]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/bbc.py
Update upstream source from tag 'upstream/2019.09.28'
[youtubedl] / youtube_dl / extractor / bbc.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import itertools
5 import re
6
7 from .common import InfoExtractor
8 from ..utils import (
9 clean_html,
10 dict_get,
11 ExtractorError,
12 float_or_none,
13 get_element_by_class,
14 int_or_none,
15 js_to_json,
16 parse_duration,
17 parse_iso8601,
18 try_get,
19 unescapeHTML,
20 url_or_none,
21 urlencode_postdata,
22 urljoin,
23 )
24 from ..compat import (
25 compat_etree_Element,
26 compat_HTTPError,
27 compat_urlparse,
28 )
29
30
31 class BBCCoUkIE(InfoExtractor):
32 IE_NAME = 'bbc.co.uk'
33 IE_DESC = 'BBC iPlayer'
34 _ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
35 _VALID_URL = r'''(?x)
36 https?://
37 (?:www\.)?bbc\.co\.uk/
38 (?:
39 programmes/(?!articles/)|
40 iplayer(?:/[^/]+)?/(?:episode/|playlist/)|
41 music/(?:clips|audiovideo/popular)[/#]|
42 radio/player/|
43 sounds/play/|
44 events/[^/]+/play/[^/]+/
45 )
46 (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
47 ''' % _ID_REGEX
48
49 _LOGIN_URL = 'https://account.bbc.com/signin'
50 _NETRC_MACHINE = 'bbc'
51
52 _MEDIASELECTOR_URLS = [
53 # Provides HQ HLS streams with even better quality that pc mediaset but fails
54 # with geolocation in some cases when it's even not geo restricted at all (e.g.
55 # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable.
56 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
57 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s',
58 ]
59
60 _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection'
61 _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist'
62
63 _NAMESPACES = (
64 _MEDIASELECTION_NS,
65 _EMP_PLAYLIST_NS,
66 )
67
68 _TESTS = [
69 {
70 'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
71 'info_dict': {
72 'id': 'b039d07m',
73 'ext': 'flv',
74 'title': 'Kaleidoscope, Leonard Cohen',
75 'description': 'The Canadian poet and songwriter reflects on his musical career.',
76 },
77 'params': {
78 # rtmp download
79 'skip_download': True,
80 }
81 },
82 {
83 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
84 'info_dict': {
85 'id': 'b00yng1d',
86 'ext': 'flv',
87 'title': 'The Man in Black: Series 3: The Printed Name',
88 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
89 'duration': 1800,
90 },
91 'params': {
92 # rtmp download
93 'skip_download': True,
94 },
95 'skip': 'Episode is no longer available on BBC iPlayer Radio',
96 },
97 {
98 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
99 'info_dict': {
100 'id': 'b00yng1d',
101 'ext': 'flv',
102 'title': 'The Voice UK: Series 3: Blind Auditions 5',
103 '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.',
104 'duration': 5100,
105 },
106 'params': {
107 # rtmp download
108 'skip_download': True,
109 },
110 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
111 },
112 {
113 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
114 'info_dict': {
115 'id': 'b03k3pb7',
116 'ext': 'flv',
117 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
118 'description': '2. Invasion',
119 'duration': 3600,
120 },
121 'params': {
122 # rtmp download
123 'skip_download': True,
124 },
125 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
126 }, {
127 'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
128 'info_dict': {
129 'id': 'b04v209v',
130 'ext': 'flv',
131 'title': 'Pete Tong, The Essential New Tune Special',
132 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
133 'duration': 10800,
134 },
135 'params': {
136 # rtmp download
137 'skip_download': True,
138 },
139 'skip': 'Episode is no longer available on BBC iPlayer Radio',
140 }, {
141 'url': 'http://www.bbc.co.uk/music/clips/p022h44b',
142 'note': 'Audio',
143 'info_dict': {
144 'id': 'p022h44j',
145 'ext': 'flv',
146 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances',
147 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.",
148 'duration': 227,
149 },
150 'params': {
151 # rtmp download
152 'skip_download': True,
153 }
154 }, {
155 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
156 'note': 'Video',
157 'info_dict': {
158 'id': 'p025c103',
159 'ext': 'flv',
160 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
161 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
162 'duration': 226,
163 },
164 'params': {
165 # rtmp download
166 'skip_download': True,
167 }
168 }, {
169 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
170 'info_dict': {
171 'id': 'p02n76xf',
172 'ext': 'flv',
173 'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
174 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
175 'duration': 3540,
176 },
177 'params': {
178 # rtmp download
179 'skip_download': True,
180 },
181 'skip': 'geolocation',
182 }, {
183 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
184 'info_dict': {
185 'id': 'b05zmgw1',
186 'ext': 'flv',
187 '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.',
188 'title': 'Royal Academy Summer Exhibition',
189 'duration': 3540,
190 },
191 'params': {
192 # rtmp download
193 'skip_download': True,
194 },
195 'skip': 'geolocation',
196 }, {
197 # iptv-all mediaset fails with geolocation however there is no geo restriction
198 # for this programme at all
199 'url': 'http://www.bbc.co.uk/programmes/b06rkn85',
200 'info_dict': {
201 'id': 'b06rkms3',
202 'ext': 'flv',
203 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1",
204 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!",
205 },
206 'params': {
207 # rtmp download
208 'skip_download': True,
209 },
210 'skip': 'Now it\'s really geo-restricted',
211 }, {
212 # compact player (https://github.com/ytdl-org/youtube-dl/issues/8147)
213 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player',
