]>
Commit | Line | Data |
---|---|---|
9afa1770 | 1 | # coding: utf-8 |
082c6c86 S |
2 | from __future__ import unicode_literals |
3 | ||
9afa1770 | 4 | import re |
c056efa2 | 5 | import xml.etree.ElementTree |
082c6c86 | 6 | |
f13b1e7d | 7 | from .common import InfoExtractor |
8683b4d8 S |
8 | from ..utils import ( |
9 | ExtractorError, | |
9afa1770 | 10 | float_or_none, |
8683b4d8 | 11 | int_or_none, |
9afa1770 S |
12 | parse_duration, |
13 | parse_iso8601, | |
8683b4d8 | 14 | ) |
c056efa2 | 15 | from ..compat import compat_HTTPError |
082c6c86 | 16 | |
d12a1a47 | 17 | |
f13b1e7d | 18 | class BBCCoUkIE(InfoExtractor): |
082c6c86 | 19 | IE_NAME = 'bbc.co.uk' |
2e3fd9ec | 20 | IE_DESC = 'BBC iPlayer' |
0692ef86 | 21 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' |
082c6c86 | 22 | |
d12a1a47 | 23 | _MEDIASELECTOR_URLS = [ |
d1c694ea | 24 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', |
d12a1a47 S |
25 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', |
26 | ] | |
a8b081a0 | 27 | |
2e3fd9ec S |
28 | _TESTS = [ |
29 | { | |
f2d0fc68 | 30 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', |
2e3fd9ec | 31 | 'info_dict': { |
f2d0fc68 | 32 | 'id': 'b039d07m', |
2e3fd9ec | 33 | 'ext': 'flv', |
c4914185 S |
34 | 'title': 'Kaleidoscope, Leonard Cohen', |
35 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', | |
f2d0fc68 | 36 | 'duration': 1740, |
2e3fd9ec S |
37 | }, |
38 | 'params': { | |
39 | # rtmp download | |
40 | 'skip_download': True, | |
41 | } | |
082c6c86 | 42 | }, |
2e3fd9ec S |
43 | { |
44 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
45 | 'info_dict': { | |
46 | 'id': 'b00yng1d', | |
47 | 'ext': 'flv', | |
48 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
49 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
50 | 'duration': 1800, | |
51 | }, | |
52 | 'params': { | |
53 | # rtmp download | |
54 | 'skip_download': True, | |
c7f0177f S |
55 | }, |
56 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
2e3fd9ec S |
57 | }, |
58 | { | |
59 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
60 | 'info_dict': { | |
61 | 'id': 'b00yng1d', | |
62 | 'ext': 'flv', | |
17968e44 S |
63 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', |
64 | '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.", | |
65 | 'duration': 5100, | |
2e3fd9ec S |
66 | }, |
67 | 'params': { | |
68 | # rtmp download | |
69 | 'skip_download': True, | |
70 | }, | |
71 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
c056efa2 S |
72 | }, |
73 | { | |
74 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
75 | 'info_dict': { | |
76 | 'id': 'b03k3pb7', | |
77 | 'ext': 'flv', | |
78 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
79 | 'description': '2. Invasion', | |
80 | 'duration': 3600, | |
81 | }, | |
82 | 'params': { | |
83 | # rtmp download | |
84 | 'skip_download': True, | |
85 | }, | |
86 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
ae6986fb S |
87 | }, { |
88 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
89 | 'info_dict': { | |
90 | 'id': 'b04v209v', | |
91 | 'ext': 'flv', | |
92 | 'title': 'Pete Tong, The Essential New Tune Special', | |
93 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
94 | 'duration': 10800, | |
95 | }, | |
96 | 'params': { | |
97 | # rtmp download | |
98 | 'skip_download': True, | |
99 | } | |
c7e67594 S |
100 | }, { |
101 | 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', | |
102 | 'note': 'Audio', | |
103 | 'info_dict': { | |
104 | 'id': 'p02frcch', | |
105 | 'ext': 'flv', | |
106 | 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', | |
107 | 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', | |
108 | 'duration': 3507, | |
109 | }, | |
110 | 'params': { | |
111 | # rtmp download | |
112 | 'skip_download': True, | |
113 | } | |
114 | }, { | |
115 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
116 | 'note': 'Video', | |
117 | 'info_dict': { | |
118 | 'id': 'p025c103', | |
119 | 'ext': 'flv', | |
