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):
299 for media in self._extract_medias(media_selection):
300 kind = media.get('kind')
301 if kind in ('video', 'audio'):
302 bitrate = int_or_none(media.get('bitrate'))
303 encoding = media.get('encoding')
304 service = media.get('service')
305 width = int_or_none(media.get('width'))
306 height = int_or_none(media.get('height'))
307 file_size = int_or_none(media.get('media_file_size'))
308 for connection in self._extract_connections(media):
309 href = connection.get('href')
314 conn_kind = connection.get('kind')
315 protocol = connection.get('protocol')
316 supplier = connection.get('supplier')
317 transfer_format = connection.get('transferFormat')
318 format_id = supplier or conn_kind or protocol
320 format_id = '%s_%s' % (service, format_id)
322 if supplier == 'asx':
323 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
326 'format_id': 'ref%s_%s' % (i, format_id),
328 elif transfer_format == 'dash':
329 formats.extend(self._extract_mpd_formats(
330 href, programme_id, mpd_id=format_id, fatal=False))
331 elif transfer_format == 'hls':
332 formats.extend(self._extract_m3u8_formats(
333 href, programme_id, ext='mp4', entry_protocol='m3u8_native',
334 m3u8_id=format_id, fatal=False))
335 elif transfer_format == 'hds':
336 formats.extend(self._extract_f4m_formats(
337 href, programme_id, f4m_id=format_id, fatal=False))
339 if not service and not supplier and bitrate:
340 format_id += '-%d' % bitrate
342 'format_id': format_id,
343 'filesize': file_size,
358 if protocol == 'http':
363 elif protocol == 'rtmp':
364 application = connection.get('application', 'ondemand')
365 auth_string = connection.get('authString')
366 identifier = connection.get('identifier')
367 server = connection.get('server')
369 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
370 'play_path': identifier,
371 'app': '%s?%s' % (application, auth_string),
372 'page_url': 'http://www.bbc.co.uk',
373 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
378 elif kind == 'captions':
379 subtitles = self.extract_subtitles(media, programme_id)
380 return formats, subtitles
382 def _download_playlist(self, playlist_id):
384 playlist = self._download_json(
385 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
386 playlist_id, 'Downloading playlist JSON')
388 version = playlist.get('defaultAvailableVersion')
390 smp_config = version['smpConfig']
391 title = smp_config['title']
392 description = smp_config['summary']
393 for item in smp_config['items']:
395 if kind != 'programme' and kind != 'radioProgramme':
397 programme_id = item.get('vpid')
398 duration = int_or_none(item.get('duration'))
399 formats, subtitles = self._download_media_selector(programme_id)
400 return programme_id, title, description, duration, formats, subtitles
401 except ExtractorError as ee:
402 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
405 # fallback to legacy playlist
406 return self._process_legacy_playlist(playlist_id)
408 def _process_legacy_playlist_url(self, url, display_id):
409 playlist = self._download_legacy_playlist_url(url, display_id)
410 return self._extract_from_legacy_playlist(playlist, display_id)
412 def _process_legacy_playlist(self, playlist_id):
413 return self._process_legacy_playlist_url(
414 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
416 def _download_legacy_playlist_url(self, url, playlist_id=None):
417 return self._download_xml(
418 url, playlist_id, 'Downloading legacy playlist XML')
420 def _extract_from_legacy_playlist(self, playlist, playlist_id):
421 no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
422 if no_items is not None:
423 reason = no_items.get('reason')
424 if reason == 'preAvailability':
425 msg = 'Episode %s is not yet available' % playlist_id
426 elif reason == 'postAvailability':
427 msg = 'Episode %s is no longer available' % playlist_id
428 elif reason == 'noMedia':
429 msg = 'Episode %s is not currently available' % playlist_id
431 msg = 'Episode %s is not available: %s' % (playlist_id, reason)
432 raise ExtractorError(msg, expected=True)
434 for item in self._extract_items(playlist):
435 kind = item.get('kind')
436 if kind != 'programme' and kind != 'radioProgramme':
438 title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
439 description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
440 description = description_el.text if description_el is not None else None
442 def get_programme_id(item):
443 def get_from_attributes(item):
444 for p in('identifier', 'group'):
446 if value and re.match(r'^[pb][\da-z]{7}$', value):
448 get_from_attributes(item)
449 mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
450 if mediator is not None:
451 return get_from_attributes(mediator)
453 programme_id = get_programme_id(item)
454 duration = int_or_none(item.get('duration'))
457 formats, subtitles = self._download_media_selector(programme_id)
459 formats, subtitles = self._process_media_selector(item, playlist_id)
460 programme_id = playlist_id
462 return programme_id, title, description, duration, formats, subtitles
464 def _real_extract(self, url):
465 group_id = self._match_id(url)
467 webpage = self._download_webpage(url, group_id, 'Downloading video page')
472 tviplayer = self._search_regex(
473 r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
474 webpage, 'player', default=None)
477 player = self._parse_json(tviplayer, group_id).get('player', {})
478 duration = int_or_none(player.get('duration'))
479 programme_id = player.get('vpid')
482 programme_id = self._search_regex(
483 r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
486 formats, subtitles = self._download_media_selector(programme_id)
