Compare commits

...

231 Commits

Author SHA1 Message Date
Sergey M․
d9606d9b6c release 2016.09.04 2016-09-04 20:51:48 +07:00
Remita Amine
433af6ad30 [theplatform] fix player regex(closes #10546) 2016-09-04 14:24:41 +01:00
Sergey M․
feaa5ad787 [youtube:playlist] Extend _VALID_URL 2016-09-04 20:12:34 +07:00
Remita Amine
100bd86a68 [rottentomatoes] delegate extraction to InternetVideoArchiveIE 2016-09-04 11:45:29 +01:00
Remita Amine
0def758782 [internetvideoarchive] extract all formats 2016-09-04 11:45:29 +01:00
Yen Chi Hsuan
919cf1a62f [downloader/dash] Abort if the first segment fails
Closes #10497, Closes #10542
2016-09-04 17:32:29 +08:00
Yen Chi Hsuan
b29cd56591 [pornovoisines] Fix extraction (closes #10469) 2016-09-04 17:01:39 +08:00
Yen Chi Hsuan
622638512b [rottentomatoes] Fix extraction
Closes #10467
2016-09-04 16:25:59 +08:00
Sergey M․
37c7490ac6 [espn] Extend _VALID_URL (Closes #10549) 2016-09-04 04:59:46 +07:00
Sergey M․
091624f9da [vimple] Extend _VALID_URL (Closes #10547) 2016-09-04 03:39:13 +07:00
Sergey M․
7e5dc339de [youtube:watchlater] Fix extraction (Closes #10544) 2016-09-04 00:29:01 +07:00
Sergey M․
4a69fa04e0 [downloader/dash] Abort download immediately after giving up on some fragment 2016-09-03 17:51:48 +07:00
Sergey M․
2e99cd30c3 [downloader/dash:hls] Report exact fragment error on retry 2016-09-03 17:51:48 +07:00
Sergey M․
25afc2a783 [downloader/dash:hls] Respect --fragment-retries and --skip-unavailable-fragments (Closes #10165, closes #10448) 2016-09-03 17:51:48 +07:00
Sergey M․
9603b66012 Introduce --skip-unavailable-fragments 2016-09-03 17:51:48 +07:00
Yen Chi Hsuan
45aab4d30b [youjizz] Fix extraction. The site has moved to HTML5
Closes #10437
2016-09-03 18:37:36 +08:00
Yen Chi Hsuan
ed2bfe93aa [fc2:embed] Add ie_key 2016-09-03 18:22:00 +08:00
Yen Chi Hsuan
cdc783510b [foxnews:insider] Add new extractor
Closes #10445
2016-09-03 18:16:19 +08:00
Yen Chi Hsuan
cf0efe9636 [fc2:embed] New extractor for Flash player URLs
Closes #10512
2016-09-03 17:25:03 +08:00
Christian Pointner
dedb177029 Fix parsing of HTML5 media elements
This fixes an error in _parse_html5_media_entries in case
an audio or video tag directly uses a src attribute insted
of <source> elements in it's body.
2016-09-03 16:09:35 +07:00
Sergey M․
86c3bbbced release 2016.09.03 2016-09-03 01:46:41 +07:00
Sergey M․
4b3a607658 [ChangeLog] Actualize 2016-09-03 01:45:17 +07:00
Sergey M․
3a7d35b982 Credit @C4K3 for #10536 2016-09-03 01:42:33 +07:00
Sergey M․
6496ccb413 [youtube] Add support for rental videos' previews (Closes #10532) 2016-09-03 01:17:15 +07:00
Sergey M․
3fcce30289 [drtv] Update tests 2016-09-02 23:53:17 +07:00
Sergey M․
c2b2c7e138 [utils] Add quicktime to mimetype2ext 2016-09-02 23:50:42 +07:00
Sergey M․
dacb3a864a [youtube:playlist] Fallback to video extraction for video/playlist URLs when playlist is broken (Closes #10537) 2016-09-02 23:43:20 +07:00
Sergey M․
6066d03db0 [drtv] Modernize and make more robust 2016-09-02 23:02:15 +07:00
Sergey M․
6562d34a8c [utils] Improve mimetype2ext 2016-09-02 22:57:48 +07:00
Sebastian Blunt
5e9e3d0f6b [drtv] Add support for dr.dk/nyheder
It's the same video player, the only difference is that the video player
is loaded differently, and certain metadata (title and description) is
not available under dr.dk/mu, so make it by default get that from some
of the html meta tags.

Skip the dr.dk/tv test

dr.dk/tv videos are only available for between 7 and 90 days due to
Danish law, and in certain cases may be readded. Skip this test as it is
no longer available.
2016-09-02 22:20:36 +07:00
Sergey M․
349fc5c705 [facebook:plugins:video] Add extractor (Closes #10530) 2016-09-02 21:13:50 +07:00
Remita Amine
2c3e0af93e [go] Add new extractor 2016-09-02 09:53:04 +01:00
Remita Amine
6150502e47 [adobepass] check for authz_token expiration(#10527) 2016-09-01 22:29:20 +01:00
Remita Amine
b207d5ebd4 [curiositystream] don't cache auth token 2016-09-01 19:46:58 +01:00
Remita Amine
4191779dcd [nytimes] improve extraction 2016-09-01 19:08:29 +01:00
Sergey M․
f97ec8bcb9 [glide] Remove unused import 2016-09-01 23:46:58 +07:00
Sergey M․
8276d3b87a [thestar] Fix extraction (Closes #10465) 2016-09-01 23:46:15 +07:00
Sergey M․
af95ee94b4 [glide] Fix extraction (Closes #10478) 2016-09-01 23:38:49 +07:00
Sergey M․
8fb6af6bba [exfm] Remove extractor (Closes #10482) 2016-09-01 23:32:28 +07:00
Sergey M․
f6af0f888b [youporn] Fix categories and tags extraction (Closes #10521) 2016-09-01 23:15:01 +07:00
Sergey M․
e816c9d158 [extractor/common] Simplify _extract_m3u8_formats 2016-09-01 22:18:16 +07:00
Sergey M․
9250181f37 [extractor/common] Restore NAME usage from EXT-X-MEDIA tag for formats codes in _extract_m3u8_formats (Closes #10522) 2016-09-01 21:37:25 +07:00
Remita Amine
f096ec2625 [curiositystream] Add new extractor 2016-09-01 13:37:09 +01:00
Yen Chi Hsuan
4c8ab6fd71 [thvideo] Remove extractor. Website down.
Closes #10464

According to a screenshot in http://tieba.baidu.com/p/4691302183,
thvideo.tv is shut down "temporarily". I see no clues that it will be up
again, so I remove it here.
2016-09-01 17:04:41 +08:00
Yen Chi Hsuan
05d4612947 [movingimage] Adapt to the new domain name and fix extraction
Closes #10466
2016-09-01 16:58:16 +08:00
Yen Chi Hsuan
746a695b36 [myvidster] Update _TESTS (closes #10473) 2016-09-01 16:42:35 +08:00
Yen Chi Hsuan
165c54e97d [southpark.cc.com:español] Skip geo-restricted _TESTS
Breaks https://travis-ci.org/rg3/youtube-dl/jobs/156728175
2016-09-01 16:28:03 +08:00
Remita Amine
2896dd73bc [cbs] extract once formats(closes #10515) 2016-09-01 08:00:13 +01:00
Remita Amine
f8fd510eb4 [limelight] skip ism manifests and reduce requests 2016-08-31 18:32:15 +01:00
Sergey M․
7a3e849f6e [porncom] Extract categories and tags (Closes #10510) 2016-08-31 22:23:55 +07:00
Sergey M․
196c6ba067 [facebook] Extract timestamp (Closes #10508) 2016-08-31 22:12:37 +07:00
Remita Amine
165620e320 [yahoo] extract more and better formats 2016-08-30 21:49:28 +01:00
Sergey M․
4fd350611c release 2016.08.31 2016-08-31 02:39:39 +07:00
Sergey M․
263fef43de [ChangeLog] Actualize 2016-08-31 02:37:40 +07:00
Sergey M․
a249ab83cb [pyvideo] Remove debugging code 2016-08-31 01:56:58 +07:00
Sergey M․
f7043ef39c [soundcloud] Fix _VALID_URL clashes with sets (Closes #10505) 2016-08-31 01:56:15 +07:00
Sergey M․
64fc49aba0 [bandcamp:album] Fix title extraction (Closes #10455) 2016-08-31 00:29:49 +07:00
Sergey M․
245023a861 [pyvideo] Fix extraction (Closes #10468) 2016-08-30 23:51:18 +07:00
Remita Amine
3c77a54d5d [turner] keep video id intact 2016-08-30 10:46:48 +01:00
Remita Amine
da30a20a4d [turner,cnn] move a check for wrong timestamp to CNNIE 2016-08-29 19:26:53 +01:00
Remita Amine
1fe48afea5 [cnn] update _TEST for CNNBlogsIE and CNNArticleIE(closes #10489) 2016-08-29 18:24:16 +01:00
Remita Amine
42e05be867 [ctv] add support for (tsn,bnn,thecomedynetwork).ca websites(#10016) 2016-08-29 18:24:16 +01:00
Remita Amine
fe45b0e060 [9c9media] fix multiple stacks extraction and extract more metadata(#10016) 2016-08-29 18:24:16 +01:00
Sergey M․
a06e1498aa [kusi] Update test 2016-08-29 22:54:33 +07:00
Sergey M․
5a80e7b43a [turner] Skip invalid subtitles' URLs 2016-08-29 22:44:15 +07:00
Sergey M․
3fb2a23029 [adultswim] Extract video info from onlineOriginals (Closes #10492) 2016-08-29 22:40:35 +07:00
Sergey M․
cd10b3ea63 [turner] Extract all formats 2016-08-29 22:13:49 +07:00
Sergey M․
547993dcd0 [turner] Fix subtitles extraction 2016-08-29 21:52:41 +07:00
Yen Chi Hsuan
6c9b71bc08 [downloader/external] Recommend --hls-prefer-native for SOCKS users
Related: #10490
2016-08-29 19:05:38 +08:00
Remita Amine
93b8404599 [generic,vodplatform] improve embed regex 2016-08-29 07:57:20 +01:00
Sergey M․
9ba1e1dcc0 [played] Remove extractor (Closes #10470) 2016-08-29 08:26:07 +07:00
Remita Amine
b8079a40bc [turner] fix secure m3u8 formats downloading 2016-08-28 17:51:53 +01:00
Remita Amine
5bc8a73af6 [cartoonnetwork] make extraction work for more videos in the website
some videos require `networkName=CN2` to be present in the feed url
2016-08-28 17:08:26 +01:00
Remita Amine
b3eaeded12 [tbs] Add new extractor(#10222) 2016-08-28 16:51:09 +01:00
Remita Amine
ec65b391cb [cartoonnetwork] Add new extractor(#10110) 2016-08-28 16:51:09 +01:00
Remita Amine
2982514072 [turner,nba,cnn,adultswim] add base extractor to parse cvp feeds 2016-08-28 16:51:09 +01:00
Yen Chi Hsuan
98908bcf7c [openload] Update algorithm again (#10408) 2016-08-28 22:49:46 +08:00
Yen Chi Hsuan
04b32c8f96 [bilibili] Fix extraction (closes #10375)
Thanks @gdkchan for the algorithm
2016-08-28 22:06:31 +08:00
Yen Chi Hsuan
40eec6b15c [openload] Fix extraction (closes #10408)
Thanks to @yokrysty again!
2016-08-28 20:27:52 +08:00
Yen Chi Hsuan
39efc6e3e0 [generic] Update some _TESTS 2016-08-28 15:46:11 +08:00
Sergey M․
1198fe14a1 release 2016.08.28 2016-08-28 07:24:08 +07:00
Sergey M․
71e90766b5 [README.md] Fix typo in download archive FAQ entry 2016-08-28 07:09:03 +07:00
Sergey M․
d7aae610f6 [ChangeLog] Actualize 2016-08-28 07:00:15 +07:00
Sergey M․
92c27a0dbf [periscope:user] Fix extraction (Closes #10453) 2016-08-28 02:35:49 +07:00
Yen Chi Hsuan
d181cff685 Merge branch 'steven7851-patch-2' 2016-08-27 01:17:12 +08:00
Yen Chi Hsuan
3b4b82d4ce [douyutv] Simplify 2016-08-27 01:16:39 +08:00
Yen Chi Hsuan
545ef4f531 Merge branch 'patch-2' of https://github.com/steven7851/youtube-dl into steven7851-patch-2 2016-08-26 22:29:46 +08:00
Yen Chi Hsuan
906b87cf5f [crackle] Revert to template-based thumbnail extraction
To reduce to number of HTTP requests
2016-08-26 19:58:47 +08:00
steven7851
b281aad2dc [douyutv] Use new api
use lapi for flv info, and html5 api for room info
#10153 #10318
2016-08-26 07:32:54 +08:00
Sergey M․
6b18a24e6e [tnaflix] Fix extraction (Closes #10434) 2016-08-26 05:57:52 +07:00
Sergey M․
c9de980106 Credit @Xender for nhk:vod (#10424) 2016-08-26 04:49:52 +07:00
Sergey M․
f9b373afda [nhk:vod] Improve extraction (Closes #10424) 2016-08-26 04:48:40 +07:00
Aleksander Nitecki
298a120ab7 [nhk] Add extractor for VoD. 2016-08-26 04:15:51 +07:00
Sergey M․
e3faecde30 [trutube] Remove extractor (Closes #10438) 2016-08-26 03:43:13 +07:00
Remita Amine
a0f071a50d [usanetwork] Add new extractor 2016-08-25 19:41:31 +01:00
Yen Chi Hsuan
20bad91d76 [downloader/external] Clarify that ffmpeg doesn't support SOCKS
Ref: #10304
2016-08-25 22:38:06 +08:00
Yen Chi Hsuan
b54a2da433 [crackle] Fix extraction and update _TESTS (closes #10333) 2016-08-25 22:22:31 +08:00
Yen Chi Hsuan
dc2c37f316 [spankbang] Fix description and uploader (closes #10339) 2016-08-25 20:47:35 +08:00
Philipp Hagemeister
c1f62dd338 [README] Clean up grammar in --download-archive paragraph 2016-08-25 14:45:01 +02:00
Sergey M․
5a3efcd27c [README.md] Add FAQ entry for download archive 2016-08-25 18:57:31 +07:00
Sergey M․
4c8f9c2577 [README.md] Add comments in sample configuration for clarity 2016-08-25 18:27:15 +07:00
Sergey M․
f26a298247 [README.md] Use en-US URL in cookies FAQ entry 2016-08-25 18:19:41 +07:00
Sergey M․
ea01cdbf61 [README.md] Clarify how to export cookies from browser for cookies FAQ entry 2016-08-25 18:17:45 +07:00
Sergey M․
6a76b53355 [README.md] Quote URL in streaming to player FAQ entry 2016-08-25 18:05:01 +07:00
Remita Amine
d37708fc86 [YoutubeDL] check only for None Value in thumbnails sorting 2016-08-25 11:53:47 +01:00
Remita Amine
5c13c28566 raise unexpected error when no stream found 2016-08-25 09:55:23 +01:00
Remita Amine
f70e9229e6 [discoverygo] detect when video needs authentication(closes #10425) 2016-08-25 09:11:23 +01:00
Remita Amine
30afe4aeb2 [cbc] Add support for watch.cbc.ca 2016-08-25 08:49:44 +01:00
Remita Amine
75fa990dc6 [YoutubeDL] add fallback value for thumbnails values in thumbnails sorting 2016-08-25 08:49:44 +01:00
Remita Amine
f39ffc5877 [common] extract formats from #EXT-X-MEDIA tags 2016-08-25 08:49:44 +01:00
Remita Amine
07ea9c9b05 [downloader/hls] fill IV with zeros for IVs shorter than 16-octet 2016-08-25 08:49:44 +01:00
Remita Amine
073ac1225f [utils] add ac-3 to the list of audio codecs in parse_codecs 2016-08-25 08:49:44 +01:00
Sergey M․
0c6422cdd6 [README.md] Add FAQ entry for streaming to player 2016-08-25 07:34:55 +07:00
Yen Chi Hsuan
08773689f3 [kickstarter] Silent the warning for og:description
Closes #10415
2016-08-25 01:29:32 +08:00
Yen Chi Hsuan
0c75abbb7b [mtvservices:embedded] Use another endpoint to get feed URL
Closes #10363

In the original mtvservices:embedded test case, config.xml is still used
to get the feed URL. Some other examples, including test_Generic_40
(http://www.vulture.com/2016/06/new-key-peele-sketches-released.html),
and the video mentioned in #10363, use another endpoint to get the feed
URL. The 'index.html' approach works for the original test case, too. So
I didn't keep the old approach.
2016-08-24 23:58:22 +08:00
Yen Chi Hsuan
97653f81b2 [bilibili] Mark as broken
Bilibili now uses emscripten, which is very difficult for reverse
engineering. I don't expect it to be fixed in near future, so I mark
it as broken.

Ref: #10375
2016-08-24 21:28:00 +08:00
Sergey M․
d38b27dd9b release 2016.08.24.1 2016-08-24 10:11:04 +07:00
Sergey M․
6d94cbd2f4 [ChangeLog] Actualize 2016-08-24 10:07:06 +07:00
Sergey M․
30317f4887 [pluralsight] Modernize and make more robust 2016-08-24 08:52:12 +07:00
Sergey M․
8c3e35dd44 [pluralsight] Add support for subtitles (Closes #9681) 2016-08-24 08:41:52 +07:00
Sergey M․
c86f51ee38 release 2016.08.24 2016-08-24 01:38:46 +07:00
Sergey M․
6e52bbb413 [ChangeLog] Actualize 2016-08-24 01:36:27 +07:00
Sergey M․
05bddcc512 [youtube] Fix authentication (2) (Closes #10392) 2016-08-24 01:29:50 +07:00
Sergey M․
1212e9972f [youtube] Fix authentication (#10392) 2016-08-24 00:25:21 +07:00
Remita Amine
ccb6570e9e [syfy,bravotv] restrict drupal settings regex 2016-08-23 17:31:35 +01:00
Yen Chi Hsuan
18b6216150 [openload] Fix extraction (closes #10408)
Thanks @yokrysty for the algorithm
2016-08-23 21:55:58 +08:00
Remita Amine
fb009b7f53 [bravotv] correct clip info extraction and add support for adobe pass auth(closes #10407) 2016-08-23 10:29:52 +01:00
Sergey M․
3083e4dc07 [eagleplatform] Improve detection of embedded videos (Closes #10409) 2016-08-23 07:22:14 +07:00
Remita Amine
7367bdef23 [awaan] fix extraction, modernize, rename the extractors and add test for live stream 2016-08-22 23:10:06 +01:00
Remita Amine
ad31642584 [nrk,abc:iview] use _extract_akamai_formats 2016-08-22 07:54:08 +01:00
Remita Amine
c7c43a93ba [common] add helper method to extract akamai m3u8 and f4m formats 2016-08-22 07:49:34 +01:00
Yen Chi Hsuan
96229e5f95 [mtvservices:embedded] Update config URL
All starts from #10363. The test case in mtvservices:embedded uses
config.xml, while the video from #10363 and the test case in generic.py
is broken. Both uses index.html for fetching the feed URL.
2016-08-22 13:56:09 +08:00
Remita Amine
55d119e2a1 [abc:iview] Add new extractor(closes #6148) 2016-08-22 00:07:17 +01:00
Sergey M․
6d2679ee26 release 2016.08.22 2016-08-22 04:17:34 +07:00
Sergey M․
afbab5688e [ChangeLog] Actualize 2016-08-22 04:15:46 +07:00
Sergey M․
3d897cc791 [ivi] Fix episode number extraction 2016-08-22 03:34:27 +07:00
Sergey M․
cf143c4d97 [ivi] Add support for 720p and 1080p 2016-08-22 03:31:33 +07:00
Yen Chi Hsuan
ad120ae1c5 [extractor/common] Change the default m3u8 protocol in HTML5
Helper functions should have consistent default values
2016-08-22 02:26:07 +08:00
Remita Amine
d0fa172e5f [firsttv] keep a test videos with multiple formats 2016-08-21 19:13:43 +01:00
Yen Chi Hsuan
f97f9f71e5 Merge branch 'TRox1972-charlierose' 2016-08-22 02:11:43 +08:00
Yen Chi Hsuan
526656726b [charlierose] Simplify and improve 2016-08-22 02:06:47 +08:00
Remita Amine
9b8c554ea7 [firsttv] fix extraction(closes #9249) 2016-08-21 17:56:25 +01:00
Yen Chi Hsuan
d13bfc07b7 Merge branch 'charlierose' of https://github.com/TRox1972/youtube-dl into TRox1972-charlierose 2016-08-22 00:48:35 +08:00
Sergey M․
efe470e261 [twitch] Renew authentication 2016-08-21 22:45:50 +07:00
Sergey M․
e3f6b56909 [twitch] Refactor API calls 2016-08-21 22:09:29 +07:00
Sergey M․
b1e676fde8 [twitch] Modernize 2016-08-21 21:28:02 +07:00
Sergey M․
92d4cfa358 [kaltura] Fallback ext calculation on caption's format 2016-08-21 21:01:01 +07:00
Remita Amine
3d47ee0a9e [zingmp3] fix extraction and add support for video clips(closes #10041) 2016-08-21 14:09:48 +01:00
Yen Chi Hsuan
d164a0d41b [README.md] Add a format selection example using comma
Ref: #10399
2016-08-21 20:00:48 +08:00
Déstin Reed
db29af6d36 [charlierose] Add new extractor 2016-08-21 11:29:48 +02:00
Sergey M․
2c6acdfd2d [kaltura] Add test for #10279 2016-08-21 08:37:01 +07:00
Sergey M․
fddaa76a59 [kaltura] Assume ttml to be default subtitles' extension 2016-08-21 08:28:36 +07:00
Sergey M․
a809446750 [kaltura] Add subtitles support when entry_id is unknown beforehand (Closes #10279) 2016-08-21 08:28:36 +07:00
Sergey M․
d8f30a7e66 [kaltura] Remove unused code 2016-08-21 08:28:36 +07:00
Sergey M․
5b1d85754e [YoutubeDL] Autocalculate ext when ext is None 2016-08-21 08:28:36 +07:00
Remita Amine
e25586e471 [cultureunplugged] fix extraction(closes #10330) 2016-08-20 20:02:49 +01:00
Remita Amine
292a2301bf [cnn] add support for money.cnn.com videos(closes #2797) 2016-08-20 19:00:25 +01:00
Remita Amine
dabe15701b [cbs, cbsnews] fix extraction(fixes #10393) 2016-08-20 13:25:32 +01:00
Sergey M․
4245f55880 [dotsub] Replace test (Closes #10386) 2016-08-20 06:18:20 +07:00
Déstin Reed
5b9d187cc6 [imdb] Improve title extraction and make thumbnail non-fatal 2016-08-20 04:50:39 +07:00
Yen Chi Hsuan
39e1c4f08c [litv] Support 'promo' URLs (closes #10385) 2016-08-20 00:52:37 +08:00
Yen Chi Hsuan
19f35402c5 [snotr] Fix extraction (closes #10338) 2016-08-20 00:18:22 +08:00
Yen Chi Hsuan
70852b47ca [utils] Recognize units with full names in parse_filename
Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-20 00:17:26 +08:00
Yen Chi Hsuan
a9a3b4a081 [miomio] Adapt to the new API and update _TESTS
The test case is from #9680
2016-08-20 00:08:23 +08:00
Yen Chi Hsuan
ecc90093f9 [vuclip] Adapt to the new API and update _TEST 2016-08-19 23:56:09 +08:00
Yen Chi Hsuan
520251c093 [extractor/common] Recognize m3u8 manifests in HTML5 multimedia tags 2016-08-19 23:53:47 +08:00
Yen Chi Hsuan
55af45fcab [radiobremen] Update _TEST (closes #10337) 2016-08-19 23:12:30 +08:00
Yen Chi Hsuan
b82232036a [n-tv.de] Fix extraction (closes #10331) 2016-08-19 20:39:28 +08:00
Yen Chi Hsuan
e4659b4547 [utils] Correct octal/hexadecimal number detection in js_to_json 2016-08-19 20:37:17 +08:00
Sergey M․
9e5751b9fe [globo:article] Relax _VALID_URL and video id regex (Closes #10379) 2016-08-19 01:13:45 +07:00
Sergey M․
bd1bcd3ea0 release 2016.08.19 2016-08-19 00:15:12 +07:00
Sergey M․
93a63b36f1 [ChangeLog] Actualize 2016-08-19 00:13:24 +07:00
Sergey M․
8b2dc4c328 [options] Remove output template description from --help
Same reasons as for --format
2016-08-18 23:59:13 +07:00
Sergey M․
850837b67a [porncom] Add extractor (Closes #2251, closes #10251) 2016-08-18 23:52:41 +07:00
Sergey M․
13585d7682 [utils] Recognize lowercase units in parse_filesize 2016-08-18 23:32:00 +07:00
Sergey M․
fd3ec986a4 [generic] Fix dbtv test (Closes #10364) 2016-08-18 21:35:41 +07:00
Sergey M․
b0d578ff7b [dbtv] Relax embed regex 2016-08-18 21:30:55 +07:00
Déstin Reed
b0c8f2e9c8 [DBTV:generic] Add support for embeds 2016-08-18 21:29:27 +07:00
Sergey M․
51815886a9 [vk:wallpost] Fix audio extraction 2016-08-18 06:14:05 +07:00
Sergey M․
08a42f9c74 [vk] Fix authentication on python3 2016-08-18 05:22:23 +07:00
Sergey M․
e15ad9ef09 [keezmovies] PEP 8 2016-08-18 04:39:31 +07:00
Sergey M․
4e9fee1015 [hgtvcom:show] Add extractor (Closes #10365) 2016-08-18 04:37:14 +07:00
Remita Amine
7273e5849b [discoverygo] extend _VALID_URL to support other networks 2016-08-17 11:03:09 +01:00
Sergey M․
b505e98784 [extremetube] Revert display_id 2016-08-17 07:02:13 +07:00
Sergey M․
92cd9fd565 [keezmovies] Make display_id optional 2016-08-17 07:01:32 +07:00
Sergey M․
b3d7dce429 release 2016.08.17 2016-08-17 06:21:21 +07:00
Sergey M․
a44694ab4e [ChangeLog] Actualize 2016-08-17 06:19:22 +07:00
Sergey M․
ab19b46b88 [extremetube] Modernize 2016-08-17 06:02:12 +07:00
Sergey M․
8804f10e6b [tube8] Modernize 2016-08-17 05:46:45 +07:00
Sergey M․
6be17c0870 [mofosex] Extract all formats and modernize (Closes #10335) 2016-08-17 05:45:49 +07:00
Sergey M․
8652770bd2 [keezmovies] Improve and modernize 2016-08-17 05:44:46 +07:00
Sergey M․
2a1321a272 [vbox7:generic] Add support for vbox7 embeds 2016-08-17 01:02:59 +07:00
Sergey M․
9c0fa60bf3 [vbox7] Add support for embed URLs 2016-08-17 00:42:02 +07:00
Sergey M․
502d87c546 [mtg] Improve view count extraction 2016-08-17 00:32:28 +07:00
Sergey M․
b35b0d73d8 [viafree] Add extractor (Closes #10358) 2016-08-17 00:21:30 +07:00
Sergey M․
6e7e4a6edf [mtg] Add support for viafree URLs (#10358) 2016-08-17 00:19:43 +07:00
Remita Amine
53fef319f1 [fxnetworks] extend _VALID_URL to support simpsonsworld.com 2016-08-16 16:22:34 +01:00
Remita Amine
2cabee2a7d [amcnetworks] fix typo 2016-08-16 16:22:34 +01:00
Remita Amine
11f502fac1 [theplatform] extract subtitles with multiple formats from the metadata 2016-08-16 16:22:34 +01:00
Sergey M․
98affc1a48 [xvideos] Fix test 2016-08-16 21:20:15 +07:00
Sergey M․
70a2829fee [xvideos] Fix HLS extraction (Closes #10356) 2016-08-16 21:17:52 +07:00
Remita Amine
837e56c8ee [amcnetworks] extract episode metadata 2016-08-16 14:49:32 +01:00
Remita Amine
b5ddee8c77 [amcnetworks] Add new extractor 2016-08-16 13:44:01 +01:00
Sergey M․
fb64adcbd3 [adobepass] PEP 8 2016-08-16 04:45:21 +07:00
Sergey M․
4f640f2890 [bbc:playlist] Fix tests 2016-08-16 04:43:10 +07:00
Sergey M․
254e64a20a [bbc:playlist] Add support for pagination (Closes #10349) 2016-08-16 04:36:23 +07:00
Remita Amine
818ac213eb [adobepass] add IE suffix to the extractor and remove duplicate constant 2016-08-15 21:36:34 +01:00
Remita Amine
cbef4d5c9f [fxnetworks] add test and check geo restriction 2016-08-15 17:10:45 +01:00
Remita Amine
bf90c46790 [fxnetworks] Add new extractor(closes #9462) 2016-08-15 16:34:32 +01:00
Yen Chi Hsuan
69eb4d699f [cbsnews] Remove invalid tests. CBS Live videos gets deleted soon. 2016-08-15 20:29:22 +08:00
Yen Chi Hsuan
6d8ec8c3b7 [ChangeLog] Update for CBSLocal and related changes 2016-08-15 13:39:43 +08:00
Yen Chi Hsuan
760845ce99 [cbslocal] Adapt to SendtoNewsIE 2016-08-15 13:37:37 +08:00
Yen Chi Hsuan
5c2d087221 [sendtonews] Fix extraction 2016-08-15 13:31:08 +08:00
Yen Chi Hsuan
b6c4e36728 [jwplatform] Parse video_id from JWPlayer data
And remove a mysterious comma from 115c65793a
2016-08-15 13:29:01 +08:00
Sergey M․
1a57b8c18c [zippcast] Remove extractor (Closes #10332)
ZippCast is shut down
2016-08-15 08:25:24 +07:00
Remita Amine
24eb13b1c6 [uplynk,viceland] update tests and change uplynk extractors names 2016-08-14 22:45:43 +01:00
Remita Amine
525e0316c0 [adobepass] fix check for pendingLogout errors 2016-08-14 21:25:43 +01:00
Remita Amine
7e60ce9cf7 [adobepass] clear cache in case of pendingLogout errors 2016-08-14 21:24:33 +01:00
Remita Amine
e811bcf8f8 [viceland] raise ExtractorError for errors other than HTTP 400 2016-08-14 20:13:35 +01:00
Remita Amine
6103f59095 [viceland] remove outdated comment 2016-08-14 19:08:35 +01:00
Remita Amine
9fa5789279 [viceland] fix info extraction(closes #8799) 2016-08-14 19:04:23 +01:00
Remita Amine
d2ac04674d [viceland] Add new extractor(#8799) 2016-08-14 18:04:50 +01:00
Remita Amine
1fd6e30988 [adobepass] create separate class for adobe pass authentication 2016-08-14 18:04:50 +01:00
Sergey M․
884cdb6cd9 [life:embed] Improve extraction 2016-08-14 20:49:11 +07:00
Remita Amine
9771b1f901 [theplatform] use _get_netrc_login_info and fix session expiration check(#10345) 2016-08-14 11:55:28 +01:00
Remita Amine
2118fdd1a9 [common] add separate method for getting netrc ligin info 2016-08-14 11:55:28 +01:00
Sergey M․
320d597c21 [vgtv] Detect geo restricted videos (#10348) 2016-08-14 16:25:14 +07:00
Remita Amine
aaf44a2f47 [uplynk] Add new extractor 2016-08-13 22:53:41 +01:00
Yen Chi Hsuan
fafabc0712 Update ChangeLog for #10342
[skip ci]
2016-08-14 02:33:15 +08:00
Yen Chi Hsuan
409760a932 Merge pull request #10342 from muphil/patch-1
[xiami] bug fix for extractor xiami.py
2016-08-14 02:30:50 +08:00
phi
097eba019d bug fix for extractor xiami.py
Before applying this patch, when downloading resources from xiami.com, it crashes with these:
Traceback (most recent call last):
  File "/home/phi/.local/bin/youtube-dl", line 11, in <module>
    sys.exit(main())
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/__init__.py", line 433, in main
    _real_main(argv)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/__init__.py", line 423, in _real_main
    retcode = ydl.download(all_urls)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/YoutubeDL.py", line 1786, in download
    url, force_generic_extractor=self.params.get('force_generic_extractor', False))
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/YoutubeDL.py", line 691, in extract_info
    ie_result = ie.extract(url)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/extractor/common.py", line 347, in extract
    return self._real_extract(url)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/extractor/xiami.py", line 116, in _real_extract
    return self._extract_tracks(self._match_id(url))[0]
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/extractor/xiami.py", line 43, in _extract_tracks
    '%s/%s%s' % (self._API_BASE_URL, item_id, '/type/%s' % typ if typ else ''), item_id)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/extractor/common.py", line 562, in _download_json
    json_string, video_id, transform_source=transform_source, fatal=fatal)
  File "/home/phi/.local/lib/python3.5/site-packages/youtube_dl/extractor/common.py", line 568, in _parse_json
    return json.loads(json_string)
  File "/usr/lib/python3.5/json/__init__.py", line 312, in loads
    s.__class__.__name__))
TypeError: the JSON object must be str, not 'NoneType'

