]>
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 S |
16 | |
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 | |
9afa1770 | 23 | _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' |
a8b081a0 | 24 | |
2e3fd9ec S |
25 | _TESTS = [ |
26 | { | |
f2d0fc68 | 27 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', |
2e3fd9ec | 28 | 'info_dict': { |
f2d0fc68 | 29 | 'id': 'b039d07m', |
2e3fd9ec | 30 | 'ext': 'flv', |
c4914185 S |
31 | 'title': 'Kaleidoscope, Leonard Cohen', |
32 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', | |
f2d0fc68 | 33 | 'duration': 1740, |
2e3fd9ec S |
34 | }, |
35 | 'params': { | |
36 | # rtmp download | |
37 | 'skip_download': True, | |
38 | } | |
082c6c86 | 39 | }, |
2e3fd9ec S |
40 | { |
41 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
42 | 'info_dict': { | |
43 | 'id': 'b00yng1d', | |
44 | 'ext': 'flv', | |
45 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
46 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
47 | 'duration': 1800, | |
48 | }, | |
49 | 'params': { | |
50 | # rtmp download | |
51 | 'skip_download': True, | |
c7f0177f S |
52 | }, |
53 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
2e3fd9ec S |
54 | }, |
55 | { | |
56 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
57 | 'info_dict': { | |
58 | 'id': 'b00yng1d', | |
59 | 'ext': 'flv', | |
17968e44 S |
60 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', |
61 | '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.", | |
62 | 'duration': 5100, | |
2e3fd9ec S |
63 | }, |
64 | 'params': { | |
65 | # rtmp download | |
66 | 'skip_download': True, | |
67 | }, | |
68 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
c056efa2 S |
69 | }, |
70 | { | |
71 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
72 | 'info_dict': { | |
73 | 'id': 'b03k3pb7', | |
74 | 'ext': 'flv', | |
75 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
76 | 'description': '2. Invasion', | |
77 | 'duration': 3600, | |
78 | }, | |
79 | 'params': { | |
80 | # rtmp download | |
81 | 'skip_download': True, | |
82 | }, | |
83 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
ae6986fb S |
84 | }, { |
85 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
86 | 'info_dict': { | |
87 | 'id': 'b04v209v', | |
88 | 'ext': 'flv', | |
89 | 'title': 'Pete Tong, The Essential New Tune Special', | |
90 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
91 | 'duration': 10800, | |
92 | }, | |
93 | 'params': { | |
94 | # rtmp download | |
95 | 'skip_download': True, | |
96 | } | |
c7e67594 S |
97 | }, { |
98 | 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', | |
99 | 'note': 'Audio', | |
100 | 'info_dict': { | |
101 | 'id': 'p02frcch', | |
102 | 'ext': 'flv', | |
103 | 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', | |
104 | 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', | |
105 | 'duration': 3507, | |
106 | }, | |
107 | 'params': { | |
108 | # rtmp download | |
109 | 'skip_download': True, | |
110 | } | |
111 | }, { | |
112 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
113 | 'note': 'Video', | |
114 | 'info_dict': { | |
115 | 'id': 'p025c103', | |
116 | 'ext': 'flv', | |
117 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', | |
118 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
119 | 'duration': 226, | |
120 | }, | |
121 | 'params': { | |
122 | # rtmp download | |
123 | 'skip_download': True, | |
124 | } | |
e68ae99a S |
125 | }, { |
126 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', | |
127 | 'info_dict': { | |
128 | 'id': 'p02n76xf', | |
129 | 'ext': 'flv', | |
130 | 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', | |
131 | 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', | |
132 | 'duration': 3540, | |
133 | }, | |
134 | 'params': { | |
135 | # rtmp download | |
136 | 'skip_download': True, | |
137 | }, | |
