2 from __future__ import unicode_literals
6 from .common import InfoExtractor
15 from ..compat import (
16 compat_etree_fromstring,
21 class BBCCoUkIE(InfoExtractor):
23 IE_DESC = 'BBC iPlayer'
24 _ID_REGEX = r'[pb][\da-z]{7}'
27 (?:www\.)?bbc\.co\.uk/
29 programmes/(?!articles/)|
30 iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
34 (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
37 _MEDIASELECTOR_URLS = [
38 # Provides HQ HLS streams with even better quality that pc mediaset but fails
39 # with geolocation in some cases when it's even not geo restricted at all (e.g.
40 # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
41 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
42 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
45 _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
46 _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
55 'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
59 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4',
60 'description': 'The Canadian poet and songwriter reflects on his musical career.',
63 'skip_download': True,
67 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
71 'title': 'The Man in Black: Series 3: The Printed Name',
72 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
77 'skip_download': True,
79 'skip': 'Episode is no longer available on BBC iPlayer Radio',
82 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
86 'title': 'The Voice UK: Series 3: Blind Auditions 5',
87 '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.',
92 'skip_download': True,
94 'skip': 'this episode is not currently available',
97 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
101 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
102 'description': '2. Invasion',
107 'skip_download': True,
109 'skip': 'this episode is not currently available',
111 'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
115 'title': 'Pete Tong, The Essential New Tune Special',
116 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
121 'skip_download': True,
123 'skip': 'Episode is no longer available on BBC iPlayer Radio',
125 'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
130 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
131 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
135 'skip_download': True,
138 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
143 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
144 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
148 'skip_download': True,
151 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
155 'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
156 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
161 'skip_download': True,
163 'skip': 'this episode is not currently available',
165 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
169 'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.',
170 'title': 'Royal Academy Summer Exhibition',
175 'skip_download': True,
177 'skip': 'this episode is not currently available',
179 # iptv-all mediaset fails with geolocation however there is no geo restriction
180 # for this programme at all
181 'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
185 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
186 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
190 'skip_download': True,
192 'skip': 'this episode is not currently available on BBC iPlayer Radio',
194 # compact player (https://github.com/rg3/youtube-dl/issues/8147)
195 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
199 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
200 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
203 'skip_download': True,
206 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
207 'only_matching': True,
209 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
210 'only_matching': True,
212 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
213 'only_matching': True,
215 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
216 'only_matching': True,
220 class MediaSelectionError(Exception):
221 def __init__(self, id):
224 def _extract_asx_playlist(self, connection, programme_id):
225 asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
226 return [ref.get('href') for ref in asx.findall('./Entry/ref')]
228 def _extract_connection(self, connection, programme_id):
230 kind = connection.get('kind')
231 protocol = connection.get('protocol')
232 supplier = connection.get('supplier')
233 if protocol == 'http':
234 href = connection.get('href')
235 transfer_format = connection.get('transferFormat')
237 if supplier == 'asx':
238 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
241 'format_id': 'ref%s_%s' % (i, supplier),
243 # Skip DASH until supported
244 elif transfer_format == 'dash':
246 elif transfer_format == 'hls':
247 formats.extend(self._extract_m3u8_formats(
248 href, programme_id, 'mp4', 'm3u8_native',
249 m3u8_id=supplier, fatal=False))
254 'format_id': supplier or kind or protocol,
256 elif protocol == 'rtmp':
257 application = connection.get('application', 'ondemand')
258 auth_string = connection.get('authString')
259 identifier = connection.get('identifier')
260 server = connection.get('server')
262 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
263 'play_path': identifier,
264 'app': '%s?%s' % (application, auth_string),
265 'page_url': 'http://www.bbc.co.uk',
266 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
269 'format_id': supplier,
273 def _extract_items(self, playlist):
274 return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
276 def _findall_ns(self, element, xpath):
278 for ns in self._NAMESPACES:
279 elements.extend(element.findall(xpath % ns))
282 def _extract_medias(self, media_selection):
283 error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
285 media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
286 if error is not None:
287 raise BBCCoUkIE.MediaSelectionError(error.get('id'))
