Compare commits

..

170 Commits

Author SHA1 Message Date
ab03c0b47c release 2015.10.23 2015-10-23 09:33:05 +02:00
7690787553 [crunchyroll] Improve subtitle regex (Closes #7262) 2015-10-22 20:34:11 +06:00
a65402ef42 [bbc.co.uk:article] Add new extractor (#7257) 2015-10-22 21:13:03 +08:00
7033bc1a51 [bbc] Fix test_BBC_9 2015-10-22 21:12:29 +08:00
89d5fbf354 [iqiyi] Update key 2015-10-22 17:47:11 +08:00
8c3533ba97 [adultswim] Don't default to the native m3u8 downloader (closes #7243)
Some of the streams are encrypted, which is not supported .
2015-10-21 23:57:23 +02:00
44d6dd08b2 [facebook] Fix extraction (Closes #7252) 2015-10-21 21:35:57 +06:00
cc449417c4 [vine] Use _search_regex for JSON data (Closes #7254, closes #7255) 2015-10-21 20:35:22 +06:00
7308b8cb3d [stitcher] Improve (Closes #7162, closes #7228) 2015-10-20 23:12:13 +06:00
4211c83aa4 [stitcher] Add extractor
Stitcher review updates

Removed re import

Stitcher review updates
2015-10-20 23:11:26 +06:00
d01949dc89 [utils:js_to_json] Fix bad escape in double quoted strings 2015-10-20 23:09:51 +06:00
63a6494834 Merge pull request #7242 from lalinsky/vimeo-seed-status
[vimeo] Fix error parsing
2015-10-20 20:57:12 +06:00
8bea039b83 [vimeo] New test, fixed one older test 2015-10-20 16:38:44 +02:00
d65889bbc0 [vidme] Update test 2015-10-20 20:18:23 +06:00
4a8963770e [vidme] Use original vid.me title template for untitled videos 2015-10-20 20:17:54 +06:00
5b0aa2c7b1 Merge pull request #7237 from lalinsky/vidme2
[vidme] Stream URL fallback, better error message for suspended videos
2015-10-20 20:14:12 +06:00
b6aa99aff8 [vimeo] Fix error parsing 2015-10-20 10:31:32 +02:00
0be30bafa4 [vidme] Stream URL fallback, better error message for suspended videos 2015-10-19 20:53:27 +02:00
7b091c370c [zdf] Modernize and PEP 8 2015-10-19 01:48:05 +06:00
334b5c3b72 Merge pull request #7225 from kennell/master
[zdf] Extract thumbnails
2015-10-19 01:30:14 +06:00
b7cedb1604 simplify thumbnail dict building 2015-10-18 21:25:26 +02:00
2038ad6ee7 [README.md] Add uploader extraction sample in example extractor 2015-10-19 01:12:41 +06:00
b243340f0c check if key attrib matches resolution pattern 2015-10-18 21:07:52 +02:00
8cc83d301d use int_or_none, check if attrib exists, remove thumbnail 2015-10-18 20:47:42 +02:00
d762f86e94 [ok] Extend _VALID_URL 2015-10-19 00:11:16 +06:00
264b23e1a4 adds thumbnail support for ZDF Mediathek extractor 2015-10-18 19:56:22 +02:00
a6e0afa2bb release 2015.10.18 2015-10-18 19:23:40 +02:00
4285a47f40 Merge pull request #7208 from yan12125/letv-fix
[Letv] Fix extraction
2015-10-18 22:32:10 +08:00
e36963e0eb [eagleplatform] Identify hls formats 2015-10-18 20:24:33 +06:00
dedd35c6bc [viewster] Fix failing m3u8 2015-10-18 19:59:18 +06:00
608945d44a [canalc2] Fix test 2015-10-18 19:27:22 +06:00
b1bf063503 [canalc2] Extract duration 2015-10-18 19:27:05 +06:00
14bddf35fb [canalc2] Add ext 2015-10-18 19:23:52 +06:00
ef6c868f23 [canalc2] Improve some regexes 2015-10-18 19:23:31 +06:00
6682049dee [canalc2] Improve rtmp extraction 2015-10-18 19:19:43 +06:00
b0f001a6cb [canalc2] fix info extraction 2015-10-18 19:06:53 +06:00
dd67702a3e [imdb] Fix extraction (fixes #7220) 2015-10-18 14:13:06 +02:00
05a3879f1c [letv] Update M3U8's MIME type
The new MIME type appears in the following places:
https://www.iana.org/assignments/media-types/media-types.xhtml#application
https://hg.python.org/cpython/file/tip/Lib/mimetypes.py
2015-10-18 19:19:46 +08:00
4a7b790384 [twitter:card] Support YouTube embeds 2015-10-18 19:07:37 +08:00
09ff81316e Merge branch 'atomicdryad-pr-twitter' 2015-10-18 18:44:21 +08:00
c88aec845a [twitter] Fix short URL extraction 2015-10-18 18:23:56 +08:00
77a54b6a65 [twitter:card] Use _html_search_regex 2015-10-18 18:08:24 +08:00
575036b405 [twitter] Simplify and improve 2015-10-18 18:04:13 +08:00
f6dfd6603a [twitter] Use _html_search_regex 2015-10-18 17:18:01 +08:00
e04edad621 [twitter] Inherit from InfoExtractor directly 2015-10-18 17:16:57 +08:00
f322bfb063 [twitter:card] Remove unneeded 'ext' 2015-10-18 17:15:47 +08:00
014e880372 [twitter] Add IE_NAMEs 2015-10-18 17:13:58 +08:00
01d22d4703 [twitter] Use _download_xml 2015-10-18 17:11:55 +08:00
48aae2d2cf [twitter] Update tests 2015-10-18 17:07:48 +08:00
c571dea953 Merge branch 'pr-twitter' of https://github.com/atomicdryad/youtube-dl into atomicdryad-pr-twitter 2015-10-18 16:49:56 +08:00
8b172c2e10 [YoutubeDL] Use DataHandler 2015-10-18 13:44:22 +08:00
0a67a3632b [compat] Add compat_urllib_request_DataHandler 2015-10-18 13:44:21 +08:00
985e4fdc07 [downloader/hls] Add headers only for http(s) URLs
ffmpeg 2.8.1 raises an error with -headers and non-http input files.
2015-10-18 13:44:21 +08:00
1e399778ee [letv] Fix extraction
Using data URIs for passing the decrypted M3U8 manifest, which is
supported by ffmpeg only.
2015-10-18 13:42:57 +08:00
2e022397c4 [vine] Add counters to tests 2015-10-18 09:36:19 +06:00
02835c6bf4 [extractor/common] Document repost_count 2015-10-18 09:34:54 +06:00
91816e8f16 [vine] Remove duplicate metadata, make more robust and modernize (Closes #7215) 2015-10-18 09:32:08 +06:00
10c38c7ca2 [vine] Fix download tests 2015-10-18 09:20:54 +06:00
94a773feb9 [vine] Use JS data to get title/alt_title 2015-10-18 09:20:46 +06:00
448ef1f31c [extractor/common] Allow angle brackets in attributes in _og_regexes (#7215) 2015-10-18 09:11:02 +06:00
49941c4e4f [crunchyroll] Add maturity wall reference tests (#7202) 2015-10-18 07:06:47 +06:00
80f48920c8 [crunchyroll] Bypass maturity wall (Closes #7202) 2015-10-18 06:57:57 +06:00
5a11b793fe [lynda] Extract all prioritized streams 2015-10-18 01:36:03 +06:00
7593fbaa12 [dailymotion] Error spelling 2015-10-18 01:00:37 +06:00
2eb0f72a0e Merge pull request #7212 from lalinsky/dailymotion-error
[dailymotion] Report errors from player v5
2015-10-18 00:54:27 +06:00
8e5b121948 [test_youtube_lists] Add test flat playlist entries' titles 2015-10-18 00:27:06 +06:00
648e6a1ffe [youtube] Generalize playlist entries extraction (Closes #6699, closes #6992) 2015-10-18 00:11:34 +06:00
583882fdce [dailymotion] Report errors from player v5 2015-10-17 19:26:30 +02:00
9eb31b265f [vidme] Add user-disabled test 2015-10-17 23:01:24 +06:00
ddeb1b3de2 Merge pull request #7211 from lalinsky/vidme-suspended
[vidme] Better error message for suspended vidme videos
2015-10-17 22:56:51 +06:00
59fe4824f8 [vidme] Better error message for suspended vidme videos 2015-10-17 18:52:25 +02:00
dd8417526b [vimeo] Clarify new react+flux website fallback 2015-10-17 22:48:14 +06:00
09670d5ba4 Merge pull request #7209 from lalinsky/vimeo-new-page
Extract config URL from (new?) React-based Vimeo's page
2015-10-17 22:39:17 +06:00
41a7b00f18 [vimeo] Extract config URL from (new?) React-based Vimeo's page 2015-10-17 18:30:56 +02:00
350c948133 [twitch:vod] Formatting 2015-10-17 18:43:12 +06:00
e5e9966199 [twitch:vod] Improve extraction 2015-10-17 18:29:54 +06:00
fbd9f6ea80 [twitch] Improve authentication 2015-10-17 18:28:21 +06:00
6df7179e6c [rte] Actually recognize https urls
There was a missing 's' before the '?'.
2015-10-17 11:53:59 +02:00
36eb802baf [rte] Replace expired test
According to their webpage it should be available until October 2035.
2015-10-17 11:49:51 +02:00
2ccb37beb9 release 2015.10.16 2015-10-16 21:40:38 +02:00
246ce10858 [rte] Update _VALID_URL (Closes #7198) 2015-10-17 01:08:23 +06:00
ba717dca97 [bandcamp] Modernize 2015-10-17 00:51:35 +06:00
1e52776ac3 [bandcamp] Prepend download URL with scheme when necessary (2) (#7077) 2015-10-17 00:46:38 +06:00
8daeeedc06 [bbc] Fix FutureWarning 2015-10-17 00:26:45 +06:00
6744f36db7 [jeuxvideo] Fallback on og:title (Closes #7186, closes #7190) 2015-10-16 08:44:19 +06:00
fafc7950e2 [channel9] Update tests' thumbnails 2015-10-15 01:59:11 +06:00
a13d06de42 [channel9] Add test for low quality mp4 2015-10-15 01:57:59 +06:00
1db82381e3 [channel9] Add low quality formats and modernize 2015-10-15 01:52:25 +06:00
cb8961eeed Merge pull request #7176 from remitamine/megavideoz
[megavideoz] remove extractor
2015-10-14 22:41:27 +06:00
af98f8ff37 [utils] Return default on fail in int_or_none 2015-10-14 22:37:03 +06:00
caf80631f0 [utils] Do not fail in float_or_none on non-numeric data 2015-10-14 22:36:37 +06:00
1812afb7b3 [utils] Do not fail in int_or_none on non-numeric data (Closes #7175) 2015-10-14 22:35:01 +06:00
9fb66c780c [megavideoz] remove extractor 2015-10-14 17:25:07 +01:00
ab953c64a0 [yandexmusic:track] Extract original size thumbnail (Closes #7160) 2015-10-14 21:15:29 +06:00
db0a8ad979 [test_InfoExtractor] Add test for unquoted attribute 2015-10-14 21:11:06 +06:00
1c29e81e62 [test_InfoExtractor] Add test for 7a6d76a64d 2015-10-14 20:58:52 +06:00
7a6d76a64d [extractor/common] Require closing quote in _og_regexes (Closes #7174)
E.g. do not match `property='og:video:type'` when `og:video` is requested.
2015-10-14 20:49:39 +06:00
4aa353673b Merge branch 'master' of github.com:rg3/youtube-dl 2015-10-14 20:32:11 +06:00
f49b3d6efc Merge pull request #7173 from remitamine/criterion
[criterion] fix description extraction
2015-10-14 19:49:54 +06:00
36bb63fad1 [criterion] fix description extraction 2015-10-14 14:13:53 +01:00
1f36085df9 [vimeo] Fix extraction of password protected videos (fixes #7169) 2015-10-14 13:41:39 +02:00
26669ea3cf [5min] extract more video info and formats
Closes #7124.
2015-10-14 13:23:58 +02:00
3dc582e5ea [fczenit] Add extractor
Closes #7143.
2015-10-13 22:31:12 +02:00
506e261d20 [channel9] strip 'session_day' 2015-10-13 21:18:30 +02:00
b30c4992a9 [channel9] Return a single dictionary for single videos (closes #7086)
Returning a list is deprecated.
2015-10-13 21:14:33 +02:00
3eeff489e8 Extract thumbnail url 2015-10-13 22:17:42 +06:00
5946cda7c6 [beeg] Fix extraction (Closes #7155) 2015-10-13 21:04:39 +06:00
ee2edd838a release 2015.10.13 2015-10-13 00:53:05 +02:00
73e732eb6b [vimeo] Fix m3u8 formats
Reported at
https://github.com/rg3/youtube-dl/pull/7126#issuecomment-147327584
2015-10-12 16:36:17 +08:00
cd7364a89c release 2015.10.12 2015-10-12 06:37:20 +02:00
57d1db8dd0 [rtbf] Fix extraction (closes #7133) 2015-10-11 22:45:13 +02:00
964e7b2dd0 [downloader/common] Always skip "already downloaded" check when outputting to stdout 2015-10-12 00:43:54 +06:00
f101079ae0 [downloader/rtmp] Respect --no-continue option
now when downloading a "rtmp-file" the --no-continue option works!
