2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from __future__ import unicode_literals
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								import re
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from .common import InfoExtractor
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								from ..utils import (
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    parse_duration,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    int_or_none,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								    qualities,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    determine_ext,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								class SunPornoIE(InfoExtractor):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)'
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    _TEST = {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        'url': 'http://www.sunporno.com/videos/807778/',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        'md5': '6457d3c165fd6de062b99ef6c2ff4c86',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        'info_dict': {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'id': '807778',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'ext': 'flv',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'title': 'md5:0a400058e8105d39e35c35e7c5184164',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'description': 'md5:a31241990e1bd3a64e72ae99afb325fb',
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'thumbnail': 're:^https?://.*\.jpg$',
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'duration': 302,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 22:38:40 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'age_limit': 18,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +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)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        title = self._html_search_regex(r'<title>([^<]+)</title>', webpage, 'title')
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        description = self._html_search_meta('description', webpage, 'description')
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        thumbnail = self._html_search_regex(
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False)
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        duration = parse_duration(self._search_regex(
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        view_count = int_or_none(self._html_search_regex(
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False))
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        comment_count = int_or_none(self._html_search_regex(
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False))
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        formats = []
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        quality = qualities(['mp4', 'flv'])
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        for video_url in re.findall(r'<source src="([^"]+)"', webpage):
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            video_ext = determine_ext(video_url)
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            formats.append({
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                'url': video_url,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                'format_id': video_ext,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                'quality': quality(video_ext),
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            })
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        self._sort_formats(formats)
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        return {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'id': video_id,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'title': title,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'description': description,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'thumbnail': thumbnail,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'duration': duration,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'view_count': view_count,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 01:08:19 +07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'comment_count': comment_count,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            'formats': formats,
							 | 
						
					
						
							
								
									
										
										
										
											2014-09-01 22:38:40 +02:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            'age_limit': 18,
							 | 
						
					
						
							
								
									
										
										
										
											2014-08-31 12:48:34 +02:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        }
							 |