2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from ..compat
import (
38 class BBCCoUkIE(InfoExtractor
):
40 IE_DESC
= 'BBC iPlayer'
41 _ID_REGEX
= r
'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
44 (?:www\.)?bbc\.co\.uk/
46 programmes/(?!articles/)|
47 iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
48 music/(?:clips|audiovideo/popular)[/#]|
51 events/[^/]+/play/[^/]+/
53 (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
56 _LOGIN_URL
= 'https://account.bbc.com/signin'
57 _NETRC_MACHINE
= 'bbc'
59 _MEDIA_SELECTOR_URL_TEMPL
= 'https://open.live.bbc.co.uk/mediaselector/6/select/version/2.0/mediaset/%s/vpid/%s'
61 # Provides HQ HLS streams with even better quality that pc mediaset but fails
62 # with geolocation in some cases when it's even not geo restricted at all (e.g.
63 # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
68 _EMP_PLAYLIST_NS
= 'http://bbc.co.uk/2008/emp/playlist'
72 'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
76 'title': 'Kaleidoscope, Leonard Cohen',
77 'description': 'The Canadian poet and songwriter reflects on his musical career.',
81 'skip_download': True,
85 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
89 'title': 'The Man in Black: Series 3: The Printed Name',
90 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
95 'skip_download': True,
97 'skip': 'Episode is no longer available on BBC iPlayer Radio',
100 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
104 'title': 'The Voice UK: Series 3: Blind Auditions 5',
105 '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.',
110 'skip_download': True,
112 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
115 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
119 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
120 'description': '2. Invasion',
125 'skip_download': True,
127 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
129 'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
133 'title': 'Pete Tong, The Essential New Tune Special',
134 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
139 'skip_download': True,
141 'skip': 'Episode is no longer available on BBC iPlayer Radio',
143 'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
148 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
149 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
154 'skip_download': True,
157 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
162 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
163 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
168 'skip_download': True,
171 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
175 'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
176 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
181 'skip_download': True,
183 'skip': 'geolocation',
185 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
189 '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.',
190 'title': 'Royal Academy Summer Exhibition',
195 'skip_download': True,
197 'skip': 'geolocation',
199 # iptv-all mediaset fails with geolocation however there is no geo restriction
200 # for this programme at all
201 'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
205 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
206 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
210 'skip_download': True,
212 'skip': 'Now it\'s really geo-restricted',
214 # compact player (https://github.com/ytdl-org/youtube-dl/issues/8147)
215 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
219 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
220 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
224 'skip_download': True,
227 'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
232 'title': 'BBC Proms, 2019, Prom 34: West–Eastern Divan Orchestra',
233 'description': "Live BBC Proms. West–Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
238 'skip_download': True,
241 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
242 'only_matching': True,
244 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
245 'only_matching': True,
247 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
248 'only_matching': True,
250 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
251 'only_matching': True,
253 'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55',
254 'only_matching': True,
256 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
257 'only_matching': True,
259 'url': 'https://www.bbc.co.uk/programmes/m00005xn',
260 'only_matching': True,
262 'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s',
263 'only_matching': True,
267 username
, password
= self
._get
_login
_info
()
271 login_page
= self
._download
_webpage
(
272 self
._LOGIN
_URL
, None, 'Downloading signin page')
274 login_form
= self
._hidden
_inputs
(login_page
)
277 'username': username
,
278 'password': password
,
281 post_url
= urljoin(self
._LOGIN
_URL
, self
._search
_regex
(
282 r
'<form[^>]+action=(["\'])(?P
<url
>.+?
)\
1', login_page,
283 'post url
', default=self._LOGIN_URL, group='url
'))
285 response, urlh = self._download_webpage_handle(
286 post_url, None, 'Logging
in', data=urlencode_postdata(login_form),
287 headers={'Referer': self._LOGIN_URL})
289 if self._LOGIN_URL in urlh.geturl():
290 error = clean_html(get_element_by_class('form
-message
', response))
292 raise ExtractorError(
293 'Unable to login
: %s' % error, expected=True)
294 raise ExtractorError('Unable to log
in')
296 def _real_initialize(self):
299 class MediaSelectionError(Exception):
300 def __init__(self, id):
303 def _extract_asx_playlist(self, connection, programme_id):
304 asx = self._download_xml(connection.get('href
'), programme_id, 'Downloading ASX playlist
')
305 return [ref.get('href
') for ref in asx.findall('./Entry
/ref
')]
307 def _extract_items(self, playlist):
308 return playlist.findall('./{%s}item
' % self._EMP_PLAYLIST_NS)
310 def _extract_medias(self, media_selection):
311 error = media_selection.get('result
')
313 raise BBCCoUkIE.MediaSelectionError(error)
314 return media_selection.get('media
') or []
316 def _extract_connections(self, media):
317 return media.get('connection
') or []
319 def _get_subtitles(self, media, programme_id):
321 for connection in self._extract_connections(media):
322 cc_url = url_or_none(connection.get('href
'))
325 captions = self._download_xml(
326 cc_url, programme_id, 'Downloading captions
', fatal=False)
327 if not isinstance(captions, compat_etree_Element):
331 'url
': connection.get('href
'),
338 def _raise_extractor_error(self, media_selection_error):
339 raise ExtractorError(
340 '%s returned error
