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
')
455 version = playlist.get('defaultAvailableVersion
')
457 smp_config = version['smpConfig
']
458 title = smp_config['title
']
459 description = smp_config['summary
']
460 for item in smp_config['items
']:
462 if kind not in ('programme
', 'radioProgramme
'):
464 programme_id = item.get('vpid
')
465 duration = int_or_none(item.get('duration
'))
466 formats, subtitles = self._download_media_selector(programme_id)
467 return programme_id, title, description, duration, formats, subtitles
468 except ExtractorError as ee:
469 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
472 # fallback to legacy playlist
473 return self._process_legacy_playlist(playlist_id)
475 def _process_legacy_playlist_url(self, url, display_id):
476 playlist = self._download_legacy_playlist_url(url, display_id)
477 return self._extract_from_legacy_playlist(playlist, display_id)
479 def _process_legacy_playlist(self, playlist_id):
480 return self._process_legacy_playlist_url(
481 'http
://www
.bbc
.co
.uk
/iplayer
/playlist
/%s' % playlist_id, playlist_id)
483 def _download_legacy_playlist_url(self, url, playlist_id=None):
484 return self._download_xml(
485 url, playlist_id, 'Downloading legacy playlist XML
')
487 def _extract_from_legacy_playlist(self, playlist, playlist_id):
488 no_items = playlist.find('./{%s}noItems
' % self._EMP_PLAYLIST_NS)
489 if no_items is not None:
490 reason = no_items.get('reason
')
491 if reason == 'preAvailability
':
492 msg = 'Episode
%s is not yet available
' % playlist_id
493 elif reason == 'postAvailability
':
494 msg = 'Episode
%s is no longer available
' % playlist_id
495 elif reason == 'noMedia
':
496 msg = 'Episode
%s is not currently available
' % playlist_id
498 msg = 'Episode
%s is not available
: %s' % (playlist_id, reason)
499 raise ExtractorError(msg, expected=True)
501 for item in self._extract_items(playlist):
502 kind = item.get('kind
')
503 if kind not in ('programme
', 'radioProgramme
'):
505 title = playlist.find('./{%s}title
' % self._EMP_PLAYLIST_NS).text
506 description_el = playlist.find('./{%s}summary
' % self._EMP_PLAYLIST_NS)
507 description = description_el.text if description_el is not None else None
509 def get_programme_id(item):
510 def get_from_attributes(item):
511 for p in ('identifier
', 'group
'):
513 if value and re.match(r'^
[pb
][\da
-z
]{7}$
', value):
515 get_from_attributes(item)
516 mediator = item.find('./{%s}mediator
' % self._EMP_PLAYLIST_NS)
517 if mediator is not None:
518 return get_from_attributes(mediator)
520 programme_id = get_programme_id(item)
521 duration = int_or_none(item.get('duration
'))
524 formats, subtitles = self._download_media_selector(programme_id)
526 formats, subtitles = self._process_media_selector(item, playlist_id)
527 programme_id = playlist_id
529 return programme_id, title, description, duration, formats, subtitles
531 def _real_extract(self, url):
532 group_id = self._match_id(url)
534 webpage = self._download_webpage(url, group_id, 'Downloading video page
')
536 error = self._search_regex(
537 r'<div
\b[^
>]+\bclass
=["\'](?:smp|playout)__message delta["\'][^
>]*>\s
*([^
<]+?
)\s
*<',
538 webpage, 'error
', default=None)
540 raise ExtractorError(error, expected=True)
545 tviplayer = self._search_regex(
546 r'mediator\
.bind\
(({.+?}
)\s
*,\s
*document\
.getElementById
',
547 webpage, 'player
', default=None)
550 player = self._parse_json(tviplayer, group_id).get('player
', {})
551 duration = int_or_none(player.get('duration
'))
552 programme_id = player.get('vpid
')
555 programme_id = self._search_regex(
556 r'"vpid"\s
*:\s
*"(%s)"' % self._ID_REGEX, webpage, 'vpid
', fatal=False, default=None)
559 formats, subtitles = self._download_media_selector(programme_id)
560 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
561 (r'<h2
[^
>]+id="parent-title"[^
>]*>(.+?
)</h2
>',
562 r'<div
[^
>]+class="info"[^
>]*>\s
*<h1
>(.+?
