Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/comedycentral.py

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