',
).+?>\s*</object>''',
webpage)
return [cls._build_brighcove_url(m) for m in matches]
return list(filter(None, [cls._build_brighcove_url(m) for m in matches]))
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})

View File

@@ -0,0 +1,99 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
from .bliptv import BlipTVIE
class CinemassacreIE(InfoExtractor):
_VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
_TESTS = [
{
'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
'md5': 'fde81fbafaee331785f58cd6c0d46190',
'info_dict': {
'id': 'Cinemassacre-19911',
'ext': 'mp4',
'upload_date': '20121110',
'title': '“Angry Video Game Nerd: The Movie” Trailer',
'description': 'md5:fb87405fcb42a331742a0dce2708560b',
},
},
{
'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
'md5': 'd72f10cd39eac4215048f62ab477a511',
'info_dict': {
'id': 'Cinemassacre-521be8ef82b16',
'ext': 'mp4',
'upload_date': '20131002',
'title': 'The Mummys Hand (1940)',
},
},
{
# blip.tv embedded video
'url': 'http://cinemassacre.com/2006/12/07/chronologically-confused-about-bad-movie-and-video-game-sequel-titles/',
'md5': 'ca9b3c8dd5a66f9375daeb5135f5a3de',
'info_dict': {
'id': '4065369',
'ext': 'flv',
'title': 'AVGN: Chronologically Confused about Bad Movie and Video Game Sequel Titles',
'upload_date': '20061207',
'uploader': 'cinemassacre',
'uploader_id': '250778',
'timestamp': 1283233867,
'description': 'md5:0a108c78d130676b207d0f6d029ecffd',
}
},
{
# Youtube embedded video
'url': 'http://cinemassacre.com/2006/09/01/mckids/',
'md5': '6eb30961fa795fedc750eac4881ad2e1',
'info_dict': {
'id': 'FnxsNhuikpo',
'ext': 'mp4',
'upload_date': '20060901',
'uploader': 'Cinemassacre Extras',
'description': 'md5:de9b751efa9e45fbaafd9c8a1123ed53',
'uploader_id': 'Cinemassacre',
'title': 'AVGN: McKids',
}
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
webpage = self._download_webpage(url, display_id)
playerdata_url = self._search_regex(
[
r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"',
],
webpage, 'player data URL', default=None)
if not playerdata_url:
playerdata_url = BlipTVIE._extract_url(webpage)
if not playerdata_url:
raise ExtractorError('Unable to find player data')
video_title = self._html_search_regex(
r'<title>(?P<title>.+?)\|', webpage, 'title')
video_description = self._html_search_regex(
r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, 'description', flags=re.DOTALL, fatal=False)
video_thumbnail = self._og_search_thumbnail(webpage)
return {
'_type': 'url_transparent',
'display_id': display_id,
'title': video_title,
'description': video_description,
'upload_date': video_date,
'thumbnail': video_thumbnail,
'url': playerdata_url,
}

View File

@@ -12,7 +12,7 @@ from ..utils import (
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
(?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
@@ -45,6 +45,12 @@ class CNNIE(InfoExtractor):
'description': 'md5:e7223a503315c9f150acac52e76de086',
'upload_date': '20141222',
}
}, {
'url': 'http://cnn.com/video/?/video/politics/2015/03/27/pkg-arizona-senator-church-attendance-mandatory.ktvk',
'only_matching': True,
}, {
'url': 'http://cnn.com/video/?/video/us/2015/04/06/dnt-baker-refuses-anti-gay-order.wkmg',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@@ -201,7 +201,7 @@ class ComedyCentralShowsIE(MTVServicesInfoExtractor):
uri = mMovieParams[0][1]
# Correct cc.com in uri
uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.com', uri)
index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
idoc = self._download_xml(

View File

@@ -23,6 +23,7 @@ from ..compat import (
)
from ..utils import (
age_restricted,
bug_reports_message,
clean_html,
compiled_regex_type,
ExtractorError,
@@ -324,7 +325,7 @@ class InfoExtractor(object):
self._downloader.report_warning(errmsg)
return False
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True):
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None, fatal=True, encoding=None):
""" Returns a tuple (page content as string, URL handle) """
# Strip hashes from the URL (#1038)
if isinstance(url_or_request, (compat_str, str)):
@@ -334,14 +335,11 @@ class InfoExtractor(object):
if urlh is False:
assert not fatal
return False
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal)
content = self._webpage_read_content(urlh, url_or_request, video_id, note, errnote, fatal, encoding=encoding)
return (content, urlh)
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
@staticmethod
def _guess_encoding_from_content(content_type, webpage_bytes):
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
if m:
encoding = m.group(1)
@@ -354,6 +352,16 @@ class InfoExtractor(object):
encoding = 'utf-16'
else:
encoding = 'utf-8'
return encoding
def _webpage_read_content(self, urlh, url_or_request, video_id, note=None, errnote=None, fatal=True, prefix=None, encoding=None):
content_type = urlh.headers.get('Content-Type', '')
webpage_bytes = urlh.read()
if prefix is not None:
webpage_bytes = prefix + webpage_bytes
if not encoding:
encoding = self._guess_encoding_from_content(content_type, webpage_bytes)
if self._downloader.params.get('dump_intermediate_pages', False):
try:
url = url_or_request.get_full_url()
@@ -410,13 +418,13 @@ class InfoExtractor(object):
return content
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5):
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
""" Returns the data of the page as a string """
success = False
try_count = 0
while success is False:
try:
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal)
res = self._download_webpage_handle(url_or_request, video_id, note, errnote, fatal, encoding=encoding)
success = True
except compat_http_client.IncompleteRead as e:
try_count += 1
@@ -431,10 +439,10 @@ class InfoExtractor(object):
def _download_xml(self, url_or_request, video_id,
note='Downloading XML', errnote='Unable to download XML',
transform_source=None, fatal=True):
transform_source=None, fatal=True, encoding=None):
"""Return the xml as an xml.etree.ElementTree.Element"""
xml_string = self._download_webpage(
url_or_request, video_id, note, errnote, fatal=fatal)
url_or_request, video_id, note, errnote, fatal=fatal, encoding=encoding)
if xml_string is False:
return xml_string
if transform_source:
@@ -445,9 +453,10 @@ class InfoExtractor(object):
note='Downloading JSON metadata',
errnote='Unable to download JSON metadata',
transform_source=None,
fatal=True):
fatal=True, encoding=None):
json_string = self._download_webpage(
url_or_request, video_id, note, errnote, fatal=fatal)
url_or_request, video_id, note, errnote, fatal=fatal,
encoding=encoding)
if (not fatal) and json_string is False:
return None
return self._parse_json(
@@ -492,7 +501,7 @@ class InfoExtractor(object):
# Methods for following #608
@staticmethod
def url_result(url, ie=None, video_id=None):
def url_result(url, ie=None, video_id=None, video_title=None):
"""Returns a url that points to a page that should be processed"""
# TODO: ie should be the class used for getting the info
video_info = {'_type': 'url',
@@ -500,6 +509,8 @@ class InfoExtractor(object):
'ie_key': ie}
if video_id is not None:
video_info['id'] = video_id
if video_title is not None:
video_info['title'] = video_title
return video_info
@staticmethod
@@ -546,8 +557,7 @@ class InfoExtractor(object):
elif fatal:
raise RegexNotFoundError('Unable to extract %s' % _name)
else:
self._downloader.report_warning('unable to extract %s; '
'please report this issue on http://yt-dl.org/bug' % _name)
self._downloader.report_warning('unable to extract %s' % _name + bug_reports_message())
return None
def _html_search_regex(self, pattern, string, name, default=_NO_DEFAULT, fatal=True, flags=0, group=None):
@@ -698,7 +708,7 @@ class InfoExtractor(object):
return self._html_search_meta('twitter:player', html,
'twitter card player')
def _sort_formats(self, formats):
def _sort_formats(self, formats, field_preference=None):
if not formats:
raise ExtractorError('No video formats found')
@@ -708,6 +718,9 @@ class InfoExtractor(object):
if not f.get('ext') and 'url' in f:
f['ext'] = determine_ext(f['url'])
if isinstance(field_preference, (list, tuple)):
return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)
preference = f.get('preference')
if preference is None:
proto = f.get('protocol')
@@ -822,7 +835,7 @@ class InfoExtractor(object):
(media_el.attrib.get('href') or media_el.attrib.get('url')))
tbr = int_or_none(media_el.attrib.get('bitrate'))
formats.append({
'format_id': '-'.join(filter(None, [f4m_id, 'f4m-%d' % (i if tbr is None else tbr)])),
'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])),
'url': manifest_url,
'ext': 'flv',
'tbr': tbr,

View File

@@ -11,39 +11,65 @@ from ..utils import (
class CrackedIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cracked\.com/video_(?P<id>\d+)_[\da-z-]+\.html'
_TEST = {
'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
'md5': '4b29a5eeec292cd5eca6388c7558db9e',
_TESTS = [{
'url': 'http://www.cracked.com/video_19070_if-animal-actors-got-e21-true-hollywood-stories.html',
'md5': '89b90b9824e3806ca95072c4d78f13f7',
'info_dict': {
'id': '19006',
'id': '19070',
'ext': 'mp4',
'title': '4 Plot Holes You Didn\'t Notice in Your Favorite Movies',
'description': 'md5:3b909e752661db86007d10e5ec2df769',
'timestamp': 1405659600,
'upload_date': '20140718',
'title': 'If Animal Actors Got E! True Hollywood Stories',
'timestamp': 1404954000,
'upload_date': '20140710',
}
}
}, {
# youtube embed
'url': 'http://www.cracked.com/video_19006_4-plot-holes-you-didnt-notice-in-your-favorite-movies.html',
'md5': 'ccd52866b50bde63a6ef3b35016ba8c7',
'info_dict': {
'id': 'EjI00A3rZD0',
'ext': 'mp4',
'title': "4 Plot Holes You Didn't Notice in Your Favorite Movies - The Spit Take",
'description': 'md5:c603708c718b796fe6079e2b3351ffc7',
'upload_date': '20140725',
'uploader_id': 'Cracked',
'uploader': 'Cracked',
}
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
youtube_url = self._search_regex(
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
webpage, 'youtube url', default=None)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
video_url = self._html_search_regex(
[r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'], webpage, 'video URL')
[r'var\s+CK_vidSrc\s*=\s*"([^"]+)"', r'<video\s+src="([^"]+)"'],
webpage, 'video URL')
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
title = self._search_regex(
[r'property="?og:title"?\s+content="([^"]+)"', r'class="?title"?>([^<]+)'],
webpage, 'title')
timestamp = self._html_search_regex(r'<time datetime="([^"]+)"', webpage, 'upload date', fatal=False)
description = self._search_regex(
r'name="?(?:og:)?description"?\s+content="([^"]+)"',
webpage, 'description', default=None)
timestamp = self._html_search_regex(
r'"date"\s*:\s*"([^"]+)"', webpage, 'upload date', fatal=False)
if timestamp:
timestamp = parse_iso8601(timestamp[:-6])
view_count = str_to_int(self._html_search_regex(
r'<span class="views" id="viewCounts">([\d,\.]+) Views</span>', webpage, 'view count', fatal=False))
r'<span\s+class="?views"? id="?viewCounts"?>([\d,\.]+) Views</span>',
webpage, 'view count', fatal=False))
comment_count = str_to_int(self._html_search_regex(
r'<span id="commentCounts">([\d,\.]+)</span>', webpage, 'comment count', fatal=False))
r'<span\s+id="?commentCounts"?>([\d,\.]+)</span>',
webpage, 'comment count', fatal=False))
m = re.search(r'_(?P<width>\d+)X(?P<height>\d+)\.mp4$', video_url)
if m:

View File

@@ -0,0 +1,60 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
qualities,
)
class CrooksAndLiarsIE(InfoExtractor):
_VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
'duration': 236,
}
}, {
'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
manifest = self._parse_json(
self._search_regex(
r'var\s+manifest\s*=\s*({.+?})\n', webpage, 'manifest JSON'),
video_id)
quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
formats = [{
'url': item['url'],
'format_id': item['type'],
'quality': quality(item['type']),
} for item in manifest['flavors'] if item['mime'].startswith('video/')]
self._sort_formats(formats)
return {
'url': url,
'id': video_id,
'title': manifest['title'],
'description': manifest.get('description'),
'thumbnail': self._proto_relative_url(manifest.get('poster')),
'timestamp': int_or_none(manifest.get('created')),
'uploader': manifest.get('author'),
'duration': int_or_none(manifest.get('duration')),
'formats': formats,
}

View File

@@ -23,7 +23,6 @@ from ..utils import (
)
from ..aes import (
aes_cbc_decrypt,
inc,
)
@@ -102,13 +101,6 @@ class CrunchyrollIE(InfoExtractor):
key = obfuscate_key(id)
class Counter:
__value = iv
def next_value(self):
temp = self.__value
self.__value = inc(self.__value)
return temp
decrypted_data = intlist_to_bytes(aes_cbc_decrypt(data, key, iv))
return zlib.decompress(decrypted_data)
@@ -271,8 +263,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
streamdata = self._download_xml(
streamdata_req, video_id,
note='Downloading media info for %s' % video_format)
video_url = streamdata.find('.//host').text
video_play_path = streamdata.find('.//file').text
video_url = streamdata.find('./host').text
video_play_path = streamdata.find('./file').text
formats.append({
'url': video_url,
'play_path': video_play_path,

