mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-21 20:46:36 -05:00
[vbox7] Fix extraction (fixes #5967)
This commit is contained in:
parent
4b9f9010b0
commit
4af98ecdfb
1 changed files with 16 additions and 5 deletions
|
@ -5,6 +5,7 @@
|
|||
from ..compat import (
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
)
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
|
@ -26,11 +27,21 @@ class Vbox7IE(InfoExtractor):
|
|||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
redirect_page, urlh = self._download_webpage_handle(url, video_id)
|
||||
new_location = self._search_regex(r'window\.location = \'(.*)\';',
|
||||
redirect_page, 'redirect location')
|
||||
redirect_url = urlh.geturl() + new_location
|
||||
webpage = self._download_webpage(redirect_url, video_id,
|
||||
# need to get the page 3 times for the correct jsSecretToken cookie
|
||||
# which is necessary for the correct title
|
||||
def get_session_id():
|
||||
redirect_page = self._download_webpage(url, video_id)
|
||||
session_id_url = self._search_regex(
|
||||
r'var\s*url\s*=\s*\'([^\']+)\';', redirect_page,
|
||||
'session id url')
|
||||
self._download_webpage(
|
||||
compat_urlparse.urljoin(url, session_id_url), video_id,
|
||||
'Getting session id')
|
||||
|
||||
get_session_id()
|
||||
get_session_id()
|
||||
|
||||
webpage = self._download_webpage(url, video_id,
|
||||
'Downloading redirect page')
|
||||
|
||||
title = self._html_search_regex(r'<title>(.*)</title>',
|
||||
|
|
Loading…
Reference in a new issue