487 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
488 (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
489 r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
490 description = self._search_regex(
491 (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
492 r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
493 webpage, 'description', default=None)
495 description = self._html_search_meta('description', webpage)
497 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
499 self._sort_formats(formats)
504 'description': description,
505 'thumbnail': self._og_search_thumbnail(webpage, default=None),
506 'duration': duration,
508 'subtitles': subtitles,
512 class BBCIE(BBCCoUkIE):
515 _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
517 _MEDIASELECTOR_URLS = [
518 # Provides HQ HLS streams but fails with geolocation in some cases when it's
519 # even not geo restricted at all
520 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
521 # Provides more formats, namely direct mp4 links, but fails on some videos with
522 # notukerror for non UK (?) users (e.g.
523 # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
524 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
525 # Provides fewer formats, but works everywhere for everybody (hopefully)
526 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
530 # article with multiple videos embedded with data-playable containing vpids
531 'url': 'http://www.bbc.com/news/world-europe-32668511',
533 'id': 'world-europe-32668511',
534 'title': 'Russia stages massive WW2 parade despite Western boycott',
535 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
539 # article with multiple videos embedded with data-playable (more videos)
540 'url': 'http://www.bbc.com/news/business-28299555',
542 'id': 'business-28299555',
543 'title': 'Farnborough Airshow: Video highlights',
544 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
549 # article with multiple videos embedded with `new SMP()`
551 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
553 'id': '3662a707-0af9-3149-963f-47bea720b460',
556 'playlist_count': 18,
558 # single video embedded with data-playable containing vpid
559 'url': 'http://www.bbc.com/news/world-europe-32041533',
563 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
564 'description': 'md5:2868290467291b37feda7863f7a83f54',
566 'timestamp': 1427219242,
567 'upload_date': '20150324',
571 'skip_download': True,
574 # article with single video embedded with data-playable containing XML playlist
575 # with direct video links as progressiveDownloadUrl (for now these are extracted)
576 # and playlist with f4m and m3u8 as streamingUrl
577 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
579 'id': '150615_telabyad_kentin_cogu',
581 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
582 'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
583 'timestamp': 1434397334,
584 'upload_date': '20150615',
587 'skip_download': True,
590 # single video embedded with data-playable containing XML playlists (regional section)
591 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
593 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
595 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
596 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
597 'timestamp': 1434713142,
598 'upload_date': '20150619',
601 'skip_download': True,
604 # single video from video playlist embedded with vxp-playlist-data JSON
605 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
609 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
611 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
614 'skip_download': True,
617 # single video story with digitalData
618 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
622 'title': 'Sri Lanka’s spicy secret',
623 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
624 'timestamp': 1437674293,
625 'upload_date': '20150723',
629 'skip_download': True,
632 # single video story without digitalData
633 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
637 'title': 'Hyundai Santa Fe Sport: Rock star',
638 'description': 'md5:b042a26142c4154a6e472933cf20793d',
639 'timestamp': 1415867444,
640 'upload_date': '20141113',
644 'skip_download': True,
647 # single video with playlist.sxml URL in playlist param
648 'url': 'http://www.bbc.com/sport/0/football/33653409',
652 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
653 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
658 'skip_download': True,
661 # article with multiple videos embedded with playlist.sxml in playlist param
662 'url': 'http://www.bbc.com/sport/0/football/34475836',
665 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
666 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
670 # school report article with single video
671 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
674 'title': 'School which breaks down barriers in Jerusalem',
678 # single video with playlist URL from weather section
679 'url': 'http://www.bbc.com/weather/features/33601775',
680 'only_matching': True,
682 # custom redirection to www.bbc.com
683 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
684 'only_matching': True,
686 # single video article embedded with data-media-vpid
687 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
688 'only_matching': True,
692 def suitable(cls, url):
693 EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
694 return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
695 else super(BBCIE, cls).suitable(url))
697 def _extract_from_media_meta(self, media_meta, video_id):
698 # Direct links to media in media metadata (e.g.
