pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 20:20:09 +09:00
Code Issues Projects Releases Wiki Activity

[youtube:tab] Improve identity token extraction (closes #27197)

Browse Source
This commit is contained in:
Sergey M․ 2020-12-09 04:17:47 +07:00
parent e029da9add
commit 470cf496f5
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 14 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
youtube_dl/extractor/youtube.py
View File

@ -3121,6 +3121,19 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
self._playlist_entries(playlist), playlist_id=playlist_id, self._playlist_entries(playlist), playlist_id=playlist_id,
playlist_title=title) playlist_title=title)
def _extract_identity_token(self, webpage, item_id):
ytcfg = self._parse_json(
self._search_regex(
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), item_id, fatal=False)
if ytcfg:
token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
if token:
return token
return self._search_regex(
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
def _real_extract(self, url): def _real_extract(self, url):
item_id = self._match_id(url) item_id = self._match_id(url)
url = compat_urlparse.urlunparse( url = compat_urlparse.urlunparse(
@ -3135,9 +3148,7 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
webpage = self._download_webpage(url, item_id) webpage = self._download_webpage(url, item_id)
identity_token = self._search_regex( identity_token = self._extract_identity_token(webpage, item_id)
r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
'identity token', default=None)
data = self._extract_yt_initial_data(item_id, webpage) data = self._extract_yt_initial_data(item_id, webpage)
tabs = try_get( tabs = try_get(
data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)