View File

@@ -7,7 +7,10 @@ from ..utils import (
int_or_none,
unescapeHTML,
find_xpath_attr,
smuggle_url,
determine_ext,
)
from .senateisvp import SenateISVPIE
class CSpanIE(InfoExtractor):
@@ -35,11 +38,22 @@ class CSpanIE(InfoExtractor):
}
}, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
'md5': '446562a736c6bf97118e389433ed88d4',
'info_dict': {
'id': '342759',
'ext': 'mp4',
'title': 'General Motors Ignition Switch Recall',
'duration': 14848,
'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
},
'playlist_duration_sum': 14855,
}, {
# Video from senate.gov
'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
'info_dict': {
'id': 'judiciary031715',
'ext': 'flv',
'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
}
}]
def _real_extract(self, url):
@@ -56,7 +70,7 @@ class CSpanIE(InfoExtractor):
# present, otherwise this is a stripped version
r'<p class=\'initial\'>(.*?)</p>'
],
webpage, 'description', flags=re.DOTALL)
webpage, 'description', flags=re.DOTALL, default=None)
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
data = self._download_json(info_url, video_id)
@@ -68,7 +82,16 @@ class CSpanIE(InfoExtractor):
title = find_xpath_attr(doc, './/string', 'name', 'title').text
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
surl = smuggle_url(senate_isvp_url, {'force_title': title})
return self.url_result(surl, 'SenateISVP', video_id, title)
files = data['video']['files']
try:
capfile = data['video']['capfile']['#text']
except KeyError:
capfile = None
entries = [{
'id': '%s_%d' % (video_id, partnum + 1),
@@ -79,11 +102,22 @@ class CSpanIE(InfoExtractor):
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(f.get('length', {}).get('#text')),
'subtitles': {
'en': [{
'url': capfile,
'ext': determine_ext(capfile, 'dfxp')
}],
} if capfile else None,
} for partnum, f in enumerate(files)]
return {
'_type': 'playlist',
'entries': entries,
'title': title,
'id': video_id,
}
if len(entries) == 1:
entry = dict(entries[0])
entry['id'] = video_id
return entry
else:
return {
'_type': 'playlist',
'entries': entries,
'title': title,
'id': video_id,
}

View File

@@ -25,8 +25,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor):
def _build_request(url):
"""Build a request with the family filter disabled"""
request = compat_urllib_request.Request(url)
request.add_header('Cookie', 'family_filter=off')
request.add_header('Cookie', 'ff=off')
request.add_header('Cookie', 'family_filter=off; ff=off')
return request
@@ -112,8 +111,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
video_upload_date = mobj.group(3) + mobj.group(2) + mobj.group(1)
embed_url = 'http://www.dailymotion.com/embed/video/%s' % video_id
embed_page = self._download_webpage(embed_url, video_id,
'Downloading embed page')
embed_request = self._build_request(embed_url)
embed_page = self._download_webpage(
embed_request, video_id, 'Downloading embed page')
info = self._search_regex(r'var info = ({.*?}),$', embed_page,
'video info', flags=re.MULTILINE)
info = json.loads(info)
@@ -224,7 +224,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor):
class DailymotionUserIE(DailymotionPlaylistIE):
IE_NAME = 'dailymotion:user'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/user/(?P<user>[^/]+)'
_VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)'
_PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s'
_TESTS = [{
'url': 'https://www.dailymotion.com/user/nqtv',

View File

@@ -0,0 +1,73 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
xpath_text,
parse_duration,
)
class DHMIE(InfoExtractor):
IE_DESC = 'Filmarchiv - Deutsches Historisches Museum'
_VALID_URL = r'https?://(?:www\.)?dhm\.de/filmarchiv/(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.dhm.de/filmarchiv/die-filme/the-marshallplan-at-work-in-west-germany/',
'md5': '11c475f670209bf6acca0b2b7ef51827',
'info_dict': {
'id': 'the-marshallplan-at-work-in-west-germany',
'ext': 'flv',
'title': 'MARSHALL PLAN AT WORK IN WESTERN GERMANY, THE',
'description': 'md5:1fabd480c153f97b07add61c44407c82',
'duration': 660,
'thumbnail': 're:^https?://.*\.jpg$',
},
}, {
'url': 'http://www.dhm.de/filmarchiv/02-mapping-the-wall/peter-g/rolle-1/',
'md5': '09890226332476a3e3f6f2cb74734aa5',
'info_dict': {
'id': 'rolle-1',
'ext': 'flv',
'title': 'ROLLE 1',
'thumbnail': 're:^https?://.*\.jpg$',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist_url = self._search_regex(
r"file\s*:\s*'([^']+)'", webpage, 'playlist url')
playlist = self._download_xml(playlist_url, video_id)
track = playlist.find(
'./{http://xspf.org/ns/0/}trackList/{http://xspf.org/ns/0/}track')
video_url = xpath_text(
track, './{http://xspf.org/ns/0/}location',
'video url', fatal=True)
thumbnail = xpath_text(
track, './{http://xspf.org/ns/0/}image',
'thumbnail')
title = self._search_regex(
[r'dc:title="([^"]+)"', r'<title> &raquo;([^<]+)</title>'],
webpage, 'title').strip()
description = self._html_search_regex(
r'<p><strong>Description:</strong>(.+?)</p>',
webpage, 'description', default=None)
duration = parse_duration(self._search_regex(
r'<em>Length\s*</em>\s*:\s*</strong>([^<]+)',
webpage, 'duration', default=None))
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
}

View File

@@ -36,7 +36,8 @@ class DotsubIE(InfoExtractor):
if not video_url:
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'"file"\s*:\s*\'([^\']+)', webpage, 'video url')
[r'<source[^>]+src="([^"]+)"', r'"file"\s*:\s*\'([^\']+)'],
webpage, 'video url')
return {
'id': video_id,

View File

@@ -0,0 +1,112 @@
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import time
from .common import InfoExtractor
from ..utils import (ExtractorError, unescapeHTML)
from ..compat import (compat_str, compat_basestring)
class DouyuTVIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'http://www.douyutv.com/iseven',
'info_dict': {
'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}$',
'description': 'md5:c93d6692dde6fe33809a46edcbecca44',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': '7师傅',
'uploader_id': '431925',
'is_live': True,
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.douyutv.com/85982',
'info_dict': {
'id': '85982',
'display_id': '85982',
'ext': 'flv',
'title': 're:^小漠从零单排记——CSOL2躲猫猫 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'md5:746a2f7a253966a06755a912f0acc0d2',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'douyu小漠',
'uploader_id': '3769985',
'is_live': True,
},
'params': {
'skip_download': True,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id.isdigit():
room_id = video_id
else:
page = self._download_webpage(url, video_id)
room_id = self._html_search_regex(
r'"room_id"\s*:\s*(\d+),', page, 'room id')
prefix = 'room/%s?aid=android&client_sys=android&time=%d' % (
room_id, int(time.time()))
auth = hashlib.md5((prefix + '1231').encode('ascii')).hexdigest()
config = self._download_json(
'http://www.douyutv.com/api/v1/%s&auth=%s' % (prefix, auth),
video_id)
data = config['data']
error_code = config.get('error', 0)
if error_code is not 0:
error_desc = 'Server reported error %i' % error_code
if isinstance(data, (compat_str, compat_basestring)):
error_desc += ': ' + data
raise ExtractorError(error_desc, expected=True)
show_status = data.get('show_status')
# 1 = live, 2 = offline
if show_status == '2':
raise ExtractorError(
'Live stream is offline', expected=True)
base_url = data['rtmp_url']
live_path = data['rtmp_live']
title = self._live_title(unescapeHTML(data['room_name']))
description = data.get('show_details')
thumbnail = data.get('room_src')
uploader = data.get('nickname')
uploader_id = data.get('owner_uid')
multi_formats = data.get('rtmp_multi_bitrate')
if not isinstance(multi_formats, dict):
multi_formats = {}
multi_formats['live'] = live_path
formats = [{
'url': '%s/%s' % (base_url, format_path),
'format_id': format_id,
'preference': 1 if format_id == 'live' else 0,
} for format_id, format_path in multi_formats.items()]
self._sort_formats(formats)
return {
'id': room_id,
'display_id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
'is_live': True,
}

View File

@@ -3,22 +3,25 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import unified_strdate
from ..utils import (
ExtractorError,
unified_strdate,
)
class DreiSatIE(InfoExtractor):
IE_NAME = '3sat'
_VALID_URL = r'(?:http://)?(?:www\.)?3sat\.de/mediathek/(?:index\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)$'
_TEST = {
'url': 'http://www.3sat.de/mediathek/index.php?obj=36983',
'md5': '9dcfe344732808dbfcc901537973c922',
'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
'md5': 'be37228896d30a88f315b638900a026e',
'info_dict': {
'id': '36983',
'id': '45918',
'ext': 'mp4',
'title': 'Kaffeeland Schweiz',
'description': 'md5:cc4424b18b75ae9948b13929a0814033',
'title': 'Waidmannsheil',
'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
'uploader': '3sat',
'upload_date': '20130622'
'upload_date': '20140913'
}
}
@@ -28,6 +31,15 @@ class DreiSatIE(InfoExtractor):
details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id
details_doc = self._download_xml(details_url, video_id, 'Downloading video details')
status_code = details_doc.find('./status/statuscode')
if status_code is not None and status_code.text != 'ok':
code = status_code.text
if code == 'notVisibleAnymore':
message = 'Video %s is not available' % video_id
else:
message = '%s returned error: %s' % (self.IE_NAME, code)
raise ExtractorError(message, expected=True)
thumbnail_els = details_doc.findall('.//teaserimage')
thumbnails = [{
'width': int(te.attrib['key'].partition('x')[0]),

View File

@@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor, ExtractorError
@@ -8,16 +9,16 @@ class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
'md5': '4a7e1dd65cdb2643500a3f753c942f25',
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
'info_dict': {
'id': 'partiets-mand-7-8',
'id': 'panisk-paske-5',
'ext': 'mp4',
'title': 'Partiets mand (7:8)',
'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
'timestamp': 1403047940,
'upload_date': '20140617',
'duration': 1299.040,
'title': 'Panisk Påske (5)',
'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
'timestamp': 1426984612,
'upload_date': '20150322',
'duration': 1455,
},
}
@@ -26,6 +27,10 @@ class DRTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if '>Programmet er ikke længere tilgængeligt' in webpage:
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
webpage, 'video id')

View File

@@ -28,12 +28,12 @@ class DumpIE(InfoExtractor):
video_url = self._search_regex(
r's1.addVariable\("file",\s*"([^"]+)"', webpage, 'video URL')
thumb = self._og_search_thumbnail(webpage)
title = self._search_regex(r'<b>([^"]+)</b>', webpage, 'title')
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
return {
'id': video_id,
'title': title,
'url': video_url,
'thumbnail': thumb,
'thumbnail': thumbnail,
}

View File

@@ -0,0 +1,60 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import qualities
class DumpertIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
_TEST = {
'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
'info_dict': {
'id': '6646981/951bc60f',
'ext': 'mp4',
'title': 'Ik heb nieuws voor je',
'description': 'Niet schrikken hoor',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
req = compat_urllib_request.Request(url)
req.add_header('Cookie', 'nsfw=1')
webpage = self._download_webpage(req, video_id)
files_base64 = self._search_regex(
r'data-files="([^"]+)"', webpage, 'data files')
files = self._parse_json(
base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
video_id)
quality = qualities(['flv', 'mobile', 'tablet', '720p'])
formats = [{
'url': video_url,
'format_id': format_id,
'quality': quality(format_id),
} for format_id, video_url in files.items() if format_id != 'still']
self._sort_formats(formats)
title = self._html_search_meta(
'title', webpage) or self._og_search_title(webpage)
description = self._html_search_meta(
'description', webpage) or self._og_search_description(webpage)
thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'formats': formats
}

View File

@@ -45,6 +45,7 @@ class EaglePlatformIE(InfoExtractor):
'duration': 216,
'view_count': int,
},
'skip': 'Georestricted',
}]
def _handle_error(self, response):

View File

@@ -6,56 +6,42 @@ import json
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_iso8601,
)
class EllenTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
_TESTS = [{
'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
'md5': 'e4af06f3bf0d5f471921a18db5764642',
_TEST = {
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
'info_dict': {
'id': '0-7jqrsr18',
'id': '0_ipq1gsai',
'ext': 'mp4',
'title': 'What\'s Wrong with These Photos? A Whole Lot',
'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
'timestamp': 1406876400,
'upload_date': '20140801',
'title': 'Fast Fingers of Fate',
'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
'timestamp': 1428035648,
'upload_date': '20150403',
'uploader_id': 'batchUser',
}
}, {
'url': 'http://ellentube.com/videos/0-dvzmabd5/',
'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
'info_dict': {
'id': '0-dvzmabd5',
'ext': 'mp4',
'title': '1 year old twin sister makes her brother laugh',
'description': '1 year old twin sister makes her brother laugh',
'timestamp': 1419542075,
'upload_date': '20141225',
}
}]
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._html_search_meta('VideoURL', webpage, 'url')
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
description = self._html_search_meta(
'description', webpage, 'description') or self._og_search_description(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<span class="publish-date"><time datetime="([^"]+)">',
webpage, 'timestamp'))
webpage = self._download_webpage(
'http://widgets.ellentube.com/videos/%s' % video_id,
video_id)
return {
'id': video_id,
'url': video_url,
'title': title,
'description': description,
'timestamp': timestamp,
}
partner_id = self._search_regex(
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
kaltura_id = self._search_regex(
[r'id="kaltura_player_([^"]+)"',
r"_wb_entry_id\s*:\s*'([^']+)",
r'data-kaltura-entry-id="([^"]+)'],
webpage, 'kaltura id')
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
class EllenTVClipsIE(InfoExtractor):
@@ -67,7 +53,7 @@ class EllenTVClipsIE(InfoExtractor):
'id': 'meryl-streep-vanessa-hudgens',
'title': 'Meryl Streep, Vanessa Hudgens',
},
'playlist_mincount': 9,
'playlist_mincount': 7,
}
def _real_extract(self, url):
@@ -91,4 +77,8 @@ class EllenTVClipsIE(InfoExtractor):
raise ExtractorError('Failed to download JSON', cause=ve)
def _extract_entries(self, playlist):
return [self.url_result(item['url'], 'EllenTV') for item in playlist]
return [
self.url_result(
'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
'Kaltura')
for item in playlist]

View File

@@ -1,11 +1,17 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import ExtractorError
class EroProfileIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?eroprofile\.com/m/videos/view/(?P<id>[^/]+)'
_TEST = {
_LOGIN_URL = 'http://www.eroprofile.com/auth/auth.php?'
_NETRC_MACHINE = 'eroprofile'
_TESTS = [{
'url': 'http://www.eroprofile.com/m/videos/view/sexy-babe-softcore',
'md5': 'c26f351332edf23e1ea28ce9ec9de32f',
'info_dict': {
@@ -16,13 +22,55 @@ class EroProfileIE(InfoExtractor):
'thumbnail': 're:https?://.*\.jpg',
'age_limit': 18,
}
}
}, {
'url': 'http://www.eroprofile.com/m/videos/view/Try-It-On-Pee_cut_2-wmv-4shared-com-file-sharing-download-movie-file',
'md5': '1baa9602ede46ce904c431f5418d8916',
'info_dict': {
'id': '1133519',
'ext': 'm4v',
'title': 'Try It On Pee_cut_2.wmv - 4shared.com - file sharing - download movie file',
'thumbnail': 're:https?://.*\.jpg',
'age_limit': 18,
},
'skip': 'Requires login',
}]
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
query = compat_urllib_parse.urlencode({
'username': username,
'password': password,
'url': 'http://www.eroprofile.com/',
})
login_url = self._LOGIN_URL + query
login_page = self._download_webpage(login_url, None, False)
m = re.search(r'Your username or password was incorrect\.', login_page)
if m:
raise ExtractorError(
'Wrong username and/or password.', expected=True)
self.report_login()
redirect_url = self._search_regex(
r'<script[^>]+?src="([^"]+)"', login_page, 'login redirect url')
self._download_webpage(redirect_url, None, False)
def _real_initialize(self):
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
m = re.search(r'You must be logged in to view this video\.', webpage)
if m:
raise ExtractorError(
'This video requires login. Please specify a username and password and try again.', expected=True)
video_id = self._search_regex(
[r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'],
webpage, 'video id', default=None)

View File

@@ -1,128 +1,105 @@
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
js_to_json,
parse_duration,
determine_ext,
clean_html,
qualities,
)
def _decrypt_config(key, string):
a = ''
i = ''
r = ''
while len(a) < (len(string) / 2):
a += key
a = a[0:int(len(string) / 2)]
t = 0
while t < len(string):
i += chr(int(string[t] + string[t + 1], 16))
t += 2
icko = [s for s in i]
for t, c in enumerate(a):
r += chr(ord(c) ^ ord(icko[t]))
return r
class EscapistIE(InfoExtractor):
_VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
_USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko'
_TEST = {
_TESTS = [{
'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
'md5': 'c6793dbda81388f4264c1ba18684a74d',
'info_dict': {
'id': '6618',
'ext': 'mp4',
'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
'uploader_id': 'the-escapist-presents',
'uploader': 'The Escapist Presents',
'title': "Breaking Down Baldur's Gate",
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 264,
}
}
}, {
'url': 'http://www.escapistmagazine.com/videos/view/zero-punctuation/10044-Evolve-One-vs-Multiplayer',
'md5': 'cf8842a8a46444d241f9a9980d7874f2',
'info_dict': {
'id': '10044',
'ext': 'mp4',
'description': 'This week, Zero Punctuation reviews Evolve.',
'title': 'Evolve - One vs Multiplayer',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 304,
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage_req = compat_urllib_request.Request(url)
webpage_req.add_header('User-Agent', self._USER_AGENT)
webpage = self._download_webpage(webpage_req, video_id)
webpage = self._download_webpage(url, video_id)
uploader_id = self._html_search_regex(
r"<h1\s+class='headline'>\s*<a\s+href='/videos/view/(.*?)'",
webpage, 'uploader ID', fatal=False)
uploader = self._html_search_regex(
r"<h1\s+class='headline'>(.*?)</a>",
webpage, 'uploader', fatal=False)
description = self._html_search_meta('description', webpage)
duration = parse_duration(self._html_search_meta('duration', webpage))
imsVideo = self._parse_json(
self._search_regex(
r'imsVideo\.play\(({.+?})\);', webpage, 'imsVideo'),
video_id)
video_id = imsVideo['videoID']
key = imsVideo['hash']
raw_title = self._html_search_meta('title', webpage, fatal=True)
title = raw_title.partition(' : ')[2]
config_url = compat_urllib_parse.unquote(self._html_search_regex(
r'''(?x)
(?:
<param\s+name="flashvars".*?\s+value="config=|
flashvars=&quot;config=
)
(https?://[^"&]+)
''',
webpage, 'config URL'))
quality = qualities(['lq', 'hq', 'hd'])
formats = []
ad_formats = []
for q in ['lq', 'hq', 'hd']:
config_req = compat_urllib_request.Request('http://www.escapistmagazine.com/videos/'
'vidconfig.php?videoID=%s&hash=%s&quality=%s' % (video_id, key, 'mp4_' + q))
config_req.add_header('Referer', url)
config = self._download_webpage(config_req, video_id, 'Downloading video config ' + q.upper())
def _add_format(name, cfg_url, quality):
cfg_req = compat_urllib_request.Request(cfg_url)
cfg_req.add_header('User-Agent', self._USER_AGENT)
config = self._download_json(
cfg_req, video_id,
'Downloading ' + name + ' configuration',
'Unable to download ' + name + ' configuration',
transform_source=js_to_json)
data = json.loads(_decrypt_config(key, config))
playlist = config['playlist']
for p in playlist:
if p.get('eventCategory') == 'Video':
ar = formats
elif p.get('eventCategory') == 'Video Postroll':
ar = ad_formats
else:
continue
title = clean_html(data['videoData']['title'])
duration = data['videoData']['duration'] / 1000
ar.append({
'url': p['url'],
'format_id': name,
'quality': quality,
'http_headers': {
'User-Agent': self._USER_AGENT,
},
})
for i, v in enumerate(data['files']['videos']):
_add_format('normal', config_url, quality=0)
hq_url = (config_url +
('&hq=1' if '?' in config_url else config_url + '?hq=1'))
try:
_add_format('hq', hq_url, quality=1)
except ExtractorError:
pass # That's fine, we'll just use normal quality
self._sort_formats(formats)
formats.append({
'url': v,
'format_id': determine_ext(v) + '_' + q + str(i),
'quality': quality(q),
})
if '/escapist/sales-marketing/' in formats[-1]['url']:
raise ExtractorError('This IP address has been blocked by The Escapist', expected=True)
res = {
return {
'id': video_id,
'formats': formats,
'uploader': uploader,
'uploader_id': uploader_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'description': description,
'description': self._og_search_description(webpage),
'duration': duration,
}
if self._downloader.params.get('include_ads') and ad_formats:
self._sort_formats(ad_formats)
ad_res = {
'id': '%s-ad' % video_id,
'title': '%s (Postroll)' % title,
'formats': ad_formats,
}
return {
'_type': 'playlist',
'entries': [res, ad_res],
'title': title,
'id': video_id,
}
return res

View File

@@ -24,8 +24,12 @@ class FacebookIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://(?:\w+\.)?facebook\.com/
(?:[^#]*?\#!/)?
(?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
(?:v|video_id)=(?P<id>[0-9]+)
(?:
(?:video/video\.php|photo\.php|video\.php|video/embed)\?(?:.*?)
(?:v|video_id)=|
[^/]+/videos/(?:[^/]+/)?
)
(?P<id>[0-9]+)
(?:.*)'''
_LOGIN_URL = 'https://www.facebook.com/login.php?next=http%3A%2F%2Ffacebook.com%2Fhome.php&login_attempt=1'
_CHECKPOINT_URL = 'https://www.facebook.com/checkpoint/?next=http%3A%2F%2Ffacebook.com%2Fhome.php&_fb_noscript=1'
@@ -50,6 +54,12 @@ class FacebookIE(InfoExtractor):
}, {
'url': 'https://www.facebook.com/video.php?v=10204634152394104',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/amogood/videos/1618742068337349/?fref=nf',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/ChristyClarkForBC/videos/vb.22819070941/10153870694020942/?type=2&theater',
'only_matching': True,
}]
def _login(self):

View File

@@ -3,9 +3,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
ExtractorError,
unescapeHTML,
find_xpath_attr,
)
@@ -29,25 +30,31 @@ class FlickrIE(InfoExtractor):
video_id = mobj.group('id')
video_uploader_id = mobj.group('uploader_id')
webpage_url = 'http://www.flickr.com/photos/' + video_uploader_id + '/' + video_id
webpage = self._download_webpage(webpage_url, video_id)
req = compat_urllib_request.Request(webpage_url)
req.add_header(
'User-Agent',
# it needs a more recent version
'Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20150101 Firefox/38.0 (Chrome)')
webpage = self._download_webpage(req, video_id)
secret = self._search_regex(r"photo_secret: '(\w+)'", webpage, 'secret')
secret = self._search_regex(r'secret"\s*:\s*"(\w+)"', webpage, 'secret')
first_url = 'https://secure.flickr.com/apps/video/video_mtl_xml.gne?v=x&photo_id=' + video_id + '&secret=' + secret + '&bitrate=700&target=_self'
first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage')
first_xml = self._download_xml(first_url, video_id, 'Downloading first data webpage')
node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>',
first_xml, 'node_id')
node_id = find_xpath_attr(
first_xml, './/{http://video.yahoo.com/YEP/1.0/}Item', 'id',
'id').text
second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1'
second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage')
second_xml = self._download_xml(second_url, video_id, 'Downloading second data webpage')
self.report_extraction(video_id)
mobj = re.search(r'<STREAM APP="(.+?)" FULLPATH="(.+?)"', second_xml)
if mobj is None:
stream = second_xml.find('.//STREAM')
if stream is None:
raise ExtractorError('Unable to extract video url')
video_url = mobj.group(1) + unescapeHTML(mobj.group(2))
video_url = stream.attrib['APP'] + stream.attrib['FULLPATH']
return {
'id': video_id,

View File

@@ -6,14 +6,21 @@ from .common import InfoExtractor
class FootyRoomIE(InfoExtractor):
_VALID_URL = r'http://footyroom\.com/(?P<id>[^/]+)'
_TEST = {
_TESTS = [{
'url': 'http://footyroom.com/schalke-04-0-2-real-madrid-2015-02/',
'info_dict': {
'id': 'schalke-04-0-2-real-madrid-2015-02',
'title': 'Schalke 04 0 2 Real Madrid',
},
'playlist_count': 3,
}
}, {
'url': 'http://footyroom.com/georgia-0-2-germany-2015-03/',
'info_dict': {
'id': 'georgia-0-2-germany-2015-03',
'title': 'Georgia 0 2 Germany',
},
'playlist_count': 1,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
@@ -36,6 +43,7 @@ class FootyRoomIE(InfoExtractor):
r'data-config="([^"]+)"', payload,
'playwire url', default=None)
if playwire_url:
entries.append(self.url_result(playwire_url, 'Playwire'))
entries.append(self.url_result(self._proto_relative_url(
playwire_url, 'http:'), 'Playwire'))
return self.playlist_result(entries, playlist_id, playlist_title)

View File

@@ -14,7 +14,9 @@ from ..utils import (
clean_html,
ExtractorError,
int_or_none,
float_or_none,
parse_duration,
determine_ext,
)
@@ -50,7 +52,8 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
if not video_url:
continue
format_id = video['format']
if video_url.endswith('.f4m'):
ext = determine_ext(video_url)
if ext == 'f4m':
if georestricted:
# See https://github.com/rg3/youtube-dl/issues/3963
# m3u8 urls work fine
@@ -60,12 +63,9 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path,
video_id, 'Downloading f4m manifest token', fatal=False)
if f4m_url:
f4m_formats = self._extract_f4m_formats(f4m_url, video_id)
for f4m_format in f4m_formats:
f4m_format['preference'] = 1
formats.extend(f4m_formats)
elif video_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
elif video_url.startswith('rtmp'):
formats.append({
'url': video_url,
@@ -86,7 +86,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
'title': info['titre'],
'description': clean_html(info['synopsis']),
'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
'duration': parse_duration(info['duree']),
'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']),
'timestamp': int_or_none(info['diffusion']['timestamp']),
'formats': formats,
}
@@ -260,22 +260,28 @@ class CultureboxIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'
_TEST = {
'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553',
'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6',
'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
'info_dict': {
'id': 'EV_22853',
'id': 'EV_50111',
'ext': 'flv',
'title': 'Dans les jardins de William Christie - Le Camus',
'description': 'md5:4710c82315c40f0c865ca8b9a68b5299',
'upload_date': '20140829',
'timestamp': 1409317200,
'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
'upload_date': '20150320',
'timestamp': 1426892400,
'duration': 2760.9,
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
webpage = self._download_webpage(url, name)
if ">Ce live n'est plus disponible en replay<" in webpage:
raise ExtractorError('Video %s is not available' % name, expected=True)
video_id, catalogue = self._search_regex(
r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')

View File

@@ -0,0 +1,70 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
js_to_json,
parse_duration,
remove_start,
)
class GamersydeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gamersyde\.com/hqstream_(?P<display_id>[\da-z_]+)-(?P<id>\d+)_[a-z]{2}\.html'
_TEST = {
'url': 'http://www.gamersyde.com/hqstream_bloodborne_birth_of_a_hero-34371_en.html',
'md5': 'f38d400d32f19724570040d5ce3a505f',
'info_dict': {
'id': '34371',
'ext': 'mp4',
'duration': 372,
'title': 'Bloodborne - Birth of a hero',
'thumbnail': 're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
playlist = self._parse_json(
self._search_regex(
r'(?s)playlist: \[({.+?})\]\s*}\);', webpage, 'files'),
display_id, transform_source=js_to_json)
formats = []
for source in playlist['sources']:
video_url = source.get('file')
if not video_url:
continue
format_id = source.get('label')
f = {
'url': video_url,
'format_id': format_id,
}
m = re.search(r'^(?P<height>\d+)[pP](?P<fps>\d+)fps', format_id)
if m:
f.update({
'height': int(m.group('height')),
'fps': int(m.group('fps')),
})
formats.append(f)
self._sort_formats(formats)
title = remove_start(playlist['title'], '%s - ' % video_id)
thumbnail = playlist.get('image')
duration = parse_duration(self._search_regex(
r'Length:</label>([^<]+)<', webpage, 'duration', fatal=False))
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
}

