from .common import InfoExtractor
from ..utils import (
+ decode_packed_codes,
ExtractorError,
int_or_none,
+ NO_DEFAULT,
sanitized_Request,
urlencode_postdata,
)
('thevideobee.to', 'TheVideoBee'),
('vidto.me', 'Vidto'),
('streamin.to', 'Streamin.To'),
+ ('xvidstage.com', 'XVIDSTAGE'),
)
IE_DESC = 'XFileShare based sites: %s' % ', '.join(list(zip(*_SITES))[1])
_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',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ',
'thumbnail': 're:http://.*\.jpg',
},
'ext': 'mp4',
'title': 'youtube-dl test video \'äBaW_jenozKc.mp4.mp4',
'thumbnail': 're:http://.*\.jpg',
- }
+ },
+ 'skip': 'Video removed',
}, {
'url': 'http://vidto.me/ku5glz52nqe1.html',
'info_dict': {
'ext': 'mp4',
'title': 'Big Buck Bunny trailer',
},
+ }, {
+ 'url': 'http://xvidstage.com/e0qcnl03co6z',
+ 'info_dict': {
+ 'id': 'e0qcnl03co6z',
+ '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)
r'>Watch (.+) ',
r'<h2 class="video-page-head">([^<]+)</h2>'],
webpage, 'title', default=None) or self._og_search_title(webpage)).strip()
- video_url = self._search_regex(
- [r'file\s*:\s*["\'](http[^"\']+)["\'],',
- r'file_link\s*=\s*\'(https?:\/\/[0-9a-zA-z.\/\-_]+)'],
- webpage, 'file url')
+
+ def extract_video_url(default=NO_DEFAULT):
+ return self._search_regex(
+ (r'file\s*:\s*(["\'])(?P<url>http.+?)\1,',
+ r'file_link\s*=\s*(["\'])(?P<url>http.+?)\1',
+ r'addVariable\((\\?["\'])file\1\s*,\s*(\\?["\'])(?P<url>http.+?)\2\)',
+ r'<embed[^>]+src=(["\'])(?P<url>http.+?)\1'),
+ webpage, 'file url', default=default, group='url')
+
+ video_url = extract_video_url(default=None)
+
+ if not video_url:
+ webpage = decode_packed_codes(self._search_regex(
+ r"(}\('(.+)',(\d+),(\d+),'[^']*\b(?:file|embed)\b[^']*'\.split\('\|'\))",
+ webpage, 'packed code'))
+ video_url = extract_video_url()
+
thumbnail = self._search_regex(
r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', default=None)