1 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 class PornHdIE(InfoExtractor):
16 _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
18 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
19 'md5': '956b8ca569f7f4d8ec563e2c41598441',
22 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
24 'title': 'Sierra loves doing laundry',
25 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
26 'thumbnail': 're:^https?://.*\.jpg',
32 def _real_extract(self, url):
33 mobj = re.match(self._VALID_URL, url)
34 video_id = mobj.group('id')
35 display_id = mobj.group('display_id')
37 webpage = self._download_webpage(url, display_id or video_id)
39 title = self._html_search_regex(
40 r'<title>(.+) porn HD.+?</title>', webpage, 'title')
41 description = self._html_search_regex(
42 r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
43 view_count = int_or_none(self._html_search_regex(
44 r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
45 thumbnail = self._search_regex(
46 r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
48 quality = qualities(['SD', 'HD'])
50 'url': source['file'],
51 'format_id': '%s-%s' % (source['label'], determine_ext(source['file'])),
52 'quality': quality(source['label']),
53 } for source in json.loads(js_to_json(self._search_regex(
54 r"(?s)'sources'\s*:\s*(\[.+?\])", webpage, 'sources')))]
55 self._sort_formats(formats)
59 'display_id': display_id,
61 'description': description,
62 'thumbnail': thumbnail,
63 'view_count': view_count,