1 from __future__ import unicode_literals
5 from .common import InfoExtractor
7 class HellPornoIE(InfoExtractor):
8 _VALID_URL = r'https?://(?:www\.)?hellporno\.com/videos/(?P<display_id>[^/]+)'
10 'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
11 'md5': '1fee339c610d2049699ef2aa699439f1',
15 'title': 'Dixie is posing with naked ass very erotic',
16 'description': 'md5:5ba02cbf31eff820147b3cc25306d89a',
17 'categories': list, # NSFW
18 'thumbnail': 're:https?://.*\.jpg$',
23 def _real_extract(self, url):
24 webpage = self._download_webpage(url, 'main')
26 video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id')
28 video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url')
30 ext = self._html_search_regex(r'postfix:\s*\'([^\']+)\'', webpage, 'ext')[1:]
32 title = self._html_search_regex(
33 r'<title>([^<]+)\s*-\s*Hell Porno</title>', webpage, 'title')
35 description = self._html_search_meta('description', webpage, 'description', fatal=False)
37 thumbnail = self._html_search_regex(
38 r'preview_url:\s*\'([^\']+)\'',
39 webpage, 'thumbnail', fatal=False)
41 categories_str = self._html_search_regex(
42 r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False)
44 None if categories_str is None
45 else categories_str.split(','))
52 'description': description,
53 'thumbnail': thumbnail,
54 'categories': categories,