699 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
700 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
701 source_files = media_meta.get('sourceFiles')
705 'format_id': format_id,
706 'ext': f.get('encoding'),
707 'tbr': float_or_none(f.get('bitrate'), 1000),
708 'filesize': int_or_none(f.get('filesize')),
709 } for format_id, f in source_files.items() if f.get('url')], []
711 programme_id = media_meta.get('externalId')
713 return self._download_media_selector(programme_id)
715 # Process playlist.sxml as legacy playlist
716 href = media_meta.get('href')
718 playlist = self._download_legacy_playlist_url(href)
719 _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
720 return formats, subtitles
724 def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
725 programme_id, title, description, duration, formats, subtitles = \
726 self._process_legacy_playlist_url(url, playlist_id)
727 self._sort_formats(formats)
731 'description': description,
732 'duration': duration,
733 'timestamp': timestamp,
735 'subtitles': subtitles,
738 def _real_extract(self, url):
739 playlist_id = self._match_id(url)
741 webpage = self._download_webpage(url, playlist_id)
743 json_ld_info = self._search_json_ld(webpage, playlist_id, default=None)
744 timestamp = json_ld_info.get('timestamp')
746 playlist_title = json_ld_info.get('title')
747 if not playlist_title:
748 playlist_title = self._og_search_title(
749 webpage, default=None) or self._html_search_regex(
750 r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
752 playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
754 playlist_description = json_ld_info.get(
755 'description') or self._og_search_description(webpage, default=None)
758 timestamp = parse_iso8601(self._search_regex(
759 [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
760 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
761 r'"datePublished":\s*"([^"]+)'],
762 webpage, 'date', default=None))
766 # article with multiple videos embedded with playlist.sxml (e.g.
767 # http://www.bbc.com/sport/0/football/34475836)
768 playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
769 playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
772 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
773 for playlist_url in playlists]
775 # news article with multiple videos embedded with data-playable
776 data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
778 for _, data_playable_json in data_playables:
779 data_playable = self._parse_json(
780 unescapeHTML(data_playable_json), playlist_id, fatal=False)
781 if not data_playable:
783 settings = data_playable.get('settings', {})
785 # data-playable with video vpid in settings.playlistObject.items (e.g.
786 # http://www.bbc.com/news/world-us-canada-34473351)
787 playlist_object = settings.get('playlistObject', {})
789 items = playlist_object.get('items')
790 if items and isinstance(items, list):
791 title = playlist_object['title']
792 description = playlist_object.get('summary')
793 duration = int_or_none(items[0].get('duration'))
794 programme_id = items[0].get('vpid')
795 formats, subtitles = self._download_media_selector(programme_id)
796 self._sort_formats(formats)
800 'description': description,
801 'timestamp': timestamp,
802 'duration': duration,
804 'subtitles': subtitles,
807 # data-playable without vpid but with a playlist.sxml URLs
808 # in otherSettings.playlist (e.g.
809 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
810 playlist = data_playable.get('otherSettings', {}).get('playlist', {})
813 for key in ('streaming', 'progressiveDownload'):
814 playlist_url = playlist.get('%sUrl' % key)
818 info = self._extract_from_playlist_sxml(
819 playlist_url, playlist_id, timestamp)
823 entry['title'] = info['title']
824 entry['formats'].extend(info['formats'])
825 except Exception as e:
826 # Some playlist URL may fail with 500, at the same time
827 # the other one may work fine (e.g.
828 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
829 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
833 self._sort_formats(entry['formats'])
834 entries.append(entry)
837 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
839 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
840 programme_id = self._search_regex(
841 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
842 r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
843 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
844 webpage, 'vpid', default=None)
847 formats, subtitles = self._download_media_selector(programme_id)
848 self._sort_formats(formats)
849 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
850 digital_data = self._parse_json(
852 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
853 programme_id, fatal=False)
854 page_info = digital_data.get('page', {}).get('pageInfo', {})
855 title = page_info.get('pageName') or self._og_search_title(webpage)
856 description = page_info.get('description') or self._og_search_description(webpage)
857 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
861 'description': description,
862 'timestamp': timestamp,
864 'subtitles': subtitles,
867 def extract_all(pattern):
868 return list(filter(None, map(
869 lambda s: self._parse_json(s, playlist_id, fatal=False),
870 re.findall(pattern, webpage))))
872 # Multiple video article (e.g.