138 | 'skip': 'geolocation', | |
25fa8d66 YCH |
139 | }, { |
140 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', | |
141 | 'info_dict': { | |
142 | 'id': 'b05zmgw1', | |
143 | 'ext': 'flv', | |
144 | '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.', | |
145 | 'title': 'Royal Academy Summer Exhibition', | |
146 | 'duration': 3540, | |
147 | }, | |
148 | 'params': { | |
149 | # rtmp download | |
150 | 'skip_download': True, | |
151 | }, | |
152 | 'skip': 'geolocation', | |
31763975 S |
153 | }, { |
154 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
155 | 'only_matching': True, | |
c7e67594 S |
156 | }, { |
157 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
158 | 'only_matching': True, | |
0692ef86 S |
159 | }, { |
160 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
161 | 'only_matching': True, | |
ae6986fb | 162 | } |
2e3fd9ec S |
163 | ] |
164 | ||
165 | def _extract_asx_playlist(self, connection, programme_id): | |
166 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
167 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
168 | ||
169 | def _extract_connection(self, connection, programme_id): | |
170 | formats = [] | |
171 | protocol = connection.get('protocol') | |
172 | supplier = connection.get('supplier') | |
173 | if protocol == 'http': | |
174 | href = connection.get('href') | |
7a896817 | 175 | transfer_format = connection.get('transferFormat') |
2e3fd9ec S |
176 | # ASX playlist |
177 | if supplier == 'asx': | |
178 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
179 | formats.append({ | |
180 | 'url': ref, | |
181 | 'format_id': 'ref%s_%s' % (i, supplier), | |
182 | }) | |
7a896817 S |
183 | # Skip DASH until supported |
184 | elif transfer_format == 'dash': | |
185 | pass | |
2e3fd9ec S |
186 | # Direct link |
187 | else: | |
188 | formats.append({ | |
189 | 'url': href, | |
190 | 'format_id': supplier, | |
191 | }) | |
192 | elif protocol == 'rtmp': | |
193 | application = connection.get('application', 'ondemand') | |
194 | auth_string = connection.get('authString') | |
195 | identifier = connection.get('identifier') | |
196 | server = connection.get('server') | |
197 | formats.append({ | |
198 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
199 | 'play_path': identifier, | |
200 | 'app': '%s?%s' % (application, auth_string), | |
201 | 'page_url': 'http://www.bbc.co.uk', | |
202 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
203 | 'rtmp_live': False, | |
204 | 'ext': 'flv', | |
205 | 'format_id': supplier, | |
206 | }) | |
207 | return formats | |
208 | ||
209 | def _extract_items(self, playlist): | |
210 | return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') | |
211 | ||
212 | def _extract_medias(self, media_selection): | |
c056efa2 S |
213 | error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') |
214 | if error is not None: | |
215 | raise ExtractorError( | |
216 | '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True) | |
2e3fd9ec S |
217 | return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') |
218 | ||
219 | def _extract_connections(self, media): | |
220 | return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') | |
221 | ||
222 | def _extract_video(self, media, programme_id): | |
223 | formats = [] | |
d97f5cd7 | 224 | vbr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
225 | vcodec = media.get('encoding') |
226 | service = media.get('service') | |
d97f5cd7 S |
227 | width = int_or_none(media.get('width')) |
228 | height = int_or_none(media.get('height')) | |
229 | file_size = int_or_none(media.get('media_file_size')) | |
2e3fd9ec S |
230 | for connection in self._extract_connections(media): |
231 | conn_formats = self._extract_connection(connection, programme_id) | |
232 | for format in conn_formats: | |
233 | format.update({ | |
234 | 'format_id': '%s_%s' % (service, format['format_id']), | |