214 'info_dict': {
215 'id': 'p028bfkj',
216 'ext': 'flv',
217 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
218 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews',
219 },
220 'params': {
221 # rtmp download
222 'skip_download': True,
223 },
224 }, {
225 'url': 'https://www.bbc.co.uk/sounds/play/m0007jzb',
226 'note': 'Audio',
227 'info_dict': {
228 'id': 'm0007jz9',
229 'ext': 'mp4',
230 'title': 'BBC Proms, 2019, Prom 34: Westā€“Eastern Divan Orchestra',
231 'description': "Live BBC Proms. Westā€“Eastern Divan Orchestra with Daniel Barenboim and Martha Argerich.",
232 'duration': 9840,
233 },
234 'params': {
235 # rtmp download
236 'skip_download': True,
237 }
238 }, {
239 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
240 'only_matching': True,
241 }, {
242 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
243 'only_matching': True,
244 }, {
245 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
246 'only_matching': True,
247 }, {
248 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf',
249 'only_matching': True,
250 }, {
251 'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55',
252 'only_matching': True,
253 }, {
254 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
255 'only_matching': True,
256 }, {
257 'url': 'https://www.bbc.co.uk/programmes/m00005xn',
258 'only_matching': True,
259 }, {
260 'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s',
261 'only_matching': True,
262 }]
263
264 _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
265
266 def _login(self):
267 username, password = self._get_login_info()
268 if username is None:
269 return
270
271 login_page = self._download_webpage(
272 self._LOGIN_URL, None, 'Downloading signin page')
273
274 login_form = self._hidden_inputs(login_page)
275
276 login_form.update({
277 'username': username,
278 'password': password,
279 })
280
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'))
284
285 response, urlh = self._download_webpage_handle(
286 post_url, None, 'Logging in', data=urlencode_postdata(login_form),
287 headers={'Referer': self._LOGIN_URL})
288
289 if self._LOGIN_URL in urlh.geturl():
290 error = clean_html(get_element_by_class('form-message', response))
291 if error:
292 raise ExtractorError(
293 'Unable to login: %s' % error, expected=True)
294 raise ExtractorError('Unable to log in')
295
296 def _real_initialize(self):
297 self._login()
298
299 class MediaSelectionError(Exception):
300 def __init__(self, id):
301 self.id = id
302
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')]
306
307 def _extract_items(self, playlist):
308 return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS)
309
310 def _findall_ns(self, element, xpath):
311 elements = []
312 for ns in self._NAMESPACES:
313 elements.extend(element.findall(xpath % ns))
314 return elements
315
316 def _extract_medias(self, media_selection):
317 error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS)
318 if error is None:
319 media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS)
320 if error is not None:
321 raise BBCCoUkIE.MediaSelectionError(error.get('id'))
322 return self._findall_ns(media_selection, './{%s}media')
323
324 def _extract_connections(self, media):
325 return self._findall_ns(media, './{%s}connection')
326
327 def _get_subtitles(self, media, programme_id):
328 subtitles = {}
329 for connection in self._extract_connections(media):
330 cc_url = url_or_none(connection.get('href'))
331 if not cc_url:
332 continue
333 captions = self._download_xml(
334 cc_url, programme_id, 'Downloading captions', fatal=False)
335 if not isinstance(captions, compat_etree_Element):
336 continue
337 lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
338 subtitles[lang] = [
339 {
340 'url': connection.get('href'),
341 'ext': 'ttml',
342 },
343 ]
344 return subtitles
345
346 def _raise_extractor_error(self, media_selection_error):
347 raise ExtractorError(
348 '%s returned error: %s' % (self.IE_NAME, media_selection_error.id),
349 expected=True)
350
351 def _download_media_selector(self, programme_id):
352 last_exception = None
353 for mediaselector_url in self._MEDIASELECTOR_URLS:
354 try:
355 return self._download_media_selector_url(
356 mediaselector_url % programme_id, programme_id)
357 except BBCCoUkIE.MediaSelectionError as e:
358 if e.id in ('notukerror', 'geolocation', 'selectionunavailable'):
359 last_exception = e
360 continue
361 self._raise_extractor_error(e)
362 self._raise_extractor_error(last_exception)
363
364 def _download_media_selector_url(self, url, programme_id=None):
365 media_selection = self._download_xml(
366 url, programme_id, 'Downloading media selection XML',
367 expected_status=(403, 404))
368 return self._process_media_selector(media_selection, programme_id)
369
370 def _process_media_selector(self, media_selection, programme_id):
371 formats = []
372 subtitles = None
373 urls = []
374
375 for media in self._extract_medias(media_selection):
376 kind = media.get('kind')
377 if kind in ('video', 'audio'):
378 bitrate = int_or_none(media.get('bitrate'))
379 encoding = media.get('encoding')
380 service = media.get('service')
381 width = int_or_none(media.get('width'))
382 height = int_or_none(media.get('height'))
383 file_size = int_or_none(media.get('media_file_size'))
384 for connection in self._extract_connections(media):
385 href = connection.get('href')
386 if href in urls:
387 continue
388 if href:
389 urls.append(href)
390 conn_kind = connection.get('kind')
391 protocol = connection.get('protocol')
392 supplier = connection.get('supplier')
393 transfer_format = connection.get('transferFormat')
394 format_id = supplier or conn_kind or protocol
395 if service:
396 format_id = '%s_%s' % (service, format_id)
397 # ASX playlist
398 if supplier == 'asx':
