Mirrors
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[vbox7] Fix extraction (fixes #5967)

This commit is contained in:
Yen Chi Hsuan 2015-06-15 18:49:27 +08:00
parent 4b9f9010b0
commit 4af98ecdfb
1 changed files with 16 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
youtube_dl/extractor/vbox7.py
View File

@ -5,6 +5,7 @@ from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_urllib_parse, compat_urllib_parse,
compat_urllib_request, compat_urllib_request,
compat_urlparse,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
@ -26,11 +27,21 @@ class Vbox7IE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
redirect_page, urlh = self._download_webpage_handle(url, video_id) # need to get the page 3 times for the correct jsSecretToken cookie
new_location = self._search_regex(r'window\.location = \'(.*)\';', # which is necessary for the correct title
redirect_page, 'redirect location') def get_session_id():
redirect_url = urlh.geturl() + new_location redirect_page = self._download_webpage(url, video_id)
webpage = self._download_webpage(redirect_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') 'Downloading redirect page')
title = self._html_search_regex(r'<title>(.*)</title>', title = self._html_search_regex(r'<title>(.*)</title>',