Compare commits

...

217 Commits

Author SHA1 Message Date
b56e41a701 release 2017.04.02 2017-04-02 02:39:15 +07:00
a76c25146a [ChangeLog] Actualize 2017-04-02 02:37:18 +07:00
361f293ab8 [rai] Skip not found content item id 2017-04-02 02:24:13 +07:00
b8d8cced9b [rai] Improve extraction (closes #11790)
* Fix georestriction detection
* Detect live streams
+ Extract relinker metadata
* Improve ContentItem detection
+ Extract series metadata
* Fix tests
2017-04-02 02:14:42 +07:00
51342717cd [rai] Fix extraction 2017-04-02 02:10:53 +07:00
48ab554feb [vrv] add support for series pages 2017-04-01 18:09:36 +01:00
a6f3a162f3 [limelight] improve extraction for audio only formats 2017-04-01 15:35:39 +01:00
91399b2fcc [funimation] fix extraction(closes #10696)(#11773) 2017-04-01 13:33:04 +01:00
eecea00d36 [xfileshare] Add support for vidabc.com (closes #12589) 2017-04-01 18:56:35 +07:00
2cd668ee59 [xfileshare] Improve extraction and extract hls formats 2017-04-01 18:55:48 +07:00
ca77b92f94 [crunchyroll] pass geo verifcation proxy 2017-04-01 09:33:23 +01:00
e97fc8d6b8 [cwtv] extract ISM formats 2017-04-01 07:50:24 +01:00
be61efdf17 [tvplay] Bypass geo restriction 2017-04-01 07:26:40 +01:00
77c8ebe631 [vrv] Add new extractor 2017-03-31 23:29:23 +01:00
7453999580 [packtpub] Add extractor (closes #12610) 2017-04-01 00:25:27 +07:00
1640eb0961 [YoutubeDL] Return early when extraction of url_transparent fails 2017-03-31 23:57:35 +07:00
3e943cfe09 [generic] pass base_url to _parse_jwplayer_data 2017-03-31 14:54:06 +01:00
82be732b17 [adn] Add new extractor 2017-03-31 12:24:23 +01:00
639e5b2a84 [allocine] Extract more metadata 2017-03-29 04:43:12 +07:00
128244657b [allocine] Fix extraction 2017-03-29 05:23:20 +08:00
12ee65ea0d [options] Mention ISM for --fragment-retries and --skip-unavailable-fragments 2017-03-28 23:35:48 +07:00
aea1dccbd0 [openload] fix extractor 2017-03-29 00:00:09 +08:00
9e691da067 release 2017.03.26 2017-03-26 08:11:40 +07:00
82eefd0be0 [ChangeLog] Actualize 2017-03-26 23:39:12 +07:00
f7923a4c39 [ChangeLog] Update after #12307 2017-03-26 22:07:12 +08:00
cc63259d18 Merge pull request #12307 from rndusr/fix/str-item-assignment
Fix "'str' object does not support item assignment"
2017-03-26 21:51:09 +08:00
2bfaf89b6c [downloader/hls] move check for m3u8 live streams to get_suitable_downloader 2017-03-25 23:07:05 +01:00
4f06c1c9fc Merge branch 'master' of github.com-rndusr:rg3/youtube-dl into fix/str-item-assignment 2017-03-25 21:36:59 +01:00
942b44a052 [test_compat] Do not use dash in env variables' names 2017-03-26 03:24:25 +07:00
a426ef6d78 [test_utils] Do not use dash in env variables' names 2017-03-26 03:22:48 +07:00
41c5e60dd5 [test_utils] Fix expand_path tests 2017-03-26 03:07:56 +07:00
d212c93d16 [pluralsight] PEP 8 2017-03-26 02:34:25 +07:00
15495cf3e5 [franceculture] PEP 8 2017-03-26 02:32:46 +07:00
5b7cc56b05 [atresplayer] PEP 8 2017-03-26 02:32:14 +07:00
590bc6f6a1 Use expand_path where appropriate (closes #12556) 2017-03-26 02:31:16 +07:00
51098426b8 [utils] Introduce expand_path 2017-03-26 02:30:10 +07:00
c73e330e7a _find_jwplayer_data() returns dict or None
This simplifies code for callers of `_find_jwplayer_data()` which no longer have
to run `_parse_json()` on the return value.

It also makes sure that `_find_jwplayer_data()` returns either a `dict` or
`None` and nothing else.
2017-03-25 19:38:30 +01:00
fb4fc44928 [downloader/hls] immediately delegate downloading to ffmpeg in case live stream 2017-03-25 19:38:23 +01:00
03486dbb01 Add test for JWPlayer where config is passed as variable 2017-03-25 19:37:45 +01:00
51ef4919df [afreecatv] Fix extraction (closes #12179) 2017-03-26 01:32:07 +08:00
d66d43c554 [atvat] Add new extractor(closes #5325) 2017-03-25 18:13:58 +01:00
610a6d1053 [atresplayer] Do not extract ISM formats
As per @remitamine: the ISM downloader does not support videos served from wowza servers(it will produce broken files)
2017-03-25 21:40:54 +07:00
c6c22e984d [test_download] Print additional IEs in summary output 2017-03-25 22:36:40 +08:00
d97729c83a [fox] remove unused import 2017-03-25 14:28:53 +01:00
7aa0ee321b [fox] Add metadata extraction
Add series, season number, episode number and episode.
2017-03-25 21:12:25 +08:00
e8e4cc5a6a [generic] Replace LazyYT test with skiplagged
discourse.ubuntu.com has gone away, repalce with skiplagged.com.
Be nice to have a non-frontpage URL that might be more stable,
though I don't have one. Maybe this should move to html
in test/test_InfoExtractor.py?
2017-03-25 19:53:32 +07:00
c7301e677b [atresplayer] Extract DASH and ISM formats 2017-03-25 18:03:46 +07:00
048086920b [atresplayer] Extract HD manifest 2017-03-25 17:52:04 +07:00
1088d76da6 [atresplayer] Fix login error detection 2017-03-25 17:47:35 +07:00
31a1214076 [franceculture] fix extraction(closes #12547) 2017-03-25 07:04:48 +01:00
d0ba55871e [youtube] Improve _VALID_URLs (closes #12538) 2017-03-25 01:18:33 +07:00
54b960f340 [generic] Do not follow redirects to the same URL 2017-03-24 00:45:24 +07:00
a3ccd6bd11 release 2017.03.24 2017-03-24 00:24:23 +07:00
7963b6cba8 [ChangeLog] Actualize 2017-03-24 00:19:58 +07:00
bea7af6947 [channel9] Remove expired comment and sort imports 2017-03-23 23:58:12 +07:00
a5d783f525 [channel9] Extract more formats 2017-03-23 23:47:43 +07:00
d0572557c2 [ninecninemedia] remove mp4 url extraction request 2017-03-23 13:53:07 +01:00
52d5ecabd5 [bellmedia] add support for etalk.ca(closes #12447) 2017-03-23 13:52:45 +01:00
b0f7f21cb9 [channel9] fix extraction(closes #11323) 2017-03-23 09:22:37 +01:00
579c99a284 [cloudy] Fix extraction (closes #12525) 2017-03-22 23:48:06 +07:00
ca5ed022e9 [hbo] add support for free episode urls and new formats extraction(closes #12519) 2017-03-22 17:28:53 +01:00
391d076d7c [condenast] Fix extraction and style (closes #12526) 2017-03-22 23:22:14 +07:00
c183e14f89 [viu] Relax _VALID_URL (closes #12529) 2017-03-22 22:26:59 +07:00
093dad9e25 release 2017.03.22 2017-03-22 02:36:50 +07:00
e8686e51d7 [ChangeLog] Actualize 2017-03-22 02:35:09 +07:00
8e5a7c5e67 [pluralsight] Omit module title from video title (closes #12506) 2017-03-22 02:28:04 +07:00
e1e35d1ac6 [pornhub] Improve extraction and style (closes #12515) 2017-03-22 01:59:27 +07:00
21fbf0f955 [pornhub] Decode obfuscated video URL (closes #12470) 2017-03-22 01:51:45 +07:00
97952bdb78 [generic] Add test for Senate ISVP iframe embed 2017-03-22 01:12:14 +08:00
8a8cc339b6 [senateisvp] Allow https URL scheme for embeds 2017-03-20 23:35:13 +08:00
957f453429 [Openload.co] Fixed Extraction
They did it again. just a minor change though. here's quick fix
2017-03-20 16:15:00 +08:00
0e9a73e612 release 2017.03.20 2017-03-20 00:07:57 +07:00
0ecdd3adbd [ChangeLog] Actualize 2017-03-20 00:03:58 +07:00
9487ce03e9 [YoutubeDL] Allow multiple input URLs to be used with stdout as output template 2017-03-19 23:59:40 +07:00
45e6ad21b4 Credit @mrBliss for vtm (#11912) 2017-03-19 23:48:02 +07:00
68220649fa [ChangeLog] Update after #12099 2017-03-19 20:42:17 +08:00
46b18f2349 [BostonGlobe] New. Nonstandard version of Brightcove.
Has a "data-brightcove-video-id" instead of a "data-video-id," otherwise
pretty much just Brightcove. Except the Globe isn't all Brightcove
videos, so fallback to Generic, too.

Also, abstract playlist_from_matches() from generic.py to common.py, and use
it here.

History of these changes can be found in
51170427d4b1143572a498dedaee61863a5b2c5b.
2017-03-19 20:40:31 +08:00
772b5ff57f [toongoggles] Add new extractor(closes #12171) 2017-03-19 00:45:38 +01:00
f68ef1e2ab [medialaan] Remove unrelated test 2017-03-18 23:23:47 +07:00
febfe1e262 [adobepass] Detect and output error on authz token extraction (#12472) 2017-03-18 06:21:31 +07:00
5f0daab1ca [openload] Fix extraction 2017-03-18 07:02:55 +08:00
2a721cdff2 [medialaan] Fix and improve extraction (closes #11912) 2017-03-18 05:58:54 +07:00
e7a51a4c02 [vtm] Add extractor (closes #9974)
Implementation of the approach described in #9974.
2017-03-18 00:27:04 +07:00
3e5856d860 [discoverynetworks] add support for more domains and bypass geo restiction 2017-03-17 09:53:44 +01:00
ea883a687c [openload] Fix extraction (closes #10408)
Thanks to @makgun02

Ref: http://pastebin.com/raw/JX9gHFUz
2017-03-17 15:22:34 +08:00
7f3590c43b [test_InfoExtractor] Add some realworld tests for _extract_jwplayer_data 2017-03-17 00:00:01 +07:00
7d539ee10a release 2017.03.16 2017-03-16 22:42:12 +07:00
6ad476079d [ChangeLog] Actualize 2017-03-16 22:39:48 +07:00
0efbc6b56d [options] Mention flac support and sort alphabetically among the audio formats 2017-03-16 12:54:47 +01:00
21bfcd3d6e [postprocessor/ffmpeg] Add support for flac
Requested at http://stackoverflow.com/q/42828041/35070
2017-03-16 12:50:45 +01:00
b51dc9db0e [extractor/common] Extract SMIL formats from jwplayer 2017-03-16 03:30:53 +07:00
a309684285 [extractor/generic] Add forgotten return for jwplayer formats 2017-03-16 03:28:01 +07:00
ba448445b8 [redbull] improve extraction
- extract 1080p quality
- correct ttml subtitle ext
- catch api errors
- reduce request size
2017-03-15 01:40:54 +01:00
5db83d79bf release 2017.03.15 2017-03-15 02:01:24 +07:00
2a751e137f [ChangeLog] Actualize 2017-03-15 02:00:10 +07:00
398887b4c0 [Openload] Fixed Extraction
They did changed it again.
2017-03-14 14:03:52 +08:00
66bf351f80 [facebook] Make title optional (closes #12443) 2017-03-14 00:38:07 +07:00
9d08963022 [telecinco] Add test for #12430 2017-03-13 22:41:28 +07:00
e313d209c2 [mitele] Add support for ooyala videos (closes #12430) 2017-03-13 22:39:15 +07:00
ff9d509d20 [openload] Fix extraction
Just a minor fix for openload
2017-03-13 04:22:35 +08:00
c1795ca6c8 [streamable] Update API URL 2017-03-13 02:51:59 +08:00
8c99623259 [crunchyroll] Extract season name 2017-03-12 12:18:10 +08:00
57b0ddb35f [discoverygo] Actualize test 2017-03-11 23:21:08 +07:00
a28f8d7396 [discoverygo] Bypass geo restriction 2017-03-11 23:18:42 +07:00
7049799470 [discoverygo:playlist] Add extractor (closes #12424) 2017-03-11 23:16:51 +07:00
4605c94d1a [__init__] Fix missing subtitles if --add-metadata is used (#12423)
The previous fix for #5594 is incorrect
2017-03-11 19:37:45 +08:00
a8e687a4da release 2017.03.10 2017-03-10 23:26:28 +07:00
f9e5c92c94 [ChangeLog] Actualize 2017-03-10 23:23:24 +07:00
c2ee861c6d [extractor/generic] Make title optional for jwplayer embeds (closes #12410) 2017-03-10 23:16:53 +07:00
bd34c32bd7 [wdr] Actualize comment 2017-03-10 23:07:36 +07:00
f802c48660 [wdr:maus] Fix extraction and update tests 2017-03-10 23:59:32 +08:00
76bee08fe7 [prosiebensat1] Improve title extraction and add test 2017-03-09 23:42:07 +07:00
2913821723 [prosiebensat1] Improve title extraction (closes #12318) 2017-03-10 00:18:37 +08:00
0e7f9a9b48 [dplayit] Relax playback info URL extraction 2017-03-08 21:30:30 +07:00
0cf2352e85 [dplayit] Separate and rewrite extractor and bypass geo restriction (closes #12393) 2017-03-08 21:20:01 +07:00
0f6b87d067 [miomio] Fix extraction
Closes #12291
Closes #12388
Closes #12402
2017-03-08 19:46:58 +08:00
d7344d33b1 [telequebec] Fix description extraction and update test (closes #12399) 2017-03-08 18:25:59 +07:00
b08cc749d6 [openload] Fix extraction 2017-03-08 06:01:27 +08:00
b68a812ea8 [extractor/generic] Add test for brigthcove UUID-like videoPlayer 2017-03-07 23:00:21 +07:00
2e76bdc850 [brightcove:legacy] Relax videoPlayer validation check (closes #12381) 2017-03-07 22:59:33 +07:00
fe646a2f10 [twitch] PEP8 2017-03-07 15:34:06 +08:00
9df53ea36e Credit @puxlit for twitch 2fa (#11974) 2017-03-07 04:05:47 +07:00
d7d7f84c95 Credit @benages for redbull.tv (#11948) 2017-03-07 04:05:47 +07:00
dccd0ab35d release 2017.03.07 2017-03-07 03:59:22 +07:00
80146dcc6c [ChangeLog] Actualize 2017-03-07 03:57:54 +07:00
e30ccf7047 [soundcloud] Update client id (closes #12376) 2017-03-06 23:05:38 +07:00
54a3a8827b [__init__] Metadata should be added after conversion
Fixes #5594
2017-03-06 18:09:12 +08:00
92cb5763f4 [ChangeLog] Update after #12357 2017-03-06 18:04:19 +08:00
da92da4b88 Openload fix extraction (#12357)
* Fix extraction
2017-03-06 18:00:17 +08:00
1664702626 release 2017.03.06 2017-03-06 04:04:39 +07:00
3f116b189b [ChangeLog] Actualize 2017-03-06 04:01:21 +07:00
4b5de77bdb [utils] Process bytestrings in urljoin (closes #12369) 2017-03-06 03:57:46 +07:00
96182695e4 [drtv] Add geo countries to GeoRestrictedError 2017-03-06 03:23:42 +07:00
fc11ad3833 [drtv:live] Bypass geo restriction 2017-03-06 03:23:42 +07:00
d2b64e04b4 [addanime] Skip an invalid test 2017-03-06 00:35:04 +08:00
5dd376345b [tunepk] Add extractor (closes #12197, closes #12243) 2017-03-05 23:31:38 +07:00
1a2192cb90 [extractor/common] Pass arguments to _parse_jwplayer_formats and PEP8 2017-03-05 23:29:17 +07:00
0236cd0dfd [extractor/common] Improve height extraction and extract bitrate 2017-03-05 23:25:03 +07:00
ed0cf9b383 [extractor/common] Move jwplayer formats extraction in separate method 2017-03-05 23:22:27 +07:00
a50862b735 [downloader/external] Add missing import and PEP8 2017-03-05 10:24:29 +07:00
6d0fe752bf [external:ffmpeg] In test harness, limit to 10k download size
Otherwise, if you screw up a playlist test by including a playlist
dictionary key, you'll be there for eons while it downloads all the
files before erroring out.
2017-03-05 11:19:44 +08:00
afa4597618 release 2017.03.05 2017-03-05 02:23:08 +07:00
75027364ba [ChangeLog] Actualize 2017-03-05 02:22:02 +07:00
5316566edc [twitch] Use better naming and simplify (closes #11974) 2017-03-05 02:06:33 +07:00
c64c03be35 [twitch] Add basic support for two-factor authentication 2017-03-05 01:06:27 +07:00
bcefc59279 Credit @vierbergenlars for vijf.be (#12304) 2017-03-05 00:03:59 +07:00
6f211dc936 Credit @obilodeau for vrak (#11452) 2017-03-05 00:03:59 +07:00
f24c1e5584 Credit @TobiX for #9725 2017-03-05 00:03:59 +07:00
466274fe9a Credit @p2004a for vodpl (#12122) 2017-03-05 00:03:59 +07:00
30f8f142d4 Credit @ThomasChr for #12015 and #12245 2017-03-05 00:03:59 +07:00
a3ba8a7acf [vier] Add support for vijf.be
vier.be and vijf.be run on the same CMS and are property of the same company,
so the same extractor can be used for both of them.
2017-03-05 00:47:19 +08:00
054a587de8 [redbulltv] Improve extraction (closes #11948, closes #3919) 2017-03-04 23:28:21 +07:00
64b7ccef3e [redbulltv] Add extractor 2017-03-04 23:26:15 +07:00
6f4e4132d8 [douyutv] Switch to the PC API to escape the 5-min limitation
Thanks @spacemeowx2 for the algo.

Ref: https://gist.github.com/spacemeowx2/629b1d131bd7e240a7d28742048e80fc

Closes #12316
2017-03-04 23:23:18 +08:00
eb3079b6ce [generic] Add support for rutube embeds 2017-03-04 00:46:33 +07:00
bc82f22879 [rutube] Relax _VALID_URL 2017-03-04 00:42:51 +07:00
4d058c9862 [vrak] Improve and update test (closes #11452) 2017-03-03 23:58:16 +07:00
d16f27ca27 [brightcove:new] Add ability to smuggle geo_countries into URL 2017-03-03 23:58:03 +07:00
cbb127568a [vrak] Add extractor 2017-03-03 23:54:21 +07:00
d02d4fa0a9 [brightcove:new] Raise GeoRestrictedError 2017-03-03 22:49:48 +07:00
692fa200ca [go] Relax _VALID_URL (closes #12341) 2017-03-03 22:28:34 +07:00
9bae185ba6 [24video] Use original host for requests (closes #12339) 2017-03-03 22:16:00 +07:00
4d345bf17b [ruutu] Disable DASH formats (closes #12322)
Due to causing out of sync issue
2017-03-02 23:53:46 +07:00
250eea6821 release 2017.03.02 2017-03-02 22:33:22 +07:00
28d15b73f8 [ChangeLog] Actualize 2017-03-02 22:29:56 +07:00
11bb6ad1a5 [facebook] Fix extraction (closes #12323)
Almost all videos now use the pagelet type 'permalink_video_pagelet'
2017-03-02 20:51:24 +08:00
c9612c0487 [youtube] Mark errors about rental videos as expected
Closes #12324
2017-03-02 16:59:53 +08:00
af5049f128 [adobepass] Add Charter Spectrum (#11465)
Thanks @tv21 for the fix!
2017-03-02 02:15:51 +08:00
158af5242e [utils] Carry long doc string 2017-03-01 23:04:02 +07:00
40df485f55 [YoutubeDL] Don't sanitize identifiers (closes #12317) 2017-03-01 23:03:36 +07:00
4b8a984c67 [npo] Add support for audio 2017-03-01 22:21:13 +07:00
83e8fce628 [npo] Improve extraction and update tests 2017-03-01 22:14:46 +07:00
aa9cc2ecbf [npo] Adapt to app.php API (closes #12311) 2017-03-01 05:03:35 +07:00
1dc24093f8 release 2017.02.28 2017-02-28 23:59:22 +07:00
11bae9cdde [ChangeLog] Actualize 2017-02-28 23:49:24 +07:00
43b38424a9 [azmedien:showplaylist] Improve (closes #12160) 2017-02-28 23:37:54 +07:00
948519b35d [azmedien:showplaylist] Add support for all episodes playlists 2017-02-28 23:36:05 +07:00
87dadd456a [youtube:playlist] Recognize another playlist pattern (closes #11928, closes #12286) 2017-02-28 23:06:47 +07:00
7c4aa6fd6f [daisuki] Add subtitles (#4738) 2017-02-28 22:29:01 +08:00
9bd05b5a18 [daisuki] Add new extractor (closes #4738) 2017-02-28 22:19:26 +08:00
0a5445ddbe [utils] Add bytes_to_long() and long_to_bytes()
Used in daisuki.net (#4738)

Both are adapted from public domain PyCrypto:
https://github.com/dlitz/pycrypto/blob/master/lib/Crypto/Util/number.py
2017-02-28 22:10:31 +08:00
f48409c7ac [utils] Add pkcs1pad
Used in daisuki.net (#4738)
2017-02-28 22:10:31 +08:00
c9619f0a17 [aes] Add aes_cbc_encrypt
Used in daisuki.net (#4738)
2017-02-28 22:10:31 +08:00
f4c68ba372 [douyu] Fix extraction and update _TESTS
They've switched from flv to hls

Closes #12301
2017-02-28 21:41:03 +08:00
ef48a1175d release 2017.02.27 2017-02-27 23:26:07 +07:00
c6184bcf7b [ChangeLog] Actualize 2017-02-27 23:24:03 +07:00
18abb74376 [npo] Relax _VALID_URL for zapp.nl 2017-02-27 23:13:51 +07:00
dbc01fdb6f [hetklokhuis] Fix IE_NAME 2017-02-27 23:10:29 +07:00
f264c62334 [npo] Add support for zapp.nl 2017-02-27 23:10:00 +07:00
0dc5a86a32 [npo] Add support for hetklokhuis.nl (closes #12293) 2017-02-27 22:43:19 +07:00
0e879f432a [youtube:channel] Remove duplicate test 2017-02-27 22:22:43 +07:00
892b47ab6c [scivee] Remove extractor (#9315)
The Wikipedia page is changed from active to down:
https://en.wikipedia.org/w/index.php?title=SciVee&diff=prev&oldid=723161154

Some other interesting bits:

$ nslookup www.scivee.tv
Server:         8.8.8.8
Address:        8.8.8.8#53

Non-authoritative answer:
www.scivee.tv   canonical name = scivee.rcsb.org.
Name:   scivee.rcsb.org
Address: 132.249.231.211

$ nslookup rcsb.org
Server:         8.8.8.8
Address:        8.8.8.8#53

Non-authoritative answer:
Name:   rcsb.org
Address: 132.249.231.77

Both IPs are from UCSD. I guess it's maintained by a lab and they don't
maintain it anymore.
2017-02-27 21:34:33 +08:00
fdeea72611 [cda] Decode URL (fixes #12255) 2017-02-26 22:05:52 +08:00
xbe
7fd4655256 [crunchyroll] Extract uploader name that's not a link
Provide the Crunchyroll extractor with the ability to extract uploader
names that aren't links. Add a test for this new functionality.
This fixes #12267.
2017-02-26 19:08:10 +08:00
fd5c4aab59 [youtube] Raise GeoRestrictedError 2017-02-26 16:52:40 +07:00
8878789f11 [dailymotion] Raise GeoRestrictedError 2017-02-26 16:52:40 +07:00
a5cf17989b [MDR] Relax _VALID_URL and playerURL matching and update _TESTS
Ref: #12169
2017-02-26 17:24:54 +08:00
b3aec47665 [tvigle] Raise GeoRestrictedError 2017-02-25 23:27:45 +07:00
9d0c08a02c [vevo] Fix videos with the new streams/streamsV3 format (closes #11719) 2017-02-26 00:15:49 +08:00
e498758b9c [freshlive] Fix issues and improve (closes #12175) 2017-02-25 22:56:42 +07:00
5fc8d89361 [freshlive] Add extractor 2017-02-25 22:55:17 +07:00
d374d943f3 [downloader/common] Limit displaying 2 digits after decimal point in sleep interval message 2017-02-25 20:59:04 +07:00
103f8c8d36 [xhamster] Capture and output videoClosed error (#12263) 2017-02-25 20:38:21 +07:00
922ab7840b [etonline] Add extractor (closes #12236) 2017-02-25 20:16:40 +07:00
831217291a [compat] Use try except for compat_numeric_types 2017-02-25 19:44:50 +07:00
db182c63fb [njpwworld] Add new extractor (closes #11561) 2017-02-25 18:44:39 +08:00
eeb0a95684 [extractor/common] Add 'preference' to _parse_html5_media_entries
Some websites, like NJPWorld, put different qualities on different
player pages.
2017-02-25 18:40:05 +08:00
231bcd0b6b [amcnetworks] Relax _VALID_URL (#12127) 2017-02-25 02:51:53 +07:00
204efc8509 release 2017.02.24.1 2017-02-24 21:59:39 +07:00
5d3a51e1b9 [ChangeLog] Actualize 2017-02-24 21:57:39 +07:00
ad3033037c [noco] Modernize 2017-02-24 21:51:56 +07:00
f3bc281239 [noco] Swtich login URL to https (closes #12246) 2017-02-24 21:48:34 +07:00
441d7a32e5 [thescene] Extract more metadata 2017-02-24 21:22:29 +07:00
51ed496307 [thescene] Fix extraction (closes #12235) 2017-02-24 22:08:45 +08:00
68f17a9c2d [tubitv] use geo bypass mechanism 2017-02-24 12:27:56 +01:00
39e7277ed1 [openload] fix extraction(closes #10408) 2017-02-24 11:21:58 +01:00
42dcdbe11c [ivi] Raise GeoRestrictedError 2017-02-24 10:54:39 +07:00
106 changed files with 4260 additions and 1449 deletions

View File

@ -6,8 +6,8 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.02.24*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.02.24**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.04.02*. If it's not read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.04.02**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through [README](https://github.com/rg3/youtube-dl/blob/master/README.md) and **most notably** [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
@ -35,7 +35,7 @@ $ youtube-dl -v <your command line>
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.02.24
[debug] youtube-dl version 2017.04.02
[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

@ -202,3 +202,11 @@ Fabian Stahl
Bagira
Odd Stråbø
Philip Herzog
Thomas Christlieb
Marek Rusinowski
Tobias Gruetzmacher
Olivier Bilodeau
Lars Vierbergen
Juanjo Benages
Xiao Di Guan
Thomas Winant

226
ChangeLog
View File

@ -1,3 +1,229 @@
version 2017.04.02
Core
[YoutubeDL] Return early when extraction of url_transparent fails
Extractors
* [rai] Fix and improve extraction (#11790)
+ [vrv] Add support for series pages
* [limelight] Improve extraction for audio only formats
* [funimation] Fix extraction (#10696, #11773)
+ [xfileshare] Add support for vidabc.com (#12589)
+ [xfileshare] Improve extraction and extract hls formats
+ [crunchyroll] Pass geo verifcation proxy
+ [cwtv] Extract ISM formats
+ [tvplay] Bypass geo restriction
+ [vrv] Add support for vrv.co
+ [packtpub] Add support for packtpub.com (#12610)
+ [generic] Pass base_url to _parse_jwplayer_data
+ [adn] Add support for animedigitalnetwork.fr (#4866)
+ [allocine] Extract more metadata
* [allocine] Fix extraction (#12592)
* [openload] Fix extraction
version 2017.03.26
Core
* Don't raise an error if JWPlayer config data is not a Javascript object
literal. _find_jwplayer_data now returns a dict rather than an str. (#12307)
* Expand environment variables for options representing paths (#12556)
+ [utils] Introduce expand_path
* [downloader/hls] Delegate downloading to ffmpeg immediately for live streams
Extractors
* [afreecatv] Fix extraction (#12179)
+ [atvat] Add support for atv.at (#5325)
+ [fox] Add metadata extraction (#12391)
+ [atresplayer] Extract DASH formats
+ [atresplayer] Extract HD manifest (#12548)
* [atresplayer] Fix login error detection (#12548)
* [franceculture] Fix extraction (#12547)
* [youtube] Improve URL regular expression (#12538)
* [generic] Do not follow redirects to the same URL
version 2017.03.24
Extractors
- [9c9media] Remove mp4 URL extraction request
+ [bellmedia] Add support for etalk.ca and space.ca (#12447)
* [channel9] Fix extraction (#11323)
* [cloudy] Fix extraction (#12525)
+ [hbo] Add support for free episode URLs and new formats extraction (#12519)
* [condenast] Fix extraction and style (#12526)
* [viu] Relax URL regular expression (#12529)
version 2017.03.22
Extractors
- [pluralsight] Omit module title from video title (#12506)
* [pornhub] Decode obfuscated video URL (#12470, #12515)
* [senateisvp] Allow https URL scheme for embeds (#12512)
version 2017.03.20
Core
+ [YoutubeDL] Allow multiple input URLs to be used with stdout (-) as
output template
+ [adobepass] Detect and output error on authz token extraction (#12472)
Extractors
+ [bostonglobe] Add extractor for bostonglobe.com (#12099)
+ [toongoggles] Add support for toongoggles.com (#12171)
+ [medialaan] Add support for Medialaan sites (#9974, #11912)
+ [discoverynetworks] Add support for more domains and bypass geo restiction
* [openload] Fix extraction (#10408)
version 2017.03.16
Core
+ [postprocessor/ffmpeg] Add support for flac
+ [extractor/common] Extract SMIL formats from jwplayer
Extractors
+ [generic] Add forgotten return for jwplayer formats
* [redbulltv] Improve extraction
version 2017.03.15
Core
* Fix missing subtitles if --add-metadata is used (#12423)
Extractors
* [facebook] Make title optional (#12443)
+ [mitele] Add support for ooyala videos (#12430)
* [openload] Fix extraction (#12435, #12446)
* [streamable] Update API URL (#12433)
+ [crunchyroll] Extract season name (#12428)
* [discoverygo] Bypass geo restriction
+ [discoverygo:playlist] Add support for playlists (#12424)
version 2017.03.10
Extractors
* [generic] Make title optional for jwplayer embeds (#12410)
* [wdr:maus] Fix extraction (#12373)
* [prosiebensat1] Improve title extraction (#12318, #12327)
* [dplayit] Separate and rewrite extractor and bypass geo restriction (#12393)
* [miomio] Fix extraction (#12291, #12388, #12402)
* [telequebec] Fix description extraction (#12399)
* [openload] Fix extraction (#12357)
* [brightcove:legacy] Relax videoPlayer validation check (#12381)
version 2017.03.07
Core
* Metadata are now added after conversion (#5594)
Extractors
* [soundcloud] Update client id (#12376)
* [openload] Fix extraction (#10408, #12357)
version 2017.03.06
Core
+ [utils] Process bytestrings in urljoin (#12369)
* [extractor/common] Improve height extraction and extract bitrate
* [extractor/common] Move jwplayer formats extraction in separate method
+ [external:ffmpeg] Limit test download size to 10KiB (#12362)
Extractors
+ [drtv] Add geo countries to GeoRestrictedError
+ [drtv:live] Bypass geo restriction
+ [tunepk] Add extractor (#12197, #12243)
version 2017.03.05
Extractors
+ [twitch] Add basic support for two-factor authentication (#11974)
+ [vier] Add support for vijf.be (#12304)
+ [redbulltv] Add support for redbull.tv (#3919, #11948)
* [douyutv] Switch to the PC API to escape the 5-min limitation (#12316)
+ [generic] Add support for rutube embeds
+ [rutube] Relax URL regular expression
+ [vrak] Add support for vrak.tv (#11452)
+ [brightcove:new] Add ability to smuggle geo_countries into URL
+ [brightcove:new] Raise GeoRestrictedError
* [go] Relax URL regular expression (#12341)
* [24video] Use original host for requests (#12339)
* [ruutu] Disable DASH formats (#12322)
version 2017.03.02
Core
+ [adobepass] Add support for Charter Spectrum (#11465)
* [YoutubeDL] Don't sanitize identifiers in output template (#12317)
Extractors
* [facebook] Fix extraction (#12323, #12330)
* [youtube] Mark errors about rental videos as expected (#12324)
+ [npo] Add support for audio
* [npo] Adapt to app.php API (#12311, #12320)
version 2017.02.28
Core
+ [utils] Add bytes_to_long and long_to_bytes
+ [utils] Add pkcs1pad
+ [aes] Add aes_cbc_encrypt
Extractors
+ [azmedien:showplaylist] Add support for show playlists (#12160)
+ [youtube:playlist] Recognize another playlist pattern (#11928, #12286)
+ [daisuki] Add support for daisuki.net (#2486, #3186, #4738, #6175, #7776,
#10060)
* [douyu] Fix extraction (#12301)
version 2017.02.27
Core
* [downloader/common] Limit displaying 2 digits after decimal point in sleep
interval message (#12183)
+ [extractor/common] Add preference to _parse_html5_media_entries
Extractors
+ [npo] Add support for zapp.nl
+ [npo] Add support for hetklokhuis.nl (#12293)
- [scivee] Remove extractor (#9315)
+ [cda] Decode download URL (#12255)
+ [crunchyroll] Improve uploader extraction (#12267)
+ [youtube] Raise GeoRestrictedError
+ [dailymotion] Raise GeoRestrictedError
+ [mdr] Recognize more URL patterns (#12169)
+ [tvigle] Raise GeoRestrictedError
* [vevo] Fix extraction for videos with the new streams/streamsV3 format
(#11719)
+ [freshlive] Add support for freshlive.tv (#12175)
+ [xhamster] Capture and output videoClosed error (#12263)
+ [etonline] Add support for etonline.com (#12236)
+ [njpwworld] Add support for njpwworld.com (#11561)
* [amcnetworks] Relax URL regular expression (#12127)
version 2017.02.24.1
Extractors
* [noco] Modernize
* [noco] Switch login URL to https (#12246)
+ [thescene] Extract more metadata
* [thescene] Fix extraction (#12235)
+ [tubitv] Use geo bypass mechanism
* [openload] Fix extraction (#10408)
+ [ivi] Raise GeoRestrictedError
version 2017.02.24
Core

