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.',
64 'skip_download': True,
68 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
72 'title': 'The Man in Black: Series 3: The Printed Name',
73 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
78 'skip_download': True,
80 'skip': 'Episode is no longer available on BBC iPlayer Radio',
83 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
87 'title': 'The Voice UK: Series 3: Blind Auditions 5',
88 '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.',
93 'skip_download': True,
95 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
98 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
102 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
103 'description': '2. Invasion',
108 'skip_download': True,
110 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
112 'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
116 'title': 'Pete Tong, The Essential New Tune Special',
117 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
122 'skip_download': True,
124 'skip': 'Episode is no longer available on BBC iPlayer Radio',
126 'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
131 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
132 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
137 'skip_download': True,
140 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
145 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
146 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
151 'skip_download': True,
154 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
158 'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
159 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
164 'skip_download': True,
166 'skip': 'geolocation',
168 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
172 '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.',
173 'title': 'Royal Academy Summer Exhibition',
178 'skip_download': True,
180 'skip': 'geolocation',
182 # iptv-all mediaset fails with geolocation however there is no geo restriction
183 # for this programme at all
184 'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
188 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
189 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
193 'skip_download': True,
195 'skip': 'Now it\'s really geo-restricted',
197 # compact player (https://github.com/rg3/youtube-dl/issues/8147)
198 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
202 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
203 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
207 'skip_download': True,
210 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
211 'only_matching': True,
213 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
214 'only_matching': True,
216 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
217 'only_matching': True,
219 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
220 'only_matching': True,
224 class MediaSelectionError(Exception):
225 def __init__(self, id):
228 def _extract_asx_playlist(self, connection, programme_id):
229 asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
230 return [ref.get('href') for ref in asx.findall('./Entry/ref')]
232 def _extract_items(self, playlist):
233 return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
235 def _findall_ns(self, element, xpath):
237 for ns in self._NAMESPACES:
238 elements.extend(element.findall(xpath % ns))
241 def _extract_medias(self, media_selection):
242 error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
244 media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
245 if error is not None:
246 raise BBCCoUkIE.MediaSelectionError(error.get('id'))
247 return self._findall_ns(media_selection, './{%s}media')
249 def _extract_connections(self, media):
250 return self._findall_ns(media, './{%s}connection')
252 def _get_subtitles(self, media, programme_id):
254 for connection in self._extract_connections(media):
255 captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
256 lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
259 'url': connection.get('href'),
265 def _raise_extractor_error(self, media_selection_error):
266 raise ExtractorError(
267 '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
270 def _download_media_selector(self, programme_id):
271 last_exception = None
272 for mediaselector_url in self._MEDIASELECTOR_URLS:
274 return self._download_media_selector_url(
275 mediaselector_url % programme_id, programme_id)
276 except BBCCoUkIE.MediaSelectionError as e:
277 if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
280 self._raise_extractor_error(e)
281 self._raise_extractor_error(last_exception)
283 def _download_media_selector_url(self, url, programme_id=None):
285 media_selection = self._download_xml(
286 url, programme_id, 'Downloading media selection XML')
287 except ExtractorError as ee:
288 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
289 media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
292 return self._process_media_selector(media_selection, programme_id)
294 def _process_media_selector(self, media_selection, programme_id):
298 for media in self._extract_medias(media_selection):
299 kind = media.get('kind')
300 if kind in ('video', 'audio'):
301 bitrate = int_or_none(media.get('bitrate'))
302 encoding = media.get('encoding')
303 service = media.get('service')
304 width = int_or_none(media.get('width'))
305 height = int_or_none(media.get('height'))
306 file_size = int_or_none(media.get('media_file_size'))
307 for connection in self._extract_connections(media):
308 conn_kind = connection.get('kind')
309 protocol = connection.get('protocol')
310 supplier = connection.get('supplier')
311 href = connection.get('href')
312 transfer_format = connection.get('transferFormat')
313 format_id = supplier or conn_kind or protocol
315 format_id = '%s_%s' % (service, format_id)
