midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[youtube:tab] Fix playlist title extraction (closes #27015)

Browse source
This commit is contained in:
Sergey M․ 2020-11-17 07:01:41 +07:00
parent 7d509c613b
commit f8c749f12c
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 21 additions and 15 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
youtube_dl/extractor/youtube.py
View file

@ -2825,30 +2825,36 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
raise ExtractorError('Unable to find selected tab') raise ExtractorError('Unable to find selected tab')
def _real_extract(self, url): def _real_extract(self, url):
channel_id = self._match_id(url) item_id = self._match_id(url)
url = compat_urlparse.urlunparse( url = compat_urlparse.urlunparse(
compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
webpage = self._download_webpage(url, channel_id) webpage = self._download_webpage(url, item_id)
data = self._extract_yt_initial_data(channel_id, webpage) data = self._extract_yt_initial_data(item_id, webpage)
tabs = data['contents']['twoColumnBrowseResultsRenderer']['tabs'] tabs = data['contents']['twoColumnBrowseResultsRenderer']['tabs']
selected_tab = self._extract_selected_tab(tabs) selected_tab = self._extract_selected_tab(tabs)
channel_title = try_get( renderer = try_get(
data, lambda x: x['metadata']['channelMetadataRenderer']['title'], data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
compat_str) if renderer:
channel_external_id = try_get( channel_title = renderer.get('title') or item_id
data, lambda x: x['metadata']['channelMetadataRenderer']['externalId'], tab_title = selected_tab.get('title')
compat_str) title = channel_title or item_id
tab_title = selected_tab.get('title') if tab_title:
title = channel_title or channel_id title += ' - %s' % tab_title
if tab_title: description = renderer.get('description')
title += ' - %s' % tab_title playlist_id = renderer.get('externalId')
renderer = try_get(
data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
if renderer:
title = renderer.get('title')
description = None
playlist_id = item_id
identity_token = self._search_regex( identity_token = self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None) 'identity token', default=None)
return self.playlist_result( return self.playlist_result(
self._entries(selected_tab['content'], identity_token), self._entries(selected_tab['content'], identity_token),
playlist_id=channel_external_id or channel_id, playlist_id=playlist_id, playlist_title=title,
playlist_title=title) playlist_description=description)
class YoutubePlaylistIE(InfoExtractor): class YoutubePlaylistIE(InfoExtractor):