Raphaël G. Git Repositories - youtubedl/blob - 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(?=/[^/]+/(?!full-episodes)))
  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|shows(?=/[^/]+/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         'url': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         playlist_id = self._match_id(url)
  50         webpage = self._download_webpage(url, playlist_id)
  51
  52         feed_json = self._search_regex(r'var triforceManifestFeed\s*=\s*(\{.+?\});\n', webpage, 'triforce feeed')
  53         feed = self._parse_json(feed_json, playlist_id)
  54         zones = feed['manifest']['zones']
  55
  56         video_zone = zones['t2_lc_promo1']
  57         feed = self._download_json(video_zone['feed'], playlist_id)
  58         mgid = feed['result']['data']['id']
  59
  60         videos_info = self._get_videos_info(mgid)
  61         return videos_info
  62
  63
  64 class ToshIE(MTVServicesInfoExtractor):
  65     IE_DESC = 'Tosh.0'
  66     _VALID_URL = r'^https?://tosh\.cc\.com/video-(?:clips|collections)/[^/]+/(?P<videotitle>[^/?#]+)'
  67     _FEED_URL = 'http://tosh.cc.com/feeds/mrss'
  68
  69     _TESTS = [{
  70         'url': 'http://tosh.cc.com/video-clips/68g93d/twitter-users-share-summer-plans',
  71         'info_dict': {
  72             'description': 'Tosh asked fans to share their summer plans.',
  73             'title': 'Twitter Users Share Summer Plans',
  74         },
  75         'playlist': [{
  76             'md5': 'f269e88114c1805bb6d7653fecea9e06',
  77             'info_dict': {
  78                 'id': '90498ec2-ed00-11e0-aca6-0026b9414f30',
  79                 'ext': 'mp4',
  80                 'title': 'Tosh.0|June 9, 2077|2|211|Twitter Users Share Summer Plans',
  81                 'description': 'Tosh asked fans to share their summer plans.',
  82                 'thumbnail': 're:^https?://.*\.jpg',
  83                 # It's really reported to be published on year 2077
  84                 'upload_date': '20770610',
  85                 'timestamp': 3390510600,
  86                 'subtitles': {
  87                     'en': 'mincount:3',
  88                 },
  89             },
  90         }]
  91     }, {
  92         'url': 'http://tosh.cc.com/video-collections/x2iz7k/just-plain-foul/m5q4fp',
  93         'only_matching': True,
  94     }]
  95
  96     @classmethod
  97     def _transform_rtmp_url(cls, rtmp_video_url):
  98         new_urls = super(ToshIE, cls)._transform_rtmp_url(rtmp_video_url)
  99         new_urls['rtmp'] = rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm')
 100         return new_urls
 101
 102
 103 class ComedyCentralTVIE(MTVServicesInfoExtractor):
 104     _VALID_URL = r'https?://(?:www\.)?comedycentral\.tv/(?:staffeln|shows)/(?P<id>[^/?#&]+)'
 105     _TESTS = [{
 106         'url': 'http://www.comedycentral.tv/staffeln/7436-the-mindy-project-staffel-4',
 107         'info_dict': {
 108             'id': 'local_playlist-f99b626bdfe13568579a',
 109             'ext': 'flv',
 110             'title': 'Episode_the-mindy-project_shows_season-4_episode-3_full-episode_part1',
 111         },
 112         'params': {
 113             # rtmp download
 114             'skip_download': True,
 115         },
 116     }, {
 117         'url': 'http://www.comedycentral.tv/shows/1074-workaholics',
 118         'only_matching': True,
 119     }, {
 120         'url': 'http://www.comedycentral.tv/shows/1727-the-mindy-project/bonus',
 121         'only_matching': True,
 122     }]
 123
 124     def _real_extract(self, url):
 125         video_id = self._match_id(url)
 126
 127         webpage = self._download_webpage(url, video_id)
 128
 129         mrss_url = self._search_regex(
 130             r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
 131             webpage, 'mrss url', group='url')
 132
 133         return self._get_videos_info_from_url(mrss_url, video_id)
 134
 135
 136 class ComedyCentralShortnameIE(InfoExtractor):
 137     _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
 138     _TESTS = [{
 139         'url': ':tds',
 140         'only_matching': True,
 141     }, {
 142         'url': ':thedailyshow',
 143         'only_matching': True,
 144     }]
 145
 146     def _real_extract(self, url):
 147         video_id = self._match_id(url)
 148         shortcut_map = {
 149             'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 150             'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
 151         }
 152         return self.url_result(shortcut_map[video_id])