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|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 ComedyCentralFullEpisodesIE(MTVServicesInfoExtractor):
  31     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
  32         (?:full-episodes)
  33         /(?P<id>[^?]+)'''
  34     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
  35
  36     _TESTS = [{
  37         'url': 'http://www.cc.com/full-episodes/pv391a/the-daily-show-with-trevor-noah-november-28--2016---ryan-speedo-green-season-22-ep-22028',
  38         'info_dict': {
  39             'description': 'Donald Trump is accused of exploiting his president-elect status for personal gain, Cuban leader Fidel Castro dies, and Ryan Speedo Green discusses "Sing for Your Life."',
  40             'title': 'November 28, 2016 - Ryan Speedo Green',
  41         },
  42         'playlist_count': 4,
  43     }]
  44
  45     def _real_extract(self, url):
  46         playlist_id = self._match_id(url)
  47         webpage = self._download_webpage(url, playlist_id)
  48
  49         feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
  50         feed = self._parse_json(feed_json, playlist_id)
  51         zones = feed['manifest']['zones']
  52
  53         video_zone = zones['t2_lc_promo1']
  54         feed = self._download_json(video_zone['feed'], playlist_id)
  55         mgid = feed['result']['data']['id']
  56
  57         videos_info = self._get_videos_info(mgid)
  58         return videos_info
  59
  60
  61 class ToshIE(MTVServicesInfoExtractor):
  62     IE_DESC = 'Tosh.0'
  63     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
  64     _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
  65
  66     _TESTS = [{
  67         'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
  68         'info_dict': {
  69             'description': 'Tosh asked fans to share their summer plans.',
  70             'title': 'Twitter Users Share Summer Plans',
  71         },
  72         'playlist': [{
  73             'md5': 'f269e88114c1805bb6d7653fecea9e06',
  74             'info_dict': {
  75                 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
  76                 'ext': 'mp4',
  77                 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
  78                 'description': 'Tosh asked fans to share their summer plans.',
  79                 'thumbnail': 're:^https?://.*\.jpg',
  80                 # It's really reported to be published on year 2077
  81                 'upload_date': '20770610',
  82                 'timestamp': 3390510600,
  83                 'subtitles': {
  84                     'en': 'mincount:3',
  85                 },
  86             },
  87         }]
  88     }, {
  89         'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
  90         'only_matching': True,
  91     }]
  92
  93     @classmethod
  94     def _transform_rtmp_url(cls, rtmp_video_url):
  95         new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
  96         new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
  97         return new_urls
  98
  99
 100 class ComedyCentralTVIE(MTVServicesInfoExtractor):
 101     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
 102     _TESTS = [{
 103         'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
 104         'info_dict': {
 105             'id': 'local_playlist-f99b626bdfe13568579a',
 106             'ext': 'flv',
 107             'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
 108         },
 109         'params': {
 110             # rtmp download
 111             'skip_download': True,
 112         },
 113     }, {
 114         'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
 115         'only_matching': True,
 116     }, {
 117         'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
 118         'only_matching': True,
 119     }]
 120
 121     def _real_extract(self, url):
 122         video_id = self._match_id(url)
 123
 124         webpage = self._download_webpage(url, video_id)
 125
 126         mrss_url = self._search_regex(
 127             r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
 128             webpage, 'mrss url', group='url')
 129
 130         return self._get_videos_info_from_url(mrss_url, video_id)
 131
 132
 133 class ComedyCentralShortnameIE(InfoExtractor):
 134     _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
 135     _TESTS = [{
 136         'url': ':tds',
 137         'only_matching': True,
 138     }, {
 139         'url': ':thedailyshow',
 140         'only_matching': True,
 141     }]
 142
 143     def _real_extract(self, url):
 144         video_id = self._match_id(url)
 145         shortcut_map = {
 146             'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 147             'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 148         }
 149         return self.url_result(shortcut_map[video_id])