)</h1
>'), webpage, 'title
')
563 description = self._search_regex(
564 (r'<p
class="[^"]*medium
-description
[^
"]*">([^
<]+)</p
>',
565 r'<div
[^
>]+class="info_+synopsis"[^
>]*>([^
<]+)</div
>'),
566 webpage, 'description
', default=None)
568 description = self._html_search_meta('description
', webpage)
570 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
572 self._sort_formats(formats)
577 'description
': description,
578 'thumbnail
': self._og_search_thumbnail(webpage, default=None),
579 'duration
': duration,
581 'subtitles
': subtitles,
585 class BBCIE(BBCCoUkIE):
588 _VALID_URL = r'https?
://(?
:www\
.)?bbc\
.(?
:com|co\
.uk
)/(?
:[^
/]+/)+(?P
<id>[^
/#?]+)'
592 'mobile-tablet-main',
596 # article with multiple videos embedded with data-playable containing vpids
597 'url': 'http://www.bbc.com/news/world-europe-32668511',
599 'id': 'world-europe-32668511',
600 'title': 'Russia stages massive WW2 parade',
601 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
605 # article with multiple videos embedded with data-playable (more videos)
606 'url': 'http://www.bbc.com/news/business-28299555',
608 'id': 'business-28299555',
609 'title': 'Farnborough Airshow: Video highlights',
610 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
615 # article with multiple videos embedded with `new SMP()`
617 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
619 'id': '3662a707-0af9-3149-963f-47bea720b460',
622 'playlist_count': 18,
624 # single video embedded with data-playable containing vpid
625 'url': 'http://www.bbc.com/news/world-europe-32041533',
629 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
630 'description': 'md5:2868290467291b37feda7863f7a83f54',
632 'timestamp': 1427219242,
633 'upload_date': '20150324',
637 'skip_download': True,
640 # article with single video embedded with data-playable containing XML playlist
641 # with direct video links as progressiveDownloadUrl (for now these are extracted)
642 # and playlist with f4m and m3u8 as streamingUrl
643 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
645 'id': '150615_telabyad_kentin_cogu',
647 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde",
648 'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
649 'timestamp': 1434397334,
650 'upload_date': '20150615',
653 'skip_download': True,
656 # single video embedded with data-playable containing XML playlists (regional section)
657 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
659 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
661 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción',
662 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
663 'timestamp': 1434713142,
664 'upload_date': '20150619',
667 'skip_download': True,
670 # single video from video playlist embedded with vxp-playlist-data JSON
671 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
675 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
677 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
680 'skip_download': True,
683 # single video story with digitalData
684 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
688 'title': 'Sri Lanka’s spicy secret',
689 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.',
690 'timestamp': 1437674293,
691 'upload_date': '20150723',
695 'skip_download': True,
698 # single video story without digitalData
699 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
703 'title': 'Hyundai Santa Fe Sport: Rock star',
704 'description': 'md5:b042a26142c4154a6e472933cf20793d',
705 'timestamp': 1415867444,
706 'upload_date': '20141113',
710 'skip_download': True,
713 # single video embedded with Morph
714 'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
718 'title': "Nigeria v Japan - Men's First Round",
719 'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
721 'uploader': 'BBC Sport',
722 'uploader_id': 'bbc_sport',
726 'skip_download': True,
728 'skip': 'Georestricted to UK',
730 # single video with playlist.sxml URL in playlist param
731 'url': 'http://www.bbc.com/sport/0/football/33653409',
735 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
736 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
741 'skip_download': True,
744 # article with multiple videos embedded with playlist.sxml in playlist param
745 'url': 'http://www.bbc.com/sport/0/football/34475836',
748 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
749 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
753 # school report article with single video
754 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
757 'title': 'School which breaks down barriers in Jerusalem',
761 # single video with playlist URL from weather section
762 'url': 'http://www.bbc.com/weather/features/33601775',
763 'only_matching': True,
765 # custom redirection to www.bbc.com
766 # also, video with window.__INITIAL_DATA__
