[bbc] Improve playlist extraction, refactor, expand support and document
This commit is contained in:
		
							parent
							
								
									ff81c4c99c
								
							
						
					
					
						commit
						9afa1770d1
					
				| @ -43,7 +43,10 @@ from .azubu import AzubuIE | ||||
| from .baidu import BaiduVideoIE | ||||
| from .bambuser import BambuserIE, BambuserChannelIE | ||||
| from .bandcamp import BandcampIE, BandcampAlbumIE | ||||
| from .bbc import BBCCoUkIE, BBCNewsIE | ||||
| from .bbc import ( | ||||
|     BBCCoUkIE, | ||||
|     BBCIE, | ||||
| ) | ||||
| from .beeg import BeegIE | ||||
| from .behindkink import BehindKinkIE | ||||
| from .beatportpro import BeatportProIE | ||||
|  | ||||
| @ -1,15 +1,18 @@ | ||||
| # coding: utf-8 | ||||
| from __future__ import unicode_literals | ||||
| 
 | ||||
| import re | ||||
| import xml.etree.ElementTree | ||||
| 
 | ||||
| from .common import InfoExtractor | ||||
| from ..utils import ( | ||||
|     ExtractorError, | ||||
|     parse_duration, | ||||
|     float_or_none, | ||||
|     int_or_none, | ||||
|     parse_duration, | ||||
|     parse_iso8601, | ||||
| ) | ||||
| from ..compat import compat_HTTPError | ||||
| import re | ||||
| 
 | ||||
| 
 | ||||
| class BBCCoUkIE(InfoExtractor): | ||||
| @ -17,7 +20,7 @@ class BBCCoUkIE(InfoExtractor): | ||||
|     IE_DESC = 'BBC iPlayer' | ||||
|     _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' | ||||
| 
 | ||||
|     mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' | ||||
|     _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' | ||||
| 
 | ||||
|     _TESTS = [ | ||||
|         { | ||||
| @ -264,16 +267,21 @@ class BBCCoUkIE(InfoExtractor): | ||||
|         return subtitles | ||||
| 
 | ||||
|     def _download_media_selector(self, programme_id): | ||||
|         return self._download_media_selector_url( | ||||
|             self._MEDIASELECTOR_URL % programme_id, programme_id) | ||||
| 
 | ||||
|     def _download_media_selector_url(self, url, programme_id=None): | ||||
|         try: | ||||
|             media_selection = self._download_xml( | ||||
|                 self.mediaselector_url % programme_id, | ||||
|                 programme_id, 'Downloading media selection XML') | ||||
|                 url, programme_id, 'Downloading media selection XML') | ||||
|         except ExtractorError as ee: | ||||
|             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | ||||
|                 media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) | ||||
|             else: | ||||
|                 raise | ||||
|         return self._process_media_selector(media_selection, programme_id) | ||||
| 
 | ||||
|     def _process_media_selector(self, media_selection, programme_id): | ||||
|         formats = [] | ||||
|         subtitles = None | ||||
| 
 | ||||
| @ -312,10 +320,21 @@ class BBCCoUkIE(InfoExtractor): | ||||
|                 raise | ||||
| 
 | ||||
|         # fallback to legacy playlist | ||||
|         playlist = self._download_xml( | ||||
|             'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, | ||||
|             playlist_id, 'Downloading legacy playlist XML') | ||||
|         return self._process_legacy_playlist(playlist_id) | ||||
| 
 | ||||
|     def _process_legacy_playlist_url(self, url, display_id): | ||||
|         playlist = self._download_legacy_playlist_url(url, display_id) | ||||
|         return self._extract_from_legacy_playlist(playlist, display_id) | ||||
| 
 | ||||
|     def _process_legacy_playlist(self, playlist_id): | ||||
|         return self._process_legacy_playlist_url( | ||||
|             'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) | ||||
| 
 | ||||
|     def _download_legacy_playlist_url(self, url, playlist_id=None): | ||||
|         return self._download_xml( | ||||
|             url, playlist_id, 'Downloading legacy playlist XML') | ||||
| 
 | ||||
|     def _extract_from_legacy_playlist(self, playlist, playlist_id): | ||||
|         no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') | ||||
|         if no_items is not None: | ||||
|             reason = no_items.get('reason') | ||||
| @ -335,8 +354,23 @@ class BBCCoUkIE(InfoExtractor): | ||||
|                 continue | ||||
|             title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | ||||
|             description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | ||||
|             programme_id = item.get('identifier') | ||||
| 
 | ||||
|             def get_programme_id(item): | ||||
|                 def get_from_attributes(item): | ||||
|                     for p in('identifier', 'group'): | ||||
|                         value = item.get(p) | ||||
|                         if value and re.match(r'^[pb][\da-z]{7}$', value): | ||||
|                             return value | ||||