This patch solves exactly this problem.
2016-08-14 02:18:59 +08:00
125 changed files with 4245 additions and 2148 deletions

View File

@@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.08.13*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.08.13**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2016.09.04*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2016.09.04**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2016.08.13
[debug] youtube-dl version 2016.09.04
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

View File

@@ -181,3 +181,5 @@ Nehal Patel
Rob van Bekkum
Petr Zvoníček
Pratyush Singh
Aleksander Nitecki
Sebastian Blunt

180
ChangeLog
View File

@@ -1,3 +1,182 @@
version 2016.09.04
Core
* If the first segment of DASH fails, abort the whole download process to
prevent throttling (#10497)
Extractors
* [pornvoisines] Fix extraction (#10469)
* [rottentomatoes] Fix extraction (#10467)
* [youjizz] Fix extraction (#10437)
+ [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512)
version 2016.09.03
Core
* Restore usage of NAME attribute from EXT-X-MEDIA tag for formats codes in
_extract_m3u8_formats (#10522)
* Handle semicolon in mimetype2ext
Extractors
+ [youtube] Add support for rental videos' previews (#10532)
* [youtube:playlist] Fallback to video extraction for video/playlist URLs when
no playlist is actually served (#10537)
+ [drtv] Add support for dr.dk/nyheder (#10536)
+ [facebook:plugins:video] Add extractor (#10530)
+ [go] Add extractor for *.go.com sites
* [adobepass] Check for authz_token expiration (#10527)
* [nytimes] improve extraction
* [thestar] Fix extraction (#10465)
* [glide] Fix extraction (#10478)
- [exfm] Remove extractor (#10482)
* [youporn] Fix categories and tags extraction (#10521)
+ [curiositystream] Add extractor for app.curiositystream.com
- [thvideo] Remove extractor (#10464)
* [movingimage] Fix for the new site name (#10466)
+ [cbs] Add support for once formats (#10515)
* [limelight] Skip ism snd duplicate manifests
+ [porncom] Extract categories and tags (#10510)
+ [facebook] Extract timestamp (#10508)
+ [yahoo] Extract more formats
version 2016.08.31
Extractors
* [soundcloud] Fix URL regular expression to avoid clashes with sets (#10505)
* [bandcamp:album] Fix title extraction (#10455)
* [pyvideo] Fix extraction (#10468)
+ [ctv] Add support for tsn.ca, bnn.ca and thecomedynetwork.ca (#10016)
* [9c9media] Extract more metadata
* [9c9media] Fix multiple stacks extraction (#10016)
* [adultswim] Improve video info extraction (#10492)
* [vodplatform] Improve embed regular expression
- [played] Remove extractor (#10470)
+ [tbs] Add extractor for tbs.com and tntdrama.com (#10222)
+ [cartoonnetwork] Add extractor for cartoonnetwork.com (#10110)
* [adultswim] Rework in terms of turner extractor
* [cnn] Rework in terms of turner extractor
* [nba] Rework in terms of turner extractor
+ [turner] Add base extractor for Turner Broadcasting System based sites
* [bilibili] Fix extraction (#10375)
* [openload] Fix extraction (#10408)
version 2016.08.28
Core
+ Add warning message that ffmpeg doesn't support SOCKS
* Improve thumbnail sorting
+ Extract formats from #EXT-X-MEDIA tags in _extract_m3u8_formats
* Fill IV with leading zeros for IVs shorter than 16 octets in hlsnative
+ Add ac-3 to the list of audio codecs in parse_codecs
Extractors
* [periscope:user] Fix extraction (#10453)
* [douyutv] Fix extraction (#10153, #10318, #10444)
+ [nhk:vod] Add extractor for www3.nhk.or.jp on demand (#4437, #10424)
- [trutube] Remove extractor (#10438)
+ [usanetwork] Add extractor for usanetwork.com
* [crackle] Fix extraction (#10333)
* [spankbang] Fix description and uploader extraction (#10339)
* [discoverygo] Detect cable provider restricted videos (#10425)
+ [cbc] Add support for watch.cbc.ca
* [kickstarter] Silent the warning for og:description (#10415)
* [mtvservices:embedded] Fix extraction for the new 'edge' player (#10363)
version 2016.08.24.1
Extractors
+ [pluralsight] Add support for subtitles (#9681)
version 2016.08.24
Extractors
* [youtube] Fix authentication (#10392)
* [openload] Fix extraction (#10408)
+ [bravotv] Add support for Adobe Pass (#10407)
* [bravotv] Fix clip info extraction (#10407)
* [eagleplatform] Improve embedded videos detection (#10409)
* [awaan] Fix extraction
* [mtvservices:embedded] Update config URL
+ [abc:iview] Add extractor (#6148)
version 2016.08.22
Core
* Improve formats and subtitles extension auto calculation
+ Recognize full unit names in parse_filesize
+ Add support for m3u8 manifests in HTML5 multimedia tags
* Fix octal/hexadecimal number detection in js_to_json
Extractors
+ [ivi] Add support for 720p and 1080p
+ [charlierose] Add new extractor (#10382)
* [1tv] Fix extraction (#9249)
* [twitch] Renew authentication
* [kaltura] Improve subtitles extension calculation
+ [zingmp3] Add support for video clips
* [zingmp3] Fix extraction (#10041)
* [kaltura] Improve subtitles extraction (#10279)
* [cultureunplugged] Fix extraction (#10330)
+ [cnn] Add support for money.cnn.com (#2797)
* [cbsnews] Fix extraction (#10362)
* [cbs] Fix extraction (#10393)
+ [litv] Support 'promo' URLs (#10385)
* [snotr] Fix extraction (#10338)
* [n-tv.de] Fix extraction (#10331)
* [globo:article] Relax URL and video id regular expressions (#10379)
version 2016.08.19
Core
- Remove output template description from --help
* Recognize lowercase units in parse_filesize
Extractors
+ [porncom] Add extractor for porn.com (#2251, #10251)
+ [generic] Add support for DBTV embeds
* [vk:wallpost] Fix audio extraction for new site layout
* [vk] Fix authentication
+ [hgtvcom:show] Add extractor for hgtv.com shows (#10365)
+ [discoverygo] Add support for another GO network sites
version 2016.08.17
Core
+ Add _get_netrc_login_info
Extractors
* [mofosex] Extract all formats (#10335)
+ [generic] Add support for vbox7 embeds
+ [vbox7] Add support for embed URLs
+ [viafree] Add extractor (#10358)
+ [mtg] Add support for viafree URLs (#10358)
* [theplatform] Extract all subtitles per language
+ [xvideos] Fix HLS extraction (#10356)
+ [amcnetworks] Add extractor
+ [bbc:playlist] Add support for pagination (#10349)
+ [fxnetworks] Add extractor (#9462)
* [cbslocal] Fix extraction for SendtoNews-based videos
* [sendtonews] Fix extraction
* [jwplatform] Extract video id from JWPlayer data
- [zippcast] Remove extractor (#10332)
+ [viceland] Add extractor (#8799)
+ [adobepass] Add base extractor for Adobe Pass Authentication
* [life:embed] Improve extraction
* [vgtv] Detect geo restricted videos (#10348)
+ [uplynk] Add extractor
* [xiami] Fix extraction (#10342)
version 2016.08.13
Core
@@ -23,6 +202,7 @@ Extractors
+ [pbs] Add support for high quality HTTP formats
+ [crunchyroll] Add support for HLS formats (#10301)
version 2016.08.12
Core

