From fc2ef392bee9e46564d4106d3b0e5f6b8d71e37b Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 15 Nov 2013 14:33:51 +0100 Subject: [ted] Fix playlists (Fixes #1770) --- youtube_dl/extractor/ted.py | 29 ++++++++++++++--------------- 1 file changed, 14 insertions(+), 15 deletions(-) (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 8001ca5a3..2e497c86e 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -43,26 +43,25 @@ class TEDIE(SubtitlesInfoExtractor): self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) return [self._playlist_videos_info(url,name,playlist_id)] - def _playlist_videos_info(self,url,name,playlist_id=0): + + def _playlist_videos_info(self, url, name, playlist_id): '''Returns the videos of the playlist''' - video_RE=r''' - (?P.+?)

' - webpage=self._download_webpage(url, playlist_id, 'Downloading playlist webpage') - m_videos=re.finditer(video_RE,webpage,re.VERBOSE) - m_names=re.finditer(video_name_RE,webpage) + + webpage = self._download_webpage( + url, playlist_id, u'Downloading playlist webpage') + matches = re.finditer( + r'/talks/[^"]+\.html)">[^<]*

', + webpage) playlist_title = self._html_search_regex(r'div class="headline">\s*?

\s*?(.*?)', webpage, 'playlist title') - playlist_entries = [] - for m_video, m_name in zip(m_videos,m_names): - talk_url='http://www.ted.com%s' % m_name.group('talk_url') - playlist_entries.append(self.url_result(talk_url, 'TED')) - return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title) + playlist_entries = [ + self.url_result(u'http://www.ted.com' + m.group('talk_url'), 'TED') + for m in matches + ] + return self.playlist_result( + playlist_entries, playlist_id=playlist_id, playlist_title=playlist_title) def _talk_info(self, url, video_id=0): """Return the video for the talk in the url""" -- cgit v1.2.3