|                 get_from_attributes(item) | ||||
|                 mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') | ||||
|                 if mediator is not None: | ||||
|                     return get_from_attributes(mediator) | ||||
| 
 | ||||
|             programme_id = get_programme_id(item) | ||||
|             duration = int_or_none(item.get('duration')) | ||||
|             # TODO: programme_id can be None and media items can be incorporated right inside | ||||
|             # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | ||||
|             # as f4m and m3u8 | ||||
|             formats, subtitles = self._download_media_selector(programme_id) | ||||
| 
 | ||||
|         return programme_id, title, description, duration, formats, subtitles | ||||
| @ -383,175 +417,276 @@ class BBCCoUkIE(InfoExtractor): | ||||
|         } | ||||
| 
 | ||||
| 
 | ||||
| class BBCNewsIE(BBCCoUkIE): | ||||
|     IE_NAME = 'bbc.com' | ||||
|     IE_DESC = 'BBC news' | ||||
|     _VALID_URL = r'https?://(?:www\.)?bbc\.com/.+?/(?P<id>[^/]+)$' | ||||
| class BBCIE(BBCCoUkIE): | ||||
|     IE_NAME = 'bbc' | ||||
|     IE_DESC = 'BBC' | ||||
|     _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)' | ||||
| 
 | ||||
|     mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s' | ||||
|     # fails with notukerror for some videos | ||||
|     #_MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s' | ||||
|     _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s' | ||||
| 
 | ||||
|     _TESTS = [{ | ||||
|         # article with multiple videos embedded with data-media-meta containing | ||||
|         # playlist.sxml, externalId and no direct video links | ||||
|         'url': 'http://www.bbc.com/news/world-europe-32668511', | ||||
|         'info_dict': { | ||||
|             'id': 'world-europe-32668511', | ||||
|             'title': 'Russia stages massive WW2 parade despite Western boycott', | ||||
|             'description': 'md5:00ff61976f6081841f759a08bf78cc9c', | ||||
|         }, | ||||
|         'playlist_count': 2, | ||||
|     }, { | ||||
|         # article with multiple videos embedded with data-media-meta (more videos) | ||||
|         'url': 'http://www.bbc.com/news/business-28299555', | ||||
|         'info_dict': { | ||||
|             'id': 'business-28299555', | ||||
|             'title': 'Farnborough Airshow: Video highlights', | ||||
|             'description': 'BBC reports and video highlights at the Farnborough Airshow.', | ||||
|         }, | ||||
|         'playlist_count': 9, | ||||
|         'skip': 'Save time', | ||||
|     }, { | ||||
|         # single video embedded with mediaAssetPage.init() | ||||
|         'url': 'http://www.bbc.com/news/world-europe-32041533', | ||||
|         'note': 'Video', | ||||
|         'info_dict': { | ||||
|             'id': 'p02mprgb', | ||||
|             'ext': 'mp4', | ||||
|             'ext': 'flv', | ||||
|             'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', | ||||
|             'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', | ||||
|             'duration': 47, | ||||
|             'timestamp': 1427219242, | ||||
|             'upload_date': '20150324', | ||||
|             'uploader': 'BBC News', | ||||
|         }, | ||||
|         'params': { | ||||
|             # rtmp download | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # article with single video embedded with data-media-meta containing | ||||
|         # direct video links (for now these are extracted) and playlist.xml (with | ||||
|         # media items as f4m and m3u8 - currently unsupported) | ||||
|         'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', | ||||
|         'note': 'Video', | ||||
|         'info_dict': { | ||||
|             'id': 'NA', | ||||
|             'id': '150615_telabyad_kentin_cogu', | ||||
|             'ext': 'mp4', | ||||
|             'title': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde', | ||||
|             'description': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde', | ||||
|             'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", | ||||
|             'duration': 47, | ||||
|             'timestamp': 1434397334, | ||||
|             'upload_date': '20150615', | ||||
|             'uploader': 'BBC News', | ||||
|         }, | ||||
|         'params': { | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # single video embedded with mediaAssetPage.init() (regional section) | ||||
|         'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', | ||||
|         'note': 'Video', | ||||
|         'info_dict': { | ||||
|             'id': '39275083', | ||||
|             'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', | ||||
|             'ext': 'mp4', | ||||
|             'title': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n', | ||||
