youtube_dl/extractor/comedycentral.py

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