projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[youjizz] Fix extraction. The site has moved to HTML5
[youtube-dl]
/
youtube_dl
/
extractor
/
xfileshare.py
diff --git
a/youtube_dl/extractor/xfileshare.py
b/youtube_dl/extractor/xfileshare.py
index fe0ab6300bf1369b516c27f2f055047f9816051f..995aada0d1565ccc76f2fa2c7654e3f53f834d91 100644
(file)
--- a/
youtube_dl/extractor/xfileshare.py
+++ b/
youtube_dl/extractor/xfileshare.py
@@
-32,14
+32,17
@@
class XFileShareIE(InfoExtractor):
_VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
_VALID_URL = (r'https?://(?P<host>(?:www\.)?(?:%s))/(?:embed-)?(?P<id>[0-9a-zA-Z]+)'
% '|'.join(re.escape(site) for site in list(zip(*_SITES))[0]))
- _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<'
+ _FILE_NOT_FOUND_REGEXES = (
+ r'>(?:404 - )?File Not Found<',
+ r'>The file was removed by administrator<',
+ )
_TESTS = [{
'url': 'http://gorillavid.in/06y9juieqpmi',
'md5': '5ae4a3580620380619678ee4875893ba',
'info_dict': {
'id': '06y9juieqpmi',
_TESTS = [{
'url': 'http://gorillavid.in/06y9juieqpmi',
'md5': '5ae4a3580620380619678ee4875893ba',
'info_dict': {
'id': '06y9juieqpmi',
- 'ext': '
flv
',
+ 'ext': '
mp4
',
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
'thumbnail': 're:http://.*\.jpg',
},
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
'thumbnail': 're:http://.*\.jpg',
},
@@
-88,6
+91,10
@@
class XFileShareIE(InfoExtractor):
'ext': 'mp4',
'title': 'Chucky Prank 2015.mp4',
},
'ext': 'mp4',
'title': 'Chucky Prank 2015.mp4',
},
+ }, {
+ # removed by administrator
+ 'url': 'http://xvidstage.com/amfy7atlkx25',
+ 'only_matching': True,
}]
def _real_extract(self, url):
}]
def _real_extract(self, url):
@@
-97,7
+104,7
@@
class XFileShareIE(InfoExtractor):
url = 'http://%s/%s' % (mobj.group('host'), video_id)
webpage = self._download_webpage(url, video_id)
url = 'http://%s/%s' % (mobj.group('host'), video_id)
webpage = self._download_webpage(url, video_id)
- if
re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None
:
+ if
any(re.search(p, webpage) for p in self._FILE_NOT_FOUND_REGEXES)
:
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)
raise ExtractorError('Video %s does not exist' % video_id, expected=True)
fields = self._hidden_inputs(webpage)