|             'description': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n', | ||||
|             'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', | ||||
|             'duration': 87, | ||||
|             'timestamp': 1434713142, | ||||
|             'upload_date': '20150619', | ||||
|             'uploader': 'BBC News', | ||||
|         }, | ||||
|         'params': { | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # single video story with digitalData | ||||
|         'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', | ||||
|         'info_dict': { | ||||
|             'id': 'p02q6gc4', | ||||
|             'ext': 'flv', | ||||
|             'title': 'Sri Lanka’s spicy secret', | ||||
|             'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', | ||||
|             'timestamp': 1437674293, | ||||
|             'upload_date': '20150723', | ||||
|         }, | ||||
|         'params': { | ||||
|             # rtmp download | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # single video story without digitalData | ||||
|         'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', | ||||
|         'info_dict': { | ||||
|             'id': 'p018zqqg', | ||||
|             'ext': 'flv', | ||||
|             'title': 'Hyundai Santa Fe Sport: Rock star', | ||||
|             'description': 'md5:b042a26142c4154a6e472933cf20793d', | ||||
|             'timestamp': 1368473503, | ||||
|             'upload_date': '20130513', | ||||
|         }, | ||||
|         'params': { | ||||
|             # rtmp download | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # single video with playlist.sxml URL | ||||
|         'url': 'http://www.bbc.com/sport/0/football/33653409', | ||||
|         'info_dict': { | ||||
|             'id': 'p02xycnp', | ||||
|             'ext': 'flv', | ||||
|             'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', | ||||
|             'description': 'md5:398fca0e2e701c609d726e034fa1fc89', | ||||
|             'duration': 140, | ||||
|         }, | ||||
|         'params': { | ||||
|             # rtmp download | ||||
|             'skip_download': True, | ||||
|         } | ||||
|     }, { | ||||
|         # single video with playlist URL from weather section | ||||
|         'url': 'http://www.bbc.com/weather/features/33601775', | ||||
|         'only_matching': True, | ||||
|     }, { | ||||
|         # custom redirection to www.bbc.com | ||||
|         'url': 'http://www.bbc.co.uk/news/science-environment-33661876', | ||||
|         'only_matching': True, | ||||
|     }] | ||||
| 
 | ||||
|     def _real_extract(self, url): | ||||
|         list_id = self._match_id(url) | ||||
|         webpage = self._download_webpage(url, list_id) | ||||
|     @classmethod | ||||
|     def suitable(cls, url): | ||||
|         return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) | ||||
| 
 | ||||
|         list_title = self._html_search_regex(r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'list title') | ||||
| 
 | ||||
|         pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None) | ||||
|         if pubdate: | ||||
|             pubdate = pubdate.replace('-', '') | ||||
| 
 | ||||
|         ret = [] | ||||
|         jsent = [] | ||||
| 
 | ||||
|         # works with bbc.com/news/something-something-123456 articles | ||||
|         jsent = map( | ||||
|             lambda m: self._parse_json(m, list_id), | ||||
|             re.findall(r"data-media-meta='({[^']+})'", webpage) | ||||
|         ) | ||||
| 
 | ||||
|         if len(jsent) == 0: | ||||
|             # http://www.bbc.com/news/video_and_audio/international | ||||
|             # and single-video articles | ||||
|             masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None) | ||||
|             if masset: | ||||
|                 jmasset = self._parse_json(masset, list_id) | ||||
|                 for key, val in jmasset.get('videos', {}).items(): | ||||
|                     for skey, sval in val.items(): | ||||
|                         sval['id'] = skey | ||||
|                         jsent.append(sval) | ||||
| 
 | ||||
|         if len(jsent) == 0: | ||||
|             # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc} | ||||
|             # in http://www.bbc.com/news/video_and_audio/international | ||||
|             # prone to breaking if entries have sourceFiles list | ||||
|             jsent = map( | ||||
|                 lambda m: self._parse_json(m, list_id), | ||||
|                 re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage) | ||||
|             ) | ||||
| 
 | ||||
|         if len(jsent) == 0: | ||||
|             raise ExtractorError('No video found', expected=True) | ||||
| 
 | ||||
|         for jent in jsent: | ||||