View File

@@ -11,7 +11,7 @@ from ..utils import remove_end
class GDCVaultIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)'
_VALID_URL = r'https?://(?:www\.)?gdcvault\.com/play/(?P<id>\d+)/(?P<name>(\w|-)+)?'
_NETRC_MACHINE = 'gdcvault'
_TESTS = [
{
@@ -19,6 +19,7 @@ class GDCVaultIE(InfoExtractor):
'md5': '7ce8388f544c88b7ac11c7ab1b593704',
'info_dict': {
'id': '1019721',
'display_id': 'Doki-Doki-Universe-Sweet-Simple',
'ext': 'mp4',
'title': 'Doki-Doki Universe: Sweet, Simple and Genuine (GDC Next 10)'
}
@@ -27,6 +28,7 @@ class GDCVaultIE(InfoExtractor):
'url': 'http://www.gdcvault.com/play/1015683/Embracing-the-Dark-Art-of',
'info_dict': {
'id': '1015683',
'display_id': 'Embracing-the-Dark-Art-of',
'ext': 'flv',
'title': 'Embracing the Dark Art of Mathematical Modeling in AI'
},
@@ -39,10 +41,15 @@ class GDCVaultIE(InfoExtractor):
'md5': 'a5eb77996ef82118afbbe8e48731b98e',
'info_dict': {
'id': '1015301',
'display_id': 'Thexder-Meets-Windows-95-or',
'ext': 'flv',
'title': 'Thexder Meets Windows 95, or Writing Great Games in the Windows 95 Environment',
},
'skip': 'Requires login',
},
{
'url': 'http://gdcvault.com/play/1020791/',
'only_matching': True,
}
]
@@ -90,7 +97,7 @@ class GDCVaultIE(InfoExtractor):
})
return video_formats
def _login(self, webpage_url, video_id):
def _login(self, webpage_url, display_id):
(username, password) = self._get_login_info()
if username is None or password is None:
self.report_warning('It looks like ' + webpage_url + ' requires a login. Try specifying a username and password and try again.')
@@ -107,9 +114,9 @@ class GDCVaultIE(InfoExtractor):
request = compat_urllib_request.Request(login_url, compat_urllib_parse.urlencode(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(request, video_id, 'Logging in')
start_page = self._download_webpage(webpage_url, video_id, 'Getting authenticated video page')
self._download_webpage(logout_url, video_id, 'Logging out')
self._download_webpage(request, display_id, 'Logging in')
start_page = self._download_webpage(webpage_url, display_id, 'Getting authenticated video page')
self._download_webpage(logout_url, display_id, 'Logging out')
return start_page
@@ -117,8 +124,10 @@ class GDCVaultIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('name') or video_id
webpage_url = 'http://www.gdcvault.com/play/' + video_id
start_page = self._download_webpage(webpage_url, video_id)
start_page = self._download_webpage(webpage_url, display_id)
direct_url = self._search_regex(
r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);',
@@ -131,6 +140,7 @@ class GDCVaultIE(InfoExtractor):
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': 'flv',
'title': title,
@@ -141,7 +151,7 @@ class GDCVaultIE(InfoExtractor):
start_page, 'xml root', default=None)
if xml_root is None:
# Probably need to authenticate
login_res = self._login(webpage_url, video_id)
login_res = self._login(webpage_url, display_id)
if login_res is None:
self.report_warning('Could not login.')
else:
@@ -159,7 +169,7 @@ class GDCVaultIE(InfoExtractor):
xml_name = self._html_search_regex(r'<iframe src=".*?\?xmlURL=xml/(?P<xml_file>.+?\.xml).*?".*?</iframe>', start_page, 'xml filename')
xml_decription_url = xml_root + 'xml/' + xml_name
xml_description = self._download_xml(xml_decription_url, video_id)
xml_description = self._download_xml(xml_decription_url, display_id)
video_title = xml_description.find('./metadata/title').text
video_formats = self._parse_mp4(xml_description)
@@ -168,6 +178,7 @@ class GDCVaultIE(InfoExtractor):
return {
'id': video_id,
'display_id': display_id,
'title': video_title,
'formats': video_formats,
}

View File

@@ -29,10 +29,14 @@ from ..utils import (
xpath_text,
)
from .brightcove import BrightcoveIE
from .nbc import NBCSportsVPlayerIE
from .ooyala import OoyalaIE
from .rutv import RUTVIE
from .smotri import SmotriIE
from .condenast import CondeNastIE
from .udn import UDNEmbedIE
from .senateisvp import SenateISVPIE
from .bliptv import BlipTVIE
class GenericIE(InfoExtractor):
@@ -527,6 +531,17 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Viddler'],
},
# Libsyn embed
{
'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
'info_dict': {
'id': '3377616',
'ext': 'mp3',
'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220',
},
},
# jwplayer YouTube
{
'url': 'http://media.nationalarchives.gov.uk/index.php/webinar-using-discovery-national-archives-online-catalogue/',
@@ -602,13 +617,34 @@ class GenericIE(InfoExtractor):
'info_dict': {
'id': '100183293',
'ext': 'mp4',
'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 694,
'age_limit': 0,
},
},
# Playwire embed
{
'url': 'http://www.cinemablend.com/new/First-Joe-Dirt-2-Trailer-Teaser-Stupid-Greatness-70874.html',
'info_dict': {
'id': '3519514',
'ext': 'mp4',
'title': 'Joe Dirt 2 Beautiful Loser Teaser Trailer',
'thumbnail': 're:^https?://.*\.png$',
'duration': 45.115,
},
},
# 5min embed
{
'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
'info_dict': {
'id': '518726732',
'ext': 'mp4',
'title': 'Facebook Creates "On This Day" | Crunch Report',
},
},
# RSS feed with enclosure
{
'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml',
@@ -618,6 +654,81 @@ class GenericIE(InfoExtractor):
'upload_date': '20150228',
'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624',
}
},
# Crooks and Liars embed
{
'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
'info_dict': {
'id': '8RUoRhRi',
'ext': 'mp4',
'title': "Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!",
'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
'timestamp': 1428207000,
'upload_date': '20150405',
'uploader': 'Heather',
},
},
# Crooks and Liars external embed
{
'url': 'http://theothermccain.com/2010/02/02/video-proves-that-bill-kristol-has-been-watching-glenn-beck/comment-page-1/',
'info_dict': {
'id': 'MTE3MjUtMzQ2MzA',
'ext': 'mp4',
'title': 'md5:5e3662a81a4014d24c250d76d41a08d5',
'description': 'md5:9b8e9542d6c3c5de42d6451b7d780cec',
'timestamp': 1265032391,
'upload_date': '20100201',
'uploader': 'Heather',
},
},
# NBC Sports vplayer embed
{
'url': 'http://www.riderfans.com/forum/showthread.php?121827-Freeman&s=e98fa1ea6dc08e886b1678d35212494a',
'info_dict': {
'id': 'ln7x1qSThw4k',
'ext': 'flv',
'title': "PFT Live: New leader in the 'new-look' defense",
'description': 'md5:65a19b4bbfb3b0c0c5768bed1dfad74e',
},
},
# UDN embed
{
'url': 'http://www.udn.com/news/story/7314/822787',
'md5': 'fd2060e988c326991037b9aff9df21a6',
'info_dict': {
'id': '300346',
'ext': 'mp4',
'title': '中一中男師變性 全校師生力挺',
'thumbnail': 're:^https?://.*\.jpg$',
}
},
# Ooyala embed
{
'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
'info_dict': {
'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs',
'ext': 'mp4',
'description': 'VIDEO: Index/Match versus VLOOKUP.',
'title': 'This is what separates the Excel masters from the wannabes',
},
'params': {
# m3u8 downloads
'skip_download': True,
}
},
# Contains a SMIL manifest
{
'url': 'http://www.telewebion.com/fa/1263668/%D9%82%D8%B1%D8%B9%D9%87%E2%80%8C%DA%A9%D8%B4%DB%8C-%D9%84%DB%8C%DA%AF-%D9%82%D9%87%D8%B1%D9%85%D8%A7%D9%86%D8%A7%D9%86-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7/%2B-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84.html',
'info_dict': {
'id': 'file',
'ext': 'flv',
'title': '+ Football: Lottery Champions League Europe',
'uploader': 'www.telewebion.com',
},
'params': {
# rtmpe downloads
'skip_download': True,
}
}
]
@@ -963,12 +1074,9 @@ class GenericIE(InfoExtractor):
}
# Look for embedded blip.tv player
mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
if mobj:
return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV')
mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage)
if mobj:
return self.url_result(mobj.group(1), 'BlipTV')
bliptv_url = BlipTVIE._extract_url(webpage)
if bliptv_url:
return self.url_result(bliptv_url, 'BlipTV')
# Look for embedded condenast player
matches = re.findall(
@@ -1006,10 +1114,24 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for NYTimes player
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for Libsyn player
mobj = re.search(
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//html5-player\.libsyn\.com/embed/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for Ooyala videos
mobj = (re.search(r'player\.ooyala\.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or
re.search(r'OO\.Player\.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage) or
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage))
re.search(r'SBN\.VideoLinkset\.ooyala\([\'"](?P<ec>.{32})[\'"]\)', webpage) or
re.search(r'data-ooyala-video-id\s*=\s*[\'"](?P<ec>.{32})[\'"]', webpage))
if mobj is not None:
return OoyalaIE._build_url_result(mobj.group('ec'))
@@ -1212,6 +1334,41 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'), 'Pladform')
# Look for Playwire embeds
mobj = re.search(
r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for 5min embeds
mobj = re.search(
r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
if mobj is not None:
return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
# Look for Crooks and Liars embeds
mobj = re.search(
r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for NBC Sports VPlayer embeds
nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage)
if nbc_sports_url:
return self.url_result(nbc_sports_url, 'NBCSportsVPlayer')
# Look for UDN embeds
mobj = re.search(
r'<iframe[^>]+src="(?P<url>%s)"' % UDNEmbedIE._VALID_URL, webpage)
if mobj is not None:
return self.url_result(
compat_urlparse.urljoin(url, mobj.group('url')), 'UDNEmbed')
# Look for Senate ISVP iframe
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url:
return self.url_result(surl, 'SenateISVP')
def check_video(vurl):
if YoutubeIE.suitable(vurl):
return True
@@ -1268,10 +1425,16 @@ class GenericIE(InfoExtractor):
# HTML5 video
found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage)
if not found:
REDIRECT_REGEX = r'[0-9]{,2};\s*(?:URL|url)=\'?([^\'"]+)'
found = re.search(
r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")'
r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)',
r'(?:[a-z-]+="[^"]+"\s+)*?content="%s' % REDIRECT_REGEX,
webpage)
if not found:
# Look also in Refresh HTTP header
refresh_header = head_response.headers.get('Refresh')
if refresh_header:
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
new_url = found.group(1)
self.report_following_redirect(new_url)
@@ -1295,13 +1458,22 @@ class GenericIE(InfoExtractor):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
entries.append({
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
})
if determine_ext(video_url) == 'smil':
entries.append({
'id': video_id,
'formats': self._extract_smil_formats(video_url, video_id),
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
})
else:
entries.append({
'id': video_id,
'url': video_url,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
})
if len(entries) == 1:
return entries[0]

View File

@@ -0,0 +1,90 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
qualities,
)
class GfycatIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gfycat\.com/(?P<id>[^/?#]+)'
_TEST = {
'url': 'http://gfycat.com/DeadlyDecisiveGermanpinscher',
'info_dict': {
'id': 'DeadlyDecisiveGermanpinscher',
'ext': 'mp4',
'title': 'Ghost in the Shell',
'timestamp': 1410656006,
'upload_date': '20140914',
'uploader': 'anonymous',
'duration': 10.4,
'view_count': int,
'like_count': int,
'dislike_count': int,
'categories': list,
'age_limit': 0,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
gfy = self._download_json(
'http://gfycat.com/cajax/get/%s' % video_id,
video_id, 'Downloading video info')['gfyItem']
title = gfy.get('title') or gfy['gfyName']
description = gfy.get('description')
timestamp = int_or_none(gfy.get('createDate'))
uploader = gfy.get('userName')
view_count = int_or_none(gfy.get('views'))
like_count = int_or_none(gfy.get('likes'))
dislike_count = int_or_none(gfy.get('dislikes'))
age_limit = 18 if gfy.get('nsfw') == '1' else 0
width = int_or_none(gfy.get('width'))
height = int_or_none(gfy.get('height'))
fps = int_or_none(gfy.get('frameRate'))
num_frames = int_or_none(gfy.get('numFrames'))
duration = float_or_none(num_frames, fps) if num_frames and fps else None
categories = gfy.get('tags') or gfy.get('extraLemmas') or []
FORMATS = ('gif', 'webm', 'mp4')
quality = qualities(FORMATS)
formats = []
for format_id in FORMATS:
video_url = gfy.get('%sUrl' % format_id)
if not video_url:
continue
filesize = gfy.get('%sSize' % format_id)
formats.append({
'url': video_url,
'format_id': format_id,
'width': width,
'height': height,
'fps': fps,
'filesize': filesize,
'quality': quality(format_id),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'categories': categories,
'age_limit': age_limit,
'formats': formats,
}

View File

@@ -15,10 +15,10 @@ from ..utils import (
class GorillaVidIE(InfoExtractor):
IE_DESC = 'GorillaVid.in, daclips.in, movpod.in and fastvideo.in'
IE_DESC = 'GorillaVid.in, daclips.in, movpod.in, fastvideo.in and realvid.net'
_VALID_URL = r'''(?x)
https?://(?P<host>(?:www\.)?
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/
(?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in|realvid\.net))/
(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?
'''
@@ -61,6 +61,15 @@ class GorillaVidIE(InfoExtractor):
'title': 'Man of Steel - Trailer',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://realvid.net/ctn2y6p2eviw',
'md5': 'b2166d2cf192efd6b6d764c18fd3710e',
'info_dict': {
'id': 'ctn2y6p2eviw',
'ext': 'flv',
'title': 'rdx 1955',
'thumbnail': 're:http://.*\.jpg',
},
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'only_matching': True,
@@ -97,7 +106,7 @@ class GorillaVidIE(InfoExtractor):
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = self._search_regex(
r'style="z-index: [0-9]+;">([^<]+)</span>',
[r'style="z-index: [0-9]+;">([^<]+)</span>', r'>Watch (.+) '],
webpage, 'title', default=None) or self._og_search_title(webpage)
video_url = self._search_regex(
r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url')

View File

@@ -140,9 +140,9 @@ class GroovesharkIE(InfoExtractor):
if webpage is not None:
o = GroovesharkHtmlParser.extract_object_tags(webpage)
return (webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed'])
return webpage, [x for x in o if x['attrs']['id'] == 'jsPlayerEmbed']
return (webpage, None)
return webpage, None
def _real_initialize(self):
self.ts = int(time.time() * 1000) # timestamp in millis
@@ -154,7 +154,7 @@ class GroovesharkIE(InfoExtractor):
swf_referer = None
if self.do_playerpage_request:
(_, player_objs) = self._get_playerpage(url)
if player_objs is not None:
if player_objs:
swf_referer = self._build_swf_referer(url, player_objs[0])
self.to_screen('SWF Referer: %s' % swf_referer)