399 for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
400 formats.append({
401 'url': ref,
402 'format_id': 'ref%s_%s' % (i, format_id),
403 })
404 elif transfer_format == 'dash':
405 formats.extend(self._extract_mpd_formats(
406 href, programme_id, mpd_id=format_id, fatal=False))
407 elif transfer_format == 'hls':
408 formats.extend(self._extract_m3u8_formats(
409 href, programme_id, ext='mp4', entry_protocol='m3u8_native',
410 m3u8_id=format_id, fatal=False))
411 if re.search(self._USP_RE, href):
412 usp_formats = self._extract_m3u8_formats(
413 re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href),
414 programme_id, ext='mp4', entry_protocol='m3u8_native',
415 m3u8_id=format_id, fatal=False)
416 for f in usp_formats:
417 if f.get('height') and f['height'] > 720:
418 continue
419 formats.append(f)
420 elif transfer_format == 'hds':
421 formats.extend(self._extract_f4m_formats(
422 href, programme_id, f4m_id=format_id, fatal=False))
423 else:
424 if not service and not supplier and bitrate:
425 format_id += '-%d' % bitrate
426 fmt = {
427 'format_id': format_id,
428 'filesize': file_size,
429 }
430 if kind == 'video':
431 fmt.update({
432 'width': width,
433 'height': height,
434 'tbr': bitrate,
435 'vcodec': encoding,
436 })
437 else:
438 fmt.update({
439 'abr': bitrate,
440 'acodec': encoding,
441 'vcodec': 'none',
442 })
443 if protocol in ('http', 'https'):
444 # Direct link
445 fmt.update({
446 'url': href,
447 })
448 elif protocol == 'rtmp':
449 application = connection.get('application', 'ondemand')
450 auth_string = connection.get('authString')
451 identifier = connection.get('identifier')
452 server = connection.get('server')
453 fmt.update({
454 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
455 'play_path': identifier,
456 'app': '%s?%s' % (application, auth_string),
457 'page_url': 'http://www.bbc.co.uk',
458 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
459 'rtmp_live': False,
460 'ext': 'flv',
461 })
462 else:
463 continue
464 formats.append(fmt)
465 elif kind == 'captions':
466 subtitles = self.extract_subtitles(media, programme_id)
467 return formats, subtitles
468
469 def _download_playlist(self, playlist_id):
470 try:
471 playlist = self._download_json(
472 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
473 playlist_id, 'Downloading playlist JSON')
474
475 version = playlist.get('defaultAvailableVersion')
476 if version:
477 smp_config = version['smpConfig']
478 title = smp_config['title']
479 description = smp_config['summary']
480 for item in smp_config['items']:
481 kind = item['kind']
482 if kind not in ('programme', 'radioProgramme'):
483 continue
484 programme_id = item.get('vpid')
485 duration = int_or_none(item.get('duration'))
486 formats, subtitles = self._download_media_selector(programme_id)
487 return programme_id, title, description, duration, formats, subtitles
488 except ExtractorError as ee:
489 if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
490 raise
491
492 # fallback to legacy playlist
493 return self._process_legacy_playlist(playlist_id)
494
495 def _process_legacy_playlist_url(self, url, display_id):
496 playlist = self._download_legacy_playlist_url(url, display_id)
497 return self._extract_from_legacy_playlist(playlist, display_id)
498
499 def _process_legacy_playlist(self, playlist_id):
500 return self._process_legacy_playlist_url(
501 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id)
502
503 def _download_legacy_playlist_url(self, url, playlist_id=None):
504 return self._download_xml(
505 url, playlist_id, 'Downloading legacy playlist XML')
506
507 def _extract_from_legacy_playlist(self, playlist, playlist_id):
508 no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS)
509 if no_items is not None:
510 reason = no_items.get('reason')
511 if reason == 'preAvailability':
512 msg = 'Episode %s is not yet available' % playlist_id
513 elif reason == 'postAvailability':
514 msg = 'Episode %s is no longer available' % playlist_id
515 elif reason == 'noMedia':
516 msg = 'Episode %s is not currently available' % playlist_id
517 else:
518 msg = 'Episode %s is not available: %s' % (playlist_id, reason)
519 raise ExtractorError(msg, expected=True)
520
521 for item in self._extract_items(playlist):
522 kind = item.get('kind')
523 if kind not in ('programme', 'radioProgramme'):
524 continue
525 title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text
526 description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS)
527 description = description_el.text if description_el is not None else None
528
529 def get_programme_id(item):
530 def get_from_attributes(item):
531 for p in('identifier', 'group'):
532 value = item.get(p)
533 if value and re.match(r'^[pb][\da-z]{7}$', value):
534 return value
535 get_from_attributes(item)
536 mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS)
537 if mediator is not None:
538 return get_from_attributes(mediator)
539
540 programme_id = get_programme_id(item)
541 duration = int_or_none(item.get('duration'))
542
543 if programme_id:
544 formats, subtitles = self._download_media_selector(programme_id)
545 else:
546 formats, subtitles = self._process_media_selector(item, playlist_id)
547 programme_id = playlist_id
548
549 return programme_id, title, description, duration, formats, subtitles
550
551 def _real_extract(self, url):
552 group_id = self._match_id(url)
553
554 webpage = self._download_webpage(url, group_id, 'Downloading video page')
555
556 error = self._search_regex(
557 r'<div\b[^>]+\bclass=["\']smp__message delta["\'][^>]*>([^<]+)<',
558 webpage, 'error', default=None)
559 if error:
560 raise ExtractorError(error, expected=True)
561
562 programme_id = None
563 duration = None
564
565 tviplayer = self._search_regex(
566 r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
