1 from __future__ import unicode_literals
5 from .common import InfoExtractor
13 class PornHdIE(InfoExtractor):
14 _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
16 'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
17 'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
20 'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
22 'title': 'Restroom selfie masturbation',
23 'description': 'md5:3748420395e03e31ac96857a8f125b2b',
24 'thumbnail': r're:^https?://.*\.jpg',
30 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
31 'md5': '956b8ca569f7f4d8ec563e2c41598441',
34 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
36 'title': 'Sierra loves doing laundry',
37 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
38 'thumbnail': r're:^https?://.*\.jpg',
42 'skip': 'Not available anymore',
45 def _real_extract(self, url):
46 mobj = re.match(self._VALID_URL, url)
47 video_id = mobj.group('id')
48 display_id = mobj.group('display_id')
50 webpage = self._download_webpage(url, display_id or video_id)
52 title = self._html_search_regex(
53 [r'<span[^>]+class=["\']video-name["\'][^>]*>([^<]+)',
54 r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
56 sources = self._parse_json(js_to_json(self._search_regex(
57 r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
58 webpage, 'sources', default='{}')), video_id)
61 message = self._html_search_regex(
62 r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P<value>.+?)</\1',
63 webpage, 'error message', group='value')
64 raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
67 for format_id, video_url in sources.items():
70 height = int_or_none(self._search_regex(
71 r'^(\d+)[pP]', format_id, 'height', default=None))
74 'format_id': format_id,
77 self._sort_formats(formats)
79 description = self._html_search_regex(
80 r'<(div|p)[^>]+class="description"[^>]*>(?P<value>[^<]+)</\1',
81 webpage, 'description', fatal=False, group='value')
82 view_count = int_or_none(self._html_search_regex(
83 r'(\d+) views\s*<', webpage, 'view count', fatal=False))
84 thumbnail = self._search_regex(
85 r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
89 'display_id': display_id,
91 'description': description,
92 'thumbnail': thumbnail,
93 'view_count': view_count,