2015-10-12 00:40:37 +06:00
0f61db4469 [chaturbate] Improve and capture error message 2015-10-11 20:36:20 +06:00
PC
1bd3903582 chaturbate streams 2015-10-11 20:36:12 +06:00
da4daed5ef [vimeo] Do not fail when no hls formats 2015-10-11 19:36:23 +06:00
7d49502ab0 [bild] Make more robust and improve hls extraction 2015-10-11 19:28:00 +06:00
03e3b4e119 [expotv] parse m3u8 manifest 2015-10-11 19:24:19 +06:00
d8348c351d [bild] Strip title 2015-10-11 19:17:18 +06:00
70cb4d51c9 [bild] extract info from json request 2015-10-11 19:17:09 +06:00
7c84562945 [vimeo] Fix password protected videos 2015-10-11 02:31:37 +06:00
68f3b61f0e [vimeo] Update tests 2015-10-11 02:22:42 +06:00
08fd433f3e Merge pull request #7126 from remitamine/vimeo
[vimeo] extract m3u8 manifest and bitrate
2015-10-11 02:15:01 +06:00
35a3ff1d33 [vimeo] always convert width, height and bitrate to int 2015-10-10 21:05:29 +01:00
fff496c689 [vimeo] remove check for empty formats 2015-10-10 20:45:34 +01:00
e5c209a1bc [vimeo] add parameters to _extract_m3u8_formats and sort formats 2015-10-10 20:34:10 +01:00
75f105d455 [adultswim] Clarify no media message 2015-10-11 01:04:41 +06:00
00cde0b8dc [adultswim] raise ExtractorError if no clips in video_info 2015-10-11 01:03:46 +06:00
58cd7e173e [adultswim] detect when video needs authentication 2015-10-11 01:03:39 +06:00
f4076bb736 [vimeo] extract m3u8 manifest and bitrate 2015-10-10 19:56:55 +01:00
6f7893653c [bbc] PEP 8 2015-10-11 00:39:28 +06:00
55ebae26f9 [bbc] Prefer iptv-all mediaset 2015-10-11 00:37:39 +06:00
ae8bdfd1a1 [bbc] Extract article JSON and actualize tests 2015-10-11 00:25:09 +06:00
6a74719060 [bbc] Update tests 2015-10-10 23:56:55 +06:00
f6295bcb04 [bbc] Remove duration 2015-10-10 23:45:15 +06:00
78f9d84318 [bbc] Support playlists of data-playable 2015-10-10 23:40:20 +06:00
b1ec70e4a9 [bbc] Improve data-playable regex 2015-10-10 23:20:30 +06:00
c936d8cc7b [bbc] Add another test 2015-10-10 23:14:25 +06:00
e6174ee975 [bbc] Extract legacy playlist embedded media 2015-10-10 23:01:20 +06:00
f790c43f6e [zingmp3:album] Skip broken items 2015-10-10 22:09:21 +06:00
8119597d6f [zingmp3] Add fatal flag 2015-10-10 22:08:38 +06:00
43abd79950 [zingmp3:album] Style 2015-10-10 22:05:01 +06:00
97ae4d166c [zingmp3:album] Add support for playlists
Update for work with playlist, it same album but different url
Ex:
http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html
http://mp3.zing.vn/album/Duong-Hong-Loan-apollobee/IWCAACCB.html
2015-10-10 22:03:05 +06:00
87cc0fbd18 [bbc] Make summary optional in legacy playlist 2015-10-10 21:38:09 +06:00
baf39a1aa8 [bbc] Add one more scenario for data-playable embeds 2015-10-10 21:38:01 +06:00
975977860d [bbc] Make playlist title optional 2015-10-10 21:37:53 +06:00
b5d48cb1ef [bbc] Add test for atricle with multiple videos embedded with playlist.sxml 2015-10-10 21:37:43 +06:00
de66571371 [bbc] Support multiple videos in articles embedded with playlist.sxml 2015-10-10 21:37:34 +06:00
dab062fb6e [bbc] Add support for videos in news articles embedded with data-playable 2015-10-10 21:37:23 +06:00
6a959f2e52 [iqiyi] Update enc_key 2015-10-10 15:03:01 +08:00
47c165c3a9 [vimeo] Fix authentication (Closes #7110) 2015-10-10 05:56:01 +06:00
4180a3d8b7 [extractor/common] Allow quoteless content attribute in og regexes (Closes #7115) 2015-10-10 01:46:01 +06:00
ef47b2c15f release 2015.10.09 2015-10-09 09:09:22 +02:00
57935b2564 [extractor/common] Allow HTML5 unquoted attribute values
Fixes #7108

HTML5 allows unquoted attribute values. See the "Unquoted attribute value
syntax" section [1] for more information

[1] http://www.w3.org/TR/html5/syntax.html
2015-10-09 14:11:00 +08:00
54a5428518 [dailymotion] Update player v5 regex (Closes #7107) 2015-10-09 03:54:49 +06:00
9d5fb3b58d [pbs] Carry long line 2015-10-09 00:09:10 +06:00
cbb7287204 Merge pull request #7105 from remitamine/pbs
[pbs] detect errors from http error code
2015-10-09 00:06:49 +06:00
0553d0ee40 [pbs] place errors into a dict 2015-10-08 18:57:57 +01:00
7faf7e7523 [pbs] detect errors from http error code 2015-10-08 18:39:24 +01:00
4356d907c1 [4tube] Try extracting sources from the webpage before fetching player.js (Closes #7103) 2015-10-08 21:05:48 +06:00
c677e49bd1 [4tube] Revert uploader regexes and make non fatal 2015-10-08 21:05:35 +06:00
96c4855331 [4tube] Style and make more robust 2015-10-08 21:05:27 +06:00
b90b0c4ffa Fixed 4tube.com extractor to pull metadata from associated Javascript and not the HTML of the desired page. 2015-10-08 21:05:16 +06:00
c725e2c8b0 Merge pull request #7100 from AndroKev/nowtv-fix
[nowtv] Update rtmp player URL
2015-10-08 19:42:46 +06:00
db7a28eccb FIX: nowtv
now the download works for me
thx to http://board.gulli.com/thread/1251646-videos-von-webseiten-runterladen-sammelthread-alle-fragen-hier-rein-/?p=14980081#post14980081
2015-10-08 09:56:39 +02:00
181f814e57 Merge pull request #7085 from TomGijselinck/patch-1
Fix typos and improve grammar and spelling
2015-10-07 12:14:17 +02:00
bd5376c182 Fix typos and improve grammar and spelling 2015-10-07 10:32:44 +02:00
9e7e0dffd5 Actually add the extractor 2015-07-21 16:56:35 -05:00
c3dea3f878 Twittercard: support vmapurl method 2015-07-21 16:45:36 -05:00
f57f84f606 Twitter: get and describe video from status urls 2015-07-21 16:38:40 -05:00
54 changed files with 1290 additions and 532 deletions

View File

@ -114,17 +114,18 @@ If you want to add support for a new site, you can follow this quick list (assum
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:

View File

@ -404,18 +404,18 @@ which means you can modify it, redistribute it or use it however you like.
# CONFIGURATION
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, system wide configuration file is located at `/etc/youtube-dl.conf` and user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configration file youtube-dl will always extract the audio, not copy the mtime and use proxy:
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime and use a proxy:
```
--extract-audio
--no-mtime
--proxy 127.0.0.1:3128
```
You can use `--ignore-config` if you want to disable configuration file for a particular youtube-dl run.
You can use `--ignore-config` if you want to disable the configuration file for a particular youtube-dl run.
### Authentication with `.netrc` file ###
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create a`.netrc` file in your `$HOME` and restrict permissions to read/write by you only:
```
touch $HOME/.netrc
chmod a-rwx,u+rw $HOME/.netrc
@ -429,13 +429,13 @@ For example:
machine youtube login myaccount@gmail.com password my_youtube_password
machine twitch login my_twitch_account_name password my_twitch_password
```
To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or place it in [configuration file](#configuration).
To activate authentication with the `.netrc` file you should pass `--netrc` to youtube-dl or place it in the [configuration file](#configuration).
On Windows you may also need to setup `%HOME%` environment variable manually.
On Windows you may also need to setup the `%HOME%` environment variable manually.
# OUTPUT TEMPLATE
The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are:
The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parentheses, followed by a lowercase S. Allowed names are:
- `id`: The sequence will be replaced by the video identifier.
- `url`: The sequence will be replaced by the video URL.
@ -463,18 +463,18 @@ youtube-dl_test_video_.mp4 # A simple file name
# FORMAT SELECTION
By default youtube-dl tries to download the best quality, but sometimes you may want to download other format.
By default youtube-dl tries to download the best quality, but sometimes you may want to download in a different format.
The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`.
If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f <video-format>+<audio-format>` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`.
Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading the best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed.
If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
If you want to preserve the old format selection behavior (prior to youtube-dl 2015.04.26), i.e. you want to download the best available quality media served as a single file, you should explicitly specify your choice with `-f best`. You may want to add it to the [configuration file](#configuration) in order not to type it every time you run youtube-dl.
# VIDEO SELECTION
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`. They accept dates in two formats:
- Absolute dates: Dates in the format `YYYYMMDD`.
- Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
@ -488,7 +488,7 @@ $ youtube-dl --dateafter now-6months
# Download only the videos uploaded on January 1, 1970
$ youtube-dl --date 19700101
$ # will only download the videos uploaded in the 200x decade
$ # Download only the videos uploaded in the 200x decade
$ youtube-dl --dateafter 20000101 --datebefore 20091231
```
@ -500,7 +500,7 @@ If you've followed [our manual installation instructions](http://rg3.github.io/y
If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distribution serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
@ -558,7 +558,7 @@ YouTube requires an additional signature since September 2012 which is not suppo
### Video URL contains an ampersand and I'm getting some strange output `[1] 2839` or `'v' is not recognized as an internal or external command` ###
That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
That's actually the output from your shell. Since ampersand is one of the special shell characters it's interpreted by the shell preventing you from passing the whole URL to youtube-dl. To disable your shell from interpreting the ampersands (or any other special characters) you have to either put the whole URL in quotes or escape them with a backslash (which approach will work depends on your shell).
For example if your URL is https://www.youtube.com/watch?t=4&v=BaW_jenozKc you should end up with following command:
@ -618,9 +618,9 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt
### How do I pass cookies to youtube-dl?
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that cookies file must be in Mozilla/Netscape format and the first line of cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in cookies file and convert newlines if necessary to correspond your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Passing cookies to youtube-dl is a good way to workaround login when particular extractor does not implement it explicitly.
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly.
### Can you add support for this anime video site, or site which shows current movies for free?
@ -710,17 +710,18 @@ If you want to add support for a new site, you can follow this quick list (assum
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L62-L200). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:

View File

@ -53,6 +53,7 @@
- **Bandcamp:album**
- **bbc**: BBC
- **bbc.co.uk**: BBC iPlayer
- **bbc.co.uk:article**: BBC articles
- **BeatportPro**
- **Beeg**
- **BehindKink**
@ -81,6 +82,7 @@
- **CBSSports**
- **CeskaTelevize**
- **channel9**: Channel 9
- **Chaturbate**
- **Chilloutzone**
- **chirbit**
- **chirbit:profile**
@ -158,6 +160,7 @@
- **facebook**
- **faz.net**
- **fc2**
- **Fczenit**
- **fernsehkritik.tv**
- **Firstpost**
- **FiveTV**
@ -280,7 +283,6 @@
- **Malemotion**
- **MDR**
- **media.ccc.de**
- **MegaVideoz**
- **metacafe**
- **Metacritic**
- **Mgoon**
@ -514,6 +516,7 @@
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **Stitcher**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
@ -587,7 +590,8 @@
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
- **TwitterCard**
- **twitter**
- **twitter:card**
- **Ubu**
- **udemy**
- **udemy:course**

View File

@ -35,10 +35,18 @@ class TestInfoExtractor(unittest.TestCase):
<meta name="og:title" content='Foo'/>
<meta content="Some video's description " name="og:description"/>
<meta property='og:image' content='http://domain.com/pic.jpg?key1=val1&amp;key2=val2'/>
<meta content='application/x-shockwave-flash' property='og:video:type'>
<meta content='Foo' property=og:foobar>
<meta name="og:test1" content='foo > < bar'/>
<meta name="og:test2" content="foo >//< bar"/>
'''
self.assertEqual(ie._og_search_title(html), 'Foo')
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
self.assertEqual(ie._og_search_video_url(html, default=None), None)
self.assertEqual(ie._og_search_property('foobar', html), 'Foo')
self.assertEqual(ie._og_search_property('test1', html), 'foo > < bar')
self.assertEqual(ie._og_search_property('test2', html), 'foo >//< bar')
def test_html_search_meta(self):
ie = self.ie

View File

@ -495,6 +495,9 @@ class TestUtil(unittest.TestCase):
"playlist":[{"controls":{"all":null}}]
}''')
inp = '''"The CW\\'s \\'Crazy Ex-Girlfriend\\'"'''
self.assertEqual(js_to_json(inp), '''"The CW's 'Crazy Ex-Girlfriend'"''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))

View File

@ -57,5 +57,14 @@ class TestYoutubeLists(unittest.TestCase):
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_titles(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))
if __name__ == '__main__':
unittest.main()

View File

@ -37,6 +37,7 @@ from .compat import (
compat_tokenize_tokenize,
compat_urllib_error,
compat_urllib_request,
compat_urllib_request_DataHandler,
)
from .utils import (
ContentTooShortError,
@ -1967,8 +1968,9 @@ class YoutubeDL(object):
debuglevel = 1 if self.params.get('debug_printtraffic') else 0
https_handler = make_HTTPS_handler(self.params, debuglevel=debuglevel)
ydlh = YoutubeDLHandler(self.params, debuglevel=debuglevel)
data_handler = compat_urllib_request_DataHandler()
opener = compat_urllib_request.build_opener(
proxy_handler, https_handler, cookie_processor, ydlh)
proxy_handler, https_handler, cookie_processor, ydlh, data_handler)
# Delete the default user-agent header, which would otherwise apply in
# cases where our custom HTTP handler doesn't come into play

View File

@ -1,7 +1,10 @@
from __future__ import unicode_literals
import binascii
import collections
import email
import getpass
import io
import optparse
import os
import re
@ -38,6 +41,11 @@ try:
except ImportError: # Python 2
import urlparse as compat_urlparse
try:
import urllib.response as compat_urllib_response
except ImportError: # Python 2
import urllib as compat_urllib_response
try:
import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
@ -155,6 +163,40 @@ except ImportError: # Python 2
string = string.replace('+', ' ')
return compat_urllib_parse_unquote(string, encoding, errors)
try:
from urllib.request import DataHandler as compat_urllib_request_DataHandler
except ImportError: # Python < 3.4
# Ported from CPython 98774:1733b3bd46db, Lib/urllib/request.py
class compat_urllib_request_DataHandler(compat_urllib_request.BaseHandler):
def data_open(self, req):
