diff options
| author | Philipp Hagemeister <phihag@phihag.de> | 2013-01-06 21:36:01 +0100 |
|---|---|---|
| committer | Philipp Hagemeister <phihag@phihag.de> | 2013-01-06 21:36:01 +0100 |
| commit | 9314810243692e02188b3ec4e1ae8a0c48e66e70 (patch) | |
| tree | 4ef6c6fc6f4087e24d42f68c506c4156f049ba4d | |
| parent | 7717ae19fabf010550cdd16801c41064db93c18f (diff) | |
| download | youtube-dl-9314810243692e02188b3ec4e1ae8a0c48e66e70.tar.gz youtube-dl-9314810243692e02188b3ec4e1ae8a0c48e66e70.tar.xz youtube-dl-9314810243692e02188b3ec4e1ae8a0c48e66e70.zip | |
fix ComedyCentral IE in Python3
| -rwxr-xr-x | youtube_dl/InfoExtractors.py | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index a65ebe179..136e4183e 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -2404,6 +2404,7 @@ class ComedyCentralIE(InfoExtractor): try: htmlHandle = compat_urllib_request.urlopen(req) html = htmlHandle.read() + webpage = html.decode('utf-8') 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)) return @@ -2418,14 +2419,14 @@ class ComedyCentralIE(InfoExtractor): return 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: # 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).*?:.*?)"', html) + altMovieParams = re.findall('data-mgid="([^"]*(?:episode|video).*?:.*?)"', webpage) if len(altMovieParams) == 0: self._downloader.trouble(u'ERROR: unable to find Flash URL in webpage ' + url) return |