767 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
771 'title': "Pluto may have 'nitrogen glaciers'",
772 'description': 'md5:6a95b593f528d7a5f2605221bc56912f',
773 'thumbnail': r
're:https?://.+/.+\.jpg',
774 'timestamp': 1437785037,
775 'upload_date': '20150725',
778 # single video article embedded with data-media-vpid
779 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
780 'only_matching': True,
782 'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
786 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
787 'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
790 'skip_download': True,
793 # window.__PRELOADED_STATE__
794 'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
798 'title': 'Prom 6: An American in Paris and Turangalila',
799 'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
800 'uploader': 'Radio 3',
801 'uploader_id': 'bbc_radio_three',
804 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
808 'title': 'md5:2fabf12a726603193a2879a055f72514',
809 'description': 'Learn English words and phrases from this story',
811 'add_ie': [BBCCoUkIE
.ie_key()],
814 'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
818 'title': 'How positive thinking is harming your happiness',
819 'alt_title': 'The downsides of positive thinking',
820 'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
822 'thumbnail': r
're:https?://.+/p07c9dsr.jpg',
823 'upload_date': '20190604',
824 'categories': ['Psychology'],
829 def suitable(cls
, url
):
830 EXCLUDE_IE
= (BBCCoUkIE
, BBCCoUkArticleIE
, BBCCoUkIPlayerEpisodesIE
, BBCCoUkIPlayerGroupIE
, BBCCoUkPlaylistIE
)
831 return (False if any(ie
.suitable(url
) for ie
in EXCLUDE_IE
)
832 else super(BBCIE
, cls
).suitable(url
))
834 def _extract_from_media_meta(self
, media_meta
, video_id
):
835 # Direct links to media in media metadata (e.g.
836 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
837 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
838 source_files
= media_meta
.get('sourceFiles')
842 'format_id': format_id
,
843 'ext': f
.get('encoding'),
844 'tbr': float_or_none(f
.get('bitrate'), 1000),
845 'filesize': int_or_none(f
.get('filesize')),
846 } for format_id
, f
in source_files
.items() if f
.get('url')], []
848 programme_id
= media_meta
.get('externalId')
850 return self
._download
_media
_selector
(programme_id
)
852 # Process playlist.sxml as legacy playlist
853 href
= media_meta
.get('href')
855 playlist
= self
._download
_legacy
_playlist
_url
(href
)
856 _
, _
, _
, _
, formats
, subtitles
= self
._extract
_from
_legacy
_playlist
(playlist
, video_id
)
857 return formats
, subtitles
861 def _extract_from_playlist_sxml(self
, url
, playlist_id
, timestamp
):
862 programme_id
, title
, description
, duration
, formats
, subtitles
= \
863 self
._process
_legacy
_playlist
_url
(url
, playlist_id
)
864 self
._sort
_formats
(formats
)
868 'description': description
,
869 'duration': duration
,
870 'timestamp': timestamp
,
872 'subtitles': subtitles
,
875 def _real_extract(self
, url
):
876 playlist_id
= self
._match
_id
(url
)
878 webpage
= self
._download
_webpage
(url
, playlist_id
)
880 json_ld_info
= self
._search
_json
_ld
(webpage
, playlist_id
, default
={})
881 timestamp
= json_ld_info
.get('timestamp')
883 playlist_title
= json_ld_info
.get('title')
884 if not playlist_title
:
885 playlist_title
= self
._og
_search
_title
(
886 webpage
, default
=None) or self
._html
_search
_regex
(
887 r
'<title>(.+?)</title>', webpage
, 'playlist title', default
=None)
889 playlist_title
= re
.sub(r
'(.+)\s*-\s*BBC.*?$', r
'\1', playlist_title
).strip()
891 playlist_description
= json_ld_info
.get(
892 'description') or self
._og
_search
_description
(webpage
, default
=None)
895 timestamp
= parse_iso8601(self
._search
_regex
(
896 [r
'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
897 r
'itemprop="datePublished"[^>]+datetime="([^"]+)"',
898 r
'"datePublished":\s*"([^"]+)'],
899 webpage
, 'date', default
=None))
903 # article with multiple videos embedded with playlist.sxml (e.g.
904 # http://www.bbc.com/sport/0/football/34475836)
905 playlists
= re
.findall(r
'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage
)
906 playlists
.extend(re
.findall(r
'data-media-id="([^"]+/playlist\.sxml)"', webpage
))
909 self
._extract
_from
_playlist
_sxml
(playlist_url
, playlist_id
, timestamp
)
910 for playlist_url
in playlists
]
912 # news article with multiple videos embedded with data-playable
913 data_playables
= re
.findall(r
'data-playable=(["\'])({.+?}
)\
1', webpage)
915 for _, data_playable_json in data_playables:
916 data_playable = self._parse_json(
917 unescapeHTML(data_playable_json), playlist_id, fatal=False)
918 if not data_playable:
920 settings = data_playable.get('settings
', {})
922 # data-playable with video vpid in settings.playlistObject.items (e.g.
