2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from __future__ import unicode_literals
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								import re
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from .common import InfoExtractor
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								from ..utils import (
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    parse_duration,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    int_or_none,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								class AnySexIE(InfoExtractor):
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								    _VALID_URL = r'https?://(?:www\.)?anysex\.com/(?P<id>\d+)'
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    _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',
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'description': 'md5:de9e418178e2931c10b62966474e1383',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'categories': ['Erotic'],
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 20:46:25 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'duration': 270,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 22:58:59 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'age_limit': 18,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        }
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    }
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    def _real_extract(self, url):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        mobj = re.match(self._VALID_URL, url)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        video_id = mobj.group('id')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        webpage = self._download_webpage(url, video_id)
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        video_url = self._html_search_regex(r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        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)
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        categories = re.findall(
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        duration = parse_duration(self._search_regex(
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            r'<b>Duration:</b> (\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))
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        return {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'id': video_id,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'url': video_url,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'ext': 'mp4',
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'title': title,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 07:05:53 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'description': description,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'thumbnail': thumbnail,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'categories': categories,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'duration': duration,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'view_count': view_count,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 22:58:59 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'age_limit': 18,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-30 18:37:45 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        }
							 |