|             programme_id = jent.get('externalId') | ||||
|             xml_url = jent.get('href') | ||||
| 
 | ||||
|             title = jent.get('caption', '') | ||||
|             if title == '': | ||||
|                 title = list_title | ||||
| 
 | ||||
|             duration = parse_duration(jent.get('duration')) | ||||
|             description = list_title | ||||
|             if jent.get('caption', '') != '': | ||||
|                 description += ' - ' + jent.get('caption') | ||||
|             thumbnail = None | ||||
|             if jent.get('image') is not None: | ||||
|                 thumbnail = jent['image'].get('href') | ||||
| 
 | ||||
|             formats = [] | ||||
|             subtitles = [] | ||||
|     def _extract_from_media_meta(self, media_meta, video_id): | ||||
|         # Direct links to media in media metadata (e.g. | ||||
|         # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | ||||
|         # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml | ||||
|         source_files = media_meta.get('sourceFiles') | ||||
|         if source_files: | ||||
|             return [{ | ||||
|                 'url': f['url'], | ||||
|                 'format_id': format_id, | ||||
|                 'ext': f.get('encoding'), | ||||
|                 'tbr': float_or_none(f.get('bitrate'), 1000), | ||||
|                 'filesize': int_or_none(f.get('filesize')), | ||||
|             } for format_id, f in source_files.items() if f.get('url')], [] | ||||
| 
 | ||||
|         programme_id = media_meta.get('externalId') | ||||
|         if programme_id: | ||||
|                 formats, subtitles = self._download_media_selector(programme_id) | ||||
|             elif jent.get('sourceFiles') is not None: | ||||
|                 # mediaselector not used at | ||||
|                 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu | ||||
|                 for key, val in jent['sourceFiles'].items(): | ||||
|                     formats.append({ | ||||
|                         'ext': val.get('encoding'), | ||||
|                         'url': val.get('url'), | ||||
|                         'filesize': int(val.get('filesize')), | ||||
|                         'format_id': key | ||||
|                     }) | ||||
|             elif xml_url: | ||||
|                 # Cheap fallback | ||||
|                 # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml | ||||
|                 xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)') | ||||
|                 programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)') | ||||
|                 formats, subtitles = self._download_media_selector(programme_id) | ||||
|             return self._download_media_selector(programme_id) | ||||
| 
 | ||||
|             if len(formats) == 0: | ||||
|                 raise ExtractorError('unsupported json media entry.\n    ' + str(jent) + '\n') | ||||
|         # Process playlist.sxml as legacy playlist | ||||
|         href = media_meta.get('href') | ||||
|         if href: | ||||
|             playlist = self._download_legacy_playlist_url(href) | ||||
|             _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) | ||||
|             return formats, subtitles | ||||
| 
 | ||||
|         return [], [] | ||||
| 
 | ||||
|     def _real_extract(self, url): | ||||
|         playlist_id = self._match_id(url) | ||||
| 
 | ||||
|         webpage = self._download_webpage(url, playlist_id) | ||||
| 
 | ||||
|         timestamp = parse_iso8601(self._search_regex( | ||||
|             [r'"datePublished":\s*"([^"]+)', | ||||
|              r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"', | ||||
|              r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], | ||||
|             webpage, 'date', default=None)) | ||||
| 
 | ||||
|         # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) | ||||
|         playlist = self._search_regex( | ||||
|             r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', | ||||
|             webpage, 'playlist', default=None) | ||||
|         if playlist: | ||||
|             programme_id, title, description, duration, formats, subtitles = \ | ||||
|                 self._process_legacy_playlist_url(playlist, playlist_id) | ||||
|             self._sort_formats(formats) | ||||
| 
 | ||||
|             id = jent.get('id') if programme_id is None else programme_id | ||||
|             if id is None: | ||||
|                 id = 'NA' | ||||
| 
 | ||||
|             ret.append({ | ||||
|                 'id': id, | ||||
|                 'uploader': 'BBC News', | ||||
|                 'upload_date': pubdate, | ||||
|             return { | ||||
|                 'id': programme_id, | ||||
|                 'title': title, | ||||
|                 'description': description, | ||||