567 webpage, 'player', default=None)
568
569 if tviplayer:
570 player = self._parse_json(tviplayer, group_id).get('player', {})
571 duration = int_or_none(player.get('duration'))
572 programme_id = player.get('vpid')
573
574 if not programme_id:
575 programme_id = self._search_regex(
576 r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None)
577
578 if programme_id:
579 formats, subtitles = self._download_media_selector(programme_id)
580 title = self._og_search_title(webpage, default=None) or self._html_search_regex(
581 (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>',
582 r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title')
583 description = self._search_regex(
584 (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
585 r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'),
586 webpage, 'description', default=None)
587 if not description:
588 description = self._html_search_meta('description', webpage)
589 else:
590 programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)
591
592 self._sort_formats(formats)
593
594 return {
595 'id': programme_id,
596 'title': title,
597 'description': description,
598 'thumbnail': self._og_search_thumbnail(webpage, default=None),
599 'duration': duration,
600 'formats': formats,
601 'subtitles': subtitles,
602 }
603
604
605 class BBCIE(BBCCoUkIE):
606 IE_NAME = 'bbc'
607 IE_DESC = 'BBC'
608 _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)'
609
610 _MEDIASELECTOR_URLS = [
611 # Provides HQ HLS streams but fails with geolocation in some cases when it's
612 # even not geo restricted at all
613 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s',
614 # Provides more formats, namely direct mp4 links, but fails on some videos with
615 # notukerror for non UK (?) users (e.g.
616 # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
617 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s',
618 # Provides fewer formats, but works everywhere for everybody (hopefully)
619 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s',
620 ]
621
622 _TESTS = [{
623 # article with multiple videos embedded with data-playable containing vpids
624 'url': 'http://www.bbc.com/news/world-europe-32668511',
625 'info_dict': {
626 'id': 'world-europe-32668511',
627 'title': 'Russia stages massive WW2 parade',
628 'description': 'md5:00ff61976f6081841f759a08bf78cc9c',
629 },
630 'playlist_count': 2,
631 }, {
632 # article with multiple videos embedded with data-playable (more videos)
633 'url': 'http://www.bbc.com/news/business-28299555',
634 'info_dict': {
635 'id': 'business-28299555',
636 'title': 'Farnborough Airshow: Video highlights',
637 'description': 'BBC reports and video highlights at the Farnborough Airshow.',
638 },
639 'playlist_count': 9,
640 'skip': 'Save time',
641 }, {
642 # article with multiple videos embedded with `new SMP()`
643 # broken
644 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460',
645 'info_dict': {
646 'id': '3662a707-0af9-3149-963f-47bea720b460',
647 'title': 'BUGGER',
648 },
649 'playlist_count': 18,
650 }, {
651 # single video embedded with data-playable containing vpid
652 'url': 'http://www.bbc.com/news/world-europe-32041533',
653 'info_dict': {
654 'id': 'p02mprgb',
655 'ext': 'mp4',
656 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
657 'description': 'md5:2868290467291b37feda7863f7a83f54',
658 'duration': 47,
659 'timestamp': 1427219242,
660 'upload_date': '20150324',
661 },
662 'params': {
663 # rtmp download
664 'skip_download': True,
665 }
666 }, {
667 # article with single video embedded with data-playable containing XML playlist
668 # with direct video links as progressiveDownloadUrl (for now these are extracted)
669 # and playlist with f4m and m3u8 as streamingUrl
670 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
671 'info_dict': {
672 'id': '150615_telabyad_kentin_cogu',
673 'ext': 'mp4',
674 'title': "YPG: Tel Abyad'ın tamamı kontrolĆ¼mĆ¼zde",
675 'description': 'md5:33a4805a855c9baf7115fcbde57e7025',
676 'timestamp': 1434397334,
677 'upload_date': '20150615',
678 },
679 'params': {
680 'skip_download': True,
681 }
682 }, {
683 # single video embedded with data-playable containing XML playlists (regional section)
684 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
685 'info_dict': {
686 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw',
687 'ext': 'mp4',
688 'title': 'Honduras militariza sus hospitales por nuevo escĆ”ndalo de corrupciĆ³n',
689 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8',
690 'timestamp': 1434713142,
691 'upload_date': '20150619',
692 },
693 'params': {
694 'skip_download': True,
695 }
696 }, {
697 # single video from video playlist embedded with vxp-playlist-data JSON
698 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376',
699 'info_dict': {
700 'id': 'p02w6qjc',
701 'ext': 'mp4',
702 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
703 'duration': 56,
704 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''',
705 },
706 'params': {
707 'skip_download': True,
708 }
709 }, {
710 # single video story with digitalData
711 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret',
712 'info_dict': {
713 'id': 'p02q6gc4',
714 'ext': 'flv',
715 'title': 'Sri Lankaā€™s spicy secret',
716 'description': 'As a new train line to Jaffna opens up the countryā€™s north, travellers can experience a truly distinct slice of Tamil culture.',
717 'timestamp': 1437674293,
718 'upload_date': '20150723',
719 },
720 'params': {
721 # rtmp download
722 'skip_download': True,
723 }
724 }, {
725 # single video story without digitalData
726 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star',
727 'info_dict': {
728 'id': 'p018zqqg',
729 'ext': 'mp4',
730 'title': 'Hyundai Santa Fe Sport: Rock star',
