X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/03342304420e5daeb428ffdcc7bbd2bbfecfa61a..fe979149c83b5a935f7d28baf75848a9137316fd:/youtube_dl/extractor/bbc.py diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 9d0dfb9..4b3cd8c 100644 --- a/youtube_dl/extractor/bbc.py +++ b/youtube_dl/extractor/bbc.py @@ -10,7 +10,6 @@ from ..utils import ( int_or_none, parse_duration, parse_iso8601, - remove_end, unescapeHTML, ) from ..compat import ( @@ -32,7 +31,7 @@ class BBCCoUkIE(InfoExtractor): music/clips[/#]| radio/player/ ) - (?P%s) + (?P%s)(?!/(?:episodes|broadcasts|clips)) ''' % _ID_REGEX _MEDIASELECTOR_URLS = [ @@ -193,6 +192,7 @@ class BBCCoUkIE(InfoExtractor): # rtmp download 'skip_download': True, }, + 'skip': 'Now it\'s really geo-restricted', }, { # compact player (https://github.com/rg3/youtube-dl/issues/8147) 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', @@ -329,6 +329,7 @@ class BBCCoUkIE(InfoExtractor): 'format_id': '%s_%s' % (service, format['format_id']), 'abr': abr, 'acodec': acodec, + 'vcodec': 'none', }) formats.extend(conn_formats) return formats @@ -561,7 +562,7 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', 'info_dict': { 'id': '3662a707-0af9-3149-963f-47bea720b460', - 'title': 'BBC Blogs - Adam Curtis - BUGGER', + 'title': 'BUGGER', }, 'playlist_count': 18, }, { @@ -670,9 +671,18 @@ class BBCIE(BBCCoUkIE): 'url': 'http://www.bbc.com/sport/0/football/34475836', 'info_dict': { 'id': '34475836', - 'title': 'What Liverpool can expect from Klopp', + 'title': 'Jurgen Klopp: Furious football from a witty and winning coach', + 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.', }, 'playlist_count': 3, + }, { + # school report article with single video + 'url': 'http://www.bbc.co.uk/schoolreport/35744779', + 'info_dict': { + 'id': '35744779', + 'title': 'School which breaks down barriers in Jerusalem', + }, + 'playlist_count': 1, }, { # single video with playlist URL from weather section 'url': 'http://www.bbc.com/weather/features/33601775', @@ -681,11 +691,17 @@ class BBCIE(BBCCoUkIE): # custom redirection to www.bbc.com 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', 'only_matching': True, + }, { + # single video article embedded with data-media-vpid + 'url': 'http://www.bbc.co.uk/sport/rowing/35908187', + 'only_matching': True, }] @classmethod def suitable(cls, url): - return False if BBCCoUkIE.suitable(url) or BBCCoUkArticleIE.suitable(url) else super(BBCIE, cls).suitable(url) + EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE) + return (False if any(ie.suitable(url) for ie in EXCLUDE_IE) + else super(BBCIE, cls).suitable(url)) def _extract_from_media_meta(self, media_meta, video_id): # Direct links to media in media metadata (e.g. @@ -735,8 +751,17 @@ class BBCIE(BBCCoUkIE): json_ld_info = self._search_json_ld(webpage, playlist_id, default=None) timestamp = json_ld_info.get('timestamp') + playlist_title = json_ld_info.get('title') - playlist_description = json_ld_info.get('description') + if not playlist_title: + playlist_title = self._og_search_title( + webpage, default=None) or self._html_search_regex( + r'(.+?)', webpage, 'playlist title', default=None) + if playlist_title: + playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip() + + playlist_description = json_ld_info.get( + 'description') or self._og_search_description(webpage, default=None) if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -797,13 +822,11 @@ class BBCIE(BBCCoUkIE): playlist.get('progressiveDownloadUrl'), playlist_id, timestamp)) if entries: - playlist_title = playlist_title or remove_end(self._og_search_title(webpage), ' - BBC News') - playlist_description = playlist_description or self._og_search_description(webpage, default=None) return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) # 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="(%s)"' % self._ID_REGEX, + [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, r']+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX, r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX], webpage, 'vpid', default=None) @@ -829,10 +852,6 @@ class BBCIE(BBCCoUkIE): 'subtitles': subtitles, } - playlist_title = self._html_search_regex( - r'(.*?)(?:\s*-\s*BBC [^ ]+)?', webpage, 'playlist title') - playlist_description = self._og_search_description(webpage, default=None) - def extract_all(pattern): return list(filter(None, map( lambda s: self._parse_json(s, playlist_id, fatal=False), @@ -932,7 +951,7 @@ class BBCIE(BBCCoUkIE): class BBCCoUkArticleIE(InfoExtractor): - _VALID_URL = 'http://www.bbc.co.uk/programmes/articles/(?P[a-zA-Z0-9]+)' + _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P[a-zA-Z0-9]+)' IE_NAME = 'bbc.co.uk:article' IE_DESC = 'BBC articles' @@ -959,3 +978,72 @@ class BBCCoUkArticleIE(InfoExtractor): r']+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkPlaylistBaseIE(InfoExtractor): + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key()) + for video_id in re.findall( + self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)] + + title, description = self._extract_title_and_description(webpage) + + return self.playlist_result(entries, playlist_id, title, description) + + +class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:iplayer:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P%s)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s' + _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)' + _TEST = { + 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 6, + } + + def _extract_title_and_description(self, webpage): + title = self._search_regex(r'

([^<]+)

', webpage, 'title', fatal=False) + description = self._search_regex( + r']+class=(["\'])subtitle\1[^>]*>(?P[^<]+)

', + webpage, 'description', fatal=False, group='value') + return title, description + + +class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE): + IE_NAME = 'bbc.co.uk:playlist' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX + _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s' + _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)' + _TESTS = [{ + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'info_dict': { + 'id': 'b05rcz9v', + 'title': 'The Disappearance - Clips - BBC Four', + 'description': 'French thriller serial about a missing teenager.', + }, + 'playlist_mincount': 7, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player', + 'only_matching': True, + }] + + def _extract_title_and_description(self, webpage): + title = self._og_search_title(webpage, fatal=False) + description = self._og_search_description(webpage) + return title, description