2 from __future__ import unicode_literals
15 from .common import InfoExtractor
18 class SockshareIE(InfoExtractor):
19 _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)'
20 _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>'
22 'url': 'http://www.sockshare.com/file/437BE28B89D799D7',
23 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd',
25 'id': '437BE28B89D799D7',
26 'title': 'big_buck_bunny_720p_surround.avi',
28 'thumbnail': 're:^http://.*\.jpg$',
32 def _real_extract(self, url):
33 video_id = self._match_id(url)
34 url = 'http://sockshare.com/file/%s' % video_id
35 webpage = self._download_webpage(url, video_id)
37 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
38 raise ExtractorError('Video %s does not exist' % video_id,
41 confirm_hash = self._html_search_regex(r'''(?x)<input\s+
49 "confirm": "Continue as Free User"
52 post = compat_urllib_parse.urlencode(fields)
53 req = compat_urllib_request.Request(url, post)
54 # Apparently, this header is required for confirmation to work.
55 req.add_header('Host', 'www.sockshare.com')
56 req.add_header('Content-type', 'application/x-www-form-urlencoded')
58 webpage = self._download_webpage(
59 req, video_id, 'Downloading video page')
61 video_url = self._html_search_regex(
62 r'<a href="([^"]*)".+class="download_file_link"',
64 video_url = "http://www.sockshare.com" + video_url
65 title = self._html_search_regex((
67 r'var name = "([^"]+)";'),
68 webpage, 'title', default=None)
69 thumbnail = self._html_search_regex(
70 r'<img\s+src="([^"]*)".+?name="bg"',
76 'ext': determine_ext(title),
82 'thumbnail': thumbnail,