923 # http://www.bbc.com/news/world-us-canada-34473351)
924 playlist_object = settings.get('playlistObject
', {})
926 items = playlist_object.get('items
')
927 if items and isinstance(items, list):
928 title = playlist_object['title
']
929 description = playlist_object.get('summary
')
930 duration = int_or_none(items[0].get('duration
'))
931 programme_id = items[0].get('vpid
')
932 formats, subtitles = self._download_media_selector(programme_id)
933 self._sort_formats(formats)
937 'description
': description,
938 'timestamp
': timestamp,
939 'duration
': duration,
941 'subtitles
': subtitles,
944 # data-playable without vpid but with a playlist.sxml URLs
945 # in otherSettings.playlist (e.g.
946 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
947 playlist = data_playable.get('otherSettings
', {}).get('playlist', {})
950 for key in ('streaming
', 'progressiveDownload
'):
951 playlist_url = playlist.get('%sUrl
' % key)
955 info = self._extract_from_playlist_sxml(
956 playlist_url, playlist_id, timestamp)
960 entry['title
'] = info['title
']
961 entry['formats
'].extend(info['formats
'])
962 except ExtractorError as e:
963 # Some playlist URL may fail with 500, at the same time
964 # the other one may work fine (e.g.
965 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
966 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
970 self._sort_formats(entry['formats
'])
971 entries.append(entry)
974 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
976 # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227
977 group_id = self._search_regex(
978 r'<div
[^
>]+\bclass
=["\']video["\'][^
>]+\bdata
-pid
=["\'](%s)' % self._ID_REGEX,
979 webpage, 'group id', default=None)
981 return self.url_result(
982 'https://www.bbc.co.uk/programmes/%s' % group_id,
983 ie=BBCCoUkIE.ie_key())
985 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
986 programme_id = self._search_regex(
987 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
988 r'<param[^>]+name="externalIdentifier
"[^>]+value="(%s)"' % self._ID_REGEX,
989 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
990 webpage, 'vpid', default=None)
993 formats, subtitles = self._download_media_selector(programme_id)
994 self._sort_formats(formats)
995 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
996 digital_data = self._parse_json(
998 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
999 programme_id, fatal=False)
1000 page_info = digital_data.get('page', {}).get('pageInfo', {})
1001 title = page_info.get('pageName') or self._og_search_title(webpage)
1002 description = page_info.get('description') or self._og_search_description(webpage)
1003 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
1007 'description': description,
1008 'timestamp': timestamp,
1010 'subtitles': subtitles,
1013 # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
1014 initial_data = self._parse_json(self._html_search_regex(
1015 r'<script[^>]+id=(["\'])initial
-data\
1[^
>]+data
-json
=(["\'])(?P<json>(?:(?!\2).)+)',
1016 webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
1018 init_data = try_get(
1019 initial_data, lambda x: x['initData']['items'][0], dict) or {}
1020 smp_data = init_data.get('smpData') or {}
1021 clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
1022 version_id = clip_data.get('versionID')
1024 title = smp_data['title']
1025 formats, subtitles = self._download_media_selector(version_id)
1026 self._sort_formats(formats)
1027 image_url = smp_data.get('holdingImageURL')
1028 display_date = init_data.get('displayDate')
1029 topic_title = init_data.get('topicTitle')
1035 'alt_title': init_data.get('shortTitle'),
1036 'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
1037 'description': smp_data.get('summary') or init_data.get('shortSummary'),
1038 'upload_date': display_date.replace('-', '') if display_date else None,
1039 'subtitles': subtitles,
1040 'duration': int_or_none(clip_data.get('duration')),
1041 'categories': [topic_title] if topic_title else None,
1044 # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
1045 # There are several setPayload calls may be present but the video
1046 # seems to be always related to the first one
1047 morph_payload = self._parse_json(
1049 r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
1050 webpage, 'morph payload', default='{}'),
1051 playlist_id, fatal=False)
1053 components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
1054 for component in components:
1055 if not isinstance(component, dict):
1057 lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
1060 identifiers = lead_media.get('identifiers')
1061 if not identifiers or not isinstance(identifiers, dict):
1063 programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
1064 if not programme_id:
1066 title = lead_media.get('title') or self._og_search_title(webpage)