288 return self._findall_ns(media_selection, './{%s}media')
290 def _extract_connections(self, media):
291 return self._findall_ns(media, './{%s}connection')
293 def _extract_video(self, media, programme_id):
295 vbr = int_or_none(media.get('bitrate'))
296 vcodec = media.get('encoding')
297 service = media.get('service')
298 width = int_or_none(media.get('width'))
299 height = int_or_none(media.get('height'))
300 file_size = int_or_none(media.get('media_file_size'))
301 for connection in self._extract_connections(media):
302 conn_formats = self._extract_connection(connection, programme_id)
303 for format in conn_formats:
304 if format.get('protocol') != 'm3u8_native':
310 'filesize': file_size,
313 format['format_id'] = '%s_%s' % (service, format['format_id'])
314 formats.extend(conn_formats)
317 def _extract_audio(self, media, programme_id):
319 abr = int_or_none(media.get('bitrate'))
320 acodec = media.get('encoding')
321 service = media.get('service')
322 for connection in self._extract_connections(media):
323 conn_formats = self._extract_connection(connection, programme_id)
324 for format in conn_formats:
326 'format_id': '%s_%s' % (service, format['format_id']),
331 formats.extend(conn_formats)
334 def _get_subtitles(self, media, programme_id):
336 for connection in self._extract_connections(media):
337 captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
338 lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
341 'url': connection.get('href'),
347 def _raise_extractor_error(self, media_selection_error):
348 raise ExtractorError(
349 '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
352 def _download_media_selector(self, programme_id):
353 last_exception = None
354 for mediaselector_url in self._MEDIASELECTOR_URLS:
356 return self._download_media_selector_url(
357 mediaselector_url % programme_id, programme_id)
358 except BBCCoUkIE.MediaSelectionError as e:
359 if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
362 self._raise_extractor_error(e)
363 self._raise_extractor_error(last_exception)
365 def _download_media_selector_url(self, url, programme_id=None):
367 media_selection = self._download_xml(
368 url, programme_id, 'Downloading media selection XML')
369 except ExtractorError as ee:
370 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
371 media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
374 return self._process_media_selector(media_selection, programme_id)
376 def _process_media_selector(self, media_selection, programme_id):
380 for media in self._extract_medias(media_selection):
381 kind = media.get('kind')
383 formats.extend(self._extract_audio(media, programme_id))
384 elif kind == 'video':
385 formats.extend(self._extract_video(media, programme_id))
386 elif kind == 'captions':
387 subtitles = self.extract_subtitles(media, programme_id)
388 return formats, subtitles
390 def _download_playlist(self, playlist_id):
392 playlist = self._download_json(
393 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
394 playlist_id, 'Downloading playlist JSON')
396 version = playlist.get('defaultAvailableVersion')
398 smp_config = version['smpConfig']
399 title = smp_config['title']
400 description = smp_config['summary']
401 for item in smp_config['items']:
403 if kind != 'programme' and kind != 'radioProgramme':
405 programme_id = item.get('vpid')
406 duration = int_or_none(item.get('duration'))
407 formats, subtitles = self._download_media_selector(programme_id)
408 return programme_id, title, description, duration, formats, subtitles
409 except ExtractorError as ee:
410 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
413 # fallback to legacy playlist
414 return self._process_legacy_playlist(playlist_id)
416 def _process_legacy_playlist_url(self, url, display_id):
417 playlist = self._download_legacy_playlist_url(url, display_id)
418 return self._extract_from_legacy_playlist(playlist, display_id)
420 def _process_legacy_playlist(self, playlist_id):
421 return self._process_legacy_playlist_url(
422 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
424 def _download_legacy_playlist_url(self, url, playlist_id=None):
425 return self._download_xml(
426 url, playlist_id, 'Downloading legacy playlist XML')
428 def _extract_from_legacy_playlist(self, playlist, playlist_id):
429 no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
430 if no_items is not None:
431 reason = no_items.get('reason')
432 if reason == 'preAvailability':
433 msg = 'Episode %s is not yet available' % playlist_id
434 elif reason == 'postAvailability':
435 msg = 'Episode %s is no longer available' % playlist_id
436 elif reason == 'noMedia':
437 msg = 'Episode %s is not currently available' % playlist_id
439 msg = 'Episode %s is not available: %s' % (playlist_id, reason)
440 raise ExtractorError(msg, expected=True)
442 for item in self._extract_items(playlist):
443 kind = item.get('kind')
444 if kind != 'programme' and kind != 'radioProgramme':
446 title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
447 description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
448 description = description_el.text if description_el is not None else None
450 def get_programme_id(item):
451 def get_from_attributes(item):
452 for p in('identifier', 'group'):
454 if value and re.match(r'^[pb][\da-z]{7}$', value):
456 get_from_attributes(item)
457 mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
458 if mediator is not None:
459 return get_from_attributes(mediator)
461 programme_id = get_programme_id(item)
462 duration = int_or_none(item.get('duration'))
465 formats, subtitles = self._download_media_selector(programme_id)
467 formats, subtitles = self._process_media_selector(item, playlist_id)
468 programme_id = playlist_id
470 return programme_id, title, description, duration, formats, subtitles
472 def _real_extract(self, url):
473 group_id = self._match_id(url)
475 webpage = self._download_webpage(url, group_id, 'Downloading video page')
480 tviplayer = self._search_regex(
