| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  | from __future__ import unicode_literals | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | import re | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | from .common import InfoExtractor | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | class BeegIE(InfoExtractor): | 
					
						
							|  |  |  |     _VALID_URL = r'https?://(?:www\.)?beeg\.com/(?P<id>\d+)' | 
					
						
							|  |  |  |     _TEST = { | 
					
						
							|  |  |  |         'url': 'http://beeg.com/5416503', | 
					
						
							| 
									
										
										
										
											2015-02-14 13:42:42 +01:00
										 |  |  |         'md5': '1bff67111adb785c51d1b42959ec10e5', | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  |         'info_dict': { | 
					
						
							|  |  |  |             'id': '5416503', | 
					
						
							|  |  |  |             'ext': 'mp4', | 
					
						
							|  |  |  |             'title': 'Sultry Striptease', | 
					
						
							|  |  |  |             'description': 'md5:6db3c6177972822aaba18652ff59c773', | 
					
						
							| 
									
										
										
										
											2014-09-01 00:00:01 +02:00
										 |  |  |             'categories': list,  # NSFW | 
					
						
							|  |  |  |             'thumbnail': 're:https?://.*\.jpg$', | 
					
						
							| 
									
										
										
										
											2014-09-01 23:13:04 +02:00
										 |  |  |             'age_limit': 18, | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +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) | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-09-02 20:54:00 +07:00
										 |  |  |         quality_arr = self._search_regex( | 
					
						
							|  |  |  |             r'(?s)var\s+qualityArr\s*=\s*{\s*(.+?)\s*}', webpage, 'quality formats') | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         formats = [{ | 
					
						
							|  |  |  |             'url': fmt[1], | 
					
						
							|  |  |  |             'format_id': fmt[0], | 
					
						
							|  |  |  |             'height': int(fmt[0][:-1]), | 
					
						
							|  |  |  |         } for fmt in re.findall(r"'([^']+)'\s*:\s*'([^']+)'", quality_arr)] | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         self._sort_formats(formats) | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-09-01 00:00:01 +02:00
										 |  |  |         title = self._html_search_regex( | 
					
						
							|  |  |  |             r'<title>([^<]+)\s*-\s*beeg\.?</title>', webpage, 'title') | 
					
						
							| 
									
										
										
										
											2014-11-23 20:41:03 +01:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  |         description = self._html_search_regex( | 
					
						
							| 
									
										
										
										
											2014-09-01 00:00:01 +02:00
										 |  |  |             r'<meta name="description" content="([^"]*)"', | 
					
						
							|  |  |  |             webpage, 'description', fatal=False) | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  |         thumbnail = self._html_search_regex( | 
					
						
							| 
									
										
										
										
											2014-09-01 00:00:01 +02:00
										 |  |  |             r'\'previewer.url\'\s*:\s*"([^"]*)"', | 
					
						
							|  |  |  |             webpage, 'thumbnail', fatal=False) | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  | 
 | 
					
						
							|  |  |  |         categories_str = self._html_search_regex( | 
					
						
							|  |  |  |             r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) | 
					
						
							| 
									
										
										
										
											2014-09-01 23:13:04 +02:00
										 |  |  |         categories = ( | 
					
						
							|  |  |  |             None if categories_str is None | 
					
						
							|  |  |  |             else categories_str.split(',')) | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  | 
 | 
					
						
							|  |  |  |         return { | 
					
						
							|  |  |  |             'id': video_id, | 
					
						
							|  |  |  |             'title': title, | 
					
						
							|  |  |  |             'description': description, | 
					
						
							|  |  |  |             'thumbnail': thumbnail, | 
					
						
							|  |  |  |             'categories': categories, | 
					
						
							| 
									
										
										
										
											2014-09-02 20:54:00 +07:00
										 |  |  |             'formats': formats, | 
					
						
							| 
									
										
										
										
											2014-09-01 23:13:04 +02:00
										 |  |  |             'age_limit': 18, | 
					
						
							| 
									
										
										
										
											2014-08-31 11:57:10 +02:00
										 |  |  |         } |