2 from __future__ import unicode_literals
5 from .common import InfoExtractor
11 class CinemassacreIE(InfoExtractor):
12 _VALID_URL = r'http://(?:www\.)?cinemassacre\.com/(?P<date_Y>[0-9]{4})/(?P<date_m>[0-9]{2})/(?P<date_d>[0-9]{2})/.+?'
15 'url': 'http://cinemassacre.com/2012/11/10/avgn-the-movie-trailer/',
17 'md5': 'fde81fbafaee331785f58cd6c0d46190',
19 'upload_date': '20121110',
20 'title': '“Angry Video Game Nerd: The Movie” – Trailer',
21 'description': 'md5:fb87405fcb42a331742a0dce2708560b',
25 'url': 'http://cinemassacre.com/2013/10/02/the-mummys-hand-1940',
26 'file': '521be8ef82b16.mp4',
27 'md5': 'd72f10cd39eac4215048f62ab477a511',
29 'upload_date': '20131002',
30 'title': 'The Mummy’s Hand (1940)',
35 def _real_extract(self, url):
36 mobj = re.match(self._VALID_URL, url)
38 webpage = self._download_webpage(url, None) # Don't know video id yet
39 video_date = mobj.group('date_Y') + mobj.group('date_m') + mobj.group('date_d')
40 mobj = re.search(r'src="(?P<embed_url>http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?id=(?:Cinemassacre-)?(?P<video_id>.+?))"', webpage)
42 raise ExtractorError('Can\'t extract embed url and video id')
43 playerdata_url = mobj.group('embed_url')
44 video_id = mobj.group('video_id')
46 video_title = self._html_search_regex(r'<title>(?P<title>.+?)\|',
48 video_description = self._html_search_regex(r'<div class="entry-content">(?P<description>.+?)</div>',
49 webpage, 'description', flags=re.DOTALL, fatal=False)
50 if len(video_description) == 0:
51 video_description = None
53 playerdata = self._download_webpage(playerdata_url, video_id)
55 sd_url = self._html_search_regex(r'file: \'(?P<sd_file>[^\']+)\', label: \'SD\'', playerdata, 'sd_file')
56 hd_url = self._html_search_regex(r'file: \'(?P<hd_file>[^\']+)\', label: \'HD\'', playerdata, 'hd_file')
57 video_thumbnail = self._html_search_regex(r'image: \'(?P<thumbnail>[^\']+)\'', playerdata, 'thumbnail', fatal=False)
78 'description': video_description,
79 'upload_date': video_date,
80 'thumbnail': video_thumbnail,