120 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', | |
121 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
122 | 'duration': 226, | |
123 | }, | |
124 | 'params': { | |
125 | # rtmp download | |
126 | 'skip_download': True, | |
127 | } | |
e68ae99a S |
128 | }, { |
129 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', | |
130 | 'info_dict': { | |
131 | 'id': 'p02n76xf', | |
132 | 'ext': 'flv', | |
133 | 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', | |
134 | 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', | |
135 | 'duration': 3540, | |
136 | }, | |
137 | 'params': { | |
138 | # rtmp download | |
139 | 'skip_download': True, | |
140 | }, | |
141 | 'skip': 'geolocation', | |
25fa8d66 YCH |
142 | }, { |
143 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', | |
144 | 'info_dict': { | |
145 | 'id': 'b05zmgw1', | |
146 | 'ext': 'flv', | |
147 | '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.', | |
148 | 'title': 'Royal Academy Summer Exhibition', | |
149 | 'duration': 3540, | |
150 | }, | |
151 | 'params': { | |
152 | # rtmp download | |
153 | 'skip_download': True, | |
154 | }, | |
155 | 'skip': 'geolocation', | |
31763975 S |
156 | }, { |
157 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
158 | 'only_matching': True, | |
c7e67594 S |
159 | }, { |
160 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
161 | 'only_matching': True, | |
0692ef86 S |
162 | }, { |
163 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
164 | 'only_matching': True, | |
ae6986fb | 165 | } |
2e3fd9ec S |
166 | ] |
167 | ||
d12a1a47 S |
168 | class MediaSelectionError(Exception): |
169 | def __init__(self, id): | |
170 | self.id = id | |
171 | ||
2e3fd9ec S |
172 | def _extract_asx_playlist(self, connection, programme_id): |
173 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
174 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
175 | ||
176 | def _extract_connection(self, connection, programme_id): | |
177 | formats = [] | |
178 | protocol = connection.get('protocol') | |
179 | supplier = connection.get('supplier') | |
180 | if protocol == 'http': | |
181 | href = connection.get('href') | |
7a896817 | 182 | transfer_format = connection.get('transferFormat') |
2e3fd9ec S |
183 | # ASX playlist |
184 | if supplier == 'asx': | |
185 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
186 | formats.append({ | |
187 | 'url': ref, | |
188 | 'format_id': 'ref%s_%s' % (i, supplier), | |
189 | }) | |
7a896817 S |
190 | # Skip DASH until supported |
191 | elif transfer_format == 'dash': | |
192 | pass | |
d1c694ea S |
193 | elif transfer_format == 'hls': |
194 | m3u8_formats = self._extract_m3u8_formats( | |
195 | href, programme_id, ext='mp4', entry_protocol='m3u8_native', | |
196 | m3u8_id=supplier, fatal=False) | |
197 | if m3u8_formats: | |
198 | formats.extend(m3u8_formats) | |
2e3fd9ec S |
199 | # Direct link |
200 | else: | |
201 | formats.append({ | |
202 | 'url': href, | |
203 | 'format_id': supplier, | |
204 | }) | |
205 | elif protocol == 'rtmp': | |
206 | application = connection.get('application', 'ondemand') | |
207 | auth_string = connection.get('authString') | |
208 | identifier = connection.get('identifier') | |
209 | server = connection.get('server') | |
210 | formats.append({ | |
211 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
212 | 'play_path': identifier, | |
213 | 'app': '%s?%s' % (application, auth_string), | |
214 | 'page_url': 'http://www.bbc.co.uk', | |
215 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
216 | 'rtmp_live': False, | |
217 | 'ext': 'flv', | |
218 | 'format_id': supplier, | |
219 | }) | |
220 | return formats | |
221 | ||
222 | def _extract_items(self, playlist): | |
223 | return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') | |
224 | ||
225 | def _extract_medias(self, media_selection): | |
c056efa2 S |
226 | error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') |
227 | if error is not None: | |
d12a1a47 | 228 | raise BBCCoUkIE.MediaSelectionError(error.get('id')) |
2e3fd9ec S |
229 | return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') |
230 | ||
231 | def _extract_connections(self, media): | |
232 | return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') | |
233 | ||
234 | def _extract_video(self, media, programme_id): | |
235 | formats = [] | |
d97f5cd7 | 236 | vbr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
237 | vcodec = media.get('encoding') |
238 | service = media.get('service') | |
d97f5cd7 S |
239 | width = int_or_none(media.get('width')) |
240 | height = int_or_none(media.get('height')) | |
241 | file_size = int_or_none(media.get('media_file_size')) | |
2e3fd9ec S |
242 | for connection in self._extract_connections(media): |
243 | conn_formats = self._extract_connection(connection, programme_id) | |
244 | for format in conn_formats: | |
245 | format.update({ | |
246 | 'format_id': '%s_%s' % (service, format['format_id']), | |
247 | 'width': width, | |
248 | 'height': height, | |
249 | 'vbr': vbr, | |
250 | 'vcodec': vcodec, | |
251 | 'filesize': file_size, | |
252 | }) | |
253 | formats.extend(conn_formats) | |
254 | return formats | |
255 | ||
256 | def _extract_audio(self, media, programme_id): | |
257 | formats = [] | |
d97f5cd7 | 258 | abr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
259 | acodec = media.get('encoding') |
260 | service = media.get('service') | |
261 | for connection in self._extract_connections(media): | |
262 | conn_formats = self._extract_connection(connection, programme_id) | |
263 | for format in conn_formats: | |
264 | format.update({ | |
265 | 'format_id': '%s_%s' % (service, format['format_id']), | |
266 | 'abr': abr, | |
267 | 'acodec': acodec, | |
268 | }) | |
269 | formats.extend(conn_formats) | |
270 | return formats | |
271 | ||
f13b1e7d | 272 | def _get_subtitles(self, media, programme_id): |
2e3fd9ec S |
273 | subtitles = {} |
274 | for connection in self._extract_connections(media): | |
275 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
276 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
f13b1e7d JMF |
277 | subtitles[lang] = [ |
278 | { | |
279 | 'url': connection.get('href'), | |
280 | 'ext': 'ttml', | |
281 | }, | |
f13b1e7d | 282 | ] |
2e3fd9ec | 283 | return subtitles |
082c6c86 | 284 | |
d12a1a47 S |
285 | def _raise_extractor_error(self, media_selection_error): |
286 | raise ExtractorError( | |
287 | '%s returned error: %s' % (self.IE_NAME, media_selection_error.id), | |
288 | expected=True) | |
289 | ||
c056efa2 | 290 | def _download_media_selector(self, programme_id): |
d12a1a47 S |
291 | last_exception = None |
292 | for mediaselector_url in self._MEDIASELECTOR_URLS: | |
293 | try: | |
294 | return self._download_media_selector_url( | |
295 | mediaselector_url % programme_id, programme_id) | |
296 | except BBCCoUkIE.MediaSelectionError as e: | |
ee3d5a6d | 297 | if e.id in ('notukerror', 'geolocation'): |
d12a1a47 S |
298 | last_exception = e |
299 | continue | |
300 | self._raise_extractor_error(e) | |
301 | self._raise_extractor_error(last_exception) | |
9afa1770 S |
302 | |
303 | def _download_media_selector_url(self, url, programme_id=None): | |
c056efa2 S |
304 | try: |
305 | media_selection = self._download_xml( | |
9afa1770 | 306 | url, programme_id, 'Downloading media selection XML') |
c056efa2 S |
307 | except ExtractorError as ee: |
308 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
974a6146 | 309 | media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) |
2e3fd9ec | 310 | else: |
c056efa2 | 311 | raise |
9afa1770 | 312 | return self._process_media_selector(media_selection, programme_id) |
082c6c86 | 313 | |
9afa1770 | 314 | def _process_media_selector(self, media_selection, programme_id): |
082c6c86 | 315 | formats = [] |
2e3fd9ec S |
316 | subtitles = None |
317 | ||
c056efa2 S |
318 | for media in self._extract_medias(media_selection): |
319 | kind = media.get('kind') | |
320 | if kind == 'audio': | |
321 | formats.extend(self._extract_audio(media, programme_id)) | |
322 | elif kind == 'video': | |
323 | formats.extend(self._extract_video(media, programme_id)) | |
324 | elif kind == 'captions': | |
f13b1e7d | 325 | subtitles = self.extract_subtitles(media, programme_id) |
c056efa2 | 326 | return formats, subtitles |
2e3fd9ec | 327 | |
ae6986fb S |
328 | def _download_playlist(self, playlist_id): |
329 | try: | |
330 | playlist = self._download_json( | |
331 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
332 | playlist_id, 'Downloading playlist JSON') | |
333 | ||
334 | version = playlist.get('defaultAvailableVersion') | |
335 | if version: | |
336 | smp_config = version['smpConfig'] | |
337 | title = smp_config['title'] | |
338 | description = smp_config['summary'] | |
339 | for item in smp_config['items']: | |
340 | kind = item['kind'] | |
341 | if kind != 'programme' and kind != 'radioProgramme': | |
342 | continue | |
343 | programme_id = item.get('vpid') | |
d97f5cd7 | 344 | duration = int_or_none(item.get('duration')) |
ae6986fb S |
345 | formats, subtitles = self._download_media_selector(programme_id) |
346 | return programme_id, title, description, duration, formats, subtitles | |
347 | except ExtractorError as ee: | |
f813928e | 348 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): |
ae6986fb S |
349 | raise |
350 | ||
351 | # fallback to legacy playlist | |
9afa1770 S |
352 | return self._process_legacy_playlist(playlist_id) |
353 | ||
354 | def _process_legacy_playlist_url(self, url, display_id): | |
355 | playlist = self._download_legacy_playlist_url(url, display_id) | |
356 | return self._extract_from_legacy_playlist(playlist, display_id) | |
357 | ||
358 | def _process_legacy_playlist(self, playlist_id): | |
359 | return self._process_legacy_playlist_url( | |
360 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) | |
361 | ||
362 | def _download_legacy_playlist_url(self, url, playlist_id=None): | |
363 | return self._download_xml( | |
364 | url, playlist_id, 'Downloading legacy playlist XML') | |
ae6986fb | 365 | |
9afa1770 | 366 | def _extract_from_legacy_playlist(self, playlist, playlist_id): |
ae6986fb S |
367 | no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') |
368 | if no_items is not None: | |
369 | reason = no_items.get('reason') | |
370 | if reason == 'preAvailability': | |
371 | msg = 'Episode %s is not yet available' % playlist_id | |
372 | elif reason == 'postAvailability': | |
373 | msg = 'Episode %s is no longer available' % playlist_id | |
374 | elif reason == 'noMedia': | |
375 | msg = 'Episode %s is not currently available' % playlist_id | |
376 | else: | |
377 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
378 | raise ExtractorError(msg, expected=True) | |
379 | ||
380 | for item in self._extract_items(playlist): | |
381 | kind = item.get('kind') | |
382 | if kind != 'programme' and kind != 'radioProgramme': | |
383 | continue | |
384 | title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | |
385 | description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | |
9afa1770 S |
386 | |
387 | def get_programme_id(item): | |
388 | def get_from_attributes(item): | |
389 | for p in('identifier', 'group'): | |
390 | value = item.get(p) | |
391 | if value and re.match(r'^[pb][\da-z]{7}$', value): | |
392 | return value | |
393 | get_from_attributes(item) | |
394 | mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') | |
395 | if mediator is not None: | |
396 | return get_from_attributes(mediator) | |
397 | ||
398 | programme_id = get_programme_id(item) | |
d97f5cd7 | 399 | duration = int_or_none(item.get('duration')) |
9afa1770 S |
400 | # TODO: programme_id can be None and media items can be incorporated right inside |
401 | # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
402 | # as f4m and m3u8 | |
ae6986fb S |
403 | formats, subtitles = self._download_media_selector(programme_id) |
404 | ||
405 | return programme_id, title, description, duration, formats, subtitles | |
406 | ||
c056efa2 S |
407 | def _real_extract(self, url): |
408 | group_id = self._match_id(url) | |
409 | ||
410 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
411 | ||
8683b4d8 S |
412 | programme_id = None |
413 | ||
414 | tviplayer = self._search_regex( | |
415 | r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', | |
416 | webpage, 'player', default=None) | |
417 | ||
418 | if tviplayer: | |
419 | player = self._parse_json(tviplayer, group_id).get('player', {}) | |
420 | duration = int_or_none(player.get('duration')) | |
421 | programme_id = player.get('vpid') | |
422 | ||
423 | if not programme_id: | |
424 | programme_id = self._search_regex( | |
425 | r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) | |
426 | ||
c056efa2 | 427 | if programme_id: |
c056efa2 | 428 | formats, subtitles = self._download_media_selector(programme_id) |
8683b4d8 S |
429 | title = self._og_search_title(webpage) |
430 | description = self._search_regex( | |
25fa8d66 | 431 | r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', |
8683b4d8 | 432 | webpage, 'description', fatal=False) |
c056efa2 | 433 | else: |
ae6986fb | 434 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |
2e3fd9ec | 435 | |
082c6c86 S |
436 | self._sort_formats(formats) |
437 | ||
438 | return { | |
2e3fd9ec | 439 | 'id': programme_id, |
082c6c86 S |
440 | 'title': title, |
441 | 'description': description, | |
650cfd0c | 442 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), |
082c6c86 S |
443 | 'duration': duration, |
444 | 'formats': formats, | |
2e3fd9ec | 445 | 'subtitles': subtitles, |
5f6a1245 | 446 | } |
10273d6e | 447 | |
448 | ||
9afa1770 S |
449 | class BBCIE(BBCCoUkIE): |
450 | IE_NAME = 'bbc' | |
451 | IE_DESC = 'BBC' | |
452 | _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)' | |
10273d6e | 453 | |
d12a1a47 S |
454 | _MEDIASELECTOR_URLS = [ |
455 | # Provides more formats, namely direct mp4 links, but fails on some videos with | |
456 | # notukerror for non UK (?) users (e.g. | |
457 | # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) | |
458 | 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s', | |
459 | # Provides fewer formats, but works everywhere for everybody (hopefully) | |
460 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s', | |
461 | ] | |
10273d6e | 462 | |
463 | _TESTS = [{ | |
9afa1770 S |
464 | # article with multiple videos embedded with data-media-meta containing |
465 | # playlist.sxml, externalId and no direct video links | |
10273d6e | 466 | 'url': 'http://www.bbc.com/news/world-europe-32668511', |
467 | 'info_dict': { | |
468 | 'id': 'world-europe-32668511', | |
469 | 'title': 'Russia stages massive WW2 parade despite Western boycott', | |
9afa1770 | 470 | 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', |
10273d6e | 471 | }, |
472 | 'playlist_count': 2, | |
a3bfddfa | 473 | }, { |
9afa1770 | 474 | # article with multiple videos embedded with data-media-meta (more videos) |
10273d6e | 475 | 'url': 'http://www.bbc.com/news/business-28299555', |
476 | 'info_dict': { | |
477 | 'id': 'business-28299555', | |
478 | 'title': 'Farnborough Airshow: Video highlights', | |
9afa1770 | 479 | 'description': 'BBC reports and video highlights at the Farnborough Airshow.', |
10273d6e | 480 | }, |
481 | 'playlist_count': 9, | |
9afa1770 | 482 | 'skip': 'Save time', |
88ed52ae S |
483 | }, { |
484 | # article with multiple videos embedded with `new SMP()` | |
485 | 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', | |
486 | 'info_dict': { | |
487 | 'id': '3662a707-0af9-3149-963f-47bea720b460', | |
488 | 'title': 'BBC Blogs - Adam Curtis - BUGGER', | |
489 | }, | |
490 | 'playlist_count': 18, | |
a3bfddfa | 491 | }, { |
9afa1770 | 492 | # single video embedded with mediaAssetPage.init() |
10273d6e | 493 | 'url': 'http://www.bbc.com/news/world-europe-32041533', |
10273d6e | 494 | 'info_dict': { |
