| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  | # coding: utf-8 | 
					
						
							|  |  |  |  | from __future__ import unicode_literals | 
					
						
							|  |  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  | import re | 
					
						
							|  |  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  | from .common import InfoExtractor | 
					
						
							|  |  |  |  | 
 | 
					
						
							|  |  |  |  | 
 | 
					
						
							|  |  |  |  | class TeleBruxellesIE(InfoExtractor): | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |     _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)' | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  |     _TESTS = [{ | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |         'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/', | 
					
						
							|  |  |  |  |         'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9', | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  |         'info_dict': { | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |             'id': '158856', | 
					
						
							|  |  |  |  |             'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe', | 
					
						
							|  |  |  |  |             'ext': 'mp4', | 
					
						
							|  |  |  |  |             'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?', | 
					
						
							|  |  |  |  |             'description': 'md5:3cf8df235d44ebc5426373050840e466', | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         }, | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  |     }, { | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |         'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/', | 
					
						
							|  |  |  |  |         'md5': 'dfe07ecc9c153ceba8582ac912687675', | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  |         'info_dict': { | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |             'id': '158433', | 
					
						
							|  |  |  |  |             'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin', | 
					
						
							|  |  |  |  |             'ext': 'mp4', | 
					
						
							|  |  |  |  |             'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin', | 
					
						
							|  |  |  |  |             'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b', | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         }, | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |     }, { | 
					
						
							|  |  |  |  |         'url': 'http://bx1.be/emission/bxenf1-gastronomie/', | 
					
						
							|  |  |  |  |         'only_matching': True, | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |     }] | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  | 
 | 
					
						
							|  |  |  |  |     def _real_extract(self, url): | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         display_id = self._match_id(url) | 
					
						
							|  |  |  |  |         webpage = self._download_webpage(url, display_id) | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         article_id = self._html_search_regex( | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  |             r"<article id=\"post-(\d+)\"", webpage, 'article ID', default=None) | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         title = self._html_search_regex( | 
					
						
							|  |  |  |  |             r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title') | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  |         description = self._og_search_description(webpage, default=None) | 
					
						
							| 
									
										
										
										
											2014-11-22 13:34:29 +01:00
										 |  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         rtmp_url = self._html_search_regex( | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  |             r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"', | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |             webpage, 'RTMP url') | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  |         rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url) | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |         formats = self._extract_wowza_formats(rtmp_url, article_id or display_id) | 
					
						
							|  |  |  |  |         self._sort_formats(formats) | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  | 
 | 
					
						
							|  |  |  |  |         return { | 
					
						
							| 
									
										
										
										
											2016-04-11 00:06:05 +06:00
										 |  |  |  |             'id': article_id or display_id, | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |             'display_id': display_id, | 
					
						
							|  |  |  |  |             'title': title, | 
					
						
							|  |  |  |  |             'description': description, | 
					
						
							| 
									
										
										
										
											2016-12-06 19:01:09 +01:00
										 |  |  |  |             'formats': formats, | 
					
						
							| 
									
										
										
										
											2014-11-23 09:44:42 +01:00
										 |  |  |  |         } |