1 from __future__ import unicode_literals
3 import xml.etree.ElementTree
5 from .common import InfoExtractor
11 from ..compat import compat_HTTPError
15 class BBCCoUkIE(InfoExtractor):
17 IE_DESC = 'BBC iPlayer'
18 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'
20 mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'
24 'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
28 'title': 'Kaleidoscope, Leonard Cohen',
29 'description': 'The Canadian poet and songwriter reflects on his musical career.',
34 'skip_download': True,
38 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
42 'title': 'The Man in Black: Series 3: The Printed Name',
43 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
48 'skip_download': True,
50 'skip': 'Episode is no longer available on BBC iPlayer Radio',
53 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
57 'title': 'The Voice UK: Series 3: Blind Auditions 5',
58 '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.",
63 'skip_download': True,
65 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
68 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
72 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
73 'description': '2. Invasion',
78 'skip_download': True,
80 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
82 'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
86 'title': 'Pete Tong, The Essential New Tune Special',
87 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
92 'skip_download': True,
95 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
100 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
101 'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
106 'skip_download': True,
109 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
114 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
115 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
120 'skip_download': True,
123 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
127 'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
128 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
133 'skip_download': True,
135 'skip': 'geolocation',
137 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
141 '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.',
142 'title': 'Royal Academy Summer Exhibition',
147 'skip_download': True,
149 'skip': 'geolocation',
151 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
152 'only_matching': True,
154 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
155 'only_matching': True,
157 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
158 'only_matching': True,
162 def _extract_asx_playlist(self, connection, programme_id):
163 asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
164 return [ref.get('href') for ref in asx.findall('./Entry/ref')]
166 def _extract_connection(self, connection, programme_id):
168 protocol = connection.get('protocol')
169 supplier = connection.get('supplier')
170 if protocol == 'http':
171 href = connection.get('href')
173 if supplier == 'asx':
174 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
177 'format_id': 'ref%s_%s' % (i, supplier),
183 'format_id': supplier,
185 elif protocol == 'rtmp':
186 application = connection.get('application', 'ondemand')
187 auth_string = connection.get('authString')
188 identifier = connection.get('identifier')
189 server = connection.get('server')
191 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
192 'play_path': identifier,
193 'app': '%s?%s' % (application, auth_string),
194 'page_url': 'http://www.bbc.co.uk',
195 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
198 'format_id': supplier,
202 def _extract_items(self, playlist):
203 return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')
205 def _extract_medias(self, media_selection):
206 error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
207 if error is not None:
208 raise ExtractorError(
209 '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
210 return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')
212 def _extract_connections(self, media):
213 return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')
215 def _extract_video(self, media, programme_id):
217 vbr = int_or_none(media.get('bitrate'))
218 vcodec = media.get('encoding')
219 service = media.get('service')
220 width = int_or_none(media.get('width'))
221 height = int_or_none(media.get('height'))
222 file_size = int_or_none(media.get('media_file_size'))
223 for connection in self._extract_connections(media):
224 conn_formats = self._extract_connection(connection, programme_id)
225 for format in conn_formats:
227 'format_id': '%s_%s' % (service, format['format_id']),
232 'filesize': file_size,
234 formats.extend(conn_formats)
237 def _extract_audio(self, media, programme_id):
239 abr = int_or_none(media.get('bitrate'))
240 acodec = media.get('encoding')
241 service = media.get('service')
242 for connection in self._extract_connections(media):
243 conn_formats = self._extract_connection(connection, programme_id)
244 for format in conn_formats:
246 'format_id': '%s_%s' % (service, format['format_id']),
250 formats.extend(conn_formats)
253 def _get_subtitles(self, media, programme_id):
255 for connection in self._extract_connections(media):
256 captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
257 lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
260 'url': connection.get('href'),
266 def _download_media_selector(self, programme_id):
268 media_selection = self._download_xml(
269 self.mediaselector_url % programme_id,
270 programme_id, 'Downloading media selection XML')
271 except ExtractorError as ee:
272 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
273 media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
280 for media in self._extract_medias(media_selection):
281 kind = media.get('kind')
283 formats.extend(self._extract_audio(media, programme_id))
284 elif kind == 'video':
285 formats.extend(self._extract_video(media, programme_id))
286 elif kind == 'captions':
287 subtitles = self.extract_subtitles(media, programme_id)
289 return formats, subtitles
291 def _download_playlist(self, playlist_id):
293 playlist = self._download_json(
294 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
295 playlist_id, 'Downloading playlist JSON')
297 version = playlist.get('defaultAvailableVersion')
299 smp_config = version['smpConfig']
300 title = smp_config['title']
301 description = smp_config['summary']
302 for item in smp_config['items']:
