github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[bbc] Support multiple videos in articles embedded with playlist.sxml

Browse source
This commit is contained in:
Sergey M․ 2015-10-10 20:40:56 +06:00
parent dab062fb6e
commit de66571371
1 changed files with 21 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/bbc.py
View file

@ -660,23 +660,27 @@ def _real_extract(self, url):
r'itemprop="datePublished"[^>]+datetime="([^"]+)"'],
webpage, 'date', default=None))
# single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng)
playlist = self._search_regex(
r'<param[^>]+name="playlist"[^>]+value="([^"]+)"',
webpage, 'playlist', default=None)
if playlist:
programme_id, title, description, duration, formats, subtitles = \
self._process_legacy_playlist_url(playlist, playlist_id)
self._sort_formats(formats)
return {
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
'subtitles': subtitles,
}
# article with multiple videos embedded with playlist.sxml (e.g.
# http://www.bbc.com/sport/0/football/34475836)
playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
if playlists:
entries = []
for playlist in playlists:
programme_id, title, description, duration, formats, subtitles = \
self._process_legacy_playlist_url(playlist, playlist_id)
self._sort_formats(formats)
entries.append({
'id': programme_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
'subtitles': subtitles,
})
playlist_title = self._og_search_title(webpage)
playlist_description = self._og_search_description(webpage)
return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
# single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
programme_id = self._search_regex(