1 from __future__ import unicode_literals
5 from .common import InfoExtractor
14 class SunPornoIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
17 'url': 'http://www.sunporno.com/videos/807778/',
18 'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
22 'title': 'md5:0a400058e8105d39e35c35e7c5184164',
23 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
24 'thumbnail': 're:^https?://.*\.jpg$',
29 def _real_extract(self, url):
30 mobj = re.match(self._VALID_URL, url)
31 video_id = mobj.group('id')
33 webpage = self._download_webpage(url, video_id)
35 title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
36 description = self._html_search_meta('description', webpage, 'description')
37 thumbnail = self._html_search_regex(
38 r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
40 duration = parse_duration(self._search_regex(
41 r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
43 view_count = int_or_none(self._html_search_regex(
44 r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
45 comment_count = int_or_none(self._html_search_regex(
46 r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
49 quality = qualities(['mp4', 'flv'])
50 for video_url in re.findall(r'<source src="([^"]+)"', webpage):
51 video_ext = determine_ext(video_url)
54 'format_id': video_ext,
55 'quality': quality(video_ext),
57 self._sort_formats(formats)
62 'description': description,
63 'thumbnail': thumbnail,
65 'view_count': view_count,
66 'comment_count': comment_count,