304 if kind != 'programme' and kind != 'radioProgramme':
306 programme_id = item.get('vpid')
307 duration = int_or_none(item.get('duration'))
308 formats, subtitles = self._download_media_selector(programme_id)
309 return programme_id, title, description, duration, formats, subtitles
310 except ExtractorError as ee:
311 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
314 # fallback to legacy playlist
315 playlist = self._download_xml(
316 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
317 playlist_id, 'Downloading legacy playlist XML')
319 no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
320 if no_items is not None:
321 reason = no_items.get('reason')
322 if reason == 'preAvailability':
323 msg = 'Episode %s is not yet available' % playlist_id
324 elif reason == 'postAvailability':
325 msg = 'Episode %s is no longer available' % playlist_id
326 elif reason == 'noMedia':
327 msg = 'Episode %s is not currently available' % playlist_id
329 msg = 'Episode %s is not available: %s' % (playlist_id, reason)
330 raise ExtractorError(msg, expected=True)
332 for item in self._extract_items(playlist):
333 kind = item.get('kind')
334 if kind != 'programme' and kind != 'radioProgramme':
336 title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
337 description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
338 programme_id = item.get('identifier')
339 duration = int_or_none(item.get('duration'))
340 formats, subtitles = self._download_media_selector(programme_id)
342 return programme_id, title, description, duration, formats, subtitles
344 def _real_extract(self, url):
345 group_id = self._match_id(url)
347 webpage = self._download_webpage(url, group_id, 'Downloading video page')
351 tviplayer = self._search_regex(
352 r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
353 webpage, 'player', default=None)
356 player = self._parse_json(tviplayer, group_id).get('player', {})
357 duration = int_or_none(player.get('duration'))
358 programme_id = player.get('vpid')
361 programme_id = self._search_regex(
362 r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)
365 formats, subtitles = self._download_media_selector(programme_id)
366 title = self._og_search_title(webpage)
367 description = self._search_regex(
368 r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
369 webpage, 'description', fatal=False)
371 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
373 self._sort_formats(formats)
378 'description': description,
379 'thumbnail': self._og_search_thumbnail(webpage, default=None),
380 'duration': duration,
382 'subtitles': subtitles,
386 class BBCNewsIE(BBCCoUkIE):
389 _VALID_URL = r'https?://(?:www\.)?bbc\.com/.+?/(?P<id>[^/]+)$'
391 mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'
394 'url': 'http://www.bbc.com/news/world-europe-32668511',
396 'id': 'world-europe-32668511',
397 'title': 'Russia stages massive WW2 parade despite Western boycott',
401 'url': 'http://www.bbc.com/news/business-28299555',
403 'id': 'business-28299555',
404 'title': 'Farnborough Airshow: Video highlights',
408 'url': 'http://www.bbc.com/news/world-europe-32041533',
413 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
414 'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
416 'upload_date': '20150324',
417 'uploader': 'BBC News',
420 'skip_download': True,
423 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
428 'title': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
429 'description': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
431 'upload_date': '20150615',
432 'uploader': 'BBC News',
435 'skip_download': True,
438 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
443 'title': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
444 'description': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
446 'upload_date': '20150619',
447 'uploader': 'BBC News',
450 'skip_download': True,
454 def _real_extract(self, url):
455 list_id = self._match_id(url)
456 webpage = self._download_webpage(url, list_id)
458 list_title = self._html_search_regex(r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'list title')
460 pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
462 pubdate = pubdate.replace('-', '')
467 # works with bbc.com/news/something-something-123456 articles
469 lambda m: self._parse_json(m, list_id),
470 re.findall(r"data-media-meta='({[^']+})'", webpage)
474 # http://www.bbc.com/news/video_and_audio/international
475 # and single-video articles
476 masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
478 jmasset = self._parse_json(masset, list_id)
479 for key, val in jmasset.get('videos', {}).items():
480 for skey, sval in val.items():
485 # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
486 # in http://www.bbc.com/news/video_and_audio/international
487 # prone to breaking if entries have sourceFiles list
489 lambda m: self._parse_json(m, list_id),
490 re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
494 raise ExtractorError('No video found', expected=True)
497 programme_id = jent.get('externalId')
498 xml_url = jent.get('href')
500 title = jent.get('caption', '')
504 duration = parse_duration(jent.get('duration'))
505 description = list_title
506 if jent.get('caption', '') != '':
507 description += ' - ' + jent.get('caption')
509 if jent.get('image') is not None:
510 thumbnail = jent['image'].get('href')
516 formats, subtitles = self._download_media_selector(programme_id)
517 elif jent.get('sourceFiles') is not None:
518 # mediaselector not used at
519 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
520 for key, val in jent['sourceFiles'].items():
522 'ext': val.get('encoding'),
523 'url': val.get('url'),
524 'filesize': int(val.get('filesize')),
529 # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
530 xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
531 programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
532 formats, subtitles = self._download_media_selector(programme_id)
534 if len(formats) == 0:
535 raise ExtractorError('unsupported json media entry.\n ' + str(jent) + '\n')
537 self._sort_formats(formats)
539 id = jent.get('id') if programme_id is None else programme_id
545 'uploader': 'BBC News',
546 'upload_date': pubdate,
548 'description': description,
549 'thumbnail': thumbnail,
550 'duration': duration,
552 'subtitles': subtitles,
556 return self.playlist_result(ret, list_id, list_title)
557 raise ExtractorError('No video found', expected=True)