# data URLs as specified in RFC 2397.
#
# ignores POSTed data
#
# syntax:
# dataurl := "data:" [ mediatype ] [ ";base64" ] "," data
# mediatype := [ type "/" subtype ] *( ";" parameter )
# data := *urlchar
# parameter := attribute "=" value
url = req.get_full_url()
scheme, data = url.split(":", 1)
mediatype, data = data.split(",", 1)
# even base64 encoded data URLs might be quoted so unquote in any case:
data = compat_urllib_parse_unquote_to_bytes(data)
if mediatype.endswith(";base64"):
data = binascii.a2b_base64(data)
mediatype = mediatype[:-7]
if not mediatype:
mediatype = "text/plain;charset=US-ASCII"
headers = email.message_from_string(
"Content-type: %s\nContent-length: %d\n" % (mediatype, len(data)))
return compat_urllib_response.addinfourl(io.BytesIO(data), headers, url)
try:
compat_basestring = basestring # Python 2
except NameError:
@ -489,6 +531,8 @@ __all__ = [
'compat_urllib_parse_unquote_to_bytes',
'compat_urllib_parse_urlparse',
'compat_urllib_request',
'compat_urllib_request_DataHandler',
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',

View File

@ -325,7 +325,7 @@ class FileDownloader(object):
)
# Check file already present
if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
if filename != '-' and (nooverwrites_and_exists or continuedl_and_exists):
self.report_file_already_downloaded(filename)
self._hook_progress({
'filename': filename,

View File

@ -30,7 +30,7 @@ class HlsFD(FileDownloader):
args = [ffpp.executable, '-y']
if info_dict['http_headers']:
if info_dict['http_headers'] and re.match(r'^https?://', url):
# Trailing \r\n after each HTTP header is important to prevent warning from ffmpeg/avconv:
# [http @ 00000000003d2fa0] No trailing CRLF found in HTTP header.
args += [

View File

@ -105,7 +105,7 @@ class RtmpFD(FileDownloader):
protocol = info_dict.get('rtmp_protocol', None)
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = info_dict.get('continuedl', True)
continue_dl = self.params.get('continuedl', True)
self.report_destination(filename)
tmpfilename = self.temp_name(filename)

View File

@ -45,6 +45,7 @@ from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbc import (
BBCCoUkIE,
BBCCoUkArticleIE,
BBCIE,
)
from .beeg import BeegIE
@ -76,6 +77,7 @@ from .cbssports import CBSSportsIE
from .ccc import CCCIE
from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE
from .chaturbate import ChaturbateIE
from .chilloutzone import ChilloutzoneIE
from .chirbit import (
ChirbitIE,
@ -166,6 +168,7 @@ from .extremetube import ExtremeTubeIE
from .facebook import FacebookIE
from .faz import FazIE
from .fc2 import FC2IE
from .fczenit import FczenitIE
from .firstpost import FirstpostIE
from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
@ -317,7 +320,6 @@ from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .malemotion import MalemotionIE
from .mdr import MDRIE
from .megavideoz import MegaVideozIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mgoon import MgoonIE
@ -585,6 +587,7 @@ from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE
from .stitcher import StitcherIE
from .sport5 import Sport5IE
from .sportbox import (
SportBoxIE,
@ -689,7 +692,7 @@ from .twitch import (
TwitchBookmarksIE,
TwitchStreamIE,
)
from .twitter import TwitterCardIE
from .twitter import TwitterCardIE, TwitterIE
from .ubu import UbuIE
from .udemy import (
UdemyIE,

View File

@ -41,7 +41,8 @@ class AdultSwimIE(InfoExtractor):
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
}
},
'skip': 'This video is only available for registered users',
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
@ -134,7 +135,13 @@ class AdultSwimIE(InfoExtractor):
show = bootstrapped_data['show']
show_title = show['title']
stream = video_info.get('stream')
clips = [stream] if stream else video_info['clips']
clips = [stream] if stream else video_info.get('clips')
if not clips:
raise ExtractorError(
'This video is only available via cable service provider subscription that'
' is not currently supported. You may want to use --cookies.'
if video_info.get('auth') is True else 'Unable to find stream or clips',
expected=True)
segment_ids = [clip['videoPlaybackID'] for clip in clips]
episode_id = video_info['id']
@ -176,7 +183,7 @@ class AdultSwimIE(InfoExtractor):
media_url = file_el.text
if determine_ext(media_url) == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, segment_title, 'mp4', 'm3u8_native', preference=0, m3u8_id='hls'))
media_url, segment_title, 'mp4', preference=0, m3u8_id='hls'))
else:
formats.append({
'format_id': '%s_%s' % (bitrate, ftype),

View File

@ -10,6 +10,8 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
)
@ -52,11 +54,11 @@ class BandcampIE(InfoExtractor):
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
'url': format_url,
'url': self._proto_relative_url(format_url, 'http:'),
'ext': ext,
'vcodec': 'none',
'acodec': ext,
'abr': int(abr_str),
'abr': int_or_none(abr_str),
})
self._sort_formats(formats)
@ -65,7 +67,7 @@ class BandcampIE(InfoExtractor):
'id': compat_str(data['id']),
'title': data['title'],
'formats': formats,
'duration': float(data['duration']),
'duration': float_or_none(data.get('duration')),
}
else:
raise ExtractorError('No free songs found')

View File

@ -11,6 +11,8 @@ from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
remove_end,
unescapeHTML,
)
from ..compat import compat_HTTPError
@ -18,7 +20,7 @@ from ..compat import compat_HTTPError
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
_VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P<id>[\da-z]{8})'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams with even better quality that pc mediaset but fails
@ -28,6 +30,14 @@ class BBCCoUkIE(InfoExtractor):
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
]
_MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
_EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
_NAMESPACES = (
_MEDIASELECTION_NS,
_EMP_PLAYLIST_NS,
)
_TESTS = [
{
'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
@ -193,6 +203,7 @@ class BBCCoUkIE(InfoExtractor):
def _extract_connection(self, connection, programme_id):
formats = []
kind = connection.get('kind')
protocol = connection.get('protocol')
supplier = connection.get('supplier')
if protocol == 'http':
@ -218,7 +229,7 @@ class BBCCoUkIE(InfoExtractor):
else:
formats.append({
'url': href,
'format_id': supplier,
'format_id': supplier or kind or protocol,
})
elif protocol == 'rtmp':
application = connection.get('application', 'ondemand')
@ -238,16 +249,24 @@ class BBCCoUkIE(InfoExtractor):
return formats
def _extract_items(self, playlist):
return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
def _findall_ns(self, element, xpath):
elements = []
for ns in self._NAMESPACES:
elements.extend(element.findall(xpath % ns))
return elements
def _extract_medias(self, media_selection):
error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
if error is None:
media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
if error is not None:
raise BBCCoUkIE.MediaSelectionError(error.get('id'))
return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
return self._findall_ns(media_selection, './{%s}media')
def _extract_connections(self, media):
return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
return self._findall_ns(media, './{%s}connection')
def _extract_video(self, media, programme_id):
formats = []
@ -261,13 +280,14 @@ class BBCCoUkIE(InfoExtractor):
conn_formats = self._extract_connection(connection, programme_id)
for format in conn_formats:
format.update({
'format_id': '%s_%s' % (service, format['format_id']),
'width': width,
'height': height,
'vbr': vbr,
'vcodec': vcodec,
'filesize': file_size,
})
if service:
format['format_id'] = '%s_%s' % (service, format['format_id'])
formats.extend(conn_formats)
return formats
@ -382,7 +402,7 @@ class BBCCoUkIE(InfoExtractor):
url, playlist_id, 'Downloading legacy playlist XML')
def _extract_from_legacy_playlist(self, playlist, playlist_id):
no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
if no_items is not None:
reason = no_items.get('reason')
if reason == 'preAvailability':
@ -399,8 +419,9 @@ class BBCCoUkIE(InfoExtractor):
kind = item.get('kind')
if kind != 'programme' and kind != 'radioProgramme':
continue
title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
description = description_el.text if description_el is not None else None
def get_programme_id(item):
def get_from_attributes(item):
@ -409,16 +430,18 @@ class BBCCoUkIE(InfoExtractor):
if value and re.match(r'^[pb][\da-z]{7}$', value):
return value
get_from_attributes(item)
mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator')
mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
if mediator is not None:
return get_from_attributes(mediator)
programme_id = get_programme_id(item)
duration = int_or_none(item.get('duration'))
# TODO: programme_id can be None and media items can be incorporated right inside
# playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
# as f4m and m3u8
formats, subtitles = self._download_media_selector(programme_id)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
else:
formats, subtitles = self._process_media_selector(item, playlist_id)
programme_id = playlist_id
return programme_id, title, description, duration, formats, subtitles
@ -470,6 +493,9 @@ class BBCIE(BBCCoUkIE):
_VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
_MEDIASELECTOR_URLS = [
# Provides HQ HLS streams but fails with geolocation in some cases when it's
# even not geo restricted at all
'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
# Provides more formats, namely direct mp4 links, but fails on some videos with
# notukerror for non UK (?) users (e.g.
# http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
@ -479,8 +505,7 @@ class BBCIE(BBCCoUkIE):
]
_TESTS = [{
# article with multiple videos embedded with data-media-meta containing
# playlist.sxml, externalId and no direct video links
# article with multiple videos embedded with data-playable containing vpids
'url': 'http://www.bbc.com/news/world-europe-32668511',
'info_dict': {
'id': 'world-europe-32668511',
@ -489,7 +514,7 @@ class BBCIE(BBCCoUkIE):
},
'playlist_count': 2,
}, {
# article with multiple videos embedded with data-media-meta (more videos)
# article with multiple videos embedded with data-playable (more videos)
'url': 'http://www.bbc.com/news/business-28299555',
'info_dict': {
'id': 'business-28299555',
@ -500,6 +525,7 @@ class BBCIE(BBCCoUkIE):
'skip': 'Save time',
}, {
# article with multiple videos embedded with `new SMP()`
# broken
'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
'info_dict': {
'id': '3662a707-0af9-3149-963f-47bea720b460',
@ -507,12 +533,13 @@ class BBCIE(BBCCoUkIE):
},
'playlist_count': 18,
}, {
# single video embedded with mediaAssetPage.init()
# single video embedded with data-playable containing vpid
'url': 'http://www.bbc.com/news/world-europe-32041533',
'info_dict': {
'id': 'p02mprgb',
'ext': 'mp4',
'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
'description': 'md5:2868290467291b37feda7863f7a83f54',
'duration': 47,
'timestamp': 1427219242,
'upload_date': '20150324',
@ -522,15 +549,14 @@ class BBCIE(BBCCoUkIE):
'skip_download': True,
}
}, {
# article with single video embedded with data-media-meta containing
# direct video links (for now these are extracted) and playlist.xml (with
# media items as f4m and m3u8 - currently unsupported)
# article with single video embedded with data-playable containing XML playlist
# with direct video links as progressiveDownloadUrl (for now these are extracted)
# and playlist with f4m and m3u8 as streamingUrl
'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
'info_dict': {
'id': '150615_telabyad_kentin_cogu',
'ext': 'mp4',
'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
'duration': 47,
'timestamp': 1434397334,
'upload_date': '20150615',
},
@ -538,13 +564,12 @@ class BBCIE(BBCCoUkIE):
'skip_download': True,
}
}, {
# single video embedded with mediaAssetPage.init() (regional section)
# single video embedded with data-playable containing XML playlists (regional section)
'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
'info_dict': {
'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
'ext': 'mp4',
'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
'duration': 87,
'timestamp': 1434713142,
'upload_date': '20150619',
},
@ -586,27 +611,35 @@ class BBCIE(BBCCoUkIE):
'ext': 'mp4',
'title': 'Hyundai Santa Fe Sport: Rock star',
'description': 'md5:b042a26142c4154a6e472933cf20793d',
'timestamp': 1368473503,
'upload_date': '20130513',
'timestamp': 1415867444,
'upload_date': '20141113',
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# single video with playlist.sxml URL
# single video with playlist.sxml URL in playlist param
'url': 'http://www.bbc.com/sport/0/football/33653409',
'info_dict': {
'id': 'p02xycnp',
'ext': 'mp4',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'md5:398fca0e2e701c609d726e034fa1fc89',
'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
'duration': 140,
},
'params': {
# rtmp download
'skip_download': True,
}
}, {
# article with multiple videos embedded with playlist.sxml in playlist param
'url': 'http://www.bbc.com/sport/0/football/34475836',
'info_dict': {
'id': '34475836',
'title': 'What Liverpool can expect from Klopp',
},
'playlist_count': 3,
}, {
# single video with playlist URL from weather section
'url': 'http://www.bbc.com/weather/features/33601775',
@ -619,7 +652,7 @@ class BBCIE(BBCCoUkIE):
@classmethod
def suitable(cls, url):
return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url)
return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url)
def _extract_from_media_meta(self, media_meta, video_id):
