mirror of
				https://github.com/yt-dlp/yt-dlp.git
				synced 2025-10-31 06:35:12 +00:00 
			
		
		
		
	
		
			
				
	
	
		
			138 lines
		
	
	
		
			5.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			138 lines
		
	
	
		
			5.4 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
| # coding: utf-8
 | |
| from __future__ import unicode_literals
 | |
| 
 | |
| import re
 | |
| 
 | |
| from .theplatform import ThePlatformBaseIE
 | |
| from ..utils import (
 | |
|     ExtractorError,
 | |
|     int_or_none,
 | |
|     update_url_query,
 | |
| )
 | |
| 
 | |
| 
 | |
| class MediasetIE(ThePlatformBaseIE):
 | |
|     _TP_TLD = 'eu'
 | |
|     _VALID_URL = r'''(?x)
 | |
|                     (?:
 | |
|                         mediaset:|
 | |
|                         https?://
 | |
|                             (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
 | |
|                             (?:
 | |
|                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
 | |
|                                 player/index\.html\?.*?\bprogramGuid=
 | |
|                             )
 | |
|                     )(?P<id>[0-9A-Z]{16})
 | |
|                     '''
 | |
|     _TESTS = [{
 | |
|         # full episode
 | |
|         'url': 'https://www.mediasetplay.mediaset.it/video/hellogoodbye/quarta-puntata_FAFU000000661824',
 | |
|         'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
 | |
|         'info_dict': {
 | |
|             'id': 'FAFU000000661824',
 | |
|             'ext': 'mp4',
 | |
|             'title': 'Quarta puntata',
 | |
|             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
 | |
|             'thumbnail': r're:^https?://.*\.jpg$',
 | |
|             'duration': 1414.26,
 | |
|             'upload_date': '20161107',
 | |
|             'series': 'Hello Goodbye',
 | |
|             'timestamp': 1478532900,
 | |
|             'uploader': 'Rete 4',
 | |
|             'uploader_id': 'R4',
 | |
|         },
 | |
|     }, {
 | |
|         'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
 | |
|         'md5': '288532f0ad18307705b01e581304cd7b',
 | |
|         'info_dict': {
 | |
|             'id': 'F309013801000501',
 | |
|             'ext': 'mp4',
 | |
|             'title': 'Puntata del 25 maggio',
 | |
|             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
 | |
|             'thumbnail': r're:^https?://.*\.jpg$',
 | |
|             'duration': 6565.007,
 | |
|             'upload_date': '20180526',
 | |
|             'series': 'Matrix',
 | |
|             'timestamp': 1527326245,
 | |
|             'uploader': 'Canale 5',
 | |
|             'uploader_id': 'C5',
 | |
|         },
 | |
|         'expected_warnings': ['HTTP Error 403: Forbidden'],
 | |
|     }, {
 | |
|         # clip
 | |
|         'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
 | |
|         'only_matching': True,
 | |
|     }, {
 | |
|         # iframe simple
 | |
|         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
 | |
|         'only_matching': True,
 | |
|     }, {
 | |
|         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
 | |
|         'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
 | |
|         'only_matching': True,
 | |
|     }, {
 | |
|         'url': 'mediaset:FAFU000000665924',
 | |
|         'only_matching': True,
 | |
|     }]
 | |
| 
 | |
|     @staticmethod
 | |
|     def _extract_urls(webpage):
 | |
|         return [
 | |
|             mobj.group('url')
 | |
|             for mobj in re.finditer(
 | |
|                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
 | |
|                 webpage)]
 | |
| 
 | |
|     def _real_extract(self, url):
 | |
|         guid = self._match_id(url)
 | |
|         tp_path = 'PR1GhC/media/guid/2702976343/' + guid
 | |
|         info = self._extract_theplatform_metadata(tp_path, guid)
 | |
| 
 | |
|         formats = []
 | |
|         subtitles = {}
 | |
|         first_e = None
 | |
|         for asset_type in ('SD', 'HD'):
 | |
|             for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
 | |
|                 try:
 | |
|                     tp_formats, tp_subtitles = self._extract_theplatform_smil(
 | |
|                         update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
 | |
|                             'mbr': 'true',
 | |
|                             'formats': f,
 | |
|                             'assetTypes': asset_type,
 | |
|                         }), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
 | |
|                 except ExtractorError as e:
 | |
|                     if not first_e:
 | |
|                         first_e = e
 | |
|                     break
 | |
|                 for tp_f in tp_formats:
 | |
|                     tp_f['quality'] = 1 if asset_type == 'HD' else 0
 | |
|                 formats.extend(tp_formats)
 | |
|                 subtitles = self._merge_subtitles(subtitles, tp_subtitles)
 | |
|         if first_e and not formats:
 | |
|             raise first_e
 | |
|         self._sort_formats(formats)
 | |
| 
 | |
|         fields = []
 | |
|         for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))):
 | |
|             fields.extend(templ % repl for repl in repls)
 | |
|         feed_data = self._download_json(
 | |
|             'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid,
 | |
|             guid, fatal=False, query={'fields': ','.join(fields)})
 | |
|         if feed_data:
 | |
|             publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
 | |
|             info.update({
 | |
|                 'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
 | |
|                 'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
 | |
|                 'series': feed_data.get('mediasetprogram$brandTitle'),
 | |
|                 'uploader': publish_info.get('description'),
 | |
|                 'uploader_id': publish_info.get('channel'),
 | |
|                 'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
 | |
|             })
 | |
| 
 | |
|         info.update({
 | |
|             'id': guid,
 | |
|             'formats': formats,
 | |
|             'subtitles': subtitles,
 | |
|         })
 | |
|         return info
 | 