731 'description': 'md5:b042a26142c4154a6e472933cf20793d',
732 'timestamp': 1415867444,
733 'upload_date': '20141113',
734 },
735 'params': {
736 # rtmp download
737 'skip_download': True,
738 }
739 }, {
740 # single video embedded with Morph
741 'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975',
742 'info_dict': {
743 'id': 'p041vhd0',
744 'ext': 'mp4',
745 'title': "Nigeria v Japan - Men's First Round",
746 'description': 'Live coverage of the first round from Group B at the Amazonia Arena.',
747 'duration': 7980,
748 'uploader': 'BBC Sport',
749 'uploader_id': 'bbc_sport',
750 },
751 'params': {
752 # m3u8 download
753 'skip_download': True,
754 },
755 'skip': 'Georestricted to UK',
756 }, {
757 # single video with playlist.sxml URL in playlist param
758 'url': 'http://www.bbc.com/sport/0/football/33653409',
759 'info_dict': {
760 'id': 'p02xycnp',
761 'ext': 'mp4',
762 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
763 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.',
764 'duration': 140,
765 },
766 'params': {
767 # rtmp download
768 'skip_download': True,
769 }
770 }, {
771 # article with multiple videos embedded with playlist.sxml in playlist param
772 'url': 'http://www.bbc.com/sport/0/football/34475836',
773 'info_dict': {
774 'id': '34475836',
775 'title': 'Jurgen Klopp: Furious football from a witty and winning coach',
776 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.',
777 },
778 'playlist_count': 3,
779 }, {
780 # school report article with single video
781 'url': 'http://www.bbc.co.uk/schoolreport/35744779',
782 'info_dict': {
783 'id': '35744779',
784 'title': 'School which breaks down barriers in Jerusalem',
785 },
786 'playlist_count': 1,
787 }, {
788 # single video with playlist URL from weather section
789 'url': 'http://www.bbc.com/weather/features/33601775',
790 'only_matching': True,
791 }, {
792 # custom redirection to www.bbc.com
793 'url': 'http://www.bbc.co.uk/news/science-environment-33661876',
794 'only_matching': True,
795 }, {
796 # single video article embedded with data-media-vpid
797 'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
798 'only_matching': True,
799 }, {
800 'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
801 'info_dict': {
802 'id': 'p06556y7',
803 'ext': 'mp4',
804 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
805 'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
806 },
807 'params': {
808 'skip_download': True,
809 }
810 }, {
811 # window.__PRELOADED_STATE__
812 'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
813 'info_dict': {
814 'id': 'b0b9z4vz',
815 'ext': 'mp4',
816 'title': 'Prom 6: An American in Paris and Turangalila',
817 'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
818 'uploader': 'Radio 3',
819 'uploader_id': 'bbc_radio_three',
820 },
821 }, {
822 'url': 'http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227',
823 'info_dict': {
824 'id': 'p06w9tws',
825 'ext': 'mp4',
826 'title': 'md5:2fabf12a726603193a2879a055f72514',
827 'description': 'Learn English words and phrases from this story',
828 },
829 'add_ie': [BBCCoUkIE.ie_key()],
830 }]
831
832 @classmethod
833 def suitable(cls, url):
834 EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
835 return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
836 else super(BBCIE, cls).suitable(url))
837
838 def _extract_from_media_meta(self, media_meta, video_id):
839 # Direct links to media in media metadata (e.g.
840 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
841 # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml
842 source_files = media_meta.get('sourceFiles')
843 if source_files:
844 return [{
845 'url': f['url'],
846 'format_id': format_id,
847 'ext': f.get('encoding'),
848 'tbr': float_or_none(f.get('bitrate'), 1000),
849 'filesize': int_or_none(f.get('filesize')),
850 } for format_id, f in source_files.items() if f.get('url')], []
851
852 programme_id = media_meta.get('externalId')
853 if programme_id:
854 return self._download_media_selector(programme_id)
855
856 # Process playlist.sxml as legacy playlist
857 href = media_meta.get('href')
858 if href:
859 playlist = self._download_legacy_playlist_url(href)
860 _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id)
861 return formats, subtitles
862
863 return [], []
864
865 def _extract_from_playlist_sxml(self, url, playlist_id, timestamp):
866 programme_id, title, description, duration, formats, subtitles = \
867 self._process_legacy_playlist_url(url, playlist_id)
868 self._sort_formats(formats)
869 return {
870 'id': programme_id,
871 'title': title,
872 'description': description,
873 'duration': duration,
874 'timestamp': timestamp,
875 'formats': formats,
876 'subtitles': subtitles,
877 }
878
879 def _real_extract(self, url):
880 playlist_id = self._match_id(url)
881
882 webpage = self._download_webpage(url, playlist_id)
883
884 json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
885 timestamp = json_ld_info.get('timestamp')
886
887 playlist_title = json_ld_info.get('title')
888 if not playlist_title:
889 playlist_title = self._og_search_title(
890 webpage, default=None) or self._html_search_regex(
891 r'<title>(.+?)</title>', webpage, 'playlist title', default=None)
892 if playlist_title:
893 playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
894
895 playlist_description = json_ld_info.get(
896 'description') or self._og_search_description(webpage, default=None)
897
898 if not timestamp:
899 timestamp = parse_iso8601(self._search_regex(
900 [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"',
901 r'itemprop="datePublished"[^>]+datetime="([^"]+)"',
902 r'"datePublished":\s*"([^"]+)'],
903 webpage, 'date', default=None))
904
905 entries = []
906
907 # article with multiple videos embedded with playlist.sxml (e.g.