235 | 'width': width, | |
236 | 'height': height, | |
237 | 'vbr': vbr, | |
238 | 'vcodec': vcodec, | |
239 | 'filesize': file_size, | |
240 | }) | |
241 | formats.extend(conn_formats) | |
242 | return formats | |
243 | ||
244 | def _extract_audio(self, media, programme_id): | |
245 | formats = [] | |
d97f5cd7 | 246 | abr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
247 | acodec = media.get('encoding') |
248 | service = media.get('service') | |
249 | for connection in self._extract_connections(media): | |
250 | conn_formats = self._extract_connection(connection, programme_id) | |
251 | for format in conn_formats: | |
252 | format.update({ | |
253 | 'format_id': '%s_%s' % (service, format['format_id']), | |
254 | 'abr': abr, | |
255 | 'acodec': acodec, | |
256 | }) | |
257 | formats.extend(conn_formats) | |
258 | return formats | |
259 | ||
f13b1e7d | 260 | def _get_subtitles(self, media, programme_id): |
2e3fd9ec S |
261 | subtitles = {} |
262 | for connection in self._extract_connections(media): | |
263 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
264 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
f13b1e7d JMF |
265 | subtitles[lang] = [ |
266 | { | |
267 | 'url': connection.get('href'), | |
268 | 'ext': 'ttml', | |
269 | }, | |
f13b1e7d | 270 | ] |
2e3fd9ec | 271 | return subtitles |
082c6c86 | 272 | |
c056efa2 | 273 | def _download_media_selector(self, programme_id): |
9afa1770 S |
274 | return self._download_media_selector_url( |
275 | self._MEDIASELECTOR_URL % programme_id, programme_id) | |
276 | ||
277 | def _download_media_selector_url(self, url, programme_id=None): | |
c056efa2 S |
278 | try: |
279 | media_selection = self._download_xml( | |
9afa1770 | 280 | url, programme_id, 'Downloading media selection XML') |
c056efa2 S |
281 | except ExtractorError as ee: |
282 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
974a6146 | 283 | media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) |
2e3fd9ec | 284 | else: |
c056efa2 | 285 | raise |
9afa1770 | 286 | return self._process_media_selector(media_selection, programme_id) |
082c6c86 | 287 | |
9afa1770 | 288 | def _process_media_selector(self, media_selection, programme_id): |
082c6c86 | 289 | formats = [] |
2e3fd9ec S |
290 | subtitles = None |
291 | ||
c056efa2 S |
292 | for media in self._extract_medias(media_selection): |
293 | kind = media.get('kind') | |
294 | if kind == 'audio': | |
295 | formats.extend(self._extract_audio(media, programme_id)) | |
296 | elif kind == 'video': | |
297 | formats.extend(self._extract_video(media, programme_id)) | |
298 | elif kind == 'captions': | |
f13b1e7d | 299 | subtitles = self.extract_subtitles(media, programme_id) |
2e3fd9ec | 300 | |
c056efa2 | 301 | return formats, subtitles |
2e3fd9ec | 302 | |
ae6986fb S |
303 | def _download_playlist(self, playlist_id): |
304 | try: | |
305 | playlist = self._download_json( | |
306 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
307 | playlist_id, 'Downloading playlist JSON') | |
308 | ||
309 | version = playlist.get('defaultAvailableVersion') | |
310 | if version: | |
311 | smp_config = version['smpConfig'] | |
312 | title = smp_config['title'] | |
313 | description = smp_config['summary'] | |
314 | for item in smp_config['items']: | |
315 | kind = item['kind'] | |
316 | if kind != 'programme' and kind != 'radioProgramme': | |
317 | continue | |
318 | programme_id = item.get('vpid') | |
d97f5cd7 | 319 | duration = int_or_none(item.get('duration')) |
ae6986fb S |
320 | formats, subtitles = self._download_media_selector(programme_id) |
321 | return programme_id, title, description, duration, formats, subtitles | |
322 | except ExtractorError as ee: | |
f813928e | 323 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): |
ae6986fb S |
324 | raise |
325 | ||
326 | # fallback to legacy playlist | |
9afa1770 S |