|                 'thumbnail': thumbnail, | ||||
|                 'duration': duration, | ||||
|                 'timestamp': timestamp, | ||||
|                 'formats': formats, | ||||
|                 'subtitles': subtitles, | ||||
|             } | ||||
| 
 | ||||
|         # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) | ||||
|         programme_id = self._search_regex( | ||||
|             [r'data-video-player-vpid="([\da-z]{8})"', | ||||
|              r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], | ||||
|             webpage, 'vpid', default=None) | ||||
|         if programme_id: | ||||
|             formats, subtitles = self._download_media_selector(programme_id) | ||||
|             self._sort_formats(formats) | ||||
|             # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) | ||||
|             digital_data = self._parse_json( | ||||
|                 self._search_regex( | ||||
|                     r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), | ||||
|                 programme_id, fatal=False) | ||||
|             page_info = digital_data.get('page', {}).get('pageInfo', {}) | ||||
|             title = page_info.get('pageName') or self._og_search_title(webpage) | ||||
|             description = page_info.get('description') or self._og_search_description(webpage) | ||||
|             timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp | ||||
|             return { | ||||
|                 'id': programme_id, | ||||
|                 'title': title, | ||||
|                 'description': description, | ||||
|                 'timestamp': timestamp, | ||||
|                 'formats': formats, | ||||
|                 'subtitles': subtitles, | ||||
|             } | ||||
| 
 | ||||
|         playlist_title = self._html_search_regex( | ||||
|             r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') | ||||
|         playlist_description = self._og_search_description(webpage) | ||||
| 
 | ||||
|         # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) | ||||
|         medias = list(filter(None, map( | ||||
|             lambda s: self._parse_json(s, playlist_id, fatal=False), | ||||
|             re.findall(r"data-media-meta='({[^']+})'", webpage)))) | ||||
| 
 | ||||
|         if not medias: | ||||
|             # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) | ||||
|             media_asset_page = self._parse_json( | ||||
|                 self._search_regex( | ||||
|                     r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'media asset'), | ||||
|                 playlist_id) | ||||
|             medias = [] | ||||
|             for video in media_asset_page.get('videos', {}).values(): | ||||
|                 medias.extend(video.values()) | ||||
| 
 | ||||
|         entries = [] | ||||
|         for num, media_meta in enumerate(medias, start=1): | ||||
|             formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) | ||||
|             if not formats: | ||||
|                 continue | ||||
|             self._sort_formats(formats) | ||||
| 
 | ||||
|             video_id = media_meta.get('externalId') | ||||
|             if not video_id: | ||||
|                 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) | ||||
| 
 | ||||
|             title = media_meta.get('caption') | ||||
|             if not title: | ||||
|                 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) | ||||
| 
 | ||||
|             duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) | ||||
| 
 | ||||
|             images = [] | ||||
|             for image in media_meta.get('images', {}).values(): | ||||
|                 images.extend(image.values()) | ||||
|             if 'image' in media_meta: | ||||
|                 images.append(media_meta['image']) | ||||
| 
 | ||||
|             thumbnails = [{ | ||||
|                 'url': image.get('href'), | ||||
|                 'width': int_or_none(image.get('width')), | ||||
|                 'height': int_or_none(image.get('height')), | ||||
|             } for image in images] | ||||
| 
 | ||||
|             entries.append({ | ||||
|                 'id': video_id, | ||||
|                 'title': title, | ||||
|                 'thumbnails': thumbnails, | ||||
|                 'duration': duration, | ||||
|                 'timestamp': timestamp, | ||||
|                 'formats': formats, | ||||
|                 'subtitles': subtitles, | ||||
|             }) | ||||
| 
 | ||||
|         if len(ret) > 0: | ||||
|             return self.playlist_result(ret, list_id, list_title) | ||||
|         raise ExtractorError('No video found', expected=True) | ||||
|         return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) | ||||
|  | ||||
		Loading…
	
	
			
			x
			
			
		
	
		Reference in New Issue
	
	Block a user