_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',
'id': '06y9juieqpmi',
'ext': 'mp4',
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
- 'thumbnail': 're:http://.*\.jpg',
+ 'thumbnail': r're:http://.*\.jpg',
},
}, {
'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
'id': '3rso4kdn6f9m',
'ext': 'mp4',
'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc',
- 'thumbnail': 're:http://.*\.jpg',
+ 'thumbnail': r're:http://.*\.jpg',
}
}, {
'url': 'http://movpod.in/0wguyyxi1yca',
'id': '3ivfabn7573c',
'ext': 'mp4',
'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
- 'thumbnail': 're:http://.*\.jpg',
+ 'thumbnail': r're:http://.*\.jpg',
},
'skip': 'Video removed',
}, {
'ext': 'mp4',
'title': 'Chucky Prank 2015.mp4',
},
+ }, {
+ # removed by administrator
+ 'url': 'http://xvidstage.com/amfy7atlkx25',
+ 'only_matching': True,
}]
def _real_extract(self, url):
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)
webpage = self._download_webpage(req, video_id, 'Downloading video page')
title = (self._search_regex(
- [r'style="z-index: [0-9]+;">([^<]+)</span>',
+ (r'style="z-index: [0-9]+;">([^<]+)</span>',
r'<td nowrap>([^<]+)</td>',
r'h4-fine[^>]*>([^<]+)<',
r'>Watch (.+) ',
- r'<h2 class="video-page-head">([^<]+)</h2>'],
- webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
+ r'<h2 class="video-page-head">([^<]+)</h2>',
+ r'<h2 style="[^"]*color:#403f3d[^"]*"[^>]*>([^<]+)<'), # streamin.to
+ webpage, 'title', default=None) or self._og_search_title(
+ webpage, default=None) or video_id).strip()
def extract_video_url(default=NO_DEFAULT):
return self._search_regex(