327 | return self._process_legacy_playlist(playlist_id) |
328 | ||
329 | def _process_legacy_playlist_url(self, url, display_id): | |
330 | playlist = self._download_legacy_playlist_url(url, display_id) | |
331 | return self._extract_from_legacy_playlist(playlist, display_id) | |
332 | ||
333 | def _process_legacy_playlist(self, playlist_id): | |
334 | return self._process_legacy_playlist_url( | |
335 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) | |
336 | ||
337 | def _download_legacy_playlist_url(self, url, playlist_id=None): | |
338 | return self._download_xml( | |
339 | url, playlist_id, 'Downloading legacy playlist XML') | |
ae6986fb | 340 | |
9afa1770 | 341 | def _extract_from_legacy_playlist(self, playlist, playlist_id): |
ae6986fb S |
342 | no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') |
343 | if no_items is not None: | |
344 | reason = no_items.get('reason') | |
345 | if reason == 'preAvailability': | |
346 | msg = 'Episode %s is not yet available' % playlist_id | |
347 | elif reason == 'postAvailability': | |
348 | msg = 'Episode %s is no longer available' % playlist_id | |
349 | elif reason == 'noMedia': | |
350 | msg = 'Episode %s is not currently available' % playlist_id | |
351 | else: | |
352 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
353 | raise ExtractorError(msg, expected=True) | |
354 | ||
355 | for item in self._extract_items(playlist): | |
356 | kind = item.get('kind') | |
357 | if kind != 'programme' and kind != 'radioProgramme': | |
358 | continue | |
359 | title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | |
360 | description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | |
9afa1770 S |
361 | |
362 | def get_programme_id(item): | |
363 | def get_from_attributes(item): | |
364 | for p in('identifier', 'group'): | |
365 | value = item.get(p) | |
366 | if value and re.match(r'^[pb][\da-z]{7}$', value): | |
367 | return value | |
368 | get_from_attributes(item) | |
369 | mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') | |
370 | if mediator is not None: | |
371 | return get_from_attributes(mediator) | |
372 | ||
373 | programme_id = get_programme_id(item) | |
d97f5cd7 | 374 | duration = int_or_none(item.get('duration')) |
9afa1770 S |
375 | # TODO: programme_id can be None and media items can be incorporated right inside |
376 | # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
377 | # as f4m and m3u8 | |
ae6986fb S |
378 | formats, subtitles = self._download_media_selector(programme_id) |
379 | ||
380 | return programme_id, title, description, duration, formats, subtitles | |
381 | ||
c056efa2 S |
382 | def _real_extract(self, url): |
383 | group_id = self._match_id(url) | |
384 | ||
385 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
386 | ||
8683b4d8 S |
387 | programme_id = None |
388 | ||
389 | tviplayer = self._search_regex( | |
390 | r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', | |
391 | webpage, 'player', default=None) | |
392 | ||
393 | if tviplayer: | |
394 | player = self._parse_json(tviplayer, group_id).get('player', {}) | |
395 | duration = int_or_none(player.get('duration')) | |
396 | programme_id = player.get('vpid') | |
397 | ||
398 | if not programme_id: | |
399 | programme_id = self._search_regex( | |
400 | r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) | |
401 | ||
c056efa2 | 402 | if programme_id: |
c056efa2 | 403 | formats, subtitles = self._download_media_selector(programme_id) |
8683b4d8 S |
404 | title = self._og_search_title(webpage) |
405 | description = self._search_regex( | |
25fa8d66 | 406 | r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', |
8683b4d8 | 407 | webpage, 'description', fatal=False) |
c056efa2 | 408 | else: |
ae6986fb | 409 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |
2e3fd9ec | 410 | |
082c6c86 S |
411 | self._sort_formats(formats) |
412 | ||
413 | return { | |