317 if supplier == 'asx':
318 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
321 'format_id': 'ref%s_%s' % (i, format_id),
323 elif transfer_format == 'dash':
324 formats.extend(self._extract_mpd_formats(
325 href, programme_id, mpd_id=format_id, fatal=False))
326 elif transfer_format == 'hls':
327 formats.extend(self._extract_m3u8_formats(
328 href, programme_id, ext='mp4', entry_protocol='m3u8_native',
329 m3u8_id=format_id, fatal=False))
330 elif transfer_format == 'hds':
331 formats.extend(self._extract_f4m_formats(
332 href, programme_id, f4m_id=format_id, fatal=False))
335 'format_id': format_id,
336 'filesize': file_size,
351 if protocol == 'http':
356 elif protocol == 'rtmp':
357 application = connection.get('application', 'ondemand')
358 auth_string = connection.get('authString')
359 identifier = connection.get('identifier')
360 server = connection.get('server')
362 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
363 'play_path': identifier,
364 'app': '%s?%s' % (application, auth_string),
365 'page_url': 'http://www.bbc.co.uk',
366 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
371 elif kind == 'captions':
372 subtitles = self.extract_subtitles(media, programme_id)
373 return formats, subtitles
375 def _download_playlist(self, playlist_id):
377 playlist = self._download_json(
378 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
379 playlist_id, 'Downloading playlist JSON')
381 version = playlist.get('defaultAvailableVersion')
383 smp_config = version['smpConfig']
384 title = smp_config['title']
385 description = smp_config['summary']
386 for item in smp_config['items']:
388 if kind != 'programme' and kind != 'radioProgramme':
390 programme_id = item.get('vpid')
391 duration = int_or_none(item.get('duration'))
392 formats, subtitles = self._download_media_selector(programme_id)
393 return programme_id, title, description, duration, formats, subtitles
394 except ExtractorError as ee:
395 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
398 # fallback to legacy playlist
399 return self._process_legacy_playlist(playlist_id)
401 def _process_legacy_playlist_url(self, url, display_id):
402 playlist = self._download_legacy_playlist_url(url, display_id)
403 return self._extract_from_legacy_playlist(playlist, display_id)
405 def _process_legacy_playlist(self, playlist_id):
406 return self._process_legacy_playlist_url(
407 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
409 def _download_legacy_playlist_url(self, url, playlist_id=None):
410 return self._download_xml(
411 url, playlist_id, 'Downloading legacy playlist XML')
413 def _extract_from_legacy_playlist(self, playlist, playlist_id):
414 no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
415 if no_items is not None:
416 reason = no_items.get('reason')
417 if reason == 'preAvailability':
418 msg = 'Episode %s is not yet available' % playlist_id
419 elif reason == 'postAvailability':
420 msg = 'Episode %s is no longer available' % playlist_id
421 elif reason == 'noMedia':
422 msg = 'Episode %s is not currently available' % playlist_id
424 msg = 'Episode %s is not available: %s' % (playlist_id, reason)
425 raise ExtractorError(msg, expected=True)
427 for item in self._extract_items(playlist):
428 kind = item.get('kind')
429 if kind != 'programme' and kind != 'radioProgramme':
431 title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
432 description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
433 description = description_el.text if description_el is not None else None
435 def get_programme_id(item):
436 def get_from_attributes(item):
437 for p in('identifier', 'group'):
439 if value and re.match(r'^[pb][\da-z]{7}$', value):
441 get_from_attributes(item)
442 mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
443 if mediator is not None:
444 return get_from_attributes(mediator)
446 programme_id = get_programme_id(item)
447 duration = int_or_none(item.get('duration'))
450 formats, subtitles = self._download_media_selector(programme_id)
452 formats, subtitles = self._process_media_selector(item, playlist_id)
453 programme_id = playlist_id
455 return programme_id, title, description, duration, formats, subtitles
457 def _real_extract(self, url):
458 group_id = self._match_id(url)
460 webpage = self._download_webpage(url, group_id, 'Downloading video page')
465 tviplayer = self._search_regex(
466 r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
467 webpage, 'player', default=None)
470 player = self._parse_json(tviplayer, group_id).get('player', {})
471 duration = int_or_none(player.get('duration'))
472 programme_id = player.get('vpid')
475 programme_id = self._search_regex(
476 r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
479 formats, subtitles = self._download_media_selector(programme_id)
480 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
481 (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
482 r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
483 description = self._search_regex(
484 (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
485 r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
486 webpage, 'description', default=None)
488 description = self._html_search_meta('description', webpage)
490 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
492 self._sort_formats(formats)
497 'description': description,
498 'thumbnail': self._og_search_thumbnail(webpage, default=None),
499 'duration': duration,
501 'subtitles': subtitles,
505 class BBCIE(BBCCoUkIE):
508 _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
510 _MEDIASELECTOR_URLS = [
511 # Provides HQ HLS streams but fails with geolocation in some cases when it's
512 # even not geo restricted at all
513 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
514 # Provides more formats, namely direct mp4 links, but fails on some videos with
515 # notukerror for non UK (?) users (e.g.