495 | 'id': 'p02mprgb', | |
cb23bcba | 496 | 'ext': 'mp4', |
10273d6e | 497 | 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', |
10273d6e | 498 | 'duration': 47, |
9afa1770 | 499 | 'timestamp': 1427219242, |
da92eeae | 500 | 'upload_date': '20150324', |
10273d6e | 501 | }, |
502 | 'params': { | |
9afa1770 | 503 | # rtmp download |
10273d6e | 504 | 'skip_download': True, |
505 | } | |
a3bfddfa | 506 | }, { |
9afa1770 S |
507 | # article with single video embedded with data-media-meta containing |
508 | # direct video links (for now these are extracted) and playlist.xml (with | |
509 | # media items as f4m and m3u8 - currently unsupported) | |
de939d89 | 510 | 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', |
de939d89 | 511 | 'info_dict': { |
9afa1770 | 512 | 'id': '150615_telabyad_kentin_cogu', |
de939d89 | 513 | 'ext': 'mp4', |
9afa1770 | 514 | 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", |
de939d89 | 515 | 'duration': 47, |
9afa1770 | 516 | 'timestamp': 1434397334, |
da92eeae | 517 | 'upload_date': '20150615', |
de939d89 | 518 | }, |
519 | 'params': { | |
520 | 'skip_download': True, | |
521 | } | |
a3bfddfa | 522 | }, { |
9afa1770 | 523 | # single video embedded with mediaAssetPage.init() (regional section) |
de939d89 | 524 | 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 525 | 'info_dict': { |
9afa1770 | 526 | 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 527 | 'ext': 'mp4', |
9afa1770 | 528 | 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', |
de939d89 | 529 | 'duration': 87, |
9afa1770 | 530 | 'timestamp': 1434713142, |
da92eeae | 531 | 'upload_date': '20150619', |
de939d89 | 532 | }, |
533 | 'params': { | |
534 | 'skip_download': True, | |
535 | } | |
a346b1ff S |
536 | }, { |
537 | # single video from video playlist embedded with vxp-playlist-data JSON | |
538 | 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376', | |
539 | 'info_dict': { | |
540 | 'id': 'p02w6qjc', | |
541 | 'ext': 'mp4', | |
542 | 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', | |
543 | 'duration': 56, | |
544 | }, | |
545 | 'params': { | |
546 | 'skip_download': True, | |
547 | } | |
9afa1770 S |
548 | }, { |
549 | # single video story with digitalData | |
550 | 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', | |
551 | 'info_dict': { | |
552 | 'id': 'p02q6gc4', | |
553 | 'ext': 'flv', | |
554 | 'title': 'Sri Lanka’s spicy secret', | |
555 | 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', | |
556 | 'timestamp': 1437674293, | |
557 | 'upload_date': '20150723', | |
558 | }, | |
559 | 'params': { | |
560 | # rtmp download | |
561 | 'skip_download': True, | |
562 | } | |
563 | }, { | |
564 | # single video story without digitalData | |
565 | 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', | |
566 | 'info_dict': { | |
567 | 'id': 'p018zqqg', | |
cb23bcba | 568 | 'ext': 'mp4', |
9afa1770 S |
569 | 'title': 'Hyundai Santa Fe Sport: Rock star', |
570 | 'description': 'md5:b042a26142c4154a6e472933cf20793d', | |
571 | 'timestamp': 1368473503, | |
572 | 'upload_date': '20130513', | |
573 | }, | |
574 | 'params': { | |
575 | # rtmp download | |
576 | 'skip_download': True, | |
577 | } | |
578 | }, { | |
579 | # single video with playlist.sxml URL | |
580 | 'url': 'http://www.bbc.com/sport/0/football/33653409', | |
581 | 'info_dict': { | |
582 | 'id': 'p02xycnp', | |
cb23bcba | 583 | 'ext': 'mp4', |
9afa1770 S |
584 | 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', |
585 | 'description': 'md5:398fca0e2e701c609d726e034fa1fc89', | |
586 | 'duration': 140, | |
587 | }, | |
588 | 'params': { | |
589 | # rtmp download | |
590 | 'skip_download': True, | |
591 | } | |
592 | }, { | |
593 | # single video with playlist URL from weather section | |
594 | 'url': 'http://www.bbc.com/weather/features/33601775', | |
595 | 'only_matching': True, | |
596 | }, { | |
597 | # custom redirection to www.bbc.com | |
598 | 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', | |