481 r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
482 webpage, 'player', default=None)
485 player = self._parse_json(tviplayer, group_id).get('player', {})
486 duration = int_or_none(player.get('duration'))
487 programme_id = player.get('vpid')
490 programme_id = self._search_regex(
491 r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
494 formats, subtitles = self._download_media_selector(programme_id)
495 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
496 (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
497 r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
498 description = self._search_regex(
499 (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
500 r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
501 webpage, 'description', default=None)
503 description = self._html_search_meta('description', webpage)
505 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
507 self._sort_formats(formats)
512 'description': description,
513 'thumbnail': self._og_search_thumbnail(webpage, default=None),
514 'duration': duration,
516 'subtitles': subtitles,
520 class BBCIE(BBCCoUkIE):
523 _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
525 _MEDIASELECTOR_URLS = [
526 # Provides HQ HLS streams but fails with geolocation in some cases when it's
527 # even not geo restricted at all
528 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
529 # Provides more formats, namely direct mp4 links, but fails on some videos with
530 # notukerror for non UK (?) users (e.g.
531 # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
532 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
533 # Provides fewer formats, but works everywhere for everybody (hopefully)
534 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
538 # article with multiple videos embedded with data-playable containing vpids
539 'url': 'http://www.bbc.com/news/world-europe-32668511',
541 'id': 'world-europe-32668511',
542 'title': 'Russia stages massive WW2 parade despite Western boycott',
543 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
547 # article with multiple videos embedded with data-playable (more videos)
548 'url': 'http://www.bbc.com/news/business-28299555',
550 'id': 'business-28299555',
551 'title': 'Farnborough Airshow: Video highlights',
552 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
557 # article with multiple videos embedded with `new SMP()`
559 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
561 'id': '3662a707-0af9-3149-963f-47bea720b460',
564 'playlist_count': 18,
566 # single video embedded with data-playable containing vpid
567 'url': 'http://www.bbc.com/news/world-europe-32041533',
571 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
572 'description': 'md5:2868290467291b37feda7863f7a83f54',
574 'timestamp': 1427219242,
575 'upload_date': '20150324',
579 'skip_download': True,
582 # article with single video embedded with data-playable containing XML playlist
583 # with direct video links as progressiveDownloadUrl (for now these are extracted)
584 # and playlist with f4m and m3u8 as streamingUrl
585 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
587 'id': '150615_telabyad_kentin_cogu',
589 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
590 'timestamp': 1434397334,
591 'upload_date': '20150615',
594 'skip_download': True,
597 # single video embedded with data-playable containing XML playlists (regional section)
598 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
600 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
602 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
603 'timestamp': 1434713142,
604 'upload_date': '20150619',
607 'skip_download': True,
610 # single video from video playlist embedded with vxp-playlist-data JSON
611 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
615 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
617 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
620 'skip_download': True,
623 # single video story with digitalData
624 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
628 'title': 'Sri Lanka’s spicy secret',
629 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
630 'timestamp': 1437674293,
631 'upload_date': '20150723',
635 'skip_download': True,
638 # single video story without digitalData
639 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
643 'title': 'Hyundai Santa Fe Sport: Rock star',
644 'description': 'md5:b042a26142c4154a6e472933cf20793d',
645 'timestamp': 1415867444,
646 'upload_date': '20141113',
650 'skip_download': True,
653 # single video with playlist.sxml URL in playlist param
654 'url': 'http://www.bbc.com/sport/0/football/33653409',
658 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
659 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
664 'skip_download': True,
667 # article with multiple videos embedded with playlist.sxml in playlist param
668 'url': 'http://www.bbc.com/sport/0/football/34475836',
671 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
672 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
676 # school report article with single video
677 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
680 'title': 'School which breaks down barriers in Jerusalem',
684 # single video with playlist URL from weather section
685 'url': 'http://www.bbc.com/weather/features/33601775',
686 'only_matching': True,
688 # custom redirection to www.bbc.com
689 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
690 'only_matching': True,
692 # single video article embedded with data-media-vpid
693 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
694 'only_matching': True,
698 def suitable(cls, url):
699 EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
700 return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
701 else super(BBCIE, cls).suitable(url))
703 def _extract_from_media_meta(self, media_meta, video_id):
704 # Direct links to media in media metadata (e.g.