1067 formats, subtitles = self._download_media_selector(programme_id)
1068 self._sort_formats(formats)
1069 description = lead_media.get('summary')
1070 uploader = lead_media.get('masterBrand')
1071 uploader_id = lead_media.get('mid')
1073 duration_d = lead_media.get('duration')
1074 if isinstance(duration_d, dict):
1075 duration = parse_duration(dict_get(
1076 duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
1080 'description': description,
1081 'duration': duration,
1082 'uploader': uploader,
1083 'uploader_id': uploader_id,
1085 'subtitles': subtitles,
1088 preload_state = self._parse_json(self._search_regex(
1089 r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
1090 'preload state', default='{}'), playlist_id, fatal=False)
1092 current_programme = preload_state.get('programmes', {}).get('current') or {}
1093 programme_id = current_programme.get('id')
1094 if current_programme and programme_id and current_programme.get('type') == 'playable_item':
1095 title = current_programme.get('titles', {}).get('tertiary') or playlist_title
1096 formats, subtitles = self._download_media_selector(programme_id)
1097 self._sort_formats(formats)
1098 synopses = current_programme.get('synopses') or {}
1099 network = current_programme.get('network') or {}
1100 duration = int_or_none(
1101 current_programme.get('duration', {}).get('value'))
1103 image_url = current_programme.get('image_url')
1105 thumbnail = image_url.replace('{recipe}', 'raw')
1109 'description': dict_get(synopses, ('long', 'medium', 'short')),
1110 'thumbnail': thumbnail,
1111 'duration': duration,
1112 'uploader': network.get('short_title'),
1113 'uploader_id': network.get('id'),
1115 'subtitles': subtitles,
1118 bbc3_config = self._parse_json(
1120 r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
1121 'bbcthree config', default='{}'),
1122 playlist_id, transform_source=js_to_json, fatal=False) or {}
1123 payload = bbc3_config.get('payload') or {}
1125 clip = payload.get('currentClip') or {}
1126 clip_vpid = clip.get('vpid')
1127 clip_title = clip.get('title')
1128 if clip_vpid and clip_title:
1129 formats, subtitles = self._download_media_selector(clip_vpid)
1130 self._sort_formats(formats)
1133 'title': clip_title,
1134 'thumbnail': dict_get(clip, ('poster', 'imageUrl')),
1135 'description': clip.get('description'),
1136 'duration': parse_duration(clip.get('duration')),
1138 'subtitles': subtitles,
1140 bbc3_playlist = try_get(
1141 payload, lambda x: x['content']['bbcMedia']['playlist'],
1144 playlist_title = bbc3_playlist.get('title') or playlist_title
1145 thumbnail = bbc3_playlist.get('holdingImageURL')
1147 for bbc3_item in bbc3_playlist['items']:
1148 programme_id = bbc3_item.get('versionID')
1149 if not programme_id:
1151 formats, subtitles = self._download_media_selector(programme_id)
1152 self._sort_formats(formats)
1155 'title': playlist_title,
1156 'thumbnail': thumbnail,
1157 'timestamp': timestamp,
1159 'subtitles': subtitles,
1161 return self.playlist_result(
1162 entries, playlist_id, playlist_title, playlist_description)
1164 initial_data = self._parse_json(self._search_regex(
1165 r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
1166 'preload state', default='{}'), playlist_id, fatal=False)
1168 def parse_media(media):
1171 for item in (try_get(media, lambda x: x['media']['items'], list) or []):
1172 item_id = item.get('id')
1173 item_title = item.get('title')
1174 if not (item_id and item_title):
1176 formats, subtitles = self._download_media_selector(item_id)
1177 self._sort_formats(formats)
1179 blocks = try_get(media, lambda x: x['summary']['blocks'], list)
1182 for block in blocks:
1183 text = try_get(block, lambda x: x['model']['text'], compat_str)
1185 summary.append(text)
1187 item_desc = '\n\n'.join(summary)
1189 for meta in try_get(media, lambda x: x['metadata']['items'], list) or []:
1190 if try_get(meta, lambda x: x['label']) == 'Published':
1191 item_time = unified_timestamp(meta.get('timestamp'))
1195 'title': item_title,
1196 'thumbnail': item.get('holdingImageUrl'),
1198 'subtitles': subtitles,
1199 'timestamp': item_time,
1200 'description': strip_or_none(item_desc),
1202 for resp in (initial_data.get('data') or {}).values():
1203 name = resp.get('name')
1204 if name == 'media-experience':
1205 parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
1206 elif name == 'article':
1207 for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
1208 if block.get('type') != 'media':
1210 parse_media(block.get('model'))
1211 return self.playlist_result(
1212 entries, playlist_id, playlist_title, playlist_description)
1214 def extract_all(pattern):
1215 return list(filter(None, map(
1216 lambda s: self._parse_json(s, playlist_id, fatal=False),
1217 re.findall(pattern, webpage))))
1219 # Multiple video article (e.g.
