from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( parse_duration, int_or_none, ) class AnySexIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)' _TEST = { 'url': 'http://anysex.com/156592/', 'md5': '023e9fbb7f7987f5529a394c34ad3d3d', 'info_dict': { 'id': '156592', 'ext': 'mp4', 'title': 'Busty and sexy blondie in her bikini strips for you', 'description': 'md5:de9e418178e2931c10b62966474e1383', 'categories': ['Erotic'], 'duration': 270, 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL') title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') description = self._html_search_regex( r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False) thumbnail = self._html_search_regex( r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) categories = re.findall( r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) duration = parse_duration(self._search_regex( r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) return { 'id': video_id, 'url': video_url, 'ext': 'mp4', 'title': title, 'description': description, 'thumbnail': thumbnail, 'categories': categories, 'duration': duration, 'view_count': view_count, 'age_limit': 18, }