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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from .mtv import MTVServicesInfoExtractor
   7 from ..compat import (
   8     compat_str,
   9     compat_urllib_parse,
  10 )
  11 from ..utils import (
  12     ExtractorError,
  13     float_or_none,
  14     unified_strdate,
  15 )
  16
  17
  18 class ComedyCentralIE(MTVServicesInfoExtractor):
  19     _VALID_URL = r'''(?x)https?://(?:www\.)?cc\.com/
  20         (video-clips|episodes|cc-studios|video-collections|full-episodes)
  21         /(?P<title>.*)'''
  22     _FEED_URL = 'http://comedycentral.com/feeds/mrss/'
  23
  24     _TEST = {
  25         'url': 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother',
  26         'md5': 'c4f48e9eda1b16dd10add0744344b6d8',
  27         'info_dict': {
  28             'id': 'cef0cbb3-e776-4bc9-b62e-8016deccb354',
  29             'ext': 'mp4',
  30             'title': 'CC:Stand-Up|Greg Fitzsimmons: Life on Stage|Uncensored - Too Good of a Mother',
  31             'description': 'After a certain point, breastfeeding becomes c**kblocking.',
  32         },
  33     }
  34
  35
  36 class ComedyCentralShowsIE(MTVServicesInfoExtractor):
  37     IE_DESC = 'The Daily Show / The Colbert Report'
  38     # urls can be abbreviations like :thedailyshow
  39     # urls for episodes like:
  40     # or urls for clips like: http://www.thedailyshow.com/watch/mon-december-10-2012/any-given-gun-day
  41     #                     or: http://www.colbertnation.com/the-colbert-report-videos/421667/november-29-2012/moon-shattering-news
  42     #                     or: http://www.colbertnation.com/the-colbert-report-collections/422008/festival-of-lights/79524
  43     _VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow)
  44                       |https?://(:www\.)?
  45                           (?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
  46                          ((?:full-)?episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
  47                           (?P<clip>
  48                               (?:(?:guests/[^/]+|videos|video-playlists|special-editions|news-team/[^/]+)/[^/]+/(?P<videotitle>[^/?#]+))
  49                               |(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
  50                               |(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
  51                           )|
  52                           (?P<interview>
  53                               extended-interviews/(?P<interID>[0-9a-z]+)/
  54                               (?:playlist_tds_extended_)?(?P<interview_title>[^/?#]*?)
  55                               (?:/[^/?#]?|[?#]|$))))
  56                      '''
  57     _TESTS = [{
  58         'url': 'http://thedailyshow.cc.com/watch/thu-december-13-2012/kristen-stewart',
  59         'md5': '4e2f5cb088a83cd8cdb7756132f9739d',
  60         'info_dict': {
  61             'id': 'ab9ab3e7-5a98-4dbe-8b21-551dc0523d55',
  62             'ext': 'mp4',
  63             'upload_date': '20121213',
  64             'description': 'Kristen Stewart learns to let loose in "On the Road."',
  65             'uploader': 'thedailyshow',
  66             'title': 'thedailyshow kristen-stewart part 1',
  67         }
  68     }, {
  69         'url': 'http://thedailyshow.cc.com/extended-interviews/b6364d/sarah-chayes-extended-interview',
  70         'info_dict': {
  71             'id': 'sarah-chayes-extended-interview',
  72             'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
  73             'title': 'thedailyshow Sarah Chayes Extended Interview',
  74         },
  75         'playlist': [
  76             {
  77                 'info_dict': {
  78                     'id': '0baad492-cbec-4ec1-9e50-ad91c291127f',
  79                     'ext': 'mp4',
  80                     'upload_date': '20150129',
  81                     'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
  82                     'uploader': 'thedailyshow',
  83                     'title': 'thedailyshow sarah-chayes-extended-interview part 1',
  84                 },
  85             },
  86             {
  87                 'info_dict': {
  88                     'id': '1e4fb91b-8ce7-4277-bd7c-98c9f1bbd283',
  89                     'ext': 'mp4',
  90                     'upload_date': '20150129',