: %s' % (self.IE_NAME, media_selection_error.id),
343 def _download_media_selector(self, programme_id):
344 last_exception = None
345 for media_set in self._MEDIA_SETS:
347 return self._download_media_selector_url(
348 self._MEDIA_SELECTOR_URL_TEMPL % (media_set, programme_id), programme_id)
349 except BBCCoUkIE.MediaSelectionError as e:
350 if e.id in ('notukerror
', 'geolocation
', 'selectionunavailable
'):
353 self._raise_extractor_error(e)
354 self._raise_extractor_error(last_exception)
356 def _download_media_selector_url(self, url, programme_id=None):
357 media_selection = self._download_json(
358 url, programme_id, 'Downloading media selection JSON
',
359 expected_status=(403, 404))
360 return self._process_media_selector(media_selection, programme_id)
362 def _process_media_selector(self, media_selection, programme_id):
367 for media in self._extract_medias(media_selection):
368 kind = media.get('kind
')
369 if kind in ('video
', 'audio
'):
370 bitrate = int_or_none(media.get('bitrate
'))
371 encoding = media.get('encoding
')
372 width = int_or_none(media.get('width
'))
373 height = int_or_none(media.get('height
'))
374 file_size = int_or_none(media.get('media_file_size
'))
375 for connection in self._extract_connections(media):
376 href = connection.get('href
')
381 conn_kind = connection.get('kind
')
382 protocol = connection.get('protocol
')
383 supplier = connection.get('supplier
')
384 transfer_format = connection.get('transferFormat
')
385 format_id = supplier or conn_kind or protocol
387 if supplier == 'asx
':
388 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
391 'format_id
': 'ref
%s_%s' % (i, format_id),
393 elif transfer_format == 'dash
':
394 formats.extend(self._extract_mpd_formats(
395 href, programme_id, mpd_id=format_id, fatal=False))
396 elif transfer_format == 'hls
':
397 formats.extend(self._extract_m3u8_formats(
398 href, programme_id, ext='mp4
', entry_protocol='m3u8_native
',
399 m3u8_id=format_id, fatal=False))
400 elif transfer_format == 'hds
':
401 formats.extend(self._extract_f4m_formats(
402 href, programme_id, f4m_id=format_id, fatal=False))
404 if not supplier and bitrate:
405 format_id += '-%d' % bitrate
407 'format_id
': format_id,
408 'filesize
': file_size,
423 if protocol in ('http
', 'https
'):
428 elif protocol == 'rtmp
':
429 application = connection.get('application
', 'ondemand
')
430 auth_string = connection.get('authString
')
431 identifier = connection.get('identifier
')
432 server = connection.get('server
')
434 'url
': '%s://%s/%s?
%s' % (protocol, server, application, auth_string),
435 'play_path
': identifier,
436 'app
': '%s?
%s' % (application, auth_string),
437 'page_url
': 'http
://www
.bbc
.co
.uk
',
438 'player_url
': 'http
://www
.bbc
.co
.uk
/emp
/releases
/iplayer
/revisions
/617463_618125_4/617463_618125_4_emp
.swf
',
445 elif kind == 'captions
':
446 subtitles = self.extract_subtitles(media, programme_id)
447 return formats, subtitles
449 def _download_playlist(self, playlist_id):
451 playlist = self._download_json(
452 'http
://www
.bbc
.co
.uk
/programmes
/%s/playlist
.json
' % playlist_id,
453 playlist_id, 'Downloading playlist JSON
')
457 for version in playlist.get('allAvailableVersions
', []):
458 smp_config = version['smpConfig
']
459 title = smp_config['title
']
460 description = smp_config['summary
']
461 for item in smp_config['items
']:
463 if kind not in ('programme
', 'radioProgramme
'):
465 programme_id = item.get('vpid
')
466 duration = int_or_none(item.get('duration
'))
467 version_formats, version_subtitles = self._download_media_selector(programme_id)
468 types = version['types
']
469 for f in version_formats:
470 f['format_note
'] = ', '.join(types)
471 if any('AudioDescribed
' in x for x in types):
472 f['language_preference
'] = -10
473 formats += version_formats
474 for tag, subformats in (version_subtitles or {}).items():
475 subtitles.setdefault(tag, []).extend(subformats)
477 return programme_id, title, description, duration, formats, subtitles
478 except ExtractorError as ee:
479 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
482 # fallback to legacy playlist
483 return self._process_legacy_playlist(playlist_id)
485 def _process_legacy_playlist_url(self, url, display_id):
486 playlist = self._download_legacy_playlist_url(url, display_id)
487 return self._extract_from_legacy_playlist(playlist, display_id)
489 def _process_legacy_playlist(self, playlist_id):
490 return self._process_legacy_playlist_url(
491 'http
://www
.bbc
.co
.uk
/iplayer
/playlist
/%s' % playlist_id, playlist_id)
493 def _download_legacy_playlist_url(self, url, playlist_id=None):
494 return self._download_xml(
495 url, playlist_id, 'Downloading legacy playlist XML
')
497 def _extract_from_legacy_playlist(self, playlist, playlist_id):
498 no_items = playlist.find('./{%s}noItems
' % self._EMP_PLAYLIST_NS)
499 if no_items is not None:
500 reason = no_items.get('reason
')
501 if reason == 'preAvailability
':
502 msg = 'Episode
%s is not yet available
' % playlist_id
503 elif reason == 'postAvailability
':
504 msg = 'Episode
%s is no longer available
' % playlist_id
505 elif reason == 'noMedia
':
506 msg = 'Episode
%s is not currently available
' % playlist_id
508 msg = 'Episode
%s is not available
: %s' % (playlist_id, reason)
509 raise ExtractorError(msg, expected=True)
511 for item in self._extract_items(playlist):
512 kind = item.get('kind
')
513 if kind not in ('programme
', 'radioProgramme
'):
515 title = playlist.find('./{%s}title
' % self._EMP_PLAYLIST_NS).text
516 description_el = playlist.find('./{%s}summary
' % self._EMP_PLAYLIST_NS)
517 description = description_el.text if description_el is not None else None
519 def get_programme_id(item):
520 def get_from_attributes(item):
521 for p in ('identifier
', 'group
'):
523 if value and re.match(r'^
[pb
][\da
-z
]{7}$
', value):
525 get_from_attributes(item)
526 mediator = item.find('./{%s}mediator
' % self._EMP_PLAYLIST_NS)
527 if mediator is not None:
528 return get_from_attributes(mediator)
530 programme_id = get_programme_id(item)
531 duration = int_or_none(item.get('duration
'))
534 formats, subtitles = self._download_media_selector(programme_id)
536 formats, subtitles = self._process_media_selector(item, playlist_id)
537 programme_id = playlist_id
539 return programme_id, title, description, duration, formats, subtitles
541 def _real_extract(self, url):
542 group_id = self._match_id(url)
544 webpage = self._download_webpage(url, group_id, 'Downloading video page
')
546 error = self._search_regex(
547 r'<div
\b[^
>]+\bclass
=["\'](?:smp|playout)__message delta["\'][^
>]*>\s
*([^
<]+?