View File

@@ -10,6 +10,7 @@ from ..utils import (
float_or_none,
int_or_none,
compat_str,
determine_ext,
)
@@ -42,7 +43,8 @@ class HitboxIE(InfoExtractor):
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)
'%s/%s' % (url, video_id), video_id,
'Downloading metadata JSON')
date = 'media_live_since'
media_type = 'livestream'
@@ -87,21 +89,41 @@ class HitboxIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
player_config = self._download_json(
'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
video_id, 'Downloading video JSON')
formats = []
for video in player_config['clip']['bitrates']:
label = video.get('label')
if label == 'Auto':
continue
video_url = video.get('url')
if not video_url:
continue
bitrate = int_or_none(video.get('bitrate'))
if determine_ext(video_url) == 'm3u8':
if not video_url.startswith('http'):
continue
formats.append({
'url': video_url,
'ext': 'mp4',
'tbr': bitrate,
'format_note': label,
'protocol': 'm3u8_native',
})
else:
formats.append({
'url': video_url,
'tbr': bitrate,
'format_note': label,
})
self._sort_formats(formats)
metadata = self._extract_metadata(
'https://www.hitbox.tv/api/media/video',
video_id)
player_config = self._download_json(
'https://www.hitbox.tv/api/player/config/video/%s' % video_id,
video_id)
clip = player_config.get('clip')
video_url = clip.get('url')
res = clip.get('bitrates', [])[0].get('label')
metadata['resolution'] = res
metadata['url'] = video_url
metadata['protocol'] = 'm3u8'
metadata['formats'] = formats
return metadata
@@ -129,10 +151,6 @@ class HitboxLiveIE(HitboxIE):
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._extract_metadata(
'https://www.hitbox.tv/api/media/live',
video_id)
player_config = self._download_json(
'https://www.hitbox.tv/api/player/config/live/%s' % video_id,
video_id)
@@ -147,20 +165,39 @@ class HitboxLiveIE(HitboxIE):
servers.append(base_url)
for stream in cdn.get('bitrates'):
label = stream.get('label')
if label != 'Auto':
if label == 'Auto':
continue
stream_url = stream.get('url')
if not stream_url:
continue
bitrate = int_or_none(stream.get('bitrate'))
if stream.get('provider') == 'hls' or determine_ext(stream_url) == 'm3u8':
if not stream_url.startswith('http'):
continue
formats.append({
'url': '%s/%s' % (base_url, stream.get('url')),
'url': stream_url,
'ext': 'mp4',
'vbr': stream.get('bitrate'),
'resolution': label,
'tbr': bitrate,
'format_note': label,
'rtmp_live': True,
})
else:
formats.append({
'url': '%s/%s' % (base_url, stream_url),
'ext': 'mp4',
'tbr': bitrate,
'rtmp_live': True,
'format_note': host,
'page_url': url,
'player_url': 'http://www.hitbox.tv/static/player/flowplayer/flowplayer.commercial-3.2.16.swf',
})
self._sort_formats(formats)
metadata = self._extract_metadata(
'https://www.hitbox.tv/api/media/live',
video_id)
metadata['formats'] = formats
metadata['is_live'] = True
metadata['title'] = self._live_title(metadata.get('title'))
return metadata

View File

@@ -61,7 +61,7 @@ class IGNIE(InfoExtractor):
},
{
'url': 'http://www.ign.com/articles/2014/08/15/rewind-theater-wild-trailer-gamescom-2014?watch',
'md5': '4e9a0bda1e5eebd31ddcf86ec0b9b3c7',
'md5': '618fedb9c901fd086f6f093564ef8558',
'info_dict': {
'id': '078fdd005f6d3c02f63d795faa1b984f',
'ext': 'mp4',
@@ -77,10 +77,10 @@ class IGNIE(InfoExtractor):
def _find_video_id(self, webpage):
res_id = [
r'"video_id"\s*:\s*"(.*?)"',
r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
r'data-video-id="(.+?)"',
r'<object id="vid_(.+?)"',
r'<meta name="og:image" content=".*/(.+?)-(.+?)/.+.jpg"',
r'class="hero-poster[^"]*?"[^>]*id="(.+?)"',
]
return self._search_regex(res_id, webpage, 'video id')

View File

@@ -3,13 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
)
from ..utils import int_or_none
class InstagramIE(InfoExtractor):
_VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
_VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
@@ -23,8 +21,8 @@ class InstagramIE(InfoExtractor):
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
webpage, 'uploader id', fatal=False)

View File

@@ -40,8 +40,10 @@ class KrasViewIE(InfoExtractor):
description = self._og_search_description(webpage, default=None)
thumbnail = flashvars.get('image') or self._og_search_thumbnail(webpage)
duration = int_or_none(flashvars.get('duration'))
width = int_or_none(self._og_search_property('video:width', webpage, 'video width'))
height = int_or_none(self._og_search_property('video:height', webpage, 'video height'))
width = int_or_none(self._og_search_property(
'video:width', webpage, 'video width', default=None))
height = int_or_none(self._og_search_property(
'video:height', webpage, 'video height', default=None))
return {
'id': video_id,

View File

@@ -88,12 +88,13 @@ class LetvIE(InfoExtractor):
play_json_req = compat_urllib_request.Request(
'http://api.letv.com/mms/out/video/playJson?' + compat_urllib_parse.urlencode(params)
)
play_json_req.add_header(
'Ytdl-request-proxy',
self._downloader.params.get('cn_verification_proxy'))
cn_verification_proxy = self._downloader.params.get('cn_verification_proxy')
if cn_verification_proxy:
play_json_req.add_header('Ytdl-request-proxy', cn_verification_proxy)
play_json = self._download_json(
play_json_req,
media_id, 'playJson data')
media_id, 'Downloading playJson data')
# Check for errors
playstatus = play_json['playstatus']

View File

@@ -0,0 +1,59 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import unified_strdate
class LibsynIE(InfoExtractor):
_VALID_URL = r'https?://html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://html5-player.libsyn.com/embed/episode/id/3377616/',
'md5': '443360ee1b58007bc3dcf09b41d093bb',
'info_dict': {
'id': '3377616',
'ext': 'mp3',
'title': "The Daily Show Podcast without Jon Stewart - Episode 12: Bassem Youssef: Egypt's Jon Stewart",
'description': 'md5:601cb790edd05908957dae8aaa866465',
'upload_date': '20150220',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = [{
'url': media_url,
} for media_url in set(re.findall('var\s+mediaURL(?:Libsyn)?\s*=\s*"([^"]+)"', webpage))]
podcast_title = self._search_regex(
r'<h2>([^<]+)</h2>', webpage, 'title')
episode_title = self._search_regex(
r'<h3>([^<]+)</h3>', webpage, 'title', default=None)
title = '%s - %s' % (podcast_title, episode_title) if podcast_title else episode_title
description = self._html_search_regex(
r'<div id="info_text_body">(.+?)</div>', webpage,
'description', fatal=False)
thumbnail = self._search_regex(
r'<img[^>]+class="info-show-icon"[^>]+src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
release_date = unified_strdate(self._search_regex(
r'<div class="release_date">Released: ([^<]+)<', webpage, 'release date', fatal=False))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': release_date,
'formats': formats,
}

View File

@@ -21,7 +21,7 @@ from ..utils import (
class LivestreamIE(InfoExtractor):
IE_NAME = 'livestream'
_VALID_URL = r'https?://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
_VALID_URL = r'https?://(?:new\.)?livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>[0-9]+)(?:/player)?)?/?(?:$|[?#])'
_TESTS = [{
'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
'md5': '53274c76ba7754fb0e8d072716f2292b',
@@ -51,6 +51,9 @@ class LivestreamIE(InfoExtractor):
}, {
'url': 'https://new.livestream.com/accounts/362/events/3557232/videos/67864563/player?autoPlay=false&height=360&mute=false&width=640',
'only_matching': True,
}, {
'url': 'http://livestream.com/bsww/concacafbeachsoccercampeonato2015',
'only_matching': True,
}]
def _parse_smil(self, video_id, smil_url):

View File

@@ -0,0 +1,56 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
xpath_text,
)
class MegaVideozIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?megavideoz\.eu/video/(?P<id>[^/]+)(?:/(?P<display_id>[^/]+))?'
_TEST = {
'url': 'http://megavideoz.eu/video/WM6UB919XMXH/SMPTE-Universal-Film-Leader',
'info_dict': {
'id': '48723',
'display_id': 'SMPTE-Universal-Film-Leader',
'ext': 'mp4',
'title': 'SMPTE Universal Film Leader',
'thumbnail': 're:https?://.*?\.jpg',
'duration': 10.93,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
if any(p in webpage for p in ('>Video Not Found<', '>404 Error<')):
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
config = self._download_xml(
self._search_regex(
r"var\s+cnf\s*=\s*'([^']+)'", webpage, 'cnf url'),
display_id)
video_url = xpath_text(config, './file', 'video url', fatal=True)
title = xpath_text(config, './title', 'title', fatal=True)
thumbnail = xpath_text(config, './image', 'thumbnail')
duration = float_or_none(xpath_text(config, './duration', 'duration'))
video_id = xpath_text(config, './mediaid', 'video id') or video_id
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'duration': duration
}

View File

@@ -0,0 +1,106 @@
# coding: utf-8
from __future__ import unicode_literals
import random
from .common import InfoExtractor
from ..utils import (
xpath_text,
int_or_none,
ExtractorError,
)
class MioMioIE(InfoExtractor):
IE_NAME = 'miomio.tv'
_VALID_URL = r'https?://(?:www\.)?miomio\.tv/watch/cc(?P<id>[0-9]+)'
_TESTS = [{
# "type=video" in flashvars
'url': 'http://www.miomio.tv/watch/cc88912/',
'md5': '317a5f7f6b544ce8419b784ca8edae65',
'info_dict': {
'id': '88912',
'ext': 'flv',
'title': '【SKY】字幕 铠武昭和VS平成 假面骑士大战FEAT战队 魔星字幕组 字幕',
'duration': 5923,
},
}, {
'url': 'http://www.miomio.tv/watch/cc184024/',
'info_dict': {
'id': '43729',
'title': '《动漫同人插画绘制》',
},
'playlist_mincount': 86,
'skip': 'This video takes time too long for retrieving the URL',
}, {
'url': 'http://www.miomio.tv/watch/cc173113/',
'info_dict': {
'id': '173113',
'title': 'The New Macbook 2015 上手试玩与简评'
},
'playlist_mincount': 2,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(
'description', webpage, 'title', fatal=True)
mioplayer_path = self._search_regex(
r'src="(/mioplayer/[^"]+)"', webpage, 'ref_path')
xml_config = self._search_regex(
r'flashvars="type=(?:sina|video)&amp;(.+?)&amp;',
webpage, 'xml config')
# skipping the following page causes lags and eventually connection drop-outs
self._request_webpage(
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/xml.php?id=%s&r=%s' % (id, random.randint(100, 999)),
video_id)
# the following xml contains the actual configuration information on the video file(s)
vid_config = self._download_xml(
'http://www.miomio.tv/mioplayer/mioplayerconfigfiles/sina.php?{0}'.format(xml_config),
video_id)
http_headers = {
'Referer': 'http://www.miomio.tv%s' % mioplayer_path,
}
if not int_or_none(xpath_text(vid_config, 'timelength')):
raise ExtractorError('Unable to load videos!', expected=True)
entries = []
for f in vid_config.findall('./durl'):
segment_url = xpath_text(f, 'url', 'video url')
if not segment_url:
continue
order = xpath_text(f, 'order', 'order')
segment_id = video_id
segment_title = title
if order:
segment_id += '-%s' % order
segment_title += ' part %s' % order
entries.append({
'id': segment_id,
'url': segment_url,
'title': segment_title,
'duration': int_or_none(xpath_text(f, 'length', 'duration'), 1000),
'http_headers': http_headers,
})
if len(entries) == 1:
segment = entries[0]
segment['id'] = video_id
segment['title'] = title
return segment
return {
'_type': 'multi_video',
'id': video_id,
'entries': entries,
'title': title,
'http_headers': http_headers,
}

View File

@@ -10,7 +10,6 @@ from ..utils import (
ExtractorError,
HEADRequest,
str_to_int,
parse_iso8601,
)
@@ -27,8 +26,6 @@ class MixcloudIE(InfoExtractor):
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
'uploader': 'Daniel Holbach',
'uploader_id': 'dholbach',
'upload_date': '20111115',
'timestamp': 1321359578,
'thumbnail': 're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
@@ -37,32 +34,27 @@ class MixcloudIE(InfoExtractor):
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
'info_dict': {
'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
'ext': 'm4a',
'title': 'Electric Relaxation vol. 3',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'uploader': 'Daniel Drumz',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*\.jpg',
'thumbnail': 're:https?://.*/images/',
'view_count': int,
'like_count': int,
},
}]
def _get_url(self, track_id, template_url):
server_count = 30
for i in range(server_count):
url = template_url % i
try:
# We only want to know if the request succeed
# don't download the whole file
self._request_webpage(
HEADRequest(url), track_id,
'Checking URL %d/%d ...' % (i + 1, server_count + 1))
return url
except ExtractorError:
pass
return None
def _check_url(self, url, track_id, ext):
try:
# We only want to know if the request succeed
# don't download the whole file
self._request_webpage(
HEADRequest(url), track_id,
'Trying %s URL' % ext)
return True
except ExtractorError:
return False
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -75,17 +67,13 @@ class MixcloudIE(InfoExtractor):
preview_url = self._search_regex(
r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url')
song_url = preview_url.replace('/previews/', '/c/originals/')
template_url = re.sub(r'(stream\d*)', 'stream%d', song_url)
final_song_url = self._get_url(track_id, template_url)
if final_song_url is None:
self.to_screen('Trying with m4a extension')
template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
final_song_url = self._get_url(track_id, template_url)
if final_song_url is None:
raise ExtractorError('Unable to extract track url')
if not self._check_url(song_url, track_id, 'mp3'):
song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
if not self._check_url(song_url, track_id, 'm4a'):
raise ExtractorError('Unable to extract track url')
PREFIX = (
r'<span class="play-button[^"]*?"'
r'm-play-on-spacebar[^>]+'
r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+')
title = self._html_search_regex(
PREFIX + r'm-title="([^"]+)"', webpage, 'title')
@@ -99,26 +87,21 @@ class MixcloudIE(InfoExtractor):
r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
description = self._og_search_description(webpage)
like_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserLikes:([0-9]+)"',
r'/favorites/?">([0-9]+)<'],
r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"',
webpage, 'like count', fatal=False))
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>'],
webpage, 'play count', fatal=False))
timestamp = parse_iso8601(self._search_regex(
r'<time itemprop="dateCreated" datetime="([^"]+)">',
webpage, 'upload date', default=None))
return {
'id': track_id,
'title': title,
'url': final_song_url,
'url': song_url,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': timestamp,
'view_count': view_count,
'like_count': like_count,
}

