R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

DiscoveryIE: make playlist extraction tolerate entries with blank 'src' values

Browse Source 
There are alot here. I assume the videos are disabled.
http://www.discovery.com/tv-shows/other-shows/videos/other-shows-when-we-left-earth-videos/

There is an 'embedurl' for all of the videos, however there is no support for the
urls in question. (todo)
This commit is contained in:
fnord 2015-07-13 07:52:03 -05:00
parent 41c0d2f8cb
commit d9dd8b5664
1 changed files with 22 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
youtube_dl/extractor/discovery.py
View File

@ -41,19 +41,27 @@ class DiscoveryIE(InfoExtractor):
info = self._download_json(url + '?flat=1', video_id) info = self._download_json(url + '?flat=1', video_id)
video_title = info.get('playlist_title') or info.get('video_title') video_title = info.get('playlist_title') or info.get('video_title')
entries = []
entries = [{ collected = {}
'id': compat_str(video_info['id']), for idx, video_info in enumerate(info['playlist']):
'formats': self._extract_m3u8_formats( if collected.get( video_info.get('id') ):
video_info['src'], video_id, ext='mp4', continue
note='Download m3u8 information for video %d' % (idx + 1)), collected[video_info.get('id')] = True
'title': video_info['title'], if video_info['src'] == '':
'description': video_info.get('description'), self.report_warning('video "%s" does not have a src url' % video_info.get('id','UNKNOWN'))
'duration': parse_duration(video_info.get('video_length')), continue
'webpage_url': video_info.get('href'), entries.append({
'thumbnail': video_info.get('thumbnailURL'), 'id': compat_str(video_info['id']),
'alt_title': video_info.get('secondary_title'), 'formats': self._extract_m3u8_formats(
'timestamp': parse_iso8601(video_info.get('publishedDate')), video_info['src'], video_id, ext='mp4',
} for idx, video_info in enumerate(info['playlist'])] note='Download m3u8 information for video %d' % (idx + 1)),
'title': video_info['title'],
'description': video_info.get('description'),
'duration': parse_duration(video_info.get('video_length')),
'webpage_url': video_info.get('href'),
'thumbnail': video_info.get('thumbnailURL'),
'alt_title': video_info.get('secondary_title'),
'timestamp': parse_iso8601(video_info.get('publishedDate')),
})
return self.playlist_result(entries, video_id, video_title) return self.playlist_result(entries, video_id, video_title)