)\s
*<',
548 webpage, 'error
', default=None)
550 raise ExtractorError(error, expected=True)
555 tviplayer = self._search_regex(
556 r'mediator\
.bind\
(({.+?}
)\s
*,\s
*document\
.getElementById
',
557 webpage, 'player
', default=None)
560 player = self._parse_json(tviplayer, group_id).get('player
', {})
561 duration = int_or_none(player.get('duration
'))
562 programme_id = player.get('vpid
')
565 programme_id = self._search_regex(
566 r'"vpid"\s
*:\s
*"(%s)"' % self._ID_REGEX, webpage, 'vpid
', fatal=False, default=None)
569 formats, subtitles = self._download_media_selector(programme_id)
570 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
571 (r'<h2
[^
>]+id="parent-title"[^
>]*>(.+?
)</h2
>',
572 r'<div
[^
>]+class="info"[^
>]*>\s
*<h1
>(.+?
)</h1
>'), webpage, 'title
')
573 description = self._search_regex(
574 (r'<p
class="[^"]*medium
-description
[^
"]*">([^
<]+)</p
>',
575 r'<div
[^
>]+class="info_+synopsis"[^
>]*>([^
<]+)</div
>'),
576 webpage, 'description
', default=None)
578 description = self._html_search_meta('description
', webpage)
580 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
582 self._sort_formats(formats)
587 'description
': description,
588 'thumbnail
': self._og_search_thumbnail(webpage, default=None),
589 'duration
': duration,
591 'subtitles
': subtitles,
595 class BBCIE(BBCCoUkIE):
598 _VALID_URL = r'https?
://(?
:www\
.)?bbc\
.(?
:com|co\
.uk
)/(?
:[^
/]+/)+(?P
<id>[^
/#?]+)'
602 'mobile-tablet-main',
606 # article with multiple videos embedded with data-playable containing vpids
607 'url': 'http://www.bbc.com/news/world-europe-32668511',
609 'id': 'world-europe-32668511',
610 'title': 'Russia stages massive WW2 parade',
611 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
615 # article with multiple videos embedded with data-playable (more videos)
616 'url': 'http://www.bbc.com/news/business-28299555',
618 'id': 'business-28299555',
619 'title': 'Farnborough Airshow: Video highlights',
620 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
625 # article with multiple videos embedded with `new SMP()`
627 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
629 'id': '3662a707-0af9-3149-963f-47bea720b460',
632 'playlist_count': 18,
634 # single video embedded with data-playable containing vpid
635 'url': 'http://www.bbc.com/news/world-europe-32041533',
639 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
640 'description': 'md5:2868290467291b37feda7863f7a83f54',
642 'timestamp': 1427219242,
643 'upload_date': '20150324',
647 'skip_download': True,
650 # article with single video embedded with data-playable containing XML playlist
651 # with direct video links as progressiveDownloadUrl (for now these are extracted)
652 # and playlist with f4m and m3u8 as streamingUrl
653 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
655 'id': '150615_telabyad_kentin_cogu',
657 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
658 'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
659 'timestamp': 1434397334,
660 'upload_date': '20150615',
663 'skip_download': True,
666 # single video embedded with data-playable containing XML playlists (regional section)
667 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
669 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
671 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
672 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
673 'timestamp': 1434713142,
674 'upload_date': '20150619',
677 'skip_download': True,
680 # single video from video playlist embedded with vxp-playlist-data JSON
681 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
685 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
687 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
690 'skip_download': True,
693 # single video story with digitalData
694 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
698 'title': 'Sri Lanka’s spicy secret',
699 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
700 'timestamp': 1437674293,
701 'upload_date': '20150723',
705 'skip_download': True,
708 # single video story without digitalData
709 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
713 'title': 'Hyundai Santa Fe Sport: Rock star',
714 'description': 'md5:b042a26142c4154a6e472933cf20793d',
715 'timestamp': 1415867444,
716 'upload_date': '20141113',
720 'skip_download': True,
723 # single video embedded with Morph
724 'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
728 'title': "Nigeria v Japan - Men's First Round",
729 'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
731 'uploader': 'BBC Sport',
732 'uploader_id': 'bbc_sport',
736 'skip_download': True,
738 'skip': 'Georestricted to UK',
740 # single video with playlist.sxml URL in playlist param
741 'url': 'http://www.bbc.com/sport/0/football/33653409',