View File

@ -181,10 +181,10 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
-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 and hlsnative
only)
--skip-unavailable-fragments Skip unavailable fragments (DASH and
hlsnative only)
is 10), or "infinite" (DASH, hlsnative and
ISM)
--skip-unavailable-fragments Skip unavailable fragments (DASH, hlsnative
and ISM)
--abort-on-unavailable-fragment Abort downloading when some fragment is not
available
--buffer-size SIZE Size of download buffer (e.g. 1024 or 16K)
@ -375,8 +375,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
(requires ffmpeg or avconv and ffprobe or
avprobe)
--audio-format FORMAT Specify audio format: "best", "aac",
"vorbis", "mp3", "m4a", "opus", or "wav";
"best" by default; No effect without -x
"flac", "mp3", "m4a", "opus", "vorbis", or
"wav"; "best" by default; No effect without
-x
--audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert
a value between 0 (better) and 9 (worse)
for VBR or a specific bitrate like 128K

View File

@ -28,6 +28,7 @@
- **acast**
- **acast:channel**
- **AddAnime**
- **ADN**: Anime Digital Network
- **AdobeTV**
- **AdobeTVChannel**
- **AdobeTVShow**
@ -67,6 +68,7 @@
- **arte.tv:playlist**
- **AtresPlayer**
- **ATTTechChannel**
- **ATVAt**
- **AudiMedia**
- **AudioBoom**
- **audiomack**
@ -78,6 +80,7 @@
- **awaan:video**
- **AZMedien**: AZ Medien videos
- **AZMedienPlaylist**: AZ Medien playlists
- **AZMedienShowPlaylist**: AZ Medien show playlists
- **Azubu**
- **AzubuLive**
- **BaiduVideo**: 百度视频
@ -107,6 +110,7 @@
- **blinkx**
- **Bloomberg**
- **BokeCC**
- **BostonGlobe**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **BravoTV**
@ -191,6 +195,8 @@
- **dailymotion:playlist**
- **dailymotion:user**
- **DailymotionCloud**
- **Daisuki**
- **DaisukiPlaylist**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
@ -205,10 +211,13 @@
- **Digiteka**
- **Discovery**
- **DiscoveryGo**
- **DiscoveryGoPlaylist**
- **DiscoveryNetworksDe**
- **Disney**
- **Dotsub**
- **DouyuTV**: 斗鱼
- **DPlay**
- **DPlayIt**
- **dramafever**
- **dramafever:series**
- **DRBonanza**
@ -239,6 +248,7 @@
- **ESPN**
- **ESPNArticle**
- **EsriVideo**
- **ETOnline**
- **Europa**
- **EveryonesMixtape**
- **ExpoTV**
@ -274,6 +284,7 @@
- **francetvinfo.fr**
- **Freesound**
- **freespeech.org**
- **FreshLive**
- **Funimation**
- **FunnyOrDie**
- **Fusion**
@ -303,13 +314,14 @@
- **GPUTechConf**
- **Groupon**
- **Hark**
- **HBO**
- **HBOEpisode**
- **hbo**
- **hbo:episode**
- **HearThisAt**
- **Heise**
- **HellPorno**
- **Helsinki**: helsinki.fi
- **HentaiStigma**
- **hetklokhuis**
- **hgtv.com:show**
- **HistoricFilms**
- **history:topic**: History.com Topic
@ -417,6 +429,7 @@
- **MatchTV**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **Medialaan**
- **Meipai**: 美拍
- **MelonVOD**
- **META**
@ -511,6 +524,7 @@
- **Nintendo**
- **njoy**: N-JOY
- **njoy:embed**
- **NJPWWorld**: 新日本プロレスワールド
- **NobelPrize**
- **Noco**
- **Normalboots**
@ -559,6 +573,8 @@
- **orf:iptv**: iptv.ORF.at
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **PacktPub**
- **PacktPubCourse**
- **PandaTV**: 熊猫TV
- **pandora.tv**: 판도라TV
- **parliamentlive.tv**: UK parliament videos
@ -616,9 +632,10 @@
- **radiofrance**
- **RadioJavan**
- **Rai**
- **RaiTV**
- **RaiPlay**
- **RBMARadio**
- **RDS**: RDS.ca
- **RedBullTV**
- **RedTube**
- **RegioTV**
- **RENTV**
@ -666,7 +683,6 @@
- **savefrom.net**
- **SBS**: sbs.com.au
- **schooltv**
- **SciVee**
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
@ -768,12 +784,12 @@
- **ThisAV**
- **ThisOldHouse**
- **tinypic**: tinypic.com videos
- **tlc.de**
- **TMZ**
- **TMZArticle**
- **TNAFlix**
- **TNAFlixNetworkEmbed**
- **toggle**
- **ToonGoggles**
- **Tosh**: Tosh.0
- **tou.tv**
- **Toypics**: Toypics user profile
@ -791,6 +807,7 @@
- **tunein:program**
- **tunein:station**
- **tunein:topic**
- **TunePk**
- **Turbo**
- **Tutv**
- **tv.dfb.de**
@ -910,7 +927,10 @@
- **VoxMedia**
- **Vporn**
- **vpro**: npo.nl and ntr.nl
- **Vrak**
- **VRT**
- **vrv**
- **vrv:series**
- **vube**: Vube.com
- **VuClip**
- **VVVVID**
@ -938,7 +958,7 @@
- **WSJ**: Wall Street Journal
- **XBef**
- **XboxClips**
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE
- **XFileShare**: XFileShare based sites: DaClips, FileHoot, GorillaVid, MovPod, PowerWatch, Rapidvideo.ws, TheVideoBee, Vidto, Streamin.To, XVIDSTAGE, Vid ABC
- **XHamster**
- **XHamsterEmbed**
- **xiami:album**: 虾米音乐 - 专辑

View File

@ -8,7 +8,7 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL
from test.helper import FakeYDL, expect_dict
from youtube_dl.extractor.common import InfoExtractor
from youtube_dl.extractor import YoutubeIE, get_info_extractor
from youtube_dl.utils import encode_data_uri, strip_jsonp, ExtractorError, RegexNotFoundError
@ -84,6 +84,97 @@ class TestInfoExtractor(unittest.TestCase):
self.assertRaises(ExtractorError, self.ie._download_json, uri, None)
self.assertEqual(self.ie._download_json(uri, None, fatal=False), None)
def test_extract_jwplayer_data_realworld(self):
# from http://www.suffolk.edu/sjc/
expect_dict(
self,
self.ie._extract_jwplayer_data(r'''
<script type='text/javascript'>
jwplayer('my-video').setup({
file: 'rtmp://192.138.214.154/live/sjclive',
fallback: 'true',
width: '95%',
aspectratio: '16:9',
primary: 'flash',
mediaid:'XEgvuql4'
});
</script>
''', None, require_title=False),
{
'id': 'XEgvuql4',
'formats': [{
'url': 'rtmp://192.138.214.154/live/sjclive',
'ext': 'flv'
}]
})
# from https://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary/
expect_dict(
self,
self.ie._extract_jwplayer_data(r'''
<script type="text/javascript">
jwplayer("mediaplayer").setup({
'videoid': "7564",
'width': "100%",
'aspectratio': "16:9",
'stretching': "exactfit",
'autostart': 'false',
'flashplayer': "https://t04.vipstreamservice.com/jwplayer/v5.10/player.swf",
'file': "https://cdn.pornoxo.com/key=MF+oEbaxqTKb50P-w9G3nA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/4b2157147afe5efa93ce1978e0265289c193874e02597.flv",
'image': "https://t03.vipstreamservice.com/thumbs/pxo-full/2009-12/14/a4b2157147afe5efa93ce1978e0265289c193874e02597.flv-full-13.jpg",
'filefallback': "https://cdn.pornoxo.com/key=9ZPsTR5EvPLQrBaak2MUGA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/m_4b2157147afe5efa93ce1978e0265289c193874e02597.mp4",
'logo.hide': true,
'skin': "https://t04.vipstreamservice.com/jwplayer/skin/modieus-blk.zip",
'plugins': "https://t04.vipstreamservice.com/jwplayer/dock/dockableskinnableplugin.swf",
'dockableskinnableplugin.piclink': "/index.php?key=ajax-videothumbsn&vid=7564&data=2009-12--14--4b2157147afe5efa93ce1978e0265289c193874e02597.flv--17370",
'controlbar': 'bottom',
'modes': [
{type: 'flash', src: 'https://t04.vipstreamservice.com/jwplayer/v5.10/player.swf'}
],
'provider': 'http'
});
//noinspection JSAnnotator
invideo.setup({
adsUrl: "/banner-iframe/?zoneId=32",
adsUrl2: "",
autostart: false
});
</script>
''', 'dummy', require_title=False),
{
'thumbnail': 'https://t03.vipstreamservice.com/thumbs/pxo-full/2009-12/14/a4b2157147afe5efa93ce1978e0265289c193874e02597.flv-full-13.jpg',
'formats': [{
'url': 'https://cdn.pornoxo.com/key=MF+oEbaxqTKb50P-w9G3nA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/4b2157147afe5efa93ce1978e0265289c193874e02597.flv',
'ext': 'flv'
}]
})
# from http://www.indiedb.com/games/king-machine/videos
expect_dict(
self,
self.ie._extract_jwplayer_data(r'''
<script>
jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/\/www.indiedb.com\/","displaytitle":false,"autostart":false,"repeat":false,"title":"king machine trailer 1","sharing":{"link":"http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1","code":"<iframe width=\"560\" height=\"315\" src=\"http:\/\/www.indiedb.com\/media\/iframe\/1522983\" frameborder=\"0\" allowfullscreen><\/iframe><br><a href=\"http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1\">king machine trailer 1 - Indie DB<\/a>"},"related":{"file":"http:\/\/rss.indiedb.com\/media\/recommended\/1522983\/feed\/rss.xml","dimensions":"160x120","onclick":"link"},"sources":[{"file":"http:\/\/cdn.dbolical.com\/cache\/videos\/games\/1\/50\/49678\/encode_mp4\/king-machine-trailer.mp4","label":"360p SD","default":"true"},{"file":"http:\/\/cdn.dbolical.com\/cache\/videos\/games\/1\/50\/49678\/encode720p_mp4\/king-machine-trailer.mp4","label":"720p HD"}],"image":"http:\/\/media.indiedb.com\/cache\/images\/games\/1\/50\/49678\/thumb_620x2000\/king-machine-trailer.mp4.jpg","advertising":{"client":"vast","tag":"http:\/\/ads.intergi.com\/adrawdata\/3.0\/5205\/4251742\/0\/1013\/ADTECH;cors=yes;width=560;height=315;referring_url=http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1;content_url=http:\/\/www.indiedb.com\/games\/king-machine\/videos\/king-machine-trailer-1;media_id=1522983;title=king+machine+trailer+1;device=__DEVICE__;model=__MODEL__;os=Windows+OS;osversion=__OSVERSION__;ua=__UA__;ip=109.171.17.81;uniqueid=1522983;tags=__TAGS__;number=58cac25928151;time=1489683033"},"width":620,"height":349}).once("play", function(event) {
videoAnalytics("play");
}).once("complete", function(event) {
videoAnalytics("completed");
});
</script>
''', 'dummy'),
{
'title': 'king machine trailer 1',
'thumbnail': 'http://media.indiedb.com/cache/images/games/1/50/49678/thumb_620x2000/king-machine-trailer.mp4.jpg',
'formats': [{
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode_mp4/king-machine-trailer.mp4',
'height': 360,
'ext': 'mp4'
}, {
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode720p_mp4/king-machine-trailer.mp4',
'height': 720,
'ext': 'mp4'
}]
})
if __name__ == '__main__':
unittest.main()

View File

@ -8,7 +8,7 @@ import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_cbc_encrypt, aes_decrypt_text
from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
import base64
@ -34,6 +34,13 @@ class TestAES(unittest.TestCase):
decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_cbc_encrypt(self):
data = bytes_to_intlist(self.secret_msg)
encrypted = intlist_to_bytes(aes_cbc_encrypt(data, self.key, self.iv))
self.assertEqual(
encrypted,
b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd")
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(

View File

@ -27,11 +27,11 @@ from youtube_dl.compat import (
class TestCompat(unittest.TestCase):
def test_compat_getenv(self):
test_str = 'тест'
compat_setenv('YOUTUBE-DL-TEST', test_str)
self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
compat_setenv('YOUTUBE_DL_COMPAT_GETENV', test_str)
self.assertEqual(compat_getenv('YOUTUBE_DL_COMPAT_GETENV'), test_str)
def test_compat_setenv(self):
test_var = 'YOUTUBE-DL-TEST'
test_var = 'YOUTUBE_DL_COMPAT_SETENV'
test_str = 'тест'
compat_setenv(test_var, test_str)
compat_getenv(test_var)

View File

@ -71,6 +71,18 @@ class TestDownload(unittest.TestCase):
maxDiff = None
def __str__(self):
"""Identify each test with the `add_ie` attribute, if available."""
def strclass(cls):
"""From 2.7's unittest; 2.6 had _strclass so we can't import it."""
return '%s.%s' % (cls.__module__, cls.__name__)
add_ie = getattr(self, self._testMethodName).add_ie
return '%s (%s)%s:' % (self._testMethodName,
strclass(self.__class__),
' [%s]' % add_ie if add_ie else '')
def setUp(self):
self.defs = defs
@ -233,6 +245,8 @@ for n, test_case in enumerate(defs):
i += 1
test_method = generator(test_case, tname)
test_method.__name__ = str(tname)
ie_list = test_case.get('add_ie')
test_method.add_ie = ie_list and ','.join(ie_list)
setattr(TestDownload, test_method.__name__, test_method)
del test_method

View File

@ -52,9 +52,11 @@ from youtube_dl.utils import (
parse_filesize,
parse_count,
parse_iso8601,
pkcs1pad,
read_batch_urls,
sanitize_filename,
sanitize_path,
expand_path,
prepend_extension,
replace_extension,
remove_start,
@ -94,6 +96,8 @@ from youtube_dl.utils import (
from youtube_dl.compat import (
compat_chr,
compat_etree_fromstring,
compat_getenv,
compat_setenv,
compat_urlparse,
compat_parse_qs,
)
@ -213,6 +217,18 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
def test_expand_path(self):
def env(var):
return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
compat_setenv('YOUTUBE_DL_EXPATH_PATH', 'expanded')
self.assertEqual(expand_path(env('YOUTUBE_DL_EXPATH_PATH')), 'expanded')
self.assertEqual(expand_path(env('HOME')), compat_getenv('HOME'))
self.assertEqual(expand_path('~'), compat_getenv('HOME'))
self.assertEqual(
expand_path('~/%s' % env('YOUTUBE_DL_EXPATH_PATH')),
'%s/expanded' % compat_getenv('HOME'))
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
@ -454,6 +470,9 @@ class TestUtil(unittest.TestCase):
def test_urljoin(self):
self.assertEqual(urljoin('http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
self.assertEqual(urljoin(b'http://foo.de/', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
self.assertEqual(urljoin('http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
self.assertEqual(urljoin(b'http://foo.de/', b'/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
self.assertEqual(urljoin('//foo.de/', '/a/b/c.txt'), '//foo.de/a/b/c.txt')
self.assertEqual(urljoin('http://foo.de/', 'a/b/c.txt'), 'http://foo.de/a/b/c.txt')
self.assertEqual(urljoin('http://foo.de', '/a/b/c.txt'), 'http://foo.de/a/b/c.txt')
@ -1104,6 +1123,14 @@ The first line
ohdave_rsa_encrypt(b'aa111222', e, N),
'726664bd9a23fd0c70f9f1b84aab5e3905ce1e45a584e9cbcf9bcc7510338fc1986d6c599ff990d923aa43c51c0d9013cd572e13bc58f4ae48f2ed8c0b0ba881')
def test_pkcs1pad(self):
data = [1, 2, 3]
padded_data = pkcs1pad(data, 32)
self.assertEqual(padded_data[:2], [0, 2])
self.assertEqual(padded_data[28:], [0, 1, 2, 3])
self.assertRaises(ValueError, pkcs1pad, data, 8)
def test_encode_base_n(self):
self.assertEqual(encode_base_n(0, 30), '0')
self.assertEqual(encode_base_n(80, 30), '2k')

View File

@ -29,7 +29,6 @@ import random
from .compat import (
compat_basestring,
compat_cookiejar,
compat_expanduser,
compat_get_terminal_size,
compat_http_client,
compat_kwargs,
@ -54,6 +53,7 @@ from .utils import (
encode_compat_str,
encodeFilename,
error_to_compat_str,
expand_path,
ExtractorError,
format_bytes,
formatSeconds,
@ -616,7 +616,7 @@ class YoutubeDL(object):
sanitize = lambda k, v: sanitize_filename(
compat_str(v),
restricted=self.params.get('restrictfilenames'),
is_id=(k == 'id'))
is_id=(k == 'id' or k.endswith('_id')))
template_dict = dict((k, v if isinstance(v, compat_numeric_types) else sanitize(k, v))
for k, v in template_dict.items()
if v is not None and not isinstance(v, (list, tuple, dict)))
@ -672,7 +672,7 @@ class YoutubeDL(object):
FORMAT_RE.format(numeric_field),
r'%({0})s'.format(numeric_field), outtmpl)
tmpl = compat_expanduser(outtmpl)
tmpl = expand_path(outtmpl)
filename = tmpl % template_dict
# Temporary fix for #4787
# 'Treat' all problem characters by passing filename through preferredencoding
@ -837,6 +837,12 @@ class YoutubeDL(object):
ie_result['url'], ie_key=ie_result.get('ie_key'),
extra_info=extra_info, download=False, process=False)
# extract_info may return None when ignoreerrors is enabled and
# extraction failed with an error, don't crash and return early
# in this case
if not info:
return info
force_properties = dict(
(k, v) for k, v in ie_result.items() if v is not None)
for f in ('_type', 'url', 'ie_key'):
@ -1872,6 +1878,7 @@ class YoutubeDL(object):
"""Download a given list of URLs."""
outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL)
if (len(url_list) > 1 and
outtmpl != '-' and
'%' not in outtmpl and
self.params.get('max_downloads') != 1):
raise SameFileError(outtmpl)
@ -2169,7 +2176,7 @@ class YoutubeDL(object):
if opts_cookiefile is None:
self.cookiejar = compat_cookiejar.CookieJar()
else:
opts_cookiefile = compat_expanduser(opts_cookiefile)
opts_cookiefile = expand_path(opts_cookiefile)
self.cookiejar = compat_cookiejar.MozillaCookieJar(
opts_cookiefile)
if os.access(opts_cookiefile, os.R_OK):

View File

@ -16,7 +16,6 @@ from .options import (
parseOpts,
)
from .compat import (
compat_expanduser,
compat_getpass,
compat_shlex_split,
workaround_optparse_bug9161,
@ -26,6 +25,7 @@ from .utils import (
decodeOption,
DEFAULT_OUTTMPL,
DownloadError,
expand_path,
match_filter_func,
MaxDownloadsReached,
preferredencoding,
@ -88,7 +88,7 @@ def _real_main(argv=None):
batchfd = sys.stdin
else:
batchfd = io.open(
compat_expanduser(opts.batchfile),
expand_path(opts.batchfile),
'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd)
if opts.verbose:
@ -196,7 +196,7 @@ def _real_main(argv=None):
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise ValueError('Playlist end must be greater than playlist start')
if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
if opts.audioformat not in ['best', 'aac', 'flac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error('invalid audio format specified')
if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K')
@ -238,18 +238,15 @@ def _real_main(argv=None):
any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
any_printing = opts.print_json
download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# PostProcessors
postprocessors = []
# Add the metadata pp first, the other pps will copy it
if opts.metafromtitle:
postprocessors.append({
'key': 'MetadataFromTitle',
'titleformat': opts.metafromtitle
})
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.extractaudio:
postprocessors.append({
'key': 'FFmpegExtractAudio',
@ -262,6 +259,16 @@ def _real_main(argv=None):
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
# FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
# FFmpegExtractAudioPP as containers before conversion may not support
# metadata (3gp, webm, etc.)
# And this post-processor should be placed before other metadata
# manipulating post-processors (FFmpegEmbedSubtitle) to prevent loss of
# extra metadata. By default ffmpeg preserves metadata applicable for both
# source and target containers. From this point the container won't change,
# so metadata can be added here.
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.convertsubtitles:
postprocessors.append({
'key': 'FFmpegSubtitlesConvertor',
@ -442,7 +449,7 @@ def _real_main(argv=None):
try:
if opts.load_info_filename is not None:
retcode = ydl.download_with_info_file(compat_expanduser(opts.load_info_filename))
retcode = ydl.download_with_info_file(expand_path(opts.load_info_filename))
else:
retcode = ydl.download(all_urls)
except MaxDownloadsReached:

View File

@ -60,6 +60,34 @@ def aes_cbc_decrypt(data, key, iv):
return decrypted_data
def aes_cbc_encrypt(data, key, iv):
"""
Encrypt with aes in CBC mode. Using PKCS#7 padding
@param {int[]} data cleartext
@param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte IV
@returns {int[]} encrypted data
"""
expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
encrypted_data = []
previous_cipher_block = iv
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
remaining_length = BLOCK_SIZE_BYTES - len(block)
block += [remaining_length] * remaining_length
mixed_block = xor(block, previous_cipher_block)
encrypted_block = aes_encrypt(mixed_block, expanded_key)
encrypted_data += encrypted_block
previous_cipher_block = encrypted_block
return encrypted_data
def key_expansion(data):
"""
Generate key schedule

View File

@ -8,8 +8,11 @@ import re
import shutil
import traceback
from .compat import compat_expanduser, compat_getenv
from .utils import write_json_file
from .compat import compat_getenv
from .utils import (
expand_path,
write_json_file,
)
class Cache(object):
@ -21,7 +24,7 @@ class Cache(object):
if res is None:
cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'youtube-dl')
return compat_expanduser(res)
return expand_path(res)
def _get_cache_fn(self, section, key, dtype):
assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \

View File

@ -2760,8 +2760,10 @@ else:
compat_kwargs = lambda kwargs: kwargs
compat_numeric_types = ((int, float, long, complex) if sys.version_info[0] < 3
else (int, float, complex))
try:
compat_numeric_types = (int, float, long, complex)
except NameError: # Python 3
compat_numeric_types = (int, float, complex)
if sys.version_info < (2, 7):

View File

@ -43,6 +43,9 @@ def get_suitable_downloader(info_dict, params={}):
if ed.can_download(info_dict):
return ed
if protocol.startswith('m3u8') and info_dict.get('is_live'):
return FFmpegFD
if protocol == 'm3u8' and params.get('hls_prefer_native') is True:
return HlsFD

View File

@ -347,7 +347,10 @@ class FileDownloader(object):
if min_sleep_interval:
max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
self.to_screen(
'[download] Sleeping %s seconds...' % (
int(sleep_interval) if sleep_interval.is_integer()
else '%.2f' % sleep_interval))
time.sleep(sleep_interval)
return self.real_download(filename, info_dict)

View File

@ -6,7 +6,10 @@ import sys
import re
from .common import FileDownloader
from ..compat import compat_setenv
from ..compat import (
compat_setenv,
compat_str,
)
from ..postprocessor.ffmpeg import FFmpegPostProcessor, EXT_TO_OUT_FORMATS
from ..utils import (
cli_option,
@ -270,6 +273,10 @@ class FFmpegFD(ExternalFD):
args += ['-rtmp_live', 'live']
args += ['-i', url, '-c', 'copy']
if self.params.get('test', False):
args += ['-fs', compat_str(self._TEST_FILE_SIZE)]
if protocol in ('m3u8', 'm3u8_native'):
if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
args += ['-f', 'mpegts']

View File

@ -25,7 +25,8 @@ class AddAnimeIE(InfoExtractor):
'ext': 'mp4',
'description': 'One Piece 606',
'title': 'One Piece 606',
}
},
'skip': 'Video is gone',
}, {
'url': 'http://add-anime.net/video/MDUGWYKNGBD8/One-Piece-687',
'only_matching': True,

136
youtube_dl/extractor/adn.py Normal file
View File

@ -0,0 +1,136 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import json
import os
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt
from ..compat import compat_ord
from ..utils import (
bytes_to_intlist,
ExtractorError,
float_or_none,
intlist_to_bytes,
srt_subtitles_timecode,
strip_or_none,
)
class ADNIE(InfoExtractor):
IE_DESC = 'Anime Digital Network'
_VALID_URL = r'https?://(?:www\.)?animedigitalnetwork\.fr/video/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'md5': 'e497370d847fd79d9d4c74be55575c7a',
'info_dict': {
'id': '7778',
'ext': 'mp4',
'title': 'Blue Exorcist - Kyôto Saga - Épisode 1',
'description': 'md5:2f7b5aa76edbc1a7a92cedcda8a528d5',
}
}
def _get_subtitles(self, sub_path, video_id):
if not sub_path:
return None
enc_subtitles = self._download_webpage(
'http://animedigitalnetwork.fr/' + sub_path,
video_id, fatal=False)
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(base64.b64decode(enc_subtitles[24:])),
bytes_to_intlist(b'\xb5@\xcfq\xa3\x98"N\xe4\xf3\x12\x98}}\x16\xd8'),
bytes_to_intlist(base64.b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
dec_subtitles[:-compat_ord(dec_subtitles[-1])],
None, fatal=False)
if not subtitles_json:
return None
subtitles = {}
for sub_lang, sub in subtitles_json.items():
srt = ''
for num, current in enumerate(sub):
start, end, text = (
float_or_none(current.get('startTime')),
float_or_none(current.get('endTime')),
current.get('text'))
if start is None or end is None or text is None:
continue
srt += os.linesep.join(
(
'%d' % num,
'%s --> %s' % (
srt_subtitles_timecode(start),
srt_subtitles_timecode(end)),
text,
os.linesep,
))
if sub_lang == 'vostf':
sub_lang = 'fr'
subtitles.setdefault(sub_lang, []).extend([{
'ext': 'json',
'data': json.dumps(sub),
}, {
'ext': 'srt',
'data': srt,
}])
return subtitles
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_config = self._parse_json(self._search_regex(
r'playerConfig\s*=\s*({.+});', webpage, 'player config'), video_id)
video_info = {}
video_info_str = self._search_regex(
r'videoInfo\s*=\s*({.+});', webpage,
'video info', fatal=False)
if video_info_str:
video_info = self._parse_json(
video_info_str, video_id, fatal=False) or {}
options = player_config.get('options') or {}
metas = options.get('metas') or {}
title = metas.get('title') or video_info['title']
links = player_config.get('links') or {}
formats = []
for format_id, qualities in links.items():
for load_balancer_url in qualities.values():
load_balancer_data = self._download_json(
load_balancer_url, video_id, fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
continue
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False)
if format_id == 'vf':
for f in m3u8_formats:
f['language'] = 'fr'
formats.extend(m3u8_formats)
error = options.get('error')
if not formats and error:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
'thumbnail': video_info.get('image'),
'formats': formats,
'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
'episode': metas.get('subtitle') or video_info.get('videoTitle'),
'series': video_info.get('playlistTitle'),
}

View File

@ -36,6 +36,11 @@ MSO_INFO = {
'username_field': 'Ecom_User_ID',
'password_field': 'Ecom_Password',
},
'Charter_Direct': {
'name': 'Charter Spectrum',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
},
'thr030': {
'name': '3 Rivers Communications'
},
@ -1453,6 +1458,8 @@ class AdobePassIE(InfoExtractor):
self._downloader.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
if '<error' in authorize:
raise ExtractorError(xml_text(authorize, 'details'), expected=True)
authz_token = unescapeHTML(xml_text(authorize, 'authzToken'))
requestor_info[guid] = authz_token
self._downloader.cache.store(self._MVPD_CACHE, requestor_id, requestor_info)

View File

@ -4,15 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..compat import compat_xpath
from ..utils import (
ExtractorError,
int_or_none,
update_url_query,
xpath_element,
xpath_text,
)
@ -43,7 +38,8 @@ class AfreecaTVIE(InfoExtractor):
'uploader': 'dailyapril',
'uploader_id': 'dailyapril',
'upload_date': '20160503',
}
},
'skip': 'Video is gone',
}, {
'url': 'http://afbbs.afreecatv.com:8080/app/read_ucc_bbs.cgi?nStationNo=16711924&nTitleNo=36153164&szBjId=dailyapril&nBbsNo=18605867',
'info_dict': {
@ -71,6 +67,19 @@ class AfreecaTVIE(InfoExtractor):
'upload_date': '20160502',
},
}],
'skip': 'Video is gone',
}, {
'url': 'http://vod.afreecatv.com/PLAYER/STATION/18650793',
'info_dict': {
'id': '18650793',
'ext': 'flv',
'uploader': '윈아디',
'uploader_id': 'badkids',
'title': '오늘은 다르다! 쏘님의 우월한 위아래~ 댄스리액션!',
},
'params': {
'skip_download': True, # requires rtmpdump
},
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
@ -90,40 +99,33 @@ class AfreecaTVIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
parsed_url = compat_urllib_parse_urlparse(url)
info_url = compat_urlparse.urlunparse(parsed_url._replace(
netloc='afbbs.afreecatv.com:8080',
path='/api/video/get_video_info.php'))
video_xml = self._download_xml(
update_url_query(info_url, {'nTitleNo': video_id}), video_id)
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, query={'nTitleNo': video_id})
if xpath_element(video_xml, './track/video/file') is None:
video_element = video_xml.findall(compat_xpath('./track/video'))[1]
if video_element is None or video_element.text is None:
raise ExtractorError('Specified AfreecaTV video does not exist',
expected=True)
title = xpath_text(video_xml, './track/title', 'title')
video_url_raw = video_element.text
app, playpath = video_url_raw.split('mp4:')
title = xpath_text(video_xml, './track/title', 'title', fatal=True)
uploader = xpath_text(video_xml, './track/nickname', 'uploader')
uploader_id = xpath_text(video_xml, './track/bj_id', 'uploader id')
duration = int_or_none(xpath_text(video_xml, './track/duration',
'duration'))
thumbnail = xpath_text(video_xml, './track/titleImage', 'thumbnail')
entries = []
for i, video_file in enumerate(video_xml.findall('./track/video/file')):
video_key = self.parse_video_key(video_file.get('key', ''))
if not video_key:
continue
entries.append({
'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
'title': title,
'upload_date': video_key.get('upload_date'),
'duration': int_or_none(video_file.get('duration')),
'url': video_file.text,
})
info = {
return {
'id': video_id,
'url': app,
'ext': 'flv',
'play_path': 'mp4:' + playpath,
'rtmp_live': True, # downloading won't end without this
'title': title,
'uploader': uploader,
'uploader_id': uploader_id,
@ -131,20 +133,6 @@ class AfreecaTVIE(InfoExtractor):
'thumbnail': thumbnail,
}
if len(entries) > 1:
info['_type'] = 'multi_video'
info['entries'] = entries
elif len(entries) == 1:
info['url'] = entries[0]['url']
info['upload_date'] = entries[0].get('upload_date')
else:
raise ExtractorError(
'No files found for the specified AfreecaTV video, either'
' the URL is incorrect or the video has been made private.',
expected=True)
return info
class AfreecaTVGlobalIE(AfreecaTVIE):
IE_NAME = 'afreecatv:global'