View File

@@ -10,7 +10,7 @@ from ..utils import (
class MLBIE(InfoExtractor):
_VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
_VALID_URL = r'https?://m(?:lb)?\.(?:[\da-z_-]+\.)?mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?P<id>n?\d+)'
_TESTS = [
{
'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea',
@@ -80,6 +80,10 @@ class MLBIE(InfoExtractor):
'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553',
'only_matching': True,
},
{
'url': 'http://m.cardinals.mlb.com/stl/video/v51175783/atlstl-piscotty-makes-great-sliding-catch-on-line/?partnerId=as_mlb_20150321_42500876&adbid=579409712979910656&adbpl=tw&adbpr=52847728',
'only_matching': True,
}
]
def _real_extract(self, url):

View File

@@ -9,6 +9,7 @@ from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import ExtractorError
class MonikerIE(InfoExtractor):
@@ -40,6 +41,15 @@ class MonikerIE(InfoExtractor):
video_id = self._match_id(url)
orig_webpage = self._download_webpage(url, video_id)
if '>File Not Found<' in orig_webpage:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
error = self._search_regex(
r'class="err">([^<]+)<', orig_webpage, 'error', default=None)
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error), expected=True)
fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
data = dict(fields)

View File

@@ -25,6 +25,7 @@ def _media_xml_tag(tag):
class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
_LANG = None
@staticmethod
def _id_from_uri(uri):
@@ -118,6 +119,14 @@ class MTVServicesInfoExtractor(InfoExtractor):
mediagen_doc = self._download_xml(mediagen_url, video_id,
'Downloading video urls')
item = mediagen_doc.find('./video/item')
if item is not None and item.get('type') == 'text':
message = '%s returned error: ' % self.IE_NAME
if item.get('code') is not None:
message += '%s - ' % item.get('code')
message += item.text
raise ExtractorError(message, expected=True)
description_node = itemdoc.find('description')
if description_node is not None:
description = description_node.text.strip()
@@ -161,8 +170,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
info_url = feed_url + '?'
if self._LANG:
info_url += 'lang=%s&' % self._LANG
info_url += data
idoc = self._download_xml(
feed_url + '?' + data, video_id,
info_url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')])

View File

@@ -14,7 +14,7 @@ from ..utils import (
class NBCIE(InfoExtractor):
_VALID_URL = r'http://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
_VALID_URL = r'https?://www\.nbc\.com/(?:[^/]+/)+(?P<id>n?\d+)'
_TESTS = [
{
@@ -50,6 +50,57 @@ class NBCIE(InfoExtractor):
return self.url_result(theplatform_url)
class NBCSportsVPlayerIE(InfoExtractor):
_VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
_TESTS = [{
'url': 'https://vplayer.nbcsports.com/p/BxmELC/nbcsports_share/select/9CsDKds0kvHI',
'info_dict': {
'id': '9CsDKds0kvHI',
'ext': 'flv',
'description': 'md5:df390f70a9ba7c95ff1daace988f0d8d',
'title': 'Tyler Kalinoski hits buzzer-beater to lift Davidson',
}
}, {
'url': 'http://vplayer.nbcsports.com/p/BxmELC/nbc_embedshare/select/_hqLjQ95yx8Z',
'only_matching': True,
}]
@staticmethod
def _extract_url(webpage):
iframe_m = re.search(
r'<iframe[^>]+src="(?P<url>https?://vplayer\.nbcsports\.com/[^"]+)"', webpage)
if iframe_m:
return iframe_m.group('url')
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
theplatform_url = self._og_search_video_url(webpage)
return self.url_result(theplatform_url, 'ThePlatform')
class NBCSportsIE(InfoExtractor):
# Does not include https becuase its certificate is invalid
_VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
_TEST = {
'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke',
'info_dict': {
'id': 'PHJSaFWbrTY9',
'ext': 'flv',
'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke',
'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
return self.url_result(
NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer')
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
(?:video/.+?/(?P<id>\d+)|

View File

@@ -22,7 +22,7 @@ class NiconicoIE(InfoExtractor):
IE_NAME = 'niconico'
IE_DESC = 'ニコニコ動画'
_TEST = {
_TESTS = [{
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'info_dict': {
@@ -39,7 +39,24 @@ class NiconicoIE(InfoExtractor):
'username': 'ydl.niconico@gmail.com',
'password': 'youtube-dl',
},
}
}, {
'url': 'http://www.nicovideo.jp/watch/nm14296458',
'md5': '8db08e0158457cf852a31519fceea5bc',
'info_dict': {
'id': 'nm14296458',
'ext': 'swf',
'title': '【鏡音リン】Dance on media【オリジナル】take2!',
'description': 'md5:',
'uploader': 'りょうた',
'uploader_id': '18822557',
'upload_date': '20110429',
'duration': 209,
},
'params': {
'username': 'ydl.niconico@gmail.com',
'password': 'youtube-dl',
},
}]
_VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/(?P<id>(?:[a-z]{2})?[0-9]+)'
_NETRC_MACHINE = 'niconico'
@@ -89,7 +106,7 @@ class NiconicoIE(InfoExtractor):
if self._AUTHENTICATED:
# Get flv info
flv_info_webpage = self._download_webpage(
'http://flapi.nicovideo.jp/api/getflv?v=' + video_id,
'http://flapi.nicovideo.jp/api/getflv/' + video_id + '?as3=1',
video_id, 'Downloading flv info')
else:
# Get external player info

View File

@@ -231,7 +231,10 @@ class NPOLiveIE(NPOBaseIE):
stream_url = self._download_json(
stream_info['stream'], display_id,
'Downloading %s URL' % stream_type,
transform_source=strip_jsonp)
'Unable to download %s URL' % stream_type,
transform_source=strip_jsonp, fatal=False)
if not stream_url:
continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(stream_url, display_id)
# f4m downloader downloads only piece of live stream

View File

@@ -14,46 +14,48 @@ from ..utils import (
class NRKIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?nrk\.no/(?:video|lyd)/[^/]+/(?P<id>[\dA-F]{16})'
_VALID_URL = r'(?:nrk:|http://(?:www\.)?nrk\.no/video/PS\*)(?P<id>\d+)'
_TESTS = [
{
'url': 'http://www.nrk.no/video/dompap_og_andre_fugler_i_piip_show/D0FA54B5C8B6CE59/emne/piipshow/',
'md5': 'a6eac35052f3b242bb6bb7f43aed5886',
'url': 'http://www.nrk.no/video/PS*150533',
'md5': 'bccd850baebefe23b56d708a113229c2',
'info_dict': {
'id': '150533',
'ext': 'flv',
'title': 'Dompap og andre fugler i Piip-Show',
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f'
'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
'duration': 263,
}
},
{
'url': 'http://www.nrk.no/lyd/lyd_av_oppleser_for_blinde/AEFDDD5473BA0198/',
'md5': '3471f2a51718195164e88f46bf427668',
'url': 'http://www.nrk.no/video/PS*154915',
'md5': '0b1493ba1aae7d9579a5ad5531bc395a',
'info_dict': {
'id': '154915',
'ext': 'flv',
'title': 'Slik høres internett ut når du er blind',
'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
'duration': 20,
}
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
page = self._download_webpage(url, video_id)
video_id = self._html_search_regex(r'<div class="nrk-video" data-nrk-id="(\d+)">', page, 'video id')
video_id = self._match_id(url)
data = self._download_json(
'http://v7.psapi.nrk.no/mediaelement/%s' % video_id, video_id, 'Downloading media JSON')
'http://v8.psapi.nrk.no/mediaelement/%s' % video_id,
video_id, 'Downloading media JSON')
if data['usageRights']['isGeoBlocked']:
raise ExtractorError('NRK har ikke rettig-heter til å vise dette programmet utenfor Norge', expected=True)
raise ExtractorError(
'NRK har ikke rettig-heter til å vise dette programmet utenfor Norge',
expected=True)
video_url = data['mediaUrl'] + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124'
video_url = data['mediaUrl'] + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81'
duration = parse_duration(data.get('duration'))
images = data.get('images')
if images:
@@ -69,10 +71,51 @@ class NRKIE(InfoExtractor):
'ext': 'flv',
'title': data['title'],
'description': data['description'],
'duration': duration,
'thumbnail': thumbnail,
}
class NRKPlaylistIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?nrk\.no/(?!video)(?:[^/]+/)+(?P<id>[^/]+)'
_TESTS = [{
'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
'info_dict': {
'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
'title': 'Gjenopplev den historiske solformørkelsen',
'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
},
'playlist_count': 2,
}, {
'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
'info_dict': {
'id': 'rivertonprisen-til-karin-fossum-1.12266449',
'title': 'Rivertonprisen til Karin Fossum',
'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
},
'playlist_count': 5,
}]
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result('nrk:%s' % video_id, 'NRK')
for video_id in re.findall(
r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
webpage)
]
playlist_title = self._og_search_title(webpage)
playlist_description = self._og_search_description(webpage)
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
class NRKTVIE(InfoExtractor):
_VALID_URL = r'(?P<baseurl>http://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'

View File

@@ -1,15 +1,17 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_iso8601
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
)
class NYTimesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nytimes\.com/video/(?:[^/]+/)+(?P<id>\d+)'
_VALID_URL = r'https?://(?:(?:www\.)?nytimes\.com/video/(?:[^/]+/)+?|graphics8\.nytimes\.com/bcvideo/\d+(?:\.\d+)?/iframe/embed\.html\?videoId=)(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
'md5': '18a525a510f942ada2720db5f31644c0',
'info_dict': {
@@ -22,18 +24,21 @@ class NYTimesIE(InfoExtractor):
'uploader': 'Brett Weiner',
'duration': 419,
}
}
}, {
'url': 'http://www.nytimes.com/video/travel/100000003550828/36-hours-in-dubai.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
video_data = self._download_json(
'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id, video_id, 'Downloading video JSON')
'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
video_id, 'Downloading video JSON')
title = video_data['headline']
description = video_data['summary']
duration = video_data['duration'] / 1000.0
description = video_data.get('summary')
duration = float_or_none(video_data.get('duration'), 1000)
uploader = video_data['byline']
timestamp = parse_iso8601(video_data['publication_date'][:-8])
@@ -49,11 +54,11 @@ class NYTimesIE(InfoExtractor):
formats = [
{
'url': video['url'],
'format_id': video['type'],
'vcodec': video['video_codec'],
'width': video['width'],
'height': video['height'],
'filesize': get_file_size(video['fileSize']),
'format_id': video.get('type'),
'vcodec': video.get('video_codec'),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'filesize': get_file_size(video.get('fileSize')),
} for video in video_data['renditions']
]
self._sort_formats(formats)
@@ -61,7 +66,8 @@ class NYTimesIE(InfoExtractor):
thumbnails = [
{
'url': 'http://www.nytimes.com/%s' % image['url'],
'resolution': '%dx%d' % (image['width'], image['height']),
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
} for image in video_data['images']
]

View File

@@ -210,16 +210,16 @@ class ORFIPTVIE(InfoExtractor):
_VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
_TEST = {
'url': 'http://iptv.orf.at/stories/2267952',
'md5': '26ffa4bab6dbce1eee78bbc7021016cd',
'url': 'http://iptv.orf.at/stories/2275236/',
'md5': 'c8b22af4718a4b4af58342529453e3e5',
'info_dict': {
'id': '339775',
'id': '350612',
'ext': 'flv',
'title': 'Kreml-Kritiker Nawalny wieder frei',
'description': 'md5:6f24e7f546d364dacd0e616a9e409236',
'duration': 84.729,
'title': 'Weitere Evakuierungen um Vulkan Calbuco',
'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
'duration': 68.197,
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20150306',
'upload_date': '20150425',
},
}

View File

@@ -0,0 +1,78 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
xpath_text,
)
class PhilharmonieDeParisIE(InfoExtractor):
IE_DESC = 'Philharmonie de Paris'
_VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
'info_dict': {
'id': '1032066',
'ext': 'flv',
'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
'timestamp': 1428179400,
'upload_date': '20150404',
'duration': 6592.278,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
'only_matching': True,
}, {
'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
concert = self._download_xml(
'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
video_id).find('./concert')
formats = []
info_dict = {
'id': video_id,
'title': xpath_text(concert, './titre', 'title', fatal=True),
'formats': formats,
}
fichiers = concert.find('./fichiers')
stream = fichiers.attrib['serveurstream']
for fichier in fichiers.findall('./fichier'):
info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
format_url = fichier.get('url%s' % suffix)
if not format_url:
continue
formats.append({
'url': stream,
'play_path': format_url,
'ext': 'flv',
'format_id': format_id,
'width': int_or_none(concert.get('largeur%s' % suffix)),
'height': int_or_none(concert.get('hauteur%s' % suffix)),
'quality': quality,
})
self._sort_formats(formats)
date, hour = concert.get('date'), concert.get('heure')
if date and hour:
info_dict['timestamp'] = parse_iso8601(
'%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
elif date:
info_dict['upload_date'] = date
return info_dict

View File

@@ -5,19 +5,33 @@ from .zdf import extract_from_xml_url
class PhoenixIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.phoenix.de/content/884301',
'md5': 'ed249f045256150c92e72dbb70eadec6',
'info_dict': {
'id': '884301',
'ext': 'mp4',
'title': 'Michael Krons mit Hans-Werner Sinn',
'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
'upload_date': '20141025',
'uploader': 'Im Dialog',
}
}
_VALID_URL = r'''(?x)https?://(?:www\.)?phoenix\.de/content/
(?:
phoenix/die_sendungen/(?:[^/]+/)?
)?
(?P<id>[0-9]+)'''
_TESTS = [
{
'url': 'http://www.phoenix.de/content/884301',
'md5': 'ed249f045256150c92e72dbb70eadec6',
'info_dict': {
'id': '884301',
'ext': 'mp4',
'title': 'Michael Krons mit Hans-Werner Sinn',
'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr',
'upload_date': '20141025',
'uploader': 'Im Dialog',
}
},
{
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/869815',
'only_matching': True,
},
{
'url': 'http://www.phoenix.de/content/phoenix/die_sendungen/diskussionen/928234',
'only_matching': True,
},
]
def _real_extract(self, url):
video_id = self._match_id(url)

View File

@@ -30,7 +30,7 @@ class PladformIE(InfoExtractor):
'info_dict': {
'id': '100183293',
'ext': 'mp4',
'title': 'Тайны перевала Дятлова • Тайна перевала Дятлова 1 серия 2 часть',
'title': 'Тайны перевала Дятлова • 1 серия 2 часть',
'description': 'Документальный сериал-расследование одной из самых жутких тайн ХХ века',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 694,

