1 # -*- coding: utf-8 -*-
2 from __future__ import unicode_literals
4 from .common import InfoExtractor
5 from ..compat import compat_urllib_parse
12 class VodlockerIE(InfoExtractor):
13 _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?:embed-)?(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
16 'url': 'http://vodlocker.com/e8wvyzz4sl42',
17 'md5': 'ce0c2d18fa0735f1bd91b69b0e54aacf',
21 'title': 'Germany vs Brazil',
22 'thumbnail': 're:http://.*\.jpg',
26 def _real_extract(self, url):
27 video_id = self._match_id(url)
28 webpage = self._download_webpage(url, video_id)
30 if any(p in webpage for p in (
31 '>THIS FILE WAS DELETED<',
33 'The file you were looking for could not be found, sorry for any inconvenience.<')):
34 raise ExtractorError('Video %s does not exist' % video_id, expected=True)
36 fields = self._hidden_inputs(webpage)
38 if fields['op'] == 'download1':
39 self._sleep(3, video_id) # they do detect when requests happen too fast!
40 post = compat_urllib_parse.urlencode(fields)
41 req = sanitized_Request(url, post)
42 req.add_header('Content-type', 'application/x-www-form-urlencoded')
43 webpage = self._download_webpage(
44 req, video_id, 'Downloading video page')
46 title = self._search_regex(
47 r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
48 thumbnail = self._search_regex(
49 r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
50 url = self._search_regex(
51 r'file:\s*"(http[^\"]+)",', webpage, 'file url')
61 'thumbnail': thumbnail,