908 # http://www.bbc.com/sport/0/football/34475836)
909 playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage)
910 playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage))
911 if playlists:
912 entries = [
913 self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp)
914 for playlist_url in playlists]
915
916 # news article with multiple videos embedded with data-playable
917 data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage)
918 if data_playables:
919 for _, data_playable_json in data_playables:
920 data_playable = self._parse_json(
921 unescapeHTML(data_playable_json), playlist_id, fatal=False)
922 if not data_playable:
923 continue
924 settings = data_playable.get('settings', {})
925 if settings:
926 # data-playable with video vpid in settings.playlistObject.items (e.g.
927 # http://www.bbc.com/news/world-us-canada-34473351)
928 playlist_object = settings.get('playlistObject', {})
929 if playlist_object:
930 items = playlist_object.get('items')
931 if items and isinstance(items, list):
932 title = playlist_object['title']
933 description = playlist_object.get('summary')
934 duration = int_or_none(items[0].get('duration'))
935 programme_id = items[0].get('vpid')
936 formats, subtitles = self._download_media_selector(programme_id)
937 self._sort_formats(formats)
938 entries.append({
939 'id': programme_id,
940 'title': title,
941 'description': description,
942 'timestamp': timestamp,
943 'duration': duration,
944 'formats': formats,
945 'subtitles': subtitles,
946 })
947 else:
948 # data-playable without vpid but with a playlist.sxml URLs
949 # in otherSettings.playlist (e.g.
950 # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani)
951 playlist = data_playable.get('otherSettings', {}).get('playlist', {})
952 if playlist:
953 entry = None
954 for key in ('streaming', 'progressiveDownload'):
955 playlist_url = playlist.get('%sUrl' % key)
956 if not playlist_url:
957 continue
958 try:
959 info = self._extract_from_playlist_sxml(
960 playlist_url, playlist_id, timestamp)
961 if not entry:
962 entry = info
963 else:
964 entry['title'] = info['title']
965 entry['formats'].extend(info['formats'])
966 except Exception as e:
967 # Some playlist URL may fail with 500, at the same time
968 # the other one may work fine (e.g.
969 # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
970 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500:
971 continue
972 raise
973 if entry:
974 self._sort_formats(entry['formats'])
975 entries.append(entry)
976
977 if entries:
978 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
979
980 # http://www.bbc.co.uk/learningenglish/chinese/features/lingohack/ep-181227
981 group_id = self._search_regex(
982 r'<div[^>]+\bclass=["\']video["\'][^>]+\bdata-pid=["\'](%s)' % self._ID_REGEX,
983 webpage, 'group id', default=None)
984 if playlist_id:
985 return self.url_result(
986 'https://www.bbc.co.uk/programmes/%s' % group_id,
987 ie=BBCCoUkIE.ie_key())
988
989 # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret)
990 programme_id = self._search_regex(
991 [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX,
992 r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX,
993 r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX],
994 webpage, 'vpid', default=None)
995
996 if programme_id:
997 formats, subtitles = self._download_media_selector(programme_id)
998 self._sort_formats(formats)
999 # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star)
1000 digital_data = self._parse_json(
1001 self._search_regex(
1002 r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'),
1003 programme_id, fatal=False)
1004 page_info = digital_data.get('page', {}).get('pageInfo', {})
1005 title = page_info.get('pageName') or self._og_search_title(webpage)
1006 description = page_info.get('description') or self._og_search_description(webpage)
1007 timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp
1008 return {
1009 'id': programme_id,
1010 'title': title,
1011 'description': description,
1012 'timestamp': timestamp,
1013 'formats': formats,
1014 'subtitles': subtitles,
1015 }
1016
1017 # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
1018 # There are several setPayload calls may be present but the video
1019 # seems to be always related to the first one
1020 morph_payload = self._parse_json(
1021 self._search_regex(
1022 r'Morph\.setPayload\([^,]+,\s*({.+?})\);',
1023 webpage, 'morph payload', default='{}'),
1024 playlist_id, fatal=False)
1025 if morph_payload:
1026 components = try_get(morph_payload, lambda x: x['body']['components'], list) or []
1027 for component in components:
1028 if not isinstance(component, dict):
1029 continue
1030 lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict)
1031 if not lead_media:
1032 continue
1033 identifiers = lead_media.get('identifiers')