# Direct links to media in media metadata (e.g.
@ -648,40 +681,107 @@ class BBCIE(BBCCoUkIE):
return [], []
def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
programme_id, title, description, duration, formats, subtitles = \
self._process_legacy_playlist_url(url, playlist_id)
self._sort_formats(formats)
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
'subtitles': subtitles,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
timestamp = parse_iso8601(self._search_regex(
[r'"datePublished":\s*"([^"]+)',
r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
r'itemprop="datePublished"[^>]+datetime="([^"]+)"'],
webpage, 'date', default=None))
timestamp = None
playlist_title = None
playlist_description = None
# single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng)
playlist = self._search_regex(
r'<param[^>]+name="playlist"[^>]+value="([^"]+)"',
webpage, 'playlist', default=None)
if playlist:
programme_id, title, description, duration, formats, subtitles = \
self._process_legacy_playlist_url(playlist, playlist_id)
self._sort_formats(formats)
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
'subtitles': subtitles,
}
ld = self._parse_json(
self._search_regex(
r'(?s)<script type="application/ld\+json">(.+?)</script>',
webpage, 'ld json', default='{}'),
playlist_id, fatal=False)
if ld:
timestamp = parse_iso8601(ld.get('datePublished'))
playlist_title = ld.get('headline')
playlist_description = ld.get('articleBody')
if not timestamp:
timestamp = parse_iso8601(self._search_regex(
[r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
r'"datePublished":\s*"([^"]+)'],
webpage, 'date', default=None))
entries = []
# article with multiple videos embedded with playlist.sxml (e.g.
# http://www.bbc.com/sport/0/football/34475836)
playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
if playlists:
entries = [
self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
for playlist_url in playlists]
# news article with multiple videos embedded with data-playable
data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
if data_playables:
for _, data_playable_json in data_playables:
data_playable = self._parse_json(
unescapeHTML(data_playable_json), playlist_id, fatal=False)
if not data_playable:
continue
settings = data_playable.get('settings', {})
if settings:
# data-playable with video vpid in settings.playlistObject.items (e.g.
# http://www.bbc.com/news/world-us-canada-34473351)
playlist_object = settings.get('playlistObject', {})
if playlist_object:
items = playlist_object.get('items')
if items and isinstance(items, list):
title = playlist_object['title']
description = playlist_object.get('summary')
duration = int_or_none(items[0].get('duration'))
programme_id = items[0].get('vpid')
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
entries.append({
'id': programme_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
})
else:
# data-playable without vpid but with a playlist.sxml URLs
# in otherSettings.playlist (e.g.
# http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
playlist = data_playable.get('otherSettings', {}).get('playlist', {})
if playlist:
entries.append(self._extract_from_playlist_sxml(
playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
if entries:
playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News')
playlist_description = playlist_description or self._og_search_description(webpage, default=None)
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(
[r'data-video-player-vpid="([\da-z]{8})"',
r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'],
webpage, 'vpid', default=None)
if programme_id:
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
@ -803,3 +903,33 @@ class BBCIE(BBCCoUkIE):
})
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
class BBCCoUkArticleIE(InfoExtractor):
_VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
IE_NAME = 'bbc.co.uk:article'
IE_DESC = 'BBC articles'
_TEST = {
'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
'info_dict': {
'id': '3jNQLTMrPlYGTBn0WV6M2MS',
'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
},
'playlist_count': 4,
'add_ie': ['BBCCoUk'],
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage).strip()
entries = [self.url_result(programme_url) for programme_url in re.findall(
r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
return self.playlist_result(entries, playlist_id, title, description)

View File

@ -1,65 +1,67 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
)
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)'
_TEST = {
'url': 'http://beeg.com/5416503',
'md5': '1bff67111adb785c51d1b42959ec10e5',
'md5': '46c384def73b33dbc581262e5ee67cef',
'info_dict': {
'id': '5416503',
'ext': 'mp4',
'title': 'Sultry Striptease',
'description': 'md5:6db3c6177972822aaba18652ff59c773',
'categories': list, # NSFW
'thumbnail': 're:https?://.*\.jpg$',
'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
'timestamp': 1391813355,
'upload_date': '20140207',
'duration': 383,
'tags': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
quality_arr = self._search_regex(
r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats')
formats = [{
'url': fmt[1],
'format_id': fmt[0],
'height': int(fmt[0][:-1]),
} for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)]
video = self._download_json(
'http://beeg.com/api/v1/video/%s' % video_id, video_id)
formats = []
for format_id, video_url in video.items():
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
'url': self._proto_relative_url(video_url.replace('{DATA_MARKERS}', ''), 'http:'),
'format_id': format_id,
'height': int(height),
})
self._sort_formats(formats)
title = self._html_search_regex(
r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title')
title = video['title']
video_id = video.get('id') or video_id
display_id = video.get('code')
description = video.get('desc')
description = self._html_search_regex(
r'<meta name="description" content="([^"]*)"',
webpage, 'description', fatal=False)
thumbnail = self._html_search_regex(
r'\'previewer.url\'\s*:\s*"([^"]*)"',
webpage, 'thumbnail', fatal=False)
timestamp = parse_iso8601(video.get('date'), ' ')
duration = int_or_none(video.get('duration'))
categories_str = self._html_search_regex(
r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
categories = (
None if categories_str is None
else categories_str.split(','))
tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'categories': categories,
'timestamp': timestamp,
'duration': duration,
'tags': tags,
'formats': formats,
'age_limit': 18,
}

View File

@ -4,7 +4,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
fix_xml_ampersands,
unescapeHTML,
)
@ -17,26 +17,24 @@ class BildIE(InfoExtractor):
'info_dict': {
'id': '38184146',
'ext': 'mp4',
'title': 'BILD hat sie getestet',
'title': 'Das können die neuen iPads',
'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 196,
'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml"
doc = self._download_xml(xml_url, video_id, transform_source=fix_xml_ampersands)
duration = int_or_none(doc.attrib.get('duration'), scale=1000)
video_data = self._download_json(
url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
return {
'id': video_id,
'title': doc.attrib['ueberschrift'],
'description': doc.attrib.get('text'),
'url': doc.attrib['src'],
'thumbnail': doc.attrib.get('img'),
'duration': duration,
'title': unescapeHTML(video_data['title']).strip(),
'description': unescapeHTML(video_data.get('description')),
'url': video_data['clipList'][0]['srces'][0]['src'],
'thumbnail': video_data.get('poster'),
'duration': int_or_none(video_data.get('durationSec')),
}

View File

@ -4,38 +4,53 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_duration
class Canalc2IE(InfoExtractor):
IE_NAME = 'canalc2.tv'
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?.*?idVideo=(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?canalc2\.tv/video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
'url': 'http://www.canalc2.tv/video/12163',
'md5': '060158428b650f896c542dfbb3d6487f',
'info_dict': {
'id': '12163',
'ext': 'mp4',
'title': 'Terrasses du Numérique'
'ext': 'flv',
'title': 'Terrasses du Numérique',
'duration': 122,
},
'params': {
'skip_download': True, # Requires rtmpdump
}
}
def _real_extract(self, url):
video_id = re.match(self._VALID_URL, url).group('id')
# We need to set the voir field for getting the file name
url = 'http://www.canalc2.tv/video.asp?idVideo=%s&voir=oui' % video_id
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
file_name = self._search_regex(
r"so\.addVariable\('file','(.*?)'\);",
webpage, 'file name')
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
video_url = self._search_regex(
r'jwplayer\((["\'])Player\1\)\.setup\({[^}]*file\s*:\s*(["\'])(?P<file>.+?)\2',
webpage, 'video_url', group='file')
formats = [{'url': video_url}]
if video_url.startswith('rtmp://'):
rtmp = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>.+/))(?P<play_path>mp4:.+)$', video_url)
formats[0].update({
'url': rtmp.group('url'),
'ext': 'flv',
'app': rtmp.group('app'),
'play_path': rtmp.group('play_path'),
'page_url': url,
})
title = self._html_search_regex(
r'class="evenement8">(.*?)</a>', webpage, 'title')
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
return {
'id': video_id,
'ext': 'mp4',
'url': video_url,
'title': title,
'duration': duration,
'formats': formats,
}

View File

@ -3,7 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
from ..utils import (
ExtractorError,
parse_filesize,
qualities,
)
class Channel9IE(InfoExtractor):
@ -28,7 +32,7 @@ class Channel9IE(InfoExtractor):
'title': 'Developer Kick-Off Session: Stuff We Love',
'description': 'md5:c08d72240b7c87fcecafe2692f80e35f',
'duration': 4576,
'thumbnail': 'http://video.ch9.ms/ch9/9d51/03902f2d-fc97-4d3c-b195-0bfe15a19d51/KOS002_220.jpg',
'thumbnail': 're:http://.*\.jpg',
'session_code': 'KOS002',
'session_day': 'Day 1',
'session_room': 'Arena 1A',
@ -44,31 +48,29 @@ class Channel9IE(InfoExtractor):
'title': 'Self-service BI with Power BI - nuclear testing',
'description': 'md5:d1e6ecaafa7fb52a2cacdf9599829f5b',
'duration': 1540,
'thumbnail': 'http://video.ch9.ms/ch9/87e1/0300391f-a455-4c72-bec3-4422f19287e1/selfservicenuk_512.jpg',
'thumbnail': 're:http://.*\.jpg',
'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',
'ext': 'mp4',
'title': 'Ranges for the Standard Library',
'description': 'md5:2e6b4917677af3728c5f6d63784c4c5d',
'duration': 5646,
'thumbnail': 're:http://.*\.jpg',
},
'params': {
'skip_download': True,
},
}
]
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
# Sorted by quality
_known_formats = ['MP3', 'MP4', 'Mid Quality WMV', 'Mid Quality MP4', 'High Quality WMV', 'High Quality MP4']
def _restore_bytes(self, formatted_size):
if not formatted_size:
return 0
m = re.match(r'^(?P<size>\d+(?:\.\d+)?)\s+(?P<units>[a-zA-Z]+)', formatted_size)
if not m:
return 0
units = m.group('units')
try:
exponent = ['B', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB', 'ZB', 'YB'].index(units.upper())
except ValueError:
return 0
size = float(m.group('size'))
return int(size * (1024 ** exponent))
def _formats_from_html(self, html):
FORMAT_REGEX = r'''
(?x)
@ -78,16 +80,20 @@ class Channel9IE(InfoExtractor):
<h3>File\s+size</h3>\s*(?P<filesize>.*?)\s*
</div>)? # File size part may be missing
'''
# Extract known formats
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': self._restore_bytes(x.group('filesize')), # File size is approximate
'preference': self._known_formats.index(x.group('quality')),
'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)) if x.group('quality') in self._known_formats]
} for x in list(re.finditer(FORMAT_REGEX, html))]
self._sort_formats(formats)
@ -158,7 +164,7 @@ class Channel9IE(InfoExtractor):
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') if m is not None else None
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)
@ -224,12 +230,12 @@ class Channel9IE(InfoExtractor):
if contents is None:
return contents
authors = self._extract_authors(html)
if len(contents) > 1:
raise ExtractorError('Got more than one entry')
result = contents[0]
result['authors'] = self._extract_authors(html)
for content in contents:
content['authors'] = authors
return contents
return result
def _extract_session(self, html, content_path):
contents = self._extract_content(html, content_path)

View File

@ -0,0 +1,50 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError
class ChaturbateIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
'id': 'siswet19',
'ext': 'mp4',
'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'age_limit': 18,
'is_live': True,
},
'params': {
'skip_download': True,
}
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
m3u8_url = self._search_regex(
r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
'playlist', default=None, group='url')
if not m3u8_url:
error = self._search_regex(
r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
webpage, 'error', group='error')
raise ExtractorError(error, expected=True)
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
return {
'id': video_id,
'title': self._live_title(video_id),
'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
'age_limit': self._rta_search(webpage),
'is_live': True,
'formats': formats,
}

View File

@ -172,6 +172,7 @@ class InfoExtractor(object):
view_count: How many users have watched the video on the platform.
like_count: Number of positive ratings of the video
dislike_count: Number of negative ratings of the video
repost_count: Number of reposts of the video
average_rating: Average rating give by users, the scale used depends on the webpage
comment_count: Number of comments on the video
comments: A list of comments, each with one or more of the following
@ -645,8 +646,9 @@ class InfoExtractor(object):
# Helper functions for extracting OpenGraph info
@staticmethod
def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'([^>]+?)\')'
property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop)
content_re = r'content=(?:"([^"]+?)"|\'([^\']+?)\'|\s*([^\s"\'=<>`]+?))'