1220 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
1221 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?
' % self._ID_REGEX
1223 for match in extract_all(r'new\s
+SMP\
(({.+?}
)\
)'):
1224 embed_url = match.get('playerSettings
', {}).get('externalEmbedUrl
')
1225 if embed_url and re.match(EMBED_URL, embed_url):
1226 entries.append(embed_url)
1227 entries.extend(re.findall(
1228 r'setPlaylist\
("(%s)"\
)' % EMBED_URL, webpage))
1230 return self.playlist_result(
1231 [self.url_result(entry_, 'BBCCoUk
') for entry_ in entries],
1232 playlist_id, playlist_title, playlist_description)
1234 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
1235 medias = extract_all(r"data-media-meta='({[^']+}
)'")
1238 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
1239 media_asset = self._search_regex(
1240 r'mediaAssetPage\
.init\
(\s
*({.+?}
), "/',
1241 webpage, 'media asset', default=None)
1243 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
1245 for video in media_asset_page.get('videos', {}).values():
1246 medias.extend(video.values())
1249 # Multiple video playlist with single `now playing` entry (e.g.
1250 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
1251 vxp_playlist = self._parse_json(
1253 r'<script[^>]+class="vxp
-playlist
-data
"[^>]+type="application
/json
"[^>]*>([^<]+)</script>',
1254 webpage, 'playlist data'),
1256 playlist_medias = []
1257 for item in vxp_playlist:
1258 media = item.get('media')
1261 playlist_medias.append(media)
1262 # Download single video if found media with asset id matching the video id from URL
1263 if item.get('advert', {}).get('assetId') == playlist_id:
1266 # Fallback to the whole playlist
1268 medias = playlist_medias
1271 for num, media_meta in enumerate(medias, start=1):
1272 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
1273 if not formats and not self.get_param('ignore_no_formats'):
1275 self._sort_formats(formats)
1277 video_id = media_meta.get('externalId')
1279 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
1281 title = media_meta.get('caption')
1283 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
1285 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
1288 for image in media_meta.get('images', {}).values():
1289 images.extend(image.values())
1290 if 'image' in media_meta:
1291 images.append(media_meta['image'])
1294 'url': image.get('href'),
1295 'width': int_or_none(image.get('width')),
1296 'height': int_or_none(image.get('height')),
1297 } for image in images]
1302 'thumbnails': thumbnails,
1303 'duration': duration,
1304 'timestamp': timestamp,
1306 'subtitles': subtitles,
1309 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
1312 class BBCCoUkArticleIE(InfoExtractor):
1313 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
1314 IE_NAME = 'bbc.co.uk:article'
1315 IE_DESC = 'BBC articles'
1318 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
1320 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
1321 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
1322 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
1324 'playlist_count': 4,
1325 'add_ie': ['BBCCoUk'],
1328 def _real_extract(self, url):
1329 playlist_id = self._match_id(url)
1331 webpage = self._download_webpage(url, playlist_id)
1333 title = self._og_search_title(webpage)
1334 description = self._og_search_description(webpage).strip()
1336 entries = [self.url_result(programme_url) for programme_url in re.findall(
1337 r'<div[^>]+typeof="Clip
"[^>]+resource="([^
"]+)"', webpage)]
1339 return self.playlist_result(entries, playlist_id, title, description)
1342 class BBCCoUkPlaylistBaseIE(InfoExtractor):
1343 def _entries(self, webpage, url, playlist_id):
1344 single_page = 'page
' in compat_urlparse.parse_qs(
1345 compat_urlparse.urlparse(url).query)
1346 for page_num in itertools.count(2):
1347 for video_id in re.findall(
1348 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
1349 yield self.url_result(
1350 self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
1353 next_page = self._search_regex(
1354 r'<li
[^
>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P
<url
>(?
