X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fchannel9.py;h=1ce004932bb9de3225c0a964149acb994aeabc1e;hb=506e261d2073d8c00d5b43d272e8173cb0d63728;hp=82a48870acbdf7223250b977e982b6961030ffb3;hpb=5f6a1245ffa9276c1af59b0835afeef67e2fb5b1;p=youtube-dl diff --git a/youtube_dl/extractor/channel9.py b/youtube_dl/extractor/channel9.py index 82a48870a..1ce004932 100644 --- a/youtube_dl/extractor/channel9.py +++ b/youtube_dl/extractor/channel9.py @@ -158,7 +158,7 @@ class Channel9IE(InfoExtractor): def _extract_session_day(self, html): m = re.search(r'
  • \s*(?P[^<]+)\s*
  • ', html) - return m.group('day') if m is not None else None + return m.group('day').strip() if m is not None else None def _extract_session_room(self, html): m = re.search(r'
  • \s*(?P.+?)\s*
  • ', html) @@ -188,16 +188,17 @@ class Channel9IE(InfoExtractor): view_count = self._extract_view_count(html) comment_count = self._extract_comment_count(html) - common = {'_type': 'video', - 'id': content_path, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'avg_rating': avg_rating, - 'rating_count': rating_count, - 'view_count': view_count, - 'comment_count': comment_count, - } + common = { + '_type': 'video', + 'id': content_path, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'avg_rating': avg_rating, + 'rating_count': rating_count, + 'view_count': view_count, + 'comment_count': comment_count, + } result = [] @@ -223,28 +224,29 @@ class Channel9IE(InfoExtractor): if contents is None: return contents - authors = self._extract_authors(html) - - for content in contents: - content['authors'] = authors + if len(contents) > 1: + raise ExtractorError('Got more than one entry') + result = contents[0] + result['authors'] = self._extract_authors(html) - return contents + return result def _extract_session(self, html, content_path): contents = self._extract_content(html, content_path) if contents is None: return contents - session_meta = {'session_code': self._extract_session_code(html), - 'session_day': self._extract_session_day(html), - 'session_room': self._extract_session_room(html), - 'session_speakers': self._extract_session_speakers(html), - } + session_meta = { + 'session_code': self._extract_session_code(html), + 'session_day': self._extract_session_day(html), + 'session_room': self._extract_session_room(html), + 'session_speakers': self._extract_session_speakers(html), + } for content in contents: content.update(session_meta) - return contents + return self.playlist_result(contents) def _extract_list(self, content_path): rss = self._download_xml(self._RSS_URL % content_path, content_path, 'Downloading RSS')