View File

@ -2,9 +2,13 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
remove_end,
int_or_none,
qualities,
remove_end,
try_get,
unified_timestamp,
url_basename,
)
@ -22,6 +26,10 @@ class AllocineIE(InfoExtractor):
'title': 'Astérix - Le Domaine des Dieux Teaser VF',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884',
'thumbnail': r're:http://.*\.jpg',
'duration': 39,
'timestamp': 1404273600,
'upload_date': '20140702',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19540403&cfilm=222257.html',
@ -33,6 +41,10 @@ class AllocineIE(InfoExtractor):
'title': 'Planes 2 Bande-annonce VF',
'description': 'Regardez la bande annonce du film Planes 2 (Planes 2 Bande-annonce VF). Planes 2, un film de Roberts Gannaway',
'thumbnail': r're:http://.*\.jpg',
'duration': 69,
'timestamp': 1385659800,
'upload_date': '20131128',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/player_gen_cmedia=19544709&cfilm=181290.html',
@ -44,6 +56,10 @@ class AllocineIE(InfoExtractor):
'title': 'Dragons 2 - Bande annonce finale VF',
'description': 'md5:6cdd2d7c2687d4c6aafe80a35e17267a',
'thumbnail': r're:http://.*\.jpg',
'duration': 144,
'timestamp': 1397589900,
'upload_date': '20140415',
'view_count': int,
},
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
@ -69,34 +85,37 @@ class AllocineIE(InfoExtractor):
r'data-model="([^"]+)"', webpage, 'data model', default=None)
if model:
model_data = self._parse_json(model, display_id)
for video_url in model_data['sources'].values():
video = model_data['videos'][0]
title = video['title']
for video_url in video['sources'].values():
video_id, format_id = url_basename(video_url).split('_')[:2]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': video_url,
})
title = model_data['title']
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
title = remove_end(
self._html_search_regex(
r'(?s)<title>(.+?)</title>', webpage, 'title').strip(),
' - AlloCiné')
for key, value in media_data['video'].items():
if not key.endswith('Path'):
continue
format_id = key[:-len('Path')]
formats.append({
'format_id': format_id,
'quality': quality(format_id),
'url': value,
})
title = remove_end(self._html_search_regex(
r'(?s)<title>(.+?)</title>', webpage, 'title'
).strip(), ' - AlloCiné')
duration, view_count, timestamp = [None] * 3
self._sort_formats(formats)
@ -104,7 +123,10 @@ class AllocineIE(InfoExtractor):
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'duration': duration,
'timestamp': timestamp,
'view_count': view_count,
'formats': formats,
}

View File

@ -10,7 +10,7 @@ from ..utils import (
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies/|shows/[^/]+/(?:full-episodes/)?[^/]+/episode-\d+(?:-(?:[^/]+/)?|/))(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
@ -44,6 +44,12 @@ class AMCNetworksIE(ThePlatformIE):
}, {
'url': 'http://www.bbcamerica.com/shows/doctor-who/full-episodes/the-power-of-the-daleks/episode-01-episode-1-color-version',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/mama-june-from-not-to-hot/full-episode/season-01/thin-tervention',
'only_matching': True,
}, {
'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -93,8 +93,7 @@ class ArkenaIE(InfoExtractor):
exts = (mimetype2ext(f.get('Type')), determine_ext(f_url, None))
if kind == 'm3u8' or 'm3u8' in exts:
formats.extend(self._extract_m3u8_formats(
f_url, video_id, 'mp4',
entry_protocol='m3u8' if is_live else 'm3u8_native',
f_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=kind, fatal=False, live=is_live))
elif kind == 'flash' or 'f4m' in exts:
formats.extend(self._extract_f4m_formats(

View File

@ -90,7 +90,8 @@ class AtresPlayerIE(InfoExtractor):
request, None, 'Logging in as %s' % username)
error = self._html_search_regex(
r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',
response, 'error', default=None)
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
@ -155,13 +156,17 @@ class AtresPlayerIE(InfoExtractor):
if format_id == 'token' or not video_url.startswith('http'):
continue
if 'geodeswowsmpra3player' in video_url:
f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
# f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
# f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
# this videos are protected by DRM, the f4m downloader doesn't support them
continue
else:
f4m_url = video_url[:-9] + '/manifest.f4m'
formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
video_url_hd = video_url.replace('free_es', 'es')
formats.extend(self._extract_f4m_formats(
video_url_hd[:-9] + '/manifest.f4m', video_id, f4m_id='hds',
fatal=False))
formats.extend(self._extract_mpd_formats(
video_url_hd[:-9] + '/manifest.mpd', video_id, mpd_id='dash',
fatal=False))
self._sort_formats(formats)
path_data = player.get('pathData')

View File

@ -0,0 +1,73 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
unescapeHTML,
)
class ATVAtIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atv\.at/(?:[^/]+/){2}(?P<id>[dv]\d+)'
_TESTS = [{
'url': 'http://atv.at/aktuell/di-210317-2005-uhr/v1698449/',
'md5': 'c3b6b975fb3150fc628572939df205f2',
'info_dict': {
'id': '1698447',
'ext': 'mp4',
'title': 'DI, 21.03.17 | 20:05 Uhr 1/1',
}
}, {
'url': 'http://atv.at/aktuell/meinrad-knapp/d8416/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_data = self._parse_json(unescapeHTML(self._search_regex(
r'class="[^"]*jsb_video/FlashPlayer[^"]*"[^>]+data-jsb="([^"]+)"',
webpage, 'player data')), display_id)['config']['initial_video']
video_id = video_data['id']
video_title = video_data['title']
parts = []
for part in video_data.get('parts', []):
part_id = part['id']
part_title = part['title']
formats = []
for source in part.get('sources', []):
source_url = source.get('src')
if not source_url:
continue
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, part_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': source.get('delivery'),
'url': source_url,
})
self._sort_formats(formats)
parts.append({
'id': part_id,
'title': part_title,
'thumbnail': part.get('preview_image_url'),
'duration': int_or_none(part.get('duration')),
'is_live': part.get('is_livestream'),
'formats': formats,
})
return {
'_type': 'multi_video',
'id': video_id,
'title': video_title,
'entries': parts,
}

View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -5,6 +6,7 @@ import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
get_element_by_class,
get_element_by_id,
strip_or_none,
urljoin,
@ -170,3 +172,42 @@ class AZMedienPlaylistIE(AZMedienBaseIE):
'video-title', webpage)), group='title')
return self.playlist_result(entries, show_id, title)
class AZMedienShowPlaylistIE(AZMedienBaseIE):
IE_DESC = 'AZ Medien show playlists'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:
telezueri\.ch|
telebaern\.tv|
telem1\.ch
)/
(?:
all-episodes|
alle-episoden
)/
(?P<id>[^/?#&]+)
'''
_TEST = {
'url': 'http://www.telezueri.ch/all-episodes/astrotalk',
'info_dict': {
'id': 'astrotalk',
'title': 'TeleZüri: AstroTalk - alle episoden',
'description': 'md5:4c0f7e7d741d906004266e295ceb4a26',
},
'playlist_mincount': 13,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
episodes = get_element_by_class('search-mobile-box', webpage)
entries = [self.url_result(
urljoin(url, m.group('url'))) for m in re.finditer(
r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1', episodes)]
title = self._og_search_title(webpage, fatal=False)
description = self._og_search_description(webpage)
return self.playlist_result(entries, playlist_id, title, description)

View File

@ -21,10 +21,11 @@ class BellMediaIE(InfoExtractor):
animalplanet|
bravo|
mtv|
space
space|
etalk
)\.ca|
much\.com
)/.*?(?:\bvid=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
)/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'http://www.ctv.ca/video/player?vid=706966',
'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
@ -58,6 +59,9 @@ class BellMediaIE(InfoExtractor):
}, {
'url': 'http://www.ctv.ca/DCs-Legends-of-Tomorrow/Video/S2E11-Turncoat-vid1051430',
'only_matching': True,
}, {
'url': 'http://www.etalk.ca/video?videoid=663455',
'only_matching': True,
}]
_DOMAINS = {
'thecomedynetwork': 'comedy',
@ -65,6 +69,7 @@ class BellMediaIE(InfoExtractor):
'sciencechannel': 'discsci',
'investigationdiscovery': 'invdisc',
'animalplanet': 'aniplan',
'etalk': 'ctv',
}
def _real_extract(self, url):

View File

@ -0,0 +1,72 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
)
class BostonGlobeIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
_TESTS = [
{
'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
'md5': '0a62181079c85c2d2b618c9a738aedaf',
'info_dict': {
'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
'id': '5320421710001',
'ext': 'mp4',
'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
'timestamp': 1486877593,
'upload_date': '20170212',
'uploader_id': '245991542',
},
},
{
# Embedded youtube video; we hand it off to the Generic extractor.
'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
'md5': '582b40327089d5c0c949b3c54b13c24b',
'info_dict': {
'title': "Who Is Matt Damon's Favorite Batman?",
'id': 'ZW1QCnlA6Qc',
'ext': 'mp4',
'upload_date': '20170217',
'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
'uploader': 'The Late Late Show with James Corden',
'uploader_id': 'TheLateLateShow',
},
'expected_warnings': ['404'],
},
]
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
page_title = self._og_search_title(webpage, default=None)
# <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
entries = []
for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
attrs = extract_attributes(video)
video_id = attrs.get('data-brightcove-video-id')
account_id = attrs.get('data-account')
player_id = attrs.get('data-player')
embed = attrs.get('data-embed')
if video_id and account_id and player_id and embed:
entries.append(
'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
% (account_id, player_id, embed, video_id))
if len(entries) == 0:
return self.url_result(url, 'Generic')
elif len(entries) == 1:
return self.url_result(entries[0], 'BrightcoveNew')
else:
return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')

View File

@ -193,7 +193,13 @@ class BrightcoveLegacyIE(InfoExtractor):
if videoPlayer is not None:
if isinstance(videoPlayer, list):
videoPlayer = videoPlayer[0]
if not (videoPlayer.isdigit() or videoPlayer.startswith('ref:')):
videoPlayer = videoPlayer.strip()
# UUID is also possible for videoPlayer (e.g.
# http://www.popcornflix.com/hoodies-vs-hooligans/7f2d2b87-bbf2-4623-acfb-ea942b4f01dd
# or http://www8.hp.com/cn/zh/home.html)
if not (re.match(
r'^(?:\d+|[\da-fA-F]{8}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{4}-?[\da-fA-F]{12})$',
videoPlayer) or videoPlayer.startswith('ref:')):
return None
params['@videoPlayer'] = videoPlayer
linkBase = find_param('linkBaseURL')
@ -515,6 +521,9 @@ class BrightcoveNewIE(InfoExtractor):
return entries
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
@ -544,8 +553,10 @@ class BrightcoveNewIE(InfoExtractor):
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
raise ExtractorError(
json_data.get('message') or json_data['error_code'], expected=True)
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message, expected=True)
raise
title = json_data['name'].strip()

View File

@ -1,6 +1,7 @@
# coding: utf-8
from __future__ import unicode_literals
import codecs
import re
from .common import InfoExtractor
@ -96,6 +97,10 @@ class CDAIE(InfoExtractor):
if not video or 'file' not in video:
self.report_warning('Unable to extract %s version information' % version)
return
if video['file'].startswith('uggc'):
video['file'] = codecs.decode(video['file'], 'rot_13')
if video['file'].endswith('adc.mp4'):
video['file'] = video['file'].replace('adc.mp4', '.mp4')
f = {
'url': video['file'],
}

View File

@ -160,8 +160,7 @@ class CeskaTelevizeIE(InfoExtractor):
for format_id, stream_url in item.get('streamUrls', {}).items():
if 'playerType=flash' in stream_url:
stream_formats = self._extract_m3u8_formats(
stream_url, playlist_id, 'mp4',
entry_protocol='m3u8' if is_live else 'm3u8_native',
stream_url, playlist_id, 'mp4', 'm3u8_native',
m3u8_id='hls-%s' % format_id, fatal=False)
else:
stream_formats = self._extract_mpd_formats(

View File

@ -4,62 +4,62 @@ import re
from .common import InfoExtractor
from ..utils import (
clean_html,
ExtractorError,
parse_filesize,
int_or_none,
parse_iso8601,
qualities,
unescapeHTML,
)
class Channel9IE(InfoExtractor):
'''
Common extractor for channel9.msdn.com.
The type of provided URL (video or playlist) is determined according to
meta Search.PageType from web page HTML rather than URL itself, as it is
not always possible to do.
'''
IE_DESC = 'Channel 9'
IE_NAME = 'channel9'
_VALID_URL = r'https?://(?:www\.)?channel9\.msdn\.com/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
_VALID_URL = r'https?://(?:www\.)?(?:channel9\.msdn\.com|s\.ch9\.ms)/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
_TESTS = [{
'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
'md5': 'bbd75296ba47916b754e73c3a4bbdf10',
'md5': '32083d4eaf1946db6d454313f44510ca',
'info_dict': {
'id': 'Events/TechEd/Australia/2013/KOS002',
'ext': 'mp4',
'id': '6c413323-383a-49dc-88f9-a22800cab024',
'ext': 'wmv',
'title': 'Developer Kick-Off Session: Stuff We Love',
'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
'description': 'md5:b80bf9355a503c193aff7ec6cd5a7731',
'duration': 4576,
'thumbnail': r're:http://.*\.jpg',
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1377717420,
'upload_date': '20130828',
'session_code': 'KOS002',
'session_day': 'Day 1',
'session_room': 'Arena 1A',
'session_speakers': ['Ed Blankenship', 'Andrew Coates', 'Brady Gaster', 'Patrick Klug',
'Mads Kristensen'],
'session_speakers': ['Andrew Coates', 'Brady Gaster', 'Mads Kristensen', 'Ed Blankenship', 'Patrick Klug'],
},
}, {
'url': 'http://channel9.msdn.com/posts/Self-service-BI-with-Power-BI-nuclear-testing',
'md5': 'b43ee4529d111bc37ba7ee4f34813e68',
'md5': 'dcf983ee6acd2088e7188c3cf79b46bc',
'info_dict': {
'id': 'posts/Self-service-BI-with-Power-BI-nuclear-testing',
'ext': 'mp4',
'id': 'fe8e435f-bb93-4e01-8e97-a28c01887024',
'ext': 'wmv',
'title': 'Self-service BI with Power BI - nuclear testing',
'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
'description': 'md5:2d17fec927fc91e9e17783b3ecc88f54',
'duration': 1540,
'thumbnail': r're:http://.*\.jpg',
'thumbnail': r're:https?://.*\.jpg',
'timestamp': 1386381991,
'upload_date': '20131207',
'authors': ['Mike Wilmot'],
},
}, {
# low quality mp4 is best
'url': 'https://channel9.msdn.com/Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
'info_dict': {
'id': 'Events/CPP/CppCon-2015/Ranges-for-the-Standard-Library',
'id': '33ad69d2-6a4e-4172-83a1-a523013dec76',
'ext': 'mp4',
'title': 'Ranges for the Standard Library',
'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
'description': 'md5:9895e0a9fd80822d2f01c454b8f4a372',
'duration': 5646,
'thumbnail': r're:http://.*\.jpg',
'thumbnail': r're:https?://.*\.jpg',
'upload_date': '20150930',
'timestamp': 1443640735,
},
'params': {
'skip_download': True,
@ -70,7 +70,7 @@ class Channel9IE(InfoExtractor):
'id': 'Niners/Splendid22/Queue/76acff796e8f411184b008028e0d492b',
'title': 'Channel 9',
},
'playlist_count': 2,
'playlist_mincount': 100,
}, {
'url': 'https://channel9.msdn.com/Events/DEVintersection/DEVintersection-2016/RSS',
'only_matching': True,
@ -81,189 +81,6 @@ class Channel9IE(InfoExtractor):
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
def _formats_from_html(self, html):
FORMAT_REGEX = r'''
(?x)
<a\s+href="(?P<url>[^"]+)">(?P<quality>[^<]+)</a>\s*
<span\s+class="usage">\((?P<note>[^\)]+)\)</span>\s*
(?:<div\s+class="popup\s+rounded">\s*
<h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
</div>)? # File size part may be missing
'''
quality = qualities((
'MP3', 'MP4',
'Low Quality WMV', 'Low Quality MP4',
'Mid Quality WMV', 'Mid Quality MP4',
'High Quality WMV', 'High Quality MP4'))
formats = [{
'url': x.group('url'),
'format_id': x.group('quality'),
'format_note': x.group('note'),
'format': '%s (%s)' % (x.group('quality'), x.group('note')),
'filesize_approx': parse_filesize(x.group('filesize')),
'quality': quality(x.group('quality')),
'vcodec': 'none' if x.group('note') == 'Audio only' else None,
} for x in list(re.finditer(FORMAT_REGEX, html))]
self._sort_formats(formats)
return formats
def _extract_title(self, html):
title = self._html_search_meta('title', html, 'title')
if title is None:
title = self._og_search_title(html)
TITLE_SUFFIX = ' (Channel 9)'
if title is not None and title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
return title
def _extract_description(self, html):
DESCRIPTION_REGEX = r'''(?sx)
<div\s+class="entry-content">\s*
<div\s+id="entry-body">\s*
(?P<description>.+?)\s*
</div>\s*
</div>
'''
m = re.search(DESCRIPTION_REGEX, html)
if m is not None:
return m.group('description')
return self._html_search_meta('description', html, 'description')
def _extract_duration(self, html):
m = re.search(r'"length": *"(?P<hours>\d{2}):(?P<minutes>\d{2}):(?P<seconds>\d{2})"', html)
return ((int(m.group('hours')) * 60 * 60) + (int(m.group('minutes')) * 60) + int(m.group('seconds'))) if m else None
def _extract_slides(self, html):
m = re.search(r'<a href="(?P<slidesurl>[^"]+)" class="slides">Slides</a>', html)
return m.group('slidesurl') if m is not None else None
def _extract_zip(self, html):
m = re.search(r'<a href="(?P<zipurl>[^"]+)" class="zip">Zip</a>', html)
return m.group('zipurl') if m is not None else None
def _extract_avg_rating(self, html):
m = re.search(r'<p class="avg-rating">Avg Rating: <span>(?P<avgrating>[^<]+)</span></p>', html)
return float(m.group('avgrating')) if m is not None else 0
def _extract_rating_count(self, html):
m = re.search(r'<div class="rating-count">\((?P<ratingcount>[^<]+)\)</div>', html)
return int(self._fix_count(m.group('ratingcount'))) if m is not None else 0
def _extract_view_count(self, html):
m = re.search(r'<li class="views">\s*<span class="count">(?P<viewcount>[^<]+)</span> Views\s*</li>', html)
return int(self._fix_count(m.group('viewcount'))) if m is not None else 0
def _extract_comment_count(self, html):
m = re.search(r'<li class="comments">\s*<a href="#comments">\s*<span class="count">(?P<commentcount>[^<]+)</span> Comments\s*</a>\s*</li>', html)
return int(self._fix_count(m.group('commentcount'))) if m is not None else 0
def _fix_count(self, count):
return int(str(count).replace(',', '')) if count is not None else None
def _extract_authors(self, html):
m = re.search(r'(?s)<li class="author">(.*?)</li>', html)
if m is None:
return None
return re.findall(r'<a href="/Niners/[^"]+">([^<]+)</a>', m.group(1))
def _extract_session_code(self, html):
m = re.search(r'<li class="code">\s*(?P<code>.+?)\s*</li>', html)
return m.group('code') if m is not None else None
def _extract_session_day(self, html):
m = re.search(r'<li class="day">\s*<a href="/Events/[^"]+">(?P<day>[^<]+)</a>\s*</li>', html)
return m.group('day').strip() if m is not None else None
def _extract_session_room(self, html):
m = re.search(r'<li class="room">\s*(?P<room>.+?)\s*</li>', html)
return m.group('room') if m is not None else None
def _extract_session_speakers(self, html):
return re.findall(r'<a href="/Events/Speakers/[^"]+">([^<]+)</a>', html)
def _extract_content(self, html, content_path):
# Look for downloadable content
formats = self._formats_from_html(html)
slides = self._extract_slides(html)
zip_ = self._extract_zip(html)
# Nothing to download
if len(formats) == 0 and slides is None and zip_ is None:
self._downloader.report_warning('None of recording, slides or zip are available for %s' % content_path)
return
# Extract meta
title = self._extract_title(html)
description = self._extract_description(html)
thumbnail = self._og_search_thumbnail(html)
duration = self._extract_duration(html)
avg_rating = self._extract_avg_rating(html)
rating_count = self._extract_rating_count(html)
view_count = self._extract_view_count(html)
comment_count = self._extract_comment_count(html)
common = {
'_type': 'video',
'id': content_path,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'avg_rating': avg_rating,
'rating_count': rating_count,
'view_count': view_count,
'comment_count': comment_count,
}
result = []
if slides is not None:
d = common.copy()
d.update({'title': title + '-Slides', 'url': slides})
result.append(d)
if zip_ is not None:
d = common.copy()
d.update({'title': title + '-Zip', 'url': zip_})
result.append(d)
if len(formats) > 0:
d = common.copy()
d.update({'title': title, 'formats': formats})
result.append(d)
return result
def _extract_entry_item(self, html, content_path):
contents = self._extract_content(html, content_path)
if contents is None:
return contents
if len(contents) > 1:
raise ExtractorError('Got more than one entry')
result = contents[0]
result['authors'] = self._extract_authors(html)
return result
def _extract_session(self, html, content_path):
contents = self._extract_content(html, content_path)
if contents is None:
return contents
session_meta = {
'session_code': self._extract_session_code(html),
'session_day': self._extract_session_day(html),
'session_room': self._extract_session_room(html),
'session_speakers': self._extract_session_speakers(html),
}
for content in contents:
content.update(session_meta)
return self.playlist_result(contents)
def _extract_list(self, video_id, rss_url=None):
if not rss_url:
rss_url = self._RSS_URL % video_id
@ -274,9 +91,7 @@ class Channel9IE(InfoExtractor):
return self.playlist_result(entries, video_id, title_text)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
content_path = mobj.group('contentpath')
rss = mobj.group('rss')
content_path, rss = re.match(self._VALID_URL, url).groups()
if rss:
return self._extract_list(content_path, url)
@ -284,17 +99,158 @@ class Channel9IE(InfoExtractor):
webpage = self._download_webpage(
url, content_path, 'Downloading web page')
page_type = self._search_regex(
r'<meta[^>]+name=(["\'])WT\.entryid\1[^>]+content=(["\'])(?P<pagetype>[^:]+).+?\2',
webpage, 'page type', default=None, group='pagetype')
if page_type:
if page_type == 'Entry': # Any 'item'-like page, may contain downloadable content
return self._extract_entry_item(webpage, content_path)
elif page_type == 'Session': # Event session page, may contain downloadable content
return self._extract_session(webpage, content_path)
elif page_type == 'Event':
return self._extract_list(content_path)
episode_data = self._search_regex(
r"data-episode='([^']+)'", webpage, 'episode data', default=None)
if episode_data:
episode_data = self._parse_json(unescapeHTML(
episode_data), content_path)
content_id = episode_data['contentId']
is_session = '/Sessions(' in episode_data['api']
content_url = 'https://channel9.msdn.com/odata' + episode_data['api']
if is_session:
content_url += '?$expand=Speakers'
else:
content_url += '?$expand=Authors'
content_data = self._download_json(content_url, content_id)
title = content_data['Title']
QUALITIES = (
'mp3',
'wmv', 'mp4',
'wmv-low', 'mp4-low',
'wmv-mid', 'mp4-mid',
'wmv-high', 'mp4-high',
)
quality_key = qualities(QUALITIES)
def quality(quality_id, format_url):
return (len(QUALITIES) if '_Source.' in format_url
else quality_key(quality_id))
formats = []
urls = set()
SITE_QUALITIES = {
'MP3': 'mp3',
'MP4': 'mp4',
'Low Quality WMV': 'wmv-low',
'Low Quality MP4': 'mp4-low',
'Mid Quality WMV': 'wmv-mid',
'Mid Quality MP4': 'mp4-mid',
'High Quality WMV': 'wmv-high',
'High Quality MP4': 'mp4-high',
}
formats_select = self._search_regex(
r'(?s)<select[^>]+name=["\']format[^>]+>(.+?)</select', webpage,
'formats select', default=None)
if formats_select:
for mobj in re.finditer(
r'<option\b[^>]+\bvalue=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*(?P<format>[^<]+?)\s*<',
formats_select):
format_url = mobj.group('url')
if format_url in urls:
continue
urls.add(format_url)
format_id = mobj.group('format')
quality_id = SITE_QUALITIES.get(format_id, format_id)
formats.append({
'url': format_url,
'format_id': quality_id,
'quality': quality(quality_id, format_url),
'vcodec': 'none' if quality_id == 'mp3' else None,
})
API_QUALITIES = {
'VideoMP4Low': 'mp4-low',
'VideoWMV': 'wmv-mid',
'VideoMP4Medium': 'mp4-mid',
'VideoMP4High': 'mp4-high',
'VideoWMVHQ': 'wmv-hq',
}
for format_id, q in API_QUALITIES.items():
q_url = content_data.get(format_id)
if not q_url or q_url in urls:
continue
urls.add(q_url)
formats.append({
'url': q_url,
'format_id': q,
'quality': quality(q, q_url),
})
self._sort_formats(formats)
slides = content_data.get('Slides')
zip_file = content_data.get('ZipFile')
if not formats and not slides and not zip_file:
raise ExtractorError(
'None of recording, slides or zip are available for %s' % content_path)
subtitles = {}
for caption in content_data.get('Captions', []):
caption_url = caption.get('Url')
if not caption_url:
continue
subtitles.setdefault(caption.get('Language', 'en'), []).append({
'url': caption_url,
'ext': 'vtt',
})
common = {
'id': content_id,
'title': title,
'description': clean_html(content_data.get('Description') or content_data.get('Body')),
'thumbnail': content_data.get('Thumbnail') or content_data.get('VideoPlayerPreviewImage'),
'duration': int_or_none(content_data.get('MediaLengthInSeconds')),
'timestamp': parse_iso8601(content_data.get('PublishedDate')),
'avg_rating': int_or_none(content_data.get('Rating')),
'rating_count': int_or_none(content_data.get('RatingCount')),
'view_count': int_or_none(content_data.get('Views')),
'comment_count': int_or_none(content_data.get('CommentCount')),
'subtitles': subtitles,
}
if is_session:
speakers = []
for s in content_data.get('Speakers', []):
speaker_name = s.get('FullName')
if not speaker_name:
continue
speakers.append(speaker_name)
common.update({
'session_code': content_data.get('Code'),
'session_room': content_data.get('Room'),
'session_speakers': speakers,
})
else:
authors = []
for a in content_data.get('Authors', []):
author_name = a.get('DisplayName')
if not author_name:
continue
authors.append(author_name)
common['authors'] = authors
contents = []
if slides:
d = common.copy()
d.update({'title': title + '-Slides', 'url': slides})
contents.append(d)
if zip_file:
d = common.copy()
d.update({'title': title + '-Zip', 'url': zip_file})
contents.append(d)
if formats:
d = common.copy()
d.update({'title': title, 'formats': formats})
contents.append(d)
return self.playlist_result(contents)
else:
raise ExtractorError('Unexpected WT.entryid %s' % page_type, expected=True)
else: # Assuming list
return self._extract_list(content_path)

View File

@ -1,97 +1,56 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_HTTPError,
)
from ..utils import (
ExtractorError,
HEADRequest,
remove_end,
str_to_int,
unified_strdate,
)
class CloudyIE(InfoExtractor):
_IE_DESC = 'cloudy.ec'
_VALID_URL = r'''(?x)
https?://(?:www\.)?cloudy\.ec/
(?:v/|embed\.php\?id=)
(?P<id>[A-Za-z0-9]+)
'''
_EMBED_URL = 'http://www.cloudy.ec/embed.php?id=%s'
_API_URL = 'http://www.cloudy.ec/api/player.api.php'
_MAX_TRIES = 2
_TEST = {
_VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
_TESTS = [{
'url': 'https://www.cloudy.ec/v/af511e2527aac',
'md5': '5cb253ace826a42f35b4740539bedf07',
'md5': '29832b05028ead1b58be86bf319397ca',
'info_dict': {
'id': 'af511e2527aac',
'ext': 'flv',
'ext': 'mp4',
'title': 'Funny Cats and Animals Compilation june 2013',
'upload_date': '20130913',
'view_count': int,
}
}
def _extract_video(self, video_id, file_key, error_url=None, try_num=0):
if try_num > self._MAX_TRIES - 1:
raise ExtractorError('Unable to extract video URL', expected=True)
form = {
'file': video_id,
'key': file_key,
}
if error_url:
form.update({
'numOfErrors': try_num,
'errorCode': '404',
'errorUrl': error_url,
})
player_data = self._download_webpage(
self._API_URL, video_id, 'Downloading player data', query=form)
data = compat_parse_qs(player_data)
try_num += 1
if 'error' in data:
raise ExtractorError(
'%s error: %s' % (self.IE_NAME, ' '.join(data['error_msg'])),
expected=True)
title = data.get('title', [None])[0]
if title:
title = remove_end(title, '&asdasdas').strip()
video_url = data.get('url', [None])[0]
if video_url:
try:
self._request_webpage(HEADRequest(video_url), video_id, 'Checking video URL')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in [404, 410]:
self.report_warning('Invalid video URL, requesting another', video_id)
return self._extract_video(video_id, file_key, video_url, try_num)
return {
'id': video_id,
'url': video_url,
'title': title,
}
}, {
'url': 'http://www.cloudy.ec/embed.php?autoplay=1&id=af511e2527aac',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
url = self._EMBED_URL % video_id
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(
'http://www.cloudy.ec/embed.php?id=%s' % video_id, video_id)
file_key = self._search_regex(
[r'key\s*:\s*"([^"]+)"', r'filekey\s*=\s*"([^"]+)"'],
webpage, 'file_key')
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
return self._extract_video(video_id, file_key)
webpage = self._download_webpage(
'https://www.cloudy.ec/v/%s' % video_id, video_id, fatal=False)
if webpage:
info.update({
'title': self._search_regex(
r'<h\d[^>]*>([^<]+)<', webpage, 'title'),
'upload_date': unified_strdate(self._search_regex(
r'>Published at (\d{4}-\d{1,2}-\d{1,2})', webpage,
'upload date', fatal=False)),
'view_count': str_to_int(self._search_regex(
r'([\d,.]+) views<', webpage, 'view count', fatal=False)),
})
if not info.get('title'):
info['title'] = video_id
info['id'] = video_id
return info

