youtube_dl/extractor/comedycentral.py

   1 from __future__ import unicode_literals
   2
   3 from .mtv import MTVServicesInfoExtractor
   4 from .common import InfoExtractor
   5
   6
   7 class ComedyCentralIE(MTVServicesInfoExtractor):
   8     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
   9         (video-clips|episodes|cc-studios|video-collections|full-episodes|shows)
  10         /(?P<title>.*)'''
  11     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
  12
  13     _TESTS = [{
  14         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
  15         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
  16         'info_dict': {
  17             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
  18             'ext': 'mp4',
  19             'title': 'CC:Stand-Up|August 18, 2013|1|0101|Uncensored - Too Good of a Mother',
  20             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
  21             'timestamp': 1376798400,
  22             'upload_date': '20130818',
  23         },
  24     }, {
  25         'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/interviews/6yx39d/exclusive-rand-paul-extended-interview',
  26         'only_matching': True,
  27     }]
  28
  29
  30 class ToshIE(MTVServicesInfoExtractor):
  31     IE_DESC = 'Tosh.0'
  32     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
  33     _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
  34
  35     _TESTS = [{
  36         'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
  37         'info_dict': {
  38             'description': 'Tosh asked fans to share their summer plans.',
  39             'title': 'Twitter Users Share Summer Plans',
  40         },
  41         'playlist': [{
  42             'md5': 'f269e88114c1805bb6d7653fecea9e06',
  43             'info_dict': {
  44                 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
  45                 'ext': 'mp4',
  46                 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
  47                 'description': 'Tosh asked fans to share their summer plans.',
  48                 'thumbnail': 're:^https?://.*\.jpg',
  49                 # It's really reported to be published on year 2077
  50                 'upload_date': '20770610',
  51                 'timestamp': 3390510600,
  52                 'subtitles': {
  53                     'en': 'mincount:3',
  54                 },
  55             },
  56         }]
  57     }, {
  58         'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
  59         'only_matching': True,
  60     }]
  61
  62     @classmethod
  63     def _transform_rtmp_url(cls, rtmp_video_url):
  64         new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
  65         new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
  66         return new_urls
  67
  68
  69 class ComedyCentralTVIE(MTVServicesInfoExtractor):
  70     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
  71     _TESTS = [{
  72         'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
  73         'info_dict': {
  74             'id': 'local_playlist-f99b626bdfe13568579a',
  75             'ext': 'flv',
  76             'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
  77         },
  78         'params': {
  79             # rtmp download
  80             'skip_download': True,
  81         },
  82     }, {
  83         'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
  84         'only_matching': True,
  85     }, {
  86         'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
  87         'only_matching': True,
  88     }]
  89
  90     def _real_extract(self, url):
  91         video_id = self._match_id(url)
  92
  93         webpage = self._download_webpage(url, video_id)
  94
  95         mrss_url = self._search_regex(
  96             r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
  97             webpage, 'mrss url', group='url')
  98
  99         return self._get_videos_info_from_url(mrss_url, video_id)
 100
 101
 102 class ComedyCentralShortnameIE(InfoExtractor):
 103     _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
 104     _TESTS = [{
 105         'url': ':tds',
 106         'only_matching': True,
 107     }, {
 108         'url': ':thedailyshow',
 109         'only_matching': True,
 110     }]
 111
 112     def _real_extract(self, url):
 113         video_id = self._match_id(url)
 114         shortcut_map = {
 115             'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 116             'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 117         }
 118         return self.url_result(shortcut_map[video_id])