745 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
746 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
751 'skip_download': True,
754 # article with multiple videos embedded with playlist.sxml in playlist param
755 'url': 'http://www.bbc.com/sport/0/football/34475836',
758 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
759 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
763 # school report article with single video
764 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
767 'title': 'School which breaks down barriers in Jerusalem',
771 # single video with playlist URL from weather section
772 'url': 'http://www.bbc.com/weather/features/33601775',
773 'only_matching': True,
775 # custom redirection to www.bbc.com
776 # also, video with window.__INITIAL_DATA__
777 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
781 'title': "Pluto may have 'nitrogen glaciers'",
782 'description': 'md5:6a95b593f528d7a5f2605221bc56912f',
783 'thumbnail': r
're:https?://.+/.+\.jpg',
784 'timestamp': 1437785037,
785 'upload_date': '20150725',
788 # single video article embedded with data-media-vpid
789 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
790 'only_matching': True,
792 'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
796 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
797 'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
800 'skip_download': True,
803 # window.__PRELOADED_STATE__
804 'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
808 'title': 'Prom 6: An American in Paris and Turangalila',
809 'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
810 'uploader': 'Radio 3',
811 'uploader_id': 'bbc_radio_three',
814 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
818 'title': 'md5:2fabf12a726603193a2879a055f72514',
819 'description': 'Learn English words and phrases from this story',
821 'add_ie': [BBCCoUkIE
.ie_key()],
824 'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
828 'title': 'How positive thinking is harming your happiness',
829 'alt_title': 'The downsides of positive thinking',
830 'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
832 'thumbnail': r
're:https?://.+/p07c9dsr.jpg',
833 'upload_date': '20190604',
834 'categories': ['Psychology'],
839 def suitable(cls
, url
):
840 EXCLUDE_IE
= (BBCCoUkIE
, BBCCoUkArticleIE
, BBCCoUkIPlayerEpisodesIE
, BBCCoUkIPlayerGroupIE
, BBCCoUkPlaylistIE
)
841 return (False if any(ie
.suitable(url
) for ie
in EXCLUDE_IE
)
842 else super(BBCIE
, cls
).suitable(url
))
844 def _extract_from_media_meta(self
, media_meta
, video_id
):
845 # Direct links to media in media metadata (e.g.
846 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
847 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
848 source_files
= media_meta
.get('sourceFiles')
852 'format_id': format_id
,
853 'ext': f
.get('encoding'),
854 'tbr': float_or_none(f
.get('bitrate'), 1000),
855 'filesize': int_or_none(f
.get('filesize')),
856 } for format_id
, f
in source_files
.items() if f
.get('url')], []
858 programme_id
= media_meta
.get('externalId')
860 return self
._download
_media
_selector
(programme_id
)
862 # Process playlist.sxml as legacy playlist
863 href
= media_meta
.get('href')
865 playlist
= self
._download
_legacy
_playlist
_url
(href
)
866 _
, _
, _
, _
, formats
, subtitles
= self
._extract
_from
_legacy
_playlist
(playlist
, video_id
)
867 return formats
, subtitles
871 def _extract_from_playlist_sxml(self
, url
, playlist_id
, timestamp
):
872 programme_id
, title
, description
, duration
, formats
, subtitles
= \
873 self
._process
_legacy
_playlist
_url
(url
, playlist_id
)
874 self
._sort
_formats
(formats
)
878 'description': description
,
879 'duration': duration
,
880 'timestamp': timestamp
,
882 'subtitles': subtitles
,
885 def _real_extract(self
, url
):
886 playlist_id
= self
._match
_id
(url
)
888 webpage
= self
._download
_webpage
(url
, playlist_id
)
890 json_ld_info
= self
._search
_json
_ld
(webpage
, playlist_id
, default
={})
891 timestamp
= json_ld_info
.get('timestamp')
893 playlist_title
= json_ld_info
.get('title')
894 if not playlist_title
:
895 playlist_title
= self
._og
_search
_title
(
896 webpage
, default
=None) or self
._html
_search
_regex
(
897 r
'<title>(.+?)</title>', webpage
, 'playlist title', default
=None)
899 playlist_title
= re
.sub(r
'(.+)\s*-\s*BBC.*?$', r
'\1', playlist_title
).strip()
901 playlist_description
= json_ld_info
.get(
902 'description') or self
._og
_search
_description
(webpage
, default
=None)
905 timestamp
= parse_iso8601(self
._search
_regex
(
906 [r
'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
907 r
'itemprop="datePublished"[^>]+datetime="([^"]+)"',
908 r
'"datePublished":\s*"([^"]+)'],
909 webpage
, 'date', default
=None))
913 # article with multiple videos embedded with playlist.sxml (e.g.