View File

@@ -89,6 +89,8 @@ which means you can modify it, redistribute it or use it however you like.
--mark-watched Mark videos watched (YouTube only)
--no-mark-watched Do not mark videos watched (YouTube only)
--no-color Do not emit color codes in output
--abort-on-unavailable-fragment Abort downloading when some fragment is not
available
## Network Options:
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
@@ -173,7 +175,10 @@ which means you can modify it, redistribute it or use it however you like.
-R, --retries RETRIES Number of retries (default is 10), or
"infinite".
--fragment-retries RETRIES Number of retries for a fragment (default
is 10), or "infinite" (DASH only)
is 10), or "infinite" (DASH and hlsnative
only)
--skip-unavailable-fragments Skip unavailable fragments (DASH and
hlsnative only)
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
(default is 1024)
--no-resize-buffer Do not automatically adjust the buffer
@@ -201,32 +206,8 @@ which means you can modify it, redistribute it or use it however you like.
-a, --batch-file FILE File containing URLs to download ('-' for
stdin)
--id Use only video ID in file name
-o, --output TEMPLATE Output filename template. Use %(title)s to
get the title, %(uploader)s for the
uploader name, %(uploader_id)s for the
uploader nickname if different,
%(autonumber)s to get an automatically
incremented number, %(ext)s for the
filename extension, %(format)s for the
format description (like "22 - 1280x720" or
"HD"), %(format_id)s for the unique id of
the format (like YouTube's itags: "137"),
%(upload_date)s for the upload date
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the
video id, %(playlist_title)s,
%(playlist_id)s, or %(playlist)s (=title if
present, ID otherwise) for the playlist the
video is in, %(playlist_index)s for the
position in the playlist. %(height)s and
%(width)s for the width and height of the
video format. %(resolution)s for a textual
description of the resolution of the video
format. %% for a literal percent. Use - to
output to stdout. Can also be used to
download to a different directory, for
example with -o '/my/downloads/%(uploader)s
/%(title)s-%(id)s.%(ext)s' .
-o, --output TEMPLATE Output filename template, see the "OUTPUT
TEMPLATE" for all the info
--autonumber-size NUMBER Specify the number of digits in
%(autonumber)s when it is present in output
filename template or --auto-number option
@@ -436,11 +417,19 @@ You can configure youtube-dl by placing any supported command line option to a c
For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
```
-x
--no-mtime
--proxy 127.0.0.1:3128
-o ~/Movies/%(title)s.%(ext)s
# Lines starting with # are comments
# Always extract audio
-x
# Do not copy the mtime
--no-mtime
# Use this proxy
--proxy 127.0.0.1:3128
# Save all videos under Movies directory in your home directory
-o ~/Movies/%(title)s.%(ext)s
```
Note that options in configuration file are just the same options aka switches used in regular command line calls thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`.
@@ -669,7 +658,11 @@ $ youtube-dl -f 'best[filesize<50M]'
# Download best format available via direct link over HTTP/HTTPS protocol
$ youtube-dl -f '(bestvideo+bestaudio/best)[protocol^=http]'
# Download the best video format and the best audio format without merging them
$ youtube-dl -f 'bestvideo,bestaudio' -o '%(title)s.f%(format_id)s.%(ext)s'
```
Note that in the last example, an output template is recommended as bestvideo and bestaudio may have the same file name.
# VIDEO SELECTION
@@ -750,7 +743,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
### I have downloaded a video but how can I play it?
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org/) or [mplayer](http://www.mplayerhq.hu/).
### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
@@ -832,10 +825,32 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
### How do I pass cookies to youtube-dl?
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
### How do I stream directly to media player?
You will first need to tell youtube-dl to stream media to stdout with `-o -`, and also tell your media player to read from stdin (it must be capable of this for streaming) and then pipe former to latter. For example, streaming to [vlc](http://www.videolan.org/) can be achieved with:
youtube-dl -o - "http://www.youtube.com/watch?v=BaW_jenozKcj" | vlc -
### How do I download only new videos from a playlist?
Use download-archive feature. With this feature you should initially download the complete playlist with `--download-archive /path/to/download/archive/file.txt` that will record identifiers of all the videos in a special file. Each subsequent run with the same `--download-archive` will download only new videos and skip all videos that have been downloaded before. Note that only successful downloads are recorded in the file.
For example, at first,
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
will download the complete `PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re` playlist and create a file `archive.txt`. Each subsequent run will only download new videos if any:
youtube-dl --download-archive archive.txt "https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re"
### Can you add support for this anime video site, or site which shows current movies for free?
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.

View File

@@ -13,9 +13,12 @@
- **5min**
- **8tracks**
- **91porn**
- **9c9media**
- **9c9media:stack**
- **9gag**
- **9now.com.au**
- **abc.net.au**
- **abc.net.au:iview**
- **Abc7News**
- **abcnews**
- **abcnews:video**
@@ -35,6 +38,7 @@
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **AMCNetworks**
- **AnimeOnDemand**
- **anitube.se**
- **AnySex**
@@ -65,6 +69,10 @@
- **audiomack**
- **audiomack:album**
- **auroravid**: AuroraVid
- **AWAAN**
- **awaan:live**
- **awaan:season**
- **awaan:video**
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
@@ -109,8 +117,11 @@
- **Canvas**
- **CarambaTV**
- **CarambaTVPage**
- **CBC**
- **CBCPlayer**
- **CartoonNetwork**
- **cbc.ca**
- **cbc.ca:player**
- **cbc.ca:watch**
- **cbc.ca:watch:video**
- **CBS**
- **CBSInteractive**
- **CBSLocal**
@@ -120,6 +131,7 @@
- **CDA**
- **CeskaTelevize**
- **channel9**: Channel 9
- **CharlieRose**
- **Chaturbate**
- **Chilloutzone**
- **chirbit**
@@ -159,6 +171,8 @@
- **CTVNews**
- **culturebox.francetvinfo.fr**
- **CultureUnplugged**
- **curiositystream**
- **curiositystream:collection**
- **CWTV**
- **DailyMail**
- **dailymotion**
@@ -170,10 +184,6 @@
- **daum.net:playlist**
- **daum.net:user**
- **DBTV**
- **DCN**
- **dcn:live**
- **dcn:season**
- **dcn:video**
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
@@ -215,13 +225,14 @@
- **EsriVideo**
- **Europa**
- **EveryonesMixtape**
- **exfm**: ex.fm
- **ExpoTV**
- **ExtremeTube**
- **EyedoTV**
- **facebook**
- **FacebookPluginsVideo**
- **faz.net**
- **fc2**
- **fc2:embed**
- **Fczenit**
- **features.aol.com**
- **fernsehkritik.tv**
@@ -235,6 +246,7 @@
- **FOX**
- **Foxgay**
- **FoxNews**: Fox News and Fox Business Video
- **foxnews:insider**
- **FoxSports**
- **france2.fr:generation-quoi**
- **FranceCulture**
@@ -247,6 +259,7 @@
- **Funimation**
- **FunnyOrDie**
- **Fusion**
- **FXNetworks**
- **GameInformer**
- **GameOne**
- **gameone:playlist**
@@ -262,6 +275,7 @@
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GloboArticle**
- **Go**
- **GodTube**
- **GodTV**
- **Golem**
@@ -277,6 +291,7 @@
- **Helsinki**: helsinki.fi
- **HentaiStigma**
- **HGTV**
- **hgtv.com:show**
- **HistoricFilms**
- **history:topic**: History.com Topic
- **hitbox**
@@ -396,8 +411,10 @@
- **MovieClips**
- **MovieFap**
- **Moviezine**
- **MovingImage**
- **MPORA**
- **MSN**
- **mtg**: MTG services
- **MTV**
- **mtv.de**
- **mtvservices:embedded**
@@ -442,6 +459,7 @@
- **NextMediaActionNews**: 蘋果日報 - 動新聞
- **nfb**: National Film Board of Canada
- **nfl.com**
- **NhkVod**
- **nhl.com**
- **nhl.com:news**: NHL news
- **nhl.com:videocenter**
@@ -450,7 +468,6 @@
- **nick.de**
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **NineCNineMedia**
- **Nintendo**
- **njoy**: N-JOY
- **njoy:embed**
@@ -508,7 +525,6 @@
- **Pinkbike**
- **Pladform**
- **play.fm**
- **played.to**
- **PlaysTV**
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
- **Playvid**
@@ -520,6 +536,7 @@
- **podomatic**
- **Pokemon**
- **PolskieRadio**
- **PornCom**
- **PornHd**
- **PornHub**: PornHub and Thumbzilla
- **PornHubPlaylist**
@@ -648,7 +665,6 @@
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
@@ -665,6 +681,7 @@
- **Tagesschau**
- **tagesschau:player**
- **Tass**
- **TBS**
- **TDSLifeway**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
@@ -690,8 +707,6 @@
- **TheStar**
- **ThisAmericanLife**
- **ThisAV**
- **THVideo**
- **THVideoPlaylist**
- **tinypic**: tinypic.com videos
- **tlc.de**
- **TMZ**
@@ -706,7 +721,6 @@
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **trollvids**
- **TruTube**
- **Tube8**
- **TubiTv**
- **tudou**
@@ -731,7 +745,6 @@
- **tvp**: Telewizja Polska
- **tvp:embed**: Telewizja Polska
- **tvp:series**
- **TVPlay**: TV3Play and related services
- **Tweakers**
- **twitch:chapter**
- **twitch:clips**
@@ -748,8 +761,11 @@
- **UDNEmbed**: 聯合影音
- **Unistra**
- **uol.com.br**
- **uplynk**
- **uplynk:preplay**
- **Urort**: NRK P3 Urørt
- **URPlay**
- **USANetwork**
- **USAToday**
- **ustream**
- **ustream:channel**
@@ -765,7 +781,9 @@
- **VevoPlaylist**
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **Viafree**
- **Vice**
- **Viceland**
- **ViceShow**
- **Vidbit**
- **Viddler**
@@ -885,6 +903,4 @@
- **Zapiks**
- **ZDF**
- **ZDFChannel**
- **zingmp3:album**: mp3.zing.vn albums
- **zingmp3:song**: mp3.zing.vn songs
- **ZippCast**
- **zingmp3**: mp3.zing.vn

View File

@@ -39,6 +39,7 @@ from youtube_dl.utils import (
is_html,
js_to_json,
limit_length,
mimetype2ext,
ohdave_rsa_encrypt,
OnDemandPagedList,
orderedSet,
@@ -625,6 +626,14 @@ class TestUtil(unittest.TestCase):
limit_length('foo bar baz asd', 12).startswith('foo bar'))
self.assertTrue('...' in limit_length('foo bar baz asd', 12))
def test_mimetype2ext(self):
self.assertEqual(mimetype2ext(None), None)
self.assertEqual(mimetype2ext('video/x-flv'), 'flv')
self.assertEqual(mimetype2ext('application/x-mpegURL'), 'm3u8')
self.assertEqual(mimetype2ext('text/vtt'), 'vtt')
self.assertEqual(mimetype2ext('text/vtt;charset=utf-8'), 'vtt')
self.assertEqual(mimetype2ext('text/html; charset=utf-8'), 'html')
def test_parse_codecs(self):
self.assertEqual(parse_codecs(''), {})
self.assertEqual(parse_codecs('avc1.77.30, mp4a.40.2'), {
@@ -712,6 +721,9 @@ class TestUtil(unittest.TestCase):
inp = '''{"foo":101}'''
self.assertEqual(js_to_json(inp), '''{"foo":101}''')
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@@ -817,7 +829,10 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_filesize('2 MiB'), 2097152)
self.assertEqual(parse_filesize('5 GB'), 5000000000)
self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
self.assertEqual(parse_filesize('1.2tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
self.assertEqual(parse_filesize('1,24 kb'), 1240)
self.assertEqual(parse_filesize('8.5 megabytes'), 8500000)
def test_parse_count(self):
self.assertEqual(parse_count(None), None)

View File

@@ -1256,8 +1256,10 @@ class YoutubeDL(object):
info_dict['thumbnails'] = thumbnails = [{'url': thumbnail}]
if thumbnails:
thumbnails.sort(key=lambda t: (
t.get('preference'), t.get('width'), t.get('height'),
t.get('id'), t.get('url')))
t.get('preference') if t.get('preference') is not None else -1,
t.get('width') if t.get('width') is not None else -1,
t.get('height') if t.get('height') is not None else -1,
t.get('id') if t.get('id') is not None else '', t.get('url')))
for i, t in enumerate(thumbnails):
t['url'] = sanitize_url(t['url'])
if t.get('width') and t.get('height'):
@@ -1299,7 +1301,7 @@ class YoutubeDL(object):
for subtitle_format in subtitle:
if subtitle_format.get('url'):
subtitle_format['url'] = sanitize_url(subtitle_format['url'])
if 'ext' not in subtitle_format:
if subtitle_format.get('ext') is None:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
if self.params.get('listsubtitles', False):
@@ -1354,7 +1356,7 @@ class YoutubeDL(object):
note=' ({0})'.format(format['format_note']) if format.get('format_note') is not None else '',
)
# Automatically determine file extension if missing
if 'ext' not in format:
if format.get('ext') is None:
format['ext'] = determine_ext(format['url']).lower()
# Automatically determine protocol if missing (useful for format
# selection purposes)

View File

@@ -318,6 +318,7 @@ def _real_main(argv=None):
'nooverwrites': opts.nooverwrites,
'retries': opts.retries,
'fragment_retries': opts.fragment_retries,
'skip_unavailable_fragments': opts.skip_unavailable_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl,

View File

@@ -38,8 +38,10 @@ class DashSegmentsFD(FragmentFD):
segments_filenames = []
fragment_retries = self.params.get('fragment_retries', 0)
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
def append_url_to_file(target_url, tmp_filename, segment_name):
def process_segment(segment, tmp_filename, fatal):
target_url, segment_name = segment
target_filename = '%s-%s' % (tmp_filename, segment_name)
count = 0
while count <= fragment_retries:
@@ -52,26 +54,35 @@ class DashSegmentsFD(FragmentFD):
down.close()
segments_filenames.append(target_sanitized)
break
except (compat_urllib_error.HTTPError, ) as err:
except compat_urllib_error.HTTPError as err:
# YouTube may often return 404 HTTP error for a fragment causing the
# whole download to fail. However if the same fragment is immediately
# retried with the same request data this usually succeeds (1-2 attemps
# is usually enough) thus allowing to download the whole file successfully.
# So, we will retry all fragments that fail with 404 HTTP error for now.
if err.code != 404:
raise
# Retry fragment
# To be future-proof we will retry all fragments that fail with any
# HTTP error.
count += 1
if count <= fragment_retries:
self.report_retry_fragment(segment_name, count, fragment_retries)
self.report_retry_fragment(err, segment_name, count, fragment_retries)
if count > fragment_retries:
if not fatal:
self.report_skip_fragment(segment_name)
return True
self.report_error('giving up after %s fragment retries' % fragment_retries)
return False
return True
if initialization_url:
append_url_to_file(initialization_url, ctx['tmpfilename'], 'Init')
for i, segment_url in enumerate(segment_urls):
append_url_to_file(segment_url, ctx['tmpfilename'], 'Seg%d' % i)
segments_to_download = [(initialization_url, 'Init')] if initialization_url else []
segments_to_download.extend([
(segment_url, 'Seg%d' % i)
for i, segment_url in enumerate(segment_urls)])
for i, segment in enumerate(segments_to_download):
# In DASH, the first segment contains necessary headers to
# generate a valid MP4 file, so always abort for the first segment
fatal = i == 0 or not skip_unavailable_fragments
if not process_segment(segment, ctx['tmpfilename'], fatal):
return False
self._finish_frag_download(ctx)

View File

@@ -220,6 +220,12 @@ class FFmpegFD(ExternalFD):
if proxy:
if not re.match(r'^[\da-zA-Z]+://', proxy):
proxy = 'http://%s' % proxy
if proxy.startswith('socks'):
self.report_warning(
'%s does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.' % self.get_basename())
# Since December 2015 ffmpeg supports -http_proxy option (see
# http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
# We could switch to the following code if we are able to detect version properly

View File

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

View File

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

View File

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

View File

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

View File

@@ -3,16 +3,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .turner import TurnerBaseIE
from ..utils import (
determine_ext,
ExtractorError,
float_or_none,
xpath_text,
int_or_none,
)
class AdultSwimIE(InfoExtractor):
class AdultSwimIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TESTS = [{
@@ -96,7 +94,8 @@ class AdultSwimIE(InfoExtractor):
'params': {
# m3u8 download
'skip_download': True,
}
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
@staticmethod
@@ -148,7 +147,10 @@ class AdultSwimIE(InfoExtractor):
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
if not video_info:
video_info = bootstrapped_data.get('heroMetadata', {}).get('trailer').get('video')
video_info = bootstrapped_data.get(
'heroMetadata', {}).get('trailer', {}).get('video')
if not video_info:
video_info = bootstrapped_data.get('onlineOriginals', [None])[0]
if not video_info:
raise ExtractorError('Unable to find video info')
@@ -162,70 +164,38 @@ class AdultSwimIE(InfoExtractor):
elif video_info.get('videoPlaybackID'):
segment_ids = [video_info['videoPlaybackID']]
else:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.'
if video_info.get('auth') is True else 'Unable to find stream or clips',
expected=True)
if video_info.get('auth') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream or clips')
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
episode_description = video_info.get('description')
episode_duration = int_or_none(video_info.get('duration'))
view_count = int_or_none(video_info.get('views'))
entries = []
for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id
segement_info = self._extract_cvp_info(
'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=desktop' % segment_id,
segment_id, {
'secure': {
'media_src': 'http://androidhls-secure.cdn.turner.com/adultswim/big',
'tokenizer_src': 'http://www.adultswim.com/astv/mvpd/processors/services/token_ipadAdobe.do',
},
})
segment_title = '%s - %s' % (show_title, episode_title)
if len(segment_ids) > 1:
segment_title += ' Part %d' % (part_num + 1)
idoc = self._download_xml(
segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information')
segment_duration = float_or_none(
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = []
file_els = idoc.findall('.//files/file') or idoc.findall('./files/file')
unique_urls = []
unique_file_els = []
for file_el in file_els:
media_url = file_el.text
if not media_url or determine_ext(media_url) == 'f4m':
continue
if file_el.text not in unique_urls:
unique_urls.append(file_el.text)
unique_file_els.append(file_el)
for file_el in unique_file_els:
bitrate = file_el.attrib.get('bitrate')
ftype = file_el.attrib.get('type')
media_url = file_el.text
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, segment_title, 'mp4', preference=0,
m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text.strip(),
# The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None,
})
self._sort_formats(formats)
entries.append({
segement_info.update({
'id': segment_id,
'title': segment_title,
'formats': formats,
'duration': segment_duration,
'description': episode_description
'description': episode_description,
})
entries.append(segement_info)
return {
'_type': 'playlist',
@@ -234,5 +204,6 @@ class AdultSwimIE(InfoExtractor):
'entries': entries,
'title': '%s - %s' % (show_title, episode_title),
'description': episode_description,
'duration': episode_duration
'duration': episode_duration,
'view_count': view_count,
}

View File

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

View File

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

View File

@@ -12,46 +12,41 @@ from ..compat import (
from ..utils import (
int_or_none,
parse_iso8601,
sanitized_Request,
smuggle_url,
unsmuggle_url,
urlencode_postdata,
)
class DCNIE(InfoExtractor):
class AWAANIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?show/(?P<show_id>\d+)/[^/]+(?:/(?P<video_id>\d+)/(?P<season_id>\d+))?'
def _real_extract(self, url):
show_id, video_id, season_id = re.match(self._VALID_URL, url).groups()
if video_id and int(video_id) > 0:
return self.url_result(
'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo')
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo')
elif season_id and int(season_id) > 0:
return self.url_result(smuggle_url(
'http://www.dcndigital.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'DCNSeason')
'http://awaan.ae/program/season/%s' % season_id,
{'show_id': show_id}), 'AWAANSeason')
else:
return self.url_result(
'http://www.dcndigital.ae/program/%s' % show_id, 'DCNSeason')
'http://awaan.ae/program/%s' % show_id, 'AWAANSeason')
class DCNBaseIE(InfoExtractor):
def _extract_video_info(self, video_data, video_id, is_live):
class AWAANBaseIE(InfoExtractor):
def _parse_video_data(self, video_data, video_id, is_live):
title = video_data.get('title_en') or video_data['title_ar']
img = video_data.get('img')
thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None
duration = int_or_none(video_data.get('duration'))
description = video_data.get('description_en') or video_data.get('description_ar')
timestamp = parse_iso8601(video_data.get('create_time'), ' ')
return {
'id': video_id,
'title': self._live_title(title) if is_live else title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'description': video_data.get('description_en') or video_data.get('description_ar'),
'thumbnail': 'http://admin.mangomolo.com/analytics/%s' % img if img else None,
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('create_time'), ' '),
'is_live': is_live,
}
@@ -75,11 +70,12 @@ class DCNBaseIE(InfoExtractor):
return formats
class DCNVideoIE(DCNBaseIE):
IE_NAME = 'dcn:video'
class AWAANVideoIE(AWAANBaseIE):
IE_NAME = 'awaan:video'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?(?:video(?:/[^/]+)?|media|catchup/[^/]+/[^/]+)/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.dcndigital.ae/#/video/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375',
'md5': '5f61c33bfc7794315c671a62d43116aa',
'info_dict':
{
'id': '17375',
@@ -90,10 +86,6 @@ class DCNVideoIE(DCNBaseIE):
'timestamp': 1227504126,
'upload_date': '20081124',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://awaan.ae/video/26723981/%D8%AF%D8%A7%D8%B1-%D8%A7%D9%84%D8%B3%D9%84%D8%A7%D9%85:-%D8%AE%D9%8A%D8%B1-%D8%AF%D9%88%D8%B1-%D8%A7%D9%84%D8%A3%D9%86%D8%B5%D8%A7%D8%B1',
'only_matching': True,
@@ -102,11 +94,10 @@ class DCNVideoIE(DCNBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
request = sanitized_Request(
video_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id,
headers={'Origin': 'http://www.dcndigital.ae'})
video_data = self._download_json(request, video_id)
info = self._extract_video_info(video_data, video_id, False)
video_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(video_data, video_id, False)
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' +
@@ -121,19 +112,31 @@ class DCNVideoIE(DCNBaseIE):
return info
class DCNLiveIE(DCNBaseIE):
IE_NAME = 'dcn:live'
class AWAANLiveIE(AWAANBaseIE):
IE_NAME = 'awaan:live'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?live/(?P<id>\d+)'
_TEST = {
'url': 'http://awaan.ae/live/6/dubai-tv',
'info_dict': {
'id': '6',
'ext': 'mp4',
'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'upload_date': '20150107',
'timestamp': 1420588800,
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
channel_id = self._match_id(url)
request = sanitized_Request(
channel_data = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/getchanneldetails?channel_id=%s' % channel_id,
headers={'Origin': 'http://www.dcndigital.ae'})
channel_data = self._download_json(request, channel_id)
info = self._extract_video_info(channel_data, channel_id, True)
channel_id, headers={'Origin': 'http://awaan.ae'})
info = self._parse_video_data(channel_data, channel_id, True)
webpage = self._download_webpage(
'http://admin.mangomolo.com/analytics/index.php/customers/embed/index?' +
@@ -148,8 +151,8 @@ class DCNLiveIE(DCNBaseIE):
return info
class DCNSeasonIE(InfoExtractor):
IE_NAME = 'dcn:season'
class AWAANSeasonIE(InfoExtractor):
IE_NAME = 'awaan:season'
_VALID_URL = r'https?://(?:www\.)?(?:awaan|dcndigital)\.ae/(?:#/)?program/(?:(?P<show_id>\d+)|season/(?P<season_id>\d+))'
_TEST = {
'url': 'http://dcndigital.ae/#/program/205024/%D9%85%D8%AD%D8%A7%D8%B6%D8%B1%D8%A7%D8%AA-%D8%A7%D9%84%D8%B4%D9%8A%D8%AE-%D8%A7%D9%84%D8%B4%D8%B9%D8%B1%D8%A7%D9%88%D9%8A',
@@ -170,21 +173,17 @@ class DCNSeasonIE(InfoExtractor):
data['season'] = season_id
show_id = smuggled_data.get('show_id')
if show_id is None:
request = sanitized_Request(
season = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/season_info?id=%s' % season_id,
headers={'Origin': 'http://www.dcndigital.ae'})
season = self._download_json(request, season_id)
season_id, headers={'Origin': 'http://awaan.ae'})
show_id = season['id']
data['show_id'] = show_id
request = sanitized_Request(
show = self._download_json(
'http://admin.mangomolo.com/analytics/index.php/plus/show',
urlencode_postdata(data),
{
'Origin': 'http://www.dcndigital.ae',
show_id, data=urlencode_postdata(data), headers={
'Origin': 'http://awaan.ae',
'Content-Type': 'application/x-www-form-urlencoded'
})
show = self._download_json(request, show_id)
if not season_id:
season_id = show['default_season']
for season in show['seasons']:
@@ -195,6 +194,6 @@ class DCNSeasonIE(InfoExtractor):
for video in show['videos']:
video_id = compat_str(video['id'])
entries.append(self.url_result(
'http://www.dcndigital.ae/media/%s' % video_id, 'DCNVideo', video_id))
'http://awaan.ae/media/%s' % video_id, 'AWAANVideo', video_id))
return self.playlist_result(entries, season_id, title)

View File

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

View File

@@ -2,6 +2,7 @@
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import (
@@ -17,6 +18,7 @@ from ..utils import (
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_urlparse,
)
@@ -1056,19 +1058,35 @@ class BBCCoUkArticleIE(InfoExtractor):
class BBCCoUkPlaylistBaseIE(InfoExtractor):
def _entries(self, webpage, url, playlist_id):
single_page = 'page' in compat_urlparse.parse_qs(
compat_urlparse.urlparse(url).query)
for page_num in itertools.count(2):
for video_id in re.findall(
self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
yield self.url_result(
self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
if single_page:
return
next_page = self._search_regex(
r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
webpage, 'next page url', default=None, group='url')
if not next_page:
break
webpage = self._download_webpage(
compat_urlparse.urljoin(url, next_page), playlist_id,
'Downloading page %d' % page_num, page_num)
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
for video_id in re.findall(
self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
title, description = self._extract_title_and_description(webpage)
return self.playlist_result(entries, playlist_id, title, description)