705 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
706 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
707 source_files = media_meta.get('sourceFiles')
711 'format_id': format_id,
712 'ext': f.get('encoding'),
713 'tbr': float_or_none(f.get('bitrate'), 1000),
714 'filesize': int_or_none(f.get('filesize')),
715 } for format_id, f in source_files.items() if f.get('url')], []
717 programme_id = media_meta.get('externalId')
719 return self._download_media_selector(programme_id)
721 # Process playlist.sxml as legacy playlist
722 href = media_meta.get('href')
724 playlist = self._download_legacy_playlist_url(href)
725 _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
726 return formats, subtitles
730 def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
731 programme_id, title, description, duration, formats, subtitles = \
732 self._process_legacy_playlist_url(url, playlist_id)
733 self._sort_formats(formats)
737 'description': description,
738 'duration': duration,
739 'timestamp': timestamp,
741 'subtitles': subtitles,
744 def _real_extract(self, url):
745 playlist_id = self._match_id(url)
747 webpage = self._download_webpage(url, playlist_id)
749 json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
750 timestamp = json_ld_info.get('timestamp')
752 playlist_title = json_ld_info.get('title')
753 if not playlist_title:
754 playlist_title = self._og_search_title(
755 webpage, default=None) or self._html_search_regex(
756 r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
758 playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
760 playlist_description = json_ld_info.get(
761 'description') or self._og_search_description(webpage, default=None)
764 timestamp = parse_iso8601(self._search_regex(
765 [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
766 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
767 r'"datePublished":\s*"([^"]+)'],
768 webpage, 'date', default=None))
772 # article with multiple videos embedded with playlist.sxml (e.g.
773 # http://www.bbc.com/sport/0/football/34475836)
774 playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
775 playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
778 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
779 for playlist_url in playlists]
781 # news article with multiple videos embedded with data-playable
782 data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
784 for _, data_playable_json in data_playables:
785 data_playable = self._parse_json(
786 unescapeHTML(data_playable_json), playlist_id, fatal=False)
787 if not data_playable:
789 settings = data_playable.get('settings', {})
791 # data-playable with video vpid in settings.playlistObject.items (e.g.
792 # http://www.bbc.com/news/world-us-canada-34473351)
793 playlist_object = settings.get('playlistObject', {})
795 items = playlist_object.get('items')
796 if items and isinstance(items, list):
797 title = playlist_object['title']
798 description = playlist_object.get('summary')
799 duration = int_or_none(items[0].get('duration'))
800 programme_id = items[0].get('vpid')
801 formats, subtitles = self._download_media_selector(programme_id)
802 self._sort_formats(formats)
806 'description': description,
807 'timestamp': timestamp,
808 'duration': duration,
810 'subtitles': subtitles,
813 # data-playable without vpid but with a playlist.sxml URLs
814 # in otherSettings.playlist (e.g.
815 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
816 playlist = data_playable.get('otherSettings', {}).get('playlist', {})
818 entries.append(self._extract_from_playlist_sxml(
819 playlist.get('progressiveDownloadUrl'), playlist_id, timestamp))
822 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
824 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
825 programme_id = self._search_regex(
826 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
827 r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
828 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
829 webpage, 'vpid', default=None)
832 formats, subtitles = self._download_media_selector(programme_id)
833 self._sort_formats(formats)
834 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
835 digital_data = self._parse_json(
837 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
838 programme_id, fatal=False)
839 page_info = digital_data.get('page', {}).get('pageInfo', {})
840 title = page_info.get('pageName') or self._og_search_title(webpage)
841 description = page_info.get('description') or self._og_search_description(webpage)
842 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
846 'description': description,
847 'timestamp': timestamp,
849 'subtitles': subtitles,
852 def extract_all(pattern):
853 return list(filter(None, map(
854 lambda s: self._parse_json(s, playlist_id, fatal=False),
855 re.findall(pattern, webpage))))
857 # Multiple video article (e.g.