914 # http://www.bbc.com/sport/0/football/34475836)
915 playlists
= re
.findall(r
'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage
)
916 playlists
.extend(re
.findall(r
'data-media-id="([^"]+/playlist\.sxml)"', webpage
))
919 self
._extract
_from
_playlist
_sxml
(playlist_url
, playlist_id
, timestamp
)
920 for playlist_url
in playlists
]
922 # news article with multiple videos embedded with data-playable
923 data_playables
= re
.findall(r
'data-playable=(["\'])({.+?}
)\
1', webpage)
925 for _, data_playable_json in data_playables:
926 data_playable = self._parse_json(
927 unescapeHTML(data_playable_json), playlist_id, fatal=False)
928 if not data_playable:
930 settings = data_playable.get('settings
', {})
932 # data-playable with video vpid in settings.playlistObject.items (e.g.
933 # http://www.bbc.com/news/world-us-canada-34473351)
934 playlist_object = settings.get('playlistObject
', {})
936 items = playlist_object.get('items
')
937 if items and isinstance(items, list):
938 title = playlist_object['title
']
939 description = playlist_object.get('summary
')
940 duration = int_or_none(items[0].get('duration
'))
941 programme_id = items[0].get('vpid
')
942 formats, subtitles = self._download_media_selector(programme_id)
943 self._sort_formats(formats)
947 'description
': description,
948 'timestamp
': timestamp,
949 'duration
': duration,
951 'subtitles
': subtitles,
954 # data-playable without vpid but with a playlist.sxml URLs
955 # in otherSettings.playlist (e.g.
956 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
957 playlist = data_playable.get('otherSettings
', {}).get('playlist', {})
960 for key in ('streaming
', 'progressiveDownload
'):
961 playlist_url = playlist.get('%sUrl
' % key)
965 info = self._extract_from_playlist_sxml(
966 playlist_url, playlist_id, timestamp)
970 entry['title
'] = info['title
']
971 entry['formats
'].extend(info['formats
'])
972 except ExtractorError as e:
973 # Some playlist URL may fail with 500, at the same time
974 # the other one may work fine (e.g.
975 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
976 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
980 self._sort_formats(entry['formats
'])
981 entries.append(entry)
984 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
986 # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227
987 group_id = self._search_regex(
988 r'<div
[^
>]+\bclass
=["\']video["\'][^
>]+\bdata
-pid
=["\'](%s)' % self._ID_REGEX,
989 webpage, 'group id', default=None)
991 return self.url_result(
992 'https://www.bbc.co.uk/programmes/%s' % group_id,
993 ie=BBCCoUkIE.ie_key())
995 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
996 programme_id = self._search_regex(
997 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
998 r'<param[^>]+name="externalIdentifier
"[^>]+value="(%s)"' % self._ID_REGEX,
999 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
1000 webpage, 'vpid', default=None)
1003 formats, subtitles = self._download_media_selector(programme_id)
1004 self._sort_formats(formats)
1005 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
1006 digital_data = self._parse_json(
1008 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
1009 programme_id, fatal=False)
1010 page_info = digital_data.get('page', {}).get('pageInfo', {})
1011 title = page_info.get('pageName') or self._og_search_title(webpage)
1012 description = page_info.get('description') or self._og_search_description(webpage)
1013 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
1017 'description': description,
1018 'timestamp': timestamp,
1020 'subtitles': subtitles,
1023 # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
1024 initial_data = self._parse_json(self._html_search_regex(
1025 r'<script[^>]+id=(["\'])initial
-data\
1[^
>]+data
-json
=(["\'])(?P<json>(?:(?!\2).)+)',
1026 webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
1028 init_data = try_get(
1029 initial_data, lambda x: x['initData']['items'][0], dict) or {}
1030 smp_data = init_data.get('smpData') or {}
1031 clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
1032 version_id = clip_data.get('versionID')
1034 title = smp_data['title']
1035 formats, subtitles = self._download_media_selector(version_id)
1036 self._sort_formats(formats)
1037 image_url = smp_data.get('holdingImageURL')
1038 display_date = init_data.get('displayDate')
1039 topic_title = init_data.get('topicTitle')
1045 'alt_title': init_data.get('shortTitle'),
1046 'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
1047 'description': smp_data.get('summary') or init_data.get('shortSummary'),
1048 'upload_date': display_date.replace('-', '') if display_date else None,
1049 'subtitles': subtitles,
1050 'duration': int_or_none(clip_data.get('duration')),
1051 'categories': [topic_title] if topic_title else None,
1054 # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
1055 # There are several setPayload calls may be present but the video
1056 # seems to be always related to the first one
1057 morph_payload = self._parse_json(
1059 r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
1060 webpage, 'morph payload', default='{}'),
1061 playlist_id, fatal=False)
1063 components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
1064 for component in components:
1065 if not isinstance(component, dict):
1067 lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
1070 identifiers = lead_media.get('identifiers')
1071 if not identifiers or not isinstance(identifiers, dict):
1073 programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
1074 if not programme_id:
1076 title = lead_media.get('title') or self._og_search_title(webpage)
1077 formats, subtitles = self._download_media_selector(programme_id)
1078 self._sort_formats(formats)
1079 description = lead_media.get('summary')
