- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- if mobj.group('shortname'):
- if mobj.group('shortname') in ('tds', 'thedailyshow'):
- url = u'http://www.thedailyshow.com/full-episodes/'
- else:
- url = u'http://www.colbertnation.com/full-episodes/'
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- assert mobj is not None
-
- if mobj.group('clip'):
- if mobj.group('showname') == 'thedailyshow':
- epTitle = mobj.group('tdstitle')
- else:
- epTitle = mobj.group('cntitle')
- dlNewest = False
- elif mobj.group('interview'):
- epTitle = mobj.group('interview_title')
- dlNewest = False
- else:
- dlNewest = not mobj.group('episode')
- if dlNewest:
- epTitle = mobj.group('showname')
- else:
- epTitle = mobj.group('episode')
-
- self.report_extraction(epTitle)
- webpage,htmlHandle = self._download_webpage_handle(url, epTitle)
- if dlNewest:
- url = htmlHandle.geturl()
- mobj = re.match(self._VALID_URL, url, re.VERBOSE)
- if mobj is None:
- raise ExtractorError(u'Invalid redirected URL: ' + url)
- if mobj.group('episode') == '':
- raise ExtractorError(u'Redirected URL is still not specific: ' + url)
- epTitle = mobj.group('episode')
-
- mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
-
- if len(mMovieParams) == 0:
- # The Colbert Report embeds the information in a without
- # a URL prefix; so extract the alternate reference
- # and then add the URL prefix manually.
-
- altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
- if len(altMovieParams) == 0:
- raise ExtractorError(u'unable to find Flash URL in webpage ' + url)
- else:
- mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
-
- uri = mMovieParams[0][1]
- indexUrl = 'http://shadow.comedycentral.com/feeds/video_player/mrss/?' + compat_urllib_parse.urlencode({'uri': uri})
- indexXml = self._download_webpage(indexUrl, epTitle,
- u'Downloading show index',
- u'unable to download episode index')
-
- results = []
-
- idoc = xml.etree.ElementTree.fromstring(indexXml)
- itemEls = idoc.findall('.//item')
- for partNum,itemEl in enumerate(itemEls):
- mediaId = itemEl.findall('./guid')[0].text
- shortMediaId = mediaId.split(':')[-1]
- showId = mediaId.split(':')[-2].replace('.com', '')
- officialTitle = itemEl.findall('./title')[0].text
- officialDate = unified_strdate(itemEl.findall('./pubDate')[0].text)
-
- configUrl = ('http://www.comedycentral.com/global/feeds/entertainment/media/mediaGenEntertainment.jhtml?' +
- compat_urllib_parse.urlencode({'uri': mediaId}))
- configXml = self._download_webpage(configUrl, epTitle,
- u'Downloading configuration for %s' % shortMediaId)
-
- cdoc = xml.etree.ElementTree.fromstring(configXml)
- turls = []
- for rendition in cdoc.findall('.//rendition'):
- finfo = (rendition.attrib['bitrate'], rendition.findall('./src')[0].text)
- turls.append(finfo)
-
- if len(turls) == 0:
- self._downloader.report_error(u'unable to download ' + mediaId + ': No videos found')
- continue
-
- formats = []
- for format, rtmp_video_url in turls:
- w, h = self._video_dimensions.get(format, (None, None))
- formats.append({
- 'url': self._transform_rtmp_url(rtmp_video_url),
- 'ext': self._video_extensions.get(format, 'mp4'),
- 'format_id': format,
- 'height': h,
- 'width': w,
- })
-
- effTitle = showId + u'-' + epTitle + u' part ' + compat_str(partNum+1)
- info = {
- 'id': shortMediaId,
- 'formats': formats,
- 'uploader': showId,
- 'upload_date': officialDate,
- 'title': effTitle,
- 'thumbnail': None,
- 'description': compat_str(officialTitle),
- }
-
- # TODO: Remove when #980 has been merged
- info.update(info['formats'][-1])
-
- results.append(info)
-
- return results
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ mrss_url = self._search_regex(
+ r'data-mrss=(["\'])(?P<url>(?:(?!\1).)+)\1',
+ webpage, 'mrss url', group='url')
+
+ return self._get_videos_info_from_url(mrss_url, video_id)
+
+
+class ComedyCentralShortnameIE(InfoExtractor):
+ _VALID_URL = r'^:(?P<id>tds|thedailyshow)$'
+ _TESTS = [{
+ 'url': ':tds',
+ 'only_matching': True,
+ }, {
+ 'url': ':thedailyshow',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ shortcut_map = {
+ 'tds': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+ 'thedailyshow': 'http://www.cc.com/shows/the-daily-show-with-trevor-noah/full-episodes',
+ }
+ return self.url_result(shortcut_map[video_id])
Rapsys Git / youtubedl / blobdiff