View File

@@ -4,85 +4,72 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..compat import compat_str
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
str_to_int,
parse_iso8601,
)
class PlayFMIE(InfoExtractor):
IE_NAME = 'play.fm'
_VALID_URL = r'https?://(?:www\.)?play\.fm/[^?#]*(?P<upload_date>[0-9]{8})(?P<id>[0-9]{6})(?:$|[?#])'
_VALID_URL = r'https?://(?:www\.)?play\.fm/(?P<slug>(?:[^/]+/)+(?P<id>[^/]+))/?(?:$|[?#])'
_TEST = {
'url': 'http://www.play.fm/recording/leipzigelectronicmusicbatofarparis_fr20140712137220',
'url': 'https://www.play.fm/dan-drastic/sven-tasnadi-leipzig-electronic-music-batofar-paris-fr-2014-07-12',
'md5': 'c505f8307825a245d0c7ad1850001f22',
'info_dict': {
'id': '137220',
'id': '71276',
'ext': 'mp3',
'title': 'LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
'uploader': 'Sven Tasnadi',
'uploader_id': 'sventasnadi',
'duration': 5627.428,
'upload_date': '20140712',
'title': 'Sven Tasnadi - LEIPZIG ELECTRONIC MUSIC @ Batofar (Paris,FR) - 2014-07-12',
'description': '',
'duration': 5627,
'timestamp': 1406033781,
'upload_date': '20140722',
'uploader': 'Dan Drastic',
'uploader_id': '71170',
'view_count': int,
'comment_count': int,
'thumbnail': 're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
upload_date = mobj.group('upload_date')
slug = mobj.group('slug')
rec_data = compat_urllib_parse.urlencode({'rec_id': video_id})
req = compat_urllib_request.Request(
'http://www.play.fm/flexRead/recording', data=rec_data)
req.add_header('Content-Type', 'application/x-www-form-urlencoded')
rec_doc = self._download_xml(req, video_id)
recordings = self._download_json(
'http://v2api.play.fm/recordings/slug/%s' % slug, video_id)
error_node = rec_doc.find('./error')
if error_node is not None:
raise ExtractorError('An error occured: %s (code %s)' % (
error_node.text, rec_doc.find('./status').text))
error = recordings.get('error')
if isinstance(error, dict):
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error.get('message')),
expected=True)
recording = rec_doc.find('./recording')
title = recording.find('./title').text
view_count = str_to_int(recording.find('./stats/playcount').text)
comment_count = str_to_int(recording.find('./stats/comments').text)
duration = float_or_none(recording.find('./duration').text, scale=1000)
thumbnail = recording.find('./image').text
artist = recording.find('./artists/artist')
uploader = artist.find('./name').text
uploader_id = artist.find('./slug').text
video_url = '%s//%s/%s/%s/offset/0/sh/%s/rec/%s/jingle/%s/loc/%s' % (
'http:', recording.find('./url').text,
recording.find('./_class').text, recording.find('./file_id').text,
rec_doc.find('./uuid').text, video_id,
rec_doc.find('./jingle/file_id').text,
'http%3A%2F%2Fwww.play.fm%2Fplayer',
)
audio_url = recordings['audio']
video_id = compat_str(recordings.get('id') or video_id)
title = recordings['title']
description = recordings.get('description')
duration = int_or_none(recordings.get('recordingDuration'))
timestamp = parse_iso8601(recordings.get('created_at'))
uploader = recordings.get('page', {}).get('title')
uploader_id = compat_str(recordings.get('page', {}).get('id'))
view_count = int_or_none(recordings.get('playCount'))
comment_count = int_or_none(recordings.get('commentCount'))
categories = [tag['name'] for tag in recordings.get('tags', []) if tag.get('name')]
return {
'id': video_id,
'url': video_url,
'ext': 'mp3',
'filesize': int_or_none(recording.find('./size').text),
'url': audio_url,
'title': title,
'upload_date': upload_date,
'view_count': view_count,
'comment_count': comment_count,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'comment_count': comment_count,
'categories': categories,
}

View File

@@ -33,10 +33,8 @@ class PornHubIE(InfoExtractor):
}
def _extract_count(self, pattern, webpage, name):
count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
if count:
count = str_to_int(count)
return count
return str_to_int(self._search_regex(
pattern, webpage, '%s count' % name, fatal=False))
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -62,11 +60,14 @@ class PornHubIE(InfoExtractor):
if thumbnail:
thumbnail = compat_urllib_parse.unquote(thumbnail)
view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
like_count = self._extract_count(
r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
dislike_count = self._extract_count(
r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
comment_count = self._extract_count(
r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
if webpage.find('"encrypted":true') != -1:

View File

@@ -0,0 +1,96 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import random
from .common import InfoExtractor
from ..utils import (
int_or_none,
float_or_none,
unified_strdate,
)
class PornoVoisinesIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
_VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
'/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
_SERVER_NUMBERS = (1, 2)
_TEST = {
'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
'info_dict': {
'id': '1285',
'display_id': 'recherche-appartement',
'ext': 'mp4',
'title': 'Recherche appartement',
'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140925',
'duration': 120,
'view_count': int,
'average_rating': float,
'categories': ['Débutante', 'Scénario', 'Sodomie'],
'age_limit': 18,
}
}
@classmethod
def build_video_url(cls, num):
return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, video_id)
video_url = self.build_video_url(video_id)
title = self._html_search_regex(
r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
description = self._html_search_regex(
r'<article id="descriptif">(.+?)</article>',
webpage, "description", fatal=False, flags=re.DOTALL)
thumbnail = self._search_regex(
r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
webpage, 'thumbnail', fatal=False)
if thumbnail:
thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
upload_date = unified_strdate(self._search_regex(
r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
duration = int_or_none(self._search_regex(
'Durée (\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'(\d+) vues', webpage, 'view count', fatal=False))
average_rating = self._search_regex(
r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', fatal=False)
if categories:
categories = [category.strip() for category in categories.split(',')]
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'average_rating': average_rating,
'categories': categories,
'age_limit': 18,
}

View File

@@ -0,0 +1,69 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import ExtractorError
class PrimeShareTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?primeshare\.tv/download/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://primeshare.tv/download/238790B611',
'md5': 'b92d9bf5461137c36228009f31533fbc',
'info_dict': {
'id': '238790B611',
'ext': 'mp4',
'title': 'Public Domain - 1960s Commercial - Crest Toothpaste-YKsuFona',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if '>File not exist<' in webpage:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = dict(re.findall(r'''(?x)<input\s+
type="hidden"\s+
name="([^"]+)"\s+
(?:id="[^"]+"\s+)?
value="([^"]*)"
''', webpage))
headers = {
'Referer': url,
'Content-Type': 'application/x-www-form-urlencoded',
}
wait_time = int(self._search_regex(
r'var\s+cWaitTime\s*=\s*(\d+)',
webpage, 'wait time', default=7)) + 1
self._sleep(wait_time, video_id)
req = compat_urllib_request.Request(
url, compat_urllib_parse.urlencode(fields), headers)
video_page = self._download_webpage(
req, video_id, 'Downloading video page')
video_url = self._search_regex(
r"url\s*:\s*'([^']+\.primeshare\.tv(?::443)?/file/[^']+)'",
video_page, 'video url')
title = self._html_search_regex(
r'<h1>Watch\s*(?:&nbsp;)?\s*\((.+?)(?:\s*\[\.\.\.\])?\)\s*(?:&nbsp;)?\s*<strong>',
video_page, 'title')
return {
'id': video_id,
'url': video_url,
'title': title,
'ext': 'mp4',
}

View File

@@ -10,6 +10,7 @@ from ..compat import (
)
from ..utils import (
unified_strdate,
int_or_none,
)
@@ -24,7 +25,7 @@ class ProSiebenSat1IE(InfoExtractor):
'info_dict': {
'id': '2104602',
'ext': 'mp4',
'title': 'Staffel 2, Episode 18 - Jahresrückblick',
'title': 'Episode 18 - Staffel 2',
'description': 'md5:8733c81b702ea472e069bc48bb658fc1',
'upload_date': '20131231',
'duration': 5845.04,
@@ -266,6 +267,9 @@ class ProSiebenSat1IE(InfoExtractor):
urls_sources = urls_sources.values()
def fix_bitrate(bitrate):
bitrate = int_or_none(bitrate)
if not bitrate:
return None
return (bitrate // 1000) if bitrate % 1000 == 0 else bitrate
for source in urls_sources:

View File

@@ -0,0 +1,170 @@
# coding: utf-8
from __future__ import unicode_literals
import random
import time
import re
from .common import InfoExtractor
from ..utils import (
strip_jsonp,
unescapeHTML,
)
from ..compat import compat_urllib_request
class QQMusicIE(InfoExtractor):
_VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': 'bed90b6db2a7a7a7e11bc585f471f63a',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'm4a',
'title': '可惜没如果',
'upload_date': '20141227',
'creator': '林俊杰',
'description': 'md5:4348ff1dd24036906baa7b6f973f8d30',
}
}]
# Reference: m_r_GetRUin() in top_player.js
# http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js
@staticmethod
def m_r_get_ruin():
curMs = int(time.time() * 1000) % 1000
return int(round(random.random() * 2147483647) * curMs % 1E10)
def _real_extract(self, url):
mid = self._match_id(url)
detail_info_page = self._download_webpage(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
mid, note='Download song detail info',
errnote='Unable to get song detail info', encoding='gbk')
song_name = self._html_search_regex(
r"songname:\s*'([^']+)'", detail_info_page, 'song name')
publish_time = self._html_search_regex(
r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
'publish time', default=None)
if publish_time:
publish_time = publish_time.replace('-', '')
singer = self._html_search_regex(
r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)
lrc_content = self._html_search_regex(
r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
detail_info_page, 'LRC lyrics', default=None)
guid = self.m_r_get_ruin()
vkey = self._download_json(
'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid,
mid, note='Retrieve vkey', errnote='Unable to get vkey',
transform_source=strip_jsonp)['key']
song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid)
return {
'id': mid,
'url': song_url,
'title': song_name,
'upload_date': publish_time,
'creator': singer,
'description': lrc_content,
}
class QQPlaylistBaseIE(InfoExtractor):
@staticmethod
def qq_static_url(category, mid):
return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)
@classmethod
def get_entries_from_page(cls, page):
entries = []
for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
song_mid = unescapeHTML(item).split('|')[-5]
entries.append(cls.url_result(
'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
song_mid))
return entries
class QQMusicSingerIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
},
'playlist_count': 12,
}
def _real_extract(self, url):
mid = self._match_id(url)
singer_page = self._download_webpage(
self.qq_static_url('singer', mid), mid, 'Download singer page')
entries = self.get_entries_from_page(singer_page)
singer_name = self._html_search_regex(
r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
default=None)
singer_id = self._html_search_regex(
r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
default=None)
singer_desc = None
if singer_id:
req = compat_urllib_request.Request(
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
req.add_header(
'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
singer_desc_page = self._download_xml(
req, mid, 'Donwload singer description XML')
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)
class QQMusicAlbumIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
_TEST = {
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
},
'playlist_count': 4,
}
def _real_extract(self, url):
mid = self._match_id(url)
album_page = self._download_webpage(
self.qq_static_url('album', mid), mid, 'Download album page')
entries = self.get_entries_from_page(album_page)
album_name = self._html_search_regex(
r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
default=None)
album_detail = self._html_search_regex(
r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
album_page, 'album details', default=None)
return self.playlist_result(entries, mid, album_name, album_detail)

View File

@@ -0,0 +1,67 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import(
unified_strdate,
str_to_int,
)
class RadioJavanIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?radiojavan\.com/videos/video/(?P<id>[^/]+)/?'
_TEST = {
'url': 'http://www.radiojavan.com/videos/video/chaartaar-ashoobam',
'md5': 'e85208ffa3ca8b83534fca9fe19af95b',
'info_dict': {
'id': 'chaartaar-ashoobam',
'ext': 'mp4',
'title': 'Chaartaar - Ashoobam',
'thumbnail': 're:^https?://.*\.jpe?g$',
'upload_date': '20150215',
'view_count': int,
'like_count': int,
'dislike_count': int,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = [{
'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
'format_id': '%sp' % height,
'height': int(height),
} for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
self._sort_formats(formats)
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
r'class="date_added">Date added: ([^<]+)<',
webpage, 'upload date', fatal=False))
view_count = str_to_int(self._search_regex(
r'class="views">Plays: ([\d,]+)',
webpage, 'view count', fatal=False))
like_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) likes',
webpage, 'like count', fatal=False))
dislike_count = str_to_int(self._search_regex(
r'class="rating">([\d,]+) dislikes',
webpage, 'dislike count', fatal=False))
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'formats': formats,
}