property_re = (r'(?:name|property)=(?:\'og:%(prop)s\'|"og:%(prop)s"|\s*og:%(prop)s\b)'
% {'prop': re.escape(prop)})
template = r'<meta[^>]+?%s[^>]+?%s'
return [
template % (property_re, content_re),

View File

@ -27,9 +27,7 @@ class CriterionIE(InfoExtractor):
final_url = self._search_regex(
r'so.addVariable\("videoURL", "(.+?)"\)\;', webpage, 'video url')
title = self._og_search_title(webpage)
description = self._html_search_regex(
r'<meta name="description" content="(.+?)" />',
webpage, 'video description')
description = self._html_search_meta('description', webpage)
thumbnail = self._search_regex(
r'so.addVariable\("thumbnailURL", "(.+?)"\)\;',
webpage, 'thumbnail url')

View File

@ -32,6 +32,26 @@ from ..aes import (
class CrunchyrollBaseIE(InfoExtractor):
_NETRC_MACHINE = 'crunchyroll'
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _download_webpage(self, url_or_request, video_id, note=None, errnote=None, fatal=True, tries=1, timeout=5, encoding=None):
request = (url_or_request if isinstance(url_or_request, compat_urllib_request.Request)
else compat_urllib_request.Request(url_or_request))
@ -46,10 +66,22 @@ class CrunchyrollBaseIE(InfoExtractor):
return super(CrunchyrollBaseIE, self)._download_webpage(
request, video_id, note, errnote, fatal, tries, timeout, encoding)
@staticmethod
def _add_skip_wall(url):
parsed_url = compat_urlparse.urlparse(url)
qs = compat_urlparse.parse_qs(parsed_url.query)
# Always force skip_wall to bypass maturity wall, namely 18+ confirmation message:
# > This content may be inappropriate for some people.
# > Are you sure you want to continue?
# since it's not disabled by default in crunchyroll account's settings.
# See https://github.com/rg3/youtube-dl/issues/7202.
qs['skip_wall'] = ['1']
return compat_urlparse.urlunparse(
parsed_url._replace(query=compat_urllib_parse.urlencode(qs, True)))
class CrunchyrollIE(CrunchyrollBaseIE):
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_NETRC_MACHINE = 'crunchyroll'
_TESTS = [{
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'info_dict': {
@ -81,10 +113,13 @@ class CrunchyrollIE(CrunchyrollBaseIE):
# rtmp
'skip_download': True,
},
}, {
'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697',
'only_matching': True,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova/episode-1-the-birth-of-the-cosplay-club-565617',
'only_matching': True,
}]
_FORMAT_IDS = {
@ -94,24 +129,6 @@ class CrunchyrollIE(CrunchyrollBaseIE):
'1080': ('80', '108'),
}
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
self.report_login()
login_url = 'https://www.crunchyroll.com/?a=formhandler'
data = urlencode_postdata({
'formname': 'RpcApiUser_Login',
'name': username,
'password': password,
})
login_request = compat_urllib_request.Request(login_url, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
self._download_webpage(login_request, None, False, 'Wrong login info')
def _real_initialize(self):
self._login()
def _decrypt_subtitles(self, data, iv, id):
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8')))
@ -228,7 +245,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
def _get_subtitles(self, video_id, webpage):
subtitles = {}
for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage):
for sub_id, sub_name in re.findall(r'\bssid=([0-9]+)"[^>]+?\btitle="([^"]+)', webpage):
sub_page = self._download_webpage(
'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id,
video_id, note='Downloading subtitles for ' + sub_name)
@ -254,7 +271,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
else:
webpage_url = 'http://www.' + mobj.group('url')
webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage')
webpage = self._download_webpage(self._add_skip_wall(webpage_url), video_id, 'Downloading webpage')
note_m = self._html_search_regex(
r'<div class="showmedia-trailer-notice">(.+?)</div>',
webpage, 'trailer-notice', default='')
@ -352,7 +369,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
IE_NAME = "crunchyroll:playlist"
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?$'
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P<id>[\w\-]+))/?(?:\?|$)'
_TESTS = [{
'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@ -361,12 +378,25 @@ class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi'
},
'playlist_count': 13,
}, {
# geo-restricted (US), 18+ maturity wall, non-premium available
'url': 'http://www.crunchyroll.com/cosplay-complex-ova',
'info_dict': {
'id': 'cosplay-complex-ova',
'title': 'Cosplay Complex OVA'
},
'playlist_count': 3,
'skip': 'Georestricted',
}, {
# geo-restricted (US), 18+ maturity wall, non-premium will be available since 2015.11.14
'url': 'http://www.crunchyroll.com/ladies-versus-butlers?skip_wall=1',
'only_matching': True,
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
webpage = self._download_webpage(self._add_skip_wall(url), show_id)
title = self._html_search_regex(
r'(?s)<h1[^>]*>\s*<span itemprop="name">(.*?)</span>',
webpage, 'title')

View File

@ -96,6 +96,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'uploader': 'HotWaves1012',
'age_limit': 18,
}
},
# geo-restricted, player v5
{
'url': 'http://www.dailymotion.com/video/xhza0o',
'only_matching': True,
}
]
@ -119,11 +124,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
webpage, 'comment count', fatal=False))
player_v5 = self._search_regex(
r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);',
[r'buildPlayer\(({.+?})\);', r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);'],
webpage, 'player v5', default=None)
if player_v5:
player = self._parse_json(player_v5, video_id)
metadata = player['metadata']
self._check_error(metadata)
formats = []
for quality, media_list in metadata['qualities'].items():
for media in media_list:
@ -201,9 +209,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'video info', flags=re.MULTILINE),
video_id)
if info.get('error') is not None:
msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title']
raise ExtractorError(msg, expected=True)
self._check_error(info)
formats = []
for (key, format_id) in self._FORMATS:
@ -246,6 +252,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
'duration': info['duration']
}
def _check_error(self, info):
if info.get('error') is not None:
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, info['error']['title']), expected=True)
def _get_subtitles(self, video_id, webpage):
try:
sub_list = self._download_webpage(

View File

@ -87,7 +87,7 @@ class EaglePlatformIE(InfoExtractor):
m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
formats = self._extract_m3u8_formats(
m3u8_url, video_id,
'mp4', entry_protocol='m3u8_native')
'mp4', entry_protocol='m3u8_native', m3u8_id='hls')
mp4_url = self._get_video_url(
# Secure mp4 URL is constructed according to Player.prototype.mp4 from

View File

@ -33,20 +33,27 @@ class ExpoTVIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
player_key = self._search_regex(
r'<param name="playerKey" value="([^"]+)"', webpage, 'player key')
config_url = 'http://client.expotv.com/video/config/%s/%s' % (
video_id, player_key)
config = self._download_json(
config_url, video_id,
note='Downloading video configuration')
'http://client.expotv.com/video/config/%s/%s' % (video_id, player_key),
video_id, 'Downloading video configuration')
formats = [{
'url': fcfg['file'],
'height': int_or_none(fcfg.get('height')),
'format_note': fcfg.get('label'),
'ext': self._search_regex(
r'filename=.*\.([a-z0-9_A-Z]+)&', fcfg['file'],
'file extension', default=None),
} for fcfg in config['sources']]
formats = []
for fcfg in config['sources']:
media_url = fcfg.get('file')
if not media_url:
continue
if fcfg.get('type') == 'm3u8':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
else:
formats.append({
'url': media_url,
'height': int_or_none(fcfg.get('height')),
'format_id': fcfg.get('label'),
'ext': self._search_regex(
r'filename=.*\.([a-z0-9_A-Z]+)&', media_url,
'file extension', default=None) or fcfg.get('type'),
})
self._sort_formats(formats)
title = self._og_search_title(webpage)

View File

@ -14,7 +14,6 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
int_or_none,
limit_length,
urlencode_postdata,
get_element_by_id,
@ -142,16 +141,20 @@ class FacebookIE(InfoExtractor):
data = dict(json.loads(m.group(1)))
params_raw = compat_urllib_parse_unquote(data['params'])
params = json.loads(params_raw)
video_data = params['video_data'][0]
formats = []
for quality in ['sd', 'hd']:
src = video_data.get('%s_src' % quality)
if src is not None:
formats.append({
'format_id': quality,
'url': src,
})
for format_id, f in params['video_data'].items():
if not f or not isinstance(f, list):
continue
for quality in ('sd', 'hd'):
for src_type in ('src', 'src_no_ratelimit'):
src = f[0].get('%s_%s' % (quality, src_type))
if src:
formats.append({
'format_id': '%s_%s_%s' % (format_id, quality, src_type),
'url': src,
'preference': -10 if format_id == 'progressive' else 0,
})
if not formats:
raise ExtractorError('Cannot find video formats')
@ -171,7 +174,5 @@ class FacebookIE(InfoExtractor):
'id': video_id,
'title': video_title,
'formats': formats,
'duration': int_or_none(video_data.get('video_duration')),
'thumbnail': video_data.get('thumbnail_src'),
'uploader': uploader,
}

View File

@ -0,0 +1,41 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class FczenitIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?fc-zenit\.ru/video/gl(?P<id>[0-9]+)'
_TEST = {
'url': 'http://fc-zenit.ru/video/gl6785/',
'md5': '458bacc24549173fe5a5aa29174a5606',
'info_dict': {
'id': '6785',
'ext': 'mp4',
'title': '«Зенит-ТВ»: как Олег Шатов играл против «Урала»',
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_title = self._html_search_regex(r'<div class=\"photoalbum__title\">([^<]+)', webpage, 'title')
bitrates_raw = self._html_search_regex(r'bitrates:.*\n(.*)\]', webpage, 'video URL')
bitrates = re.findall(r'url:.?\'(.+?)\'.*?bitrate:.?([0-9]{3}?)', bitrates_raw)
formats = [{
'url': furl,
'tbr': tbr,
} for furl, tbr in bitrates]
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
'formats': formats,
}

View File

@ -2,11 +2,15 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
compat_parse_qs,
compat_urllib_parse_urlparse,
compat_urlparse,
)
from ..utils import (
ExtractorError,
parse_duration,
replace_extension,
)
@ -28,6 +32,7 @@ class FiveMinIE(InfoExtractor):
'id': '518013791',
'ext': 'mp4',
'title': 'iPad Mini with Retina Display Review',
'duration': 177,
},
},
{
@ -38,9 +43,52 @@ class FiveMinIE(InfoExtractor):
'id': '518086247',
'ext': 'mp4',
'title': 'How to Make a Next-Level Fruit Salad',
'duration': 184,
},
},
]
_ERRORS = {
'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
}
_QUALITIES = {
1: {
'width': 640,
'height': 360,
},
2: {
'width': 854,
'height': 480,
},
4: {
'width': 1280,
'height': 720,
},
8: {
'width': 1920,
'height': 1080,
},
16: {
'width': 640,
'height': 360,
},
32: {
'width': 854,
'height': 480,
},
64: {
'width': 1280,
'height': 720,
},
128: {
'width': 640,
'height': 360,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
@ -59,26 +107,36 @@ class FiveMinIE(InfoExtractor):
'https://syn.5min.com/handlers/SenseHandler.ashx?' + query,
video_id)
if not response['success']:
err_msg = response['errorMessage']
if err_msg == 'ErrorVideoUserNotGeo':
msg = 'Video not available from your location'
else:
msg = 'Aol said: %s' % err_msg
raise ExtractorError(msg, expected=True, video_id=video_id)
raise ExtractorError(
'%s said: %s' % (
self.IE_NAME,
self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
expected=True)
info = response['binding'][0]
second_id = compat_str(int(video_id[:-2]) + 1)
formats = []
for quality, height in [(1, 320), (2, 480), (4, 720), (8, 1080)]:
if any(r['ID'] == quality for r in info['Renditions']):
parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
for rendition in info['Renditions']:
if rendition['RenditionType'] == 'm3u8':
formats.extend(self._extract_m3u8_formats(rendition['Url'], video_id, m3u8_id='hls'))
elif rendition['RenditionType'] == 'aac':
continue
else:
rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
quality = self._QUALITIES.get(rendition['ID'], {})
formats.append({
'format_id': compat_str(quality),
'url': 'http://avideos.5min.com/%s/%s/%s_%s.mp4' % (second_id[-3:], second_id, video_id, quality),
'height': height,
'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
'url': rendition_url,
'width': quality.get('width'),
'height': quality.get('height'),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info['Title'],
'thumbnail': info.get('ThumbURL'),
'duration': parse_duration(info.get('Duration')),
'formats': formats,
}

View File

@ -46,10 +46,10 @@ class FourTubeIE(InfoExtractor):
thumbnail = self._html_search_meta('thumbnailUrl', webpage)
uploader_id = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/([^/"]+)" title="Go to [^"]+ page">',
webpage, 'uploader id')
webpage, 'uploader id', fatal=False)
uploader = self._html_search_regex(
r'<a class="img-avatar" href="[^"]+/channels/[^/"]+" title="Go to ([^"]+) page">',
webpage, 'uploader')
webpage, 'uploader', fatal=False)
categories_html = self._search_regex(
r'(?s)><i class="icon icon-tag"></i>\s*Categories / Tags\s*.*?<ul class="list">(.*?)</ul>',
@ -68,13 +68,24 @@ class FourTubeIE(InfoExtractor):
webpage, 'like count', fatal=False))
duration = parse_duration(self._html_search_meta('duration', webpage))
params_js = self._search_regex(
r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
webpage, 'initialization parameters'
)
params = self._parse_json('[%s]' % params_js, video_id)
media_id = params[0]
sources = ['%s' % p for p in params[2]]
media_id = self._search_regex(
r'<button[^>]+data-id=(["\'])(?P<id>\d+)\1[^>]+data-quality=', webpage,
'media id', default=None, group='id')
sources = [
quality
for _, quality in re.findall(r'<button[^>]+data-quality=(["\'])(.+?)\1', webpage)]
if not (media_id and sources):
player_js = self._download_webpage(
self._search_regex(