  91                     'description': 'Carnegie Endowment Senior Associate Sarah Chayes discusses how corrupt institutions function throughout the world in her book "Thieves of State: Why Corruption Threatens Global Security."',
  92                     'uploader': 'thedailyshow',
  93                     'title': 'thedailyshow sarah-chayes-extended-interview part 2',
  94                 },
  95             },
  96         ],
  97         'params': {
  98             'skip_download': True,
  99         },
 100     }, {
 101         'url': 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
 102         'only_matching': True,
 103     }, {
 104         'url': 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
 105         'only_matching': True,
 106     }, {
 107         'url': 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
 108         'only_matching': True,
 109     }, {
 110         'url': 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
 111         'only_matching': True,
 112     }, {
 113         'url': 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
 114         'only_matching': True,
 115     }, {
 116         'url': 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
 117         'only_matching': True,
 118     }, {
 119         'url': 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
 120         'only_matching': True,
 121     }, {
 122         'url': 'http://thedailyshow.cc.com/video-playlists/t6d9sg/the-daily-show-20038-highlights/be3cwo',
 123         'only_matching': True,
 124     }, {
 125         'url': 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
 126         'only_matching': True,
 127     }, {
 128         'url': 'http://thedailyshow.cc.com/news-team/michael-che/7wnfel/we-need-to-talk-about-israel',
 129         'only_matching': True,
 130     }]
 131
 132     _available_formats = ['3500', '2200', '1700', '1200', '750', '400']
 133
 134     _video_extensions = {
 135         '3500': 'mp4',
 136         '2200': 'mp4',
 137         '1700': 'mp4',
 138         '1200': 'mp4',
 139         '750': 'mp4',
 140         '400': 'mp4',
 141     }
 142     _video_dimensions = {
 143         '3500': (1280, 720),
 144         '2200': (960, 540),
 145         '1700': (768, 432),
 146         '1200': (640, 360),
 147         '750': (512, 288),
 148         '400': (384, 216),
 149     }
 150
 151     def _real_extract(self, url):
 152         mobj = re.match(self._VALID_URL, url)
 153
 154         if mobj.group('shortname'):
 155             if mobj.group('shortname') in ('tds', 'thedailyshow'):
 156                 url = 'http://thedailyshow.cc.com/full-episodes/'
 157             else:
 158                 url = 'http://thecolbertreport.cc.com/full-episodes/'
 159             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
 160             assert mobj is not None
 161
 162         if mobj.group('clip'):
 163             if mobj.group('videotitle'):
 164                 epTitle = mobj.group('videotitle')
 165             elif mobj.group('showname') == 'thedailyshow':
 166                 epTitle = mobj.group('tdstitle')
 167             else:
 168                 epTitle = mobj.group('cntitle')
 169             dlNewest = False
 170         elif mobj.group('interview'):
 171             epTitle = mobj.group('interview_title')
 172             dlNewest = False
 173         else:
 174             dlNewest = not mobj.group('episode')
 175             if dlNewest:
 176                 epTitle = mobj.group('showname')
 177             else:
 178                 epTitle = mobj.group('episode')
 179         show_name = mobj.group('showname')
 180
 181         webpage, htmlHandle = self._download_webpage_handle(url, epTitle)
 182         if dlNewest:
 183             url = htmlHandle.geturl()
 184             mobj = re.match(self._VALID_URL, url, re.VERBOSE)
 185             if mobj is None:
 186                 raise ExtractorError('Invalid redirected URL: ' + url)
 187             if mobj.group('episode') == '':
 188                 raise ExtractorError('Redirected URL is still not specific: ' + url)
 189             epTitle = (mobj.group('episode') or mobj.group('videotitle')).rpartition('/')[-1]
 190
 191         mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
 192         if len(mMovieParams) == 0:
 193             # The Colbert Report embeds the information in a without
 194             # a URL prefix; so extract the alternate reference
 195             # and then add the URL prefix manually.