1080 uploader = lead_media.get('masterBrand')
1081 uploader_id = lead_media.get('mid')
1083 duration_d = lead_media.get('duration')
1084 if isinstance(duration_d, dict):
1085 duration = parse_duration(dict_get(
1086 duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
1090 'description': description,
1091 'duration': duration,
1092 'uploader': uploader,
1093 'uploader_id': uploader_id,
1095 'subtitles': subtitles,
1098 preload_state = self._parse_json(self._search_regex(
1099 r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
1100 'preload state', default='{}'), playlist_id, fatal=False)
1102 current_programme = preload_state.get('programmes', {}).get('current') or {}
1103 programme_id = current_programme.get('id')
1104 if current_programme and programme_id and current_programme.get('type') == 'playable_item':
1105 title = current_programme.get('titles', {}).get('tertiary') or playlist_title
1106 formats, subtitles = self._download_media_selector(programme_id)
1107 self._sort_formats(formats)
1108 synopses = current_programme.get('synopses') or {}
1109 network = current_programme.get('network') or {}
1110 duration = int_or_none(
1111 current_programme.get('duration', {}).get('value'))
1113 image_url = current_programme.get('image_url')
1115 thumbnail = image_url.replace('{recipe}', 'raw')
1119 'description': dict_get(synopses, ('long', 'medium', 'short')),
1120 'thumbnail': thumbnail,
1121 'duration': duration,
1122 'uploader': network.get('short_title'),
1123 'uploader_id': network.get('id'),
1125 'subtitles': subtitles,
1128 bbc3_config = self._parse_json(
1130 r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
1131 'bbcthree config', default='{}'),
1132 playlist_id, transform_source=js_to_json, fatal=False) or {}
1133 payload = bbc3_config.get('payload') or {}
1135 clip = payload.get('currentClip') or {}
1136 clip_vpid = clip.get('vpid')
1137 clip_title = clip.get('title')
1138 if clip_vpid and clip_title:
1139 formats, subtitles = self._download_media_selector(clip_vpid)
1140 self._sort_formats(formats)
1143 'title': clip_title,
1144 'thumbnail': dict_get(clip, ('poster', 'imageUrl')),
1145 'description': clip.get('description'),
1146 'duration': parse_duration(clip.get('duration')),
1148 'subtitles': subtitles,
1150 bbc3_playlist = try_get(
1151 payload, lambda x: x['content']['bbcMedia']['playlist'],
1154 playlist_title = bbc3_playlist.get('title') or playlist_title
1155 thumbnail = bbc3_playlist.get('holdingImageURL')
1157 for bbc3_item in bbc3_playlist['items']:
1158 programme_id = bbc3_item.get('versionID')
1159 if not programme_id:
1161 formats, subtitles = self._download_media_selector(programme_id)
1162 self._sort_formats(formats)
1165 'title': playlist_title,
1166 'thumbnail': thumbnail,
1167 'timestamp': timestamp,
1169 'subtitles': subtitles,
1171 return self.playlist_result(
1172 entries, playlist_id, playlist_title, playlist_description)
1174 initial_data = self._parse_json(self._search_regex(
1175 r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
1176 'preload state', default='{}'), playlist_id, fatal=False)
1178 def parse_media(media):
1181 for item in (try_get(media, lambda x: x['media']['items'], list) or []):
1182 item_id = item.get('id')
1183 item_title = item.get('title')
1184 if not (item_id and item_title):
1186 formats, subtitles = self._download_media_selector(item_id)
1187 self._sort_formats(formats)
1189 blocks = try_get(media, lambda x: x['summary']['blocks'], list)
1192 for block in blocks:
1193 text = try_get(block, lambda x: x['model']['text'], compat_str)
1195 summary.append(text)
1197 item_desc = '\n\n'.join(summary)
1199 for meta in try_get(media, lambda x: x['metadata']['items'], list) or []:
1200 if try_get(meta, lambda x: x['label']) == 'Published':
1201 item_time = unified_timestamp(meta.get('timestamp'))
1205 'title': item_title,
1206 'thumbnail': item.get('holdingImageUrl'),
1208 'subtitles': subtitles,
1209 'timestamp': item_time,
1210 'description': strip_or_none(item_desc),
1212 for resp in (initial_data.get('data') or {}).values():
1213 name = resp.get('name')
1214 if name == 'media-experience':
1215 parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
1216 elif name == 'article':
1217 for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
1218 if block.get('type') != 'media':
1220 parse_media(block.get('model'))
1221 return self.playlist_result(
1222 entries, playlist_id, playlist_title, playlist_description)
1224 def extract_all(pattern):
1225 return list(filter(None, map(
1226 lambda s: self._parse_json(s, playlist_id, fatal=False),
1227 re.findall(pattern, webpage))))
1229 # Multiple video article (e.g.
1230 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
1231 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?
' % self._ID_REGEX
1233 for match in extract_all(r'new\s
+SMP\
(({.+?}
)\
)'):
1234 embed_url = match.get('playerSettings
', {}).get('externalEmbedUrl
')
1235 if embed_url and re.match(EMBED_URL, embed_url):
1236 entries.append(embed_url)
1237 entries.extend(re.findall(
1238 r'setPlaylist\
("(%s)"\
)' % EMBED_URL, webpage))
1240 return self.playlist_result(
1241 [self.url_result(entry_, 'BBCCoUk
') for entry_ in entries],
1242 playlist_id, playlist_title, playlist_description)
1244 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
1245 medias = extract_all(r"data-media-meta='({[^']+}
)'")
1248 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
1249 media_asset = self._search_regex(
1250 r'mediaAssetPage\
.init\
(\s
*({.+?}
), "/',
1251 webpage, 'media asset', default=None)
1253 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
1255 for video in media_asset_page.get('videos', {}).values():
1256 medias.extend(video.values())
1259 # Multiple video playlist with single `now playing` entry (e.g.
