X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9ed7fe4fe4c445eb7d9f3197bb300d0db8f1807a..d1d8237037fb87a57bd1d073c3b9e642d4a75016:/youtube_dl/extractor/bbc.py diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py index 33b296e..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 ( @@ -22,7 +21,18 @@ from ..compat import ( class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:programmes/(?!articles/)|iplayer(?:/[^/]+)?/(?:episode/|playlist/))|music/clips[/#])(?P[\da-z]{8})' + _ID_REGEX = r'[pb][\da-z]{7}' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?bbc\.co\.uk/ + (?: + programmes/(?!articles/)| + iplayer(?:/[^/]+)?/(?:episode/|playlist/)| + music/clips[/#]| + radio/player/ + ) + (?P%s)(?!/(?:episodes|broadcasts|clips)) + ''' % _ID_REGEX _MEDIASELECTOR_URLS = [ # Provides HQ HLS streams with even better quality that pc mediaset but fails @@ -46,9 +56,8 @@ class BBCCoUkIE(InfoExtractor): 'info_dict': { 'id': 'b039d07m', 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', + 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, }, 'params': { # rtmp download @@ -76,7 +85,7 @@ class BBCCoUkIE(InfoExtractor): 'id': 'b00yng1d', 'ext': 'flv', 'title': 'The Voice UK: Series 3: Blind Auditions 5', - 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.", + 'description': 'Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.', 'duration': 5100, }, 'params': { @@ -111,16 +120,17 @@ class BBCCoUkIE(InfoExtractor): 'params': { # rtmp download 'skip_download': True, - } + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', }, { - 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', + 'url': 'http://www.bbc.co.uk/music/clips/p022h44b', 'note': 'Audio', 'info_dict': { - 'id': 'p02frcch', + 'id': 'p022h44j', 'ext': 'flv', - 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', - 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', - 'duration': 3507, + 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances', + 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.", + 'duration': 227, }, 'params': { # rtmp download @@ -171,13 +181,26 @@ class BBCCoUkIE(InfoExtractor): }, { # iptv-all mediaset fails with geolocation however there is no geo restriction # for this programme at all - 'url': 'http://www.bbc.co.uk/programmes/b06bp7lf', + 'url': 'http://www.bbc.co.uk/programmes/b06rkn85', 'info_dict': { - 'id': 'b06bp7kf', + 'id': 'b06rkms3', 'ext': 'flv', - 'title': "Annie Mac's Friday Night, B.Traits sits in for Annie", - 'description': 'B.Traits sits in for Annie Mac with a Mini-Mix from Disclosure.', - 'duration': 10800, + 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1", + 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!", + }, + 'params': { + # 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', + 'info_dict': { + 'id': 'p028bfkj', + 'ext': 'flv', + 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', + 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', }, 'params': { # rtmp download @@ -192,6 +215,9 @@ class BBCCoUkIE(InfoExtractor): }, { 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf', + 'only_matching': True, } ] @@ -222,11 +248,9 @@ class BBCCoUkIE(InfoExtractor): elif transfer_format == 'dash': pass elif transfer_format == 'hls': - m3u8_formats = self._extract_m3u8_formats( + formats.extend(self._extract_m3u8_formats( href, programme_id, ext='mp4', entry_protocol='m3u8_native', - m3u8_id=supplier, fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) + m3u8_id=supplier, fatal=False)) # Direct link else: formats.append({ @@ -305,6 +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 @@ -453,6 +478,7 @@ class BBCCoUkIE(InfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') programme_id = None + duration = None tviplayer = self._search_regex( r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', @@ -465,14 +491,19 @@ class BBCCoUkIE(InfoExtractor): if not programme_id: programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None) if programme_id: formats, subtitles = self._download_media_selector(programme_id) - title = self._og_search_title(webpage) + title = self._og_search_title(webpage, default=None) or self._html_search_regex( + (r']+id="parent-title"[^>]*>(.+?)', + r']+class="info"[^>]*>\s*

(.+?)

'), webpage, 'title') description = self._search_regex( - r'

([^<]+)

', - webpage, 'description', fatal=False) + (r'

([^<]+)

', + r']+class="info_+synopsis"[^>]*>([^<]+)'), + webpage, 'description', default=None) + if not description: + description = self._html_search_meta('description', webpage) else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) @@ -531,7 +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, }, { @@ -586,6 +617,7 @@ class BBCIE(BBCCoUkIE): 'ext': 'mp4', 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', 'duration': 56, + 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', }, 'params': { 'skip_download': True, @@ -639,9 +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', @@ -650,11 +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. @@ -702,19 +749,19 @@ class BBCIE(BBCCoUkIE): webpage = self._download_webpage(url, playlist_id) - timestamp = None - playlist_title = None - playlist_description = None + 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') + 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() - ld = self._parse_json( - self._search_regex( - r'(?s)', - webpage, 'ld json', default='{}'), - playlist_id, fatal=False) - if ld: - timestamp = parse_iso8601(ld.get('datePublished')) - playlist_title = ld.get('headline') - playlist_description = ld.get('articleBody') + playlist_description = json_ld_info.get( + 'description') or self._og_search_description(webpage, default=None) if not timestamp: timestamp = parse_iso8601(self._search_regex( @@ -728,6 +775,7 @@ class BBCIE(BBCCoUkIE): # article with multiple videos embedded with playlist.sxml (e.g. # http://www.bbc.com/sport/0/football/34475836) playlists = re.findall(r']+name="playlist"[^>]+value="([^"]+)"', webpage) + playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) if playlists: entries = [ self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) @@ -774,14 +822,13 @@ 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="([\da-z]{8})"', - r']+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], + [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) if programme_id: @@ -805,10 +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), @@ -816,7 +859,7 @@ class BBCIE(BBCCoUkIE): # Multiple video article (e.g. # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) - EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' + EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX entries = [] for match in extract_all(r'new\s+SMP\(({.+?})\)'): embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') @@ -908,7 +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' @@ -935,3 +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