from __future__ import unicode_literals import re import json from .common import InfoExtractor from ..utils import ( int_or_none, js_to_json, qualities, ) class PornHdIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?P.+))?' _TEST = { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { 'id': '1962', 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', 'title': 'Sierra loves doing laundry', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', 'thumbnail': 're:^https?://.*\.jpg', 'view_count': int, 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id or video_id) title = self._html_search_regex( [r']+class=["\']video-name["\'][^>]*>([^<]+)', r'(.+?) - .*?[Pp]ornHD.*?'], webpage, 'title') description = self._html_search_regex( r'<(div|p)[^>]+class="description"[^>]*>(?P[^<]+)