_VALID_URL = r'''(?x)^(:(?P<shortname>tds|thedailyshow|cr|colbert|colbertnation|colbertreport)
|https?://(:www\.)?
(?P<showname>thedailyshow|thecolbertreport)\.(?:cc\.)?com/
- (full-episodes/(?P<episode>.*)|
+ (full-episodes/(?:[0-9a-z]{6}/)?(?P<episode>.*)|
(?P<clip>
- (?:videos/[^/]+/(?P<videotitle>[^/?#]+))
+ (?:(?:guests/[^/]+|videos)/[^/]+/(?P<videotitle>[^/?#]+))
|(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*))
)|
content = itemEl.find('.//{http://search.yahoo.com/mrss/}content')
duration = float_or_none(content.attrib.get('duration'))
mediagen_url = content.attrib['url']
- guid = itemEl.find('.//guid').text.rpartition(':')[-1]
+ guid = itemEl.find('./guid').text.rpartition(':')[-1]
cdoc = self._download_xml(
mediagen_url, epTitle,