1260 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
1261 vxp_playlist = self._parse_json(
1263 r'<script[^>]+class="vxp
-playlist
-data
"[^>]+type="application
/json
"[^>]*>([^<]+)</script>',
1264 webpage, 'playlist data'),
1266 playlist_medias = []
1267 for item in vxp_playlist:
1268 media = item.get('media')
1271 playlist_medias.append(media)
1272 # Download single video if found media with asset id matching the video id from URL
1273 if item.get('advert', {}).get('assetId') == playlist_id:
1276 # Fallback to the whole playlist
1278 medias = playlist_medias
1281 for num, media_meta in enumerate(medias, start=1):
1282 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
1283 if not formats and not self.get_param('ignore_no_formats'):
1285 self._sort_formats(formats)
1287 video_id = media_meta.get('externalId')
1289 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
1291 title = media_meta.get('caption')
1293 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
1295 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
1298 for image in media_meta.get('images', {}).values():
1299 images.extend(image.values())
1300 if 'image' in media_meta:
1301 images.append(media_meta['image'])
1304 'url': image.get('href'),
1305 'width': int_or_none(image.get('width')),
1306 'height': int_or_none(image.get('height')),
1307 } for image in images]
1312 'thumbnails': thumbnails,
1313 'duration': duration,
1314 'timestamp': timestamp,
1316 'subtitles': subtitles,
1319 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
1322 class BBCCoUkArticleIE(InfoExtractor):
1323 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
1324 IE_NAME = 'bbc.co.uk:article'
1325 IE_DESC = 'BBC articles'
1328 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
1330 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
1331 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
1332 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
1334 'playlist_count': 4,
1335 'add_ie': ['BBCCoUk'],
1338 def _real_extract(self, url):
1339 playlist_id = self._match_id(url)
1341 webpage = self._download_webpage(url, playlist_id)
1343 title = self._og_search_title(webpage)
1344 description = self._og_search_description(webpage).strip()
1346 entries = [self.url_result(programme_url) for programme_url in re.findall(
1347 r'<div[^>]+typeof="Clip
"[^>]+resource="([^
"]+)"', webpage)]
1349 return self.playlist_result(entries, playlist_id, title, description)
1352 class BBCCoUkPlaylistBaseIE(InfoExtractor):
1353 def _entries(self, webpage, url, playlist_id):
1354 single_page = 'page
' in compat_urlparse.parse_qs(
1355 compat_urlparse.urlparse(url).query)
1356 for page_num in itertools.count(2):
1357 for video_id in re.findall(
1358 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
1359 yield self.url_result(
1360 self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
1363 next_page = self._search_regex(
1364 r'<li
[^
>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P
<url
>(?
:(?
!\
2).)+)\
2',
1365 webpage, 'next page url
', default=None, group='url
')
1368 webpage = self._download_webpage(
1369 compat_urlparse.urljoin(url, next_page), playlist_id,
1370 'Downloading page
%d' % page_num, page_num)
1372 def _real_extract(self, url):
1373 playlist_id = self._match_id(url)
1375 webpage = self._download_webpage(url, playlist_id)
1377 title, description = self._extract_title_and_description(webpage)
1379 return self.playlist_result(
1380 self._entries(webpage, url, playlist_id),
1381 playlist_id, title, description)
1384 class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
1385 _VALID_URL_TMPL = r'https?
://(?
:www\
.)?bbc\
.co\
.uk
/iplayer
/%%s/(?P
<id>%s)' % BBCCoUkIE._ID_REGEX
1388 def _get_default(episode, key, default_key='default
'):
1389 return try_get(episode, lambda x: x[key][default_key])
1391 def _get_description(self, data):
1392 synopsis = data.get(self._DESCRIPTION_KEY) or {}
1393 return dict_get(synopsis, ('large
', 'medium
', 'small
'))
1395 def _fetch_page(self, programme_id, per_page, series_id, page):
1396 elements = self._get_elements(self._call_api(
1397 programme_id, per_page, page + 1, series_id))
1398 for element in elements:
1399 episode = self._get_episode(element)
1400 episode_id = episode.get('id')
1404 image = self._get_episode_image(episode)
1406 thumbnail = image.replace('{recipe}
', 'raw
')
1407 category = self._get_default(episode, 'labels
', 'category
')
1411 'title
': self._get_episode_field(episode, 'subtitle
'),
1412 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episode
/' + episode_id,
1413 'thumbnail
': thumbnail,
1414 'description
': self._get_description(episode),
1415 'categories
': [category] if category else None,
1416 'series
': self._get_episode_field(episode, 'title
'),
1417 'ie_key
': BBCCoUkIE.ie_key(),
1420 def _real_extract(self, url):
1421 pid = self._match_id(url)
1423 series_id = qs.get('seriesId
', [None])[0]
1424 page = qs.get('page
', [None])[0]
1425 per_page = 36 if page else self._PAGE_SIZE
1426 fetch_page = functools.partial(self._fetch_page, pid, per_page, series_id)
1427 entries = fetch_page(int(page) - 1) if page else OnDemandPagedList(fetch_page, self._PAGE_SIZE)
1428 playlist_data = self._get_playlist_data(self._call_api(pid, 1))
1429 return self.playlist_result(
1430 entries, pid, self._get_playlist_title(playlist_data),