2e3fd9ec | 414 | 'id': programme_id, |
082c6c86 S |
415 | 'title': title, |
416 | 'description': description, | |
650cfd0c | 417 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), |
082c6c86 S |
418 | 'duration': duration, |
419 | 'formats': formats, | |
2e3fd9ec | 420 | 'subtitles': subtitles, |
5f6a1245 | 421 | } |
10273d6e | 422 | |
423 | ||
9afa1770 S |
424 | class BBCIE(BBCCoUkIE): |
425 | IE_NAME = 'bbc' | |
426 | IE_DESC = 'BBC' | |
427 | _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)' | |
10273d6e | 428 | |
9afa1770 | 429 | # fails with notukerror for some videos |
51da40e6 | 430 | # _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s' |
9afa1770 | 431 | _MEDIASELECTOR_URL = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s' |
10273d6e | 432 | |
433 | _TESTS = [{ | |
9afa1770 S |
434 | # article with multiple videos embedded with data-media-meta containing |
435 | # playlist.sxml, externalId and no direct video links | |
10273d6e | 436 | 'url': 'http://www.bbc.com/news/world-europe-32668511', |
437 | 'info_dict': { | |
438 | 'id': 'world-europe-32668511', | |
439 | 'title': 'Russia stages massive WW2 parade despite Western boycott', | |
9afa1770 | 440 | 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', |
10273d6e | 441 | }, |
442 | 'playlist_count': 2, | |
a3bfddfa | 443 | }, { |
9afa1770 | 444 | # article with multiple videos embedded with data-media-meta (more videos) |
10273d6e | 445 | 'url': 'http://www.bbc.com/news/business-28299555', |
446 | 'info_dict': { | |
447 | 'id': 'business-28299555', | |
448 | 'title': 'Farnborough Airshow: Video highlights', | |
9afa1770 | 449 | 'description': 'BBC reports and video highlights at the Farnborough Airshow.', |
10273d6e | 450 | }, |
451 | 'playlist_count': 9, | |
9afa1770 | 452 | 'skip': 'Save time', |
a3bfddfa | 453 | }, { |
9afa1770 | 454 | # single video embedded with mediaAssetPage.init() |
10273d6e | 455 | 'url': 'http://www.bbc.com/news/world-europe-32041533', |
10273d6e | 456 | 'info_dict': { |
457 | 'id': 'p02mprgb', | |
9afa1770 | 458 | 'ext': 'flv', |
10273d6e | 459 | 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', |
10273d6e | 460 | 'duration': 47, |
9afa1770 | 461 | 'timestamp': 1427219242, |
da92eeae | 462 | 'upload_date': '20150324', |
10273d6e | 463 | }, |
464 | 'params': { | |
9afa1770 | 465 | # rtmp download |
10273d6e | 466 | 'skip_download': True, |
467 | } | |
a3bfddfa | 468 | }, { |
9afa1770 S |
469 | # article with single video embedded with data-media-meta containing |
470 | # direct video links (for now these are extracted) and playlist.xml (with | |
471 | # media items as f4m and m3u8 - currently unsupported) | |
de939d89 | 472 | 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', |
de939d89 | 473 | 'info_dict': { |
9afa1770 | 474 | 'id': '150615_telabyad_kentin_cogu', |
de939d89 | 475 | 'ext': 'mp4', |
9afa1770 | 476 | 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", |
de939d89 | 477 | 'duration': 47, |
9afa1770 | 478 | 'timestamp': 1434397334, |
da92eeae | 479 | 'upload_date': '20150615', |
de939d89 | 480 | }, |
481 | 'params': { | |
482 | 'skip_download': True, | |
483 | } | |
a3bfddfa | 484 | }, { |
9afa1770 | 485 | # single video embedded with mediaAssetPage.init() (regional section) |
de939d89 | 486 | 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 487 | 'info_dict': { |
9afa1770 | 488 | 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 489 | 'ext': 'mp4', |
9afa1770 | 490 | 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', |
de939d89 | 491 | 'duration': 87, |
9afa1770 | 492 | 'timestamp': 1434713142, |
da92eeae | 493 | 'upload_date': '20150619', |
de939d89 | 494 | }, |
495 | 'params': { | |
496 | 'skip_download': True, | |
497 | } | |
9afa1770 S |
498 | }, { |
499 | # single video story with digitalData | |
500 | 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', | |