599 | 'only_matching': True, | |
10273d6e | 600 | }] |
601 | ||
9afa1770 S |
602 | @classmethod |
603 | def suitable(cls, url): | |
604 | return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) | |
605 | ||
606 | def _extract_from_media_meta(self, media_meta, video_id): | |
607 | # Direct links to media in media metadata (e.g. | |
608 | # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
609 | # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml | |
610 | source_files = media_meta.get('sourceFiles') | |
611 | if source_files: | |
612 | return [{ | |
613 | 'url': f['url'], | |
614 | 'format_id': format_id, | |
615 | 'ext': f.get('encoding'), | |
616 | 'tbr': float_or_none(f.get('bitrate'), 1000), | |
617 | 'filesize': int_or_none(f.get('filesize')), | |
618 | } for format_id, f in source_files.items() if f.get('url')], [] | |
619 | ||
620 | programme_id = media_meta.get('externalId') | |
621 | if programme_id: | |
622 | return self._download_media_selector(programme_id) | |
623 | ||
624 | # Process playlist.sxml as legacy playlist | |
625 | href = media_meta.get('href') | |
626 | if href: | |
627 | playlist = self._download_legacy_playlist_url(href) | |
628 | _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) | |
629 | return formats, subtitles | |
630 | ||
631 | return [], [] | |
632 | ||
10273d6e | 633 | def _real_extract(self, url): |
9afa1770 S |
634 | playlist_id = self._match_id(url) |
635 | ||
636 | webpage = self._download_webpage(url, playlist_id) | |
637 | ||
638 | timestamp = parse_iso8601(self._search_regex( | |
639 | [r'"datePublished":\s*"([^"]+)', | |
640 | r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"', | |
641 | r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], | |
642 | webpage, 'date', default=None)) | |
643 | ||
644 | # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) | |
645 | playlist = self._search_regex( | |
646 | r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', | |
647 | webpage, 'playlist', default=None) | |
648 | if playlist: | |
649 | programme_id, title, description, duration, formats, subtitles = \ | |
650 | self._process_legacy_playlist_url(playlist, playlist_id) | |
651 | self._sort_formats(formats) | |
652 | return { | |
653 | 'id': programme_id, | |
654 | 'title': title, | |
655 | 'description': description, | |
656 | 'duration': duration, | |
657 | 'timestamp': timestamp, | |
658 | 'formats': formats, | |
659 | 'subtitles': subtitles, | |
660 | } | |
de939d89 | 661 | |
9afa1770 S |
662 | # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) |
663 | programme_id = self._search_regex( | |
664 | [r'data-video-player-vpid="([\da-z]{8})"', | |
665 | r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], | |
666 | webpage, 'vpid', default=None) | |
667 | if programme_id: | |
668 | formats, subtitles = self._download_media_selector(programme_id) | |
669 | self._sort_formats(formats) | |
670 | # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) | |
671 | digital_data = self._parse_json( | |
672 | self._search_regex( | |
673 | r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), | |
674 | programme_id, fatal=False) | |
675 | page_info = digital_data.get('page', {}).get('pageInfo', {}) | |
676 | title = page_info.get('pageName') or self._og_search_title(webpage) | |
677 | description = page_info.get('description') or self._og_search_description(webpage) | |
678 | timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp | |
679 | return { | |
680 | 'id': programme_id, | |
681 | 'title': title, | |
682 | 'description': description, | |
683 | 'timestamp': timestamp, | |
684 | 'formats': formats, | |
685 | 'subtitles': subtitles, | |
686 | } | |
a3bfddfa | 687 | |
9afa1770 S |
688 | playlist_title = self._html_search_regex( |
689 | r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') | |
88ed52ae S |
690 | playlist_description = self._og_search_description(webpage, default=None) |
691 | ||
692 | def extract_all(pattern): | |
