_ Git - youtube-dl/blob - youtube_dl/extractor/comedycentral.py

   1 from __future__ import unicode_literals
   2
   3 from .mtv import MTVServicesInfoExtractor
   4
   5
   6 class ComedyCentralIE(MTVServicesInfoExtractor):
   7     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
   8         (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
   9         /(?P<title>.*)'''
  10     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
  11
  12     _TESTS = [{
  13         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
  14         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
  15         'info_dict': {
  16             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
  17             'ext': 'mp4',
  18             'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
  19             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
  20             'timestamp': 1376798400,
  21             'upload_date': '20130818',
  22         },
  23     }, {
  24         'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
  25         'only_matching': True,
  26     }]
  27
  28
  29 class ToshIE(MTVServicesInfoExtractor):
  30     IE_DESC = 'Tosh.0'
  31     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
  32     _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
  33
  34     _TESTS = [{
  35         'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
  36         'info_dict': {
  37             'description': 'Tosh asked fans to share their summer plans.',
  38             'title': 'Twitter Users Share Summer Plans',
  39         },
  40         'playlist': [{
  41             'md5': 'f269e88114c1805bb6d7653fecea9e06',
  42             'info_dict': {
  43                 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
  44                 'ext': 'mp4',
  45                 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
  46                 'description': 'Tosh asked fans to share their summer plans.',
  47                 'thumbnail': 're:^https?://.*\.jpg',
  48                 # It's really reported to be published on year 2077
  49                 'upload_date': '20770610',
  50                 'timestamp': 3390510600,
  51                 'subtitles': {
  52                     'en': 'mincount:3',
  53                 },
  54             },
  55         }]
  56     }, {
  57         'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
  58         'only_matching': True,
  59     }]
  60
  61     @classmethod
  62     def _transform_rtmp_url(cls, rtmp_video_url):
  63         new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
  64         new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
  65         return new_urls
  66
  67
  68 class ComedyCentralTVIE(MTVServicesInfoExtractor):
  69     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
  70     _TESTS = [{
  71         'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
  72         'info_dict': {
  73             'id': 'local_playlist-f99b626bdfe13568579a',
  74             'ext': 'flv',
  75             'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
  76         },
  77         'params': {
  78             # rtmp download
  79             'skip_download': True,
  80         },
  81     }, {
  82         'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
  83         'only_matching': True,
  84     }, {
  85         'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
  86         'only_matching': True,
  87     }]
  88
  89     def _real_extract(self, url):
  90         video_id = self._match_id(url)
  91
  92         webpage = self._download_webpage(url, video_id)
  93
  94         mrss_url = self._search_regex(
  95             r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
  96             webpage, 'mrss url', group='url')
  97
  98         return self._get_videos_info_from_url(mrss_url, video_id)