View File

@ -36,34 +36,35 @@ from ..utils import (
clean_html,
compiled_regex_type,
determine_ext,
determine_protocol,
error_to_compat_str,
ExtractorError,
extract_attributes,
fix_xml_ampersands,
float_or_none,
GeoRestrictedError,
GeoUtils,
int_or_none,
js_to_json,
mimetype2ext,
orderedSet,
parse_codecs,
parse_duration,
parse_iso8601,
parse_m3u8_attributes,
RegexNotFoundError,
sanitize_filename,
sanitized_Request,
sanitize_filename,
unescapeHTML,
unified_strdate,
unified_timestamp,
update_Request,
update_url_query,
urljoin,
url_basename,
xpath_element,
xpath_text,
xpath_with_ns,
determine_protocol,
parse_duration,
mimetype2ext,
update_Request,
update_url_query,
parse_m3u8_attributes,
extract_attributes,
parse_codecs,
urljoin,
)
@ -714,6 +715,13 @@ class InfoExtractor(object):
video_info['title'] = video_title
return video_info
def playlist_from_matches(self, matches, video_id, video_title, getter=None, ie=None):
urlrs = orderedSet(
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
for m in matches)
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
@staticmethod
def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None):
"""Returns a playlist"""
@ -2010,7 +2018,7 @@ class InfoExtractor(object):
})
return formats
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None):
def absolute_url(video_url):
return compat_urlparse.urljoin(base_url, video_url)
@ -2032,7 +2040,8 @@ class InfoExtractor(object):
is_plain_url = False
formats = self._extract_m3u8_formats(
full_url, video_id, ext='mp4',
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id)
entry_protocol=m3u8_entry_protocol, m3u8_id=m3u8_id,
preference=preference)
elif ext == 'mpd':
is_plain_url = False
formats = self._extract_mpd_formats(
@ -2160,18 +2169,24 @@ class InfoExtractor(object):
})
return formats
@staticmethod
def _find_jwplayer_data(webpage):
def _find_jwplayer_data(self, webpage, video_id=None, transform_source=js_to_json):
mobj = re.search(
r'jwplayer\((?P<quote>[\'"])[^\'" ]+(?P=quote)\)\.setup\s*\((?P<options>[^)]+)\)',
webpage)
if mobj:
return mobj.group('options')
try:
jwplayer_data = self._parse_json(mobj.group('options'),
video_id=video_id,
transform_source=transform_source)
except ExtractorError:
pass
else:
if isinstance(jwplayer_data, dict):
return jwplayer_data
def _extract_jwplayer_data(self, webpage, video_id, *args, **kwargs):
jwplayer_data = self._parse_json(
self._find_jwplayer_data(webpage), video_id,
transform_source=js_to_json)
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
return self._parse_jwplayer_data(
jwplayer_data, video_id, *args, **kwargs)
@ -2197,56 +2212,9 @@ class InfoExtractor(object):
this_video_id = video_id or video_data['mediaid']
formats = []
for source in video_data['sources']:
source_url = self._proto_relative_url(source['file'])
if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, this_video_id, 'mp4', 'm3u8_native', m3u8_id=m3u8_id, fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
source_url, this_video_id, mpd_id=mpd_id, fatal=False))
# https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
elif source_type.startswith('audio') or ext in ('oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
formats.append({
'url': source_url,
'vcodec': 'none',
'ext': ext,
})
else:
height = int_or_none(source.get('height'))
if height is None:
# Often no height is provided but there is a label in
# format like 1080p.
height = int_or_none(self._search_regex(
r'^(\d{3,})[pP]$', source.get('label') or '',
'height', default=None))
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
'height': height,
'ext': ext,
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv'
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
rtmp_url_parts = re.split(
r'((?:mp4|mp3|flv):)', source_url, 1)
if len(rtmp_url_parts) == 3:
rtmp_url, prefix, play_path = rtmp_url_parts
a_format.update({
'url': rtmp_url,
'play_path': prefix + play_path,
})
if rtmp_params:
a_format.update(rtmp_params)
formats.append(a_format)
formats = self._parse_jwplayer_formats(
video_data['sources'], video_id=this_video_id, m3u8_id=m3u8_id,
mpd_id=mpd_id, rtmp_params=rtmp_params, base_url=base_url)
self._sort_formats(formats)
subtitles = {}
@ -2277,6 +2245,65 @@ class InfoExtractor(object):
else:
return self.playlist_result(entries)
def _parse_jwplayer_formats(self, jwplayer_sources_data, video_id=None,
m3u8_id=None, mpd_id=None, rtmp_params=None, base_url=None):
formats = []
for source in jwplayer_sources_data:
source_url = self._proto_relative_url(source['file'])
if base_url:
source_url = compat_urlparse.urljoin(base_url, source_url)
source_type = source.get('type') or ''
ext = mimetype2ext(source_type) or determine_ext(source_url)
if source_type == 'hls' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=m3u8_id, fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
source_url, video_id, mpd_id=mpd_id, fatal=False))
elif ext == 'smil':
formats.extend(self._extract_smil_formats(
source_url, video_id, fatal=False))
# https://github.com/jwplayer/jwplayer/blob/master/src/js/providers/default.js#L67
elif source_type.startswith('audio') or ext in (
'oga', 'aac', 'mp3', 'mpeg', 'vorbis'):
formats.append({
'url': source_url,
'vcodec': 'none',
'ext': ext,
})
else:
height = int_or_none(source.get('height'))
if height is None:
# Often no height is provided but there is a label in
# format like "1080p", "720p SD", or 1080.
height = int_or_none(self._search_regex(
r'^(\d{3,4})[pP]?(?:\b|$)', compat_str(source.get('label') or ''),
'height', default=None))
a_format = {
'url': source_url,
'width': int_or_none(source.get('width')),
'height': height,
'tbr': int_or_none(source.get('bitrate')),
'ext': ext,
}
if source_url.startswith('rtmp'):
a_format['ext'] = 'flv'
# See com/longtailvideo/jwplayer/media/RTMPMediaProvider.as
# of jwplayer.flash.swf
rtmp_url_parts = re.split(
r'((?:mp4|mp3|flv):)', source_url, 1)
if len(rtmp_url_parts) == 3:
rtmp_url, prefix, play_path = rtmp_url_parts
a_format.update({
'url': rtmp_url,
'play_path': prefix + play_path,
})
if rtmp_params:
a_format.update(rtmp_params)
formats.append(a_format)
return formats
def _live_title(self, name):
""" Generate the title for a live video """
now = datetime.datetime.now()

View File

@ -9,13 +9,14 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
orderedSet,
remove_end,
extract_attributes,
mimetype2ext,
determine_ext,
extract_attributes,
int_or_none,
js_to_json,
mimetype2ext,
orderedSet,
parse_iso8601,
remove_end,
)
@ -66,6 +67,16 @@ class CondeNastIE(InfoExtractor):
'upload_date': '20130314',
'timestamp': 1363219200,
}
}, {
'url': 'http://video.gq.com/watch/the-closer-with-keith-olbermann-the-only-true-surprise-trump-s-an-idiot?c=series',
'info_dict': {
'id': '58d1865bfd2e6126e2000015',
'ext': 'mp4',
'title': 'The Only True Surprise? Trumps an Idiot',
'uploader': 'gq',
'upload_date': '20170321',
'timestamp': 1490126427,
},
}, {
# JS embed
'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
@ -114,26 +125,33 @@ class CondeNastIE(InfoExtractor):
})
video_id = query['videoId']
video_info = None
info_page = self._download_webpage(
info_page = self._download_json(
'http://player.cnevids.com/player/video.js',
video_id, 'Downloading video info', query=query, fatal=False)
video_id, 'Downloading video info', fatal=False, query=query)
if info_page:
video_info = self._parse_json(self._search_regex(
r'loadCallback\(({.+})\)', info_page, 'video info'), video_id)['video']
else:
video_info = info_page.get('video')
if not video_info:
info_page = self._download_webpage(
'http://player.cnevids.com/player/loader.js',
video_id, 'Downloading loader info', query=query)
video_info = self._parse_json(self._search_regex(
r'var\s+video\s*=\s*({.+?});', info_page, 'video info'), video_id)
video_info = self._parse_json(
self._search_regex(
r'(?s)var\s+config\s*=\s*({.+?});', info_page, 'config'),
video_id, transform_source=js_to_json)['video']
title = video_info['title']
formats = []
for fdata in video_info.get('sources', [{}])[0]:
for fdata in video_info['sources']:
src = fdata.get('src')
if not src:
continue
ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
src, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
quality = fdata.get('quality')
formats.append({
'format_id': ext + ('-%s' % quality if quality else ''),
@ -169,7 +187,6 @@ class CondeNastIE(InfoExtractor):
path=remove_end(parsed_url.path, '.js').replace('/embedjs/', '/embed/')))
url_type = 'embed'
self.to_screen('Extracting from %s with the Condé Nast extractor' % self._SITES[site])
webpage = self._download_webpage(url, item_id)
if url_type == 'series':

View File

@ -177,6 +177,7 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'uploader': 'Kadokawa Pictures Inc.',
'upload_date': '20170118',
'series': "KONOSUBA -God's blessing on this wonderful world!",
'season': "KONOSUBA -God's blessing on this wonderful world! 2",
'season_number': 2,
'episode': 'Give Me Deliverance from this Judicial Injustice!',
'episode_number': 1,
@ -207,6 +208,38 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# Just test metadata extraction
'skip_download': True,
},
}, {
# make sure we can extract an uploader name that's not a link
'url': 'http://www.crunchyroll.com/hakuoki-reimeiroku/episode-1-dawn-of-the-divine-warriors-606899',
'info_dict': {
'id': '606899',
'ext': 'mp4',
'title': 'Hakuoki Reimeiroku Episode 1 Dawn of the Divine Warriors',
'description': 'Ryunosuke was left to die, but Serizawa-san asked him a simple question "Do you want to live?"',
'uploader': 'Geneon Entertainment',
'upload_date': '20120717',
},
'params': {
# just test metadata extraction
'skip_download': True,
},
}, {
# A video with a vastly different season name compared to the series name
'url': 'http://www.crunchyroll.com/nyarko-san-another-crawling-chaos/episode-1-test-590532',
'info_dict': {
'id': '590532',
'ext': 'mp4',
'title': 'Haiyoru! Nyaruani (ONA) Episode 1 Test',
'description': 'Mahiro and Nyaruko talk about official certification.',
'uploader': 'TV TOKYO',
'upload_date': '20120305',
'series': 'Nyarko-san: Another Crawling Chaos',
'season': 'Haiyoru! Nyaruani (ONA)',
},
'params': {
# Just test metadata extraction
'skip_download': True,
},
}]
_FORMAT_IDS = {
@ -357,7 +390,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
else:
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
webpage = self._download_webpage(
self._add_skip_wall(webpage_url), video_id,
headers=self.geo_verification_headers())
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
@ -388,8 +423,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
if video_upload_date:
video_upload_date = unified_strdate(video_upload_date)
video_uploader = self._html_search_regex(
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
'video_uploader', fatal=False)
# try looking for both an uploader that's a link and one that's not
[r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', r'<div>\s*Publisher:\s*<span>\s*(.+?)\s*</span>\s*</div>'],
webpage, 'video_uploader', fatal=False)
available_fmts = []
for a, fmt in re.findall(r'(<a[^>]+token=["\']showmedia\.([0-9]{3,4})p["\'][^>]+>)', webpage):
@ -475,7 +511,8 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
# webpage provide more accurate data than series_title from XML
series = self._html_search_regex(
r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
webpage, 'series', default=xpath_text(metadata, 'series_title'))
webpage, 'series', fatal=False)
season = xpath_text(metadata, 'series_title')
episode = xpath_text(metadata, 'episode_title')
episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
@ -492,6 +529,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
'uploader': video_uploader,
'upload_date': video_upload_date,
'series': series,
'season': season,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
@ -529,7 +567,9 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
webpage = self._download_webpage(
self._add_skip_wall(url), show_id,
headers=self.geo_verification_headers())
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')

View File

@ -82,6 +82,11 @@ class CWTVIE(InfoExtractor):
'url': quality_url,
'tbr': tbr,
})
video_metadata = video_data['assetFields']
ism_url = video_metadata.get('smoothStreamingUrl')
if ism_url:
formats.extend(self._extract_ism_formats(
ism_url, video_id, ism_id='mss', fatal=False))
self._sort_formats(formats)
thumbnails = [{
@ -90,8 +95,6 @@ class CWTVIE(InfoExtractor):
'height': image.get('height'),
} for image_id, image in video_data['images'].items() if image.get('uri')] if video_data.get('images') else None
video_metadata = video_data['assetFields']
subtitles = {
'en': [{
'url': video_metadata['UnicornCcUrl'],

View File

@ -282,9 +282,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
}
def _check_error(self, info):
error = info.get('error')
if info.get('error') is not None:
title = error['title']
# See https://developer.dailymotion.com/api#access-error
if error.get('code') == 'DM007':
self.raise_geo_restricted(msg=title)
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
'%s said: %s' % (self.IE_NAME, title), expected=True)
def _get_subtitles(self, video_id, webpage):
try:

View File

@ -0,0 +1,159 @@
from __future__ import unicode_literals
import base64
import json
import random
import re
from .common import InfoExtractor
from ..aes import (
aes_cbc_decrypt,
aes_cbc_encrypt,
)
from ..utils import (
bytes_to_intlist,
bytes_to_long,
clean_html,
ExtractorError,
intlist_to_bytes,
get_element_by_id,
js_to_json,
int_or_none,
long_to_bytes,
pkcs1pad,
remove_end,
)
class DaisukiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?daisuki\.net/[^/]+/[^/]+/[^/]+/watch\.[^.]+\.(?P<id>\d+)\.html'
_TEST = {
'url': 'http://www.daisuki.net/tw/en/anime/watch.TheIdolMasterCG.11213.html',
'info_dict': {
'id': '11213',
'ext': 'mp4',
'title': '#01 Who is in the pumpkin carriage? - THE IDOLM@STER CINDERELLA GIRLS',
'subtitles': {
'mul': [{
'ext': 'ttml',
}],
},
'creator': 'BANDAI NAMCO Entertainment',
},
'params': {
'skip_download': True, # AES-encrypted HLS stream
},
}
# The public key in PEM format can be found in clientlibs_anime_watch.min.js
_RSA_KEY = (0xc5524c25e8e14b366b3754940beeb6f96cb7e2feef0b932c7659a0c5c3bf173d602464c2df73d693b513ae06ff1be8f367529ab30bf969c5640522181f2a0c51ea546ae120d3d8d908595e4eff765b389cde080a1ef7f1bbfb07411cc568db73b7f521cedf270cbfbe0ddbc29b1ac9d0f2d8f4359098caffee6d07915020077d, 65537)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
flashvars = self._parse_json(self._search_regex(
r'(?s)var\s+flashvars\s*=\s*({.+?});', webpage, 'flashvars'),
video_id, transform_source=js_to_json)
iv = [0] * 16
data = {}
for key in ('device_cd', 'mv_id', 'ss1_prm', 'ss2_prm', 'ss3_prm', 'ss_id'):
data[key] = flashvars.get(key, '')
encrypted_rtn = None
# Some AES keys are rejected. Try it with different AES keys
for idx in range(5):
aes_key = [random.randint(0, 254) for _ in range(32)]
padded_aeskey = intlist_to_bytes(pkcs1pad(aes_key, 128))
n, e = self._RSA_KEY
encrypted_aeskey = long_to_bytes(pow(bytes_to_long(padded_aeskey), e, n))
init_data = self._download_json('http://www.daisuki.net/bin/bgn/init', video_id, query={
's': flashvars.get('s', ''),
'c': flashvars.get('ss3_prm', ''),
'e': url,
'd': base64.b64encode(intlist_to_bytes(aes_cbc_encrypt(
bytes_to_intlist(json.dumps(data)),
aes_key, iv))).decode('ascii'),
'a': base64.b64encode(encrypted_aeskey).decode('ascii'),
}, note='Downloading JSON metadata' + (' (try #%d)' % (idx + 1) if idx > 0 else ''))
if 'rtn' in init_data:
encrypted_rtn = init_data['rtn']
break
self._sleep(5, video_id)
if encrypted_rtn is None:
raise ExtractorError('Failed to fetch init data')
rtn = self._parse_json(
intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist(
base64.b64decode(encrypted_rtn)),
aes_key, iv)).decode('utf-8').rstrip('\0'),
video_id)
formats = self._extract_m3u8_formats(
rtn['play_url'], video_id, ext='mp4', entry_protocol='m3u8_native')
title = remove_end(self._og_search_title(webpage), ' - DAISUKI')
creator = self._html_search_regex(
r'Creator\s*:\s*([^<]+)', webpage, 'creator', fatal=False)
subtitles = {}
caption_url = rtn.get('caption_url')
if caption_url:
# mul: multiple languages
subtitles['mul'] = [{
'url': caption_url,
'ext': 'ttml',
}]
return {
'id': video_id,
'title': title,
'formats': formats,
'subtitles': subtitles,
'creator': creator,
}
class DaisukiPlaylistIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)daisuki\.net/[^/]+/[^/]+/[^/]+/detail\.(?P<id>[a-zA-Z0-9]+)\.html'
_TEST = {
'url': 'http://www.daisuki.net/tw/en/anime/detail.TheIdolMasterCG.html',
'info_dict': {
'id': 'TheIdolMasterCG',
'title': 'THE IDOLM@STER CINDERELLA GIRLS',
'description': 'md5:0f2c028a9339f7a2c7fbf839edc5c5d8',
},
'playlist_count': 26,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
episode_pattern = r'''(?sx)
<img[^>]+delay="[^"]+/(\d+)/movie\.jpg".+?
<p[^>]+class=".*?\bepisodeNumber\b.*?">(?:<a[^>]+>)?([^<]+)'''
entries = [{
'_type': 'url_transparent',
'url': url.replace('detail', 'watch').replace('.html', '.' + movie_id + '.html'),
'episode_id': episode_id,
'episode_number': int_or_none(episode_id),
} for movie_id, episode_id in re.findall(episode_pattern, webpage)]
playlist_title = remove_end(
self._og_search_title(webpage, fatal=False), ' - Anime - DAISUKI')
playlist_description = clean_html(get_element_by_id('synopsisTxt', webpage))
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)

View File

@ -1,17 +1,21 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
extract_attributes,
ExtractorError,
int_or_none,
parse_age_limit,
ExtractorError,
remove_end,
unescapeHTML,
)
class DiscoveryGoIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(?:www\.)?(?:
class DiscoveryGoBaseIE(InfoExtractor):
_VALID_URL_TEMPLATE = r'''(?x)https?://(?:www\.)?(?:
discovery|
investigationdiscovery|
discoverylife|
@ -21,18 +25,23 @@ class DiscoveryGoIE(InfoExtractor):
sciencechannel|
tlc|
velocitychannel
)go\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'''
)go\.com/%s(?P<id>[^/?#&]+)'''
class DiscoveryGoIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % r'(?:[^/]+/)+'
_GEO_COUNTRIES = ['US']
_TEST = {
'url': 'https://www.discoverygo.com/love-at-first-kiss/kiss-first-ask-questions-later/',
'url': 'https://www.discoverygo.com/bering-sea-gold/reaper-madness/',
'info_dict': {
'id': '57a33c536b66d1cd0345eeb1',
'id': '58c167d86b66d12f2addeb01',
'ext': 'mp4',
'title': 'Kiss First, Ask Questions Later!',
'description': 'md5:fe923ba34050eae468bffae10831cb22',
'duration': 2579,
'series': 'Love at First Kiss',
'season_number': 1,
'episode_number': 1,
'title': 'Reaper Madness',
'description': 'md5:09f2c625c99afb8946ed4fb7865f6e78',
'duration': 2519,
'series': 'Bering Sea Gold',
'season_number': 8,
'episode_number': 6,
'age_limit': 14,
},
}
@ -113,3 +122,46 @@ class DiscoveryGoIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
}
class DiscoveryGoPlaylistIE(DiscoveryGoBaseIE):
_VALID_URL = DiscoveryGoBaseIE._VALID_URL_TEMPLATE % ''
_TEST = {
'url': 'https://www.discoverygo.com/bering-sea-gold/',
'info_dict': {
'id': 'bering-sea-gold',
'title': 'Bering Sea Gold',
'description': 'md5:cc5c6489835949043c0cc3ad66c2fa0e',
},
'playlist_mincount': 6,
}
@classmethod
def suitable(cls, url):
return False if DiscoveryGoIE.suitable(url) else super(
DiscoveryGoPlaylistIE, cls).suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entries = []
for mobj in re.finditer(r'data-json=(["\'])(?P<json>{.+?})\1', webpage):
data = self._parse_json(
mobj.group('json'), display_id,
transform_source=unescapeHTML, fatal=False)
if not isinstance(data, dict) or data.get('type') != 'episode':
continue
episode_url = data.get('socialUrl')
if not episode_url:
continue
entries.append(self.url_result(
episode_url, ie=DiscoveryGoIE.ie_key(),
video_id=data.get('id')))
return self.playlist_result(
entries, display_id,
remove_end(self._og_search_title(
webpage, fatal=False), ' | Discovery GO'),
self._og_search_description(webpage))

View File

@ -9,13 +9,13 @@ from ..compat import (
compat_parse_qs,
compat_urlparse,
)
from ..utils import smuggle_url
class TlcDeIE(InfoExtractor):
IE_NAME = 'tlc.de'
_VALID_URL = r'https?://(?:www\.)?tlc\.de/(?:[^/]+/)*videos/(?P<title>[^/?#]+)?(?:.*#(?P<id>\d+))?'
class DiscoveryNetworksDeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:discovery|tlc|animalplanet|dmax)\.de/(?:.*#(?P<id>\d+)|(?:[^/]+/)*videos/(?P<title>[^/?#]+))'
_TEST = {
_TESTS = [{
'url': 'http://www.tlc.de/sendungen/breaking-amish/videos/#3235167922001',
'info_dict': {
'id': '3235167922001',
@ -29,7 +29,13 @@ class TlcDeIE(InfoExtractor):
'upload_date': '20140404',
'uploader_id': '1659832546',
},
}
}, {
'url': 'http://www.dmax.de/programme/storage-hunters-uk/videos/storage-hunters-uk-episode-6/',
'only_matching': True,
}, {
'url': 'http://www.discovery.de/#5332316765001',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1659832546/default_default/index.html?videoId=%s'
def _real_extract(self, url):
@ -39,5 +45,8 @@ class TlcDeIE(InfoExtractor):
title = mobj.group('title')
webpage = self._download_webpage(url, title)
brightcove_legacy_url = BrightcoveLegacyIE._extract_brightcove_url(webpage)
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(brightcove_legacy_url).query)['@videoPlayer'][0]
return self.url_result(self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, 'BrightcoveNew', brightcove_id)
brightcove_id = compat_parse_qs(compat_urlparse.urlparse(
brightcove_legacy_url).query)['@videoPlayer'][0]
return self.url_result(smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id, {'geo_countries': ['DE']}),
'BrightcoveNew', brightcove_id)

View File

@ -1,15 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import time
import uuid
import hashlib
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
unescapeHTML,
@ -25,7 +20,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732',
'display_id': 'iseven',
'ext': 'flv',
'title': 're:^清晨醒脑T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^清晨醒脑T-ARA根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅',
@ -56,7 +51,7 @@ class DouyuTVIE(InfoExtractor):
'id': '17732',
'display_id': '17732',
'ext': 'flv',
'title': 're:^清晨醒脑T-ara根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'title': 're:^清晨醒脑T-ARA根本停不下来! [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': r're:.*m7show@163\.com.*',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': '7师傅',
@ -74,10 +69,6 @@ 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)
@ -88,6 +79,7 @@ class DouyuTVIE(InfoExtractor):
room_id = self._html_search_regex(
r'"room_id\\?"\s*:\s*(\d+),', page, 'room id')
# Grab metadata from mobile API
room = self._download_json(
'http://m.douyu.com/html5/live?roomId=%s' % room_id, video_id,
note='Downloading room info')['data']
@ -96,38 +88,22 @@ class DouyuTVIE(InfoExtractor):
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(
'%s reported error %i' % (self.IE_NAME, error_code),
expected=True)
base_url = video_info['data']['rtmp_url']
live_path = video_info['data']['rtmp_live']
video_url = '%s/%s' % (base_url, live_path)
# Grab the URL from PC client API
# The m3u8 url from mobile API requires re-authentication every 5 minutes
tt = int(time.time())
signContent = 'lapi/live/thirdPart/getPlay/%s?aid=pcclient&rate=0&time=%d9TUk5fjjUjg9qIMH3sdnh' % (room_id, tt)
sign = hashlib.md5(signContent.encode('ascii')).hexdigest()
video_url = self._download_json(
'http://coapi.douyucdn.cn/lapi/live/thirdPart/getPlay/' + room_id,
video_id, note='Downloading video URL info',
query={'rate': 0}, headers={
'auth': sign,
'time': str(tt),
'aid': 'pcclient'
})['data']['live_url']
title = self._live_title(unescapeHTML(room['room_name']))
description = room.get('notice')
description = room.get('show_details')
thumbnail = room.get('room_src')
uploader = room.get('nickname')

View File

@ -6,37 +6,24 @@ import re
import time
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..compat import (
compat_urlparse,
compat_HTTPError,
)
from ..utils import (
USER_AGENTS,
ExtractorError,
int_or_none,
unified_strdate,
remove_end,
update_url_query,
)
class DPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?P<domain>it\.dplay\.com|www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?P<domain>www\.dplay\.(?:dk|se|no))/[^/]+/(?P<id>[^/?#]+)'
_TESTS = [{
# geo restricted, via direct unsigned hls URL
'url': 'http://it.dplay.com/take-me-out/stagione-1-episodio-25/',
'info_dict': {
'id': '1255600',
'display_id': 'stagione-1-episodio-25',
'ext': 'mp4',
'title': 'Episodio 25',
'description': 'md5:cae5f40ad988811b197d2d27a53227eb',
'duration': 2761,
'timestamp': 1454701800,
'upload_date': '20160205',
'creator': 'RTIT',
'series': 'Take me out',
'season_number': 1,
'episode_number': 25,
'age_limit': 0,
},
'expected_warnings': ['Unable to download f4m manifest'],
}, {
# non geo restricted, via secure api, unsigned download hls URL
'url': 'http://www.dplay.se/nugammalt-77-handelser-som-format-sverige/season-1-svensken-lar-sig-njuta-av-livet/',
'info_dict': {
@ -168,3 +155,90 @@ class DPlayIE(InfoExtractor):
'formats': formats,
'subtitles': subtitles,
}
class DPlayItIE(InfoExtractor):
_VALID_URL = r'https?://it\.dplay\.com/[^/]+/[^/]+/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['IT']
_TEST = {
'url': 'http://it.dplay.com/nove/biografie-imbarazzanti/luigi-di-maio-la-psicosi-di-stanislawskij/',
'md5': '2b808ffb00fc47b884a172ca5d13053c',
'info_dict': {
'id': '6918',
'display_id': 'luigi-di-maio-la-psicosi-di-stanislawskij',
'ext': 'mp4',
'title': 'Biografie imbarazzanti: Luigi Di Maio: la psicosi di Stanislawskij',
'description': 'md5:3c7a4303aef85868f867a26f5cc14813',
'thumbnail': r're:^https?://.*\.jpe?g',
'upload_date': '20160524',
'series': 'Biografie imbarazzanti',
'season_number': 1,
'episode': 'Luigi Di Maio: la psicosi di Stanislawskij',
'episode_number': 1,
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
info_url = self._search_regex(
r'url\s*:\s*["\']((?:https?:)?//[^/]+/playback/videoPlaybackInfo/\d+)',
webpage, 'video id')
title = remove_end(self._og_search_title(webpage), ' | Dplay')
try:
info = self._download_json(
info_url, display_id, headers={
'Authorization': 'Bearer %s' % self._get_cookies(url).get(
'dplayit_token').value,
'Referer': url,
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code in (400, 403):
info = self._parse_json(e.cause.read().decode('utf-8'), display_id)
error = info['errors'][0]
if error.get('code') == 'access.denied.geoblocked':
self.raise_geo_restricted(
msg=error.get('detail'), countries=self._GEO_COUNTRIES)
raise ExtractorError(info['errors'][0]['detail'], expected=True)
raise
hls_url = info['data']['attributes']['streaming']['hls']['url']
formats = self._extract_m3u8_formats(
hls_url, display_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
series = self._html_search_regex(
r'(?s)<h1[^>]+class=["\'].*?\bshow_title\b.*?["\'][^>]*>(.+?)</h1>',
webpage, 'series', fatal=False)
episode = self._search_regex(
r'<p[^>]+class=["\'].*?\bdesc_ep\b.*?["\'][^>]*>\s*<br/>\s*<b>([^<]+)',
webpage, 'episode', fatal=False)
mobj = re.search(
r'(?s)<span[^>]+class=["\']dates["\'][^>]*>.+?\bS\.(?P<season_number>\d+)\s+E\.(?P<episode_number>\d+)\s*-\s*(?P<upload_date>\d{2}/\d{2}/\d{4})',
webpage)
if mobj:
season_number = int(mobj.group('season_number'))
episode_number = int(mobj.group('episode_number'))
upload_date = unified_strdate(mobj.group('upload_date'))
else:
season_number = episode_number = upload_date = None
return {
'id': info_url.rpartition('/')[-1],
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
'upload_date': upload_date,
'formats': formats,
}

View File

@ -15,6 +15,8 @@ from ..utils import (
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv/se|nyheder|radio/ondemand)/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['DK']
IE_NAME = 'drtv'
_TESTS = [{
'url': 'https://www.dr.dk/tv/se/boern/ultra/klassen-ultra/klassen-darlig-taber-10',
@ -137,7 +139,7 @@ class DRTVIE(InfoExtractor):
if not formats and restricted_to_denmark:
self.raise_geo_restricted(
'Unfortunately, DR is not allowed to show this program outside Denmark.',
expected=True)
countries=self._GEO_COUNTRIES)
self._sort_formats(formats)
@ -156,6 +158,7 @@ class DRTVIE(InfoExtractor):
class DRTVLiveIE(InfoExtractor):
IE_NAME = 'drtv:live'
_VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
_GEO_COUNTRIES = ['DK']
_TEST = {
'url': 'https://www.dr.dk/tv/live/dr1',
'info_dict': {

View File

@ -0,0 +1,39 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class ETOnlineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?etonline\.com/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.etonline.com/tv/211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale/',
'info_dict': {
'id': '211130_dove_cameron_liv_and_maddie_emotional_episode_series_finale',
'title': 'md5:a21ec7d3872ed98335cbd2a046f34ee6',
'description': 'md5:8b94484063f463cca709617c79618ccd',
},
'playlist_count': 2,
}, {
'url': 'http://www.etonline.com/media/video/here_are_the_stars_who_love_bringing_their_moms_as_dates_to_the_oscars-211359/',
'only_matching': True,
}]
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1242911076001/default_default/index.html?videoId=ref:%s'
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result(
self.BRIGHTCOVE_URL_TEMPLATE % video_id, 'BrightcoveNew', video_id)
for video_id in re.findall(
r'site\.brightcove\s*\([^,]+,\s*["\'](title_\d+)', webpage)]
return self.playlist_result(
entries, playlist_id,
self._og_search_title(webpage, fatal=False),
self._og_search_description(webpage))