501 | 'info_dict': { | |
502 | 'id': 'p02q6gc4', | |
503 | 'ext': 'flv', | |
504 | 'title': 'Sri Lanka’s spicy secret', | |
505 | 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', | |
506 | 'timestamp': 1437674293, | |
507 | 'upload_date': '20150723', | |
508 | }, | |
509 | 'params': { | |
510 | # rtmp download | |
511 | 'skip_download': True, | |
512 | } | |
513 | }, { | |
514 | # single video story without digitalData | |
515 | 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', | |
516 | 'info_dict': { | |
517 | 'id': 'p018zqqg', | |
518 | 'ext': 'flv', | |
519 | 'title': 'Hyundai Santa Fe Sport: Rock star', | |
520 | 'description': 'md5:b042a26142c4154a6e472933cf20793d', | |
521 | 'timestamp': 1368473503, | |
522 | 'upload_date': '20130513', | |
523 | }, | |
524 | 'params': { | |
525 | # rtmp download | |
526 | 'skip_download': True, | |
527 | } | |
528 | }, { | |
529 | # single video with playlist.sxml URL | |
530 | 'url': 'http://www.bbc.com/sport/0/football/33653409', | |
531 | 'info_dict': { | |
532 | 'id': 'p02xycnp', | |
533 | 'ext': 'flv', | |
534 | 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', | |
535 | 'description': 'md5:398fca0e2e701c609d726e034fa1fc89', | |
536 | 'duration': 140, | |
537 | }, | |
538 | 'params': { | |
539 | # rtmp download | |
540 | 'skip_download': True, | |
541 | } | |
542 | }, { | |
543 | # single video with playlist URL from weather section | |
544 | 'url': 'http://www.bbc.com/weather/features/33601775', | |
545 | 'only_matching': True, | |
546 | }, { | |
547 | # custom redirection to www.bbc.com | |
548 | 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', | |
549 | 'only_matching': True, | |
10273d6e | 550 | }] |
551 | ||
9afa1770 S |
552 | @classmethod |
553 | def suitable(cls, url): | |
554 | return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) | |
555 | ||
556 | def _extract_from_media_meta(self, media_meta, video_id): | |
557 | # Direct links to media in media metadata (e.g. | |
558 | # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
559 | # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml | |
560 | source_files = media_meta.get('sourceFiles') | |
561 | if source_files: | |
562 | return [{ | |
563 | 'url': f['url'], | |
564 | 'format_id': format_id, | |
565 | 'ext': f.get('encoding'), | |
566 | 'tbr': float_or_none(f.get('bitrate'), 1000), | |
567 | 'filesize': int_or_none(f.get('filesize')), | |
568 | } for format_id, f in source_files.items() if f.get('url')], [] | |
569 | ||
570 | programme_id = media_meta.get('externalId') | |
571 | if programme_id: | |
572 | return self._download_media_selector(programme_id) | |
573 | ||
574 | # Process playlist.sxml as legacy playlist | |
575 | href = media_meta.get('href') | |
576 | if href: | |
577 | playlist = self._download_legacy_playlist_url(href) | |
578 | _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) | |
579 | return formats, subtitles | |
580 | ||
581 | return [], [] | |
582 | ||
10273d6e | 583 | def _real_extract(self, url): |
9afa1770 S |
584 | playlist_id = self._match_id(url) |
585 | ||
586 | webpage = self._download_webpage(url, playlist_id) | |
587 | ||
588 | timestamp = parse_iso8601(self._search_regex( | |
589 | [r'"datePublished":\s*"([^"]+)', | |
590 | r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"', | |
591 | r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], | |
592 | webpage, 'date', default=None)) | |
593 | ||
594 | # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) | |
595 | playlist = self._search_regex( | |
596 | r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', | |
597 | webpage, 'playlist', default=None) | |
598 | if playlist: | |
599 | programme_id, title, description, duration, formats, subtitles = \ | |
600 | self._process_legacy_playlist_url(playlist, playlist_id) | |
601 | self._sort_formats(formats) | |
