2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class HostingBulkIE(InfoExtractor):
17 https?://(?:www\.)?hostingbulk\.com/
18 (?:embed-)?(?P<id>[A-Za-z0-9]{12})(?:-\d+x\d+)?\.html'''
19 _FILE_DELETED_REGEX = r'<b>File Not Found</b>'
21 'url': 'http://hostingbulk.com/n0ulw1hv20fm.html',
22 'md5': '6c8653c8ecf7ebfa83b76e24b7b2fe3f',
26 'title': 'md5:5afeba33f48ec87219c269e054afd622',
28 'thumbnail': 're:^http://.*\.jpg$',
32 def _real_extract(self, url):
33 mobj = re.match(self._VALID_URL, url)
34 video_id = mobj.group('id')
36 url = 'http://hostingbulk.com/{0:}.html'.format(video_id)
38 # Custom request with cookie to set language to English, so our file
39 # deleted regex would work.
40 request = compat_urllib_request.Request(
41 url, headers={'Cookie': 'lang=english'})
42 webpage = self._download_webpage(request, video_id)
44 if re.search(self._FILE_DELETED_REGEX, webpage) is not None:
45 raise ExtractorError('Video %s does not exist' % video_id,
48 title = self._html_search_regex(r'<h3>(.*?)</h3>', webpage, 'title')
49 filesize = int_or_none(
51 r'<small>\((\d+)\sbytes?\)</small>',
57 thumbnail = self._search_regex(
58 r'<img src="([^"]+)".+?class="pic"',
59 webpage, 'thumbnail', fatal=False)
61 fields = dict(re.findall(r'''(?x)<input\s+
67 request = compat_urllib_request.Request(url, urlencode_postdata(fields))
68 request.add_header('Content-type', 'application/x-www-form-urlencoded')
69 response = self._request_webpage(request, video_id,
70 'Submiting download request')
71 video_url = response.geturl()
82 'thumbnail': thumbnail,