return self.playlist_result(
self._entries(webpage, url, playlist_id),
playlist_id, title, description)
class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
@@ -1117,6 +1135,24 @@ class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
'description': 'French thriller serial about a missing teenager.',
},
'playlist_mincount': 7,
}, {
# multipage playlist, explicit page
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Frozen Planet - Clips - BBC One',
'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
},
'playlist_mincount': 24,
}, {
# multipage playlist, all pages
'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
'info_dict': {
'id': 'b00mfl7n',
'title': 'Frozen Planet - Clips - BBC One',
'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
},
'playlist_mincount': 142,
}, {
'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
'only_matching': True,

View File

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

View File

@@ -1,22 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
import hashlib
import re
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
compat_str,
compat_parse_qs,
compat_xml_parse_error,
)
from ..compat import compat_parse_qs
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
xpath_text,
unified_timestamp,
)
@@ -27,7 +20,7 @@ class BiliBiliIE(InfoExtractor):
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
'info_dict': {
'id': '1554319',
'id': '1074402',
'ext': 'mp4',
'title': '【金坷垃】金泡沫',
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
@@ -41,24 +34,28 @@ class BiliBiliIE(InfoExtractor):
}, {
'url': 'http://www.bilibili.com/video/av1041170/',
'info_dict': {
'id': '1507019',
'id': '1041170',
'ext': 'mp4',
'title': '【BD1080P】刀语【诸神&异域】',
'description': '这是个神奇的故事~每个人不留弹幕不给走哦~切利哦!~',
'duration': 3382.259,
'timestamp': 1396530060,
'upload_date': '20140403',
'thumbnail': 're:^https?://.+\.jpg',
'uploader': '枫叶逝去',
'uploader_id': '520116',
},
}, {
'url': 'http://www.bilibili.com/video/av4808130/',
'info_dict': {
'id': '7802182',
'id': '4808130',
'ext': 'mp4',
'title': '【长篇】哆啦A梦443【钉铛】',
'description': '(2016.05.27)来组合客人的脸吧&amp;amp;寻母六千里锭 抱歉,又轮到周日上班现在才到家 封面www.pixiv.net/member_illust.php?mode=medium&amp;amp;illust_id=56912929',
'duration': 1493.995,
'timestamp': 1464564180,
'upload_date': '20160529',
'thumbnail': 're:^https?://.+\.jpg',
'uploader': '喜欢拉面',
'uploader_id': '151066',
},
@@ -66,12 +63,14 @@ class BiliBiliIE(InfoExtractor):
# Missing upload time
'url': 'http://www.bilibili.com/video/av1867637/',
'info_dict': {
'id': '2880301',
'id': '1867637',
'ext': 'mp4',
'title': '【HDTV】【喜剧】岳父岳母真难当 2014【法国票房冠军】',
'description': '一个信奉天主教的法国旧式传统资产阶级家庭中有四个女儿。三个女儿却分别找了阿拉伯、犹太、中国丈夫,老夫老妻唯独期盼剩下未嫁的小女儿能找一个信奉天主教的法国白人,结果没想到小女儿找了一位非裔黑人……【这次应该不会跳帧了】',
'duration': 5760.0,
'uploader': '黑夜为猫',
'uploader_id': '610729',
'thumbnail': 're:^https?://.+\.jpg',
},
'params': {
# Just to test metadata extraction
@@ -80,86 +79,61 @@ class BiliBiliIE(InfoExtractor):
'expected_warnings': ['upload time'],
}]
# BiliBili blocks keys from time to time. The current key is extracted from
# the Android client
# TODO: find the sign algorithm used in the flash player
_APP_KEY = '86385cdc024c0f6c'
_APP_KEY = '6f90a59ac58a4123'
_BILIBILI_KEY = '0bfd84cc3940035173f35e6777508326'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
params = compat_parse_qs(self._search_regex(
cid = compat_parse_qs(self._search_regex(
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
webpage, 'player parameters'))
cid = params['cid'][0]
webpage, 'player parameters'))['cid'][0]
info_xml_str = self._download_webpage(
'http://interface.bilibili.com/v_cdn_play',
cid, query={'appkey': self._APP_KEY, 'cid': cid},
note='Downloading video info page')
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
err_msg = None
durls = None
info_xml = None
try:
info_xml = compat_etree_fromstring(info_xml_str.encode('utf-8'))
except compat_xml_parse_error:
info_json = self._parse_json(info_xml_str, video_id, fatal=False)
err_msg = (info_json or {}).get('error_text')
else:
err_msg = xpath_text(info_xml, './message')
if info_xml is not None:
durls = info_xml.findall('./durl')
if not durls:
if err_msg:
raise ExtractorError('%s said: %s' % (self.IE_NAME, err_msg), expected=True)
else:
raise ExtractorError('No videos found!')
video_info = self._download_json(
'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page')
entries = []
for durl in durls:
size = xpath_text(durl, ['./filesize', './size'])
for idx, durl in enumerate(video_info['durl']):
formats = [{
'url': durl.find('./url').text,
'filesize': int_or_none(size),
'url': durl['url'],
'filesize': int_or_none(durl['size']),
}]
for backup_url in durl.findall('./backup_url/url'):
for backup_url in durl['backup_url']:
formats.append({
'url': backup_url.text,
'url': backup_url,
# backup URLs have lower priorities
'preference': -2 if 'hd.mp4' in backup_url.text else -3,
'preference': -2 if 'hd.mp4' in backup_url else -3,
})
self._sort_formats(formats)
entries.append({
'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
'duration': int_or_none(xpath_text(durl, './length'), 1000),
'id': '%s_part%s' % (video_id, idx),
'duration': float_or_none(durl.get('length'), 1000),
'formats': formats,
})
title = self._html_search_regex('<h1[^>]+title="([^"]+)">', webpage, 'title')
description = self._html_search_meta('description', webpage)
datetime_str = self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False)
timestamp = None
if datetime_str:
timestamp = calendar.timegm(datetime.datetime.strptime(datetime_str, '%Y-%m-%dT%H:%M').timetuple())
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', fatal=False))
# TODO 'view_count' requires deobfuscating Javascript
info = {
'id': compat_str(cid),
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'thumbnail': self._html_search_meta('thumbnailUrl', webpage),
'duration': float_or_none(xpath_text(info_xml, './timelength'), scale=1000),
'duration': float_or_none(video_info.get('timelength'), scale=1000),
}
uploader_mobj = re.search(

View File

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

View File

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

View File

@@ -9,10 +9,19 @@ from ..utils import (
js_to_json,
smuggle_url,
try_get,
xpath_text,
xpath_element,
xpath_with_ns,
find_xpath_attr,
parse_iso8601,
parse_age_limit,
int_or_none,
ExtractorError,
)
class CBCIE(InfoExtractor):
IE_NAME = 'cbc.ca'
_VALID_URL = r'https?://(?:www\.)?cbc\.ca/(?!player/)(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
# with mediaId
@@ -114,6 +123,7 @@ class CBCIE(InfoExtractor):
class CBCPlayerIE(InfoExtractor):
IE_NAME = 'cbc.ca:player'
_VALID_URL = r'(?:cbcplayer:|https?://(?:www\.)?cbc\.ca/(?:player/play/|i/caffeine/syndicate/\?mediaId=))(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.cbc.ca/player/play/2683190193',
@@ -167,3 +177,165 @@ class CBCPlayerIE(InfoExtractor):
}),
'id': video_id,
}
class CBCWatchBaseIE(InfoExtractor):
_device_id = None
_device_token = None
_API_BASE_URL = 'https://api-cbc.cloud.clearleap.com/cloffice/client/'
_NS_MAP = {
'media': 'http://search.yahoo.com/mrss/',
'clearleap': 'http://www.clearleap.com/namespace/clearleap/1.0/',
}
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
result = self._download_xml(url, video_id, headers={
'X-Clearleap-DeviceId': self._device_id,
'X-Clearleap-DeviceToken': self._device_token,
})
error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage')
if error_message:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message))
return result
def _real_initialize(self):
if not self._device_id or not self._device_token:
device = self._downloader.cache.load('cbcwatch', 'device') or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if not self._device_id or not self._device_token:
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
'cbcwatch', 'device', {
'id': self._device_id,
'token': self._device_token,
})
def _parse_rss_feed(self, rss):
channel = xpath_element(rss, 'channel', fatal=True)
def _add_ns(path):
return xpath_with_ns(path, self._NS_MAP)
entries = []
for item in channel.findall('item'):
guid = xpath_text(item, 'guid', fatal=True)
title = xpath_text(item, 'title', fatal=True)
media_group = xpath_element(item, _add_ns('media:group'), fatal=True)
content = xpath_element(media_group, _add_ns('media:content'), fatal=True)
content_url = content.attrib['url']
thumbnails = []
for thumbnail in media_group.findall(_add_ns('media:thumbnail')):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'id': thumbnail.get('profile'),
'url': thumbnail_url,
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
timestamp = None
release_date = find_xpath_attr(
item, _add_ns('media:credit'), 'role', 'releaseDate')
if release_date is not None:
timestamp = parse_iso8601(release_date.text)
entries.append({
'_type': 'url_transparent',
'url': content_url,
'id': guid,
'title': title,
'description': xpath_text(item, 'description'),
'timestamp': timestamp,
'duration': int_or_none(content.get('duration')),
'age_limit': parse_age_limit(xpath_text(item, _add_ns('media:rating'))),
'episode': xpath_text(item, _add_ns('clearleap:episode')),
'episode_number': int_or_none(xpath_text(item, _add_ns('clearleap:episodeInSeason'))),
'series': xpath_text(item, _add_ns('clearleap:series')),
'season_number': int_or_none(xpath_text(item, _add_ns('clearleap:season'))),
'thumbnails': thumbnails,
'ie_key': 'CBCWatchVideo',
})
return self.playlist_result(
entries, xpath_text(channel, 'guid'),
xpath_text(channel, 'title'),
xpath_text(channel, 'description'))
class CBCWatchVideoIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch:video'
_VALID_URL = r'https?://api-cbc\.cloud\.clearleap\.com/cloffice/client/web/play/?\?.*?\bcontentId=(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
def _real_extract(self, url):
video_id = self._match_id(url)
result = self._call_api(url, video_id)
m3u8_url = xpath_text(result, 'url', fatal=True)
formats = self._extract_m3u8_formats(re.sub(r'/([^/]+)/[^/?]+\.m3u8', r'/\1/\1.m3u8', m3u8_url), video_id, 'mp4', fatal=False)
if len(formats) < 2:
formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4')
# Despite metadata in m3u8 all video+audio formats are
# actually video-only (no audio)
for f in formats:
if f.get('acodec') != 'none' and f.get('vcodec') != 'none':
f['acodec'] = 'none'
self._sort_formats(formats)
info = {
'id': video_id,
'title': video_id,
'formats': formats,
}
rss = xpath_element(result, 'rss')
if rss:
info.update(self._parse_rss_feed(rss)['entries'][0])
del info['url']
del info['_type']
del info['ie_key']
return info
class CBCWatchIE(CBCWatchBaseIE):
IE_NAME = 'cbc.ca:watch'
_VALID_URL = r'https?://watch\.cbc\.ca/(?:[^/]+/)+(?P<id>[0-9a-f-]+)'
_TESTS = [{
'url': 'http://watch.cbc.ca/doc-zone/season-6/customer-disservice/38e815a-009e3ab12e4',
'info_dict': {
'id': '38e815a-009e3ab12e4',
'ext': 'mp4',
'title': 'Customer (Dis)Service',
'description': 'md5:8bdd6913a0fe03d4b2a17ebe169c7c87',
'upload_date': '20160219',
'timestamp': 1455840000,
},
'params': {
# m3u8 download
'skip_download': True,
'format': 'bestvideo',
},
'skip': 'Geo-restricted to Canada',
}, {
'url': 'http://watch.cbc.ca/arthur/all/1ed4b385-cd84-49cf-95f0-80f004680057',
'info_dict': {
'id': '1ed4b385-cd84-49cf-95f0-80f004680057',
'title': 'Arthur',
'description': 'Arthur, the sweetest 8-year-old aardvark, and his pals solve all kinds of problems with humour, kindness and teamwork.',
},
'playlist_mincount': 30,
'skip': 'Geo-restricted to Canada',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
rss = self._call_api('web/browse/' + video_id, video_id)
return self._parse_rss_feed(rss)

View File

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

View File

@@ -41,13 +41,8 @@ class CBSLocalIE(AnvatoIE):
'url': 'http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/',
'info_dict': {
'id': 'GxfCe0Zo7D-175909-5588',
'ext': 'mp4',
'title': 'Recap: CLE 15, CIN 6',
'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
'upload_date': '20160516',
'timestamp': 1463433840,
'duration': 49,
},
'playlist_count': 9,
'params': {
# m3u8 download
'skip_download': True,
@@ -60,12 +55,11 @@ class CBSLocalIE(AnvatoIE):
sendtonews_url = SendtoNewsIE._extract_url(webpage)
if sendtonews_url:
info_dict = {
'_type': 'url_transparent',
'url': compat_urlparse.urljoin(url, sendtonews_url),
}
else:
info_dict = self._extract_anvato_videos(webpage, display_id)
return self.url_result(
compat_urlparse.urljoin(url, sendtonews_url),
ie=SendtoNewsIE.ie_key())
info_dict = self._extract_anvato_videos(webpage, display_id)
time_str = self._html_search_regex(
r'class="entry-date">([^<]+)<', webpage, 'released date', fatal=False)

View File

@@ -2,13 +2,13 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .cbs import CBSBaseIE
from .cbs import CBSIE
from ..utils import (
parse_duration,
)
class CBSNewsIE(CBSBaseIE):
class CBSNewsIE(CBSIE):
IE_DESC = 'CBS News'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
@@ -35,7 +35,8 @@ class CBSNewsIE(CBSBaseIE):
'ext': 'mp4',
'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
'upload_date': '19700101',
'upload_date': '20140404',
'timestamp': 1396650660,
'uploader': 'CBSI-NEW',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 205,
@@ -63,14 +64,15 @@ class CBSNewsIE(CBSBaseIE):
item = video_info['item'] if 'item' in video_info else video_info
guid = item['mpxRefId']
return self._extract_video_info('byGuid=%s' % guid, guid)
return self._extract_video_info(guid)
class CBSNewsLiveVideoIE(InfoExtractor):
IE_DESC = 'CBS News Live Videos'
_VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
_TESTS = [{
# Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
_TEST = {
'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
'info_dict': {
'id': 'clinton-sanders-prepare-to-face-off-in-nh',
@@ -78,15 +80,8 @@ class CBSNewsLiveVideoIE(InfoExtractor):
'title': 'Clinton, Sanders Prepare To Face Off In NH',
'duration': 334,
},
'skip': 'Video gone, redirected to http://www.cbsnews.com/live/',
}, {
'url': 'http://www.cbsnews.com/live/video/video-shows-intense-paragliding-accident/',
'info_dict': {
'id': 'video-shows-intense-paragliding-accident',
'ext': 'flv',
'title': 'Video Shows Intense Paragliding Accident',
},
}]
'skip': 'Video gone',
}
def _real_extract(self, url):
video_id = self._match_id(url)

View File

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

View File

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

View File

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

View File

@@ -662,6 +662,24 @@ class InfoExtractor(object):
else:
return res
def _get_netrc_login_info(self, netrc_machine=None):
username = None
password = None
netrc_machine = netrc_machine or self._NETRC_MACHINE
if self._downloader.params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(netrc_machine)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % netrc_machine)
except (IOError, netrc.NetrcParseError) as err:
self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
return (username, password)
def _get_login_info(self):
"""
Get the login info as (username, password)
@@ -679,16 +697,8 @@ class InfoExtractor(object):
if downloader_params.get('username') is not None:
username = downloader_params['username']
password = downloader_params['password']
elif downloader_params.get('usenetrc', False):
try:
info = netrc.netrc().authenticators(self._NETRC_MACHINE)
if info is not None:
username = info[0]
password = info[2]
else:
raise netrc.NetrcParseError('No authenticators for %s' % self._NETRC_MACHINE)
except (IOError, netrc.NetrcParseError) as err:
self._downloader.report_warning('parsing .netrc: %s' % error_to_compat_str(err))
else:
username, password = self._get_netrc_login_info()
return (username, password)
@@ -1153,13 +1163,6 @@ class InfoExtractor(object):
m3u8_id=None, note=None, errnote=None,
fatal=True, live=False):
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
format_url = lambda u: (
u
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
res = self._download_webpage_handle(
m3u8_url, video_id,
note=note or 'Downloading m3u8 information',
@@ -1170,6 +1173,13 @@ class InfoExtractor(object):
m3u8_doc, urlh = res
m3u8_url = urlh.geturl()
formats = [self._m3u8_meta_format(m3u8_url, ext, preference, m3u8_id)]
format_url = lambda u: (
u
if re.match(r'^https?://', u)
else compat_urlparse.urljoin(m3u8_url, u))
# We should try extracting formats only from master playlists [1], i.e.
# playlists that describe available qualities. On the other hand media
# playlists [2] should be returned as is since they contain just the media
@@ -1191,27 +1201,44 @@ class InfoExtractor(object):
'protocol': entry_protocol,
'preference': preference,
}]
last_info = None
last_media = None
last_info = {}
last_media = {}
for line in m3u8_doc.splitlines():
if line.startswith('#EXT-X-STREAM-INF:'):
last_info = parse_m3u8_attributes(line)
elif line.startswith('#EXT-X-MEDIA:'):
last_media = parse_m3u8_attributes(line)
media = parse_m3u8_attributes(line)
media_type = media.get('TYPE')
if media_type in ('VIDEO', 'AUDIO'):
media_url = media.get('URI')
if media_url:
format_id = []
for v in (media.get('GROUP-ID'), media.get('NAME')):
if v:
format_id.append(v)
formats.append({
'format_id': '-'.join(format_id),
'url': format_url(media_url),
'language': media.get('LANGUAGE'),
'vcodec': 'none' if media_type == 'AUDIO' else None,
'ext': ext,
'protocol': entry_protocol,
'preference': preference,
})
else:
# When there is no URI in EXT-X-MEDIA let this tag's
# data be used by regular URI lines below
last_media = media
elif line.startswith('#') or not line.strip():
continue
else:
if last_info is None:
formats.append({'url': format_url(line)})
continue
tbr = int_or_none(last_info.get('BANDWIDTH'), scale=1000)
tbr = int_or_none(last_info.get('AVERAGE-BANDWIDTH') or last_info.get('BANDWIDTH'), scale=1000)
format_id = []
if m3u8_id:
format_id.append(m3u8_id)
last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') not in ('SUBTITLES', 'CLOSED-CAPTIONS') else None
# Despite specification does not mention NAME attribute for
# EXT-X-STREAM-INF it still sometimes may be present
stream_name = last_info.get('NAME') or last_media_name
stream_name = last_info.get('NAME') or last_media.get('NAME')
# Bandwidth of live streams may differ over time thus making
# format_id unpredictable. So it's better to keep provided
# format_id intact.
@@ -1242,11 +1269,9 @@ class InfoExtractor(object):
'abr': abr,
})
f.update(parse_codecs(last_info.get('CODECS')))
if last_media is not None:
f['m3u8_media'] = last_media
last_media = None
formats.append(f)
last_info = {}
last_media = {}
return formats
@staticmethod
@@ -1685,7 +1710,7 @@ class InfoExtractor(object):
self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type)
return formats
def _parse_html5_media_entries(self, base_url, webpage):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8'):
def absolute_url(video_url):
return compat_urlparse.urljoin(base_url, video_url)
@@ -1700,6 +1725,21 @@ class InfoExtractor(object):
return f
return {}
def _media_formats(src, cur_media_type):
full_url = absolute_url(src)
if determine_ext(full_url) == 'm3u8':
is_plain_url = False
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
else:
is_plain_url = True
formats = [{
'url': full_url,
'vcodec': 'none' if cur_media_type == 'audio' else None,
}]
return is_plain_url, formats
entries = []
for media_tag, media_type, media_content in re.findall(r'(?s)(<(?P<tag>video|audio)[^>]*>)(.*?)</(?P=tag)>', webpage):
media_info = {
@@ -1709,10 +1749,8 @@ class InfoExtractor(object):
media_attributes = extract_attributes(media_tag)
src = media_attributes.get('src')
if src:
media_info['formats'].append({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
_, formats = _media_formats(src, media_type)
media_info['formats'].extend(formats)
media_info['thumbnail'] = media_attributes.get('poster')
if media_content:
for source_tag in re.findall(r'<source[^>]+>', media_content):
@@ -1720,12 +1758,13 @@ class InfoExtractor(object):
src = source_attributes.get('src')
if not src:
continue
f = parse_content_type(source_attributes.get('type'))
f.update({
'url': absolute_url(src),
'vcodec': 'none' if media_type == 'audio' else None,
})
media_info['formats'].append(f)
is_plain_url, formats = _media_formats(src, media_type)
if is_plain_url:
f = parse_content_type(source_attributes.get('type'))
f.update(formats[0])
media_info['formats'].append(f)
else:
media_info['formats'].extend(formats)
for track_tag in re.findall(r'<track[^>]+>', media_content):
track_attributes = extract_attributes(track_tag)
kind = track_attributes.get('kind')
@@ -1741,6 +1780,18 @@ class InfoExtractor(object):
entries.append(media_info)
return entries
def _extract_akamai_formats(self, manifest_url, video_id):
formats = []
f4m_url = re.sub(r'(https?://.+?)/i/', r'\1/z/', manifest_url).replace('/master.m3u8', '/manifest.f4m')
formats.extend(self._extract_f4m_formats(
update_url_query(f4m_url, {'hdcore': '3.7.0'}),
video_id, f4m_id='hds', fatal=False))
m3u8_url = re.sub(r'(https?://.+?)/z/', r'\1/i/', manifest_url).replace('/manifest.f4m', '/master.m3u8')
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()

View File

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

View File

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

View File

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

View File

@@ -0,0 +1,120 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
urlencode_postdata,
compat_str,
ExtractorError,
)
class CuriosityStreamBaseIE(InfoExtractor):
_NETRC_MACHINE = 'curiositystream'
_auth_token = None
_API_BASE_URL = 'https://api.curiositystream.com/v1/'
def _handle_errors(self, result):
error = result.get('error', {}).get('message')
if error:
if isinstance(error, dict):
error = ', '.join(error.values())
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
def _call_api(self, path, video_id):
headers = {}
if self._auth_token:
headers['X-Auth-Token'] = self._auth_token
result = self._download_json(
self._API_BASE_URL + path, video_id, headers=headers)
self._handle_errors(result)
return result['data']
def _real_initialize(self):
(email, password) = self._get_login_info()
if email is None:
return
result = self._download_json(
self._API_BASE_URL + 'login', None, data=urlencode_postdata({
'email': email,
'password': password,
}))
self._handle_errors(result)
self._auth_token = result['message']['auth_token']
def _extract_media_info(self, media):
video_id = compat_str(media['id'])
limelight_media_id = media['limelight_media_id']
title = media['title']
subtitles = {}
for closed_caption in media.get('closed_captions', []):
sub_url = closed_caption.get('file')
if not sub_url:
continue
lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
subtitles.setdefault(lang, []).append({
'url': sub_url,
})
return {
'_type': 'url_transparent',
'id': video_id,
'url': 'limelight:media:' + limelight_media_id,
'title': title,
'description': media.get('description'),
'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
'duration': int_or_none(media.get('duration')),
'tags': media.get('tags'),
'subtitles': subtitles,
'ie_key': 'LimelightMedia',
}
class CuriosityStreamIE(CuriosityStreamBaseIE):
IE_NAME = 'curiositystream'
_VALID_URL = r'https?://app\.curiositystream\.com/video/(?P<id>\d+)'
_TEST = {
'url': 'https://app.curiositystream.com/video/2',
'md5': 'a0074c190e6cddaf86900b28d3e9ee7a',
'info_dict': {
'id': '2',
'ext': 'mp4',
'title': 'How Did You Develop The Internet?',
'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
'timestamp': 1448388615,
'upload_date': '20151124',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
media = self._call_api('media/' + video_id, video_id)
return self._extract_media_info(media)
class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
IE_NAME = 'curiositystream:collection'
_VALID_URL = r'https?://app\.curiositystream\.com/collection/(?P<id>\d+)'
_TEST = {
'url': 'https://app.curiositystream.com/collection/2',
'info_dict': {
'id': '2',
'title': 'Curious Minds: The Internet',
'description': 'How is the internet shaping our lives in the 21st Century?',
},
'playlist_mincount': 17,
}
def _real_extract(self, url):
collection_id = self._match_id(url)
collection = self._call_api(
'collections/' + collection_id, collection_id)
entries = []
for media in collection.get('media', []):
entries.append(self._extract_media_info(media))
return self.playlist_result(
entries, collection_id,
collection.get('title'), collection.get('description'))

View File

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

View File

@@ -7,11 +7,22 @@ from ..utils import (
int_or_none,
parse_age_limit,
unescapeHTML,
ExtractorError,
)
class DiscoveryGoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?discoverygo\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
animalplanet|
ahctv|
destinationamerica|
sciencechannel|
tlc|
velocitychannel
)go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
_TEST = {
'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
'info_dict': {
@@ -43,7 +54,14 @@ class DiscoveryGoIE(InfoExtractor):
title = video['name']
stream = video['stream']
stream = video.get('stream')
if not stream:
if video.get('authenticated') is True:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.', expected=True)
else:
raise ExtractorError('Unable to find stream')
STREAM_URL_SUFFIX = 'streamUrl'
formats = []
for stream_kind in ('', 'hds'):

View File

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

View File

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

View File

@@ -4,26 +4,45 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
mimetype2ext,
parse_iso8601,
remove_end,
)
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'https://www.dr.dk/tv/se/boern/ultra/panisk-paske/panisk-paske-5',
'md5': 'dc515a9ab50577fa14cc4e4b0265168f',
_TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
'md5': '25e659cccc9a2ed956110a299fdf5983',
'info_dict': {
'id': 'panisk-paske-5',
'id': 'klassen-darlig-taber-10',
'ext': 'mp4',
'title': 'Panisk Påske (5)',
'description': 'md5:ca14173c5ab24cd26b0fcc074dff391c',
'timestamp': 1426984612,
'upload_date': '20150322',
'duration': 1455,
'title': 'Klassen - Dårlig taber (10)',
'description': 'md5:815fe1b7fa656ed80580f31e8b3c79aa',
'timestamp': 1471991907,
'upload_date': '20160823',
'duration': 606.84,
},
}
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
'md5': '2c37175c718155930f939ef59952474a',
'info_dict': {
'id': 'christiania-pusher-street-ryddes-drdkrjpo',
'ext': 'mp4',
'title': 'LIVE Christianias rydning af Pusher Street er i gang',
'description': '- Det er det fedeste, der er sket i 20 år, fortæller christianit til DR Nyheder.',
'timestamp': 1472800279,
'upload_date': '20160902',