View File

@ -19,6 +19,7 @@ from .acast import (
ACastChannelIE,
)
from .addanime import AddAnimeIE
from .adn import ADNIE
from .adobetv import (
AdobeTVIE,
AdobeTVShowIE,
@ -71,6 +72,7 @@ from .arte import (
)
from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .atvat import ATVAtIE
from .audimedia import AudiMediaIE
from .audioboom import AudioBoomIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
@ -83,6 +85,7 @@ from .awaan import (
from .azmedien import (
AZMedienIE,
AZMedienPlaylistIE,
AZMedienShowPlaylistIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE
@ -116,6 +119,7 @@ from .bleacherreport import (
from .blinkx import BlinkxIE
from .bloomberg import BloombergIE
from .bokecc import BokeCCIE
from .bostonglobe import BostonGlobeIE
from .bpb import BpbIE
from .br import BRIE
from .bravotv import BravoTVIE
@ -227,6 +231,10 @@ from .dailymotion import (
DailymotionUserIE,
DailymotionCloudIE,
)
from .daisuki import (
DaisukiIE,
DaisukiPlaylistIE,
)
from .daum import (
DaumIE,
DaumClipIE,
@ -241,7 +249,10 @@ from .dfb import DFBIE
from .dhm import DHMIE
from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .dplay import DPlayIE
from .dplay import (
DPlayIE,
DPlayItIE,
)
from .dramafever import (
DramaFeverIE,
DramaFeverSeriesIE,
@ -257,7 +268,11 @@ from .dvtv import DVTVIE
from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .discoverygo import DiscoveryGoIE
from .discoverygo import (
DiscoveryGoIE,
DiscoveryGoPlaylistIE,
)
from .discoverynetworks import DiscoveryNetworksDeIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .dropbox import DropboxIE
@ -288,6 +303,7 @@ from .espn import (
ESPNArticleIE,
)
from .esri import EsriVideoIE
from .etonline import ETOnlineIE
from .europa import EuropaIE
from .everyonesmixtape import EveryonesMixtapeIE
from .expotv import ExpoTVIE
@ -338,6 +354,7 @@ from .francetv import (
)
from .freesound import FreesoundIE
from .freespeech import FreespeechIE
from .freshlive import FreshLiveIE
from .funimation import FunimationIE
from .funnyordie import FunnyOrDieIE
from .fusion import FusionIE
@ -637,6 +654,7 @@ from .ninecninemedia import (
from .ninegag import NineGagIE
from .ninenow import NineNowIE
from .nintendo import NintendoIE
from .njpwworld import NJPWWorldIE
from .nobelprize import NobelPrizeIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
@ -666,6 +684,7 @@ from .npo import (
NPORadioIE,
NPORadioFragmentIE,
SchoolTVIE,
HetKlokhuisIE,
VPROIE,
WNLIE,
)
@ -710,6 +729,10 @@ from .orf import (
ORFFM4IE,
ORFIPTVIE,
)
from .packtpub import (
PacktPubIE,
PacktPubCourseIE,
)
from .pandatv import PandaTVIE
from .pandoratv import PandoraTVIE
from .parliamentliveuk import ParliamentLiveUKIE
@ -779,11 +802,12 @@ from .radiojavan import RadioJavanIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE
from .rai import (
RaiTVIE,
RaiPlayIE,
RaiIE,
)
from .rbmaradio import RBMARadioIE
from .rds import RDSIE
from .redbulltv import RedBullTVIE
from .redtube import RedTubeIE
from .regiotv import RegioTVIE
from .rentv import (
@ -835,7 +859,6 @@ from .safari import (
from .sapo import SapoIE
from .savefrom import SaveFromIE
from .sbs import SBSIE
from .scivee import SciVeeIE
from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .scrippsnetworks import ScrippsNetworksWatchIE
@ -958,7 +981,6 @@ from .thisav import ThisAVIE
from .thisoldhouse import ThisOldHouseIE
from .threeqsdn import ThreeQSDNIE
from .tinypic import TinyPicIE
from .tlc import TlcDeIE
from .tmz import (
TMZIE,
TMZArticleIE,
@ -971,6 +993,7 @@ from .tnaflix import (
)
from .toggle import ToggleIE
from .tonline import TOnlineIE
from .toongoggles import ToonGogglesIE
from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE
@ -991,6 +1014,7 @@ from .tunein import (
TuneInTopicIE,
TuneInShortenerIE,
)
from .tunepk import TunePkIE
from .turbo import TurboIE
from .tutv import TutvIE
from .tv2 import (
@ -1157,6 +1181,12 @@ from .voicerepublic import VoiceRepublicIE
from .voxmedia import VoxMediaIE
from .vporn import VpornIE
from .vrt import VRTIE
from .vrak import VrakIE
from .vrv import (
VRVIE,
VRVSeriesIE,
)
from .medialaan import MedialaanIE
from .vube import VubeIE
from .vuclip import VuClipIE
from .vvvvid import VVVVIDIE

View File

@ -54,7 +54,7 @@ class EyedoTVIE(InfoExtractor):
'id': video_id,
'title': title,
'formats': self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8' if is_live else 'm3u8_native'),
m3u8_url, video_id, 'mp4', 'm3u8_native'),
'description': xpath_text(video_data, _add_ns('Description')),
'duration': parse_duration(xpath_text(video_data, _add_ns('Duration'))),
'uploader': xpath_text(video_data, _add_ns('Createur')),

View File

@ -196,6 +196,10 @@ class FacebookIE(InfoExtractor):
}, {
'url': 'https://www.facebookcorewwwi.onion/video.php?v=274175099429670',
'only_matching': True,
}, {
# no title
'url': 'https://www.facebook.com/onlycleverentertainment/videos/1947995502095005/',
'only_matching': True,
}]
@staticmethod
@ -303,7 +307,7 @@ class FacebookIE(InfoExtractor):
if not video_data:
server_js_data = self._parse_json(
self._search_regex(
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall)',
r'bigPipe\.onPageletArrive\(({.+?})\)\s*;\s*}\s*\)\s*,\s*["\']onPageletArrive\s+(?:stream_pagelet|pagelet_group_mall|permalink_video_pagelet)',
webpage, 'js data', default='{}'),
video_id, transform_source=js_to_json, fatal=False)
if server_js_data:
@ -353,15 +357,15 @@ class FacebookIE(InfoExtractor):
self._sort_formats(formats)
video_title = self._html_search_regex(
r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title',
default=None)
r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage,
'title', default=None)
if not video_title:
video_title = self._html_search_regex(
r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>',
webpage, 'alternative title', default=None)
if not video_title:
video_title = self._html_search_meta(
'description', webpage, 'title')
'description', webpage, 'title', default=None)
if video_title:
video_title = limit_length(video_title, 80)
else:

View File

@ -47,9 +47,12 @@ class FOXIE(AdobePassIE):
resource = self._get_mvpd_resource('fbc-fox', None, ap_p['videoGUID'], rating)
query['auth'] = self._extract_mvpd_auth(url, video_id, 'fbc-fox', resource)
return {
info = self._search_json_ld(webpage, video_id, fatal=False)
info.update({
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(update_url_query(release_url, query), {'force_smil_url': True}),
'id': video_id,
}
})
return info

View File

@ -4,7 +4,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
unified_strdate,
extract_attributes,
int_or_none,
)
@ -19,6 +20,7 @@ class FranceCultureIE(InfoExtractor):
'title': 'Rendez-vous au pays des geeks',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20140301',
'timestamp': 1393642916,
'vcodec': 'none',
}
}
@ -28,30 +30,34 @@ class FranceCultureIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_url = self._search_regex(
r'(?s)<div[^>]+class="[^"]*?title-zone-diffusion[^"]*?"[^>]*>.*?<button[^>]+data-asset-source="([^"]+)"',
webpage, 'video path')
video_data = extract_attributes(self._search_regex(
r'(?s)<div[^>]+class="[^"]*?(?:title-zone-diffusion|heading-zone-(?:wrapper|player-button))[^"]*?"[^>]*>.*?(<button[^>]+data-asset-source="[^"]+"[^>]+>)',
webpage, 'video data'))
title = self._og_search_title(webpage)
video_url = video_data['data-asset-source']
title = video_data.get('data-asset-title') or self._og_search_title(webpage)
upload_date = unified_strdate(self._search_regex(
'(?s)<div[^>]+class="date"[^>]*>.*?<span[^>]+class="inner"[^>]*>([^<]+)<',
webpage, 'upload date', fatal=False))
description = self._html_search_regex(
r'(?s)<div[^>]+class="intro"[^>]*>.*?<h2>(.+?)</h2>',
webpage, 'description', default=None)
thumbnail = self._search_regex(
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+data-dejavu-src="([^"]+)"',
r'(?s)<figure[^>]+itemtype="https://schema.org/ImageObject"[^>]*>.*?<img[^>]+(?:data-dejavu-)?src="([^"]+)"',
webpage, 'thumbnail', fatal=False)
uploader = self._html_search_regex(
r'(?s)<div id="emission".*?<span class="author">(.*?)</span>',
r'(?s)<span class="author">(.*?)</span>',
webpage, 'uploader', default=None)
vcodec = 'none' if determine_ext(video_url.lower()) == 'mp3' else None
ext = determine_ext(video_url.lower())
return {
'id': display_id,
'display_id': display_id,
'url': video_url,
'title': title,
'description': description,
'thumbnail': thumbnail,
'vcodec': vcodec,
'ext': ext,
'vcodec': 'none' if ext == 'mp3' else None,
'uploader': uploader,
'upload_date': upload_date,
'timestamp': int_or_none(video_data.get('data-asset-created-date')),
'duration': int_or_none(video_data.get('data-duration')),
}

View File

@ -0,0 +1,83 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
try_get,
unified_timestamp,
)
class FreshLiveIE(InfoExtractor):
_VALID_URL = r'https?://freshlive\.tv/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'https://freshlive.tv/satotv/74712',
'md5': '9f0cf5516979c4454ce982df3d97f352',
'info_dict': {
'id': '74712',
'ext': 'mp4',
'title': 'テスト',
'description': 'テスト',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1511,
'timestamp': 1483619655,
'upload_date': '20170105',
'uploader': 'サトTV',
'uploader_id': 'satotv',
'view_count': int,
'comment_count': int,
'is_live': False,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
options = self._parse_json(
self._search_regex(
r'window\.__CONTEXT__\s*=\s*({.+?});\s*</script>',
webpage, 'initial context'),
video_id)
info = options['context']['dispatcher']['stores']['ProgramStore']['programs'][video_id]
title = info['title']
if info.get('status') == 'upcoming':
raise ExtractorError('Stream %s is upcoming' % video_id, expected=True)
stream_url = info.get('liveStreamUrl') or info['archiveStreamUrl']
is_live = info.get('liveStreamUrl') is not None
formats = self._extract_m3u8_formats(
stream_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls')
if is_live:
title = self._live_title(title)
return {
'id': video_id,
'formats': formats,
'title': title,
'description': info.get('description'),
'thumbnail': info.get('thumbnailUrl'),
'duration': int_or_none(info.get('airTime')),
'timestamp': unified_timestamp(info.get('createdAt')),
'uploader': try_get(
info, lambda x: x['channel']['title'], compat_str),
'uploader_id': try_get(
info, lambda x: x['channel']['code'], compat_str),
'uploader_url': try_get(
info, lambda x: x['channel']['permalink'], compat_str),
'view_count': int_or_none(info.get('viewCount')),
'comment_count': int_or_none(info.get('commentCount')),
'tags': info.get('tags', []),
'is_live': is_live,
}

View File

@ -7,9 +7,9 @@ from ..compat import (
compat_urllib_parse_unquote_plus,
)
from ..utils import (
clean_html,
determine_ext,
int_or_none,
js_to_json,
sanitized_Request,
ExtractorError,
urlencode_postdata
@ -17,34 +17,26 @@ from ..utils import (
class FunimationIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?funimation\.com/shows/[^/]+/videos/(?:official|promotional)/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?funimation(?:\.com|now\.uk)/shows/[^/]+/(?P<id>[^/?#&]+)'
_NETRC_MACHINE = 'funimation'
_TESTS = [{
'url': 'http://www.funimation.com/shows/air/videos/official/breeze',
'url': 'https://www.funimation.com/shows/hacksign/role-play/',
'info_dict': {
'id': '658',
'display_id': 'breeze',
'ext': 'mp4',
'title': 'Air - 1 - Breeze',
'description': 'md5:1769f43cd5fc130ace8fd87232207892',
'thumbnail': r're:https?://.*\.jpg',
},
'skip': 'Access without user interaction is forbidden by CloudFlare, and video removed',
}, {
'url': 'http://www.funimation.com/shows/hacksign/videos/official/role-play',
'info_dict': {
'id': '31128',
'id': '91144',
'display_id': 'role-play',
'ext': 'mp4',
'title': '.hack//SIGN - 1 - Role Play',
'title': '.hack//SIGN - Role Play',
'description': 'md5:b602bdc15eef4c9bbb201bb6e6a4a2dd',
'thumbnail': r're:https?://.*\.jpg',
},
'skip': 'Access without user interaction is forbidden by CloudFlare',
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.funimation.com/shows/attack-on-titan-junior-high/videos/promotional/broadcast-dub-preview',
'url': 'https://www.funimation.com/shows/attack-on-titan-junior-high/broadcast-dub-preview/',
'info_dict': {
'id': '9635',
'display_id': 'broadcast-dub-preview',
@ -54,25 +46,13 @@ class FunimationIE(InfoExtractor):
'thumbnail': r're:https?://.*\.(?:jpg|png)',
},
'skip': 'Access without user interaction is forbidden by CloudFlare',
}, {
'url': 'https://www.funimationnow.uk/shows/puzzle-dragons-x/drop-impact/simulcast/',
'only_matching': True,
}]
_LOGIN_URL = 'http://www.funimation.com/login'
def _download_webpage(self, *args, **kwargs):
try:
return super(FunimationIE, self)._download_webpage(*args, **kwargs)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
response = ee.cause.read()
if b'>Please complete the security check to access<' in response:
raise ExtractorError(
'Access to funimation.com is blocked by CloudFlare. '
'Please browse to http://www.funimation.com/, solve '
'the reCAPTCHA, export browser cookies to a text file,'
' and then try again with --cookies YOUR_COOKIE_FILE.',
expected=True)
raise
def _extract_cloudflare_session_ua(self, url):
ci_session_cookie = self._get_cookies(url).get('ci_session')
if ci_session_cookie:
@ -114,119 +94,74 @@ class FunimationIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
def _search_kane(name):
return self._search_regex(
r"KANE_customdimensions\.%s\s*=\s*'([^']+)';" % name,
webpage, name, default=None)
title_data = self._parse_json(self._search_regex(
r'TITLE_DATA\s*=\s*({[^}]+})',
webpage, 'title data', default=''),
display_id, js_to_json, fatal=False) or {}
video_id = title_data.get('id') or self._search_regex([
r"KANE_customdimensions.videoID\s*=\s*'(\d+)';",
r'<iframe[^>]+src="/player/(\d+)"',
], webpage, 'video_id', default=None)
if not video_id:
player_url = self._html_search_meta([
'al:web:url',
'og:video:url',
'og:video:secure_url',
], webpage, fatal=True)
video_id = self._search_regex(r'/player/(\d+)', player_url, 'video id')
title = episode = title_data.get('title') or _search_kane('videoTitle') or self._og_search_title(webpage)
series = _search_kane('showName')
if series:
title = '%s - %s' % (series, title)
description = self._html_search_meta(['description', 'og:description'], webpage, fatal=True)
try:
sources = self._download_json(
'https://prod-api-funimationnow.dadcdigital.com/api/source/catalog/video/%s/signed/' % video_id,
video_id)['items']
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
error = self._parse_json(e.cause.read(), video_id)['errors'][0]
raise ExtractorError('%s said: %s' % (
self.IE_NAME, error.get('detail') or error.get('title')), expected=True)
raise
errors = []
formats = []
ERRORS_MAP = {
'ERROR_MATURE_CONTENT_LOGGED_IN': 'matureContentLoggedIn',
'ERROR_MATURE_CONTENT_LOGGED_OUT': 'matureContentLoggedOut',
'ERROR_SUBSCRIPTION_LOGGED_OUT': 'subscriptionLoggedOut',
'ERROR_VIDEO_EXPIRED': 'videoExpired',
'ERROR_TERRITORY_UNAVAILABLE': 'territoryUnavailable',
'SVODBASIC_SUBSCRIPTION_IN_PLAYER': 'basicSubscription',
'SVODNON_SUBSCRIPTION_IN_PLAYER': 'nonSubscription',
'ERROR_PLAYER_NOT_RESPONDING': 'playerNotResponding',
'ERROR_UNABLE_TO_CONNECT_TO_CDN': 'unableToConnectToCDN',
'ERROR_STREAM_NOT_FOUND': 'streamNotFound',
}
USER_AGENTS = (
# PC UA is served with m3u8 that provides some bonus lower quality formats
('pc', 'Mozilla/5.0 (Windows NT 5.2; WOW64; rv:42.0) Gecko/20100101 Firefox/42.0'),
# Mobile UA allows to extract direct links and also does not fail when
# PC UA fails with hulu error (e.g.
# http://www.funimation.com/shows/hacksign/videos/official/role-play)
('mobile', 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'),
)
user_agent = self._extract_cloudflare_session_ua(url)
if user_agent:
USER_AGENTS = ((None, user_agent),)
for kind, user_agent in USER_AGENTS:
request = sanitized_Request(url)
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(
request, display_id,
'Downloading %s webpage' % kind if kind else 'Downloading webpage')
playlist = self._parse_json(
self._search_regex(
r'var\s+playersData\s*=\s*(\[.+?\]);\n',
webpage, 'players data'),
display_id)[0]['playlist']
items = next(item['items'] for item in playlist if item.get('items'))
item = next(item for item in items if item.get('itemAK') == display_id)
error_messages = {}
video_error_messages = self._search_regex(
r'var\s+videoErrorMessages\s*=\s*({.+?});\n',
webpage, 'error messages', default=None)
if video_error_messages:
error_messages_json = self._parse_json(video_error_messages, display_id, fatal=False)
if error_messages_json:
for _, error in error_messages_json.items():
type_ = error.get('type')
description = error.get('description')
content = error.get('content')
if type_ == 'text' and description and content:
error_message = ERRORS_MAP.get(description)
if error_message:
error_messages[error_message] = content
for video in item.get('videoSet', []):
auth_token = video.get('authToken')
if not auth_token:
for source in sources:
source_url = source.get('src')
if not source_url:
continue
funimation_id = video.get('FUNImationID') or video.get('videoId')
preference = 1 if video.get('languageMode') == 'dub' else 0
if not auth_token.startswith('?'):
auth_token = '?%s' % auth_token
for quality, height in (('sd', 480), ('hd', 720), ('hd1080', 1080)):
format_url = video.get('%sUrl' % quality)
if not format_url:
continue
if not format_url.startswith(('http', '//')):
errors.append(format_url)
continue
if determine_ext(format_url) == 'm3u8':
source_type = source.get('videoType') or determine_ext(source_url)
if source_type == 'm3u8':
formats.extend(self._extract_m3u8_formats(
format_url + auth_token, display_id, 'mp4', entry_protocol='m3u8_native',
preference=preference, m3u8_id='%s-hls' % funimation_id, fatal=False))
source_url, video_id, 'mp4',
m3u8_id='hls', fatal=False))
else:
tbr = int_or_none(self._search_regex(
r'-(\d+)[Kk]', format_url, 'tbr', default=None))
formats.append({
'url': format_url + auth_token,
'format_id': '%s-http-%dp' % (funimation_id, height),
'height': height,
'tbr': tbr,
'preference': preference,
'format_id': source_type,
'url': source_url,
})
if not formats and errors:
raise ExtractorError(
'%s returned error: %s'
% (self.IE_NAME, clean_html(error_messages.get(errors[0], errors[0]))),
expected=True)
self._sort_formats(formats)
title = item['title']
artist = item.get('artist')
if artist:
title = '%s - %s' % (artist, title)
description = self._og_search_description(webpage) or item.get('description')
thumbnail = self._og_search_thumbnail(webpage) or item.get('posterUrl')
video_id = item.get('itemId') or display_id
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'thumbnail': self._og_search_thumbnail(webpage),
'series': series,
'season_number': int_or_none(title_data.get('seasonNum') or _search_kane('season')),
'episode_number': int_or_none(title_data.get('episodeNum')),
'episode': episode,
'season_id': title_data.get('seriesId'),
'formats': formats,
}

View File

@ -84,6 +84,7 @@ from .twentymin import TwentyMinutenIE
from .ustream import UstreamIE
from .openload import OpenloadIE
from .videopress import VideoPressIE
from .rutube import RutubeIE
class GenericIE(InfoExtractor):
@ -448,6 +449,23 @@ class GenericIE(InfoExtractor):
},
}],
},
{
# Brightcove with UUID in videoPlayer
'url': 'http://www8.hp.com/cn/zh/home.html',
'info_dict': {
'id': '5255815316001',
'ext': 'mp4',
'title': 'Sprocket Video - China',
'description': 'Sprocket Video - China',
'uploader': 'HP-Video Gallery',
'timestamp': 1482263210,
'upload_date': '20161220',
'uploader_id': '1107601872001',
},
'params': {
'skip_download': True, # m3u8 download
},
},
# ooyala video
{
'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219',
@ -884,12 +902,13 @@ class GenericIE(InfoExtractor):
},
# LazyYT
{
'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986',
'url': 'https://skiplagged.com/',
'info_dict': {
'id': '1986',
'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse',
'id': 'skiplagged',
'title': 'Skiplagged: The smart way to find cheap flights',
},
'playlist_mincount': 2,
'playlist_mincount': 1,
'add_ie': ['Youtube'],
},
# Cinchcast embed
{
@ -972,6 +991,20 @@ class GenericIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
# JWPlayer config passed as variable
'url': 'http://www.txxx.com/videos/3326530/ariele/',
'info_dict': {
'id': '3326530_hq',
'ext': 'mp4',
'title': 'ARIELE | Tube Cup',
'uploader': 'www.txxx.com',
'age_limit': 18,
},
'params': {
'skip_download': True,
}
},
# rtl.nl embed
{
'url': 'http://www.rtlnieuws.nl/nieuws/buitenland/aanslagen-kopenhagen',
@ -1502,11 +1535,39 @@ class GenericIE(InfoExtractor):
},
'add_ie': [VideoPressIE.ie_key()],
},
{
# Rutube embed
'url': 'http://magazzino.friday.ru/videos/vipuski/kazan-2',
'info_dict': {
'id': '9b3d5bee0a8740bf70dfd29d3ea43541',
'ext': 'flv',
'title': 'Магаззино: Казань 2',
'description': 'md5:99bccdfac2269f0e8fdbc4bbc9db184a',
'uploader': 'Магаззино',
'upload_date': '20170228',
'uploader_id': '996642',
},
'params': {
'skip_download': True,
},
'add_ie': [RutubeIE.ie_key()],
},
{
# ThePlatform embedded with whitespaces in URLs
'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
'only_matching': True,
},
{
# Senate ISVP iframe https
'url': 'https://www.hsgac.senate.gov/hearings/canadas-fast-track-refugee-plan-unanswered-questions-and-implications-for-us-national-security',
'md5': 'fb8c70b0b515e5037981a2492099aab8',
'info_dict': {
'id': 'govtaff020316',
'ext': 'mp4',
'title': 'Integrated Senate Video Player',
},
'add_ie': [SenateISVPIE.ie_key()],
},
# {
# # TODO: find another test
# # http://schema.org/VideoObject
@ -1806,14 +1867,6 @@ class GenericIE(InfoExtractor):
video_description = self._og_search_description(webpage, default=None)
video_thumbnail = self._og_search_thumbnail(webpage, default=None)
# Helper method
def _playlist_from_matches(matches, getter=None, ie=None):
urlrs = orderedSet(
self.url_result(self._proto_relative_url(getter(m) if getter else m), ie)
for m in matches)
return self.playlist_result(
urlrs, playlist_id=video_id, playlist_title=video_title)
# Look for Brightcove Legacy Studio embeds
bc_urls = BrightcoveLegacyIE._extract_brightcove_urls(webpage)
if bc_urls:
@ -1834,28 +1887,28 @@ class GenericIE(InfoExtractor):
# Look for Brightcove New Studio embeds
bc_urls = BrightcoveNewIE._extract_urls(webpage)
if bc_urls:
return _playlist_from_matches(bc_urls, ie='BrightcoveNew')
return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew')
# Look for ThePlatform embeds
tp_urls = ThePlatformIE._extract_urls(webpage)
if tp_urls:
return _playlist_from_matches(tp_urls, ie='ThePlatform')
return self.playlist_from_matches(tp_urls, video_id, video_title, ie='ThePlatform')
# Look for Vessel embeds
vessel_urls = VesselIE._extract_urls(webpage)
if vessel_urls:
return _playlist_from_matches(vessel_urls, ie=VesselIE.ie_key())
return self.playlist_from_matches(vessel_urls, video_id, video_title, ie=VesselIE.ie_key())
# Look for embedded rtl.nl player
matches = re.findall(
r'<iframe[^>]+?src="((?:https?:)?//(?:www\.)?rtl\.nl/system/videoplayer/[^"]+(?:video_)?embed[^"]+)"',
webpage)
if matches:
return _playlist_from_matches(matches, ie='RtlNl')
return self.playlist_from_matches(matches, video_id, video_title, ie='RtlNl')
vimeo_urls = VimeoIE._extract_urls(url, webpage)
if vimeo_urls:
return _playlist_from_matches(vimeo_urls, ie=VimeoIE.ie_key())
return self.playlist_from_matches(vimeo_urls, video_id, video_title, ie=VimeoIE.ie_key())
vid_me_embed_url = self._search_regex(
r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
@ -1877,25 +1930,25 @@ class GenericIE(InfoExtractor):
(?:embed|v|p)/.+?)
\1''', webpage)
if matches:
return _playlist_from_matches(
matches, lambda m: unescapeHTML(m[1]))
return self.playlist_from_matches(
matches, video_id, video_title, lambda m: unescapeHTML(m[1]))
# Look for lazyYT YouTube embed
matches = re.findall(
r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)
if matches:
return _playlist_from_matches(matches, lambda m: unescapeHTML(m))
return self.playlist_from_matches(matches, video_id, video_title, lambda m: unescapeHTML(m))
# Look for Wordpress "YouTube Video Importer" plugin
matches = re.findall(r'''(?x)<div[^>]+
class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
if matches:
return _playlist_from_matches(matches, lambda m: m[-1])
return self.playlist_from_matches(matches, video_id, video_title, lambda m: m[-1])
matches = DailymotionIE._extract_urls(webpage)
if matches:
return _playlist_from_matches(matches)
return self.playlist_from_matches(matches, video_id, video_title)
# Look for embedded Dailymotion playlist player (#3822)
m = re.search(
@ -1904,8 +1957,8 @@ class GenericIE(InfoExtractor):
playlists = re.findall(
r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url')))
if playlists:
return _playlist_from_matches(
playlists, lambda p: '//dailymotion.com/playlist/%s' % p)
return self.playlist_from_matches(
playlists, video_id, video_title, lambda p: '//dailymotion.com/playlist/%s' % p)
# Look for embedded Wistia player
match = re.search(
@ -2012,8 +2065,9 @@ class GenericIE(InfoExtractor):
if mobj is not None:
embeds = self._parse_json(mobj.group(1), video_id, fatal=False)
if embeds:
return _playlist_from_matches(
embeds, getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
return self.playlist_from_matches(
embeds, video_id, video_title,
getter=lambda v: OoyalaIE._url_for_embed_code(smuggle_url(v['provider_video_id'], {'domain': url})), ie='Ooyala')
# Look for Aparat videos
mobj = re.search(r'<iframe .*?src="(http://www\.aparat\.com/video/[^"]+)"', webpage)
@ -2075,13 +2129,13 @@ class GenericIE(InfoExtractor):
# Look for funnyordie embed
matches = re.findall(r'<iframe[^>]+?src="(https?://(?:www\.)?funnyordie\.com/embed/[^"]+)"', webpage)
if matches:
return _playlist_from_matches(
matches, getter=unescapeHTML, ie='FunnyOrDie')
return self.playlist_from_matches(
matches, video_id, video_title, getter=unescapeHTML, ie='FunnyOrDie')
# Look for BBC iPlayer embed
matches = re.findall(r'setPlaylist\("(https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)', webpage)
if matches:
return _playlist_from_matches(matches, ie='BBCCoUk')
return self.playlist_from_matches(matches, video_id, video_title, ie='BBCCoUk')
# Look for embedded RUTV player
rutv_url = RUTVIE._extract_url(webpage)
@ -2096,32 +2150,32 @@ class GenericIE(InfoExtractor):
# Look for embedded SportBox player
sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
if sportbox_urls:
return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed')
# Look for embedded XHamster player
xhamster_urls = XHamsterEmbedIE._extract_urls(webpage)
if xhamster_urls:
return _playlist_from_matches(xhamster_urls, ie='XHamsterEmbed')
return self.playlist_from_matches(xhamster_urls, video_id, video_title, ie='XHamsterEmbed')
# Look for embedded TNAFlixNetwork player
tnaflix_urls = TNAFlixNetworkEmbedIE._extract_urls(webpage)
if tnaflix_urls:
return _playlist_from_matches(tnaflix_urls, ie=TNAFlixNetworkEmbedIE.ie_key())
return self.playlist_from_matches(tnaflix_urls, video_id, video_title, ie=TNAFlixNetworkEmbedIE.ie_key())
# Look for embedded PornHub player
pornhub_urls = PornHubIE._extract_urls(webpage)
if pornhub_urls:
return _playlist_from_matches(pornhub_urls, ie=PornHubIE.ie_key())
return self.playlist_from_matches(pornhub_urls, video_id, video_title, ie=PornHubIE.ie_key())
# Look for embedded DrTuber player
drtuber_urls = DrTuberIE._extract_urls(webpage)
if drtuber_urls:
return _playlist_from_matches(drtuber_urls, ie=DrTuberIE.ie_key())
return self.playlist_from_matches(drtuber_urls, video_id, video_title, ie=DrTuberIE.ie_key())
# Look for embedded RedTube player
redtube_urls = RedTubeIE._extract_urls(webpage)
if redtube_urls:
return _playlist_from_matches(redtube_urls, ie=RedTubeIE.ie_key())
return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key())
# Look for embedded Tvigle player
mobj = re.search(
@ -2167,12 +2221,12 @@ class GenericIE(InfoExtractor):
# Look for embedded soundcloud player
soundcloud_urls = SoundcloudIE._extract_urls(webpage)
if soundcloud_urls:
return _playlist_from_matches(soundcloud_urls, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
return self.playlist_from_matches(soundcloud_urls, video_id, video_title, getter=unescapeHTML, ie=SoundcloudIE.ie_key())
# Look for tunein player
tunein_urls = TuneInBaseIE._extract_urls(webpage)
if tunein_urls:
return _playlist_from_matches(tunein_urls)
return self.playlist_from_matches(tunein_urls, video_id, video_title)
# Look for embedded mtvservices player
mtvservices_url = MTVServicesEmbeddedIE._extract_url(webpage)
@ -2455,30 +2509,36 @@ class GenericIE(InfoExtractor):
# Look for DBTV embeds
dbtv_urls = DBTVIE._extract_urls(webpage)
if dbtv_urls:
return _playlist_from_matches(dbtv_urls, ie=DBTVIE.ie_key())
return self.playlist_from_matches(dbtv_urls, video_id, video_title, ie=DBTVIE.ie_key())
# Look for Videa embeds
videa_urls = VideaIE._extract_urls(webpage)
if videa_urls:
return _playlist_from_matches(videa_urls, ie=VideaIE.ie_key())
return self.playlist_from_matches(videa_urls, video_id, video_title, ie=VideaIE.ie_key())
# Look for 20 minuten embeds
twentymin_urls = TwentyMinutenIE._extract_urls(webpage)
if twentymin_urls:
return _playlist_from_matches(
twentymin_urls, ie=TwentyMinutenIE.ie_key())
return self.playlist_from_matches(
twentymin_urls, video_id, video_title, ie=TwentyMinutenIE.ie_key())
# Look for Openload embeds
openload_urls = OpenloadIE._extract_urls(webpage)
if openload_urls:
return _playlist_from_matches(
openload_urls, ie=OpenloadIE.ie_key())
return self.playlist_from_matches(
openload_urls, video_id, video_title, ie=OpenloadIE.ie_key())
# Look for VideoPress embeds
videopress_urls = VideoPressIE._extract_urls(webpage)
if videopress_urls:
return _playlist_from_matches(
videopress_urls, ie=VideoPressIE.ie_key())
return self.playlist_from_matches(
videopress_urls, video_id, video_title, ie=VideoPressIE.ie_key())
# Look for Rutube embeds
rutube_urls = RutubeIE._extract_urls(webpage)
if rutube_urls:
return self.playlist_from_matches(
rutube_urls, ie=RutubeIE.ie_key())
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
@ -2504,14 +2564,14 @@ class GenericIE(InfoExtractor):
self._sort_formats(entry['formats'])
return self.playlist_result(entries)
jwplayer_data_str = self._find_jwplayer_data(webpage)
if jwplayer_data_str:
try:
jwplayer_data = self._parse_json(
jwplayer_data_str, video_id, transform_source=js_to_json)
return self._parse_jwplayer_data(jwplayer_data, video_id)
except ExtractorError:
pass
jwplayer_data = self._find_jwplayer_data(
webpage, video_id, transform_source=js_to_json)
if jwplayer_data:
info = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False, base_url=url)
if not info.get('title'):
info['title'] = video_title
return info
def check_video(vurl):
if YoutubeIE.suitable(vurl):
@ -2586,11 +2646,14 @@ class GenericIE(InfoExtractor):
found = re.search(REDIRECT_REGEX, refresh_header)
if found:
new_url = compat_urlparse.urljoin(url, unescapeHTML(found.group(1)))
if new_url != url:
self.report_following_redirect(new_url)
return {
'_type': 'url',
'url': new_url,
}
else:
found = None
if not found:
# twitter:player is a https URL to iframe player that may or may not

