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

Update youtube.py

Browse Source 
(#25848 #25720 #16627 #25652)
This commit is contained in:
Crypto90 2020-07-01 03:01:32 +02:00 committed by GitHub
parent 07af16b92e
commit 9dce8410d2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
youtube_dl/extractor/youtube.py
View File

@ -326,35 +326,48 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content):
for video_id, video_title in self.extract_videos_from_page(content):
yield self.url_result(video_id, 'Youtube', video_id, video_title)
for video_id, video_title, video_duration in self.extract_videos_from_page(content):
if len(video_id) == 11:
# Youtube video id found
yield self.url_result(video_id, 'Youtube', video_id, video_title)
elif len(video_id) > 11:
# Youtube playlist id found
yield self.url_result('https://www.youtube.com/playlist?list=%s' % video_id, 'YoutubePlaylist', video_id, video_title)
def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page):
def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page, durations_in_page):
for mobj in re.finditer(video_re, page):
# The link with index 0 is not the first video of the playlist (not sure if still actual)
if 'index' in mobj.groupdict() and mobj.group('id') == '0':
continue
video_id = mobj.group('id')
video_title = unescapeHTML(
mobj.group('title')) if 'title' in mobj.groupdict() else None
playlist_id = mobj.group('plid') if 'plid' in mobj.groupdict() else None
if playlist_id is not None:
video_id = playlist_id
video_title = unescapeHTML(mobj.group('title')) if 'title' in mobj.groupdict() else None
if video_title:
video_title = video_title.strip()
if video_title == '► Play all':
video_title = None
video_duration = mobj.group('duration') if 'duration' in mobj.groupdict() else None
if video_duration:
video_duration = video_duration.strip()
try:
idx = ids_in_page.index(video_id)
if video_title and not titles_in_page[idx]:
titles_in_page[idx] = video_title
if video_duration and not durations_in_page[idx]:
durations_in_page[idx] = video_duration
except ValueError:
ids_in_page.append(video_id)
titles_in_page.append(video_title)
durations_in_page.append(video_duration)
def extract_videos_from_page(self, page):
ids_in_page = []
titles_in_page = []
self.extract_videos_from_page_impl(
self._VIDEO_RE, page, ids_in_page, titles_in_page)
return zip(ids_in_page, titles_in_page)
durations_in_page = []
self.extract_videos_from_page_impl(self._VIDEO_RE, page, ids_in_page, titles_in_page, durations_in_page)
return zip(ids_in_page, titles_in_page, durations_in_page)
class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
@ -3149,7 +3162,7 @@ class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(&amp;list=(?P<plid>[0-9A-Za-z_-]+))?(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?(.*Duration:\s*(?P<duration>([0-1]?[0-9]|2[0-3]):[0-5][0-9]))?'
class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):