r'<script[^>]id=(["\'])playerembed\1[^>]+src=(["\'])(?P<url>.+?)\2',
webpage, 'player JS', group='url'),
video_id, 'Downloading player JS')
params_js = self._search_regex(
r'\$\.ajax\(url,\ opts\);\s*\}\s*\}\)\(([0-9,\[\] ]+)\)',
player_js, 'initialization parameters')
params = self._parse_json('[%s]' % params_js, video_id)
media_id = params[0]
sources = ['%s' % p for p in params[2]]
token_url = 'http://tkn.4tube.com/{0}/desktop/{1}'.format(
media_id, '+'.join(sources))

View File

@ -4,8 +4,8 @@ import re
import json
from .common import InfoExtractor
from ..compat import (
compat_urlparse,
from ..utils import (
qualities,
)
@ -30,24 +30,33 @@ class ImdbIE(InfoExtractor):
descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
available_formats = re.findall(
r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
flags=re.MULTILINE)
player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
# the player page contains the info for the default format, we have to
# fetch other pages for the rest of the formats
extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
format_pages = [
self._download_webpage(
f_url, video_id, 'Downloading info for %s format' % f_name)
for f_url, f_name in extra_formats]
format_pages.append(player_page)
quality = qualities(['SD', '480p', '720p'])
formats = []
for f_id, f_path in available_formats:
f_path = f_path.strip()
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
'Downloading info for %s format' % f_id)
for format_page in format_pages:
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
f_id = format_info['ffname']
formats.append({
'format_id': f_id,
'url': format_info['videoInfoList'][0]['videoUrl'],
'quality': quality(f_id),
})
self._sort_formats(formats)
return {
'id': video_id,

View File

@ -191,7 +191,7 @@ class IqiyiIE(InfoExtractor):
'vid': video_id,
'vinfo': 1,
'tm': tm,
'enc': self.md5_text((enc_key + tail)[1:64:2] + tail),
'enc': self.md5_text(enc_key + tail),
'qyid': _uuid,
'tn': random.random(),
'um': 0,
@ -205,7 +205,9 @@ class IqiyiIE(InfoExtractor):
def get_enc_key(self, swf_url, video_id):
# TODO: automatic key extraction
enc_key = 'eac64f22daf001da6ba9aa8da4d501508bbe90a4d4091fea3b0582a85b38c2cc' # last update at 2015-09-23-23 for Zombie::bite
# last update at 2015-10-22 for Zombie::bite
# '7223c67061dbea1259d0ceb44f44b6d62288f4f80c972170de5201d2321060270e05'[2:66][0::2]
enc_key = '2c76de15dcb44bd28ff0927d50d31620'
return enc_key
def _real_extract(self, url):

View File

@ -28,7 +28,7 @@ class JeuxVideoIE(InfoExtractor):
mobj = re.match(self._VALID_URL, url)
title = mobj.group(1)
webpage = self._download_webpage(url, title)
title = self._html_search_meta('name', webpage)
title = self._html_search_meta('name', webpage) or self._og_search_title(webpage)
config_url = self._html_search_regex(
r'data-src="(/contenu/medias/video.php.*?)"',
webpage, 'config URL')

View File

@ -9,13 +9,14 @@ from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urllib_request,
compat_urlparse,
compat_ord,
)
from ..utils import (
determine_ext,
ExtractorError,
parse_iso8601,
int_or_none,
encode_data_uri,
)
@ -25,15 +26,16 @@ class LetvIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.letv.com/ptv/vplay/22005890.html',
'md5': 'cab23bd68d5a8db9be31c9a222c1e8df',
'md5': 'edadcfe5406976f42f9f266057ee5e40',
'info_dict': {
'id': '22005890',
'ext': 'mp4',
'title': '第87届奥斯卡颁奖礼完美落幕 《鸟人》成最大赢家',
'timestamp': 1424747397,
'upload_date': '20150224',
'description': 'md5:a9cb175fd753e2962176b7beca21a47c',
}
},
'params': {
'hls_prefer_native': True,
},
}, {
'url': 'http://www.letv.com/ptv/vplay/1415246.html',
'info_dict': {
@ -42,16 +44,22 @@ class LetvIE(InfoExtractor):
'title': '美人天下01',
'description': 'md5:f88573d9d7225ada1359eaf0dbf8bcda',
},
'params': {
'hls_prefer_native': True,
},
}, {
'note': 'This video is available only in Mainland China, thus a proxy is needed',
'url': 'http://www.letv.com/ptv/vplay/1118082.html',
'md5': 'f80936fbe20fb2f58648e81386ff7927',
'md5': '2424c74948a62e5f31988438979c5ad1',
'info_dict': {
'id': '1118082',
'ext': 'mp4',
'title': '与龙共舞 完整版',
'description': 'md5:7506a5eeb1722bb9d4068f85024e3986',
},
'params': {
'hls_prefer_native': True,
},
'skip': 'Only available in China',
}]
@ -74,6 +82,27 @@ class LetvIE(InfoExtractor):
_loc3_ = self.ror(_loc3_, _loc2_ % 17)
return _loc3_
# see M3U8Encryption class in KLetvPlayer.swf
@staticmethod
def decrypt_m3u8(encrypted_data):
if encrypted_data[:5].decode('utf-8').lower() != 'vc_01':
return encrypted_data
encrypted_data = encrypted_data[5:]
_loc4_ = bytearray()
while encrypted_data:
b = compat_ord(encrypted_data[0])
_loc4_.extend([b // 16, b & 0x0f])
encrypted_data = encrypted_data[1:]
idx = len(_loc4_) - 11
_loc4_ = _loc4_[idx:] + _loc4_[:idx]
_loc7_ = bytearray()
while _loc4_:
_loc7_.append(_loc4_[0] * 16 + _loc4_[1])
_loc4_ = _loc4_[2:]
return bytes(_loc7_)
def _real_extract(self, url):
media_id = self._match_id(url)
page = self._download_webpage(url, media_id)
@ -115,23 +144,28 @@ class LetvIE(InfoExtractor):
for format_id in formats:
if format_id in dispatch:
media_url = playurl['domain'][0] + dispatch[format_id][0]
# Mimic what flvxz.com do
url_parts = list(compat_urlparse.urlparse(media_url))
qs = dict(compat_urlparse.parse_qs(url_parts[4]))
qs.update({
'platid': '14',
'splatid': '1401',
'tss': 'no',
'retry': 1
media_url += '&' + compat_urllib_parse.urlencode({
'm3v': 1,
'format': 1,
'expect': 3,
'rateid': format_id,
})
url_parts[4] = compat_urllib_parse.urlencode(qs)
media_url = compat_urlparse.urlunparse(url_parts)
nodes_data = self._download_json(
media_url, media_id,
'Download JSON metadata for format %s' % format_id)
req = self._request_webpage(
nodes_data['nodelist'][0]['location'], media_id,
note='Downloading m3u8 information for format %s' % format_id)
m3u8_data = self.decrypt_m3u8(req.read())
url_info_dict = {
'url': media_url,
'url': encode_data_uri(m3u8_data, 'application/vnd.apple.mpegurl'),
'ext': determine_ext(dispatch[format_id][1]),
'format_id': format_id,
'protocol': 'm3u8',
}
if format_id[-1:] == 'p':

View File

@ -140,13 +140,14 @@ class LyndaIE(LyndaBaseIE):
prioritized_streams = video_json.get('PrioritizedStreams')
if prioritized_streams:
formats.extend([
{
'url': video_url,
'width': int_or_none(format_id),
'format_id': format_id,
} for format_id, video_url in prioritized_streams['0'].items()
])
for prioritized_stream_id, prioritized_stream in prioritized_streams.items():
formats.extend([
{
'url': video_url,
'width': int_or_none(format_id),
'format_id': '%s-%s' % (prioritized_stream_id, format_id),
} for format_id, video_url in prioritized_stream.items()
])
self._check_formats(formats, video_id)
self._sort_formats(formats)

View File

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

View File

@ -167,8 +167,8 @@ class NowTVIE(InfoExtractor):
'app': app,
'play_path': 'mp4:%s' % play_path,
'ext': 'flv',
'page_url': url,
'player_url': 'http://rtl-now.rtl.de/includes/nc_player.swf',
'page_url': 'http://rtlnow.rtl.de',
'player_url': 'http://cdn.static-fra.de/now/vodplayer.swf',
'tbr': int_or_none(item.get('bitrate')),
})
self._sort_formats(formats)

View File

@ -13,7 +13,7 @@ from ..utils import (
class OdnoklassnikiIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_VALID_URL = r'https?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
_TESTS = [{
# metadata in JSON
'url': 'http://ok.ru/video/20079905452',
@ -66,6 +66,9 @@ class OdnoklassnikiIE(InfoExtractor):
}, {
'url': 'http://www.ok.ru/video/20648036891',
'only_matching': True,
}, {
'url': 'http://www.ok.ru/videoembed/20648036891',
'only_matching': True,
}]
def _real_extract(self, url):

View File

@ -108,12 +108,12 @@ class PBSIE(InfoExtractor):
{
'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
'info_dict': {
'id': '2280706814',
'id': '2276541483',
'display_id': 'player',
'ext': 'mp4',
'title': 'American Experience - Death and the Civil War',
'title': 'American Experience - Death and the Civil War, Chapter 1',
'description': 'American Experience, TVs most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
'duration': 6705,
'duration': 682,
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
@ -134,6 +134,7 @@ class PBSIE(InfoExtractor):
'params': {
'skip_download': True, # requires ffmpeg
},
'skip': 'Expired',
},
{
# Video embedded in iframe containing angle brackets as attribute's value (e.g.
@ -154,6 +155,12 @@ class PBSIE(InfoExtractor):
},
}
]
_ERRORS = {
101: 'We\'re sorry, but this video is not yet available.',
403: 'We\'re sorry, but this video is not available in your region due to right restrictions.',
404: 'We are experiencing technical difficulties that are preventing us from playing the video at this time. Please check back again soon.',
410: 'This video has expired and is no longer available for online streaming.',
}
def _extract_webpage(self, url):
mobj = re.match(self._VALID_URL, url)
@ -231,13 +238,11 @@ class PBSIE(InfoExtractor):
'Downloading %s video url info' % encoding_name)
if redirect_info['status'] == 'error':
if redirect_info['http_code'] == 403:
message = (
'The video is not available in your region due to '
'right restrictions')
else:
message = redirect_info['message']
raise ExtractorError(message, expected=True)
raise ExtractorError(
'%s said: %s' % (
self.IE_NAME,
self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])),
expected=True)
format_url = redirect_info.get('url')
if not format_url:

View File

@ -36,7 +36,7 @@ class RTBFIE(InfoExtractor):
data = self._parse_json(
unescapeHTML(self._search_regex(
r'data-video="([^"]+)"', webpage, 'data video')),
r'data-media="([^"]+)"', webpage, 'data video')),
video_id)
if data.get('provider').lower() == 'youtube':

View File

@ -9,16 +9,16 @@ from ..utils import (
class RteIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/(?P<id>[0-9]+)/'
_VALID_URL = r'https?://(?:www\.)?rte\.ie/player/[^/]{2,3}/show/[^/]+/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://www.rte.ie/player/de/show/10363114/',
'url': 'http://www.rte.ie/player/ie/show/iwitness-862/10478715/',
'info_dict': {
'id': '10363114',
'id': '10478715',
'ext': 'mp4',
'title': 'One News',
'title': 'Watch iWitness online',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'The One O\'Clock News followed by Weather.',
'duration': 436.844,
'description': 'iWitness : The spirit of Ireland, one voice and one minute at a time.',
'duration': 60.046,
},
'params': {
'skip_download': 'f4m fails with --test atm'

View File

@ -0,0 +1,81 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
js_to_json,
unescapeHTML,
)
class StitcherIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/(?:[^/]+/)+e/(?:(?P<display_id>[^/#?&]+?)-)?(?P<id>\d+)(?:[/#?&]|$)'
_TESTS = [{
'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
'info_dict': {
'id': '40789481',
'ext': 'mp3',
'title': 'Machine Learning Mastery and Cancer Clusters',
'description': 'md5:55163197a44e915a14a1ac3a1de0f2d3',
'duration': 1604,
'thumbnail': 're:^https?://.*\.jpg',
},
}, {
'url': 'http://www.stitcher.com/podcast/panoply/vulture-tv/e/the-rare-hourlong-comedy-plus-40846275?autoplay=true',
'info_dict': {
'id': '40846275',
'display_id': 'the-rare-hourlong-comedy-plus',
'ext': 'mp3',
'title': "The CW's 'Crazy Ex-Girlfriend'",
'description': 'md5:04f1e2f98eb3f5cbb094cea0f9e19b17',
'duration': 2235,
'thumbnail': 're:^https?://.*\.jpg',
},
'params': {
'skip_download': True,
},
}, {
# escaped title
'url': 'http://www.stitcher.com/podcast/marketplace-on-stitcher/e/40910226?autoplay=true',
'only_matching': True,
}, {
'url': 'http://www.stitcher.com/podcast/panoply/getting-in/e/episode-2a-how-many-extracurriculars-should-i-have-40876278?autoplay=true',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
audio_id = mobj.group('id')
display_id = mobj.group('display_id') or audio_id
webpage = self._download_webpage(url, display_id)
episode = self._parse_json(
js_to_json(self._search_regex(
r'(?s)var\s+stitcher\s*=\s*({.+?});\n', webpage, 'episode config')),
display_id)['config']['episode']
title = unescapeHTML(episode['title'])
formats = [{
'url': episode[episode_key],
'ext': determine_ext(episode[episode_key]) or 'mp3',
'vcodec': 'none',
} for episode_key in ('origEpisodeURL', 'episodeURL') if episode.get(episode_key)]
description = self._search_regex(
r'Episode Info:\s*</span>([^<]+)<', webpage, 'description', fatal=False)
duration = int_or_none(episode.get('duration'))
thumbnail = episode.get('episodeImage')
return {
'id': audio_id,
'display_id': display_id,
'title': title,
'description': description,
'duration': duration,
'thumbnail': thumbnail,
'formats': formats,
}

View File

@ -15,6 +15,7 @@ from ..compat import (
compat_urlparse,
)
from ..utils import (
encode_dict,
ExtractorError,
int_or_none,
parse_duration,
@ -27,8 +28,7 @@ class TwitchBaseIE(InfoExtractor):
_API_BASE = 'https://api.twitch.tv'
_USHER_BASE = 'http://usher.twitch.tv'
_LOGIN_URL = 'https://secure.twitch.tv/login'
_LOGIN_POST_URL = 'https://passport.twitch.tv/authentications/new'
_LOGIN_URL = 'http://www.twitch.tv/login'
_NETRC_MACHINE = 'twitch'
def _handle_error(self, response):
@ -61,26 +61,28 @@ class TwitchBaseIE(InfoExtractor):
if username is None:
return
login_page = self._download_webpage(
login_page, handle = self._download_webpage_handle(
self._LOGIN_URL, None, 'Downloading login page')
login_form = self._hidden_inputs(login_page)
login_form.update({
'login': username.encode('utf-8'),
'password': password.encode('utf-8'),
'username': username,
'password': password,
})
redirect_url = handle.geturl()
post_url = self._search_regex(
r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page,
'post url', default=self._LOGIN_POST_URL, group='url')
'post url', default=redirect_url, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
post_url = compat_urlparse.urljoin(redirect_url, post_url)
request = compat_urllib_request.Request(
post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Referer', self._LOGIN_URL)