'duration': 131.4,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -35,7 +54,8 @@ class DRTVIE(InfoExtractor):
'Video %s is not available' % video_id, expected=True)
video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
(r'data-(?:material-identifier|episode-slug)="([^"]+)"',
r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
webpage, 'video id')
programcard = self._download_json(
@@ -43,9 +63,12 @@ class DRTVIE(InfoExtractor):
video_id, 'Downloading video JSON')
data = programcard['Data'][0]
title = data['Title']
description = data['Description']
timestamp = parse_iso8601(data['CreatedTime'])
title = remove_end(self._og_search_title(
webpage, default=None), ' | TV | DR') or data['Title']
description = self._og_search_description(
webpage, default=None) or data.get('Description')
timestamp = parse_iso8601(data.get('CreatedTime'))
thumbnail = None
duration = None
@@ -56,16 +79,18 @@ class DRTVIE(InfoExtractor):
subtitles = {}
for asset in data['Assets']:
if asset['Kind'] == 'Image':
thumbnail = asset['Uri']
elif asset['Kind'] == 'VideoResource':
duration = asset['DurationInMilliseconds'] / 1000.0
restricted_to_denmark = asset['RestrictedToDenmark']
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
uri = link['Uri']
target = link['Target']
format_id = target
if asset.get('Kind') == 'Image':
thumbnail = asset.get('Uri')
elif asset.get('Kind') == 'VideoResource':
duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
restricted_to_denmark = asset.get('RestrictedToDenmark')
spoken_subtitles = asset.get('Target') == 'SpokenSubtitles'
for link in asset.get('Links', []):
uri = link.get('Uri')
if not uri:
continue
target = link.get('Target')
format_id = target or ''
preference = None
if spoken_subtitles:
preference = -1
@@ -76,8 +101,8 @@ class DRTVIE(InfoExtractor):
video_id, preference, f4m_id=format_id))
elif target == 'HLS':
formats.extend(self._extract_m3u8_formats(
uri, video_id, 'mp4', preference=preference,
m3u8_id=format_id))
uri, video_id, 'mp4', entry_protocol='m3u8_native',
preference=preference, m3u8_id=format_id))
else:
bitrate = link.get('Bitrate')
if bitrate:
@@ -85,7 +110,7 @@ class DRTVIE(InfoExtractor):
formats.append({
'url': uri,
'format_id': format_id,
'tbr': bitrate,
'tbr': int_or_none(bitrate),
'ext': link.get('FileFormat'),
})
subtitles_list = asset.get('SubtitlesList')
@@ -94,12 +119,18 @@ class DRTVIE(InfoExtractor):
'Danish': 'da',
}
for subs in subtitles_list:
lang = subs['Language']
subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
if not subs.get('Uri'):
continue
lang = subs.get('Language') or 'da'
subtitles.setdefault(LANGS.get(lang, lang), []).append({
'url': subs['Uri'],
'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
})
if not formats and restricted_to_denmark:
raise ExtractorError(
'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
self.raise_geo_restricted(
'Unfortunately, DR is not allowed to show this program outside Denmark.',
expected=True)
self._sort_formats(formats)

View File

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

View File

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

View File

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

View File

@@ -1,7 +1,10 @@
# flake8: noqa
from __future__ import unicode_literals
from .abc import ABCIE
from .abc import (
ABCIE,
ABCIViewIE,
)
from .abc7news import Abc7NewsIE
from .abcnews import (
AbcNewsIE,
@@ -29,6 +32,7 @@ from .aftonbladet import AftonbladetIE
from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .amcnetworks import AMCNetworksIE
from .animeondemand import AnimeOnDemandIE
from .anitube import AnitubeIE
from .anysex import AnySexIE
@@ -67,6 +71,12 @@ from .atttechchannel import ATTTechChannelIE
from .audimedia import AudiMediaIE
from .audioboom import AudioBoomIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .awaan import (
AWAANIE,
AWAANVideoIE,
AWAANLiveIE,
AWAANSeasonIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
from .bambuser import BambuserIE, BambuserChannelIE
@@ -117,9 +127,12 @@ from .carambatv import (
CarambaTVIE,
CarambaTVPageIE,
)
from .cartoonnetwork import CartoonNetworkIE
from .cbc import (
CBCIE,
CBCPlayerIE,
CBCWatchVideoIE,
CBCWatchIE,
)
from .cbs import CBSIE
from .cbslocal import CBSLocalIE
@@ -133,6 +146,7 @@ from .ccc import CCCIE
from .cda import CDAIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .charlierose import CharlieRoseIE
from .chaturbate import ChaturbateIE
from .chilloutzone import ChilloutzoneIE
from .chirbit import (
@@ -180,6 +194,10 @@ from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
from .cultureunplugged import CultureUnpluggedIE
from .curiositystream import (
CuriosityStreamIE,
CuriosityStreamCollectionIE,
)
from .cwtv import CWTVIE
from .dailymail import DailyMailIE
from .dailymotion import (
@@ -195,12 +213,6 @@ from .daum import (
DaumUserIE,
)
from .dbtv import DBTVIE
from .dcn import (
DCNIE,
DCNVideoIE,
DCNLiveIE,
DCNSeasonIE,
)
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE
from .democracynow import DemocracynowIE
@@ -249,13 +261,18 @@ from .espn import ESPNIE
from .esri import EsriVideoIE
from .europa import EuropaIE
from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE
from .expotv import ExpoTVIE
from .extremetube import ExtremeTubeIE
from .eyedotv import EyedoTVIE
from .facebook import FacebookIE
from .facebook import (
FacebookIE,
FacebookPluginsVideoIE,
)
from .faz import FazIE
from .fc2 import FC2IE
from .fc2 import (
FC2IE,
FC2EmbedIE,
)
from .fczenit import FczenitIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
@@ -270,7 +287,10 @@ from .formula1 import Formula1IE
from .fourtube import FourTubeIE
from .fox import FOXIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .foxnews import (
FoxNewsIE,
FoxNewsInsiderIE,
)
from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
@@ -287,6 +307,7 @@ from .freevideo import FreeVideoIE
from .funimation import FunimationIE
from .funnyordie import FunnyOrDieIE
from .fusion import FusionIE
from .fxnetworks import FXNetworksIE
from .gameinformer import GameInformerIE
from .gameone import (
GameOneIE,
@@ -306,6 +327,7 @@ from .globo import (
GloboIE,
GloboArticleIE,
)
from .go import GoIE
from .godtube import GodTubeIE
from .godtv import GodTVIE
from .golem import GolemIE
@@ -322,7 +344,10 @@ from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE
from .hgtv import HGTVIE
from .hgtv import (
HGTVIE,
HGTVComShowIE,
)
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE
@@ -474,6 +499,7 @@ from .motherless import MotherlessIE
from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE
from .moviezine import MoviezineIE
from .movingimage import MovingImageIE
from .msn import MSNIE
from .mtv import (
MTVIE,
@@ -530,6 +556,7 @@ from .nextmedia import (
)
from .nfb import NFBIE
from .nfl import NFLIE
from .nhk import NhkVodIE
from .nhl import (
NHLVideocenterIE,
NHLNewsIE,
@@ -541,7 +568,10 @@ from .nick import (
NickDeIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninecninemedia import NineCNineMediaIE
from .ninecninemedia import (
NineCNineMediaStackIE,
NineCNineMediaIE,
)
from .ninegag import NineGagIE
from .ninenow import NineNowIE
from .nintendo import NintendoIE
@@ -623,7 +653,6 @@ from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .pinkbike import PinkbikeIE
from .pladform import PladformIE
from .played import PlayedIE
from .playfm import PlayFMIE
from .plays import PlaysTVIE
from .playtvak import PlaytvakIE
@@ -637,6 +666,7 @@ from .podomatic import PodomaticIE
from .pokemon import PokemonIE
from .polskieradio import PolskieRadioIE
from .porn91 import Porn91IE
from .porncom import PornComIE
from .pornhd import PornHdIE
from .pornhub import (
PornHubIE,
@@ -790,7 +820,6 @@ from .srgssr import (
SRGSSRPlayIE,
)
from .srmediathek import SRMediathekIE
from .ssa import SSAIE
from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE
from .streamable import StreamableIE
@@ -810,6 +839,7 @@ from .tagesschau import (
TagesschauIE,
)
from .tass import TassIE
from .tbs import TBSIE
from .tdslifeway import TDSLifewayIE
from .teachertube import (
TeacherTubeIE,
@@ -852,16 +882,11 @@ from .tnaflix import (
MovieFapIE,
)
from .toggle import ToggleIE
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
)
from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
from .trilulilu import TriluliluIE
from .trollvids import TrollvidsIE
from .trutube import TruTubeIE
from .tube8 import Tube8IE
from .tubitv import TubiTvIE
from .tudou import (
@@ -896,7 +921,10 @@ from .tvp import (
TVPIE,
TVPSeriesIE,
)
from .tvplay import TVPlayIE
from .tvplay import (
TVPlayIE,
ViafreeIE,
)
from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
from .twentymin import TwentyMinutenIE
@@ -926,8 +954,13 @@ from .udn import UDNEmbedIE
from .digiteka import DigitekaIE
from .unistra import UnistraIE
from .uol import UOLIE
from .uplynk import (
UplynkIE,
UplynkPreplayIE,
)
from .urort import UrortIE
from .urplay import URPlayIE
from .usanetwork import USANetworkIE
from .usatoday import USATodayIE
from .ustream import UstreamIE, UstreamChannelIE
from .ustudio import (
@@ -954,6 +987,7 @@ from .vice import (
ViceIE,
ViceShowIE,
)
from .viceland import VicelandIE
from .vidbit import VidbitIE
from .viddler import ViddlerIE
from .videodetective import VideoDetectiveIE
@@ -1100,8 +1134,4 @@ from .youtube import (
)
from .zapiks import ZapiksIE
from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
)
from .zippcast import ZippCastIE
from .zingmp3 import ZingMp3IE

View File

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

View File

@@ -15,6 +15,7 @@ from ..compat import (
from ..utils import (
error_to_compat_str,
ExtractorError,
int_or_none,
limit_length,
sanitized_Request,
urlencode_postdata,
@@ -62,6 +63,8 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam',
'uploader': 'Tennis on Facebook',
'upload_date': '20140908',
'timestamp': 1410199200,
}
}, {
'note': 'Video without discernible title',
@@ -71,6 +74,8 @@ class FacebookIE(InfoExtractor):
'ext': 'mp4',
'title': 'Facebook video #274175099429670',
'uploader': 'Asif Nawab Butt',
'upload_date': '20140506',
'timestamp': 1399398998,
},
'expected_warnings': [
'title'
@@ -78,12 +83,14 @@ class FacebookIE(InfoExtractor):
}, {
'note': 'Video with DASH manifest',
'url': 'https://www.facebook.com/video.php?v=957955867617029',
'md5': '54706e4db4f5ad58fbad82dde1f1213f',
'md5': 'b2c28d528273b323abe5c6ab59f0f030',
'info_dict': {
'id': '957955867617029',
'ext': 'mp4',
'title': 'When you post epic content on instagram.com/433 8 million followers, this is ...',
'uploader': 'Demy de Zeeuw',
'upload_date': '20160110',
'timestamp': 1452431627,
},
}, {
'url': 'https://www.facebook.com/maxlayn/posts/10153807558977570',
@@ -306,12 +313,16 @@ class FacebookIE(InfoExtractor):
if not video_title:
video_title = 'Facebook video #%s' % video_id
uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage))
timestamp = int_or_none(self._search_regex(
r'<abbr[^>]+data-utime=["\'](\d+)', webpage,
'timestamp', default=None))
info_dict = {
'id': video_id,
'title': video_title,
'formats': formats,
'uploader': uploader,
'timestamp': timestamp,
}
return webpage, info_dict
@@ -340,3 +351,32 @@ class FacebookIE(InfoExtractor):
self._VIDEO_PAGE_TEMPLATE % video_id,
video_id, fatal_if_no_video=True)
return info_dict
class FacebookPluginsVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:[\w-]+\.)?facebook\.com/plugins/video\.php\?.*?\bhref=(?P<id>https.+)'
_TESTS = [{
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fgov.sg%2Fvideos%2F10154383743583686%2F&show_text=0&width=560',
'md5': '5954e92cdfe51fe5782ae9bda7058a07',
'info_dict': {
'id': '10154383743583686',
'ext': 'mp4',
'title': 'What to do during the haze?',
'uploader': 'Gov.sg',
'upload_date': '20160826',
'timestamp': 1472184808,
},
'add_ie': [FacebookIE.ie_key()],
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https%3A%2F%2Fwww.facebook.com%2Fvideo.php%3Fv%3D10204634152394104',
'only_matching': True,
}, {
'url': 'https://www.facebook.com/plugins/video.php?href=https://www.facebook.com/gov.sg/videos/10154383743583686/&show_text=0&width=560',
'only_matching': True,
}]
def _real_extract(self, url):
return self.url_result(
compat_urllib_parse_unquote(self._match_id(url)),
FacebookIE.ie_key())

View File

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

View File

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

View File

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

View File

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

View File

@@ -72,6 +72,8 @@ from .kaltura import KalturaIE
from .eagleplatform import EaglePlatformIE
from .facebook import FacebookIE
from .soundcloud import SoundcloudIE
from .vbox7 import Vbox7IE
from .dbtv import DBTVIE
class GenericIE(InfoExtractor):
@@ -102,7 +104,8 @@ class GenericIE(InfoExtractor):
},
'expected_warnings': [
'URL could be a direct video link, returning it as such.'
]
],
'skip': 'URL invalid',
},
# Direct download with broken HEAD
{
@@ -266,7 +269,8 @@ class GenericIE(InfoExtractor):
'params': {
# m3u8 downloads
'skip_download': True,
}
},
'skip': 'video gone',
},
# m3u8 served with Content-Type: text/plain
{
@@ -281,7 +285,8 @@ class GenericIE(InfoExtractor):
'params': {
# m3u8 downloads
'skip_download': True,
}
},
'skip': 'video gone',
},
# google redirect
{
@@ -366,6 +371,7 @@ class GenericIE(InfoExtractor):
'description': 'Mississauga resident David Farmer is still out of power as a result of the ice storm a month ago. To keep the house warm, Farmer cuts wood from his property for a wood burning stove downstairs.',
},
'add_ie': ['BrightcoveLegacy'],
'skip': 'video gone',
},
{
'url': 'http://www.championat.com/video/football/v/87/87499.html',
@@ -419,6 +425,7 @@ class GenericIE(InfoExtractor):
'params': {
'skip_download': True,
},
'skip': 'movie expired',
},
# embed.ly video
{
@@ -446,6 +453,8 @@ class GenericIE(InfoExtractor):
'title': 'Between Two Ferns with Zach Galifianakis: President Barack Obama',
'description': 'Episode 18: President Barack Obama sits down with Zach Galifianakis for his most memorable interview yet.',
},
# HEAD requests lead to endless 301, while GET is OK
'expected_warnings': ['301'],
},
# RUTV embed
{
@@ -520,6 +529,9 @@ class GenericIE(InfoExtractor):
'title': '[NSFL] [FM15] which pumiscer was this ( vid ) ( alfa as fuck srx )',
},
'playlist_mincount': 7,
# This forum does not allow <iframe> syntaxes anymore
# Now HTML tags are displayed as-is
'skip': 'No videos on this page',
},
# Embedded TED video
{
@@ -568,7 +580,8 @@ class GenericIE(InfoExtractor):
},
'params': {
'skip_download': 'Requires rtmpdump'
}
},
'skip': 'video gone',
},
# francetv embed
{
@@ -1373,6 +1386,27 @@ class GenericIE(InfoExtractor):
},
'add_ie': [ArkenaIE.ie_key()],
},
{
'url': 'http://nova.bg/news/view/2016/08/16/156543/%D0%BD%D0%B0-%D0%BA%D0%BE%D1%81%D1%8A%D0%BC-%D0%BE%D1%82-%D0%B2%D0%B7%D1%80%D0%B8%D0%B2-%D0%BE%D1%82%D1%86%D0%B5%D0%BF%D0%B8%D1%85%D0%B0-%D1%86%D1%8F%D0%BB-%D0%BA%D0%B2%D0%B0%D1%80%D1%82%D0%B0%D0%BB-%D0%B7%D0%B0%D1%80%D0%B0%D0%B4%D0%B8-%D0%B8%D0%B7%D1%82%D0%B8%D1%87%D0%B0%D0%BD%D0%B5-%D0%BD%D0%B0-%D0%B3%D0%B0%D0%B7-%D0%B2-%D0%BF%D0%BB%D0%BE%D0%B2%D0%B4%D0%B8%D0%B2/',
'info_dict': {
'id': '1c7141f46c',
'ext': 'mp4',
'title': 'НА КОСЪМ ОТ ВЗРИВ: Изтичане на газ на бензиностанция в Пловдив',
},
'params': {
'skip_download': True,
},
'add_ie': [Vbox7IE.ie_key()],
},
{
# DBTV embeds
'url': 'http://www.dagbladet.no/2016/02/23/nyheter/nordlys/ski/troms/ver/43254897/',
'info_dict': {
'id': '43254897',
'title': 'Etter ett års planlegging, klaffet endelig alt: - Jeg måtte ta en liten dans',
},
'playlist_mincount': 3,
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@@ -2209,11 +2243,11 @@ class GenericIE(InfoExtractor):
# Look for VODPlatform embeds
mobj = re.search(
r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?vod-platform\.net/embed/[^/?#]+)',
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vod-platform\.net/[eE]mbed/.+?)\1',
webpage)
if mobj is not None:
return self.url_result(
self._proto_relative_url(unescapeHTML(mobj.group(1))), 'VODPlatform')
self._proto_relative_url(unescapeHTML(mobj.group('url'))), 'VODPlatform')
# Look for Instagram embeds
instagram_embed_url = InstagramIE._extract_embed_url(webpage)
@@ -2239,6 +2273,16 @@ class GenericIE(InfoExtractor):
'uploader': video_uploader,
}
# Look for VBOX7 embeds
vbox7_url = Vbox7IE._extract_url(webpage)
if vbox7_url:
return self.url_result(vbox7_url, Vbox7IE.ie_key())
# Look for DBTV embeds
dbtv_urls = DBTVIE._extract_urls(webpage)
if dbtv_urls:
return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')

View File

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

View File

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

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

@@ -0,0 +1,101 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
determine_ext,
parse_age_limit,
)
class GoIE(InfoExtractor):
_BRANDS = {
'abc': '001',
'freeform': '002',
'watchdisneychannel': '004',
'watchdisneyjunior': '008',
'watchdisneyxd': '009',
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/.*?vdka(?P<id>\w+)' % '|'.join(_BRANDS.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'info_dict': {
'id': '0_g86w5onx',
'ext': 'mp4',
'title': 'Sneak Peek: Language Arts',
'description': 'md5:7dcdab3b2d17e5217c953256af964e9c',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
'only_matching': True,
}]
def _real_extract(self, url):
sub_domain, video_id = re.match(self._VALID_URL, url).groups()
video_data = self._download_json(
'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (self._BRANDS[sub_domain], video_id),
video_id)['video'][0]
title = video_data['title']
formats = []
for asset in video_data.get('assets', {}).get('asset', []):
asset_url = asset.get('value')
if not asset_url:
continue
format_id = asset.get('format')
ext = determine_ext(asset_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False))
else:
formats.append({
'format_id': format_id,
'url': asset_url,
'ext': ext,
})
self._sort_formats(formats)
subtitles = {}
for cc in video_data.get('closedcaption', {}).get('src', []):
cc_url = cc.get('value')
if not cc_url:
continue
ext = determine_ext(cc_url)
if ext == 'xml':
ext = 'ttml'
subtitles.setdefault(cc.get('lang'), []).append({
'url': cc_url,
'ext': ext,
})
thumbnails = []
for thumbnail in video_data.get('thumbnails', {}).get('thumbnail', []):
thumbnail_url = thumbnail.get('value')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'width': int_or_none(thumbnail.get('width')),
'height': int_or_none(thumbnail.get('height')),
})
return {
'id': video_id,
'title': title,
'description': video_data.get('longdescription') or video_data.get('description'),
'duration': int_or_none(video_data.get('duration', {}).get('value'), 1000),
'age_limit': parse_age_limit(video_data.get('tvrating', {}).get('rating')),
'episode_number': int_or_none(video_data.get('episodenumber')),
'series': video_data.get('show', {}).get('title'),
'season_number': int_or_none(video_data.get('season', {}).get('num')),
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subtitles,
}

View File

@@ -46,3 +46,34 @@ class HGTVIE(InfoExtractor):
'episode_number': int_or_none(embed_vars.get('episode')),
'ie_key': 'ThePlatform',
}
class HGTVComShowIE(InfoExtractor):
IE_NAME = 'hgtv.com:show'
_VALID_URL = r'https?://(?:www\.)?hgtv\.com/shows/[^/]+/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.hgtv.com/shows/flip-or-flop/flip-or-flop-full-episodes-videos',
'info_dict': {
'id': 'flip-or-flop-full-episodes-videos',
'title': 'Flip or Flop Full Episodes',
},
'playlist_mincount': 15,
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
config = self._parse_json(
self._search_regex(
r'(?s)data-module=["\']video["\'][^>]*>.*?<script[^>]+type=["\']text/x-config["\'][^>]*>(.+?)</script',
webpage, 'video config'),
display_id)['channels'][0]
entries = [
self.url_result(video['releaseUrl'])
for video in config['videos'] if video.get('releaseUrl')]
return self.playlist_result(
entries, display_id, config.get('title'), config.get('description'))

View File

@@ -6,6 +6,7 @@ from .common import InfoExtractor
from ..utils import (
mimetype2ext,
qualities,
remove_end,
)
@@ -19,7 +20,7 @@ class ImdbIE(InfoExtractor):
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
'title': 'Ice Age: Continental Drift Trailer (No. 2)',
'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
}
}, {
@@ -83,10 +84,10 @@ class ImdbIE(InfoExtractor):
return {
'id': video_id,
'title': self._og_search_title(webpage),
'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
'formats': formats,
'description': descr,
'thumbnail': format_info['slate'],
'thumbnail': format_info.get('slate'),
}

View File

@@ -48,13 +48,23 @@ class InternetVideoArchiveIE(InfoExtractor):
# There are multiple videos in the playlist whlie only the first one
# matches the video played in browsers
video_info = configuration['playlist'][0]
title = video_info['title']
formats = []
for source in video_info['sources']:
file_url = source['file']
if determine_ext(file_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
file_url, video_id, ext='mp4', m3u8_id='hls'))
m3u8_formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
file_url = m3u8_formats[0]['url']
formats.extend(self._extract_f4m_formats(
file_url.replace('.m3u8', '.f4m'),
video_id, f4m_id='hds', fatal=False))
formats.extend(self._extract_mpd_formats(
file_url.replace('.m3u8', '.mpd'),
video_id, mpd_id='dash', fatal=False))
else:
a_format = {
'url': file_url,
@@ -70,7 +80,6 @@ class InternetVideoArchiveIE(InfoExtractor):
self._sort_formats(formats)
title = video_info['title']
description = video_info.get('description')
thumbnail = video_info.get('image')
else:

View File

@@ -1,4 +1,4 @@
# encoding: utf-8
# coding: utf-8
from __future__ import unicode_literals
import re
@@ -8,7 +8,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
sanitized_Request,
qualities,
)
@@ -49,11 +49,27 @@ class IviIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$',
},
'skip': 'Only works from Russia',
},
{
# with MP4-HD720 format
'url': 'http://www.ivi.ru/watch/146500',
'md5': 'd63d35cdbfa1ea61a5eafec7cc523e1e',
'info_dict': {
'id': '146500',
'ext': 'mp4',
'title': 'Кукла',
'description': 'md5:ffca9372399976a2d260a407cc74cce6',
'duration': 5599,
'thumbnail': 're:^https?://.*\.jpg$',
},
'skip': 'Only works from Russia',
}
]
# Sorted by quality
_KNOWN_FORMATS = ['MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi', 'MP4-SHQ']
_KNOWN_FORMATS = (
'MP4-low-mobile', 'MP4-mobile', 'FLV-lo', 'MP4-lo', 'FLV-hi', 'MP4-hi',
'MP4-SHQ', 'MP4-HD720', 'MP4-HD1080')
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -69,10 +85,9 @@ class IviIE(InfoExtractor):
]
}
request = sanitized_Request(
'http://api.digitalaccess.ru/api/json/', json.dumps(data))
video_json = self._download_json(
request, video_id, 'Downloading video JSON')
'http://api.digitalaccess.ru/api/json/', video_id,
'Downloading video JSON', data=json.dumps(data))
if 'error' in video_json:
error = video_json['error']
@@ -84,11 +99,13 @@ class IviIE(InfoExtractor):
result = video_json['result']
quality = qualities(self._KNOWN_FORMATS)
formats = [{
'url': x['url'],
'format_id': x['content_format'],
'preference': self._KNOWN_FORMATS.index(x['content_format']),
} for x in result['files'] if x['content_format'] in self._KNOWN_FORMATS]
'format_id': x.get('content_format'),
'quality': quality(x.get('content_format')),
} for x in result['files'] if x.get('url')]
self._sort_formats(formats)
@@ -115,7 +132,7 @@ class IviIE(InfoExtractor):
webpage, 'season number', default=None))
episode_number = int_or_none(self._search_regex(
r'<meta[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
r'[^>]+itemprop="episode"[^>]*>\s*<meta[^>]+itemprop="episodeNumber"[^>]+content="(\d+)',
webpage, 'episode number', default=None))
description = self._og_search_description(webpage, default=None) or self._html_search_meta(

View File

@@ -30,7 +30,7 @@ class JWPlatformBaseIE(InfoExtractor):
return self._parse_jwplayer_data(
jwplayer_data, video_id, *args, **kwargs)
def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
def _parse_jwplayer_data(self, jwplayer_data, video_id=None, require_title=True, m3u8_id=None, rtmp_params=None, base_url=None):
# JWPlayer backward compatibility: flattened playlists
# https://github.com/jwplayer/jwplayer/blob/v7.4.3/src/js/api/config.js#L81-L96
if 'playlist' not in jwplayer_data:
@@ -43,6 +43,8 @@ class JWPlatformBaseIE(InfoExtractor):
if 'sources' not in video_data:
video_data['sources'] = [video_data]
this_video_id = video_id or video_data['mediaid']
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
@@ -52,7 +54,7 @@ class JWPlatformBaseIE(InfoExtractor):
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
# https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
formats.append({
@@ -68,7 +70,7 @@ class JWPlatformBaseIE(InfoExtractor):
'ext': ext,
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv',
a_format['ext'] = 'flv'
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
@@ -95,7 +97,7 @@ class JWPlatformBaseIE(InfoExtractor):
})
entries.append({
'id': video_id,
'id': this_video_id,
'title': video_data['title'] if require_title else video_data.get('title'),
'description': video_data.get('description'),
'thumbnail': self._proto_relative_url(video_data.get('image')),

View File

@@ -36,6 +36,12 @@ class KalturaIE(InfoExtractor):
'''
_SERVICE_URL = 'http://cdnapi.kaltura.com'
_SERVICE_BASE = '/api_v3/index.php'
# See https://github.com/kaltura/server/blob/master/plugins/content/caption/base/lib/model/enums/CaptionType.php
_CAPTION_TYPES = {
1: 'srt',
2: 'ttml',
3: 'vtt',
}
_TESTS = [
{
'url': 'kaltura:269692:1_1jc2y3e4',
@@ -67,6 +73,27 @@ class KalturaIE(InfoExtractor):
# video with subtitles
'url': 'kaltura:111032:1_cw786r8q',
'only_matching': True,
},
{
# video with ttml subtitles (no fileExt)
'url': 'kaltura:1926081:0_l5ye1133',
'info_dict': {
'id': '0_l5ye1133',
'ext': 'mp4',
'title': 'What Can You Do With Python?',
'upload_date': '20160221',
'uploader_id': 'stork',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'timestamp': int,
'subtitles': {
'en': [{
'ext': 'ttml',
}],
},
},
'params': {
'skip_download': True,
},
}
]
@@ -122,18 +149,6 @@ class KalturaIE(InfoExtractor):
return data
def _get_kaltura_signature(self, video_id, partner_id, service_url=None):
actions = [{
'apiVersion': '3.1',
'expiry': 86400,
'format': 1,
'service': 'session',
'action': 'startWidgetSession',
'widgetId': '_%s' % partner_id,
}]
return self._kaltura_api_call(
video_id, actions, service_url, note='Downloading Kaltura signature')['ks']
def _get_video_info(self, video_id, partner_id, service_url=None):