516 # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
517 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
518 # Provides fewer formats, but works everywhere for everybody (hopefully)
519 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
523 # article with multiple videos embedded with data-playable containing vpids
524 'url': 'http://www.bbc.com/news/world-europe-32668511',
526 'id': 'world-europe-32668511',
527 'title': 'Russia stages massive WW2 parade despite Western boycott',
528 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
532 # article with multiple videos embedded with data-playable (more videos)
533 'url': 'http://www.bbc.com/news/business-28299555',
535 'id': 'business-28299555',
536 'title': 'Farnborough Airshow: Video highlights',
537 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
542 # article with multiple videos embedded with `new SMP()`
544 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
546 'id': '3662a707-0af9-3149-963f-47bea720b460',
549 'playlist_count': 18,
551 # single video embedded with data-playable containing vpid
552 'url': 'http://www.bbc.com/news/world-europe-32041533',
556 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
557 'description': 'md5:2868290467291b37feda7863f7a83f54',
559 'timestamp': 1427219242,
560 'upload_date': '20150324',
564 'skip_download': True,
567 # article with single video embedded with data-playable containing XML playlist
568 # with direct video links as progressiveDownloadUrl (for now these are extracted)
569 # and playlist with f4m and m3u8 as streamingUrl
570 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
572 'id': '150615_telabyad_kentin_cogu',
574 'title': "Tel Abyad'da IŞİD bayrağı indirildi YPG bayrağı çekildi",
575 'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
576 'timestamp': 1434397334,
577 'upload_date': '20150615',
580 'skip_download': True,
583 # single video embedded with data-playable containing XML playlists (regional section)
584 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
586 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
588 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
589 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
590 'timestamp': 1434713142,
591 'upload_date': '20150619',
594 'skip_download': True,
597 # single video from video playlist embedded with vxp-playlist-data JSON
598 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
602 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
604 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
607 'skip_download': True,
610 # single video story with digitalData
611 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
615 'title': 'Sri Lanka’s spicy secret',
616 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
617 'timestamp': 1437674293,
618 'upload_date': '20150723',
622 'skip_download': True,
625 # single video story without digitalData
626 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
630 'title': 'Hyundai Santa Fe Sport: Rock star',
631 'description': 'md5:b042a26142c4154a6e472933cf20793d',
632 'timestamp': 1415867444,
633 'upload_date': '20141113',
637 'skip_download': True,
640 # single video with playlist.sxml URL in playlist param
641 'url': 'http://www.bbc.com/sport/0/football/33653409',
645 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
646 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
651 'skip_download': True,
654 # article with multiple videos embedded with playlist.sxml in playlist param
655 'url': 'http://www.bbc.com/sport/0/football/34475836',
658 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
659 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
663 # school report article with single video
664 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
667 'title': 'School which breaks down barriers in Jerusalem',
671 # single video with playlist URL from weather section
672 'url': 'http://www.bbc.com/weather/features/33601775',
673 'only_matching': True,
675 # custom redirection to www.bbc.com
676 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
677 'only_matching': True,
679 # single video article embedded with data-media-vpid
680 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
681 'only_matching': True,
685 def suitable(cls, url):
686 EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
687 return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
688 else super(BBCIE, cls).suitable(url))
690 def _extract_from_media_meta(self, media_meta, video_id):
691 # Direct links to media in media metadata (e.g.