View File

@@ -13,7 +13,7 @@ from ..utils import (
class RaiIE(InfoExtractor):
_VALID_URL = r'(?P<url>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
_VALID_URL = r'(?P<url>(?P<host>http://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it))/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)'
_TESTS = [
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
@@ -62,34 +62,78 @@ class RaiIE(InfoExtractor):
'description': 'Edizione delle ore 20:30 ',
}
},
{
'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
'md5': '02b64456f7cc09f96ff14e7dd489017e',
'info_dict': {
'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
'ext': 'flv',
'title': 'Il Candidato - Primo episodio: "Le Primarie"',
'description': 'Primo appuntamento con "Il candidato" con Filippo Timi, alias Piero Zucca presidente!',
'uploader': 'RaiTre',
}
}
]
def _extract_relinker_url(self, webpage):
return self._proto_relative_url(self._search_regex(
[r'name="videourl" content="([^"]+)"', r'var\s+videoURL(?:_MP4)?\s*=\s*"([^"]+)"'],
webpage, 'relinker url', default=None))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
media = self._download_json('%s?json' % mobj.group('url'), video_id, 'Downloading video JSON')
webpage = self._download_webpage(url, video_id)
title = media.get('name')
description = media.get('desc')
thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
duration = parse_duration(media.get('length'))
uploader = media.get('author')
upload_date = unified_strdate(media.get('date'))
relinker_url = self._extract_relinker_url(webpage)
formats = []
if not relinker_url:
iframe_path = self._search_regex(
r'<iframe[^>]+src="/?(dl/[^"]+\?iframe\b[^"]*)"',
webpage, 'iframe')
webpage = self._download_webpage(
'%s/%s' % (host, iframe_path), video_id)
relinker_url = self._extract_relinker_url(webpage)
for format_id in ['wmv', 'm3u8', 'mediaUri', 'h264']:
media_url = media.get(format_id)
if not media_url:
continue
formats.append({
relinker = self._download_json(
'%s&output=47' % relinker_url, video_id)
media_url = relinker['video'][0]
ct = relinker.get('ct')
if ct == 'f4m':
formats = self._extract_f4m_formats(
media_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id)
else:
formats = [{
'url': media_url,
'format_id': format_id,
'ext': 'mp4',
})
'format_id': ct,
}]
subtitles = self.extract_subtitles(video_id, url)
json_link = self._html_search_meta(
'jsonlink', webpage, 'JSON link', default=None)
if json_link:
media = self._download_json(
host + json_link, video_id, 'Downloading video JSON')
title = media.get('name')
description = media.get('desc')
thumbnail = media.get('image_300') or media.get('image_medium') or media.get('image')
duration = parse_duration(media.get('length'))
uploader = media.get('author')
upload_date = unified_strdate(media.get('date'))
else:
title = (self._search_regex(
r'var\s+videoTitolo\s*=\s*"(.+?)";',
webpage, 'title', default=None) or self._og_search_title(webpage)).replace('\\"', '"')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
duration = None
uploader = self._html_search_meta('Editore', webpage, 'uploader')
upload_date = unified_strdate(self._html_search_meta(
'item-date', webpage, 'upload date', default=None))
subtitles = self.extract_subtitles(video_id, webpage)
return {
'id': video_id,
@@ -103,8 +147,7 @@ class RaiIE(InfoExtractor):
'subtitles': subtitles,
}
def _get_subtitles(self, video_id, url):
webpage = self._download_webpage(url, video_id)
def _get_subtitles(self, video_id, webpage):
subtitles = {}
m = re.search(r'<meta name="closedcaption" content="(?P<captions>[^"]+)"', webpage)
if m:

View File

@@ -1,17 +1,19 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError
class RedTubeIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.redtube.com/66418',
'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
'info_dict': {
'id': '66418',
'ext': 'mp4',
"title": "Sucked on a toilet",
"age_limit": 18,
'title': 'Sucked on a toilet',
'age_limit': 18,
}
}
@@ -19,6 +21,9 @@ class RedTubeIE(InfoExtractor):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)
video_url = self._html_search_regex(
r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
video_title = self._html_search_regex(

View File

@@ -8,8 +8,10 @@ import time
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
float_or_none,
remove_end,
std_headers,
struct_unpack,
)
@@ -84,13 +86,22 @@ class RTVEALaCartaIE(InfoExtractor):
'only_matching': True,
}]
def _real_initialize(self):
user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
manager_info = self._download_json(
'http://www.rtve.es/odin/loki/' + user_agent_b64,
None, 'Fetching manager info')
self._manager = manager_info['manager']
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % video_id
if info['state'] == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True)
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
if not video_url.endswith('.f4m'):
@@ -127,6 +138,47 @@ class RTVEALaCartaIE(InfoExtractor):
for s in subs)
class RTVEInfantilIE(InfoExtractor):
IE_NAME = 'rtve.es:infantil'
IE_DESC = 'RTVE infantil'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
_TESTS = [{
'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
'md5': '915319587b33720b8e0357caaa6617e6',
'info_dict': {
'id': '3040283',
'ext': 'mp4',
'title': 'Maneras de vivir',
'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
'duration': 357.958,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
video_id)['page']['items'][0]
webpage = self._download_webpage(url, video_id)
vidplayer_id = self._search_regex(
r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
png = self._download_webpage(png_url, video_id, 'Downloading url information')
video_url = _decrypt_url(png)
return {
'id': video_id,
'ext': 'mp4',
'title': info['title'],
'url': video_url,
'thumbnail': info.get('image'),
'duration': float_or_none(info.get('duration'), scale=1000),
}
class RTVELiveIE(InfoExtractor):
IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams'

View File

@@ -0,0 +1,157 @@
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveIE
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
smuggle_url,
std_headers,
)
class SafariBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/'
_SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>'
_ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com'
_NETRC_MACHINE = 'safari'
_API_BASE = 'https://www.safaribooksonline.com/api/v1/book'
_API_FORMAT = 'json'
LOGGED_IN = False
def _real_initialize(self):
# We only need to log in once for courses or individual videos
if not self.LOGGED_IN:
self._login()
SafariBaseIE.LOGGED_IN = True
def _login(self):
(username, password) = self._get_login_info()
if username is None:
raise ExtractorError(
self._ACCOUNT_CREDENTIALS_HINT,
expected=True)
headers = std_headers
if 'Referer' not in headers:
headers['Referer'] = self._LOGIN_URL
login_page = self._download_webpage(
self._LOGIN_URL, None,
'Downloading login form')
csrf = self._html_search_regex(
r"name='csrfmiddlewaretoken'\s+value='([^']+)'",
login_page, 'csrf token')
login_form = {
'csrfmiddlewaretoken': csrf,
'email': username,
'password1': password,
'login': 'Sign In',
'next': '',
}
request = compat_urllib_request.Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form), headers=headers)
login_page = self._download_webpage(
request, None, 'Logging in as %s' % username)
if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None:
raise ExtractorError(
'Login failed; make sure your credentials are correct and try again.',
expected=True)
self.to_screen('Login successful')
class SafariIE(SafariBaseIE):
IE_NAME = 'safari'
IE_DESC = 'safaribooksonline.com online video'
_VALID_URL = r'''(?x)https?://
(?:www\.)?safaribooksonline\.com/
(?:
library/view/[^/]+|
api/v1/book
)/
(?P<course_id>\d+)/
(?:chapter(?:-content)?/)?
(?P<part>part\d+)\.html
'''
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/part00.html',
'md5': '5b0c4cc1b3c1ba15dda7344085aa5592',
'info_dict': {
'id': '2842601850001',
'ext': 'mp4',
'title': 'Introduction',
},
'skip': 'Requires safaribooksonline account credentials',
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
course_id = mobj.group('course_id')
part = mobj.group('part')
webpage = self._download_webpage(
'%s/%s/chapter-content/%s.html' % (self._API_BASE, course_id, part),
part)
bc_url = BrightcoveIE._extract_brightcove_url(webpage)
if not bc_url:
raise ExtractorError('Could not extract Brightcove URL from %s' % url, expected=True)
return self.url_result(smuggle_url(bc_url, {'Referer': url}), 'Brightcove')
class SafariCourseIE(SafariBaseIE):
IE_NAME = 'safari:course'
IE_DESC = 'safaribooksonline.com online courses'
_VALID_URL = r'https?://(?:www\.)?safaribooksonline\.com/(?:library/view/[^/]+|api/v1/book)/(?P<id>\d+)/?(?:[#?]|$)'
_TESTS = [{
'url': 'https://www.safaribooksonline.com/library/view/hadoop-fundamentals-livelessons/9780133392838/',
'info_dict': {
'id': '9780133392838',
'title': 'Hadoop Fundamentals LiveLessons',
},
'playlist_count': 22,
'skip': 'Requires safaribooksonline account credentials',
}, {
'url': 'https://www.safaribooksonline.com/api/v1/book/9781449396459/?override_format=json',
'only_matching': True,
}]
def _real_extract(self, url):
course_id = self._match_id(url)
course_json = self._download_json(
'%s/%s/?override_format=%s' % (self._API_BASE, course_id, self._API_FORMAT),
course_id, 'Downloading course JSON')
if 'chapters' not in course_json:
raise ExtractorError(
'No chapters found for course %s' % course_id, expected=True)
entries = [
self.url_result(chapter, 'Safari')
for chapter in course_json['chapters']]
course_title = course_json['title']
return self.playlist_result(entries, course_id, course_title)

View File

@@ -81,60 +81,6 @@ class ScreenwaveMediaIE(InfoExtractor):
}
class CinemassacreIE(InfoExtractor):
_VALID_URL = 'https?://(?:www\.)?cinemassacre\.com/(?P<date_y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/(?P<display_id>[^?#/]+)'
_TESTS = [
{
'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
'md5': 'fde81fbafaee331785f58cd6c0d46190',
'info_dict': {
'id': 'Cinemassacre-19911',
'ext': 'mp4',
'upload_date': '20121110',
'title': '“Angry Video Game Nerd: The Movie” Trailer',
'description': 'md5:fb87405fcb42a331742a0dce2708560b',
},
},
{
'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
'md5': 'd72f10cd39eac4215048f62ab477a511',
'info_dict': {
'id': 'Cinemassacre-521be8ef82b16',
'ext': 'mp4',
'upload_date': '20131002',
'title': 'The Mummys Hand (1940)',
},
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
video_date = mobj.group('date_y') + mobj.group('date_m') + mobj.group('date_d')
webpage = self._download_webpage(url, display_id)
playerdata_url = self._search_regex(
r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"',
webpage, 'player data URL')
video_title = self._html_search_regex(
r'<title>(?P<title>.+?)\|', webpage, 'title')
video_description = self._html_search_regex(
r'<div class="entry-content">(?P<description>.+?)</div>',
webpage, 'description', flags=re.DOTALL, fatal=False)
video_thumbnail = self._og_search_thumbnail(webpage)
return {
'_type': 'url_transparent',
'display_id': display_id,
'title': video_title,
'description': video_description,
'upload_date': video_date,
'thumbnail': video_thumbnail,
'url': playerdata_url,
}
class TeamFourIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/video/(?P<id>[a-z0-9\-]+)/?'
_TEST = {

View File

@@ -0,0 +1,141 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unsmuggle_url,
)
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
class SenateISVPIE(InfoExtractor):
_COMM_MAP = [
["ag", "76440", "http://ag-f.akamaihd.net"],
["aging", "76442", "http://aging-f.akamaihd.net"],
["approps", "76441", "http://approps-f.akamaihd.net"],
["armed", "76445", "http://armed-f.akamaihd.net"],
["banking", "76446", "http://banking-f.akamaihd.net"],
["budget", "76447", "http://budget-f.akamaihd.net"],
["cecc", "76486", "http://srs-f.akamaihd.net"],
["commerce", "80177", "http://commerce1-f.akamaihd.net"],
["csce", "75229", "http://srs-f.akamaihd.net"],
["dpc", "76590", "http://dpc-f.akamaihd.net"],
["energy", "76448", "http://energy-f.akamaihd.net"],
["epw", "76478", "http://epw-f.akamaihd.net"],
["ethics", "76449", "http://ethics-f.akamaihd.net"],
["finance", "76450", "http://finance-f.akamaihd.net"],
["foreign", "76451", "http://foreign-f.akamaihd.net"],
["govtaff", "76453", "http://govtaff-f.akamaihd.net"],
["help", "76452", "http://help-f.akamaihd.net"],
["indian", "76455", "http://indian-f.akamaihd.net"],
["intel", "76456", "http://intel-f.akamaihd.net"],
["intlnarc", "76457", "http://intlnarc-f.akamaihd.net"],
["jccic", "85180", "http://jccic-f.akamaihd.net"],
["jec", "76458", "http://jec-f.akamaihd.net"],
["judiciary", "76459", "http://judiciary-f.akamaihd.net"],
["rpc", "76591", "http://rpc-f.akamaihd.net"],
["rules", "76460", "http://rules-f.akamaihd.net"],
["saa", "76489", "http://srs-f.akamaihd.net"],
["smbiz", "76461", "http://smbiz-f.akamaihd.net"],
["srs", "75229", "http://srs-f.akamaihd.net"],
["uscc", "76487", "http://srs-f.akamaihd.net"],
["vetaff", "76462", "http://vetaff-f.akamaihd.net"],
["arch", "", "http://ussenate-f.akamaihd.net/"]
]
_IE_NAME = 'senate.gov'
_VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)'
_TESTS = [{
'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',
'info_dict': {
'id': 'judiciary031715',
'ext': 'flv',
'title': 'Integrated Senate Video Player',
'thumbnail': 're:^https?://.*\.(?:jpg|png)$',
}
}, {
'url': 'http://www.senate.gov/isvp/?type=live&comm=commerce&filename=commerce011514.mp4&auto_play=false',
'info_dict': {
'id': 'commerce011514',
'ext': 'flv',
'title': 'Integrated Senate Video Player'
}
}, {
'url': 'http://www.senate.gov/isvp/?type=arch&comm=intel&filename=intel090613&hc_location=ufi',
# checksum differs each time
'info_dict': {
'id': 'intel090613',
'ext': 'mp4',
'title': 'Integrated Senate Video Player'
}
}]
@staticmethod
def _search_iframe_url(webpage):
mobj = re.search(
r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]",
webpage)
if mobj:
return mobj.group('url')
def _get_info_for_comm(self, committee):
for entry in self._COMM_MAP:
if entry[0] == committee:
return entry[1:]
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
qs = compat_parse_qs(re.match(self._VALID_URL, url).group('qs'))
if not qs.get('filename') or not qs.get('type') or not qs.get('comm'):
raise ExtractorError('Invalid URL', expected=True)
video_id = re.sub(r'.mp4$', '', qs['filename'][0])
webpage = self._download_webpage(url, video_id)
if smuggled_data.get('force_title'):
title = smuggled_data['force_title']
else:
title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, video_id)
poster = qs.get('poster')
thumbnail = poster[0] if poster else None
video_type = qs['type'][0]
committee = video_type if video_type == 'arch' else qs['comm'][0]
stream_num, domain = self._get_info_for_comm(committee)
formats = []
if video_type == 'arch':
filename = video_id if '.' in video_id else video_id + '.mp4'
formats = [{
# All parameters in the query string are necessary to prevent a 403 error
'url': compat_urlparse.urljoin(domain, filename) + '?v=3.1.0&fp=&r=&g=',
}]
else:
hdcore_sign = '?hdcore=3.1.0'
url_params = (domain, video_id, stream_num)
f4m_url = '%s/z/%s_1@%s/manifest.f4m' % url_params + hdcore_sign
m3u8_url = '%s/i/%s_1@%s/master.m3u8' % url_params
for entry in self._extract_f4m_formats(f4m_url, video_id, f4m_id='f4m'):
# URLs without the extra param induce an 404 error
entry.update({'extra_param_to_segment_url': hdcore_sign})
formats.append(entry)
for entry in self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', m3u8_id='m3u8'):
mobj = re.search(r'(?P<tag>(?:-p|-b)).m3u8', entry['url'])
if mobj:
entry['format_id'] += mobj.group('tag')
formats.append(entry)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
}

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