mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-02 11:26:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

[duboku] fix list results, minor error checking

Browse source
This commit is contained in:
lkho 2020-08-30 15:53:07 +08:00
parent 7cc9d5b321
commit bf7392922f
1 changed files with 7 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
youtube_dl/extractor/duboku.py
View file

@ -101,7 +101,7 @@ def _real_extract(self, url):
player_data = self._search_regex( player_data = self._search_regex(
self._PLAYER_DATA_PATTERN, webpage_html, 'player_data') self._PLAYER_DATA_PATTERN, webpage_html, 'player_data')
player_data = self._parse_json(js_to_json(player_data), video_id) player_data = self._parse_json(player_data, video_id, js_to_json)
# extract title # extract title
@ -121,8 +121,9 @@ def _real_extract(self, url):
title = re.sub(r'[\s\r\n\t]+', ' ', title) title = re.sub(r'[\s\r\n\t]+', ' ', title)
break break
data_url = player_data['url'] data_url = player_data.get('url')
assert data_url if not data_url:
raise ExtractorError('Cannot find url in player_data')
data_from = player_data.get('from') data_from = player_data.get('from')
# if it is an embedded iframe, maybe it's an external source # if it is an embedded iframe, maybe it's an external source
@ -225,7 +226,7 @@ def _real_extract(self, url):
playlist = playlists.get(fragment) playlist = playlists.get(fragment)
playlist_id = fragment playlist_id = fragment
else: else:
first = next(iter(playlists.items())) first = next(iter(playlists.items()), None)
if first: if first:
(playlist_id, playlist) = first (playlist_id, playlist) = first
if not playlist: if not playlist:
@ -235,5 +236,6 @@ def _real_extract(self, url):
# return url results # return url results
return self.playlist_result([ return self.playlist_result([
self.url_result( self.url_result(
'https://www.duboku.co' + x['href'], DubokuIE.IE_NAME, video_title=x.get('title')) compat_urlparse.urljoin('https://www.duboku.co', x['href']),
ie=DubokuIE.ie_key(), video_title=x.get('title'))
for x in playlist], series_id + '#' + playlist_id, title) for x in playlist], series_id + '#' + playlist_id, title)