:(?
!\
2).)+)\
2',
1355 webpage, 'next page url
', default=None, group='url
')
1358 webpage = self._download_webpage(
1359 compat_urlparse.urljoin(url, next_page), playlist_id,
1360 'Downloading page
%d' % page_num, page_num)
1362 def _real_extract(self, url):
1363 playlist_id = self._match_id(url)
1365 webpage = self._download_webpage(url, playlist_id)
1367 title, description = self._extract_title_and_description(webpage)
1369 return self.playlist_result(
1370 self._entries(webpage, url, playlist_id),
1371 playlist_id, title, description)
1374 class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
1375 _VALID_URL_TMPL = r'https?
://(?
:www\
.)?bbc\
.co\
.uk
/iplayer
/%%s/(?P
<id>%s)' % BBCCoUkIE._ID_REGEX
1378 def _get_default(episode, key, default_key='default
'):
1379 return try_get(episode, lambda x: x[key][default_key])
1381 def _get_description(self, data):
1382 synopsis = data.get(self._DESCRIPTION_KEY) or {}
1383 return dict_get(synopsis, ('large
', 'medium
', 'small
'))
1385 def _fetch_page(self, programme_id, per_page, series_id, page):
1386 elements = self._get_elements(self._call_api(
1387 programme_id, per_page, page + 1, series_id))
1388 for element in elements:
1389 episode = self._get_episode(element)
1390 episode_id = episode.get('id')
1394 image = self._get_episode_image(episode)
1396 thumbnail = image.replace('{recipe}
', 'raw
')
1397 category = self._get_default(episode, 'labels
', 'category
')
1401 'title
': self._get_episode_field(episode, 'subtitle
'),
1402 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episode
/' + episode_id,
1403 'thumbnail
': thumbnail,
1404 'description
': self._get_description(episode),
1405 'categories
': [category] if category else None,
1406 'series
': self._get_episode_field(episode, 'title
'),
1407 'ie_key
': BBCCoUkIE.ie_key(),
1410 def _real_extract(self, url):
1411 pid = self._match_id(url)
1413 series_id = qs.get('seriesId
', [None])[0]
1414 page = qs.get('page
', [None])[0]
1415 per_page = 36 if page else self._PAGE_SIZE
1416 fetch_page = functools.partial(self._fetch_page, pid, per_page, series_id)
1417 entries = fetch_page(int(page) - 1) if page else OnDemandPagedList(fetch_page, self._PAGE_SIZE)
1418 playlist_data = self._get_playlist_data(self._call_api(pid, 1))
1419 return self.playlist_result(
1420 entries, pid, self._get_playlist_title(playlist_data),
1421 self._get_description(playlist_data))
1424 class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
1425 IE_NAME = 'bbc
.co
.uk
:iplayer
:episodes
'
1426 _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'episodes
'
1428 'url
': 'http
://www
.bbc
.co
.uk
/iplayer
/episodes
/b05rcz9v
',
1431 'title
': 'The Disappearance
',
1432 'description
': 'md5
:58eb101aee3116bad4da05f91179c0cb
',
1434 'playlist_mincount
': 8,
1437 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/b094m5t9
/doctor
-foster
',
1440 'title
': 'Doctor Foster
',
1441 'description
': 'md5
:5aa9195fad900e8e14b52acd765a9fd6
',
1443 'playlist_mincount
': 10,
1446 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/b094m5t9
/doctor
-foster?seriesId
=b094m6nv
',
1449 'title
': 'Doctor Foster
',
1450 'description
': 'md5
:5aa9195fad900e8e14b52acd765a9fd6
',
1452 'playlist_mincount
': 5,
1455 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/m0004c4v
/beechgrove
',
1458 'title
': 'Beechgrove
',
1459 'description
': 'Gardening show that celebrates Scottish horticulture
and growing conditions
.',
1461 'playlist_mincount
': 37,
1464 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/episodes
/m0004c4v
/beechgrove?page
=2',
1467 'title
': 'Beechgrove
',
1468 'description
': 'Gardening show that celebrates Scottish horticulture
and growing conditions
.',
1470 'playlist_mincount
': 1,
1473 _DESCRIPTION_KEY = 'synopsis
'
1475 def _get_episode_image(self, episode):
1476 return self._get_default(episode, 'image
')