 196
 197             altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video|playlist).*?:.*?)"', webpage)
 198             if len(altMovieParams) == 0:
 199                 raise ExtractorError('unable to find Flash URL in webpage ' + url)
 200             else:
 201                 mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
 202
 203         uri = mMovieParams[0][1]
 204         # Correct cc.com in uri
 205         uri = re.sub(r'(episode:[^.]+)(\.cc)?\.com', r'\1.cc.com', uri)
 206
 207         index_url = 'http://%s.cc.com/feeds/mrss?%s' % (show_name, compat_urllib_parse.urlencode({'uri': uri}))
 208         idoc = self._download_xml(
 209             index_url, epTitle,
 210             'Downloading show index', 'Unable to download episode index')
 211
 212         title = idoc.find('./channel/title').text
 213         description = idoc.find('./channel/description').text
 214
 215         entries = []
 216         item_els = idoc.findall('.//item')
 217         for part_num, itemEl in enumerate(item_els):
 218             upload_date = unified_strdate(itemEl.findall('./pubDate')[0].text)
 219             thumbnail = itemEl.find('.//{http://search.yahoo.com/mrss/}thumbnail').attrib.get('url')
 220
 221             content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
 222             duration = float_or_none(content.attrib.get('duration'))
 223             mediagen_url = content.attrib['url']
 224             guid = itemEl.find('./guid').text.rpartition(':')[-1]
 225
 226             cdoc = self._download_xml(
 227                 mediagen_url, epTitle,
 228                 'Downloading configuration for segment %d / %d' % (part_num + 1, len(item_els)))
 229
 230             turls = []
 231             for rendition in cdoc.findall('.//rendition'):
 232                 finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
 233                 turls.append(finfo)
 234
 235             formats = []
 236             for format, rtmp_video_url in turls:
 237                 w, h = self._video_dimensions.get(format, (None, None))
 238                 formats.append({
 239                     'format_id': 'vhttp-%s' % format,
 240                     'url': self._transform_rtmp_url(rtmp_video_url),
 241                     'ext': self._video_extensions.get(format, 'mp4'),
 242                     'height': h,
 243                     'width': w,
 244                 })
 245                 formats.append({
 246                     'format_id': 'rtmp-%s' % format,
 247                     'url': rtmp_video_url.replace('viacomccstrm', 'viacommtvstrm'),
 248                     'ext': self._video_extensions.get(format, 'mp4'),
 249                     'height': h,
 250                     'width': w,
 251                 })
 252                 self._sort_formats(formats)
 253
 254             subtitles = self._extract_subtitles(cdoc, guid)
 255
 256             virtual_id = show_name + ' ' + epTitle + ' part ' + compat_str(part_num + 1)
 257             entries.append({
 258                 'id': guid,
 259                 'title': virtual_id,
 260                 'formats': formats,
 261                 'uploader': show_name,
 262                 'upload_date': upload_date,
 263                 'duration': duration,
 264                 'thumbnail': thumbnail,
 265                 'description': description,
 266                 'subtitles': subtitles,
 267             })
 268
 269         return {
 270             '_type': 'playlist',
 271             'id': epTitle,
 272             'entries': entries,
 273             'title': show_name + ' ' + title,
 274             'description': description,
 275         }
 276
 277 class TheDailyShowPodcastIE(InfoExtractor):
 278     _VALID_URL = r'(?P<scheme>https?:)?//thedailyshow\.cc\.com/podcast/(?P<id>[a-z\-]+)'
 279
 280     def _real_extract(self, url):
 281         display_id = self._match_id(url)
 282         webpage = self._download_webpage(url, display_id)
 283
 284         player_url = self._search_regex(r'<iframe(?:\s+[^>]+)?\s*src="((?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/[0-9]+)', webpage, 'player URL')
 285         if player_url.startswith('//'):
 286             mobj = re.match(self._VALID_URL, url)
 287             scheme = mobj.group('scheme')
 288             if not scheme:
 289                 scheme = 'https:'
 290             player_url = scheme + player_url
 291
 292         return {
 293             '_type': 'url_transparent',
 294             'url': player_url,
 295         }