actions = [
{
@@ -208,6 +223,17 @@ class KalturaIE(InfoExtractor):
reference_id)['entryResult']
info, flavor_assets = entry_data['meta'], entry_data['contextData']['flavorAssets']
entry_id = info['id']
# Unfortunately, data returned in kalturaIframePackageData lacks
# captions so we will try requesting the complete data using
# regular approach since we now know the entry_id
try:
_, info, flavor_assets, captions = self._get_video_info(
entry_id, partner_id)
except ExtractorError:
# Regular scenario failed but we already have everything
# extracted apart from captions and can process at least
# with this
pass
else:
raise ExtractorError('Invalid URL', expected=True)
ks = params.get('flashvars[ks]', [None])[0]
@@ -265,9 +291,12 @@ class KalturaIE(InfoExtractor):
# Continue if caption is not ready
if f.get('status') != 2:
continue
if not caption.get('id'):
continue
caption_format = int_or_none(caption.get('format'))
subtitles.setdefault(caption.get('languageCode') or caption.get('language'), []).append({
'url': '%s/api_v3/service/caption_captionasset/action/serve/captionAssetId/%s' % (self._SERVICE_URL, caption['id']),
'ext': caption.get('fileExt'),
'ext': caption.get('fileExt') or self._CAPTION_TYPES.get(caption_format) or 'ttml',
})
return {

View File

@@ -3,64 +3,126 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..aes import aes_decrypt_text
from ..compat import (
compat_str,
compat_urllib_parse_unquote,
)
from ..utils import (
sanitized_Request,
url_basename,
determine_ext,
ExtractorError,
int_or_none,
str_to_int,
strip_or_none,
)
class KeezMoviesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/.+?(?P<id>[0-9]+)(?:[/?&]|$)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?keezmovies\.com/video/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.keezmovies.com/video/petite-asian-lady-mai-playing-in-bathtub-1214711',
'md5': '1c1e75d22ffa53320f45eeb07bc4cdc0',
'info_dict': {
'id': '1214711',
'display_id': 'petite-asian-lady-mai-playing-in-bathtub',
'ext': 'mp4',
'title': 'Petite Asian Lady Mai Playing In Bathtub',
'age_limit': 18,
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
'age_limit': 18,
}
}
}, {
'url': 'http://www.keezmovies.com/video/1214711',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
def _extract_info(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = (mobj.group('display_id')
if 'display_id' in mobj.groupdict()
else None) or mobj.group('id')
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
# embedded video
mobj = re.search(r'href="([^"]+)"></iframe>', webpage)
if mobj:
embedded_url = mobj.group(1)
return self.url_result(embedded_url)
video_title = self._html_search_regex(
r'<h1 [^>]*>([^<]+)', webpage, 'title')
flashvars = self._parse_json(self._search_regex(
r'var\s+flashvars\s*=\s*([^;]+);', webpage, 'flashvars'), video_id)
webpage = self._download_webpage(
url, display_id, headers={'Cookie': 'age_verified=1'})
formats = []
for height in (180, 240, 480):
if flashvars.get('quality_%dp' % height):
video_url = flashvars['quality_%dp' % height]
a_format = {
'url': video_url,
'height': height,
'format_id': '%dp' % height,
}
filename_parts = url_basename(video_url).split('_')
if len(filename_parts) >= 2 and re.match(r'\d+[Kk]', filename_parts[1]):
a_format['tbr'] = int(filename_parts[1][:-1])
formats.append(a_format)
format_urls = set()
age_limit = self._rta_search(webpage)
title = None
thumbnail = None
duration = None
encrypted = False
return {
def extract_format(format_url, height=None):
if not isinstance(format_url, compat_str) or not format_url.startswith('http'):
return
if format_url in format_urls:
return
format_urls.add(format_url)
tbr = int_or_none(self._search_regex(
r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
if not height:
height = int_or_none(self._search_regex(
r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
if encrypted:
format_url = aes_decrypt_text(
video_url, title, 32).decode('utf-8')
formats.append({
'url': format_url,
'format_id': '%dp' % height if height else None,
'height': height,
'tbr': tbr,
})
flashvars = self._parse_json(
self._search_regex(
r'flashvars\s*=\s*({.+?});', webpage,
'flashvars', default='{}'),
display_id, fatal=False)
if flashvars:
title = flashvars.get('video_title')
thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration'))
encrypted = flashvars.get('encrypted') is True
for key, value in flashvars.items():
mobj = re.search(r'quality_(\d+)[pP]', key)
if mobj:
extract_format(value, int(mobj.group(1)))
video_url = flashvars.get('video_url')
if video_url and determine_ext(video_url, None):
extract_format(video_url)
video_url = self._html_search_regex(
r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
webpage, 'video url', default=None, group='url')
if video_url:
extract_format(compat_urllib_parse_unquote(video_url))
if not formats:
if 'title="This video is no longer available"' in webpage:
raise ExtractorError(
'Video %s is no longer available' % video_id, expected=True)
self._sort_formats(formats)
if not title:
title = self._html_search_regex(
r'<h1[^>]*>([^<]+)', webpage, 'title')
return webpage, {
'id': video_id,
'title': video_title,
'display_id': display_id,
'title': strip_or_none(title),
'thumbnail': thumbnail,
'duration': duration,
'age_limit': 18,
'formats': formats,
'age_limit': age_limit,
'thumbnail': flashvars.get('image_url')
}
def _real_extract(self, url):
webpage, info = self._extract_info(url)
info['view_count'] = str_to_int(self._search_regex(
r'<b>([\d,.]+)</b> Views?', webpage, 'view count', fatal=False))
return info

View File

@@ -37,7 +37,6 @@ class KickStarterIE(InfoExtractor):
'ext': 'mp4',
'title': 'Power Drive 2000',
},
'expected_warnings': ['OpenGraph description'],
}]
def _real_extract(self, url):
@@ -67,6 +66,6 @@ class KickStarterIE(InfoExtractor):
'id': video_id,
'url': video_url,
'title': title,
'description': self._og_search_description(webpage),
'description': self._og_search_description(webpage, default=None),
'thumbnail': thumbnail,
}

View File

@@ -18,31 +18,20 @@ from ..utils import (
class KUSIIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
_TESTS = [{
'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
'url': 'http://www.kusi.com/story/32849881/turko-files-refused-to-help-it-aint-right',
'md5': '4e76ce8e53660ce9697d06c0ba6fc47d',
'info_dict': {
'id': '12203019',
'id': '12689020',
'ext': 'mp4',
'title': 'Turko Files: Case Closed! & Put On Hold!',
'duration': 231.0,
'upload_date': '20160210',
'timestamp': 1455087571,
'title': "Turko Files: Refused to Help, It Ain't Right!",
'duration': 223.586,
'upload_date': '20160826',
'timestamp': 1472233118,
'thumbnail': 're:^https?://.*\.jpg$'
},
}, {
'url': 'http://kusi.com/video?clipId=12203019',
'info_dict': {
'id': '12203019',
'ext': 'mp4',
'title': 'Turko Files: Case Closed! & Put On Hold!',
'duration': 231.0,
'upload_date': '20160210',
'timestamp': 1455087571,
'thumbnail': 're:^https?://.*\.jpg$'
},
'params': {
'skip_download': True, # Same as previous one
},
'only_matching': True,
}]
def _real_extract(self, url):

View File

@@ -4,7 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..compat import (
compat_str,
compat_urlparse,
)
from ..utils import (
determine_ext,
ExtractorError,
@@ -96,7 +99,7 @@ class LifeNewsIE(InfoExtractor):
r'<video[^>]+><source[^>]+src=["\'](.+?)["\']', webpage)
iframe_links = re.findall(
r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/embed/.+?)["\']',
r'<iframe[^>]+src=["\']((?:https?:)?//embed\.life\.ru/(?:embed|video)/.+?)["\']',
webpage)
if not video_urls and not iframe_links:
@@ -164,9 +167,9 @@ class LifeNewsIE(InfoExtractor):
class LifeEmbedIE(InfoExtractor):
IE_NAME = 'life:embed'
_VALID_URL = r'https?://embed\.life\.ru/embed/(?P<id>[\da-f]{32})'
_VALID_URL = r'https?://embed\.life\.ru/(?:embed|video)/(?P<id>[\da-f]{32})'
_TEST = {
_TESTS = [{
'url': 'http://embed.life.ru/embed/e50c2dec2867350528e2574c899b8291',
'md5': 'b889715c9e49cb1981281d0e5458fbbe',
'info_dict': {
@@ -175,30 +178,57 @@ class LifeEmbedIE(InfoExtractor):
'title': 'e50c2dec2867350528e2574c899b8291',
'thumbnail': 're:http://.*\.jpg',
}
}
}, {
# with 1080p
'url': 'https://embed.life.ru/video/e50c2dec2867350528e2574c899b8291',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
thumbnail = None
formats = []
for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
video_url = compat_urlparse.urljoin(url, video_url)
ext = determine_ext(video_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='m3u8'))
else:
formats.append({
'url': video_url,
'format_id': ext,
'preference': 1,
})
def extract_m3u8(manifest_url):
formats.extend(self._extract_m3u8_formats(
manifest_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='m3u8'))
def extract_original(original_url):
formats.append({
'url': original_url,
'format_id': determine_ext(original_url, None),
'preference': 1,
})
playlist = self._parse_json(
self._search_regex(
r'options\s*=\s*({.+?});', webpage, 'options', default='{}'),
video_id).get('playlist', {})
if playlist:
master = playlist.get('master')
if isinstance(master, compat_str) and determine_ext(master) == 'm3u8':
extract_m3u8(compat_urlparse.urljoin(url, master))
original = playlist.get('original')
if isinstance(original, compat_str):
extract_original(original)
thumbnail = playlist.get('image')
# Old rendition fallback
if not formats:
for video_url in re.findall(r'"file"\s*:\s*"([^"]+)', webpage):
video_url = compat_urlparse.urljoin(url, video_url)
if determine_ext(video_url) == 'm3u8':
extract_m3u8(video_url)
else:
extract_original(video_url)
self._sort_formats(formats)
thumbnail = self._search_regex(
thumbnail = thumbnail or self._search_regex(
r'"image"\s*:\s*"([^"]+)', webpage, 'thumbnail', default=None)
return {

View File

@@ -34,11 +34,12 @@ class LimelightBaseIE(InfoExtractor):
def _extract_info(self, streams, mobile_urls, properties):
video_id = properties['media_id']
formats = []
urls = []
for stream in streams:
stream_url = stream.get('url')
if not stream_url or stream.get('drmProtected'):
if not stream_url or stream.get('drmProtected') or stream_url in urls:
continue
urls.append(stream_url)
ext = determine_ext(stream_url)
if ext == 'f4m':
formats.extend(self._extract_f4m_formats(
@@ -58,9 +59,11 @@ class LimelightBaseIE(InfoExtractor):
format_id = 'rtmp'
if stream.get('videoBitRate'):
format_id += '-%d' % int_or_none(stream['videoBitRate'])
http_url = 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:])
urls.append(http_url)
http_fmt = fmt.copy()
http_fmt.update({
'url': 'http://%s/%s' % (rtmp.group('host').replace('csl.', 'cpl.'), rtmp.group('playpath')[4:]),
'url': http_url,
'format_id': format_id.replace('rtmp', 'http'),
})
formats.append(http_fmt)
@@ -76,8 +79,9 @@ class LimelightBaseIE(InfoExtractor):
for mobile_url in mobile_urls:
media_url = mobile_url.get('mobileUrl')
format_id = mobile_url.get('targetMediaPlatform')
if not media_url or format_id == 'Widevine':
if not media_url or format_id in ('Widevine', 'SmoothStreaming') or media_url in urls:
continue
urls.append(media_url)
ext = determine_ext(media_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(

View File

@@ -14,7 +14,7 @@ from ..utils import (
class LiTVIE(InfoExtractor):
_VALID_URL = r'https?://www\.litv\.tv/vod/[^/]+/content\.do\?.*?\bid=(?P<id>[^&]+)'
_VALID_URL = r'https?://www\.litv\.tv/(?:vod|promo)/[^/]+/(?:content\.do)?\?.*?\b(?:content_)?id=(?P<id>[^&]+)'
_URL_TEMPLATE = 'https://www.litv.tv/vod/%s/content.do?id=%s'
@@ -27,6 +27,7 @@ class LiTVIE(InfoExtractor):
'playlist_count': 50,
}, {
'url': 'https://www.litv.tv/vod/drama/content.do?brc_id=root&id=VOD00041610&isUHEnabled=true&autoPlay=1',
'md5': '969e343d9244778cb29acec608e53640',
'info_dict': {
'id': 'VOD00041610',
'ext': 'mp4',
@@ -37,7 +38,16 @@ class LiTVIE(InfoExtractor):
},
'params': {
'noplaylist': True,
'skip_download': True, # m3u8 download
},
'skip': 'Georestricted to Taiwan',
}, {
'url': 'https://www.litv.tv/promo/miyuezhuan/?content_id=VOD00044841&',
'md5': '88322ea132f848d6e3e18b32a832b918',
'info_dict': {
'id': 'VOD00044841',
'ext': 'mp4',
'title': '芈月傳第1集 霸星芈月降世楚國',
'description': '楚威王二年,太史令唐昧夜觀星象,發現霸星即將現世。王后得知霸星的預言後,想盡辦法不讓孩子順利出生,幸得莒姬相護化解危機。沒想到眾人期待下出生的霸星卻是位公主,楚威王對此失望至極。楚王后命人將女嬰丟棄河中,居然奇蹟似的被少司命像攔下,楚威王認為此女非同凡響,為她取名芈月。',
},
'skip': 'Georestricted to Taiwan',
}]
@@ -92,13 +102,18 @@ class LiTVIE(InfoExtractor):
# endpoint gives the same result as the data embedded in the webpage.
# If georestricted, there are no embedded data, so an extra request is
# necessary to get the error code
if 'assetId' not in view_data:
view_data = self._download_json(
'https://www.litv.tv/vod/ajax/getProgramInfo', video_id,
query={'contentId': video_id},
headers={'Accept': 'application/json'})
video_data = self._parse_json(self._search_regex(
r'uiHlsUrl\s*=\s*testBackendData\(([^;]+)\);',
webpage, 'video data', default='{}'), video_id)
if not video_data:
payload = {
'assetId': view_data['assetId'],
'watchDevices': vod_data['watchDevices'],
'watchDevices': view_data['watchDevices'],
'contentType': view_data['contentType'],
}
video_data = self._download_json(
@@ -115,7 +130,8 @@ class LiTVIE(InfoExtractor):
raise ExtractorError('Unexpected result from %s' % self.IE_NAME)
formats = self._extract_m3u8_formats(
video_data['fullpath'], video_id, ext='mp4', m3u8_id='hls')
video_data['fullpath'], video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls')
for a_format in formats:
# LiTV HLS segments doesn't like compressions
a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = True

View File

@@ -25,10 +25,7 @@ class MioMioIE(InfoExtractor):
'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,
},
'params': {
# The server provides broken file
'skip_download': True,
}
'skip': 'Unable to load videos',
}, {
'url': 'http://www.miomio.tv/watch/cc184024/',
'info_dict': {
@@ -47,16 +44,12 @@ class MioMioIE(InfoExtractor):
'skip': 'Unable to load videos',
}, {
# new 'h5' player
'url': 'http://www.miomio.tv/watch/cc273295/',
'md5': '',
'url': 'http://www.miomio.tv/watch/cc273997/',
'md5': '0b27a4b4495055d826813f8c3a6b2070',
'info_dict': {
'id': '273295',
'id': '273997',
'ext': 'mp4',
'title': 'アウト×デラックス 20160526',
},
'params': {
# intermittent HTTP 500
'skip_download': True,
'title': 'マツコの知らない世界【劇的進化SPビニール傘冷凍食品2016】 1_2 - 16 05 31',
},
}]
@@ -116,7 +109,7 @@ class MioMioIE(InfoExtractor):
player_webpage = self._download_webpage(
player_url, video_id,
note='Downloading player webpage', headers={'Referer': url})
entries = self._parse_html5_media_entries(player_url, player_webpage)
entries = self._parse_html5_media_entries(player_url, player_webpage, video_id)
http_headers = {'Referer': player_url}
else:
http_headers = {'Referer': 'http://www.miomio.tv%s' % mioplayer_path}

View File

@@ -1,53 +1,56 @@
from __future__ import unicode_literals
import os
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_unquote,
compat_urllib_parse_urlparse,
from ..utils import (
int_or_none,
str_to_int,
unified_strdate,
)
from ..utils import sanitized_Request
from .keezmovies import KeezMoviesIE
class MofosexIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
_TEST = {
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
class MofosexIE(KeezMoviesIE):
_VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
_TESTS = [{
'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
'md5': '39a15853632b7b2e5679f92f69b78e91',
'info_dict': {
'id': '5018',
'id': '318131',
'display_id': 'amateur-teen-playing-and-masturbating-318131',
'ext': 'mp4',
'title': 'Japanese Teen Music Video',
'title': 'amateur teen playing and masturbating',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20121114',
'view_count': int,
'like_count': int,
'dislike_count': int,
'age_limit': 18,
}
}
}, {
# This video is no longer available
'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
url = 'http://www.' + mobj.group('url')
webpage, info = self._extract_info(url)
req = sanitized_Request(url)
req.add_header('Cookie', 'age_verified=1')
webpage = self._download_webpage(req, video_id)
view_count = str_to_int(self._search_regex(
r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
like_count = int_or_none(self._search_regex(
r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
'like count', fatal=False))
dislike_count = int_or_none(self._search_regex(
r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
'like count', fatal=False))
upload_date = unified_strdate(self._html_search_regex(
r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
path = compat_urllib_parse_urlparse(video_url).path
extension = os.path.splitext(path)[1][1:]
format = path.split('/')[5].split('_')[:2]
format = '-'.join(format)
info.update({
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'upload_date': upload_date,
'thumbnail': self._og_search_thumbnail(webpage),
})
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'title': video_title,
'url': video_url,
'ext': extension,
'format': format,
'format_id': format,
'age_limit': age_limit,
}
return info

View File

@@ -7,22 +7,19 @@ from ..utils import (
)
class SSAIE(InfoExtractor):
_VALID_URL = r'https?://ssa\.nls\.uk/film/(?P<id>\d+)'
class MovingImageIE(InfoExtractor):
_VALID_URL = r'https?://movingimage\.nls\.uk/film/(?P<id>\d+)'
_TEST = {
'url': 'http://ssa.nls.uk/film/3561',
'url': 'http://movingimage.nls.uk/film/3561',
'md5': '4caa05c2b38453e6f862197571a7be2f',
'info_dict': {
'id': '3561',
'ext': 'flv',
'ext': 'mp4',
'title': 'SHETLAND WOOL',
'description': 'md5:c5afca6871ad59b4271e7704fe50ab04',
'duration': 900,
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
# rtmp download
'skip_download': True,
},
}
def _real_extract(self, url):
@@ -30,10 +27,9 @@ class SSAIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
streamer = self._search_regex(
r"'streamer'\s*,\S*'(rtmp[^']+)'", webpage, 'streamer')
play_path = self._search_regex(
r"'file'\s*,\s*'([^']+)'", webpage, 'file').rpartition('.')[0]
formats = self._extract_m3u8_formats(
self._html_search_regex(r'file\s*:\s*"([^"]+)"', webpage, 'm3u8 manifest URL'),
video_id, ext='mp4', entry_protocol='m3u8_native')
def search_field(field_name, fatal=False):
return self._search_regex(
@@ -44,13 +40,11 @@ class SSAIE(InfoExtractor):
description = unescapeHTML(search_field('Description'))
duration = parse_duration(search_field('Running time'))
thumbnail = self._search_regex(
r"'image'\s*,\s*'([^']+)'", webpage, 'thumbnails', fatal=False)
r"image\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
return {
'id': video_id,
'url': streamer,
'play_path': play_path,
'ext': 'flv',
'formats': formats,
'title': title,
'description': description,
'duration': duration,

View File

@@ -4,7 +4,6 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
compat_xpath,
)
@@ -14,12 +13,13 @@ from ..utils import (
fix_xml_ampersands,
float_or_none,
HEADRequest,
RegexNotFoundError,
sanitized_Request,
strip_or_none,
timeconvert,
unescapeHTML,
update_url_query,
url_basename,
RegexNotFoundError,
xpath_text,
)
@@ -36,6 +36,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
def _id_from_uri(uri):
return uri.split(':')[-1]
@staticmethod
def _remove_template_parameter(url):
# Remove the templates, like &device={device}
return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
# This was originally implemented for ComedyCentral, but it also works here
@classmethod
def _transform_rtmp_url(cls, rtmp_video_url):
@@ -117,9 +122,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
video_id = self._id_from_uri(uri)
self.report_extraction(video_id)
content_el = itemdoc.find('%s/%s' % (_media_xml_tag('group'), _media_xml_tag('content')))
mediagen_url = content_el.attrib['url']
# Remove the templates, like &device={device}
mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url)
mediagen_url = self._remove_template_parameter(content_el.attrib['url'])
if 'acceptMethods' not in mediagen_url:
mediagen_url += '&' if '?' in mediagen_url else '?'
mediagen_url += 'acceptMethods=fms'
@@ -178,12 +181,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
data = {'uri': uri}
if self._LANG:
data['lang'] = self._LANG
return compat_urllib_parse_urlencode(data)
return data
def _get_videos_info(self, uri):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
info_url = feed_url + '?' + self._get_feed_query(uri)
info_url = update_url_query(feed_url, self._get_feed_query(uri))
return self._get_videos_info_from_url(info_url, video_id)
def _get_videos_info_from_url(self, url, video_id):
@@ -256,13 +259,9 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
def _get_feed_url(self, uri):
video_id = self._id_from_uri(uri)
site_id = uri.replace(video_id, '')
config_url = ('http://media.mtvnservices.com/pmt/e1/players/{0}/'
'context4/context5/config.xml'.format(site_id))
config_doc = self._download_xml(config_url, video_id)
feed_node = config_doc.find('.//feed')
feed_url = feed_node.text.strip().split('?')[0]
return feed_url
config = self._download_json(
'http://media.mtvnservices.com/pmt/e1/access/index.html?uri=%s&configtype=edge' % uri, video_id)
return self._remove_template_parameter(config['feedWithQueryParams'])
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

View File

@@ -13,7 +13,7 @@ class MyVidsterIE(InfoExtractor):
'id': '3685814',
'title': 'md5:7d8427d6d02c4fbcef50fe269980c749',
'upload_date': '20141027',
'uploader_id': 'utkualp',
'uploader': 'utkualp',
'ext': 'mp4',
'age_limit': 18,
},

View File

@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..utils import (
smuggle_url,
url_basename,
@@ -65,7 +65,7 @@ class NationalGeographicVideoIE(InfoExtractor):
}
class NationalGeographicIE(ThePlatformIE):
class NationalGeographicIE(AdobePassIE):
IE_NAME = 'natgeo'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?[^/]+/(?:videos|episodes)/(?P<id>[^/?]+)'
@@ -119,7 +119,7 @@ class NationalGeographicIE(ThePlatformIE):
auth_resource_id = self._search_regex(
r"video_auth_resourceId\s*=\s*'([^']+)'",
webpage, 'auth resource id')
query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id) or ''
query['auth'] = self._extract_mvpd_auth(url, display_id, 'natgeo', auth_resource_id)
return {
'_type': 'url_transparent',
@@ -131,7 +131,7 @@ class NationalGeographicIE(ThePlatformIE):
}
class NationalGeographicEpisodeGuideIE(ThePlatformIE):
class NationalGeographicEpisodeGuideIE(InfoExtractor):
IE_NAME = 'natgeo:episodeguide'
_VALID_URL = r'https?://channel\.nationalgeographic\.com/(?:wild/)?(?P<id>[^/]+)/episode-guide'
_TESTS = [

View File

@@ -1,25 +1,20 @@
from __future__ import unicode_literals
import functools
import os.path
import re
from .common import InfoExtractor
from .turner import TurnerBaseIE
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
int_or_none,
OnDemandPagedList,
parse_duration,
remove_start,
xpath_text,
xpath_attr,
)
class NBAIE(InfoExtractor):
class NBAIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:watch\.|www\.)?nba\.com/(?P<path>(?:[^/]+/)+(?P<id>[^?]*?))/?(?:/index\.html)?(?:\?.*)?$'
_TESTS = [{
'url': 'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
@@ -44,28 +39,30 @@ class NBAIE(InfoExtractor):
'url': 'http://watch.nba.com/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
'md5': 'b2b39b81cf28615ae0c3360a3f9668c4',
'info_dict': {
'id': '0041400301-cle-atl-recap',
'id': 'channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba',
'ext': 'mp4',
'title': 'Hawks vs. Cavaliers Game 1',
'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d',
'duration': 228,
'timestamp': 1432134543,
'upload_date': '20150520',
}
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.nba.com/clippers/news/doc-rivers-were-not-trading-blake',
'info_dict': {
'id': '1455672027478-Doc_Feb16_720',
'id': 'teams/clippers/2016/02/17/1455672027478-Doc_Feb16_720.mov-297324',
'ext': 'mp4',
'title': 'Practice: Doc Rivers - 2/16/16',
'description': 'Head Coach Doc Rivers addresses the media following practice.',
'upload_date': '20160217',
'upload_date': '20160216',
'timestamp': 1455672000,
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
'info_dict': {
@@ -80,7 +77,7 @@ class NBAIE(InfoExtractor):
}, {
'url': 'http://www.nba.com/timberwolves/wiggins-shootaround#',
'info_dict': {
'id': 'Wigginsmp4',
'id': 'teams/timberwolves/2014/12/12/Wigginsmp4-3462601',
'ext': 'mp4',
'title': 'Shootaround Access - Dec. 12 | Andrew Wiggins',
'description': 'Wolves rookie Andrew Wiggins addresses the media after Friday\'s shootaround.',
@@ -92,6 +89,7 @@ class NBAIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Unable to download f4m manifest'],
}]
_PAGE_SIZE = 30
@@ -145,53 +143,12 @@ class NBAIE(InfoExtractor):
if path.startswith('video/teams'):
path = 'video/channels/proxy/' + path[6:]
video_info = self._download_xml('http://www.nba.com/%s.xml' % path, video_id)
video_id = os.path.splitext(xpath_text(video_info, 'slug'))[0]
title = xpath_text(video_info, 'headline')
description = xpath_text(video_info, 'description')
duration = parse_duration(xpath_text(video_info, 'length'))
timestamp = int_or_none(xpath_attr(video_info, 'dateCreated', 'uts'))
thumbnails = []
for image in video_info.find('images'):
thumbnails.append({
'id': image.attrib.get('cut'),
'url': image.text,
'width': int_or_none(image.attrib.get('width')),
'height': int_or_none(image.attrib.get('height')),
return self._extract_cvp_info(
'http://www.nba.com/%s.xml' % path, video_id, {
'default': {
'media_src': 'http://nba.cdn.turner.com/nba/big',
},
'm3u8': {
'media_src': 'http://nbavod-f.akamaihd.net',
},
})
formats = []
for video_file in video_info.findall('.//file'):
video_url = video_file.text
if video_url.startswith('/'):
continue
if video_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls', fatal=False))
elif video_url.endswith('.f4m'):
formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.1.1', video_id, f4m_id='hds', fatal=False))
else:
key = video_file.attrib.get('bitrate')
format_info = {
'format_id': key,
'url': video_url,
}
mobj = re.search(r'(\d+)x(\d+)(?:_(\d+))?', key)
if mobj:
format_info.update({
'width': int(mobj.group(1)),
'height': int(mobj.group(2)),
'tbr': int_or_none(mobj.group(3)),
})
formats.append(format_info)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'thumbnails': thumbnails,
'formats': formats,
}

View File

@@ -0,0 +1,50 @@
from __future__ import unicode_literals
from .common import InfoExtractor
class NhkVodIE(InfoExtractor):
_VALID_URL = r'https?://www3\.nhk\.or\.jp/nhkworld/en/vod/(?P<id>.+?)\.html'
_TEST = {
# Videos available only for a limited period of time. Visit
# http://www3.nhk.or.jp/nhkworld/en/vod/ for working samples.
'url': 'http://www3.nhk.or.jp/nhkworld/en/vod/tokyofashion/20160815.html',
'info_dict': {
'id': 'A1bnNiNTE6nY3jLllS-BIISfcC_PpvF5',
'ext': 'flv',
'title': 'TOKYO FASHION EXPRESS - The Kimono as Global Fashion',
'description': 'md5:db338ee6ce8204f415b754782f819824',