1431 self._get_description(playlist_data))
1434 class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
1435 IE_NAME = 'bbc
.co
.uk
:iplayer
:episodes
'
1436 _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'episodes
'
1438 'url
': 'http
://www
.bbc
.co
.uk
/iplayer
/episodes
/b05rcz9v
',
1441 'title
': 'The Disappearance
',
1442 'description
': 'md5
:58eb101aee3116bad4da05f91179c0cb
',
1444 'playlist_mincount
': 8,
1447 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/b094m5t9
/doctor
-foster
',
1450 'title
': 'Doctor Foster
',
1451 'description
': 'md5
:5aa9195fad900e8e14b52acd765a9fd6
',
1453 'playlist_mincount
': 10,
1456 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/b094m5t9
/doctor
-foster?seriesId
=b094m6nv
',
1459 'title
': 'Doctor Foster
',
1460 'description
': 'md5
:5aa9195fad900e8e14b52acd765a9fd6
',
1462 'playlist_mincount
': 5,
1465 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/m0004c4v
/beechgrove
',
1468 'title
': 'Beechgrove
',
1469 'description
': 'Gardening show that celebrates Scottish horticulture
and growing conditions
.',
1471 'playlist_mincount
': 37,
1474 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/m0004c4v
/beechgrove?page
=2',
1477 'title
': 'Beechgrove
',
1478 'description
': 'Gardening show that celebrates Scottish horticulture
and growing conditions
.',
1480 'playlist_mincount
': 1,
1483 _DESCRIPTION_KEY = 'synopsis
'
1485 def _get_episode_image(self, episode):
1486 return self._get_default(episode, 'image
')
1488 def _get_episode_field(self, episode, field):
1489 return self._get_default(episode, field)
1492 def _get_elements(data):
1493 return data['entities
']['results
']
1496 def _get_episode(element):
1497 return element.get('episode
') or {}
1499 def _call_api(self, pid, per_page, page=1, series_id=None):
1503 'perPage
': per_page,
1506 variables['sliceId
'] = series_id
1507 return self._download_json(
1508 'https
://graph
.ibl
.api
.bbc
.co
.uk
/', pid, headers={
1509 'Content
-Type
': 'application
/json
'
1510 }, data=json.dumps({
1511 'id': '5692d93d5aac8d796a0305e895e61551
',
1512 'variables
': variables,
1513 }).encode('utf
-8'))['data
']['programme
']
1516 def _get_playlist_data(data):
1519 def _get_playlist_title(self, data):
1520 return self._get_default(data, 'title
')
1523 class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
1524 IE_NAME = 'bbc
.co
.uk
:iplayer
:group
'
1525 _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'group
'
1527 # Available for over a year unlike 30 days for most other programmes
1528 'url
': 'http
://www
.bbc
.co
.uk
/iplayer
/group
/p02tcc32
',
1531 'title
': 'Bohemian Icons
',
1532 'description
': 'md5
:683e901041b2fe9ba596f2ab04c4dbe7
',
1534 'playlist_mincount
': 10,
1537 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/group
/p081d7j7
',
1540 'title
': 'Music
in Scotland
',
1541 'description
': 'Perfomances
in Scotland
and programmes featuring Scottish acts
.',
1543 'playlist_mincount
': 47,
1546 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/group
/p081d7j7?page
=2',
1549 'title
': 'Music
in Scotland
',
1550 'description
': 'Perfomances
in Scotland
and programmes featuring Scottish acts
.',
1552 'playlist_mincount
': 11,
1555 _DESCRIPTION_KEY = 'synopses
'
1557 def _get_episode_image(self, episode):
1558 return self._get_default(episode, 'images
', 'standard
')
1560 def _get_episode_field(self, episode, field):
1561 return episode.get(field)
1564 def _get_elements(data):
1565 return data['elements
']
1568 def _get_episode(element):
1571 def _call_api(self, pid, per_page, page=1, series_id=None):
1572 return self._download_json(
1573 'http
://ibl
.api
.bbc
.co
.uk
/ibl
/v1
/groups
/%s/episodes
' % pid,
1576 'per_page
': per_page,
1577 })['group_episodes
']
1580 def _get_playlist_data(data):
1581 return data['group
']
1583 def _get_playlist_title(self, data):
1584 return data.get('title
')
1587 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1588 IE_NAME = 'bbc
.co
.uk
:playlist
'
1589 _VALID_URL = r'https?
://(?
:www\
.)?bbc\
.co\
.uk
/programmes
/(?P
<id>%s)/(?
:episodes|broadcasts|clips
)' % BBCCoUkIE._ID_REGEX
1590 _URL_TEMPLATE = 'http
://www
.bbc
.co
.uk
/programmes
/%s'
1591 _VIDEO_ID_TEMPLATE = r'data
-pid
=["\'](%s)'
1593 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1596 'title': 'The Disappearance - Clips - BBC Four',
1597 'description': 'French thriller serial about a missing teenager.',
1599 'playlist_mincount': 7,
1601 # multipage playlist, explicit page
1602 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
1605 'title': 'Frozen Planet - Clips - BBC One',
1606 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1608 'playlist_mincount': 24,
1610 # multipage playlist, all pages
1611 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
1614 'title': 'Frozen Planet - Clips - BBC One',
1615 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1617 'playlist_mincount': 142,
1619 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1620 'only_matching': True,
1622 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1623 'only_matching': True,
1625 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1626 'only_matching': True,
1629 def _extract_title_and_description(self, webpage):
1630 title = self._og_search_title(webpage, fatal=False)
1631 description = self._og_search_description(webpage)
1632 return title, description