github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[vbox7] Fix extraction (Closes #10309)

Browse source
This commit is contained in:
Sergey M․ 2016-08-13 15:47:20 +07:00
parent e581224843
commit cb55908e51
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 30 additions and 27 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

57
youtube_dl/extractor/vbox7.py
View file

@ -12,7 +12,15 @@
class Vbox7IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
_TEST = {
_TESTS = [{
'url': 'http://vbox7.com/play:0946fff23c',
'md5': 'a60f9ab3a3a2f013ef9a967d5f7be5bf',
'info_dict': {
'id': '0946fff23c',
'ext': 'mp4',
'title': 'Борисов: Притеснен съм за бъдещето на България',
},
}, {
'url': 'http://vbox7.com/play:249bb972c2',
'md5': '99f65c0c9ef9b682b97313e052734c3f',
'info_dict': {
@ -20,43 +28,38 @@ class Vbox7IE(InfoExtractor):
'ext': 'mp4',
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
},
}
'skip': 'georestricted',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
# 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')
webpage = self._download_webpage(url, video_id)
get_session_id()
get_session_id()
title = self._html_search_regex(
r'<title>(.*)</title>', webpage, 'title').split('/')[0].strip()
webpage = self._download_webpage(url, video_id,
'Downloading redirect page')
video_url = self._search_regex(
r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
webpage, 'video url', default=None, group='url')
title = self._html_search_regex(r'<title>(.*)</title>',
webpage, 'title').split('/')[0].strip()
thumbnail_url = self._og_search_thumbnail(webpage)
info_url = 'http://vbox7.com/play/magare.do'
data = urlencode_postdata({'as3': '1', 'vid': video_id})
info_request = sanitized_Request(info_url, data)
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
if info_response is None:
raise ExtractorError('Unable to extract the media url')
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
if not video_url:
info_response = self._download_webpage(
'http://vbox7.com/play/magare.do', video_id,
'Downloading info webpage',
data=urlencode_postdata({'as3': '1', 'vid': video_id}),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
final_url, thumbnail_url = map(
lambda x: x.split('=')[1], info_response.split('&'))
if '/na.mp4' in video_url:
self.raise_geo_restricted()
return {
'id': video_id,
'url': final_url,
'url': self._proto_relative_url(video_url, 'http:'),
'title': title,
'thumbnail': thumbnail_url,
}