1 from __future__ import unicode_literals
5 from .common import InfoExtractor
8 class SexuIE(InfoExtractor):
9 _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
11 'url': 'http://sexu.com/961791/',
12 'md5': 'ff615aca9691053c94f8f10d96cd7884',
16 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
17 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54',
18 'categories': list, # NSFW
19 'thumbnail': 're:https?://.*\.jpg$',
24 def _real_extract(self, url):
25 mobj = re.match(self._VALID_URL, url)
26 video_id = mobj.group('id')
28 webpage = self._download_webpage(url, video_id)
30 quality_arr = self._search_regex(r'sources:\s*\[([^\]]+)\]', webpage, 'quality formats')
33 'url': fmt[0].replace('\\', ''),
35 'height': int(fmt[1][:3]),
36 } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)]
37 self._sort_formats(formats)
39 title = self._html_search_regex(
40 r'<title>([^<]+)\s*-\s*Sexu.Com</title>', webpage, 'title')
42 description = self._html_search_meta('description', webpage, 'description')
44 thumbnail = self._html_search_regex(
45 r'image:\s*"([^"]+)"',
46 webpage, 'thumbnail', fatal=False)
48 categories_str = self._html_search_meta('keywords', webpage, 'categories', fatal=False)
50 None if categories_str is None
51 else categories_str.split(','))
56 'description': description,
57 'thumbnail': thumbnail,
58 'categories': categories,