View File

@ -36,7 +36,7 @@ class GoIE(AdobePassIE):
'requestor_id': 'DisneyXD',
}
}
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|season-\d+/\d+-(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_VALID_URL = r'https?://(?:(?P<sub_domain>%s)\.)?go\.com/(?:[^/]+/)*(?:vdka(?P<id>\w+)|(?:[^/]+/)*(?P<display_id>[^/?#]+))' % '|'.join(_SITE_INFO.keys())
_TESTS = [{
'url': 'http://abc.go.com/shows/castle/video/most-recent/vdka0_g86w5onx',
'info_dict': {
@ -52,6 +52,12 @@ class GoIE(AdobePassIE):
}, {
'url': 'http://abc.go.com/shows/after-paradise/video/most-recent/vdka3335601',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
xpath_text,
xpath_element,
@ -14,14 +15,26 @@ from ..utils import (
class HBOBaseIE(InfoExtractor):
_FORMATS_INFO = {
'pro7': {
'width': 1280,
'height': 720,
},
'1920': {
'width': 1280,
'height': 720,
},
'pro6': {
'width': 768,
'height': 432,
},
'640': {
'width': 768,
'height': 432,
},
'pro5': {
'width': 640,
'height': 360,
},
'highwifi': {
'width': 640,
'height': 360,
@ -78,6 +91,17 @@ class HBOBaseIE(InfoExtractor):
formats.extend(self._extract_m3u8_formats(
video_url.replace('.tar', '/base_index_w8.m3u8'),
video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
elif source.tag == 'hls':
# #EXT-X-BYTERANGE is not supported by native hls downloader
# and ffmpeg (#10955)
# formats.extend(self._extract_m3u8_formats(
# video_url.replace('.tar', '/base_index.m3u8'),
# video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
continue
elif source.tag == 'dash':
formats.extend(self._extract_mpd_formats(
video_url.replace('.tar', '/manifest.mpd'),
video_id, mpd_id='dash', fatal=False))
else:
format_info = self._FORMATS_INFO.get(source.tag, {})
formats.append({
@ -112,10 +136,11 @@ class HBOBaseIE(InfoExtractor):
class HBOIE(HBOBaseIE):
IE_NAME = 'hbo'
_VALID_URL = r'https?://(?:www\.)?hbo\.com/video/video\.html\?.*vid=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.hbo.com/video/video.html?autoplay=true&g=u&vid=1437839',
'md5': '1c33253f0c7782142c993c0ba62a8753',
'md5': '2c6a6bc1222c7e91cb3334dad1746e5a',
'info_dict': {
'id': '1437839',
'ext': 'mp4',
@ -131,11 +156,12 @@ class HBOIE(HBOBaseIE):
class HBOEpisodeIE(HBOBaseIE):
_VALID_URL = r'https?://(?:www\.)?hbo\.com/(?!video)([^/]+/)+video/(?P<id>[0-9a-z-]+)\.html'
IE_NAME = 'hbo:episode'
_VALID_URL = r'https?://(?:www\.)?hbo\.com/(?P<path>(?!video)(?:(?:[^/]+/)+video|watch-free-episodes)/(?P<id>[0-9a-z-]+))(?:\.html)?'
_TESTS = [{
'url': 'http://www.hbo.com/girls/episodes/5/52-i-love-you-baby/video/ep-52-inside-the-episode.html?autoplay=true',
'md5': '689132b253cc0ab7434237fc3a293210',
'md5': '61ead79b9c0dfa8d3d4b07ef4ac556fb',
'info_dict': {
'id': '1439518',
'display_id': 'ep-52-inside-the-episode',
@ -147,16 +173,19 @@ class HBOEpisodeIE(HBOBaseIE):
}, {
'url': 'http://www.hbo.com/game-of-thrones/about/video/season-5-invitation-to-the-set.html?autoplay=true',
'only_matching': True,
}, {
'url': 'http://www.hbo.com/watch-free-episodes/last-week-tonight-with-john-oliver',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
path, display_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
content = self._download_json(
'http://www.hbo.com/api/content/' + path, display_id)['content']
video_id = self._search_regex(
r'(?P<q1>[\'"])videoId(?P=q1)\s*:\s*(?P<q2>[\'"])(?P<video_id>\d+)(?P=q2)',
webpage, 'video ID', group='video_id')
video_id = compat_str((content.get('parsed', {}).get(
'common:FullBleedVideo', {}) or content['selectedEpisode'])['videoId'])
info_dict = self._extract_from_id(video_id)
info_dict['display_id'] = display_id

View File

@ -16,6 +16,8 @@ class IviIE(InfoExtractor):
IE_DESC = 'ivi.ru'
IE_NAME = 'ivi'
_VALID_URL = r'https?://(?:www\.)?ivi\.ru/(?:watch/(?:[^/]+/)?|video/player\?.*?videoId=)(?P<id>\d+)'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['RU']
_TESTS = [
# Single movie
@ -91,7 +93,11 @@ class IviIE(InfoExtractor):
if 'error' in video_json:
error = video_json['error']
if error['origin'] == 'NoRedisValidData':
origin = error['origin']
if origin == 'NotAllowedForLocation':
self.raise_geo_restricted(
msg=error['message'], countries=self._GEO_COUNTRIES)
elif origin == 'NoRedisValidData':
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
raise ExtractorError(
'Unable to download video %s: %s' % (video_id, error['message']),

View File

@ -62,13 +62,21 @@ class LimelightBaseIE(InfoExtractor):
fmt = {
'url': stream_url,
'abr': float_or_none(stream.get('audioBitRate')),
'vbr': float_or_none(stream.get('videoBitRate')),
'fps': float_or_none(stream.get('videoFrameRate')),
'width': int_or_none(stream.get('videoWidthInPixels')),
'height': int_or_none(stream.get('videoHeightInPixels')),
'ext': ext,
}
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp4:.+)$', stream_url)
width = int_or_none(stream.get('videoWidthInPixels'))
height = int_or_none(stream.get('videoHeightInPixels'))
vbr = float_or_none(stream.get('videoBitRate'))
if width or height or vbr:
fmt.update({
'width': width,
'height': height,
'vbr': vbr,
})
else:
fmt['vcodec'] = 'none'
rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', stream_url)
if rtmp:
format_id = 'rtmp'
if stream.get('videoBitRate'):

View File

@ -119,7 +119,8 @@ class LivestreamIE(InfoExtractor):
m3u8_url = video_data.get('m3u8_url')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
f4m_url = video_data.get('f4m_url')
if f4m_url:
@ -158,11 +159,11 @@ class LivestreamIE(InfoExtractor):
if smil_url:
formats.extend(self._extract_smil_formats(smil_url, broadcast_id))
entry_protocol = 'm3u8' if is_live else 'm3u8_native'
m3u8_url = stream_info.get('m3u8_url')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, broadcast_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=False))
m3u8_url, broadcast_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
rtsp_url = stream_info.get('rtsp_url')
if rtsp_url:
@ -276,7 +277,7 @@ class LivestreamOriginalIE(InfoExtractor):
'view_count': view_count,
}
def _extract_video_formats(self, video_data, video_id, entry_protocol):
def _extract_video_formats(self, video_data, video_id):
formats = []
progressive_url = video_data.get('progressiveUrl')
@ -289,7 +290,8 @@ class LivestreamOriginalIE(InfoExtractor):
m3u8_url = video_data.get('httpUrl')
if m3u8_url:
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', entry_protocol, m3u8_id='hls', fatal=False))
m3u8_url, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
rtsp_url = video_data.get('rtspUrl')
if rtsp_url:
@ -340,11 +342,10 @@ class LivestreamOriginalIE(InfoExtractor):
}
video_data = self._download_json(stream_url, content_id)
is_live = video_data.get('isLive')
entry_protocol = 'm3u8' if is_live else 'm3u8_native'
info.update({
'id': content_id,
'title': self._live_title(info['title']) if is_live else info['title'],
'formats': self._extract_video_formats(video_data, content_id, entry_protocol),
'formats': self._extract_video_formats(video_data, content_id),
'is_live': is_live,
})
return info

View File

@ -14,7 +14,7 @@ from ..utils import (
class MDRIE(InfoExtractor):
IE_DESC = 'MDR.DE and KiKA'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z]+-?(?P<id>\d+)(?:_.+?)?\.html'
_VALID_URL = r'https?://(?:www\.)?(?:mdr|kika)\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)(?:_.+?)?\.html'
_TESTS = [{
# MDR regularly deletes its videos
@ -31,6 +31,7 @@ class MDRIE(InfoExtractor):
'duration': 250,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
'skip': '404 not found',
}, {
'url': 'http://www.kika.de/baumhaus/videos/video19636.html',
'md5': '4930515e36b06c111213e80d1e4aad0e',
@ -41,6 +42,7 @@ class MDRIE(InfoExtractor):
'duration': 134,
'uploader': 'KIKA',
},
'skip': '404 not found',
}, {
'url': 'http://www.kika.de/sendungen/einzelsendungen/weihnachtsprogramm/videos/video8182.html',
'md5': '5fe9c4dd7d71e3b238f04b8fdd588357',
@ -49,11 +51,21 @@ class MDRIE(InfoExtractor):
'ext': 'mp4',
'title': 'Beutolomäus und der geheime Weihnachtswunsch',
'description': 'md5:b69d32d7b2c55cbe86945ab309d39bbd',
'timestamp': 1450950000,
'upload_date': '20151224',
'timestamp': 1482541200,
'upload_date': '20161224',
'duration': 4628,
'uploader': 'KIKA',
},
}, {
# audio with alternative playerURL pattern
'url': 'http://www.mdr.de/kultur/videos-und-audios/audio-radio/operation-mindfuck-robert-wilson100.html',
'info_dict': {
'id': '100',
'ext': 'mp4',
'title': 'Feature: Operation Mindfuck - Robert Anton Wilson',
'duration': 3239,
'uploader': 'MITTELDEUTSCHER RUNDFUNK',
},
}, {
'url': 'http://www.kika.de/baumhaus/sendungen/video19636_zc-fea7f8a0_zs-4bf89c60.html',
'only_matching': True,
@ -71,7 +83,7 @@ class MDRIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
data_url = self._search_regex(
r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+/(?:video|audio)-?[0-9]+-avCustom\.xml)\1',
r'(?:dataURL|playerXml(?:["\'])?)\s*:\s*(["\'])(?P<url>.+?-avCustom\.xml)\1',
webpage, 'data url', group='url').replace(r'\/', '/')
doc = self._download_xml(

View File

@ -0,0 +1,259 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
parse_duration,
try_get,
unified_timestamp,
urlencode_postdata,
)
class MedialaanIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:
(?P<site_id>vtm|q2|vtmkzoom)\.be/
(?:
video(?:/[^/]+/id/|/?\?.*?\baid=)|
(?:[^/]+/)*
)
)
(?P<id>[^/?#&]+)
'''
_NETRC_MACHINE = 'medialaan'
_APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-'
_SITE_TO_APP_ID = {
'vtm': 'vtm_watch',
'q2': 'q2',
'vtmkzoom': 'vtmkzoom',
}
_TESTS = [{
# vod
'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch',
'info_dict': {
'id': 'vtm_20170219_VM0678361_vtmwatch',
'ext': 'mp4',
'title': 'Allemaal Chris afl. 6',
'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2',
'timestamp': 1487533280,
'upload_date': '20170219',
'duration': 2562,
'series': 'Allemaal Chris',
'season': 'Allemaal Chris',
'season_number': 1,
'season_id': '256936078124527',
'episode': 'Allemaal Chris afl. 6',
'episode_number': 6,
'episode_id': '256936078591527',
},
'params': {
'skip_download': True,
},
'skip': 'Requires account credentials',
}, {
# clip
'url': 'http://vtm.be/video?aid=168332',
'info_dict': {
'id': '168332',
'ext': 'mp4',
'title': '"Veronique liegt!"',
'description': 'md5:1385e2b743923afe54ba4adc38476155',
'timestamp': 1489002029,
'upload_date': '20170308',
'duration': 96,
},
}, {
# vod
'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000',
'only_matching': True,
}, {
# vod
'url': 'http://vtm.be/video?aid=163157',
'only_matching': True,
}, {
# vod
'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2',
'only_matching': True,
}, {
# clip
'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio',
'only_matching': True,
}]
def _real_initialize(self):
self._logged_in = False
def _login(self):
username, password = self._get_login_info()
if username is None:
self.raise_login_required()
auth_data = {
'APIKey': self._APIKEY,
'sdk': 'js_6.1',
'format': 'json',
'loginID': username,
'password': password,
}
auth_info = self._download_json(
'https://accounts.eu1.gigya.com/accounts.login', None,
note='Logging in', errnote='Unable to log in',
data=urlencode_postdata(auth_data))
error_message = auth_info.get('errorDetails') or auth_info.get('errorMessage')
if error_message:
raise ExtractorError(
'Unable to login: %s' % error_message, expected=True)
self._uid = auth_info['UID']
self._uid_signature = auth_info['UIDSignature']
self._signature_timestamp = auth_info['signatureTimestamp']
self._logged_in = True
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id, site_id = mobj.group('id', 'site_id')
webpage = self._download_webpage(url, video_id)
config = self._parse_json(
self._search_regex(
r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);',
webpage, 'config', default='{}'), video_id,
transform_source=lambda s: s.replace(
'\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'"))
vod_id = config.get('vodId') or self._search_regex(
(r'\\"vodId\\"\s*:\s*\\"(.+?)\\"',
r'<[^>]+id=["\']vod-(\d+)'),
webpage, 'video_id', default=None)
# clip, no authentication required
if not vod_id:
player = self._parse_json(
self._search_regex(
r'vmmaplayer\(({.+?})\);', webpage, 'vmma player',
default=''),
video_id, transform_source=lambda s: '[%s]' % s, fatal=False)
if player:
video = player[-1]
info = {
'id': video_id,
'url': video['videoUrl'],
'title': video['title'],
'thumbnail': video.get('imageUrl'),
'timestamp': int_or_none(video.get('createdDate')),
'duration': int_or_none(video.get('duration')),
}
else:
info = self._parse_html5_media_entries(
url, webpage, video_id, m3u8_id='hls')[0]
info.update({
'id': video_id,
'title': self._html_search_meta('description', webpage),
'duration': parse_duration(self._html_search_meta('duration', webpage)),
})
# vod, authentication required
else:
if not self._logged_in:
self._login()
settings = self._parse_json(
self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);',
webpage, 'drupal settings', default='{}'),
video_id)
def get(container, item):
return try_get(
settings, lambda x: x[container][item],
compat_str) or self._search_regex(
r'"%s"\s*:\s*"([^"]+)' % item, webpage, item,
default=None)
app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch')
sso = get('vod', 'gigyaDatabase') or 'vtm-sso'
data = self._download_json(
'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id,
video_id, query={
'app_id': app_id,
'user_network': sso,
'UID': self._uid,
'UIDSignature': self._uid_signature,
'signatureTimestamp': self._signature_timestamp,
})
formats = self._extract_m3u8_formats(
data['response']['uri'], video_id, entry_protocol='m3u8_native',
ext='mp4', m3u8_id='hls')
self._sort_formats(formats)
info = {
'id': vod_id,
'formats': formats,
}
api_key = get('vod', 'apiKey')
channel = get('medialaanGigya', 'channel')
if api_key:
videos = self._download_json(
'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False,
query={
'channels': channel,
'ids': vod_id,
'limit': 1,
'apikey': api_key,
})
if videos:
video = try_get(
videos, lambda x: x['response']['videos'][0], dict)
if video:
def get(container, item, expected_type=None):
return try_get(
video, lambda x: x[container][item], expected_type)
def get_string(container, item):
return get(container, item, compat_str)
info.update({
'series': get_string('program', 'title'),
'season': get_string('season', 'title'),
'season_number': int_or_none(get('season', 'number')),
'season_id': get_string('season', 'id'),
'episode': get_string('episode', 'title'),
'episode_number': int_or_none(get('episode', 'number')),
'episode_id': get_string('episode', 'id'),
'duration': int_or_none(
video.get('duration')) or int_or_none(
video.get('durationMillis'), scale=1000),
'title': get_string('episode', 'title'),
'description': get_string('episode', 'text'),
'timestamp': unified_timestamp(get_string(
'publication', 'begin')),
})
if not info.get('title'):
info['title'] = try_get(
config, lambda x: x['videoConfig']['title'],
compat_str) or self._html_search_regex(
r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title',
default=None) or self._og_search_title(webpage)
if not info.get('description'):
info['description'] = self._html_search_regex(
r'<div[^>]+class="field-item\s+even">\s*<p>(.+?)</p>',
webpage, 'description', default=None)
return info

View File

@ -51,6 +51,7 @@ class MioMioIE(InfoExtractor):
'ext': 'mp4',
'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',
},
'skip': 'Unable to load videos',
}]
def _extract_mioplayer(self, webpage, video_id, title, http_headers):
@ -94,9 +95,18 @@ class MioMioIE(InfoExtractor):
return entries
def _download_chinese_webpage(self, *args, **kwargs):
# Requests with English locales return garbage
headers = {
'Accept-Language': 'zh-TW,en-US;q=0.7,en;q=0.3',
}
kwargs.setdefault('headers', {}).update(headers)
return self._download_webpage(*args, **kwargs)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_chinese_webpage(
url, video_id)
title = self._html_search_meta(
'description', webpage, 'title', fatal=True)
@ -106,7 +116,7 @@ class MioMioIE(InfoExtractor):
if '_h5' in mioplayer_path:
player_url = compat_urlparse.urljoin(url, mioplayer_path)
player_webpage = self._download_webpage(
player_webpage = self._download_chinese_webpage(
player_url, video_id,
note='Downloading player webpage', headers={'Referer': url})
entries = self._parse_html5_media_entries(player_url, player_webpage, video_id)

View File

@ -4,6 +4,7 @@ from __future__ import unicode_literals
import uuid
from .common import InfoExtractor
from .ooyala import OoyalaIE
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
@ -24,6 +25,9 @@ class MiTeleBaseIE(InfoExtractor):
r'(?s)(<ms-video-player.+?</ms-video-player>)',
webpage, 'ms video player'))
video_id = player_data['data-media-id']
if player_data.get('data-cms-id') == 'ooyala':
return self.url_result(
'ooyala:%s' % video_id, ie=OoyalaIE.ie_key(), video_id=video_id)
config_url = compat_urlparse.urljoin(url, player_data['data-config'])
config = self._download_json(
config_url, video_id, 'Downloading config JSON')

View File

@ -34,12 +34,6 @@ class NineCNineMediaStackIE(NineCNineMediaBaseIE):
formats.extend(self._extract_f4m_formats(
stack_base_url + 'f4m', stack_id,
f4m_id='hds', fatal=False))
mp4_url = self._download_webpage(stack_base_url + 'pd', stack_id, fatal=False)
if mp4_url:
formats.append({
'url': mp4_url,
'format_id': 'mp4',
})
self._sort_formats(formats)
return {

View File

@ -0,0 +1,83 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
get_element_by_class,
urlencode_postdata,
)
class NJPWWorldIE(InfoExtractor):
_VALID_URL = r'https?://njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
IE_DESC = '新日本プロレスワールド'
_NETRC_MACHINE = 'njpwworld'
_TEST = {
'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
'info_dict': {
'id': 's_series_00155_1_9',
'ext': 'mp4',
'title': '第9試合 ランディ・サベージ vs リック・スタイナー',
'tags': list,
},
'params': {
'skip_download': True, # AES-encrypted m3u8
},
'skip': 'Requires login',
}
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
# No authentication to be performed
if not username:
return True
webpage, urlh = self._download_webpage_handle(
'https://njpwworld.com/auth/login', None,
note='Logging in', errnote='Unable to login',
data=urlencode_postdata({'login_id': username, 'pw': password}))
# /auth/login will return 302 for successful logins
if urlh.geturl() == 'https://njpwworld.com/auth/login':
self.report_warning('unable to login')
return False
return True
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
formats = []
for player_url, kind in re.findall(r'<a[^>]+href="(/player[^"]+)".+?<img[^>]+src="[^"]+qf_btn_([^".]+)', webpage):
player_url = compat_urlparse.urljoin(url, player_url)
player_page = self._download_webpage(
player_url, video_id, note='Downloading player page')
entries = self._parse_html5_media_entries(
player_url, player_page, video_id, m3u8_id='hls-%s' % kind,
m3u8_entry_protocol='m3u8_native',
preference=2 if 'hq' in kind else 1)
formats.extend(entries[0]['formats'])
self._sort_formats(formats)
post_content = get_element_by_class('post-content', webpage)
tags = re.findall(
r'<li[^>]+class="tag-[^"]+"><a[^>]*>([^<]+)</a></li>', post_content
) if post_content else None
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'tags': tags,
}

View File

@ -23,7 +23,7 @@ from ..utils import (
class NocoIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P<id>\d+)'
_LOGIN_URL = 'http://noco.tv/do.php'
_LOGIN_URL = 'https://noco.tv/do.php'
_API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s'
_SUB_LANG_TEMPLATE = '&sub_lang=%s'
_NETRC_MACHINE = 'noco'
@ -69,16 +69,17 @@ class NocoIE(InfoExtractor):
if username is None:
return
login_form = {
login = self._download_json(
self._LOGIN_URL, None, 'Logging in as %s' % username,
data=urlencode_postdata({
'a': 'login',
'cookie': '1',
'username': username,
'password': password,
}
request = sanitized_Request(self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8')
login = self._download_json(request, None, 'Logging in as %s' % username)
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
})
if 'erreur' in login:
raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True)

View File

@ -3,41 +3,27 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..compat import (
compat_HTTPError,
compat_str,
)
from ..utils import (
determine_ext,
ExtractorError,
fix_xml_ampersands,
orderedSet,
parse_duration,
qualities,
strip_jsonp,
unified_strdate,
ExtractorError,
)
class NPOBaseIE(InfoExtractor):
def _get_token(self, video_id):
token_page = self._download_webpage(
'http://ida.omroep.nl/npoplayer/i.js',
video_id, note='Downloading token')
token = self._search_regex(
r'npoplayer\.token = "(.+?)"', token_page, 'token')
# Decryption algorithm extracted from http://npoplayer.omroep.nl/csjs/npoplayer-min.js
token_l = list(token)
first = second = None
for i in range(5, len(token_l) - 4):
if token_l[i].isdigit():
if first is None:
first = i
elif second is None:
second = i
if first is None or second is None:
first = 12
second = 13
token_l[first], token_l[second] = token_l[second], token_l[first]
return ''.join(token_l)
return self._download_json(
'http://ida.omroep.nl/app.php/auth', video_id,
note='Downloading token')['token']
class NPOIE(NPOBaseIE):
@ -51,14 +37,14 @@ class NPOIE(NPOBaseIE):
(?:
npo\.nl/(?!live|radio)(?:[^/]+/){2}|
ntr\.nl/(?:[^/]+/){2,}|
omroepwnl\.nl/video/fragment/[^/]+__
omroepwnl\.nl/video/fragment/[^/]+__|
zapp\.nl/[^/]+/[^/]+/
)
)
(?P<id>[^/?#]+)
'''
_TESTS = [
{
_TESTS = [{
'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
'md5': '4b3f9c429157ec4775f2c9cb7b911016',
'info_dict': {
@ -68,8 +54,7 @@ class NPOIE(NPOBaseIE):
'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
'upload_date': '20140622',
},
},
{
}, {
'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
'info_dict': {
@ -80,46 +65,42 @@ class NPOIE(NPOBaseIE):
'upload_date': '20090227',
'duration': 2400,
},
},
{
}, {
'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht: De toekomst komt uit Afrika',
'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
'upload_date': '20130225',
'duration': 3000,
},
},
{
}, {
'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
'info_dict': {
'id': 'WO_VPRO_043706',
'ext': 'wmv',
'ext': 'm4v',
'title': 'De nieuwe mens - Deel 1',
'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
'duration': 4680,
},
'params': {
# mplayer mms download
'skip_download': True,
}
},
}, {
# non asf in streams
{
'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
'md5': 'b3da13de374cbe2d5332a7e910bef97f',
'info_dict': {
'id': 'WO_NOS_762771',
'ext': 'mp4',
'title': 'Hoe gaat Europa verder na Parijs?',
},
},
{
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
'md5': '01c6a2841675995da1f0cf776f03a9c3',
'info_dict': {
'id': 'VPWON_1233944',
'ext': 'm4v',
@ -128,10 +109,11 @@ class NPOIE(NPOBaseIE):
'upload_date': '20150508',
'duration': 599,
},
},
{
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
'md5': 'd30cd8417b8b9bca1fdff27428860d08',
'info_dict': {
'id': 'POW_00996502',
'ext': 'm4v',
@ -140,8 +122,35 @@ class NPOIE(NPOBaseIE):
'upload_date': '20150508',
'duration': 462,
},
'params': {
'skip_download': True,
}
]
}, {
# audio
'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
'info_dict': {
'id': 'RBX_FUNX_6683215',
'ext': 'mp3',
'title': 'Jouw Stad Rotterdam',
'description': 'md5:db251505244f097717ec59fabc372d9f',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
'only_matching': True,
}, {
'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
'only_matching': True,
}, {
'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
'only_matching': True,
}, {
# live stream
'url': 'npo:LI_NL1_4188102',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -170,69 +179,114 @@ class NPOIE(NPOBaseIE):
token = self._get_token(video_id)
formats = []
urls = set()
pubopties = metadata.get('pubopties')
if pubopties:
quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
for format_id in pubopties:
format_info = self._download_json(
'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
% (video_id, format_id, token),
video_id, 'Downloading %s JSON' % format_id)
if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
items = self._download_json(
'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
'Downloading formats JSON', query={
'adaptive': 'yes',
'token': token,
})['items'][0]
for num, item in enumerate(items):
item_url = item.get('url')
if not item_url or item_url in urls:
continue
streams = format_info.get('streams')
if streams:
try:
video_info = self._download_json(
streams[0] + '&type=json',
video_id, 'Downloading %s stream JSON' % format_id)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
error = (self._parse_json(ee.cause.read().decode(), video_id, fatal=False) or {}).get('errorstring')
if error:
raise ExtractorError(error, expected=True)
raise
else:
video_info = format_info
video_url = video_info.get('url')
if not video_url:
continue
if format_id == 'adaptive':
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4'))
else:
urls.add(item_url)
format_id = self._search_regex(
r'video/ida/([^/]+)', item_url, 'format id',
default=None)
def add_format_url(format_url):
formats.append({
'url': video_url,
'url': format_url,
'format_id': format_id,
'quality': quality(format_id),
})
streams = metadata.get('streams')
if streams:
for i, stream in enumerate(streams):
# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
if item.get('contentType') in ('url', 'audio'):
add_format_url(item_url)
continue
try:
stream_info = self._download_json(
item_url + '&type=json', video_id,
'Downloading %s stream JSON'
% item.get('label') or item.get('format') or format_id or num)
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
error = (self._parse_json(
ee.cause.read().decode(), video_id,
fatal=False) or {}).get('errorstring')
if error:
raise ExtractorError(error, expected=True)
raise
# Stream URL instead of JSON, example: npo:LI_NL1_4188102
if isinstance(stream_info, compat_str):
if not stream_info.startswith('http'):
continue
video_url = stream_info
# JSON
else:
video_url = stream_info.get('url')
if not video_url or video_url in urls:
continue
urls.add(item_url)
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
else:
add_format_url(video_url)
is_live = metadata.get('medium') == 'live'
if not is_live:
for num, stream in enumerate(metadata.get('streams', [])):
stream_url = stream.get('url')
if not stream_url:
if not stream_url or stream_url in urls:
continue
if '.asf' not in stream_url:
formats.append({
'url': stream_url,
'quality': stream.get('kwaliteit'),
})
urls.add(stream_url)
# smooth streaming is not supported
stream_type = stream.get('type', '').lower()
if stream_type in ['ss', 'ms']:
continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(
stream_url, video_id, fatal=False)
# f4m downloader downloads only piece of live stream
for f4m_format in f4m_formats:
f4m_format['preference'] = -1
formats.extend(f4m_formats)
elif stream_type == 'hls':
formats.extend(self._extract_m3u8_formats(
stream_url, video_id, ext='mp4', fatal=False))
# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
elif '.asf' in stream_url:
asx = self._download_xml(
stream_url, video_id,
'Downloading stream %d ASX playlist' % i,
transform_source=fix_xml_ampersands)
'Downloading stream %d ASX playlist' % num,
transform_source=fix_xml_ampersands, fatal=False)
if not asx:
continue
ref = asx.find('./ENTRY/Ref')
if ref is None:
continue
video_url = ref.get('href')
if not video_url:
if not video_url or video_url in urls:
continue
urls.add(video_url)
formats.append({
'url': video_url,
'ext': stream.get('formaat', 'asf'),
'quality': stream.get('kwaliteit'),
'preference': -10,
})
else:
formats.append({
'url': stream_url,
'quality': stream.get('kwaliteit'),
})
self._sort_formats(formats)
@ -246,28 +300,28 @@ class NPOIE(NPOBaseIE):
return {
'id': video_id,
'title': title,
'title': self._live_title(title) if is_live else title,
'description': metadata.get('info'),
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'upload_date': unified_strdate(metadata.get('gidsdatum')),
'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}
class NPOLiveIE(NPOBaseIE):
IE_NAME = 'npo.nl:live'
_VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
_VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://www.npo.nl/live/npo-1',
'info_dict': {
'id': 'LI_NEDERLAND1_136692',
'id': 'LI_NL1_4188102',
'display_id': 'npo-1',
'ext': 'mp4',
'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'Livestream',
'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'is_live': True,
},
'params': {
@ -283,58 +337,12 @@ class NPOLiveIE(NPOBaseIE):
live_id = self._search_regex(
r'data-prid="([^"]+)"', webpage, 'live id')
metadata = self._download_json(
'http://e.omroep.nl/metadata/%s' % live_id,
display_id, transform_source=strip_jsonp)
token = self._get_token(display_id)
formats = []
streams = metadata.get('streams')
if streams:
for stream in streams:
stream_type = stream.get('type').lower()
# smooth streaming is not supported
if stream_type in ['ss', 'ms']:
continue
stream_info = self._download_json(
'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
% (stream.get('url'), token),
display_id, 'Downloading %s JSON' % stream_type)
if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
continue
stream_url = self._download_json(
stream_info['stream'], display_id,
'Downloading %s URL' % stream_type,
'Unable to download %s URL' % stream_type,
transform_source=strip_jsonp, fatal=False)
if not stream_url:
continue
if stream_type == 'hds':
f4m_formats = self._extract_f4m_formats(stream_url, display_id)
# f4m downloader downloads only piece of live stream
for f4m_format in f4m_formats:
f4m_format['preference'] = -1
formats.extend(f4m_formats)
elif stream_type == 'hls':
formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
else:
formats.append({
'url': stream_url,
'preference': -10,
})
self._sort_formats(formats)
return {
'_type': 'url_transparent',
'url': 'npo:%s' % live_id,
'ie_key': NPOIE.ie_key(),
'id': live_id,
'display_id': display_id,
'title': self._live_title(metadata['titel']),
'description': metadata['info'],
'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
'formats': formats,
'is_live': True,
}
@ -416,7 +424,21 @@ class NPORadioFragmentIE(InfoExtractor):
}
class SchoolTVIE(InfoExtractor):
class NPODataMidEmbedIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
return {
'_type': 'url_transparent',
'ie_key': 'NPO',
'url': 'npo:%s' % video_id,
'display_id': display_id
}
class SchoolTVIE(NPODataMidEmbedIE):
IE_NAME = 'schooltv'
_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
@ -435,16 +457,24 @@ class SchoolTVIE(InfoExtractor):
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
return {
'_type': 'url_transparent',
'ie_key': 'NPO',
'url': 'npo:%s' % video_id,
'display_id': display_id
class HetKlokhuisIE(NPODataMidEmbedIE):
IE_NAME = 'hetklokhuis'
_VALID_URL = r'https?://(?:www\.)?hetklokhuis.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
'info_dict': {
'id': 'VPWON_1260528',
'display_id': 'Zwaartekrachtsgolven',
'ext': 'm4v',
'title': 'Het Klokhuis: Zwaartekrachtsgolven',
'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
'upload_date': '20170223',
},
'params': {
'skip_download': True
}
}

