Fixes the InfoExtractor for the Colbert Report.

This commit is contained in:
Christopher Neugebauer 2012-11-27 23:54:43 +11:00
parent feb22fe5fe
commit 4a702f3819

View File

@ -2332,9 +2332,18 @@ def _real_extract(self, url):
epTitle = mobj.group('episode') epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html) mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*episode.*?:.*?))"', html)
if len(mMovieParams) == 0: 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.*?:.*?)"', html)
if len(altMovieParams) == 0:
self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url)
return return
else:
mMovieParams = [("http://media.mtvnservices.com/" + altMovieParams[0], altMovieParams[0])]
playerUrl_raw = mMovieParams[0][0] playerUrl_raw = mMovieParams[0][0]
self.report_player_url(epTitle) self.report_player_url(epTitle)