692 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
693 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
694 source_files = media_meta.get('sourceFiles')
698 'format_id': format_id,
699 'ext': f.get('encoding'),
700 'tbr': float_or_none(f.get('bitrate'), 1000),
701 'filesize': int_or_none(f.get('filesize')),
702 } for format_id, f in source_files.items() if f.get('url')], []
704 programme_id = media_meta.get('externalId')
706 return self._download_media_selector(programme_id)
708 # Process playlist.sxml as legacy playlist
709 href = media_meta.get('href')
711 playlist = self._download_legacy_playlist_url(href)
712 _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
713 return formats, subtitles
717 def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
718 programme_id, title, description, duration, formats, subtitles = \
719 self._process_legacy_playlist_url(url, playlist_id)
720 self._sort_formats(formats)
724 'description': description,
725 'duration': duration,
726 'timestamp': timestamp,
728 'subtitles': subtitles,
731 def _real_extract(self, url):
732 playlist_id = self._match_id(url)
734 webpage = self._download_webpage(url, playlist_id)
736 json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
737 timestamp = json_ld_info.get('timestamp')
739 playlist_title = json_ld_info.get('title')
740 if not playlist_title:
741 playlist_title = self._og_search_title(
742 webpage, default=None) or self._html_search_regex(
743 r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
745 playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
747 playlist_description = json_ld_info.get(
748 'description') or self._og_search_description(webpage, default=None)
751 timestamp = parse_iso8601(self._search_regex(
752 [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
753 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
754 r'"datePublished":\s*"([^"]+)'],
755 webpage, 'date', default=None))
759 # article with multiple videos embedded with playlist.sxml (e.g.
760 # http://www.bbc.com/sport/0/football/34475836)
761 playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
762 playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
765 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
766 for playlist_url in playlists]
768 # news article with multiple videos embedded with data-playable
769 data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
771 for _, data_playable_json in data_playables:
772 data_playable = self._parse_json(
773 unescapeHTML(data_playable_json), playlist_id, fatal=False)
774 if not data_playable:
776 settings = data_playable.get('settings', {})
778 # data-playable with video vpid in settings.playlistObject.items (e.g.
779 # http://www.bbc.com/news/world-us-canada-34473351)
780 playlist_object = settings.get('playlistObject', {})
782 items = playlist_object.get('items')
783 if items and isinstance(items, list):
784 title = playlist_object['title']
785 description = playlist_object.get('summary')
786 duration = int_or_none(items[0].get('duration'))
787 programme_id = items[0].get('vpid')
788 formats, subtitles = self._download_media_selector(programme_id)
789 self._sort_formats(formats)
793 'description': description,
794 'timestamp': timestamp,
795 'duration': duration,
797 'subtitles': subtitles,
800 # data-playable without vpid but with a playlist.sxml URLs
801 # in otherSettings.playlist (e.g.
802 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
803 playlist = data_playable.get('otherSettings', {}).get('playlist', {})
806 for key in ('streaming', 'progressiveDownload'):
807 playlist_url = playlist.get('%sUrl' % key)
811 info = self._extract_from_playlist_sxml(
812 playlist_url, playlist_id, timestamp)
816 entry['title'] = info['title']
817 entry['formats'].extend(info['formats'])
818 except Exception as e:
819 # Some playlist URL may fail with 500, at the same time
820 # the other one may work fine (e.g.
821 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
822 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
826 self._sort_formats(entry['formats'])
827 entries.append(entry)
830 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
832 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
833 programme_id = self._search_regex(
834 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
835 r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
836 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
837 webpage, 'vpid', default=None)
840 formats, subtitles = self._download_media_selector(programme_id)
841 self._sort_formats(formats)
842 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
843 digital_data = self._parse_json(
845 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
846 programme_id, fatal=False)
847 page_info = digital_data.get('page', {}).get('pageInfo', {})
848 title = page_info.get('pageName') or self._og_search_title(webpage)
849 description = page_info.get('description') or self._og_search_description(webpage)
850 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
854 'description': description,
855 'timestamp': timestamp,
857 'subtitles': subtitles,
860 def extract_all(pattern):
861 return list(filter(None, map(
862 lambda s: self._parse_json(s, playlist_id, fatal=False),
863 re.findall(pattern, webpage))))
865 # Multiple video article (e.g.