View File

@ -72,20 +72,41 @@ class OpenloadIE(InfoExtractor):
raise ExtractorError('File not found', expected=True)
ol_id = self._search_regex(
'<span[^>]+id="[^"]+"[^>]*>([0-9]+)</span>',
'<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
webpage, 'openload ID')
first_two_chars = int(float(ol_id[0:][:2]))
urlcode = []
num = 2
decoded = ''
a = ol_id[0:24]
b = []
for i in range(0, len(a), 8):
b.append(int(a[i:i + 8] or '0', 16))
ol_id = ol_id[24:]
j = 0
k = 0
while j < len(ol_id):
c = 128
d = 0
e = 0
f = 0
_more = True
while _more:
if j + 1 >= len(ol_id):
c = 143
f = int(ol_id[j:j + 2] or '0', 16)
j += 2
d += (f & 127) << e
e += 7
_more = f >= c
g = d ^ b[k % 3]
for i in range(4):
char_dec = (g >> 8 * i) & (c + 127)
char = compat_chr(char_dec)
if char != '#':
decoded += char
k += 1
while num < len(ol_id):
key = int(float(ol_id[num + 3:][:2]))
urlcode.append((key, compat_chr(int(float(ol_id[num:][:3])) - first_two_chars)))
num += 5
video_url = 'https://openload.co/stream/' + ''.join(
[value for _, value in sorted(urlcode, key=lambda x: x[0])])
video_url = 'https://openload.co/stream/%s?mime=true'
video_url = video_url % decoded
title = self._og_search_title(webpage, default=None) or self._search_regex(
r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,

View File

@ -0,0 +1,138 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
ExtractorError,
remove_end,
strip_or_none,
unified_timestamp,
urljoin,
)
class PacktPubBaseIE(InfoExtractor):
_PACKT_BASE = 'https://www.packtpub.com'
_MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
class PacktPubIE(PacktPubBaseIE):
_VALID_URL = r'https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
_TEST = {
'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
'md5': '1e74bd6cfd45d7d07666f4684ef58f70',
'info_dict': {
'id': '20530',
'ext': 'mp4',
'title': 'Project Intro',
'thumbnail': r're:(?i)^https?://.*\.jpg',
'timestamp': 1490918400,
'upload_date': '20170331',
},
}
def _handle_error(self, response):
if response.get('status') != 'success':
raise ExtractorError(
'% said: %s' % (self.IE_NAME, response['message']),
expected=True)
def _download_json(self, *args, **kwargs):
response = super(PacktPubIE, self)._download_json(*args, **kwargs)
self._handle_error(response)
return response
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
course_id, chapter_id, video_id = mobj.group(
'course_id', 'chapter_id', 'id')
video = self._download_json(
'%s/users/me/products/%s/chapters/%s/sections/%s'
% (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
'Downloading JSON video')['data']
content = video.get('content')
if not content:
raise ExtractorError('This video is locked', expected=True)
video_url = content['file']
metadata = self._download_json(
'%s/products/%s/chapters/%s/sections/%s/metadata'
% (self._MAPT_REST, course_id, chapter_id, video_id),
video_id)['data']
title = metadata['pageTitle']
course_title = metadata.get('title')
if course_title:
title = remove_end(title, ' - %s' % course_title)
timestamp = unified_timestamp(metadata.get('publicationDate'))
thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
}
class PacktPubCourseIE(PacktPubBaseIE):
_VALID_URL = r'(?P<url>https?://(?:www\.)?packtpub\.com/mapt/video/[^/]+/(?P<id>\d+))'
_TEST = {
'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215',
'info_dict': {
'id': '9781787122215',
'title': 'Learn Nodejs by building 12 projects [Video]',
},
'playlist_count': 90,
}
@classmethod
def suitable(cls, url):
return False if PacktPubIE.suitable(url) else super(
PacktPubCourseIE, cls).suitable(url)
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
url, course_id = mobj.group('url', 'id')
course = self._download_json(
'%s/products/%s/metadata' % (self._MAPT_REST, course_id),
course_id)['data']
entries = []
for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
if chapter.get('type') != 'chapter':
continue
children = chapter.get('children')
if not isinstance(children, list):
continue
chapter_info = {
'chapter': chapter.get('title'),
'chapter_number': chapter_num,
'chapter_id': chapter.get('id'),
}
for section in children:
if section.get('type') != 'section':
continue
section_url = section.get('seoUrl')
if not isinstance(section_url, compat_str):
continue
entry = {
'_type': 'url_transparent',
'url': urljoin(url + '/', section_url),
'title': strip_or_none(section.get('title')),
'description': clean_html(section.get('summary')),
'ie_key': PacktPubIE.ie_key(),
}
entry.update(chapter_info)
entries.append(entry)
return self.playlist_result(entries, course_id, course.get('title'))

View File

@ -40,7 +40,7 @@ class PluralsightIE(PluralsightBaseIE):
'info_dict': {
'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04',
'ext': 'mp4',
'title': 'Management of SQL Server - Demo Monitoring',
'title': 'Demo Monitoring',
'duration': 338,
},
'skip': 'Requires pluralsight account credentials',
@ -169,11 +169,10 @@ class PluralsightIE(PluralsightBaseIE):
collection = course['modules']
module, clip = None, None
clip = None
for module_ in collection:
if name in (module_.get('moduleName'), module_.get('name')):
module = module_
for clip_ in module_.get('clips', []):
clip_index = clip_.get('clipIndex')
if clip_index is None:
@ -187,7 +186,7 @@ class PluralsightIE(PluralsightBaseIE):
if not clip:
raise ExtractorError('Unable to resolve clip')
title = '%s - %s' % (module['title'], clip['title'])
title = clip['title']
QUALITIES = {
'low': {'width': 640, 'height': 480},

View File

@ -1,7 +1,9 @@
# coding: utf-8
from __future__ import unicode_literals
import functools
import itertools
import operator
# import os
import re
@ -18,6 +20,7 @@ from ..utils import (
js_to_json,
orderedSet,
# sanitized_Request,
remove_quotes,
str_to_int,
)
# from ..aes import (
@ -129,9 +132,32 @@ class PornHubIE(InfoExtractor):
tv_webpage = dl_webpage('tv')
video_url = self._search_regex(
r'<video[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//.+?)\1', tv_webpage,
'video url', group='url')
assignments = self._search_regex(
r'(var.+?mediastring.+?)</script>', tv_webpage,
'encoded url').split(';')
js_vars = {}
def parse_js_value(inp):
inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
if '+' in inp:
inps = inp.split('+')
return functools.reduce(
operator.concat, map(parse_js_value, inps))
inp = inp.strip()
if inp in js_vars:
return js_vars[inp]
return remove_quotes(inp)
for assn in assignments:
assn = assn.strip()
if not assn:
continue
assn = re.sub(r'var\s+', '', assn)
vname, value = assn.split('=', 1)
js_vars[vname] = parse_js_value(value)
video_url = js_vars['mediastring']
title = self._search_regex(
r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)

View File

@ -300,6 +300,21 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
'skip_download': True,
},
},
{
# title in <h2 class="subtitle">
'url': 'http://www.prosieben.de/stars/oscar-award/videos/jetzt-erst-enthuellt-das-geheimnis-von-emma-stones-oscar-robe-clip',
'info_dict': {
'id': '4895826',
'ext': 'mp4',
'title': 'Jetzt erst enthüllt: Das Geheimnis von Emma Stones Oscar-Robe',
'description': 'md5:e5ace2bc43fadf7b63adc6187e9450b9',
'upload_date': '20170302',
},
'params': {
'skip_download': True,
},
'skip': 'geo restricted to Germany',
},
{
# geo restricted to Germany
'url': 'http://www.kabeleinsdoku.de/tv/mayday-alarm-im-cockpit/video/102-notlandung-im-hudson-river-ganze-folge',
@ -338,6 +353,7 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
r'<header class="module_header">\s*<h2>([^<]+)</h2>\s*</header>',
r'<h2 class="video-title" itemprop="name">\s*(.+?)</h2>',
r'<div[^>]+id="veeseoTitle"[^>]*>(.+?)</div>',
r'<h2[^>]+class="subtitle"[^>]*>([^<]+)</h2>',
]
_DESCRIPTION_REGEXES = [
r'<p itemprop="description">\s*(.+?)</p>',
@ -369,7 +385,9 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE):
def _extract_clip(self, url, webpage):
clip_id = self._html_search_regex(
self._CLIPID_REGEXES, webpage, 'clip id')
title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title')
title = self._html_search_regex(
self._TITLE_REGEXES, webpage, 'title',
default=None) or self._og_search_title(webpage)
info = self._extract_video_info(url, clip_id)
description = self._html_search_regex(
self._DESCRIPTION_REGEXES, webpage, 'description', default=None)

View File

@ -1,23 +1,40 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..compat import (
compat_urlparse,
compat_str,
)
from ..utils import (
determine_ext,
ExtractorError,
determine_ext,
find_xpath_attr,
fix_xml_ampersands,
GeoRestrictedError,
int_or_none,
parse_duration,
strip_or_none,
try_get,
unified_strdate,
unified_timestamp,
update_url_query,
urljoin,
xpath_text,
)
class RaiBaseIE(InfoExtractor):
def _extract_relinker_formats(self, relinker_url, video_id):
_UUID_RE = r'[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}'
_GEO_COUNTRIES = ['IT']
_GEO_BYPASS = False
def _extract_relinker_info(self, relinker_url, video_id):
formats = []
geoprotection = None
is_live = None
duration = None
for platform in ('mon', 'flash', 'native'):
relinker = self._download_xml(
@ -27,9 +44,27 @@ class RaiBaseIE(InfoExtractor):
query={'output': 45, 'pl': platform},
headers=self.geo_verification_headers())
media_url = find_xpath_attr(relinker, './url', 'type', 'content').text
if not geoprotection:
geoprotection = xpath_text(
relinker, './geoprotection', default=None) == 'Y'
if not is_live:
is_live = xpath_text(
relinker, './is_live', default=None) == 'Y'
if not duration:
duration = parse_duration(xpath_text(
relinker, './duration', default=None))
url_elem = find_xpath_attr(relinker, './url', 'type', 'content')
if url_elem is None:
continue
media_url = url_elem.text
# This does not imply geo restriction (e.g.
# http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html)
if media_url == 'http://download.rai.it/video_no_available.mp4':
self.raise_geo_restricted()
continue
ext = determine_ext(media_url)
if (ext == 'm3u8' and platform != 'mon') or (ext == 'f4m' and platform != 'flash'):
@ -53,35 +88,225 @@ class RaiBaseIE(InfoExtractor):
'format_id': 'http-%d' % bitrate if bitrate > 0 else 'http',
})
return formats
if not formats and geoprotection is True:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
def _extract_from_content_id(self, content_id, base_url):
return dict((k, v) for k, v in {
'is_live': is_live,
'duration': duration,
'formats': formats,
}.items() if v is not None)
class RaiPlayIE(RaiBaseIE):
_VALID_URL = r'(?P<url>https?://(?:www\.)?raiplay\.it/.+?-(?P<id>%s)\.html)' % RaiBaseIE._UUID_RE
_TESTS = [{
'url': 'http://www.raiplay.it/video/2016/10/La-Casa-Bianca-e06118bb-59a9-4636-b914-498e4cfd2c66.html?source=twitter',
'md5': '340aa3b7afb54bfd14a8c11786450d76',
'info_dict': {
'id': 'e06118bb-59a9-4636-b914-498e4cfd2c66',
'ext': 'mp4',
'title': 'La Casa Bianca',
'alt_title': 'S2016 - Puntata del 23/10/2016',
'description': 'md5:a09d45890850458077d1f68bb036e0a5',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 3',
'creator': 'Rai 3',
'duration': 3278,
'timestamp': 1477764300,
'upload_date': '20161029',
'series': 'La Casa Bianca',
'season': '2016',
},
}, {
'url': 'http://www.raiplay.it/video/2014/04/Report-del-07042014-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': '8970abf8caf8aef4696e7b1f2adfc696',
'info_dict': {
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4',
'title': 'Report del 07/04/2014',
'alt_title': 'S2013/14 - Puntata del 07/04/2014',
'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Rai 5',
'creator': 'Rai 5',
'duration': 6160,
'series': 'Report',
'season_number': 5,
'season': '2013/14',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://www.raiplay.it/video/2016/11/gazebotraindesi-efebe701-969c-4593-92f3-285f0d1ce750.html?',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
url, video_id = mobj.group('url', 'id')
media = self._download_json(
'%s?json' % url, video_id, 'Downloading video JSON')
title = media['name']
video = media['video']
relinker_info = self._extract_relinker_info(video['contentUrl'], video_id)
self._sort_formats(relinker_info['formats'])
thumbnails = []
if 'images' in media:
for _, value in media.get('images').items():
if value:
thumbnails.append({
'url': value.replace('[RESOLUTION]', '600x400')
})
timestamp = unified_timestamp(try_get(
media, lambda x: x['availabilities'][0]['start'], compat_str))
info = {
'id': video_id,
'title': title,
'alt_title': media.get('subtitle'),
'description': media.get('description'),
'uploader': media.get('channel'),
'creator': media.get('editor'),
'duration': parse_duration(video.get('duration')),
'timestamp': timestamp,
'thumbnails': thumbnails,
'series': try_get(
media, lambda x: x['isPartOf']['name'], compat_str),
'season_number': int_or_none(try_get(
media, lambda x: x['isPartOf']['numeroStagioni'])),
'season': media.get('stagione') or None,
}
info.update(relinker_info)
return info
class RaiIE(RaiBaseIE):
_VALID_URL = r'https?://[^/]+\.(?:rai\.(?:it|tv)|rainews\.it)/dl/.+?-(?P<id>%s)(?:-.+?)?\.html' % RaiBaseIE._UUID_RE
_TESTS = [{
# var uniquename = "ContentItem-..."
# data-id="ContentItem-..."
'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
'info_dict': {
'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
'ext': 'mp4',
'title': 'TG PRIMO TEMPO',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1758,
'upload_date': '20140612',
}
}, {
# with ContentItem in many metas
'url': 'http://www.rainews.it/dl/rainews/media/Weekend-al-cinema-da-Hollywood-arriva-il-thriller-di-Tate-Taylor-La-ragazza-del-treno-1632c009-c843-4836-bb65-80c33084a64b.html',
'info_dict': {
'id': '1632c009-c843-4836-bb65-80c33084a64b',
'ext': 'mp4',
'title': 'Weekend al cinema, da Hollywood arriva il thriller di Tate Taylor "La ragazza del treno"',
'description': 'I film in uscita questa settimana.',
'thumbnail': r're:^https?://.*\.png$',
'duration': 833,
'upload_date': '20161103',
}
}, {
# with ContentItem in og:url
'url': 'http://www.rai.it/dl/RaiTV/programmi/media/ContentItem-efb17665-691c-45d5-a60c-5301333cbb0c.html',
'md5': '11959b4e44fa74de47011b5799490adf',
'info_dict': {
'id': 'efb17665-691c-45d5-a60c-5301333cbb0c',
'ext': 'mp4',
'title': 'TG1 ore 20:00 del 03/11/2016',
'description': 'TG1 edizione integrale ore 20:00 del giorno 03/11/2016',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2214,
'upload_date': '20161103',
}
}, {
# drawMediaRaiTV(...)
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
'md5': '2dd727e61114e1ee9c47f0da6914e178',
'info_dict': {
'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
'ext': 'mp4',
'title': 'Il pacco',
'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
'thumbnail': r're:^https?://.*\.jpg$',
'upload_date': '20141221',
},
}, {
# initEdizione('ContentItem-...'
'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
'info_dict': {
'id': 'c2187016-8484-4e3a-8ac8-35e475b07303',
'ext': 'mp4',
'title': r're:TG1 ore \d{2}:\d{2} del \d{2}/\d{2}/\d{4}',
'duration': 2274,
'upload_date': '20170401',
},
'skip': 'Changes daily',
}, {
# HDS live stream with only relinker URL
'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
'info_dict': {
'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
'ext': 'flv',
'title': 'EuroNews',
},
'params': {
'skip_download': True,
},
}, {
# HLS live stream with ContentItem in og:url
'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
'info_dict': {
'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
'ext': 'mp4',
'title': 'La diretta di Rainews24',
},
'params': {
'skip_download': True,
},
}]
def _extract_from_content_id(self, content_id, url):
media = self._download_json(
'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-%s.html?json' % content_id,
content_id, 'Downloading video JSON')
title = media['name'].strip()
media_type = media['type']
if 'Audio' in media_type:
relinker_info = {
'formats': {
'format_id': media.get('formatoAudio'),
'url': media['audioUrl'],
'ext': media.get('formatoAudio'),
}
}
elif 'Video' in media_type:
relinker_info = self._extract_relinker_info(media['mediaUri'], content_id)
else:
raise ExtractorError('not a media file')
self._sort_formats(relinker_info['formats'])
thumbnails = []
for image_type in ('image', 'image_medium', 'image_300'):
thumbnail_url = media.get(image_type)
if thumbnail_url:
thumbnails.append({
'url': compat_urlparse.urljoin(base_url, thumbnail_url),
'url': compat_urlparse.urljoin(url, thumbnail_url),
})
formats = []
media_type = media['type']
if 'Audio' in media_type:
formats.append({
'format_id': media.get('formatoAudio'),
'url': media['audioUrl'],
'ext': media.get('formatoAudio'),
})
elif 'Video' in media_type:
formats.extend(self._extract_relinker_formats(media['mediaUri'], content_id))
self._sort_formats(formats)
else:
raise ExtractorError('not a media file')
subtitles = {}
captions = media.get('subtitlesUrl')
if captions:
@ -94,174 +319,90 @@ class RaiBaseIE(InfoExtractor):
'url': captions,
}]
return {
info = {
'id': content_id,
'title': media['name'],
'description': media.get('desc'),
'title': title,
'description': strip_or_none(media.get('desc')),
'thumbnails': thumbnails,
'uploader': media.get('author'),
'upload_date': unified_strdate(media.get('date')),
'duration': parse_duration(media.get('length')),
'formats': formats,
'subtitles': subtitles,
}
info.update(relinker_info)
class RaiTVIE(RaiBaseIE):
_VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/(?:[^/]+/)+(?:media|ondemand)/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
_TESTS = [
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html',
'md5': '8970abf8caf8aef4696e7b1f2adfc696',
'info_dict': {
'id': 'cb27157f-9dd0-4aee-b788-b1f67643a391',
'ext': 'mp4',
'title': 'Report del 07/04/2014',
'description': 'md5:f27c544694cacb46a078db84ec35d2d9',
'upload_date': '20140407',
'duration': 6160,
'thumbnail': r're:^https?://.*\.jpg$',
}
},
{
# no m3u8 stream
'url': 'http://www.raisport.rai.it/dl/raiSport/media/rassegna-stampa-04a9f4bd-b563-40cf-82a6-aad3529cb4a9.html',
# HDS download, MD5 is unstable
'info_dict': {
'id': '04a9f4bd-b563-40cf-82a6-aad3529cb4a9',
'ext': 'flv',
'title': 'TG PRIMO TEMPO',
'upload_date': '20140612',
'duration': 1758,
'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'Geo-restricted to Italy',
},
{
'url': 'http://www.rainews.it/dl/rainews/media/state-of-the-net-Antonella-La-Carpia-regole-virali-7aafdea9-0e5d-49d5-88a6-7e65da67ae13.html',
'md5': '35cf7c229f22eeef43e48b5cf923bef0',
'info_dict': {
'id': '7aafdea9-0e5d-49d5-88a6-7e65da67ae13',
'ext': 'mp4',
'title': 'State of the Net, Antonella La Carpia: regole virali',
'description': 'md5:b0ba04a324126903e3da7763272ae63c',
'upload_date': '20140613',
},
'skip': 'Error 404',
},
{
'url': 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-b4a49761-e0cc-4b14-8736-2729f6f73132-tg2.html',
'info_dict': {
'id': 'b4a49761-e0cc-4b14-8736-2729f6f73132',
'ext': 'mp4',
'title': 'Alluvione in Sardegna e dissesto idrogeologico',
'description': 'Edizione delle ore 20:30 ',
},
'skip': 'invalid urls',
},
{
'url': 'http://www.ilcandidato.rai.it/dl/ray/media/Il-Candidato---Primo-episodio-Le-Primarie-28e5525a-b495-45e8-a7c3-bc48ba45d2b6.html',
'md5': 'e57493e1cb8bc7c564663f363b171847',
'info_dict': {
'id': '28e5525a-b495-45e8-a7c3-bc48ba45d2b6',
'ext': 'mp4',
'title': 'Il Candidato - Primo episodio: "Le Primarie"',
'description': 'md5:364b604f7db50594678f483353164fb8',
'upload_date': '20140923',
'duration': 386,
'thumbnail': r're:^https?://.*\.jpg$',
}
},
]
return info
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_from_content_id(video_id, url)
class RaiIE(RaiBaseIE):
_VALID_URL = r'https?://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html'
_TESTS = [
{
'url': 'http://www.report.rai.it/dl/Report/puntata/ContentItem-0c7a664b-d0f4-4b2c-8835-3f82e46f433e.html',
'md5': '2dd727e61114e1ee9c47f0da6914e178',
'info_dict': {
'id': '59d69d28-6bb6-409d-a4b5-ed44096560af',
'ext': 'mp4',
'title': 'Il pacco',
'description': 'md5:4b1afae1364115ce5d78ed83cd2e5b3a',
'upload_date': '20141221',
},
},
{
# Direct relinker URL
'url': 'http://www.rai.tv/dl/RaiTV/dirette/PublishingBlock-1912dbbf-3f96-44c3-b4cf-523681fbacbc.html?channel=EuroNews',
# HDS live stream, MD5 is unstable
'info_dict': {
'id': '1912dbbf-3f96-44c3-b4cf-523681fbacbc',
'ext': 'flv',
'title': 'EuroNews',
},
'skip': 'Geo-restricted to Italy',
},
{
# Embedded content item ID
'url': 'http://www.tg1.rai.it/dl/tg1/2010/edizioni/ContentSet-9b6e0cba-4bef-4aef-8cf0-9f7f665b7dfb-tg1.html?item=undefined',
'md5': '84c1135ce960e8822ae63cec34441d63',
'info_dict': {
'id': '0960e765-62c8-474a-ac4b-7eb3e2be39c8',
'ext': 'mp4',
'title': 'TG1 ore 20:00 del 02/07/2016',
'upload_date': '20160702',
},
},
{
'url': 'http://www.rainews.it/dl/rainews/live/ContentItem-3156f2f2-dc70-4953-8e2f-70d7489d4ce9.html',
# HDS live stream, MD5 is unstable
'info_dict': {
'id': '3156f2f2-dc70-4953-8e2f-70d7489d4ce9',
'ext': 'flv',
'title': 'La diretta di Rainews24',
},
},
]
@classmethod
def suitable(cls, url):
return False if RaiTVIE.suitable(url) else super(RaiIE, cls).suitable(url)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
iframe_url = self._search_regex(
[r'<iframe[^>]+src="([^"]*/dl/[^"]+\?iframe\b[^"]*)"',
r'drawMediaRaiTV\(["\'](.+?)["\']'],
webpage, 'iframe', default=None)
if iframe_url:
if not iframe_url.startswith('http'):
iframe_url = compat_urlparse.urljoin(url, iframe_url)
return self.url_result(iframe_url)
content_item_id = None
content_item_url = self._html_search_meta(
('og:url', 'og:video', 'og:video:secure_url', 'twitter:url',
'twitter:player', 'jsonlink'), webpage, default=None)
if content_item_url:
content_item_id = self._search_regex(
r'initEdizione\((?P<q1>[\'"])ContentItem-(?P<content_id>[^\'"]+)(?P=q1)',
webpage, 'content item ID', group='content_id', default=None)
if content_item_id:
return self._extract_from_content_id(content_item_id, url)
r'ContentItem-(%s)' % self._UUID_RE, content_item_url,
'content item id', default=None)
relinker_url = compat_urlparse.urljoin(url, self._search_regex(
r'(?:var\s+videoURL|mediaInfo\.mediaUri)\s*=\s*(?P<q1>[\'"])(?P<url>(https?:)?//mediapolis\.rai\.it/relinker/relinkerServlet\.htm\?cont=\d+)(?P=q1)',
webpage, 'relinker URL', group='url'))
formats = self._extract_relinker_formats(relinker_url, video_id)
self._sort_formats(formats)
if not content_item_id:
content_item_id = self._search_regex(
r'''(?x)
(?:
(?:initEdizione|drawMediaRaiTV)\(|
<(?:[^>]+\bdata-id|var\s+uniquename)=
)
(["\'])
(?:(?!\1).)*\bContentItem-(?P<id>%s)
''' % self._UUID_RE,
webpage, 'content item id', default=None, group='id')
content_item_ids = set()
if content_item_id:
content_item_ids.add(content_item_id)
if video_id not in content_item_ids:
content_item_ids.add(video_id)
for content_item_id in content_item_ids:
try:
return self._extract_from_content_id(content_item_id, url)
except GeoRestrictedError:
raise
except ExtractorError:
pass
relinker_url = self._search_regex(
r'''(?x)
(?:
var\s+videoURL|
mediaInfo\.mediaUri
)\s*=\s*
([\'"])
(?P<url>
(?:https?:)?
//mediapolis(?:vod)?\.rai\.it/relinker/relinkerServlet\.htm\?
(?:(?!\1).)*\bcont=(?:(?!\1).)+)\1
''',
webpage, 'relinker URL', group='url')
relinker_info = self._extract_relinker_info(
urljoin(url, relinker_url), video_id)
self._sort_formats(relinker_info['formats'])
title = self._search_regex(
r'var\s+videoTitolo\s*=\s*([\'"])(?P<title>[^\'"]+)\1',
webpage, 'title', group='title', default=None) or self._og_search_title(webpage)
webpage, 'title', group='title',
default=None) or self._og_search_title(webpage)
return {
info = {
'id': video_id,
'title': title,
'formats': formats,
}
info.update(relinker_info)
return info

View File

@ -0,0 +1,122 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
float_or_none,
int_or_none,
try_get,
# unified_timestamp,
ExtractorError,
)
class RedBullTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?redbull\.tv/(?:video|film)/(?P<id>AP-\w+)'
_TESTS = [{
# film
'url': 'https://www.redbull.tv/video/AP-1Q756YYX51W11/abc-of-wrc',
'md5': 'fb0445b98aa4394e504b413d98031d1f',
'info_dict': {
'id': 'AP-1Q756YYX51W11',
'ext': 'mp4',
'title': 'ABC of...WRC',
'description': 'md5:5c7ed8f4015c8492ecf64b6ab31e7d31',
'duration': 1582.04,
# 'timestamp': 1488405786,
# 'upload_date': '20170301',
},
}, {
# episode
'url': 'https://www.redbull.tv/video/AP-1PMT5JCWH1W11/grime?playlist=shows:shows-playall:web',
'info_dict': {
'id': 'AP-1PMT5JCWH1W11',
'ext': 'mp4',
'title': 'Grime - Hashtags S2 E4',
'description': 'md5:334b741c8c1ce65be057eab6773c1cf5',
'duration': 904.6,
# 'timestamp': 1487290093,
# 'upload_date': '20170217',
'series': 'Hashtags',
'season_number': 2,
'episode_number': 4,
},
}, {
'url': 'https://www.redbull.tv/film/AP-1MSKKF5T92111/in-motion',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
session = self._download_json(
'https://api-v2.redbull.tv/session', video_id,
note='Downloading access token', query={
'build': '4.370.0',
'category': 'personal_computer',
'os_version': '1.0',
'os_family': 'http',
})
if session.get('code') == 'error':
raise ExtractorError('%s said: %s' % (
self.IE_NAME, session['message']))
auth = '%s %s' % (session.get('token_type', 'Bearer'), session['access_token'])
try:
info = self._download_json(
'https://api-v2.redbull.tv/content/%s' % video_id,
video_id, note='Downloading video information',
headers={'Authorization': auth}
)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
error_message = self._parse_json(
e.cause.read().decode(), video_id)['message']
raise ExtractorError('%s said: %s' % (
self.IE_NAME, error_message), expected=True)
raise
video = info['video_product']
title = info['title'].strip()
formats = self._extract_m3u8_formats(
video['url'], video_id, 'mp4', 'm3u8_native')
self._sort_formats(formats)
subtitles = {}
for _, captions in (try_get(
video, lambda x: x['attachments']['captions'],
dict) or {}).items():
if not captions or not isinstance(captions, list):
continue
for caption in captions:
caption_url = caption.get('url')
if not caption_url:
continue
ext = caption.get('format')
if ext == 'xml':
ext = 'ttml'
subtitles.setdefault(caption.get('lang') or 'en', []).append({
'url': caption_url,
'ext': ext,
})
subheading = info.get('subheading')
if subheading:
title += ' - %s' % subheading
return {
'id': video_id,
'title': title,
'description': info.get('long_description') or info.get(
'short_description'),
'duration': float_or_none(video.get('duration'), scale=1000),
# 'timestamp': unified_timestamp(info.get('published')),
'series': info.get('show_title'),
'season_number': int_or_none(info.get('season_number')),
'episode_number': int_or_none(info.get('episode_number')),
'formats': formats,
'subtitles': subtitles,
}

View File

@ -17,7 +17,7 @@ from ..utils import (
class RutubeIE(InfoExtractor):
IE_NAME = 'rutube'
IE_DESC = 'Rutube videos'
_VALID_URL = r'https?://rutube\.ru/(?:video|play/embed)/(?P<id>[\da-z]{32})'
_VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'
_TESTS = [{
'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
@ -39,8 +39,17 @@ class RutubeIE(InfoExtractor):
}, {
'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}, {
'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [mobj.group('url') for mobj in re.finditer(
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(

View File

@ -82,6 +82,9 @@ class RuutuIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds', fatal=False))
elif ext == 'mpd':
# video-only and audio-only streams are of different
# duration resulting in out of sync issue
continue
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))
else:

View File

@ -1,57 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import int_or_none
class SciVeeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?scivee\.tv/node/(?P<id>\d+)'
_TEST = {
'url': 'http://www.scivee.tv/node/62352',
'md5': 'b16699b74c9e6a120f6772a44960304f',
'info_dict': {
'id': '62352',
'ext': 'mp4',
'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
'description': 'md5:81f1710638e11a481358fab1b11059d7',
},
'skip': 'Not accessible from Travis CI server',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
# annotations XML is malformed
annotations = self._download_webpage(
'http://www.scivee.tv/assets/annotations/%s' % video_id, video_id, 'Downloading annotations')
title = self._html_search_regex(r'<title>([^<]+)</title>', annotations, 'title')
description = self._html_search_regex(r'<abstract>([^<]+)</abstract>', annotations, 'abstract', fatal=False)
filesize = int_or_none(self._html_search_regex(
r'<filesize>([^<]+)</filesize>', annotations, 'filesize', fatal=False))
formats = [
{
'url': 'http://www.scivee.tv/assets/audio/%s' % video_id,
'ext': 'mp3',
'format_id': 'audio',
},
{
'url': 'http://www.scivee.tv/assets/video/%s' % video_id,
'ext': 'mp4',
'format_id': 'video',
'filesize': filesize,
},
]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id,
'formats': formats,
}

View File

@ -89,7 +89,7 @@ class SenateISVPIE(InfoExtractor):
@staticmethod
def _search_iframe_url(webpage):
mobj = re.search(
r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]",
webpage)
if mobj:
return mobj.group('url')

View File

@ -121,7 +121,7 @@ class SoundcloudIE(InfoExtractor):
},
]
_CLIENT_ID = 'fDoItMDbsbZz8dY16ZzARCZmzgHBPotA'
_CLIENT_ID = '2t9loNQH90kzJcsFCODdigxfp325aq4z'
_IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf'
@staticmethod

View File

@ -65,7 +65,7 @@ class StreamableIE(InfoExtractor):
# to return video info like the title properly sometimes, and doesn't
# include info like the video duration
video = self._download_json(
'https://streamable.com/ajax/videos/%s' % video_id, video_id)
'https://ajax.streamable.com/videos/%s' % video_id, video_id)
# Format IDs:
# 0 The video is being uploaded