602 | return { | |
603 | 'id': programme_id, | |
604 | 'title': title, | |
605 | 'description': description, | |
606 | 'duration': duration, | |
607 | 'timestamp': timestamp, | |
608 | 'formats': formats, | |
609 | 'subtitles': subtitles, | |
610 | } | |
de939d89 | 611 | |
9afa1770 S |
612 | # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) |
613 | programme_id = self._search_regex( | |
614 | [r'data-video-player-vpid="([\da-z]{8})"', | |
615 | r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], | |
616 | webpage, 'vpid', default=None) | |
617 | if programme_id: | |
618 | formats, subtitles = self._download_media_selector(programme_id) | |
619 | self._sort_formats(formats) | |
620 | # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) | |
621 | digital_data = self._parse_json( | |
622 | self._search_regex( | |
623 | r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), | |
624 | programme_id, fatal=False) | |
625 | page_info = digital_data.get('page', {}).get('pageInfo', {}) | |
626 | title = page_info.get('pageName') or self._og_search_title(webpage) | |
627 | description = page_info.get('description') or self._og_search_description(webpage) | |
628 | timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp | |
629 | return { | |
630 | 'id': programme_id, | |
631 | 'title': title, | |
632 | 'description': description, | |
633 | 'timestamp': timestamp, | |
634 | 'formats': formats, | |
635 | 'subtitles': subtitles, | |
636 | } | |
a3bfddfa | 637 | |
9afa1770 S |
638 | playlist_title = self._html_search_regex( |
639 | r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') | |
640 | playlist_description = self._og_search_description(webpage) | |
641 | ||
642 | # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) | |
643 | medias = list(filter(None, map( | |
644 | lambda s: self._parse_json(s, playlist_id, fatal=False), | |
645 | re.findall(r"data-media-meta='({[^']+})'", webpage)))) | |
646 | ||
647 | if not medias: | |
648 | # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) | |
649 | media_asset_page = self._parse_json( | |
650 | self._search_regex( | |
651 | r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'media asset'), | |
652 | playlist_id) | |
653 | medias = [] | |
654 | for video in media_asset_page.get('videos', {}).values(): | |
655 | medias.extend(video.values()) | |
656 | ||
657 | entries = [] | |
658 | for num, media_meta in enumerate(medias, start=1): | |
659 | formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) | |
660 | if not formats: | |
661 | continue | |
10273d6e | 662 | self._sort_formats(formats) |
663 | ||
9afa1770 S |
664 | video_id = media_meta.get('externalId') |
665 | if not video_id: | |
666 | video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) | |
667 | ||
668 | title = media_meta.get('caption') | |
669 | if not title: | |
670 | title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) | |
671 | ||
672 | duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) | |
da92eeae | 673 | |
9afa1770 S |
674 | images = [] |
675 | for image in media_meta.get('images', {}).values(): | |
676 | images.extend(image.values()) | |
677 | if 'image' in media_meta: | |
678 | images.append(media_meta['image']) | |
679 | ||
680 | thumbnails = [{ | |
681 | 'url': image.get('href'), | |
682 | 'width': int_or_none(image.get('width')), | |
683 | 'height': int_or_none(image.get('height')), | |
684 | } for image in images] | |
685 | ||
686 | entries.append({ | |
687 | 'id': video_id, | |
10273d6e | 688 | 'title': title, |
9afa1770 | 689 | 'thumbnails': thumbnails, |
10273d6e | 690 | 'duration': duration, |
9afa1770 | 691 | 'timestamp': timestamp, |
10273d6e | 692 | 'formats': formats, |
693 | 'subtitles': subtitles, | |
a3bfddfa | 694 | }) |
10273d6e | 695 | |
9afa1770 | 696 | return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) |