post_url, compat_urllib_parse.urlencode(encode_dict(login_form)).encode('utf-8'))
request.add_header('Referer', redirect_url)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
@ -238,14 +240,24 @@ class TwitchVodIE(TwitchItemBaseIE):
def _real_extract(self, url):
item_id = self._match_id(url)
info = self._download_info(self._ITEM_SHORTCUT, item_id)
access_token = self._download_json(
'%s/api/vods/%s/access_token' % (self._API_BASE, item_id), item_id,
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
'%s/vod/%s?nauth=%s&nauthsig=%s&allow_source=true'
% (self._USHER_BASE, item_id, access_token['token'], access_token['sig']),
'%s/vod/%s?%s' % (
self._USHER_BASE, item_id,
compat_urllib_parse.urlencode({
'allow_source': 'true',
'allow_spectre': 'true',
'player': 'twitchweb',
'nauth': access_token['token'],
'nauthsig': access_token['sig'],
})),
item_id, 'mp4')
self._prefer_source(formats)
info['formats'] = formats

View File

@ -1,3 +1,4 @@
# coding: utf-8
from __future__ import unicode_literals
import re
@ -6,23 +7,51 @@ from .common import InfoExtractor
from ..compat import compat_urllib_request
from ..utils import (
float_or_none,
unescapeHTML,
xpath_text,
remove_end,
)
class TwitterCardIE(InfoExtractor):
IE_NAME = 'twitter:card'
_VALID_URL = r'https?://(?:www\.)?twitter\.com/i/cards/tfw/v1/(?P<id>\d+)'
_TEST = {
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
'md5': 'a74f50b310c83170319ba16de6955192',
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 30.033,
_TESTS = [
{
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
'md5': '7d2f6b4d2eb841a7ccc893d479bfceb4',
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg$',
'duration': 30.033,
}
},
}
{
'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
'info_dict': {
'id': '623160978427936768',
'ext': 'mp4',
'title': 'TwitterCard',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 80.155,
},
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
'md5': 'b6f35e8b08a0bec6c8af77a2f4b3a814',
'info_dict': {
'id': 'dq4Oj5quskI',
'ext': 'mp4',
'title': 'Ubuntu 11.10 Overview',
'description': 'Take a quick peek at what\'s new and improved in Ubuntu 11.10.\n\nOnce installed take a look at 10 Things to Do After Installing: http://www.omgubuntu.co.uk/2011/10/10-things-to-do-after-installing-ubuntu-11-10/',
'upload_date': '20111013',
'uploader': 'OMG! Ubuntu!',
'uploader_id': 'omgubuntu',
},
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
@ -40,10 +69,24 @@ class TwitterCardIE(InfoExtractor):
request.add_header('User-Agent', user_agent)
webpage = self._download_webpage(request, video_id)
config = self._parse_json(
unescapeHTML(self._search_regex(
r'data-player-config="([^"]+)"', webpage, 'data player config')),
youtube_url = self._html_search_regex(
r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
webpage, 'youtube iframe', default=None)
if youtube_url:
return self.url_result(youtube_url, 'Youtube')
config = self._parse_json(self._html_search_regex(
r'data-player-config="([^"]+)"', webpage, 'data player config'),
video_id)
if 'playlist' not in config:
if 'vmapUrl' in config:
vmap_data = self._download_xml(config['vmapUrl'], video_id)
video_url = xpath_text(vmap_data, './/MediaFile').strip()
formats.append({
'url': video_url,
})
break # same video regardless of UA
continue
video_url = config['playlist'][0]['source']
@ -70,3 +113,54 @@ class TwitterCardIE(InfoExtractor):
'duration': duration,
'formats': formats,
}
class TwitterIE(InfoExtractor):
IE_NAME = 'twitter'
_VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?P<user_id>[^/]+)/status/(?P<id>\d+)'
_TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
_TEST = {
'url': 'https://twitter.com/freethenipple/status/643211948184596480',
'md5': '31cd83a116fc41f99ae3d909d4caf6a0',
'info_dict': {
'id': '643211948184596480',
'ext': 'mp4',
'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 12.922,
'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
'uploader': 'FREE THE NIPPLE',
'uploader_id': 'freethenipple',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
user_id = mobj.group('user_id')
twid = mobj.group('id')
webpage = self._download_webpage(self._TEMPLATE_URL % (user_id, twid), twid)
username = remove_end(self._og_search_title(webpage), ' on Twitter')
title = self._og_search_description(webpage).strip('').replace('\n', ' ')
# strip 'https -_t.co_BJYgOjSeGA' junk from filenames
mobj = re.match(r'“(.*)\s+(https?://[^ ]+)”', title)
title, short_url = mobj.groups()
card_id = self._search_regex(
r'["\']/i/cards/tfw/v1/(\d+)', webpage, 'twitter card url')
card_url = 'https://twitter.com/i/cards/tfw/v1/' + card_id
return {
'_type': 'url_transparent',
'ie_key': 'TwitterCard',
'uploader_id': user_id,
'uploader': username,
'url': card_url,
'webpage_url': url,
'description': '%s on Twitter: "%s %s"' % (username, title, short_url),
'title': username + ' - ' + title,
}

View File

@ -14,7 +14,7 @@ class VidmeIE(InfoExtractor):
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
_TESTS = [{
'url': 'https://vid.me/QNB',
'md5': 'c62f1156138dc3323902188c5b5a8bd6',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'info_dict': {
'id': 'QNB',
'ext': 'mp4',
@ -93,6 +93,35 @@ class VidmeIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# nsfw, user-disabled
'url': 'https://vid.me/dzGJ',
'only_matching': True,
}, {
# suspended
'url': 'https://vid.me/Ox3G',
'only_matching': True,
}, {
# no formats in the API response
'url': 'https://vid.me/e5g',
'info_dict': {
'id': 'e5g',
'ext': 'mp4',
'title': 'Video upload (e5g)',
'thumbnail': 're:^https?://.*\.jpg',
'timestamp': 1401480195,
'upload_date': '20140530',
'uploader': None,
'uploader_id': None,
'age_limit': 0,
'duration': 483,
'view_count': int,
'like_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -114,6 +143,12 @@ class VidmeIE(InfoExtractor):
video = response['video']
if video.get('state') in ('user-disabled', 'suspended'):
raise ExtractorError(
'Vidme said: This video has been suspended either due to a copyright claim, '
'or for violating the terms of use.',
expected=True)
formats = [{
'format_id': f.get('type'),
'url': f['uri'],
@ -121,6 +156,14 @@ class VidmeIE(InfoExtractor):
'height': int_or_none(f.get('height')),
'preference': 0 if f.get('type', '').endswith('clip') else 1,
} for f in video.get('formats', []) if f.get('uri')]
if not formats and video.get('complete_url'):
formats.append({
'url': video.get('complete_url'),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
})
self._sort_formats(formats)
title = video['title']
@ -137,7 +180,7 @@ class VidmeIE(InfoExtractor):
return {
'id': video_id,
'title': title,
'title': title or 'Video upload (%s)' % video_id,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,

View File

@ -131,10 +131,11 @@ class ViewsterIE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id='hds'))
elif ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls',
fatal=False # m3u8 sometimes fail
))
fatal=False) # m3u8 sometimes fail
if m3u8_formats:
formats.extend(m3u8_formats)
else:
format_id = media.get('Bitrate')
f = {

View File

@ -39,7 +39,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
return
self.report_login()
webpage = self._download_webpage(self._LOGIN_URL, None, False)
token = self._extract_xsrft(webpage)
token, vuid = self._extract_xsrft_and_vuid(webpage)
data = urlencode_postdata({
'action': 'login',
'email': username,
@ -49,13 +49,18 @@ class VimeoBaseInfoExtractor(InfoExtractor):
})
login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
login_request.add_header('Cookie', 'vuid=%s' % vuid)
login_request.add_header('Referer', self._LOGIN_URL)
self._download_webpage(login_request, None, False, 'Wrong login info')
def _extract_xsrft(self, webpage):
return self._search_regex(
def _extract_xsrft_and_vuid(self, webpage):
xsrft = self._search_regex(
r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
webpage, 'login token', group='xsrft')
vuid = self._search_regex(
r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
webpage, 'vuid', group='vuid')
return xsrft, vuid
class VimeoIE(VimeoBaseInfoExtractor):
@ -80,12 +85,12 @@ class VimeoIE(VimeoBaseInfoExtractor):
'info_dict': {
'id': '56015672',
'ext': 'mp4',
"upload_date": "20121220",
"description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
"uploader_id": "user7108434",
"uploader": "Filippo Valsorda",
"title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
"duration": 10,
'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
'description': 'md5:2d3305bad981a06ff79f027f19865021',
'upload_date': '20121220',
'uploader_id': 'user7108434',
'uploader': 'Filippo Valsorda',
'duration': 10,
},
},
{
@ -98,7 +103,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'openstreetmapus',
'uploader': 'OpenStreetMap US',
'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
'description': 'md5:380943ec71b89736ff4bf27183233d09',
'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
'duration': 1595,
},
},
@ -128,7 +133,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user18948128',
'uploader': 'Jaime Marquínez Ferrándiz',
'duration': 10,
'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.',
'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
},
'params': {
'videopassword': 'youtube-dl',
@ -152,7 +157,6 @@ class VimeoIE(VimeoBaseInfoExtractor):
},
{
'url': 'http://vimeo.com/76979871',
'md5': '3363dd6ffebe3784d56f4132317fd446',
'note': 'Video with subtitles',
'info_dict': {
'id': '76979871',
@ -177,6 +181,11 @@ class VimeoIE(VimeoBaseInfoExtractor):
'uploader_id': 'user28849593',
},
},
{
'url': 'https://vimeo.com/109815029',
'note': 'Video not completely processed, "failed" seed status',
'only_matching': True,
},
]
@staticmethod
@ -198,7 +207,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
password = self._downloader.params.get('videopassword', None)
if password is None:
raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
token = self._extract_xsrft(webpage)
token, vuid = self._extract_xsrft_and_vuid(webpage)
data = urlencode_postdata({
'password': password,
'token': token,
@ -208,6 +217,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
url = url.replace('http://', 'https://')
password_request = compat_urllib_request.Request(url + '/password', data)
password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
password_request.add_header('Referer', url)
return self._download_webpage(
password_request, video_id,
@ -268,20 +278,30 @@ class VimeoIE(VimeoBaseInfoExtractor):
self.report_extraction(video_id)
vimeo_config = self._search_regex(
r'vimeo\.config\s*=\s*({.+?});', webpage,
r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
'vimeo config', default=None)
if vimeo_config:
seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
if seed_status.get('state') == 'failed':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, seed_status['title']),
'%s said: %s' % (self.IE_NAME, seed_status['title']),
expected=True)
# Extract the config JSON
try:
try:
config_url = self._html_search_regex(
r' data-config-url="(.+?)"', webpage, 'config URL')
r' data-config-url="(.+?)"', webpage,
'config URL', default=None)
if not config_url:
# Sometimes new react-based page is served instead of old one that require
# different config URL extraction approach (see
# https://github.com/rg3/youtube-dl/pull/7209)
vimeo_clip_page_config = self._search_regex(
r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
'vimeo clip page config')
config_url = self._parse_json(
vimeo_clip_page_config, video_id)['player']['config_url']
config_json = self._download_webpage(config_url, video_id)
config = json.loads(config_json)
except RegexNotFoundError:
@ -391,14 +411,20 @@ class VimeoIE(VimeoBaseInfoExtractor):
'ext': codec_extension,
'url': video_url,
'format_id': format_id,
'width': file_info.get('width'),
'height': file_info.get('height'),
'width': int_or_none(file_info.get('width')),
'height': int_or_none(file_info.get('height')),
'tbr': int_or_none(file_info.get('bitrate')),
})
formats = []
m3u8_url = config_files.get('hls', {}).get('all')
if m3u8_url:
m3u8_formats = self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
if m3u8_formats:
formats.extend(m3u8_formats)
for key in ('other', 'sd', 'hd'):
formats += files[key]
if len(formats) == 0:
raise ExtractorError('No known codec found')
self._sort_formats(formats)
subtitles = {}
text_tracks = config['request'].get('text_tracks')
@ -459,7 +485,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
if password is None:
raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
fields = self._hidden_inputs(login_form)
token = self._extract_xsrft(webpage)
token, vuid = self._extract_xsrft_and_vuid(webpage)
fields['token'] = token
fields['password'] = password
post = urlencode_postdata(fields)
@ -468,6 +494,7 @@ class VimeoChannelIE(VimeoBaseInfoExtractor):
password_url = compat_urlparse.urljoin(page_url, password_path)
password_request = compat_urllib_request.Request(password_url, post)
password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
password_request.add_header('Cookie', 'vuid=%s' % vuid)
self._set_cookie('vimeo.com', 'xsrft', token)
return self._download_webpage(

View File

@ -1,10 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import itertools
from .common import InfoExtractor
from ..utils import unified_strdate
from ..utils import (
int_or_none,
unified_strdate,
)
class VineIE(InfoExtractor):
@ -17,10 +21,12 @@ class VineIE(InfoExtractor):
'ext': 'mp4',
'title': 'Chicken.',
'alt_title': 'Vine by Jack Dorsey',
'description': 'Chicken.',
'upload_date': '20130519',
'uploader': 'Jack Dorsey',
'uploader_id': '76',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/MYxVapFvz2z',
@ -29,11 +35,13 @@ class VineIE(InfoExtractor):
'id': 'MYxVapFvz2z',
'ext': 'mp4',
'title': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Luna',
'description': 'Fuck Da Police #Mikebrown #justice #ferguson #prayforferguson #protesting #NMOS14',