View File

@ -44,6 +44,10 @@ class TelecincoIE(MiTeleBaseIE):
}, {
'url': 'http://www.telecinco.es/espanasinirmaslejos/Espana-gran-destino-turistico_2_1240605043.html',
'only_matching': True,
}, {
# ooyala video
'url': 'http://www.cuatro.com/chesterinlove/a-carta/chester-chester_in_love-chester_edu_2_2331030022.html',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -2,15 +2,17 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
smuggle_url,
try_get,
)
class TeleQuebecIE(InfoExtractor):
_VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P<id>\d+)'
_TEST = {
_TESTS = [{
'url': 'http://zonevideo.telequebec.tv/media/20984/le-couronnement-de-new-york/couronnement-de-new-york',
'md5': 'fe95a0957e5707b1b01f5013e725c90f',
'info_dict': {
@ -18,10 +20,14 @@ class TeleQuebecIE(InfoExtractor):
'ext': 'mp4',
'title': 'Le couronnement de New York',
'description': 'md5:f5b3d27a689ec6c1486132b2d687d432',
'upload_date': '20160220',
'timestamp': 1455965438,
}
'upload_date': '20170201',
'timestamp': 1485972222,
}
}, {
# no description
'url': 'http://zonevideo.telequebec.tv/media/30261',
'only_matching': True,
}]
def _real_extract(self, url):
media_id = self._match_id(url)
@ -31,9 +37,13 @@ class TeleQuebecIE(InfoExtractor):
return {
'_type': 'url_transparent',
'id': media_id,
'url': smuggle_url('limelight:media:' + media_data['streamInfo']['sourceId'], {'geo_countries': ['CA']}),
'url': smuggle_url(
'limelight:media:' + media_data['streamInfo']['sourceId'],
{'geo_countries': ['CA']}),
'title': media_data['title'],
'description': media_data.get('descriptions', [{'text': None}])[0].get('text'),
'duration': int_or_none(media_data.get('durationInMilliseconds'), 1000),
'description': try_get(
media_data, lambda x: x['descriptions'][0]['text'], compat_str),
'duration': int_or_none(
media_data.get('durationInMilliseconds'), 1000),
'ie_key': 'LimelightMedia',
}

View File

@ -3,7 +3,10 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import qualities
from ..utils import (
int_or_none,
qualities,
)
class TheSceneIE(InfoExtractor):
@ -16,6 +19,11 @@ class TheSceneIE(InfoExtractor):
'ext': 'mp4',
'title': 'Narciso Rodriguez: Spring 2013 Ready-to-Wear',
'display_id': 'narciso-rodriguez-spring-2013-ready-to-wear',
'duration': 127,
'series': 'Style.com Fashion Shows',
'season': 'Ready To Wear Spring 2013',
'tags': list,
'categories': list,
},
}
@ -32,21 +40,29 @@ class TheSceneIE(InfoExtractor):
player = self._download_webpage(player_url, display_id)
info = self._parse_json(
self._search_regex(
r'(?m)var\s+video\s+=\s+({.+?});$', player, 'info json'),
r'(?m)video\s*:\s*({.+?}),$', player, 'info json'),
display_id)
video_id = info['id']
title = info['title']
qualities_order = qualities(('low', 'high'))
formats = [{
'format_id': '{0}-{1}'.format(f['type'].split('/')[0], f['quality']),
'url': f['src'],
'quality': qualities_order(f['quality']),
} for f in info['sources'][0]]
} for f in info['sources']]
self._sort_formats(formats)
return {
'id': info['id'],
'id': video_id,
'display_id': display_id,
'title': info['title'],
'title': title,
'formats': formats,
'thumbnail': info.get('poster_frame'),
'duration': int_or_none(info.get('duration')),
'series': info.get('series_title'),
'season': info.get('season_title'),
'tags': info.get('tags'),
'categories': info.get('categories'),
}

View File

@ -0,0 +1,81 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
)
class ToonGogglesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?toongoggles\.com/shows/(?P<show_id>\d+)(?:/[^/]+/episodes/(?P<episode_id>\d+))?'
_TESTS = [{
'url': 'http://www.toongoggles.com/shows/217143/bernard-season-2/episodes/217147/football',
'md5': '18289fc2b951eff6b953a9d8f01e6831',
'info_dict': {
'id': '217147',
'ext': 'mp4',
'title': 'Football',
'uploader_id': '1',
'description': 'Bernard decides to play football in order to be better than Lloyd and tries to beat him no matter how, he even cheats.',
'upload_date': '20160718',
'timestamp': 1468879330,
}
}, {
'url': 'http://www.toongoggles.com/shows/227759/om-nom-stories-around-the-world',
'info_dict': {
'id': '227759',
'title': 'Om Nom Stories Around The World',
},
'playlist_mincount': 11,
}]
def _call_api(self, action, page_id, query):
query.update({
'for_ng': 1,
'for_web': 1,
'show_meta': 1,
'version': 7.0,
})
return self._download_json('http://api.toongoggles.com/' + action, page_id, query=query)
def _parse_episode_data(self, episode_data):
title = episode_data['episode_name']
return {
'_type': 'url_transparent',
'id': episode_data['episode_id'],
'title': title,
'url': 'kaltura:513551:' + episode_data['entry_id'],
'thumbnail': episode_data.get('thumbnail_url'),
'description': episode_data.get('description'),
'duration': parse_duration(episode_data.get('hms')),
'series': episode_data.get('show_name'),
'season_number': int_or_none(episode_data.get('season_num')),
'episode_id': episode_data.get('episode_id'),
'episode': title,
'episode_number': int_or_none(episode_data.get('episode_num')),
'categories': episode_data.get('categories'),
'ie_key': 'Kaltura',
}
def _real_extract(self, url):
show_id, episode_id = re.match(self._VALID_URL, url).groups()
if episode_id:
episode_data = self._call_api('search', episode_id, {
'filter': 'episode',
'id': episode_id,
})['objects'][0]
return self._parse_episode_data(episode_data)
else:
show_data = self._call_api('getepisodesbyshow', show_id, {
'max': 1000000000,
'showid': show_id,
})
entries = []
for episode_data in show_data.get('objects', []):
entries.append(self._parse_episode_data(episode_data))
return self.playlist_result(entries, show_id, show_data.get('show_name'))

View File

@ -16,6 +16,7 @@ class TubiTvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?tubitv\.com/video/(?P<id>[0-9]+)'
_LOGIN_URL = 'http://tubitv.com/login'
_NETRC_MACHINE = 'tubitv'
_GEO_COUNTRIES = ['US']
_TEST = {
'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday',
'md5': '43ac06be9326f41912dc64ccf7a80320',

View File

@ -0,0 +1,90 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
try_get,
unified_timestamp,
)
class TunePkIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?tune\.pk/(?:video/|player/embed_player.php?.*?\bvid=)|
embed\.tune\.pk/play/
)
(?P<id>\d+)
'''
_TESTS = [{
'url': 'https://tune.pk/video/6919541/maudie-2017-international-trailer-1-ft-ethan-hawke-sally-hawkins',
'md5': '0c537163b7f6f97da3c5dd1e3ef6dd55',
'info_dict': {
'id': '6919541',
'ext': 'mp4',
'title': 'Maudie (2017) | International Trailer # 1 ft Ethan Hawke, Sally Hawkins',
'description': 'md5:eb5a04114fafef5cec90799a93a2d09c',
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1487327564,
'upload_date': '20170217',
'uploader': 'Movie Trailers',
'duration': 107,
'view_count': int,
}
}, {
'url': 'https://tune.pk/player/embed_player.php?vid=6919541&folder=2017/02/17/&width=600&height=350&autoplay=no',
'only_matching': True,
}, {
'url': 'https://embed.tune.pk/play/6919541?autoplay=no&ssl=yes&inline=true',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://tune.pk/video/%s' % video_id, video_id)
details = self._parse_json(
self._search_regex(
r'new\s+TunePlayer\(({.+?})\)\s*;\s*\n', webpage, 'tune player'),
video_id)['details']
video = details['video']
title = video.get('title') or self._og_search_title(
webpage, default=None) or self._html_search_meta(
'title', webpage, 'title', fatal=True)
formats = self._parse_jwplayer_formats(
details['player']['sources'], video_id)
self._sort_formats(formats)
description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'description', webpage, 'description')
thumbnail = video.get('thumb') or self._og_search_thumbnail(
webpage, default=None) or self._html_search_meta(
'thumbnail', webpage, 'thumbnail')
timestamp = unified_timestamp(video.get('date_added'))
uploader = try_get(
video, lambda x: x['uploader']['name'],
compat_str) or self._html_search_meta('author', webpage, 'author')
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('views'))
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
'view_count': view_count,
'formats': formats,
}

View File

@ -17,6 +17,9 @@ class TvigleIE(InfoExtractor):
IE_DESC = 'Интернет-телевидение Tvigle.ru'
_VALID_URL = r'https?://(?:www\.)?(?:tvigle\.ru/(?:[^/]+/)+(?P<display_id>[^/]+)/$|cloud\.tvigle\.ru/video/(?P<id>\d+))'
_GEO_BYPASS = False
_GEO_COUNTRIES = ['RU']
_TESTS = [
{
'url': 'http://www.tvigle.ru/video/sokrat/',
@ -72,8 +75,13 @@ class TvigleIE(InfoExtractor):
error_message = item.get('errorMessage')
if not videos and error_message:
if item.get('isGeoBlocked') is True:
self.raise_geo_restricted(
msg=error_message, countries=self._GEO_COUNTRIES)
else:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
'%s returned error: %s' % (self.IE_NAME, error_message),
expected=True)
title = item['title']
description = item.get('description')

View File

@ -31,9 +31,8 @@ class TVNoeIE(InfoExtractor):
r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
ifs_page = self._download_webpage(iframe_url, video_id)
jwplayer_data = self._parse_json(
self._find_jwplayer_data(ifs_page),
video_id, transform_source=js_to_json)
jwplayer_data = self._find_jwplayer_data(
ifs_page, video_id, transform_source=js_to_json)
info_dict = self._parse_jwplayer_data(
jwplayer_data, video_id, require_title=False, base_url=iframe_url)

View File

@ -225,7 +225,11 @@ class TVPlayIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
geo_country = self._search_regex(
r'https?://[^/]+\.([a-z]{2})', url,
'geo country', default=None)
if geo_country:
self._initialize_geo_bypass([geo_country.upper()])
video = self._download_json(
'http://playapi.mtgx.tv/v3/videos/%s' % video_id, video_id, 'Downloading video JSON')

View File

@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
@ -12,7 +14,7 @@ from ..utils import (
class TwentyFourVideoIE(InfoExtractor):
IE_NAME = '24video'
_VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx|sex|tube)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sex|tube))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.24video.net/video/view/1044982',
@ -43,10 +45,12 @@ class TwentyFourVideoIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
webpage = self._download_webpage(
'http://www.24video.sex/video/view/%s' % video_id, video_id)
'http://%s/video/view/%s' % (host, video_id), video_id)
title = self._og_search_title(webpage)
description = self._html_search_regex(
@ -72,11 +76,11 @@ class TwentyFourVideoIE(InfoExtractor):
# Sets some cookies
self._download_xml(
r'http://www.24video.sex/video/xml/%s?mode=init' % video_id,
r'http://%s/video/xml/%s?mode=init' % (host, video_id),
video_id, 'Downloading init XML')
video_xml = self._download_xml(
'http://www.24video.sex/video/xml/%s?mode=play' % video_id,
'http://%s/video/xml/%s?mode=play' % (host, video_id),
video_id, 'Downloading video XML')
video = xpath_element(video_xml, './/video', 'video', fatal=True)

View File

@ -12,7 +12,6 @@ from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
clean_html,
@ -24,6 +23,7 @@ from ..utils import (
parse_iso8601,
update_url_query,
urlencode_postdata,
urljoin,
)
@ -32,7 +32,7 @@ class TwitchBaseIE(InfoExtractor):
_API_BASE = 'https://api.twitch.tv'
_USHER_BASE = 'https://usher.ttvnw.net'
_LOGIN_URL = 'http://www.twitch.tv/login'
_LOGIN_URL = 'https://www.twitch.tv/login'
_CLIENT_ID = 'jzkbprff40iqj646a697cyrvl0zt2m6'
_NETRC_MACHINE = 'twitch'
@ -64,35 +64,22 @@ class TwitchBaseIE(InfoExtractor):
raise ExtractorError(
'Unable to login. Twitch said: %s' % message, expected=True)
login_page, handle = self._download_webpage_handle(
self._LOGIN_URL, None, 'Downloading login page')
# Some TOR nodes and public proxies are blocked completely
if 'blacklist_message' in login_page:
fail(clean_html(login_page))
login_form = self._hidden_inputs(login_page)
login_form.update({
'username': username,
'password': password,
})
redirect_url = handle.geturl()
def login_step(page, urlh, note, data):
form = self._hidden_inputs(page)
form.update(data)
page_url = urlh.geturl()
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=redirect_url, group='url')
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', page,
'post url', default=page_url, group='url')
post_url = urljoin(page_url, post_url)
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(redirect_url, post_url)
headers = {'Referer': redirect_url}
headers = {'Referer': page_url}
try:
response = self._download_json(
post_url, None, 'Logging in as %s' % username,
data=urlencode_postdata(login_form),
post_url, None, note,
data=urlencode_postdata(form),
headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
@ -101,11 +88,32 @@ class TwitchBaseIE(InfoExtractor):
fail(response['message'])
raise
if response.get('redirect'):
self._download_webpage(
response['redirect'], None, 'Downloading login redirect page',
redirect_url = urljoin(post_url, response['redirect'])
return self._download_webpage_handle(
redirect_url, None, 'Downloading login redirect page',
headers=headers)
login_page, handle = self._download_webpage_handle(
self._LOGIN_URL, None, 'Downloading login page')
# Some TOR nodes and public proxies are blocked completely
if 'blacklist_message' in login_page:
fail(clean_html(login_page))
redirect_page, handle = login_step(
login_page, handle, 'Logging in as %s' % username, {
'username': username,
'password': password,
})
if re.search(r'(?i)<form[^>]+id="two-factor-submit"', redirect_page) is not None:
# TODO: Add mechanism to request an SMS or phone call
tfa_token = self._get_tfa_info('two-factor authentication token')
login_step(redirect_page, handle, 'Submitting TFA token', {
'authy_token': tfa_token,
'remember_2fa': 'true',
})
def _prefer_source(self, formats):
try:
source = next(f for f in formats if f['format_id'] == 'Source')

View File

@ -17,12 +17,12 @@ from ..utils import (
class VevoBaseIE(InfoExtractor):
def _extract_json(self, webpage, video_id, item):
def _extract_json(self, webpage, video_id):
return self._parse_json(
self._search_regex(
r'window\.__INITIAL_STORE__\s*=\s*({.+?});\s*</script>',
webpage, 'initial store'),
video_id)['default'][item]
video_id)
class VevoIE(VevoBaseIE):
@ -139,6 +139,11 @@ class VevoIE(VevoBaseIE):
# no genres available
'url': 'http://www.vevo.com/watch/INS171400764',
'only_matching': True,
}, {
# Another case available only via the webpage; using streams/streamsV3 formats
# Geo-restricted to Netherlands/Germany
'url': 'http://www.vevo.com/watch/boostee/pop-corn-clip-officiel/FR1A91600909',
'only_matching': True,
}]
_VERSIONS = {
0: 'youtube', # only in AuthenticateVideo videoVersions
@ -193,7 +198,14 @@ class VevoIE(VevoBaseIE):
# https://github.com/rg3/youtube-dl/issues/9366)
if not video_versions:
webpage = self._download_webpage(url, video_id)
video_versions = self._extract_json(webpage, video_id, 'streams')[video_id][0]
json_data = self._extract_json(webpage, video_id)
if 'streams' in json_data.get('default', {}):
video_versions = json_data['default']['streams'][video_id][0]
else:
video_versions = [
value
for key, value in json_data['apollo']['data'].items()
if key.startswith('%s.streams' % video_id)]
uploader = None
artist = None
@ -207,7 +219,7 @@ class VevoIE(VevoBaseIE):
formats = []
for video_version in video_versions:
version = self._VERSIONS.get(video_version['version'])
version = self._VERSIONS.get(video_version.get('version'), 'generic')
version_url = video_version.get('url')
if not version_url:
continue
@ -339,7 +351,7 @@ class VevoPlaylistIE(VevoBaseIE):
if video_id:
return self.url_result('vevo:%s' % video_id, VevoIE.ie_key())
playlists = self._extract_json(webpage, playlist_id, '%ss' % playlist_kind)
playlists = self._extract_json(webpage, playlist_id)['default']['%ss' % playlist_kind]
playlist = (list(playlists.values())[0]
if playlist_kind == 'playlist' else playlists[playlist_id])

View File

@ -9,7 +9,7 @@ from .common import InfoExtractor
class VierIE(InfoExtractor):
IE_NAME = 'vier'
_VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
_VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
_TESTS = [{
'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
'info_dict': {
@ -23,6 +23,19 @@ class VierIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
'info_dict': {
'id': '2561614',
'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
'ext': 'mp4',
'title': 'ZO grappig: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s',
'description': 'Het spel is simpel: Annelien Coorevits en Rick Brandsteder krijgen telkens 2 dilemma\'s voorgeschoteld en ze MOETEN een keuze maken.',
},
'params': {
# m3u8 download
'skip_download': True,
},
}, {
'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
'only_matching': True,
@ -35,6 +48,7 @@ class VierIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
embed_id = mobj.group('embed_id')
display_id = mobj.group('display_id') or embed_id
site = mobj.group('site')
webpage = self._download_webpage(url, display_id)
@ -43,7 +57,7 @@ class VierIE(InfoExtractor):
webpage, 'video id')
application = self._search_regex(
[r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
webpage, 'application', default='vier_vod')
webpage, 'application', default=site + '_vod')
filename = self._search_regex(
[r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
webpage, 'filename')
@ -68,13 +82,19 @@ class VierIE(InfoExtractor):
class VierVideosIE(InfoExtractor):
IE_NAME = 'vier:videos'
_VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
_VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
_TESTS = [{
'url': 'http://www.vier.be/demoestuin/videos',
'info_dict': {
'id': 'demoestuin',
},
'playlist_mincount': 153,
}, {
'url': 'http://www.vijf.be/temptationisland/videos',
'info_dict': {
'id': 'temptationisland',
},
'playlist_mincount': 159,
}, {
'url': 'http://www.vier.be/demoestuin/videos?page=6',
'info_dict': {
@ -92,6 +112,7 @@ class VierVideosIE(InfoExtractor):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
program = mobj.group('program')
site = mobj.group('site')
page_id = mobj.group('page')
if page_id:
@ -105,13 +126,13 @@ class VierVideosIE(InfoExtractor):
entries = []
for current_page_id in itertools.count(start_page):
current_page = self._download_webpage(
'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id),
program,
'Downloading page %d' % (current_page_id + 1))
page_entries = [
self.url_result('http://www.vier.be' + video_url, 'Vier')
self.url_result('http://www.' + site + '.be' + video_url, 'Vier')
for video_url in re.findall(
r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
entries.extend(page_entries)
if page_id or '>Meer<' not in current_page:
break

View File

@ -44,7 +44,7 @@ class ViuBaseIE(InfoExtractor):
class ViuIE(ViuBaseIE):
_VALID_URL = r'(?:viu:|https?://www\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
_VALID_URL = r'(?:viu:|https?://[^/]+\.viu\.com/[a-z]{2}/media/)(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.viu.com/en/media/1116705532?containerId=playlist-22168059',
'info_dict': {
@ -69,6 +69,9 @@ class ViuIE(ViuBaseIE):
'skip_download': 'm3u8 download',
},
'skip': 'Geo-restricted to Indonesia',
}, {
'url': 'https://india.viu.com/en/media/1126286865',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -432,8 +432,7 @@ class VKIE(VKBaseIE):
})
elif format_id == 'hls':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4',
entry_protocol='m3u8' if is_live else 'm3u8_native',
format_url, video_id, 'mp4', 'm3u8_native',
m3u8_id=format_id, fatal=False, live=is_live))
elif format_id == 'rtmp':
formats.append({

View File

@ -0,0 +1,80 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .brightcove import BrightcoveNewIE
from ..utils import (
int_or_none,
parse_age_limit,
smuggle_url,
unescapeHTML,
)
class VrakIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vrak\.tv/videos\?.*?\btarget=(?P<id>[\d.]+)'
_TEST = {
'url': 'http://www.vrak.tv/videos?target=1.2306782&filtre=emission&id=1.1806721',
'info_dict': {
'id': '5345661243001',
'ext': 'mp4',
'title': 'Obésité, film de hockey et Roseline Filion',
'timestamp': 1488492126,
'upload_date': '20170302',
'uploader_id': '2890187628001',
'creator': 'VRAK.TV',
'age_limit': 8,
'series': 'ALT (Actualité Légèrement Tordue)',
'episode': 'Obésité, film de hockey et Roseline Filion',
'tags': list,
},
'params': {
'skip_download': True,
},
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/2890187628001/default_default/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<h\d\b[^>]+\bclass=["\']videoTitle["\'][^>]*>([^<]+)',
webpage, 'title', default=None) or self._og_search_title(webpage)
content = self._parse_json(
self._search_regex(
r'data-player-options-content=(["\'])(?P<content>{.+?})\1',
webpage, 'content', default='{}', group='content'),
video_id, transform_source=unescapeHTML)
ref_id = content.get('refId') or self._search_regex(
r'refId&quot;:&quot;([^&]+)&quot;', webpage, 'ref id')
brightcove_id = self._search_regex(
r'''(?x)
java\.lang\.String\s+value\s*=\s*["']brightcove\.article\.\d+\.%s
[^>]*
java\.lang\.String\s+value\s*=\s*["'](\d+)
''' % re.escape(ref_id), webpage, 'brightcove id')
return {
'_type': 'url_transparent',
'ie_key': BrightcoveNewIE.ie_key(),
'url': smuggle_url(
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
{'geo_countries': ['CA']}),
'id': brightcove_id,
'description': content.get('description'),
'creator': content.get('brand'),
'age_limit': parse_age_limit(content.get('rating')),
'series': content.get('showName') or content.get(
'episodeName'), # this is intentional
'season_number': int_or_none(content.get('seasonNumber')),
'episode': title,
'episode_number': int_or_none(content.get('episodeNumber')),
'tags': content.get('tags', []),
}

191
youtube_dl/extractor/vrv.py Normal file
View File

@ -0,0 +1,191 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import json
import hashlib
import hmac
import random
import string
import time
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_urlparse,
)
from ..utils import (
float_or_none,
int_or_none,
)
class VRVBaseIE(InfoExtractor):
_API_DOMAIN = None
_API_PARAMS = {}
_CMS_SIGNING = {}
def _call_api(self, path, video_id, note, data=None):
base_url = self._API_DOMAIN + '/core/' + path
encoded_query = compat_urllib_parse_urlencode({
'oauth_consumer_key': self._API_PARAMS['oAuthKey'],
'oauth_nonce': ''.join([random.choice(string.ascii_letters) for _ in range(32)]),
'oauth_signature_method': 'HMAC-SHA1',
'oauth_timestamp': int(time.time()),
'oauth_version': '1.0',
})
headers = self.geo_verification_headers()
if data:
data = json.dumps(data).encode()
headers['Content-Type'] = 'application/json'
method = 'POST' if data else 'GET'
base_string = '&'.join([method, compat_urlparse.quote(base_url, ''), compat_urlparse.quote(encoded_query, '')])
oauth_signature = base64.b64encode(hmac.new(
(self._API_PARAMS['oAuthSecret'] + '&').encode('ascii'),
base_string.encode(), hashlib.sha1).digest()).decode()
encoded_query += '&oauth_signature=' + compat_urlparse.quote(oauth_signature, '')
return self._download_json(
'?'.join([base_url, encoded_query]), video_id,
note='Downloading %s JSON metadata' % note, headers=headers, data=data)
def _call_cms(self, path, video_id, note):
if not self._CMS_SIGNING:
self._CMS_SIGNING = self._call_api('index', video_id, 'CMS Signing')['cms_signing']
return self._download_json(
self._API_DOMAIN + path, video_id, query=self._CMS_SIGNING,
note='Downloading %s JSON metadata' % note, headers=self.geo_verification_headers())
def _set_api_params(self, webpage, video_id):
if not self._API_PARAMS:
self._API_PARAMS = self._parse_json(self._search_regex(
r'window\.__APP_CONFIG__\s*=\s*({.+?})</script>',
webpage, 'api config'), video_id)['cxApiParams']
self._API_DOMAIN = self._API_PARAMS.get('apiDomain', 'https://api.vrv.co')
def _get_cms_resource(self, resource_key, video_id):
return self._call_api(
'cms_resource', video_id, 'resource path', data={
'resource_key': resource_key,
})['__links__']['cms_resource']['href']
class VRVIE(VRVBaseIE):
IE_NAME = 'vrv'
_VALID_URL = r'https?://(?:www\.)?vrv\.co/watch/(?P<id>[A-Z0-9]+)'
_TEST = {
'url': 'https://vrv.co/watch/GR9PNZ396/Hidden-America-with-Jonah-Ray:BOSTON-WHERE-THE-PAST-IS-THE-PRESENT',
'info_dict': {
'id': 'GR9PNZ396',
'ext': 'mp4',
'title': 'BOSTON: WHERE THE PAST IS THE PRESENT',
'description': 'md5:4ec8844ac262ca2df9e67c0983c6b83f',
'uploader_id': 'seeso',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id,
headers=self.geo_verification_headers())
media_resource = self._parse_json(self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*({.+?})</script>',
webpage, 'inital state'), video_id).get('watch', {}).get('mediaResource') or {}
video_data = media_resource.get('json')
if not video_data:
self._set_api_params(webpage, video_id)
episode_path = self._get_cms_resource(
'cms:/episodes/' + video_id, video_id)
video_data = self._call_cms(episode_path, video_id, 'video')
title = video_data['title']
streams_json = media_resource.get('streams', {}).get('json', {})
if not streams_json:
self._set_api_params(webpage, video_id)
streams_path = video_data['__links__']['streams']['href']
streams_json = self._call_cms(streams_path, video_id, 'streams')
audio_locale = streams_json.get('audio_locale')
formats = []
for stream_id, stream in streams_json.get('streams', {}).get('adaptive_hls', {}).items():
stream_url = stream.get('url')
if not stream_url:
continue
stream_id = stream_id or audio_locale
m3u8_formats = self._extract_m3u8_formats(
stream_url, video_id, 'mp4', m3u8_id=stream_id,
note='Downloading %s m3u8 information' % stream_id,
fatal=False)
if audio_locale:
for f in m3u8_formats:
f['language'] = audio_locale
formats.extend(m3u8_formats)
self._sort_formats(formats)
thumbnails = []
for thumbnail in video_data.get('images', {}).get('thumbnails', []):
thumbnail_url = thumbnail.get('source')
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,
'formats': formats,
'thumbnails': thumbnails,
'description': video_data.get('description'),
'duration': float_or_none(video_data.get('duration_ms'), 1000),
'uploader_id': video_data.get('channel_id'),
'series': video_data.get('series_title'),
'season': video_data.get('season_title'),
'season_number': int_or_none(video_data.get('season_number')),
'season_id': video_data.get('season_id'),
'episode': title,
'episode_number': int_or_none(video_data.get('episode_number')),
'episode_id': video_data.get('production_episode_id'),
}
class VRVSeriesIE(VRVBaseIE):
IE_NAME = 'vrv:series'
_VALID_URL = r'https?://(?:www\.)?vrv\.co/series/(?P<id>[A-Z0-9]+)'
_TEST = {
'url': 'https://vrv.co/series/G68VXG3G6/The-Perfect-Insider',
'info_dict': {
'id': 'G68VXG3G6',
},
'playlist_mincount': 11,
}
def _real_extract(self, url):
series_id = self._match_id(url)
webpage = self._download_webpage(
url, series_id,
headers=self.geo_verification_headers())
self._set_api_params(webpage, series_id)
seasons_path = self._get_cms_resource(
'cms:/seasons?series_id=' + series_id, series_id)
seasons_data = self._call_cms(seasons_path, series_id, 'seasons')
entries = []
for season in seasons_data.get('items', []):
episodes_path = season['__links__']['season/episodes']['href']
episodes = self._call_cms(episodes_path, series_id, 'episodes')
for episode in episodes.get('items', []):
episode_id = episode['id']
entries.append(self.url_result(
'https://vrv.co/watch/' + episode_id,
'VRV', episode_id, episode.get('title')))
return self.playlist_result(entries, series_id)

View File

@ -19,9 +19,10 @@ class WDRBaseIE(InfoExtractor):
def _extract_wdr_video(self, webpage, display_id):
# for wdr.de the data-extension is in a tag with the class "mediaLink"
# for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn"
# for wdrmaus its in a link to the page in a multiline "videoLink"-tag
# for wdrmaus, in a tag with the class "videoButton" (previously a link
# to the page in a multiline "videoLink"-tag)
json_metadata = self._html_search_regex(
r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
r'class=(?:"(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b[^"]*"[^>]+|"videoLink\b[^"]*"[\s]*>\n[^\n]*)data-extension="([^"]+)"',
webpage, 'media link', default=None, flags=re.MULTILINE)
if not json_metadata:
@ -32,7 +33,7 @@ class WDRBaseIE(InfoExtractor):
jsonp_url = media_link_obj['mediaObj']['url']
metadata = self._download_json(
jsonp_url, 'metadata', transform_source=strip_jsonp)
jsonp_url, display_id, transform_source=strip_jsonp)
metadata_tracker_data = metadata['trackerData']
metadata_media_resource = metadata['mediaResource']
@ -161,23 +162,23 @@ class WDRIE(WDRBaseIE):
{
'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
'info_dict': {
'id': 'mdb-1096487',
'ext': 'flv',
'id': 'mdb-1323501',
'ext': 'mp4',
'upload_date': 're:^[0-9]{8}$',
'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$',
'description': '- Die Sendung mit der Maus -',
'description': 'Die Seite mit der Maus -',
},
'skip': 'The id changes from week to week because of the new episode'
},
{
'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/achterbahn.php5',
'url': 'http://www.wdrmaus.de/filme/sachgeschichten/achterbahn.php5',
'md5': '803138901f6368ee497b4d195bb164f2',
'info_dict': {
'id': 'mdb-186083',
'ext': 'mp4',
'upload_date': '20130919',
'title': 'Sachgeschichte - Achterbahn ',
'description': '- Die Sendung mit der Maus -',
'description': 'Die Seite mit der Maus -',
},
},
{
@ -186,7 +187,7 @@ class WDRIE(WDRBaseIE):
'info_dict': {
'id': 'mdb-869971',
'ext': 'flv',
'title': 'Funkhaus Europa Livestream',
'title': 'COSMO Livestream',
'description': 'md5:2309992a6716c347891c045be50992e4',
'upload_date': '20160101',
},

View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor
from ..utils import (
decode_packed_codes,
determine_ext,
ExtractorError,
int_or_none,
NO_DEFAULT,
@ -26,6 +27,7 @@ class XFileShareIE(InfoExtractor):
('vidto.me', 'Vidto'),
('streamin.to', 'Streamin.To'),
('xvidstage.com', 'XVIDSTAGE'),
('vidabc.com', 'Vid ABC'),
)
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
@ -95,6 +97,16 @@ class XFileShareIE(InfoExtractor):
# removed by administrator
'url': 'http://xvidstage.com/amfy7atlkx25',
'only_matching': True,
}, {
'url': 'http://vidabc.com/i8ybqscrphfv',
'info_dict': {
'id': 'i8ybqscrphfv',
'ext': 'mp4',
'title': 're:Beauty and the Beast 2017',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -133,31 +145,45 @@ class XFileShareIE(InfoExtractor):
webpage, 'title', default=None) or self._og_search_title(
webpage, default=None) or video_id).strip()
def extract_video_url(default=NO_DEFAULT):
return self._search_regex(
(r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
webpage, 'file url', default=default, group='url')
def extract_formats(default=NO_DEFAULT):
urls = []
for regex in (
r'file\s*:\s*(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1',
r'file_link\s*=\s*(["\'])(?P<url>http(?:(?!\1).)+)\1',
r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http(?:(?!\2).)+)\2\)',
r'<embed[^>]+src=(["\'])(?P<url>http(?:(?!\1).)+\.(?:m3u8|mp4|flv)(?:(?!\1).)*)\1'):
for mobj in re.finditer(regex, webpage):
video_url = mobj.group('url')
if video_url not in urls:
urls.append(video_url)
formats = []
for video_url in urls:
if determine_ext(video_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False))
else:
formats.append({
'url': video_url,
'format_id': 'sd',
})
if not formats and default is not NO_DEFAULT:
return default
self._sort_formats(formats)
return formats
video_url = extract_video_url(default=None)
formats = extract_formats(default=None)
if not video_url:
if not formats:
webpage = decode_packed_codes(self._search_regex(
r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
webpage, 'packed code'))
video_url = extract_video_url()
formats = extract_formats()
thumbnail = self._search_regex(
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)
formats = [{
'format_id': 'sd',
'url': video_url,
'quality': 1,
}]
return {
'id': video_id,
'title': title,

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