Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 19:52:40 +01:00
Code Issues Releases Activity

[ted] Fix playlists (Fixes #1770)

Browse Source
This commit is contained in:
Philipp Hagemeister 2013-11-15 14:33:51 +01:00
parent 463a908705
commit fc2ef392be
1 changed files with 14 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/ted.py
View File

@ -43,26 +43,25 @@ def _real_extract(self, url):
self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name)) self.to_screen(u'Getting info of playlist %s: "%s"' % (playlist_id,name))
return [self._playlist_videos_info(url,name,playlist_id)] 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''' '''Returns the videos of the playlist'''
video_RE=r'''
<li\ id="talk_(\d+)"([.\s]*?)data-id="(?P<video_id>\d+)" webpage = self._download_webpage(
([.\s]*?)data-playlist_item_id="(\d+)" url, playlist_id, u'Downloading playlist webpage')
([.\s]*?)data-mediaslug="(?P<mediaSlug>.+?)" matches = re.finditer(
''' r'<p\s+class="talk-title[^"]*"><a\s+href="(?P<talk_url>/talks/[^"]+\.html)">[^<]*</a></p>',
video_name_RE=r'<p\ class="talk-title"><a href="(?P<talk_url>/talks/(.+).html)">(?P<fullname>.+?)</a></p>' webpage)
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)
playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>', playlist_title = self._html_search_regex(r'div class="headline">\s*?<h1>\s*?<span>(.*?)</span>',
webpage, 'playlist title') webpage, 'playlist title')
playlist_entries = [] playlist_entries = [
for m_video, m_name in zip(m_videos,m_names): self.url_result(u'http://www.ted.com' + m.group('talk_url'), 'TED')
talk_url='http://www.ted.com%s' % m_name.group('talk_url') for m in matches
playlist_entries.append(self.url_result(talk_url, 'TED')) ]
return self.playlist_result(playlist_entries, playlist_id = playlist_id, playlist_title = playlist_title) return self.playlist_result(
playlist_entries, playlist_id=playlist_id, playlist_title=playlist_title)
def _talk_info(self, url, video_id=0): def _talk_info(self, url, video_id=0):
"""Return the video for the talk in the url""" """Return the video for the talk in the url"""