# coding: utf-8 from __future__ import unicode_literals import re import random from .common import InfoExtractor from ..utils import ( int_or_none, float_or_none, unified_strdate, ) class PornoVoisinesIE(InfoExtractor): _VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P\d+)/(?P[^/]+)' _VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \ '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4' _SERVER_NUMBERS = (1, 2) _TEST = { 'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/', 'md5': '5ac670803bc12e9e7f9f662ce64cf1d1', 'info_dict': { 'id': '1285', 'display_id': 'recherche-appartement', 'ext': 'mp4', 'title': 'Recherche appartement', 'description': 'md5:819ea0b785e2a04667a1a01cdc89594e', 'thumbnail': 're:^https?://.*\.jpg$', 'upload_date': '20140925', 'duration': 120, 'view_count': int, 'average_rating': float, 'categories': ['Débutantes', 'Scénario', 'Sodomie'], 'age_limit': 18, } } @classmethod def build_video_url(cls, num): return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num) 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, video_id) video_url = self.build_video_url(video_id) title = self._html_search_regex( r'

(.+?)

', webpage, 'title', flags=re.DOTALL) description = self._html_search_regex( r'
(.+?)
', webpage, 'description', fatal=False, flags=re.DOTALL) thumbnail = self._search_regex( r'
\s*