1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
6 from .common import InfoExtractor
10 compat_urllib_request,
14 class GorillaVidIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?gorillavid\.in/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)?'
18 'url': 'http://gorillavid.in/06y9juieqpmi',
19 'md5': '5ae4a3580620380619678ee4875893ba',
23 'title': 'Rebecca Black My Moment Official Music Video Reaction',
24 'thumbnail': 're:http://.*\.jpg',
27 'url': 'http://gorillavid.in/embed-z08zf8le23c6-960x480.html',
28 'md5': 'c9e293ca74d46cad638e199c3f3fe604',
32 'title': 'Say something nice',
33 'thumbnail': 're:http://.*\.jpg',
37 def _real_extract(self, url):
38 mobj = re.match(self._VALID_URL, url)
39 video_id = mobj.group('id')
41 url = 'http://gorillavid.in/%s' % video_id
43 webpage = self._download_webpage(url, video_id)
45 fields = dict(re.findall(r'''(?x)<input\s+
52 if fields['op'] == 'download1':
53 post = compat_urllib_parse.urlencode(fields)
55 req = compat_urllib_request.Request(url, post)
56 req.add_header('Content-type', 'application/x-www-form-urlencoded')
58 webpage = self._download_webpage(req, video_id, 'Downloading video page')
60 title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?</span>', webpage, 'title')
61 thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail')
62 url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url')
67 'ext': determine_ext(url),
74 'thumbnail': thumbnail,