mirror of
https://github.com/blackjack4494/yt-dlc.git
synced 2024-12-23 00:07:49 +00:00
[vbox7] Fix extraction (Closes #10309)
This commit is contained in:
parent
e581224843
commit
cb55908e51
1 changed files with 30 additions and 27 deletions
|
@ -12,7 +12,15 @@ from ..utils import (
|
||||||
|
|
||||||
class Vbox7IE(InfoExtractor):
|
class Vbox7IE(InfoExtractor):
|
||||||
_VALID_URL = r'https?://(?:www\.)?vbox7\.com/play:(?P<id>[^/]+)'
|
_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',
|
'url': 'http://vbox7.com/play:249bb972c2',
|
||||||
'md5': '99f65c0c9ef9b682b97313e052734c3f',
|
'md5': '99f65c0c9ef9b682b97313e052734c3f',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
|
@ -20,43 +28,38 @@ class Vbox7IE(InfoExtractor):
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
|
'title': 'Смях! Чудо - чист за секунди - Скрита камера',
|
||||||
},
|
},
|
||||||
}
|
'skip': 'georestricted',
|
||||||
|
}]
|
||||||
|
|
||||||
def _real_extract(self, url):
|
def _real_extract(self, url):
|
||||||
video_id = self._match_id(url)
|
video_id = self._match_id(url)
|
||||||
|
|
||||||
# need to get the page 3 times for the correct jsSecretToken cookie
|
webpage = self._download_webpage(url, video_id)
|
||||||
# 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()
|
title = self._html_search_regex(
|
||||||
get_session_id()
|
r'<title>(.*)</title>', webpage, 'title').split('/')[0].strip()
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id,
|
video_url = self._search_regex(
|
||||||
'Downloading redirect page')
|
r'src\s*:\s*(["\'])(?P<url>.+?.mp4.*?)\1',
|
||||||
|
webpage, 'video url', default=None, group='url')
|
||||||
|
|
||||||
title = self._html_search_regex(r'<title>(.*)</title>',
|
thumbnail_url = self._og_search_thumbnail(webpage)
|
||||||
webpage, 'title').split('/')[0].strip()
|
|
||||||
|
|
||||||
info_url = 'http://vbox7.com/play/magare.do'
|
if not video_url:
|
||||||
data = urlencode_postdata({'as3': '1', 'vid': video_id})
|
info_response = self._download_webpage(
|
||||||
info_request = sanitized_Request(info_url, data)
|
'http://vbox7.com/play/magare.do', video_id,
|
||||||
info_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
'Downloading info webpage',
|
||||||
info_response = self._download_webpage(info_request, video_id, 'Downloading info webpage')
|
data=urlencode_postdata({'as3': '1', 'vid': video_id}),
|
||||||
if info_response is None:
|
headers={'Content-Type': 'application/x-www-form-urlencoded'})
|
||||||
raise ExtractorError('Unable to extract the media url')
|
final_url, thumbnail_url = map(
|
||||||
(final_url, thumbnail_url) = map(lambda x: x.split('=')[1], info_response.split('&'))
|
lambda x: x.split('=')[1], info_response.split('&'))
|
||||||
|
|
||||||
|
if '/na.mp4' in video_url:
|
||||||
|
self.raise_geo_restricted()
|
||||||
|
|
||||||
return {
|
return {
|
||||||
'id': video_id,
|
'id': video_id,
|
||||||
'url': final_url,
|
'url': self._proto_relative_url(video_url, 'http:'),
|
||||||
'title': title,
|
'title': title,
|
||||||
'thumbnail': thumbnail_url,
|
'thumbnail': thumbnail_url,
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue