From d830b7c297b947348ae6f16f978a076d62ce93c1 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Tue, 1 Jan 2013 20:43:43 +0100 Subject: [PATCH] _download_webpage helper function --- youtube_dl/InfoExtractors.py | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index 0c101e704..f141e5bc6 100755 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -105,6 +105,20 @@ def _real_extract(self, url): def IE_NAME(self): return type(self).__name__[:-2] + def _download_webpage(self, url, video_id, note=None, errnote=None): + if note is None: + note = u'Downloading video webpage' + self._downloader.to_screen(u'[%s] %s: %s' % (self.IE_NAME, video_id, note)) + try: + urlh = compat_urllib_request.urlopen(url) + webpage_bytes = urlh.read() + return webpage_bytes.decode('utf-8', 'replace') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + if errnote is None: + errnote = u'Unable to download webpage' + raise ExtractorError(u'%s: %s' % (errnote, compat_str(err))) + + class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" @@ -3803,12 +3817,7 @@ def _real_extract(self, url): m = re.match(self._VALID_URL, url) video_id = m.group('videoID') video_url = u'http://tcdn.ustream.tv/video/%s' % video_id - try: - urlh = compat_urllib_request.urlopen(url) - webpage_bytes = urlh.read() - webpage = webpage_bytes.decode('utf-8', 'ignore') - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'unable to download webpage: %s' % compat_str(err)) + webpage = self._download_webpage(url, video_id) m = re.search(r'data-title="(?P.+)"',webpage) title = m.group('title') m = re.search(r'<a class="state" data-content-type="channel" data-content-id="(?P<uploader>\d+)"',webpage)