866 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
867 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
869 for match in extract_all(r'new\s+SMP\(({.+?})\)'):
870 embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
871 if embed_url and re.match(EMBED_URL, embed_url):
872 entries.append(embed_url)
873 entries.extend(re.findall(
874 r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
876 return self.playlist_result(
877 [self.url_result(entry, 'BBCCoUk') for entry in entries],
878 playlist_id, playlist_title, playlist_description)
880 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
881 medias = extract_all(r"data-media-meta='({[^']+})'")
884 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
885 media_asset = self._search_regex(
886 r'mediaAssetPage\.init\(\s*({.+?}), "/',
887 webpage, 'media asset', default=None)
889 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
891 for video in media_asset_page.get('videos', {}).values():
892 medias.extend(video.values())
895 # Multiple video playlist with single `now playing` entry (e.g.
896 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
897 vxp_playlist = self._parse_json(
899 r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
900 webpage, 'playlist data'),
903 for item in vxp_playlist:
904 media = item.get('media')
907 playlist_medias.append(media)
908 # Download single video if found media with asset id matching the video id from URL
909 if item.get('advert', {}).get('assetId') == playlist_id:
912 # Fallback to the whole playlist
914 medias = playlist_medias
917 for num, media_meta in enumerate(medias, start=1):
918 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
921 self._sort_formats(formats)
923 video_id = media_meta.get('externalId')
925 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
927 title = media_meta.get('caption')
929 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
931 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
934 for image in media_meta.get('images', {}).values():
935 images.extend(image.values())
936 if 'image' in media_meta:
937 images.append(media_meta['image'])
940 'url': image.get('href'),
941 'width': int_or_none(image.get('width')),
942 'height': int_or_none(image.get('height')),
943 } for image in images]
948 'thumbnails': thumbnails,
949 'duration': duration,
950 'timestamp': timestamp,
952 'subtitles': subtitles,
955 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
958 class BBCCoUkArticleIE(InfoExtractor):
959 _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
960 IE_NAME = 'bbc.co.uk:article'
961 IE_DESC = 'BBC articles'
964 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
966 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
967 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
968 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
971 'add_ie': ['BBCCoUk'],
974 def _real_extract(self, url):
975 playlist_id = self._match_id(url)
977 webpage = self._download_webpage(url, playlist_id)
979 title = self._og_search_title(webpage)
980 description = self._og_search_description(webpage).strip()
982 entries = [self.url_result(programme_url) for programme_url in re.findall(
983 r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
985 return self.playlist_result(entries, playlist_id, title, description)
988 class BBCCoUkPlaylistBaseIE(InfoExtractor):
989 def _real_extract(self, url):
990 playlist_id = self._match_id(url)
992 webpage = self._download_webpage(url, playlist_id)
995 self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
996 for video_id in re.findall(
997 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
999 title, description = self._extract_title_and_description(webpage)
1001 return self.playlist_result(entries, playlist_id, title, description)
1004 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
1005 IE_NAME = 'bbc.co.uk:iplayer:playlist'
1006 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
1007 _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
1008 _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
1010 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
1013 'title': 'The Disappearance',
1014 'description': 'French thriller serial about a missing teenager.',
1016 'playlist_mincount': 6,
1017 'skip': 'This programme is not currently available on BBC iPlayer',
1019 # Available for over a year unlike 30 days for most other programmes
1020 'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
1023 'title': 'Bohemian Icons',
1024 'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
1026 'playlist_mincount': 10,
1029 def _extract_title_and_description(self, webpage):
1030 title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
1031 description = self._search_regex(
1032 r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
1033 webpage, 'description', fatal=False, group='value')
1034 return title, description
1037 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1038 IE_NAME = 'bbc.co.uk:playlist'
1039 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
1040 _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
1041 _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
1043 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1046 'title': 'The Disappearance - Clips - BBC Four',
1047 'description': 'French thriller serial about a missing teenager.',
1049 'playlist_mincount': 7,
1051 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1052 'only_matching': True,
1054 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1055 'only_matching': True,
1057 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1058 'only_matching': True,
1061 def _extract_title_and_description(self, webpage):
1062 title = self._og_search_title(webpage, fatal=False)
1063 description = self._og_search_description(webpage)
1064 return title, description