873 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
874 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
876 for match in extract_all(r'new\s+SMP\(({.+?})\)'):
877 embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
878 if embed_url and re.match(EMBED_URL, embed_url):
879 entries.append(embed_url)
880 entries.extend(re.findall(
881 r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
883 return self.playlist_result(
884 [self.url_result(entry, 'BBCCoUk') for entry in entries],
885 playlist_id, playlist_title, playlist_description)
887 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
888 medias = extract_all(r"data-media-meta='({[^']+})'")
891 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
892 media_asset = self._search_regex(
893 r'mediaAssetPage\.init\(\s*({.+?}), "/',
894 webpage, 'media asset', default=None)
896 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
898 for video in media_asset_page.get('videos', {}).values():
899 medias.extend(video.values())
902 # Multiple video playlist with single `now playing` entry (e.g.
903 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
904 vxp_playlist = self._parse_json(
906 r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
907 webpage, 'playlist data'),
910 for item in vxp_playlist:
911 media = item.get('media')
914 playlist_medias.append(media)
915 # Download single video if found media with asset id matching the video id from URL
916 if item.get('advert', {}).get('assetId') == playlist_id:
919 # Fallback to the whole playlist
921 medias = playlist_medias
924 for num, media_meta in enumerate(medias, start=1):
925 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
928 self._sort_formats(formats)
930 video_id = media_meta.get('externalId')
932 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
934 title = media_meta.get('caption')
936 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
938 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
941 for image in media_meta.get('images', {}).values():
942 images.extend(image.values())
943 if 'image' in media_meta:
944 images.append(media_meta['image'])
947 'url': image.get('href'),
948 'width': int_or_none(image.get('width')),
949 'height': int_or_none(image.get('height')),
950 } for image in images]
955 'thumbnails': thumbnails,
956 'duration': duration,
957 'timestamp': timestamp,
959 'subtitles': subtitles,
962 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
965 class BBCCoUkArticleIE(InfoExtractor):
966 _VALID_URL = r'https?://www.bbc.co.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
967 IE_NAME = 'bbc.co.uk:article'
968 IE_DESC = 'BBC articles'
971 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
973 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
974 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
975 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
978 'add_ie': ['BBCCoUk'],
981 def _real_extract(self, url):
982 playlist_id = self._match_id(url)
984 webpage = self._download_webpage(url, playlist_id)
986 title = self._og_search_title(webpage)
987 description = self._og_search_description(webpage).strip()
989 entries = [self.url_result(programme_url) for programme_url in re.findall(
990 r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
992 return self.playlist_result(entries, playlist_id, title, description)
995 class BBCCoUkPlaylistBaseIE(InfoExtractor):
996 def _real_extract(self, url):
997 playlist_id = self._match_id(url)
999 webpage = self._download_webpage(url, playlist_id)
1002 self.url_result(self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
1003 for video_id in re.findall(
1004 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage)]
1006 title, description = self._extract_title_and_description(webpage)
1008 return self.playlist_result(entries, playlist_id, title, description)
1011 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
1012 IE_NAME = 'bbc.co.uk:iplayer:playlist'
1013 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
1014 _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
1015 _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
1017 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
1020 'title': 'The Disappearance',
1021 'description': 'French thriller serial about a missing teenager.',
1023 'playlist_mincount': 6,
1024 'skip': 'This programme is not currently available on BBC iPlayer',
1026 # Available for over a year unlike 30 days for most other programmes
1027 'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
1030 'title': 'Bohemian Icons',
1031 'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
1033 'playlist_mincount': 10,
1036 def _extract_title_and_description(self, webpage):
1037 title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
1038 description = self._search_regex(
1039 r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
1040 webpage, 'description', fatal=False, group='value')
1041 return title, description
1044 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1045 IE_NAME = 'bbc.co.uk:playlist'
1046 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
1047 _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
1048 _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
1050 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1053 'title': 'The Disappearance - Clips - BBC Four',
1054 'description': 'French thriller serial about a missing teenager.',
1056 'playlist_mincount': 7,
1058 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1059 'only_matching': True,
1061 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1062 'only_matching': True,
1064 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1065 'only_matching': True,
1068 def _extract_title_and_description(self, webpage):
1069 title = self._og_search_title(webpage, fatal=False)
1070 description = self._og_search_description(webpage)
1071 return title, description