1478 def _get_episode_field(self, episode, field):
1479 return self._get_default(episode, field)
1482 def _get_elements(data):
1483 return data['entities
']['results
']
1486 def _get_episode(element):
1487 return element.get('episode
') or {}
1489 def _call_api(self, pid, per_page, page=1, series_id=None):
1493 'perPage
': per_page,
1496 variables['sliceId
'] = series_id
1497 return self._download_json(
1498 'https
://graph
.ibl
.api
.bbc
.co
.uk
/', pid, headers={
1499 'Content
-Type
': 'application
/json
'
1500 }, data=json.dumps({
1501 'id': '5692d93d5aac8d796a0305e895e61551
',
1502 'variables
': variables,
1503 }).encode('utf
-8'))['data
']['programme
']
1506 def _get_playlist_data(data):
1509 def _get_playlist_title(self, data):
1510 return self._get_default(data, 'title
')
1513 class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
1514 IE_NAME = 'bbc
.co
.uk
:iplayer
:group
'
1515 _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'group
'
1517 # Available for over a year unlike 30 days for most other programmes
1518 'url
': 'http
://www
.bbc
.co
.uk
/iplayer
/group
/p02tcc32
',
1521 'title
': 'Bohemian Icons
',
1522 'description
': 'md5
:683e901041b2fe9ba596f2ab04c4dbe7
',
1524 'playlist_mincount
': 10,
1527 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/group
/p081d7j7
',
1530 'title
': 'Music
in Scotland
',
1531 'description
': 'Perfomances
in Scotland
and programmes featuring Scottish acts
.',
1533 'playlist_mincount
': 47,
1536 'url
': 'https
://www
.bbc
.co
.uk
/iplayer
/group
/p081d7j7?page
=2',
1539 'title
': 'Music
in Scotland
',
1540 'description
': 'Perfomances
in Scotland
and programmes featuring Scottish acts
.',
1542 'playlist_mincount
': 11,
1545 _DESCRIPTION_KEY = 'synopses
'
1547 def _get_episode_image(self, episode):
1548 return self._get_default(episode, 'images
', 'standard
')
1550 def _get_episode_field(self, episode, field):
1551 return episode.get(field)
1554 def _get_elements(data):
1555 return data['elements
']
1558 def _get_episode(element):
1561 def _call_api(self, pid, per_page, page=1, series_id=None):
1562 return self._download_json(
1563 'http
://ibl
.api
.bbc
.co
.uk
/ibl
/v1
/groups
/%s/episodes
' % pid,
1566 'per_page
': per_page,
1567 })['group_episodes
']
1570 def _get_playlist_data(data):
1571 return data['group
']
1573 def _get_playlist_title(self, data):
1574 return data.get('title
')
1577 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1578 IE_NAME = 'bbc
.co
.uk
:playlist
'
1579 _VALID_URL = r'https?
://(?
:www\
.)?bbc\
.co\
.uk
/programmes
/(?P
<id>%s)/(?
:episodes|broadcasts|clips
)' % BBCCoUkIE._ID_REGEX
1580 _URL_TEMPLATE = 'http
://www
.bbc
.co
.uk
/programmes
/%s'
1581 _VIDEO_ID_TEMPLATE = r'data
-pid
=["\'](%s)'
1583 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1586 'title': 'The Disappearance - Clips - BBC Four',
1587 'description': 'French thriller serial about a missing teenager.',
1589 'playlist_mincount': 7,
1591 # multipage playlist, explicit page
1592 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
1595 'title': 'Frozen Planet - Clips - BBC One',
1596 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1598 'playlist_mincount': 24,
1600 # multipage playlist, all pages
1601 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
1604 'title': 'Frozen Planet - Clips - BBC One',
1605 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1607 'playlist_mincount': 142,
1609 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1610 'only_matching': True,
1612 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1613 'only_matching': True,
1615 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1616 'only_matching': True,
1619 def _extract_title_and_description(self, webpage):
1620 title = self._og_search_title(webpage, fatal=False)
1621 description = self._og_search_description(webpage)
1622 return title, description