'alt_title': 'Vine by Mars Ruiz',
'upload_date': '20140815',
'uploader': 'Luna',
'uploader': 'Mars Ruiz',
'uploader_id': '1102363502380728320',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/v/bxVjBbZlPUH',
@ -43,14 +51,33 @@ class VineIE(InfoExtractor):
'ext': 'mp4',
'title': '#mw3 #ac130 #killcam #angelofdeath',
'alt_title': 'Vine by Z3k3',
'description': '#mw3 #ac130 #killcam #angelofdeath',
'upload_date': '20130430',
'uploader': 'Z3k3',
'uploader_id': '936470460173008896',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
}, {
'url': 'https://vine.co/oembed/MYxVapFvz2z.json',
'only_matching': True,
}, {
'url': 'https://vine.co/v/e192BnZnZ9V',
'info_dict': {
'id': 'e192BnZnZ9V',
'ext': 'mp4',
'title': 'ยิ้ม~ เขิน~ อาย~ น่าร้ากอ้ะ >//< @n_whitewo @orlameena #lovesicktheseries #lovesickseason2',
'alt_title': 'Vine by Pimry_zaa',
'upload_date': '20150705',
'uploader': 'Pimry_zaa',
'uploader_id': '1135760698325307392',
'like_count': int,
'comment_count': int,
'repost_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
@ -58,32 +85,33 @@ class VineIE(InfoExtractor):
webpage = self._download_webpage('https://vine.co/v/' + video_id, video_id)
data = self._parse_json(
self._html_search_regex(
r'window\.POST_DATA = { %s: ({.+?}) };\s*</script>' % video_id,
self._search_regex(
r'window\.POST_DATA\s*=\s*{\s*%s\s*:\s*({.+?})\s*};\s*</script>' % video_id,
webpage, 'vine data'),
video_id)
formats = [{
'format_id': '%(format)s-%(rate)s' % f,
'vcodec': f['format'],
'quality': f['rate'],
'vcodec': f.get('format'),
'quality': f.get('rate'),
'url': f['videoUrl'],
} for f in data['videoUrls']]
} for f in data['videoUrls'] if f.get('videoUrl')]
self._sort_formats(formats)
username = data.get('username')
return {
'id': video_id,
'title': self._og_search_title(webpage),
'alt_title': self._og_search_description(webpage, default=None),
'description': data['description'],
'thumbnail': data['thumbnailUrl'],
'upload_date': unified_strdate(data['created']),
'uploader': data['username'],
'uploader_id': data['userIdStr'],
'like_count': data['likes']['count'],
'comment_count': data['comments']['count'],
'repost_count': data['reposts']['count'],
'title': data.get('description') or self._og_search_title(webpage),
'alt_title': 'Vine by %s' % username if username else self._og_search_description(webpage, default=None),
'thumbnail': data.get('thumbnailUrl'),
'upload_date': unified_strdate(data.get('created')),
'uploader': username,
'uploader_id': data.get('userIdStr'),
'like_count': int_or_none(data.get('likes', {}).get('count')),
'comment_count': int_or_none(data.get('comments', {}).get('count')),
'repost_count': int_or_none(data.get('reposts', {}).get('count')),
'formats': formats,
}

View File

@ -46,6 +46,12 @@ class YandexMusicTrackIE(InfoExtractor):
% (data['host'], key, data['ts'] + data['path'], storage[1]))
def _get_track_info(self, track):
thumbnail = None
cover_uri = track.get('albums', [{}])[0].get('coverUri')
if cover_uri:
thumbnail = cover_uri.replace('%%', 'orig')
if not thumbnail.startswith('http'):
thumbnail = 'http://' + thumbnail
return {
'id': track['id'],
'ext': 'mp3',
@ -53,6 +59,7 @@ class YandexMusicTrackIE(InfoExtractor):
'title': '%s - %s' % (track['artists'][0]['name'], track['title']),
'filesize': int_or_none(track.get('fileSize')),
'duration': float_or_none(track.get('durationMs'), 1000),
'thumbnail': thumbnail,
}
def _real_extract(self, url):

View File

@ -178,6 +178,52 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
return
class YoutubePlaylistBaseInfoExtractor(InfoExtractor):
# Extract the video ids from the playlist pages
def _entries(self, page, playlist_id):
more_widget_html = content_html = page
for page_num in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html):
yield self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
# have more videos
break
more_widget_html = more['load_more_widget_html']
def extract_videos_from_page(self, page):
ids_in_page = []
titles_in_page = []
for mobj in re.finditer(self._VIDEO_RE, page):
# The link with index 0 is not the first video of the playlist (not sure if still actual)
if 'index' in mobj.groupdict() and mobj.group('id') == '0':
continue
video_id = mobj.group('id')
video_title = unescapeHTML(mobj.group('title'))
if video_title:
video_title = video_title.strip()
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
return zip(ids_in_page, titles_in_page)
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
_VALID_URL = r"""(?x)^
@ -1419,7 +1465,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
}
class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com playlists'
_VALID_URL = r"""(?x)(?:
(?:https?://)?
@ -1440,7 +1486,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
)"""
_TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
IE_NAME = 'youtube:playlist'
_TESTS = [{
'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
@ -1557,37 +1603,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
else:
self.report_warning('Youtube gives an alert message: ' + match)
# Extract the video ids from the playlist pages
def _entries():
more_widget_html = content_html = page
for page_num in itertools.count(1):
matches = re.finditer(self._VIDEO_RE, content_html)
# We remove the duplicates and the link with index 0
# (it's not the first video of the playlist)
new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0')
for vid_id in new_ids:
yield self.url_result(vid_id, 'Youtube', video_id=vid_id)
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), playlist_id,
'Downloading page #%s' % page_num,
transform_source=uppercase_escape)
content_html = more['content_html']
if not content_html.strip():
# Some webpages show a "Load more" button but they don't
# have more videos
break
more_widget_html = more['load_more_widget_html']
playlist_title = self._html_search_regex(
r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>',
page, 'title')
return self.playlist_result(_entries(), playlist_id, playlist_title)
return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
def _real_extract(self, url):
# Extract playlist id
@ -1613,10 +1633,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor):
return self._extract_playlist(playlist_id)
class YoutubeChannelIE(InfoExtractor):
class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
IE_DESC = 'YouTube.com channels'
_VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
_TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
_VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
IE_NAME = 'youtube:channel'
_TESTS = [{
'note': 'paginated channel',
@ -1627,22 +1648,6 @@ class YoutubeChannelIE(InfoExtractor):
}
}]
@staticmethod
def extract_videos_from_page(page):
ids_in_page = []
titles_in_page = []
for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page):
video_id = mobj.group('id')
video_title = unescapeHTML(mobj.group('title'))
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
return zip(ids_in_page, titles_in_page)
def _real_extract(self, url):
channel_id = self._match_id(url)
@ -1685,29 +1690,7 @@ class YoutubeChannelIE(InfoExtractor):
for video_id, video_title in self.extract_videos_from_page(channel_page)]
return self.playlist_result(entries, channel_id)
def _entries():
more_widget_html = content_html = channel_page
for pagenum in itertools.count(1):
for video_id, video_title in self.extract_videos_from_page(content_html):
yield self.url_result(
video_id, 'Youtube', video_id=video_id,
video_title=video_title)
mobj = re.search(
r'data-uix-load-more-href="/?(?P<more>[^"]+)"',
more_widget_html)
if not mobj:
break
more = self._download_json(
'https://youtube.com/%s' % mobj.group('more'), channel_id,
'Downloading page #%s' % (pagenum + 1),
transform_source=uppercase_escape)
content_html = more['content_html']
more_widget_html = more['load_more_widget_html']
return self.playlist_result(_entries(), channel_id)
return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
class YoutubeUserIE(YoutubeChannelIE):

View File

@ -9,6 +9,7 @@ from ..utils import (
int_or_none,
unified_strdate,
OnDemandPagedList,
xpath_text,
)
@ -19,13 +20,11 @@ def extract_from_xml_url(ie, video_id, xml_url):
errnote='Failed to download video info')
title = doc.find('.//information/title').text
description = doc.find('.//information/detail').text
duration = int(doc.find('.//details/lengthSec').text)
uploader_node = doc.find('.//details/originChannelTitle')
uploader = None if uploader_node is None else uploader_node.text
uploader_id_node = doc.find('.//details/originChannelId')
uploader_id = None if uploader_id_node is None else uploader_id_node.text
upload_date = unified_strdate(doc.find('.//details/airtime').text)
description = xpath_text(doc, './/information/detail', 'description')
duration = int_or_none(xpath_text(doc, './/details/lengthSec', 'duration'))
uploader = xpath_text(doc, './/details/originChannelTitle', 'uploader')
uploader_id = xpath_text(doc, './/details/originChannelId', 'uploader id')
upload_date = unified_strdate(xpath_text(doc, './/details/airtime', 'upload date'))
def xml_to_format(fnode):
video_url = fnode.find('url').text
@ -40,15 +39,14 @@ def extract_from_xml_url(ie, video_id, xml_url):
ext = format_m.group('container')
proto = format_m.group('proto').lower()
quality = fnode.find('./quality').text
abr = int(fnode.find('./audioBitrate').text) // 1000
vbr_node = fnode.find('./videoBitrate')
vbr = None if vbr_node is None else int(vbr_node.text) // 1000
quality = xpath_text(fnode, './quality', 'quality')
abr = int_or_none(xpath_text(fnode, './audioBitrate', 'abr'), 1000)
vbr = int_or_none(xpath_text(fnode, './videoBitrate', 'vbr'), 1000)
width_node = fnode.find('./width')
width = None if width_node is None else int_or_none(width_node.text)
height_node = fnode.find('./height')
height = None if height_node is None else int_or_none(height_node.text)
width = int_or_none(xpath_text(fnode, './width', 'width'))
height = int_or_none(xpath_text(fnode, './height', 'height'))
filesize = int_or_none(xpath_text(fnode, './filesize', 'filesize'))
format_note = ''
if not format_note:
@ -64,12 +62,31 @@ def extract_from_xml_url(ie, video_id, xml_url):
'vbr': vbr,
'width': width,
'height': height,
'filesize': int_or_none(fnode.find('./filesize').text),
'filesize': filesize,
'format_note': format_note,
'protocol': proto,
'_available': is_available,
}
def xml_to_thumbnails(fnode):
thumbnails = []
for node in fnode:
thumbnail_url = node.text
if not thumbnail_url:
continue
thumbnail = {
'url': thumbnail_url,
}
if 'key' in node.attrib:
m = re.match('^([0-9]+)x([0-9]+)$', node.attrib['key'])
if m:
thumbnail['width'] = int(m.group(1))
thumbnail['height'] = int(m.group(2))
thumbnails.append(thumbnail)
return thumbnails
thumbnails = xml_to_thumbnails(doc.findall('.//teaserimages/teaserimage'))
format_nodes = doc.findall('.//formitaeten/formitaet')
formats = list(filter(
lambda f: f['_available'],
@ -81,6 +98,7 @@ def extract_from_xml_url(ie, video_id, xml_url):
'title': title,
'description': description,
'duration': duration,
'thumbnails': thumbnails,
'uploader': uploader,
'uploader_id': uploader_id,
'upload_date': upload_date,

View File

@ -9,9 +9,11 @@ from ..utils import ExtractorError
class ZingMp3BaseInfoExtractor(InfoExtractor):
def _extract_item(self, item):
def _extract_item(self, item, fatal=True):
error_message = item.find('./errormessage').text
if error_message:
if not fatal:
return
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, error_message),
expected=True)
@ -43,7 +45,9 @@ class ZingMp3BaseInfoExtractor(InfoExtractor):
entries = []
for i, item in enumerate(items, 1):
entry = self._extract_item(item)
entry = self._extract_item(item, fatal=False)
if not entry:
continue
entry['id'] = '%s-%d' % (id, i)
entries.append(entry)
@ -85,7 +89,7 @@ class ZingMp3SongIE(ZingMp3BaseInfoExtractor):
class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
_VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
_VALID_URL = r'https?://mp3\.zing\.vn/(?:album|playlist)/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html'
_TESTS = [{
'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html',
'info_dict': {
@ -94,6 +98,9 @@ class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor):
'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless',
},
'playlist_count': 10,
}, {
'url': 'http://mp3.zing.vn/playlist/Duong-Hong-Loan-apollobee/IWCAACCB.html',
'only_matching': True,
}]
IE_NAME = 'zingmp3:album'
IE_DESC = 'mp3.zing.vn albums'

View File

@ -3,6 +3,7 @@
from __future__ import unicode_literals
import base64
import calendar
import codecs
import contextlib
@ -1371,7 +1372,12 @@ def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
v = getattr(v, get_attr, None)
if v == '':
v = None
return default if v is None else (int(v) * invscale // scale)
if v is None:
return default
try:
return int(v) * invscale // scale
except ValueError:
return default
def str_or_none(v, default=None):
@ -1387,7 +1393,12 @@ def str_to_int(int_str):
def float_or_none(v, scale=1, invscale=1, default=None):
return default if v is None else (float(v) * invscale / scale)
if v is None:
return default
try:
return float(v) * invscale / scale
except ValueError:
return default
def parse_duration(s):
@ -1690,8 +1701,8 @@ def js_to_json(code):
if v in ('true', 'false', 'null'):
return v
if v.startswith('"'):
return v
if v.startswith("'"):
v = re.sub(r"\\'", "'", v[1:-1])
elif v.startswith("'"):
v = v[1:-1]
v = re.sub(r"\\\\|\\'|\"", lambda m: {
'\\\\': '\\\\',
@ -1785,6 +1796,10 @@ def urlhandle_detect_ext(url_handle):
return mimetype2ext(getheader('Content-Type'))
def encode_data_uri(data, mime_type):
return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
def age_restricted(content_limit, age_limit):
""" Returns True iff the content should be blocked """

View File

@ -1,3 +1,3 @@
from __future__ import unicode_literals
__version__ = '2015.10.06.2'
__version__ = '2015.10.23'