diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-06-15 18:49:27 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-06-15 18:49:27 +0800 |
commit | 4af98ecdfb896c16e73cb9f7306908cc686782e8 (patch) | |
tree | b3d202e881351c923474e4c6679ea631bb4819f3 /youtube_dl/extractor | |
parent | 4b9f9010b0d744969189c383e98e8729f9fe9623 (diff) |
[vbox7] Fix extraction (fixes #5967)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/vbox7.py | 21 |
1 files changed, 16 insertions, 5 deletions
diff --git a/youtube_dl/extractor/vbox7.py b/youtube_dl/extractor/vbox7.py index dd026748d..722eb5236 100644 --- a/youtube_dl/extractor/vbox7.py +++ b/youtube_dl/extractor/vbox7.py @@ -5,6 +5,7 @@ from .common import InfoExtractor 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>', |