1034 if not identifiers or not isinstance(identifiers, dict):
1035 continue
1036 programme_id = identifiers.get('vpid') or identifiers.get('playablePid')
1037 if not programme_id:
1038 continue
1039 title = lead_media.get('title') or self._og_search_title(webpage)
1040 formats, subtitles = self._download_media_selector(programme_id)
1041 self._sort_formats(formats)
1042 description = lead_media.get('summary')
1043 uploader = lead_media.get('masterBrand')
1044 uploader_id = lead_media.get('mid')
1045 duration = None
1046 duration_d = lead_media.get('duration')
1047 if isinstance(duration_d, dict):
1048 duration = parse_duration(dict_get(
1049 duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration')))
1050 return {
1051 'id': programme_id,
1052 'title': title,
1053 'description': description,
1054 'duration': duration,
1055 'uploader': uploader,
1056 'uploader_id': uploader_id,
1057 'formats': formats,
1058 'subtitles': subtitles,
1059 }
1060
1061 preload_state = self._parse_json(self._search_regex(
1062 r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
1063 'preload state', default='{}'), playlist_id, fatal=False)
1064 if preload_state:
1065 current_programme = preload_state.get('programmes', {}).get('current') or {}
1066 programme_id = current_programme.get('id')
1067 if current_programme and programme_id and current_programme.get('type') == 'playable_item':
1068 title = current_programme.get('titles', {}).get('tertiary') or playlist_title
1069 formats, subtitles = self._download_media_selector(programme_id)
1070 self._sort_formats(formats)
1071 synopses = current_programme.get('synopses') or {}
1072 network = current_programme.get('network') or {}
1073 duration = int_or_none(
1074 current_programme.get('duration', {}).get('value'))
1075 thumbnail = None
1076 image_url = current_programme.get('image_url')
1077 if image_url:
1078 thumbnail = image_url.replace('{recipe}', '1920x1920')
1079 return {
1080 'id': programme_id,
1081 'title': title,
1082 'description': dict_get(synopses, ('long', 'medium', 'short')),
1083 'thumbnail': thumbnail,
1084 'duration': duration,
1085 'uploader': network.get('short_title'),
1086 'uploader_id': network.get('id'),
1087 'formats': formats,
1088 'subtitles': subtitles,
1089 }
1090
1091 bbc3_config = self._parse_json(
1092 self._search_regex(
1093 r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
1094 'bbcthree config', default='{}'),
1095 playlist_id, transform_source=js_to_json, fatal=False)
1096 if bbc3_config:
1097 bbc3_playlist = try_get(
1098 bbc3_config, lambda x: x['payload']['content']['bbcMedia']['playlist'],
1099 dict)
1100 if bbc3_playlist:
1101 playlist_title = bbc3_playlist.get('title') or playlist_title
1102 thumbnail = bbc3_playlist.get('holdingImageURL')
1103 entries = []
1104 for bbc3_item in bbc3_playlist['items']:
1105 programme_id = bbc3_item.get('versionID')
1106 if not programme_id:
1107 continue
1108 formats, subtitles = self._download_media_selector(programme_id)
1109 self._sort_formats(formats)
1110 entries.append({
1111 'id': programme_id,
1112 'title': playlist_title,
1113 'thumbnail': thumbnail,
1114 'timestamp': timestamp,
1115 'formats': formats,
1116 'subtitles': subtitles,
1117 })
1118 return self.playlist_result(
1119 entries, playlist_id, playlist_title, playlist_description)
1120
1121 def extract_all(pattern):
1122 return list(filter(None, map(
1123 lambda s: self._parse_json(s, playlist_id, fatal=False),
1124 re.findall(pattern, webpage))))
1125
1126 # Multiple video article (e.g.
1127 # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460)
1128 EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX
1129 entries = []
1130 for match in extract_all(r'new\s+SMP\(({.+?})\)'):
1131 embed_url = match.get('playerSettings', {}).get('externalEmbedUrl')
1132 if embed_url and re.match(EMBED_URL, embed_url):
1133 entries.append(embed_url)
1134 entries.extend(re.findall(
1135 r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage))
1136 if entries:
1137 return self.playlist_result(
1138 [self.url_result(entry_, 'BBCCoUk') for entry_ in entries],
1139 playlist_id, playlist_title, playlist_description)
1140
1141 # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511)
1142 medias = extract_all(r"data-media-meta='({[^']+})'")
1143
1144 if not medias:
1145 # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international)
1146 media_asset = self._search_regex(
1147 r'mediaAssetPage\.init\(\s*({.+?}), "/',
1148 webpage, 'media asset', default=None)
1149 if media_asset:
1150 media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False)
1151 medias = []
1152 for video in media_asset_page.get('videos', {}).values():
1153 medias.extend(video.values())
1154
1155 if not medias:
1156 # Multiple video playlist with single `now playing` entry (e.g.
