| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  | # coding: utf-8 | 
					
						
							|  |  |  | from __future__ import unicode_literals | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | import re | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | from .common import InfoExtractor | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | class OnceIE(InfoExtractor): | 
					
						
							| 
									
										
										
										
											2017-10-11 15:48:32 +00:00
										 |  |  |     _VALID_URL = r'https?://.+?\.unicornmedia\.com/now/(?:ads/vmap/)?[^/]+/[^/]+/(?P<domain_id>[^/]+)/(?P<application_id>[^/]+)/(?:[^/]+/)?(?P<media_item_id>[^/]+)/content\.(?:once|m3u8|mp4)' | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |     ADAPTIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/master/playlist/%s/%s/%s/content.m3u8' | 
					
						
							|  |  |  |     PROGRESSIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/media/progressive/%s/%s/%s/%s/content.mp4' | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2017-11-13 10:24:35 +01:00
										 |  |  |     def _extract_once_formats(self, url, http_formats_preference=None): | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |         domain_id, application_id, media_item_id = re.match( | 
					
						
							|  |  |  |             OnceIE._VALID_URL, url).groups() | 
					
						
							| 
									
										
										
										
											2016-03-18 11:50:04 +01:00
										 |  |  |         formats = self._extract_m3u8_formats( | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |             self.ADAPTIVE_URL_TEMPLATE % ( | 
					
						
							|  |  |  |                 domain_id, application_id, media_item_id), | 
					
						
							|  |  |  |             media_item_id, 'mp4', m3u8_id='hls', fatal=False) | 
					
						
							| 
									
										
										
										
											2016-03-18 11:50:04 +01:00
										 |  |  |         progressive_formats = [] | 
					
						
							|  |  |  |         for adaptive_format in formats: | 
					
						
							| 
									
										
										
										
											2016-03-22 23:48:05 +06:00
										 |  |  |             # Prevent advertisement from embedding into m3u8 playlist (see | 
					
						
							| 
									
										
										
										
											2019-03-09 19:14:41 +07:00
										 |  |  |             # https://github.com/ytdl-org/youtube-dl/issues/8893#issuecomment-199912684) | 
					
						
							| 
									
										
										
										
											2016-03-22 23:48:05 +06:00
										 |  |  |             adaptive_format['url'] = re.sub( | 
					
						
							|  |  |  |                 r'\badsegmentlength=\d+', r'adsegmentlength=0', adaptive_format['url']) | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |             rendition_id = self._search_regex( | 
					
						
							|  |  |  |                 r'/now/media/playlist/[^/]+/[^/]+/([^/]+)', | 
					
						
							|  |  |  |                 adaptive_format['url'], 'redition id', default=None) | 
					
						
							| 
									
										
										
										
											2017-11-13 10:24:35 +01:00
										 |  |  |             if rendition_id: | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |                 progressive_format = adaptive_format.copy() | 
					
						
							|  |  |  |                 progressive_format.update({ | 
					
						
							|  |  |  |                     'url': self.PROGRESSIVE_URL_TEMPLATE % ( | 
					
						
							|  |  |  |                         domain_id, application_id, rendition_id, media_item_id), | 
					
						
							|  |  |  |                     'format_id': adaptive_format['format_id'].replace( | 
					
						
							|  |  |  |                         'hls', 'http'), | 
					
						
							|  |  |  |                     'protocol': 'http', | 
					
						
							| 
									
										
										
										
											2017-11-13 10:24:35 +01:00
										 |  |  |                     'preference': http_formats_preference, | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |                 }) | 
					
						
							| 
									
										
										
										
											2016-03-18 11:50:04 +01:00
										 |  |  |                 progressive_formats.append(progressive_format) | 
					
						
							|  |  |  |         self._check_formats(progressive_formats, media_item_id) | 
					
						
							|  |  |  |         formats.extend(progressive_formats) | 
					
						
							| 
									
										
										
										
											2016-03-17 16:05:31 +01:00
										 |  |  |         return formats |