858 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
859 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
861 for match in extract_all(r'new\s+SMP\(({.+?})\)'):
862 embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
863 if embed_url and re.match(EMBED_URL, embed_url):
864 entries.append(embed_url)
865 entries.extend(re.findall(
866 r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
868 return self.playlist_result(
869 [self.url_result(entry, 'BBCCoUk') for entry in entries],
870 playlist_id, playlist_title, playlist_description)
872 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
873 medias = extract_all(r"data-media-meta='({[^']+})'")
876 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
877 media_asset = self._search_regex(
878 r'mediaAssetPage\.init\(\s*({.+?}), "/',
879 webpage, 'media asset', default=None)
881 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
883 for video in media_asset_page.get('videos', {}).values():
884 medias.extend(video.values())
887 # Multiple video playlist with single `now playing` entry (e.g.
888 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
889 vxp_playlist = self._parse_json(
891 r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
892 webpage, 'playlist data'),
895 for item in vxp_playlist:
896 media = item.get('media')
899 playlist_medias.append(media)
900 # Download single video if found media with asset id matching the video id from URL
901 if item.get('advert', {}).get('assetId') == playlist_id:
904 # Fallback to the whole playlist
906 medias = playlist_medias
909 for num, media_meta in enumerate(medias, start=1):
910 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
913 self._sort_formats(formats)
915 video_id = media_meta.get('externalId')
917 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
919 title = media_meta.get('caption')
921 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
923 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
926 for image in media_meta.get('images', {}).values():
927 images.extend(image.values())
928 if 'image' in media_meta:
929 images.append(media_meta['image'])
932 'url': image.get('href'),
933 'width': int_or_none(image.get('width')),
934 'height': int_or_none(image.get('height')),
935 } for image in images]
940 'thumbnails': thumbnails,
941 'duration': duration,
942 'timestamp': timestamp,
944 'subtitles': subtitles,
947 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
950 class BBCCoUkArticleIE(InfoExtractor):
951 _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
952 IE_NAME = 'bbc.co.uk:article'
953 IE_DESC = 'BBC articles'
956 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
958 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
959 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
960 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
963 'add_ie': ['BBCCoUk'],
966 def _real_extract(self, url):
967 playlist_id = self._match_id(url)
969 webpage = self._download_webpage(url, playlist_id)
971 title = self._og_search_title(webpage)
972 description = self._og_search_description(webpage).strip()
974 entries = [self.url_result(programme_url) for programme_url in re.findall(
975 r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
977 return self.playlist_result(entries, playlist_id, title, description)
980 class BBCCoUkPlaylistBaseIE(InfoExtractor):
981 def _real_extract(self, url):
982 playlist_id = self._match_id(url)
984 webpage = self._download_webpage(url, playlist_id)
987 self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
988 for video_id in re.findall(
989 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
991 title, description = self._extract_title_and_description(webpage)
993 return self.playlist_result(entries, playlist_id, title, description)
996 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
997 IE_NAME = 'bbc.co.uk:iplayer:playlist'
998 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/episodes/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
999 _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
1000 _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
1002 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
1005 'title': 'The Disappearance',
1006 'description': 'French thriller serial about a missing teenager.',
1008 'playlist_mincount': 6,
1011 def _extract_title_and_description(self, webpage):
1012 title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
1013 description = self._search_regex(
1014 r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
1015 webpage, 'description', fatal=False, group='value')
1016 return title, description
1019 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1020 IE_NAME = 'bbc.co.uk:playlist'
1021 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
1022 _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
1023 _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
1025 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1028 'title': 'The Disappearance - Clips - BBC Four',
1029 'description': 'French thriller serial about a missing teenager.',
1031 'playlist_mincount': 7,
1033 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1034 'only_matching': True,
1036 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1037 'only_matching': True,
1039 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1040 'only_matching': True,
1043 def _extract_title_and_description(self, webpage):
1044 title = self._og_search_title(webpage, fatal=False)
1045 description = self._og_search_description(webpage)
1046 return title, description