1157 # http://www.bbc.com/news/video_and_audio/must_see/33767813)
1158 vxp_playlist = self._parse_json(
1159 self._search_regex(
1160 r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>',
1161 webpage, 'playlist data'),
1162 playlist_id)
1163 playlist_medias = []
1164 for item in vxp_playlist:
1165 media = item.get('media')
1166 if not media:
1167 continue
1168 playlist_medias.append(media)
1169 # Download single video if found media with asset id matching the video id from URL
1170 if item.get('advert', {}).get('assetId') == playlist_id:
1171 medias = [media]
1172 break
1173 # Fallback to the whole playlist
1174 if not medias:
1175 medias = playlist_medias
1176
1177 entries = []
1178 for num, media_meta in enumerate(medias, start=1):
1179 formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id)
1180 if not formats:
1181 continue
1182 self._sort_formats(formats)
1183
1184 video_id = media_meta.get('externalId')
1185 if not video_id:
1186 video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num)
1187
1188 title = media_meta.get('caption')
1189 if not title:
1190 title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num)
1191
1192 duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration'))
1193
1194 images = []
1195 for image in media_meta.get('images', {}).values():
1196 images.extend(image.values())
1197 if 'image' in media_meta:
1198 images.append(media_meta['image'])
1199
1200 thumbnails = [{
1201 'url': image.get('href'),
1202 'width': int_or_none(image.get('width')),
1203 'height': int_or_none(image.get('height')),
1204 } for image in images]
1205
1206 entries.append({
1207 'id': video_id,
1208 'title': title,
1209 'thumbnails': thumbnails,
1210 'duration': duration,
1211 'timestamp': timestamp,
1212 'formats': formats,
1213 'subtitles': subtitles,
1214 })
1215
1216 return self.playlist_result(entries, playlist_id, playlist_title, playlist_description)
1217
1218
1219 class BBCCoUkArticleIE(InfoExtractor):
1220 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)'
1221 IE_NAME = 'bbc.co.uk:article'
1222 IE_DESC = 'BBC articles'
1223
1224 _TEST = {
1225 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer',
1226 'info_dict': {
1227 'id': '3jNQLTMrPlYGTBn0WV6M2MS',
1228 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four',
1229 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.',
1230 },
1231 'playlist_count': 4,
1232 'add_ie': ['BBCCoUk'],
1233 }
1234
1235 def _real_extract(self, url):
1236 playlist_id = self._match_id(url)
1237
1238 webpage = self._download_webpage(url, playlist_id)
1239
1240 title = self._og_search_title(webpage)
1241 description = self._og_search_description(webpage).strip()
1242
1243 entries = [self.url_result(programme_url) for programme_url in re.findall(
1244 r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)]
1245
1246 return self.playlist_result(entries, playlist_id, title, description)
1247
1248
1249 class BBCCoUkPlaylistBaseIE(InfoExtractor):
1250 def _entries(self, webpage, url, playlist_id):
1251 single_page = 'page' in compat_urlparse.parse_qs(
1252 compat_urlparse.urlparse(url).query)
1253 for page_num in itertools.count(2):
1254 for video_id in re.findall(
1255 self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage):
1256 yield self.url_result(
1257 self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key())
1258 if single_page:
1259 return
1260 next_page = self._search_regex(
1261 r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2',
1262 webpage, 'next page url', default=None, group='url')
1263 if not next_page:
1264 break
1265 webpage = self._download_webpage(
1266 compat_urlparse.urljoin(url, next_page), playlist_id,
1267 'Downloading page %d' % page_num, page_num)
1268
1269 def _real_extract(self, url):
1270 playlist_id = self._match_id(url)
1271
1272 webpage = self._download_webpage(url, playlist_id)
1273
1274 title, description = self._extract_title_and_description(webpage)
1275
1276 return self.playlist_result(
1277 self._entries(webpage, url, playlist_id),
1278 playlist_id, title, description)
1279
1280
1281 class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
1282 IE_NAME = 'bbc.co.uk:iplayer:playlist'
1283 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
1284 _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
1285 _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
1286 _TESTS = [{
1287 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
1288 'info_dict': {
1289 'id': 'b05rcz9v',
1290 'title': 'The Disappearance',
1291 'description': 'French thriller serial about a missing teenager.',
1292 },
1293 'playlist_mincount': 6,
1294 'skip': 'This programme is not currently available on BBC iPlayer',
1295 }, {
1296 # Available for over a year unlike 30 days for most other programmes
1297 'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
1298 'info_dict': {
1299 'id': 'p02tcc32',
1300 'title': 'Bohemian Icons',
1301 'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
1302 },
1303 'playlist_mincount': 10,
1304 }]
1305
1306 def _extract_title_and_description(self, webpage):
1307 title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
1308 description = self._search_regex(
1309 r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
1310 webpage, 'description', fatal=False, group='value')
1311 return title, description
1312
1313
1314 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):
1315 IE_NAME = 'bbc.co.uk:playlist'
1316 _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX
1317 _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s'
1318 _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)'
1319 _TESTS = [{
1320 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1321 'info_dict': {
1322 'id': 'b05rcz9v',
1323 'title': 'The Disappearance - Clips - BBC Four',
1324 'description': 'French thriller serial about a missing teenager.',
1325 },
1326 'playlist_mincount': 7,
1327 }, {
1328 # multipage playlist, explicit page
1329 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1',
1330 'info_dict': {
1331 'id': 'b00mfl7n',
1332 'title': 'Frozen Planet - Clips - BBC One',
1333 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1334 },
1335 'playlist_mincount': 24,
1336 }, {
1337 # multipage playlist, all pages
1338 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips',
1339 'info_dict': {
1340 'id': 'b00mfl7n',
1341 'title': 'Frozen Planet - Clips - BBC One',
1342 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c',
1343 },
1344 'playlist_mincount': 142,
1345 }, {
1346 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06',
1347 'only_matching': True,
1348 }, {
1349 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips',
1350 'only_matching': True,
1351 }, {
1352 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player',
1353 'only_matching': True,
1354 }]
1355
1356 def _extract_title_and_description(self, webpage):
1357 title = self._og_search_title(webpage, fatal=False)
1358 description = self._og_search_description(webpage)
1359 return title, description