'series': 'TOKYO FASHION EXPRESS',
'episode': 'The Kimono as Global Fashion',
},
'skip': 'Videos available only for a limited period of time',
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
embed_code = self._search_regex(
r'nw_vod_ooplayer\([^,]+,\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'ooyala embed code', group='id')
title = self._search_regex(
r'<div[^>]+class=["\']episode-detail["\']>\s*<h\d+>([^<]+)',
webpage, 'title', default=None)
description = self._html_search_regex(
r'(?s)<p[^>]+class=["\']description["\'][^>]*>(.+?)</p>',
webpage, 'description', default=None)
series = self._search_regex(
r'<h2[^>]+class=["\']detail-top-player-title[^>]+><a[^>]+>([^<]+)',
webpage, 'series', default=None)
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % embed_code,
'title': '%s - %s' % (series, title) if series and title else title,
'description': description,
'series': series,
'episode': title,
}

View File

@@ -2,7 +2,6 @@
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..utils import update_url_query
@@ -59,10 +58,10 @@ class NickIE(MTVServicesInfoExtractor):
}]
def _get_feed_query(self, uri):
return compat_urllib_parse_urlencode({
return {
'feed': 'nick_arc_player_prime',
'mgid': uri,
})
}
def _extract_mgid(self, webpage):
return self._search_regex(r'data-contenturi="([^"]+)', webpage, 'mgid')

View File

@@ -4,40 +4,36 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
parse_iso8601,
parse_duration,
ExtractorError
float_or_none,
ExtractorError,
int_or_none,
)
class NineCNineMediaIE(InfoExtractor):
_VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
class NineCNineMediaBaseIE(InfoExtractor):
_API_BASE_TEMPLATE = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/'
class NineCNineMediaStackIE(NineCNineMediaBaseIE):
IE_NAME = '9c9media:stack'
_VALID_URL = r'9c9media:stack:(?P<destination_code>[^:]+):(?P<content_id>\d+):(?P<content_package>\d+):(?P<id>\d+)'
def _real_extract(self, url):
destination_code, video_id = re.match(self._VALID_URL, url).groups()
api_base_url = 'http://capi.9c9media.com/destinations/%s/platforms/desktop/contents/%s/' % (destination_code, video_id)
content = self._download_json(api_base_url, video_id, query={
'$include': '[contentpackages]',
})
title = content['Name']
if len(content['ContentPackages']) > 1:
raise ExtractorError('multiple content packages')
content_package = content['ContentPackages'][0]
stacks_base_url = api_base_url + 'contentpackages/%s/stacks/' % content_package['Id']
stacks = self._download_json(stacks_base_url, video_id)['Items']
if len(stacks) > 1:
raise ExtractorError('multiple stacks')
stack = stacks[0]
stack_base_url = '%s%s/manifest.' % (stacks_base_url, stack['Id'])
destination_code, content_id, package_id, stack_id = re.match(self._VALID_URL, url).groups()
stack_base_url_template = self._API_BASE_TEMPLATE + 'contentpackages/%s/stacks/%s/manifest.'
stack_base_url = stack_base_url_template % (destination_code, content_id, package_id, stack_id)
formats = []
formats.extend(self._extract_m3u8_formats(
stack_base_url + 'm3u8', video_id, 'mp4',
stack_base_url + 'm3u8', stack_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
formats.extend(self._extract_f4m_formats(
stack_base_url + 'f4m', video_id,
stack_base_url + 'f4m', stack_id,
f4m_id='hds', fatal=False))
mp4_url = self._download_webpage(stack_base_url + 'pd', video_id, fatal=False)
mp4_url = self._download_webpage(stack_base_url + 'pd', stack_id, fatal=False)
if mp4_url:
formats.append({
'url': mp4_url,
@@ -46,10 +42,86 @@ class NineCNineMediaIE(InfoExtractor):
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': content.get('Desc') or content.get('ShortDesc'),
'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
'duration': parse_duration(content.get('BroadcastTime')),
'id': stack_id,
'formats': formats,
}
class NineCNineMediaIE(NineCNineMediaBaseIE):
IE_NAME = '9c9media'
_VALID_URL = r'9c9media:(?P<destination_code>[^:]+):(?P<id>\d+)'
def _real_extract(self, url):
destination_code, content_id = re.match(self._VALID_URL, url).groups()
api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
content = self._download_json(api_base_url, content_id, query={
'$include': '[Media,Season,ContentPackages]',
})
title = content['Name']
if len(content['ContentPackages']) > 1:
raise ExtractorError('multiple content packages')
content_package = content['ContentPackages'][0]
package_id = content_package['Id']
content_package_url = api_base_url + 'contentpackages/%s/' % package_id
content_package = self._download_json(content_package_url, content_id)
if content_package.get('Constraints', {}).get('Security', {}).get('Type') == 'adobe-drm':
raise ExtractorError('This video is DRM protected.', expected=True)
stacks = self._download_json(content_package_url + 'stacks/', package_id)['Items']
multistacks = len(stacks) > 1
thumbnails = []
for image in content.get('Images', []):
image_url = image.get('Url')
if not image_url:
continue
thumbnails.append({
'url': image_url,
'width': int_or_none(image.get('Width')),
'height': int_or_none(image.get('Height')),
})
tags, categories = [], []
for source_name, container in (('Tags', tags), ('Genres', categories)):
for e in content.get(source_name, []):
e_name = e.get('Name')
if not e_name:
continue
container.append(e_name)
description = content.get('Desc') or content.get('ShortDesc')
season = content.get('Season', {})
base_info = {
'description': description,
'timestamp': parse_iso8601(content.get('BroadcastDateTime')),
'episode_number': int_or_none(content.get('Episode')),
'season': season.get('Name'),
'season_number': season.get('Number'),
'season_id': season.get('Id'),
'series': content.get('Media', {}).get('Name'),
'tags': tags,
'categories': categories,
}
entries = []
for stack in stacks:
stack_id = compat_str(stack['Id'])
entry = {
'_type': 'url_transparent',
'url': '9c9media:stack:%s:%s:%s:%s' % (destination_code, content_id, package_id, stack_id),
'id': stack_id,
'title': '%s_part%s' % (title, stack['Name']) if multistacks else title,
'duration': float_or_none(stack.get('Duration')),
'ie_key': 'NineCNineMediaStack',
}
entry.update(base_info)
entries.append(entry)
return {
'_type': 'multi_video',
'id': content_id,
'title': title,
'description': description,
'entries': entries,
}

View File

@@ -14,16 +14,6 @@ from ..utils import (
class NRKBaseIE(InfoExtractor):
def _extract_formats(self, manifest_url, video_id, fatal=True):
formats = []
formats.extend(self._extract_f4m_formats(
manifest_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81',
video_id, f4m_id='hds', fatal=fatal))
formats.extend(self._extract_m3u8_formats(manifest_url.replace(
'akamaihd.net/z/', 'akamaihd.net/i/').replace('/manifest.f4m', '/master.m3u8'),
video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=fatal))
return formats
def _real_extract(self, url):
video_id = self._match_id(url)
@@ -45,7 +35,7 @@ class NRKBaseIE(InfoExtractor):
asset_url = asset.get('url')
if not asset_url:
continue
formats = self._extract_formats(asset_url, video_id, fatal=False)
formats = self._extract_akamai_formats(asset_url, video_id)
if not formats:
continue
self._sort_formats(formats)
@@ -69,7 +59,7 @@ class NRKBaseIE(InfoExtractor):
if not entries:
media_url = data.get('mediaUrl')
if media_url:
formats = self._extract_formats(media_url, video_id)
formats = self._extract_akamai_formats(media_url, video_id)
self._sort_formats(formats)
duration = parse_duration(data.get('duration'))
entries = [{

View File

@@ -1,6 +1,8 @@
# encoding: utf-8
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
@@ -40,8 +42,8 @@ class NTVDeIE(InfoExtractor):
timestamp = int_or_none(info.get('publishedDateAsUnixTimeStamp'))
vdata = self._parse_json(self._search_regex(
r'(?s)\$\(\s*"\#player"\s*\)\s*\.data\(\s*"player",\s*(\{.*?\})\);',
webpage, 'player data'),
video_id, transform_source=js_to_json)
webpage, 'player data'), video_id,
transform_source=lambda s: js_to_json(re.sub(r'advertising:\s*{[^}]+},', '', s)))
duration = parse_duration(vdata.get('duration'))
formats = []

View File

@@ -1,26 +1,37 @@
from __future__ import unicode_literals
import hmac
import hashlib
import base64
from .common import InfoExtractor
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
mimetype2ext,
determine_ext,
)
class NYTimesBaseIE(InfoExtractor):
_SECRET = b'pX(2MbU2);4N{7J8)>YwKRJ+/pQ3JkiU2Q^V>mFYv6g6gYvt6v'
def _extract_video_from_id(self, video_id):
video_data = self._download_json(
'http://www.nytimes.com/svc/video/api/v2/video/%s' % video_id,
video_id, 'Downloading video JSON')
# Authorization generation algorithm is reverse engineered from `signer` in
# http://graphics8.nytimes.com/video/vhs/vhs-2.x.min.js
path = '/svc/video/api/v3/video/' + video_id
hm = hmac.new(self._SECRET, (path + ':vhs').encode(), hashlib.sha512).hexdigest()
video_data = self._download_json('http://www.nytimes.com' + path, video_id, 'Downloading video JSON', headers={
'Authorization': 'NYTV ' + base64.b64encode(hm.encode()).decode(),
'X-NYTV': 'vhs',
}, fatal=False)
if not video_data:
video_data = self._download_json(
'http://www.nytimes.com/svc/video/api/v2/video/' + video_id,
video_id, 'Downloading video JSON')
title = video_data['headline']
description = video_data.get('summary')
duration = float_or_none(video_data.get('duration'), 1000)
uploader = video_data.get('byline')
publication_date = video_data.get('publication_date')
timestamp = parse_iso8601(publication_date[:-8]) if publication_date else None
def get_file_size(file_size):
if isinstance(file_size, int):
@@ -28,35 +39,59 @@ class NYTimesBaseIE(InfoExtractor):
elif isinstance(file_size, dict):
return int(file_size.get('value', 0))
else:
return 0
return None
formats = [
{
'url': video['url'],
'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'] if video.get('url')
]
urls = []
formats = []
for video in video_data.get('renditions', []):
video_url = video.get('url')
format_id = video.get('type')
if not video_url or format_id == 'thumbs' or video_url in urls:
continue
urls.append(video_url)
ext = mimetype2ext(video.get('mimetype')) or determine_ext(video_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id or 'hls', fatal=False))
elif ext == 'mpd':
continue
# formats.extend(self._extract_mpd_formats(
# video_url, video_id, format_id or 'dash', fatal=False))
else:
formats.append({
'url': video_url,
'format_id': format_id,
'vcodec': video.get('videoencoding') or video.get('video_codec'),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'filesize': get_file_size(video.get('file_size') or video.get('fileSize')),
'tbr': int_or_none(video.get('bitrate'), 1000),
'ext': ext,
})
self._sort_formats(formats)
thumbnails = [
{
'url': 'http://www.nytimes.com/%s' % image['url'],
thumbnails = []
for image in video_data.get('images', []):
image_url = image.get('url')
if not image_url:
continue
thumbnails.append({
'url': 'http://www.nytimes.com/' + image_url,
'width': int_or_none(image.get('width')),
'height': int_or_none(image.get('height')),
} for image in video_data.get('images', []) if image.get('url')
]
})
publication_date = video_data.get('publication_date')
timestamp = parse_iso8601(publication_date[:-8]) if publication_date else None
return {
'id': video_id,
'title': title,
'description': description,
'description': video_data.get('summary'),
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
'uploader': video_data.get('byline'),
'duration': float_or_none(video_data.get('duration'), 1000),
'formats': formats,
'thumbnails': thumbnails,
}
@@ -67,7 +102,7 @@ class NYTimesIE(NYTimesBaseIE):
_TESTS = [{
'url': 'http://www.nytimes.com/video/opinion/100000002847155/verbatim-what-is-a-photocopier.html?playlistId=100000001150263',
'md5': '18a525a510f942ada2720db5f31644c0',
'md5': 'd665342765db043f7e225cff19df0f2d',
'info_dict': {
'id': '100000002847155',
'ext': 'mov',

View File

@@ -1,12 +1,12 @@
# coding: utf-8
from __future__ import unicode_literals, division
import math
from .common import InfoExtractor
from ..compat import compat_chr
from ..compat import (
compat_chr,
compat_ord,
)
from ..utils import (
decode_png,
determine_ext,
ExtractorError,
)
@@ -42,71 +42,28 @@ class OpenloadIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
if 'File not found' in webpage:
if 'File not found' in webpage or 'deleted by the owner' in webpage:
raise ExtractorError('File not found', expected=True)
# The following extraction logic is proposed by @Belderak and @gdkchan
# and declared to be used freely in youtube-dl
# See https://github.com/rg3/youtube-dl/issues/9706
# The following decryption algorithm is written by @yokrysty and
# declared to be freely used in youtube-dl
# See https://github.com/rg3/youtube-dl/issues/10408
enc_data = self._html_search_regex(
r'<span[^>]+id="hiddenurl"[^>]*>([^<]+)</span>', webpage, 'encrypted data')
numbers_js = self._download_webpage(
'https://openload.co/assets/js/obfuscator/n.js', video_id,
note='Downloading signature numbers')
signums = self._search_regex(
r'window\.signatureNumbers\s*=\s*[\'"](?P<data>[a-z]+)[\'"]',
numbers_js, 'signature numbers', group='data')
video_url_chars = []
linkimg_uri = self._search_regex(
r'<img[^>]+id="linkimg"[^>]+src="([^"]+)"', webpage, 'link image')
linkimg = self._request_webpage(
linkimg_uri, video_id, note=False).read()
for idx, c in enumerate(enc_data):
j = compat_ord(c)
if j >= 33 and j <= 126:
j = ((j + 14) % 94) + 33
if idx == len(enc_data) - 1:
j += 1
video_url_chars += compat_chr(j)
width, height, pixels = decode_png(linkimg)
output = ''
for y in range(height):
for x in range(width):
r, g, b = pixels[y][3 * x:3 * x + 3]
if r == 0 and g == 0 and b == 0:
break
else:
output += compat_chr(r)
output += compat_chr(g)
output += compat_chr(b)
img_str_length = len(output) // 200
img_str = [[0 for x in range(img_str_length)] for y in range(10)]
sig_str_length = len(signums) // 260
sig_str = [[0 for x in range(sig_str_length)] for y in range(10)]
for i in range(10):
for j in range(img_str_length):
begin = i * img_str_length * 20 + j * 20
img_str[i][j] = output[begin:begin + 20]
for j in range(sig_str_length):
begin = i * sig_str_length * 26 + j * 26
sig_str[i][j] = signums[begin:begin + 26]
parts = []
# TODO: find better names for str_, chr_ and sum_
str_ = ''
for i in [2, 3, 5, 7]:
str_ = ''
sum_ = float(99)
for j in range(len(sig_str[i])):
for chr_idx in range(len(img_str[i][j])):
if sum_ > float(122):
sum_ = float(98)
chr_ = compat_chr(int(math.floor(sum_)))
if sig_str[i][j][chr_idx] == chr_ and j >= len(str_):
sum_ += float(2.5)
str_ += img_str[i][j][chr_idx]
parts.append(str_.replace(',', ''))
video_url = 'https://openload.co/stream/%s~%s~%s~%s' % (parts[3], parts[1], parts[2], parts[0])
video_url = 'https://openload.co/stream/%s?mime=true' % ''.join(video_url_chars)
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,

View File

@@ -8,7 +8,14 @@ from ..utils import (
)
class PeriscopeIE(InfoExtractor):
class PeriscopeBaseIE(InfoExtractor):
def _call_api(self, method, query, item_id):
return self._download_json(
'https://api.periscope.tv/api/v2/%s' % method,
item_id, query=query)
class PeriscopeIE(PeriscopeBaseIE):
IE_DESC = 'Periscope'
IE_NAME = 'periscope'
_VALID_URL = r'https?://(?:www\.)?periscope\.tv/[^/]+/(?P<id>[^/?#]+)'
@@ -34,14 +41,11 @@ class PeriscopeIE(InfoExtractor):
'only_matching': True,
}]
def _call_api(self, method, value):
return self._download_json(
'https://api.periscope.tv/api/v2/%s?broadcast_id=%s' % (method, value), value)
def _real_extract(self, url):
token = self._match_id(url)
broadcast_data = self._call_api('getBroadcastPublic', token)
broadcast_data = self._call_api(
'getBroadcastPublic', {'broadcast_id': token}, token)
broadcast = broadcast_data['broadcast']
status = broadcast['status']
@@ -61,7 +65,8 @@ class PeriscopeIE(InfoExtractor):
'url': broadcast[image],
} for image in ('image_url', 'image_url_small') if broadcast.get(image)]
stream = self._call_api('getAccessPublic', token)
stream = self._call_api(
'getAccessPublic', {'broadcast_id': token}, token)
formats = []
for format_id in ('replay', 'rtmp', 'hls', 'https_hls'):
@@ -88,7 +93,7 @@ class PeriscopeIE(InfoExtractor):
}
class PeriscopeUserIE(InfoExtractor):
class PeriscopeUserIE(PeriscopeBaseIE):
_VALID_URL = r'https?://www\.periscope\.tv/(?P<id>[^/]+)/?$'
IE_DESC = 'Periscope user videos'
IE_NAME = 'periscope:user'
@@ -106,26 +111,34 @@ class PeriscopeUserIE(InfoExtractor):
}
def _real_extract(self, url):
user_id = self._match_id(url)
user_name = self._match_id(url)
webpage = self._download_webpage(url, user_id)
webpage = self._download_webpage(url, user_name)
data_store = self._parse_json(
unescapeHTML(self._search_regex(
r'data-store=(["\'])(?P<data>.+?)\1',
webpage, 'data store', default='{}', group='data')),
user_id)
user_name)
user = data_store.get('User', {}).get('user', {})
title = user.get('display_name') or user.get('username')
user = list(data_store['UserCache']['users'].values())[0]['user']
user_id = user['id']
session_id = data_store['SessionToken']['broadcastHistory']['token']['session_id']
broadcasts = self._call_api(
'getUserBroadcastsPublic',
{'user_id': user_id, 'session_id': session_id},
user_name)['broadcasts']
broadcast_ids = [
broadcast['id'] for broadcast in broadcasts if broadcast.get('id')]
title = user.get('display_name') or user.get('username') or user_name
description = user.get('description')
broadcast_ids = (data_store.get('UserBroadcastHistory', {}).get('broadcastIds') or
data_store.get('BroadcastCache', {}).get('broadcastIds', []))
entries = [
self.url_result(
'https://www.periscope.tv/%s/%s' % (user_id, broadcast_id))
'https://www.periscope.tv/%s/%s' % (user_name, broadcast_id))
for broadcast_id in broadcast_ids]
return self.playlist_result(entries, user_id, title, description)

View File

@@ -1,60 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import os.path
from .common import InfoExtractor
from ..utils import (
ExtractorError,
sanitized_Request,
urlencode_postdata,
)
class PlayedIE(InfoExtractor):
IE_NAME = 'played.to'
_VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
_TEST = {
'url': 'http://played.to/j2f2sfiiukgt',
'md5': 'c2bd75a368e82980e7257bf500c00637',
'info_dict': {
'id': 'j2f2sfiiukgt',
'ext': 'flv',
'title': 'youtube-dl_test_video.mp4',
},
'skip': 'Removed for copyright infringement.', # oh wow
}
def _real_extract(self, url):
video_id = self._match_id(url)
orig_webpage = self._download_webpage(url, video_id)
m_error = re.search(
r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
if m_error:
raise ExtractorError(m_error.group('msg'), expected=True)
data = self._hidden_inputs(orig_webpage)
self._sleep(2, video_id)
post = urlencode_postdata(data)
headers = {
b'Content-Type': b'application/x-www-form-urlencoded',
}
req = sanitized_Request(url, post, headers)
webpage = self._download_webpage(
req, video_id, note='Downloading video page ...')
title = os.path.splitext(data['fname'])[0]
video_url = self._search_regex(
r'file: "?(.+?)",', webpage, 'video URL')
return {
'id': video_id,
'title': title,
'url': video_url,
}

View File

@@ -1,9 +1,10 @@
from __future__ import unicode_literals
import re
import json
import random
import collections
import json
import os
import random
import re
from .common import InfoExtractor
from ..compat import (
@@ -12,10 +13,11 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
parse_duration,
qualities,
sanitized_Request,
srt_subtitles_timecode,
urlencode_postdata,
)
@@ -75,12 +77,10 @@ class PluralsightIE(PluralsightBaseIE):
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
request = sanitized_Request(
post_url, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
post_url, None, 'Logging in as %s' % username,
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
error = self._search_regex(
r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>',
@@ -91,6 +91,53 @@ class PluralsightIE(PluralsightBaseIE):
if all(p not in response for p in ('__INITIAL_STATE__', '"currentUser"')):
raise ExtractorError('Unable to log in')
def _get_subtitles(self, author, clip_id, lang, name, duration, video_id):
captions_post = {
'a': author,
'cn': clip_id,
'lc': lang,
'm': name,
}
captions = self._download_json(
'%s/training/Player/Captions' % self._API_BASE, video_id,
'Downloading captions JSON', 'Unable to download captions JSON',
fatal=False, data=json.dumps(captions_post).encode('utf-8'),
headers={'Content-Type': 'application/json;charset=utf-8'})
if captions:
return {
lang: [{
'ext': 'json',
'data': json.dumps(captions),
}, {
'ext': 'srt',
'data': self._convert_subtitles(duration, captions),
}]
}
@staticmethod
def _convert_subtitles(duration, subs):
srt = ''
for num, current in enumerate(subs):
current = subs[num]
start, text = float_or_none(
current.get('DisplayTimeOffset')), current.get('Text')
if start is None or text is None:
continue
end = duration if num == len(subs) - 1 else float_or_none(
subs[num + 1].get('DisplayTimeOffset'))
if end is None:
continue
srt += os.linesep.join(
(
'%d' % num,
'%s --> %s' % (
srt_subtitles_timecode(start),
srt_subtitles_timecode(end)),
text,
os.linesep,
))
return srt
def _real_extract(self, url):
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
@@ -138,6 +185,8 @@ class PluralsightIE(PluralsightBaseIE):
if not clip:
raise ExtractorError('Unable to resolve clip')
title = '%s - %s' % (module['title'], clip['title'])
QUALITIES = {
'low': {'width': 640, 'height': 480},
'medium': {'width': 848, 'height': 640},
@@ -196,13 +245,12 @@ class PluralsightIE(PluralsightBaseIE):
'mt': ext,
'q': '%dx%d' % (f['width'], f['height']),
}
request = sanitized_Request(
'%s/training/Player/ViewClip' % self._API_BASE,
json.dumps(clip_post).encode('utf-8'))
request.add_header('Content-Type', 'application/json;charset=utf-8')
format_id = '%s-%s' % (ext, quality)
clip_url = self._download_webpage(
request, display_id, 'Downloading %s URL' % format_id, fatal=False)
'%s/training/Player/ViewClip' % self._API_BASE, display_id,
'Downloading %s URL' % format_id, fatal=False,
data=json.dumps(clip_post).encode('utf-8'),
headers={'Content-Type': 'application/json;charset=utf-8'})
# Pluralsight tracks multiple sequential calls to ViewClip API and start
# to return 429 HTTP errors after some time (see
@@ -225,18 +273,20 @@ class PluralsightIE(PluralsightBaseIE):
formats.append(f)
self._sort_formats(formats)
# TODO: captions
# http://www.pluralsight.com/training/Player/ViewClip + cap = true
# or
# http://www.pluralsight.com/training/Player/Captions
# { a = author, cn = clip_id, lc = end, m = name }
duration = int_or_none(
clip.get('duration')) or parse_duration(clip.get('formattedDuration'))
# TODO: other languages?
subtitles = self.extract_subtitles(
author, clip_id, 'en', name, duration, display_id)
return {
'id': clip.get('clipName') or clip['name'],
'title': '%s - %s' % (module['title'], clip['title']),
'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')),
'title': title,
'duration': duration,
'creator': author,
'formats': formats
'formats': formats,
'subtitles': subtitles,
}

View File

@@ -0,0 +1,100 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
int_or_none,
js_to_json,
parse_filesize,
str_to_int,
)
class PornComIE(InfoExtractor):
_VALID_URL = r'https?://(?:[a-zA-Z]+\.)?porn\.com/videos/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.porn.com/videos/teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec-2603339',
'md5': '3f30ce76267533cd12ba999263156de7',
'info_dict': {
'id': '2603339',
'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec',
'ext': 'mp4',
'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 551,
'view_count': int,
'age_limit': 18,
'categories': list,
'tags': list,
},
}, {
'url': 'http://se.porn.com/videos/marsha-may-rides-seth-on-top-of-his-thick-cock-2658067',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
config = self._parse_json(
self._search_regex(
r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*=',
webpage, 'config', default='{}'),
display_id, transform_source=js_to_json, fatal=False)
if config:
title = config['title']
formats = [{
'url': stream['url'],
'format_id': stream.get('id'),
'height': int_or_none(self._search_regex(
r'^(\d+)[pP]', stream.get('id') or '', 'height', default=None))
} for stream in config['streams'] if stream.get('url')]
thumbnail = (compat_urlparse.urljoin(
config['thumbCDN'], config['poster'])
if config.get('thumbCDN') and config.get('poster') else None)
duration = int_or_none(config.get('length'))
else:
title = self._search_regex(
(r'<title>([^<]+)</title>', r'<h1[^>]*>([^<]+)</h1>'),
webpage, 'title')
formats = [{
'url': compat_urlparse.urljoin(url, format_url),
'format_id': '%sp' % height,
'height': int(height),
'filesize_approx': parse_filesize(filesize),
} for format_url, height, filesize in re.findall(
r'<a[^>]+href="(/download/[^"]+)">MPEG4 (\d+)p<span[^>]*>(\d+\s+[a-zA-Z]+)<',
webpage)]
thumbnail = None
duration = None
self._sort_formats(formats)
view_count = str_to_int(self._search_regex(
r'class=["\']views["\'][^>]*><p>([\d,.]+)', webpage,
'view count', fatal=False))
def extract_list(kind):
s = self._search_regex(
r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize(),
webpage, kind, fatal=False)
return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'view_count': view_count,
'formats': formats,
'age_limit': 18,
'categories': extract_list('categories'),
'tags': extract_list('tags'),
}

View File

@@ -2,7 +2,6 @@
from __future__ import unicode_literals
import re
import random
from .common import InfoExtractor
from ..utils import (
@@ -13,61 +12,69 @@ from ..utils import (
class PornoVoisinesIE(InfoExtractor):
_VALID_URL = r'https?://(?: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)
_VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
_TEST = {
'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
'md5': '6f8aca6a058592ab49fe701c8ba8317b',
'info_dict': {
'id': '1285',
'id': '919',
'display_id': 'recherche-appartement',
'ext': 'mp4',
'title': 'Recherche appartement',
'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140925',
'duration': 120,
'view_count': int,
'average_rating': float,
'categories': ['Débutantes', 'Scénario', 'Sodomie'],
'categories': ['butante', 'butantes', 'Scénario', 'Sodomie'],
'age_limit': 18,
'subtitles': {
'fr': [{
'ext': 'vtt',
}]
},
}
}
@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')
settings_url = self._download_json(
'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
video_id, note='Getting settings URL')['video_settings_url']
settings = self._download_json(settings_url, video_id)['data']
formats = []
for kind, data in settings['variants'].items():
if kind == 'HLS':
formats.extend(self._extract_m3u8_formats(
data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
elif kind == 'MP4':
for item in data:
formats.append({
