fix ComedyCentral IE in Python3

This commit is contained in:
Philipp Hagemeister 2013-01-06 21:36:01 +01:00
parent 7717ae19fa
commit 9314810243

View File

@ -2404,6 +2404,7 @@ class ComedyCentralIE(InfoExtractor):
try: try:
htmlHandle = compat_urllib_request.urlopen(req) htmlHandle = compat_urllib_request.urlopen(req)
html = htmlHandle.read() html = htmlHandle.read()
webpage = html.decode('utf-8')
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err)) self._downloader.trouble(u'ERROR: unable to download webpage: %s' % compat_str(err))
return return
@ -2418,14 +2419,14 @@ class ComedyCentralIE(InfoExtractor):
return return
epTitle = mobj.group('episode') epTitle = mobj.group('episode')
mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', html) mMovieParams = re.findall('(?:<param name="movie" value="|var url = ")(http://media.mtvnservices.com/([^"]*(?:episode|video).*?:.*?))"', webpage)
if len(mMovieParams) == 0: if len(mMovieParams) == 0:
# The Colbert Report embeds the information in a without # The Colbert Report embeds the information in a without
# a URL prefix; so extract the alternate reference # a URL prefix; so extract the alternate reference
# and then add the URL prefix manually. # and then add the URL prefix manually.
altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', html) altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage)
if len(altMovieParams) == 0: 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