693 | return list(filter(None, map( | |
694 | lambda s: self._parse_json(s, playlist_id, fatal=False), | |
695 | re.findall(pattern, webpage)))) | |
696 | ||
697 | # Multiple video article (e.g. | |
698 | # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) | |
d247a2c8 | 699 | EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' |
88ed52ae S |
700 | entries = [] |
701 | for match in extract_all(r'new\s+SMP\(({.+?})\)'): | |
702 | embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') | |
703 | if embed_url and re.match(EMBED_URL, embed_url): | |
704 | entries.append(embed_url) | |
705 | entries.extend(re.findall( | |
706 | r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage)) | |
707 | if entries: | |
708 | return self.playlist_result( | |
709 | [self.url_result(entry, 'BBCCoUk') for entry in entries], | |
710 | playlist_id, playlist_title, playlist_description) | |
9afa1770 S |
711 | |
712 | # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) | |
88ed52ae | 713 | medias = extract_all(r"data-media-meta='({[^']+})'") |
9afa1770 S |
714 | |
715 | if not medias: | |
716 | # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) | |
a346b1ff S |
717 | media_asset = self._search_regex( |
718 | r'mediaAssetPage\.init\(\s*({.+?}), "/', | |
719 | webpage, 'media asset', default=None) | |
720 | if media_asset: | |
721 | media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False) | |
722 | medias = [] | |
723 | for video in media_asset_page.get('videos', {}).values(): | |
724 | medias.extend(video.values()) | |
725 | ||
726 | if not medias: | |
727 | # Multiple video playlist with single `now playing` entry (e.g. | |
728 | # http://www.bbc.com/news/video_and_audio/must_see/33767813) | |
729 | vxp_playlist = self._parse_json( | |
9afa1770 | 730 | self._search_regex( |
a346b1ff S |
731 | r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>', |
732 | webpage, 'playlist data'), | |
9afa1770 | 733 | playlist_id) |
a346b1ff S |
734 | playlist_medias = [] |
735 | for item in vxp_playlist: | |
736 | media = item.get('media') | |
737 | if not media: | |
738 | continue | |
739 | playlist_medias.append(media) | |
740 | # Download single video if found media with asset id matching the video id from URL | |
741 | if item.get('advert', {}).get('assetId') == playlist_id: | |
742 | medias = [media] | |
743 | break | |
744 | # Fallback to the whole playlist | |
745 | if not medias: | |
746 | medias = playlist_medias | |
9afa1770 S |
747 | |
748 | entries = [] | |
749 | for num, media_meta in enumerate(medias, start=1): | |
750 | formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) | |
751 | if not formats: | |
752 | continue | |
10273d6e | 753 | self._sort_formats(formats) |
754 | ||
9afa1770 S |
755 | video_id = media_meta.get('externalId') |
756 | if not video_id: | |
757 | video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) | |
758 | ||
759 | title = media_meta.get('caption') | |
760 | if not title: | |
761 | title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) | |
762 | ||
763 | duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) | |
da92eeae | 764 | |
9afa1770 S |
765 | images = [] |
766 | for image in media_meta.get('images', {}).values(): | |
767 | images.extend(image.values()) | |
768 | if 'image' in media_meta: | |
769 | images.append(media_meta['image']) | |
770 | ||
771 | thumbnails = [{ | |
772 | 'url': image.get('href'), | |
773 | 'width': int_or_none(image.get('width')), | |
774 | 'height': int_or_none(image.get('height')), | |
775 | } for image in images] | |
776 | ||
777 | entries.append({ | |
778 | 'id': video_id, | |
10273d6e | 779 | 'title': title, |
9afa1770 | 780 | 'thumbnails': thumbnails, |
10273d6e | 781 | 'duration': duration, |
9afa1770 | 782 | 'timestamp': timestamp, |
10273d6e | 783 | 'formats': formats, |
784 | 'subtitles': subtitles, | |
a3bfddfa | 785 | }) |
10273d6e | 786 | |
9afa1770 | 787 | return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) |