'url': item['url'],
'height': item.get('height'),
'bitrate': item.get('bitrate'),
})
self._sort_formats(formats)
webpage = self._download_webpage(url, video_id)
video_url = self.build_video_url(video_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
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
# The webpage has a bug - there's no space between "thumb" and src=
thumbnail = self._html_search_regex(
r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
webpage, 'thumbnail', fatal=False, group='url')
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))
r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
duration = settings.get('main', {}).get('duration')
view_count = int_or_none(self._search_regex(
r'(\d+) vues', webpage, 'view count', fatal=False))
average_rating = self._search_regex(
@@ -75,15 +82,19 @@ class PornoVoisinesIE(InfoExtractor):
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', fatal=False)
categories = self._html_search_regex(
r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
if categories:
categories = [category.strip() for category in categories.split(',')]
subtitles = {'fr': [{
'url': subtitle,
} for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'formats': formats,
'title': title,
'description': description,
'thumbnail': thumbnail,
@@ -93,4 +104,5 @@ class PornoVoisinesIE(InfoExtractor):
'average_rating': average_rating,
'categories': categories,
'age_limit': 18,
'subtitles': subtitles,
}

View File

@@ -1,59 +1,72 @@
from __future__ import unicode_literals
import re
import os
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import int_or_none
class PyvideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pyvideo\.org/video/(?P<id>\d+)/(.*)'
_VALID_URL = r'https?://(?:www\.)?pyvideo\.org/(?P<category>[^/]+)/(?P<id>[^/?#&.]+)'
_TESTS = [
{
'url': 'http://pyvideo.org/video/1737/become-a-logging-expert-in-30-minutes',
'md5': '520915673e53a5c5d487c36e0c4d85b5',
'info_dict': {
'id': '24_4WWkSmNo',
'ext': 'webm',
'title': 'Become a logging expert in 30 minutes',
'description': 'md5:9665350d466c67fb5b1598de379021f7',
'upload_date': '20130320',
'uploader': 'Next Day Video',
'uploader_id': 'NextDayVideo',
},
'add_ie': ['Youtube'],
_TESTS = [{
'url': 'http://pyvideo.org/pycon-us-2013/become-a-logging-expert-in-30-minutes.html',
'info_dict': {
'id': 'become-a-logging-expert-in-30-minutes',
},
{
'url': 'http://pyvideo.org/video/2542/gloriajw-spotifywitherikbernhardsson182m4v',
'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
'info_dict': {
'id': '2542',
'ext': 'm4v',
'title': 'Gloriajw-SpotifyWithErikBernhardsson182',
},
'playlist_count': 2,
}, {
'url': 'http://pyvideo.org/pygotham-2012/gloriajw-spotifywitherikbernhardsson182m4v.html',
'md5': '5fe1c7e0a8aa5570330784c847ff6d12',
'info_dict': {
'id': '2542',
'ext': 'm4v',
'title': 'Gloriajw-SpotifyWithErikBernhardsson182.m4v',
},
]
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
category = mobj.group('category')
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
entries = []
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', webpage)
if m_youtube is not None:
return self.url_result(m_youtube.group(1), 'Youtube')
data = self._download_json(
'https://raw.githubusercontent.com/pyvideo/data/master/%s/videos/%s.json'
% (category, video_id), video_id, fatal=False)
title = self._html_search_regex(
r'<div class="section">\s*<h3(?:\s+class="[^"]*"[^>]*)?>([^>]+?)</h3>',
webpage, 'title', flags=re.DOTALL)
video_url = self._search_regex(
[r'<source src="(.*?)"', r'<dt>Download</dt>.*?<a href="(.+?)"'],
webpage, 'video url', flags=re.DOTALL)
if data:
for video in data['videos']:
video_url = video.get('url')
if video_url:
if video.get('type') == 'youtube':
entries.append(self.url_result(video_url, 'Youtube'))
else:
entries.append({
'id': compat_str(data.get('id') or video_id),
'url': video_url,
'title': data['title'],
'description': data.get('description') or data.get('summary'),
'thumbnail': data.get('thumbnail_url'),
'duration': int_or_none(data.get('duration')),
})
else:
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
media_urls = self._search_regex(
r'(?s)Media URL:(.+?)</li>', webpage, 'media urls')
for m in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>http.+?)\1', media_urls):
media_url = m.group('url')
if re.match(r'https?://www\.youtube\.com/watch\?v=.*', media_url):
entries.append(self.url_result(media_url, 'Youtube'))
else:
entries.append({
'id': video_id,
'url': media_url,
'title': title,
})
return {
'id': video_id,
'title': os.path.splitext(title)[0],
'url': video_url,
}
return self.playlist_result(entries, video_id)

View File

@@ -13,15 +13,15 @@ class RadioBremenIE(InfoExtractor):
IE_NAME = 'radiobremen'
_TEST = {
'url': 'http://www.radiobremen.de/mediathek/index.html?id=114720',
'url': 'http://www.radiobremen.de/mediathek/?id=141876',
'info_dict': {
'id': '114720',
'id': '141876',
'ext': 'mp4',
'duration': 1685,
'duration': 178,
'width': 512,
'title': 'buten un binnen vom 22. Dezember',
'title': 'Druck auf Patrick Öztürk',
'thumbnail': 're:https?://.*\.jpg$',
'description': 'Unter anderem mit diesen Themen: 45 Flüchtlinge sind in Worpswede angekommen +++ Freies Internet für alle: Bremer arbeiten an einem flächendeckenden W-Lan-Netzwerk +++ Aktivisten kämpfen für das Unibad +++ So war das Wetter 2014 +++',
'description': 'Gegen den SPD-Bürgerschaftsabgeordneten Patrick Öztürk wird wegen Beihilfe zum gewerbsmäßigen Betrug ermittelt. Am Donnerstagabend sollte er dem Vorstand des SPD-Unterbezirks Bremerhaven dazu Rede und Antwort stehen.',
},
}

View File

@@ -1,7 +1,6 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from .internetvideoarchive import InternetVideoArchiveIE
@@ -11,21 +10,23 @@ class RottenTomatoesIE(InfoExtractor):
_TEST = {
'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
'info_dict': {
'id': '613340',
'id': '11028566',
'ext': 'mp4',
'title': 'Toy Story 3',
'description': 'From the creators of the beloved TOY STORY films, comes a story that will reunite the gang in a whole new way.',
'thumbnail': 're:^https?://.*\.jpg$',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
og_video = self._og_search_video_url(webpage)
query = compat_urlparse.urlparse(og_video).query
iva_id = self._search_regex(r'publishedid=(\d+)', webpage, 'internet video archive id')
return {
'_type': 'url_transparent',
'url': InternetVideoArchiveIE._build_xml_url(query),
'url': 'http://video.internetvideoarchive.net/player/6/configuration.ashx?domain=www.videodetective.com&customerid=69249&playerid=641&publishedid=' + iva_id,
'ie_key': InternetVideoArchiveIE.ie_key(),
'id': video_id,
'title': self._og_search_title(webpage),
}

View File

@@ -4,33 +4,43 @@ from __future__ import unicode_literals
import re
from .jwplatform import JWPlatformBaseIE
from ..compat import compat_parse_qs
from ..utils import (
ExtractorError,
parse_duration,
float_or_none,
parse_iso8601,
update_url_query,
)
class SendtoNewsIE(JWPlatformBaseIE):
_VALID_URL = r'https?://embed\.sendtonews\.com/player/embed\.php\?(?P<query>[^#]+)'
_VALID_URL = r'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
_TEST = {
# From http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/
'url': 'http://embed.sendtonews.com/player/embed.php?SK=GxfCe0Zo7D&MK=175909&PK=5588&autoplay=on&sound=yes',
'url': 'http://embed.sendtonews.com/player2/embedplayer.php?SC=GxfCe0Zo7D-175909-5588&type=single&autoplay=on&sound=YES',
'info_dict': {
'id': 'GxfCe0Zo7D-175909-5588',
'ext': 'mp4',
'title': 'Recap: CLE 15, CIN 6',
'description': '5/16/16: Indians\' bats explode for 15 runs in a win',
'duration': 49,
'id': 'GxfCe0Zo7D-175909-5588'
},
'playlist_count': 9,
# test the first video only to prevent lengthy tests
'playlist': [{
'info_dict': {
'id': '198180',
'ext': 'mp4',
'title': 'Recap: CLE 5, LAA 4',
'description': '8/14/16: Naquin, Almonte lead Indians in 5-4 win',
'duration': 57.343,
'thumbnail': 're:https?://.*\.jpg$',
'upload_date': '20160815',
'timestamp': 1471221961,
},
}],
'params': {
# m3u8 download
'skip_download': True,
},
}
_URL_TEMPLATE = '//embed.sendtonews.com/player/embed.php?SK=%s&MK=%s&PK=%s'
_URL_TEMPLATE = '//embed.sendtonews.com/player2/embedplayer.php?SC=%s'
@classmethod
def _extract_url(cls, webpage):
@@ -39,48 +49,41 @@ class SendtoNewsIE(JWPlatformBaseIE):
.*\bSC=(?P<SC>[0-9a-zA-Z-]+).*
\1>''', webpage)
if mobj:
sk, mk, pk = mobj.group('SC').split('-')
return cls._URL_TEMPLATE % (sk, mk, pk)
sc = mobj.group('SC')
return cls._URL_TEMPLATE % sc
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
params = compat_parse_qs(mobj.group('query'))
playlist_id = self._match_id(url)
if 'SK' not in params or 'MK' not in params or 'PK' not in params:
raise ExtractorError('Invalid URL', expected=True)
data_url = update_url_query(
url.replace('embedplayer.php', 'data_read.php'),
{'cmd': 'loadInitial'})
playlist_data = self._download_json(data_url, playlist_id)
video_id = '-'.join([params['SK'][0], params['MK'][0], params['PK'][0]])
entries = []
for video in playlist_data['playlistData'][0]:
info_dict = self._parse_jwplayer_data(
video['jwconfiguration'],
require_title=False, rtmp_params={'no_resume': True})
webpage = self._download_webpage(url, video_id)
thumbnails = []
if video.get('thumbnailUrl'):
thumbnails.append({
'id': 'normal',
'url': video['thumbnailUrl'],
})
if video.get('smThumbnailUrl'):
thumbnails.append({
'id': 'small',
'url': video['smThumbnailUrl'],
})
info_dict.update({
'title': video['S_headLine'],
'description': video.get('S_fullStory'),
'thumbnails': thumbnails,
'duration': float_or_none(video.get('SM_length')),
'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
})
entries.append(info_dict)
jwplayer_data_str = self._search_regex(
r'jwplayer\("[^"]+"\)\.setup\((.+?)\);', webpage, 'JWPlayer data')
js_vars = {
'w': 1024,
'h': 768,
'modeVar': 'html5',
}
for name, val in js_vars.items():
js_val = '%d' % val if isinstance(val, int) else '"%s"' % val
jwplayer_data_str = jwplayer_data_str.replace(':%s,' % name, ':%s,' % js_val)
info_dict = self._parse_jwplayer_data(
self._parse_json(jwplayer_data_str, video_id),
video_id, require_title=False, rtmp_params={'no_resume': True})
title = self._html_search_regex(
r'<div[^>]+class="embedTitle">([^<]+)</div>', webpage, 'title')
description = self._html_search_regex(
r'<div[^>]+class="embedSubTitle">([^<]+)</div>', webpage,
'description', fatal=False)
duration = parse_duration(self._html_search_regex(
r'<div[^>]+class="embedDetails">([0-9:]+)', webpage,
'duration', fatal=False))
info_dict.update({
'title': title,
'description': description,
'duration': duration,
})
return info_dict
return self.playlist_result(entries, playlist_id)

View File

@@ -5,9 +5,9 @@ import re
from .common import InfoExtractor
from ..utils import (
float_or_none,
str_to_int,
parse_duration,
parse_filesize,
str_to_int,
)
@@ -17,21 +17,24 @@ class SnotrIE(InfoExtractor):
'url': 'http://www.snotr.com/video/13708/Drone_flying_through_fireworks',
'info_dict': {
'id': '13708',
'ext': 'flv',
'ext': 'mp4',
'title': 'Drone flying through fireworks!',
'duration': 247,
'filesize_approx': 98566144,
'duration': 248,
'filesize_approx': 40700000,
'description': 'A drone flying through Fourth of July Fireworks',
}
'thumbnail': 're:^https?://.*\.jpg$',
},
'expected_warnings': ['description'],
}, {
'url': 'http://www.snotr.com/video/530/David_Letteman_-_George_W_Bush_Top_10',
'info_dict': {
'id': '530',
'ext': 'flv',
'ext': 'mp4',
'title': 'David Letteman - George W. Bush Top 10',
'duration': 126,
'filesize_approx': 8912896,
'filesize_approx': 8500000,
'description': 'The top 10 George W. Bush moments, brought to you by David Letterman!',
'thumbnail': 're:^https?://.*\.jpg$',
}
}]
@@ -43,26 +46,28 @@ class SnotrIE(InfoExtractor):
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
video_url = 'http://cdn.videos.snotr.com/%s.flv' % video_id
info_dict = self._parse_html5_media_entries(
url, webpage, video_id, m3u8_entry_protocol='m3u8_native')[0]
view_count = str_to_int(self._html_search_regex(
r'<p>\n<strong>Views:</strong>\n([\d,\.]+)</p>',
r'<p[^>]*>\s*<strong[^>]*>Views:</strong>\s*<span[^>]*>([\d,\.]+)',
webpage, 'view count', fatal=False))
duration = parse_duration(self._html_search_regex(
r'<p>\n<strong>Length:</strong>\n\s*([0-9:]+).*?</p>',
r'<p[^>]*>\s*<strong[^>]*>Length:</strong>\s*<span[^>]*>([\d:]+)',
webpage, 'duration', fatal=False))
filesize_approx = float_or_none(self._html_search_regex(
r'<p>\n<strong>Filesize:</strong>\n\s*([0-9.]+)\s*megabyte</p>',
webpage, 'filesize', fatal=False), invscale=1024 * 1024)
filesize_approx = parse_filesize(self._html_search_regex(
r'<p[^>]*>\s*<strong[^>]*>Filesize:</strong>\s*<span[^>]*>([^<]+)',
webpage, 'filesize', fatal=False))
return {
info_dict.update({
'id': video_id,
'description': description,
'title': title,
'url': video_url,
'view_count': view_count,
'duration': duration,
'filesize_approx': filesize_approx,
}
})
return info_dict

View File

@@ -32,7 +32,7 @@ class SoundcloudIE(InfoExtractor):
_VALID_URL = r'''(?x)^(?:https?://)?
(?:(?:(?:www\.|m\.)?soundcloud\.com/
(?P<uploader>[\w\d-]+)/
(?!(?:tracks|sets(?:/[^/?#]+)?|reposts|likes|spotlight)/?(?:$|[?#]))
(?!(?:tracks|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
(?P<title>[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
@@ -265,6 +265,9 @@ class SoundcloudSetIE(SoundcloudIE):
'title': 'The Royal Concept EP',
},
'playlist_mincount': 6,
}, {
'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep/token',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@@ -35,6 +35,7 @@ class SouthParkEsIE(SouthParkIE):
'description': 'Cartman Consigue Una Sonda Anal',
},
'playlist_count': 4,
'skip': 'Geo-restricted',
}]

View File

@@ -14,7 +14,7 @@ class SpankBangIE(InfoExtractor):
'id': '3vvn',
'ext': 'mp4',
'title': 'fantasy solo',
'description': 'dillion harper masturbates on a bed',
'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
'thumbnail': 're:^https?://.*\.jpg$',
'uploader': 'silly2587',
'age_limit': 18,
@@ -44,12 +44,10 @@ class SpankBangIE(InfoExtractor):
title = self._html_search_regex(
r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
description = self._search_regex(
r'class="desc"[^>]*>([^<]+)',
webpage, 'description', default=None)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
uploader = self._search_regex(
r'class="user"[^>]*>([^<]+)',
r'class="user"[^>]*><img[^>]+>([^<]+)',
webpage, 'uploader', fatal=False)
age_limit = self._rta_search(webpage)

View File

@@ -1,13 +1,13 @@
from __future__ import unicode_literals
from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..utils import (
update_url_query,
smuggle_url,
)
class SyfyIE(ThePlatformIE):
class SyfyIE(AdobePassIE):
_VALID_URL = r'https?://www\.syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',
@@ -31,7 +31,7 @@ class SyfyIE(ThePlatformIE):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
syfy_mpx = list(self._parse_json(self._search_regex(
r'jQuery\.extend\([^,]+,\s*({.+})\);', webpage, 'drupal settings'),
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
display_id)['syfy']['syfy_mpx'].values())[0]
video_id = syfy_mpx['mpxGUID']
title = syfy_mpx['episodeTitle']
@@ -40,7 +40,9 @@ class SyfyIE(ThePlatformIE):
'manifest': 'm3u',
}
if syfy_mpx.get('entitlement') == 'auth':
resource = '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>syfy</title><item><title><![CDATA[%s]]></title><guid>%s</guid><media:rating scheme="urn:v-chip">%s</media:rating></item></channel></rss>' % (title, video_id, syfy_mpx.get('mpxRating', 'TV-14'))
resource = self._get_mvpd_resource(
'syfy', title, video_id,
syfy_mpx.get('mpxRating', 'TV-14'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'syfy', resource)

View File

@@ -0,0 +1,59 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .turner import TurnerBaseIE
from ..utils import (
extract_attributes,
ExtractorError,
)
class TBSIE(TurnerBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>tbs|tntdrama)\.com/videos/(?:[^/]+/)+(?P<id>[^/?#]+)\.html'
_TESTS = [{
'url': 'http://www.tbs.com/videos/people-of-earth/season-1/extras/2007318/theatrical-trailer.html',
'md5': '9e61d680e2285066ade7199e6408b2ee',
'info_dict': {
'id': '2007318',
'ext': 'mp4',
'title': 'Theatrical Trailer',
'description': 'Catch the latest comedy from TBS, People of Earth, premiering Halloween night--Monday, October 31, at 9/8c.',
}
}, {
'url': 'http://www.tntdrama.com/videos/good-behavior/season-1/extras/1538823/you-better-run.html',
'md5': 'ce53c6ead5e9f3280b4ad2031a6fab56',
'info_dict': {
'id': '1538823',
'ext': 'mp4',
'title': 'You Better Run',
'description': 'Letty Raines must figure out what she\'s running toward while running away from her past. Good Behavior premieres November 15 at 9/8c.',
}
}]
def _real_extract(self, url):
domain, display_id = re.match(self._VALID_URL, url).groups()
site = domain[:3]
webpage = self._download_webpage(url, display_id)
video_params = extract_attributes(self._search_regex(r'(<[^>]+id="page-video"[^>]*>)', webpage, 'video params'))
if video_params.get('isAuthRequired') == 'true':
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported.', expected=True)
query = None
clip_id = video_params.get('clipid')
if clip_id:
query = 'id=' + clip_id
else:
query = 'titleId=' + video_params['titleid']
return self._extract_cvp_info(
'http://www.%s.com/service/cvpXml?%s' % (domain, query), display_id, {
'default': {
'media_src': 'http://ht.cdn.turner.com/%s/big' % site,
},
'secure': {
'media_src': 'http://apple-secure.cdn.turner.com/%s/big' % site,
'tokenizer_src': 'http://www.%s.com/video/processors/services/token_ipadAdobe.do' % domain,
},
})

View File

@@ -6,10 +6,10 @@ import time
import hmac
import binascii
import hashlib
import netrc
from .once import OnceIE
from .adobepass import AdobePassIE
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
@@ -25,9 +25,6 @@ from ..utils import (
xpath_with_ns,
mimetype2ext,
find_xpath_attr,
unescapeHTML,
urlencode_postdata,
unified_timestamp,
)
default_ns = 'http://www.w3.org/2005/SMIL21/Language'
@@ -76,10 +73,10 @@ class ThePlatformBaseIE(OnceIE):
if isinstance(captions, list):
for caption in captions:
lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
subtitles[lang] = [{
subtitles.setdefault(lang, []).append({
'ext': mimetype2ext(mime),
'url': src,
}]
})
return {
'title': info['title'],
@@ -96,10 +93,10 @@ class ThePlatformBaseIE(OnceIE):
return self._parse_theplatform_metadata(info)
class ThePlatformIE(ThePlatformBaseIE):
class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
(?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
(?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)?|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?
|theplatform:)(?P<id>[^/\?&]+)'''
_TESTS = [{
@@ -119,6 +116,7 @@ class ThePlatformIE(ThePlatformBaseIE):
# rtmp download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
# from http://www.cnet.com/videos/tesla-model-s-a-second-step-towards-a-cleaner-motoring-future/
'url': 'http://link.theplatform.com/s/kYEXFC/22d_qsQ6MIRT',
@@ -167,7 +165,6 @@ class ThePlatformIE(ThePlatformBaseIE):
'url': 'http://player.theplatform.com/p/NnzsPC/onsite_universal/select/media/guid/2410887629/2928790?fwsitesection=nbc_the_blacklist_video_library&autoPlay=true&carouselID=137781',
'only_matching': True,
}]
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
@classmethod
def _extract_urls(cls, webpage):
@@ -202,96 +199,6 @@ class ThePlatformIE(ThePlatformBaseIE):
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
return '%s&sig=%s' % (url, sig)
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
def xml_text(xml_str, tag):
return self._search_regex(
'<%s>(.+?)</%s>' % (tag, tag), xml_str, tag)
mvpd_headers = {
'ap_42': 'anonymous',
'ap_11': 'Linux i686',
'ap_z': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0',
}
guid = xml_text(resource, 'guid')
requestor_info = self._downloader.cache.load('mvpd', requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token:
token_expires = unified_timestamp(xml_text(authn_token, 'simpleTokenExpires').replace('_GMT', ''))
if token_expires and token_expires >= time.time():
authn_token = None
if not authn_token:
# TODO add support for other TV Providers
mso_id = 'DTV'
login_info = netrc.netrc().authenticators(mso_id)
if not login_info:
return None
def post_form(form_page, note, data={}):
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
return self._download_webpage(
post_url, video_id, note, data=urlencode_postdata(data or self._hidden_inputs(form_page)), headers={
'Content-Type': 'application/x-www-form-urlencoded',
})
provider_redirect_page = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
'Downloading Provider Redirect Page', query={
'noflash': 'true',
'mso_id': mso_id,
'requestor_id': requestor_id,
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
})
provider_login_page = post_form(
provider_redirect_page, 'Downloading Provider Login Page')
mvpd_confirm_page = post_form(provider_login_page, 'Logging in', {
'username': login_info[0],
'password': login_info[2],
})
post_form(mvpd_confirm_page, 'Confirming Login')
session = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'session', video_id,
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
}), headers=mvpd_headers)
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
requestor_info['authn_token'] = authn_token
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
authz_token = requestor_info.get(guid)
if not authz_token:
authorize = self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'authorize', video_id,
'Retrieving Authorization Token', data=urlencode_postdata({
'resource_id': resource,
'requestor_id': requestor_id,
'authentication_token': authn_token,
'mso_id': xml_text(authn_token, 'simpleTokenMsoID'),
'userMeta': '1',
}), headers=mvpd_headers)
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
requestor_info[guid] = authz_token
self._downloader.cache.store('mvpd', requestor_id, requestor_info)
mvpd_headers.update({
'ap_19': xml_text(authn_token, 'simpleSamlNameID'),
'ap_23': xml_text(authn_token, 'simpleSamlSessionIndex'),
})
return self._download_webpage(
self._SERVICE_PROVIDER_TEMPLATE % 'shortAuthorize',
video_id, 'Retrieving Media Token', data=urlencode_postdata({
'authz_token': authz_token,
'requestor_id': requestor_id,
'session_guid': xml_text(authn_token, 'simpleTokenAuthenticationGuid'),
'hashed_guid': 'false',
}), headers=mvpd_headers)
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})

View File

@@ -2,8 +2,6 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from .brightcove import BrightcoveLegacyIE
from ..compat import compat_parse_qs
class TheStarIE(InfoExtractor):
@@ -30,6 +28,9 @@ class TheStarIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
brightcove_id = compat_parse_qs(brightcove_legacy_url)['@videoPlayer'][0]
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
brightcove_id = self._search_regex(
r'mainartBrightcoveVideoId["\']?\s*:\s*["\']?(\d+)',
webpage, 'brightcove id')
return self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
'BrightcoveNew', brightcove_id)

View File

@@ -1,84 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate
)
class THVideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)'
_TEST = {
'url': 'http://thvideo.tv/v/th1987/',
'md5': 'fa107b1f73817e325e9433505a70db50',
'info_dict': {
'id': '1987',
'ext': 'mp4',
'title': '【动画】秘封活动记录 The Sealed Esoteric History.分镜稿预览',
'display_id': 'th1987',
'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg',
'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...',
'upload_date': '20140722'
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
# extract download link from mobile player page
webpage_player = self._download_webpage(
'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id),
video_id, note='Downloading video source page')
video_url = self._html_search_regex(
r'<source src="(.*?)" type', webpage_player, 'video url')
# extract video info from main page
webpage = self._download_webpage(
'http://thvideo.tv/v/th%s' % (video_id), video_id)
title = self._og_search_title(webpage)
display_id = 'th%s' % video_id
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
upload_date = unified_strdate(self._html_search_regex(
r'span itemprop="datePublished" content="(.*?)">', webpage,
'upload date', fatal=False))
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
'display_id': display_id,
'thumbnail': thumbnail,
'description': description,
'upload_date': upload_date
}
class THVideoPlaylistIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)'
_TEST = {
'url': 'http://thvideo.tv/mylist2',
'info_dict': {
'id': '2',
'title': '幻想万華鏡',
},
'playlist_mincount': 23,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
list_title = self._html_search_regex(
r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title',
fatal=False)
entries = [
self.url_result('http://thvideo.tv/v/th' + id, 'THVideo')
for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)]
return self.playlist_result(entries, playlist_id, list_title)

View File

@@ -10,6 +10,7 @@ from ..utils import (
int_or_none,
parse_duration,
str_to_int,
unescapeHTML,
xpath_text,
)
@@ -80,7 +81,8 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
if not cfg_url:
inputs = self._hidden_inputs(webpage)
cfg_url = 'https://cdn-fck.tnaflix.com/tnaflix/%s.fid?key=%s' % (inputs['vkey'], inputs['nkey'])
cfg_url = ('https://cdn-fck.tnaflix.com/tnaflix/%s.fid?key=%s&VID=%s&premium=1&vip=1&alpha'
% (inputs['vkey'], inputs['nkey'], video_id))
cfg_xml = self._download_xml(
cfg_url, display_id, 'Downloading metadata',
@@ -89,7 +91,7 @@ class TNAFlixNetworkBaseIE(InfoExtractor):
formats = []
def extract_video_url(vl):
return re.sub('speed=\d+', 'speed=', vl.text)
return re.sub('speed=\d+', 'speed=', unescapeHTML(vl.text))
video_link = cfg_xml.find('./videoLink')
if video_link is not None:
@@ -201,7 +203,7 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
_TESTS = [{
# anonymous uploader, no categories
'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878',
'md5': '7e569419fe6d69543d01e6be22f5f7c4',
'md5': 'ecf3498417d09216374fc5907f9c6ec0',
'info_dict': {
'id': '553878',
'display_id': 'Carmella-Decesare-striptease',
@@ -215,11 +217,11 @@ class TNAFlixIE(TNAFlixNetworkBaseIE):
}, {
# non-anonymous uploader, categories
'url': 'https://www.tnaflix.com/teen-porn/Educational-xxx-video/video6538',
'md5': 'fcba2636572895aba116171a899a5658',
'md5': '0f5d4d490dbfd117b8607054248a07c0',
'info_dict': {
'id': '6538',
'display_id': 'Educational-xxx-video',
'ext': 'flv',
'ext': 'mp4',
'title': 'Educational xxx video',
'description': 'md5:b4fab8f88a8621c8fabd361a173fe5b8',
'thumbnail': 're:https?://.*\.jpg$',

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