]>
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 = [ |
26ccc68b S |
24 | # Provides HQ HLS streams with even better quality that pc mediaset but fails |
25 | # with geolocation in some cases when it's even not geo restricted at all (e.g. | |
26 | # http://www.bbc.co.uk/programmes/b06bp7lf) | |
d1c694ea | 27 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', |
d12a1a47 S |
28 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', |
29 | ] | |
a8b081a0 | 30 | |
2e3fd9ec S |
31 | _TESTS = [ |
32 | { | |
f2d0fc68 | 33 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', |
2e3fd9ec | 34 | 'info_dict': { |
f2d0fc68 | 35 | 'id': 'b039d07m', |
2e3fd9ec | 36 | 'ext': 'flv', |
c4914185 S |
37 | 'title': 'Kaleidoscope, Leonard Cohen', |
38 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', | |
f2d0fc68 | 39 | 'duration': 1740, |
2e3fd9ec S |
40 | }, |
41 | 'params': { | |
42 | # rtmp download | |
43 | 'skip_download': True, | |
44 | } | |
082c6c86 | 45 | }, |
2e3fd9ec S |
46 | { |
47 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
48 | 'info_dict': { | |
49 | 'id': 'b00yng1d', | |
50 | 'ext': 'flv', | |
51 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
52 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
53 | 'duration': 1800, | |
54 | }, | |
55 | 'params': { | |
56 | # rtmp download | |
57 | 'skip_download': True, | |
c7f0177f S |
58 | }, |
59 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
2e3fd9ec S |
60 | }, |
61 | { | |
62 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
63 | 'info_dict': { | |
64 | 'id': 'b00yng1d', | |
65 | 'ext': 'flv', | |
17968e44 S |
66 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', |
67 | '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.", | |
68 | 'duration': 5100, | |
2e3fd9ec S |
69 | }, |
70 | 'params': { | |
71 | # rtmp download | |
72 | 'skip_download': True, | |
73 | }, | |
74 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
c056efa2 S |
75 | }, |
76 | { | |
77 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
78 | 'info_dict': { | |
79 | 'id': 'b03k3pb7', | |
80 | 'ext': 'flv', | |
81 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
82 | 'description': '2. Invasion', | |
83 | 'duration': 3600, | |
84 | }, | |
85 | 'params': { | |
86 | # rtmp download | |
87 | 'skip_download': True, | |
88 | }, | |
89 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
ae6986fb S |
90 | }, { |
91 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
92 | 'info_dict': { | |
93 | 'id': 'b04v209v', | |
94 | 'ext': 'flv', | |
95 | 'title': 'Pete Tong, The Essential New Tune Special', | |
96 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
97 | 'duration': 10800, | |
98 | }, | |
99 | 'params': { | |
100 | # rtmp download | |
101 | 'skip_download': True, | |
102 | } | |
c7e67594 S |
103 | }, { |
104 | 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', | |
105 | 'note': 'Audio', | |
106 | 'info_dict': { | |
107 | 'id': 'p02frcch', | |
108 | 'ext': 'flv', | |
109 | 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', | |
110 | 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', | |
111 | 'duration': 3507, | |
112 | }, | |
113 | 'params': { | |
114 | # rtmp download | |
115 | 'skip_download': True, | |
116 | } | |
117 | }, { | |
118 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
119 | 'note': 'Video', | |
120 | 'info_dict': { | |
121 | 'id': 'p025c103', | |
122 | 'ext': 'flv', | |
123 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', | |
124 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
125 | 'duration': 226, | |
126 | }, | |
127 | 'params': { | |
128 | # rtmp download | |
129 | 'skip_download': True, | |
130 | } | |
e68ae99a S |
131 | }, { |
132 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', | |
133 | 'info_dict': { | |
134 | 'id': 'p02n76xf', | |
135 | 'ext': 'flv', | |
136 | 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', | |
137 | 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', | |
138 | 'duration': 3540, | |
139 | }, | |
140 | 'params': { | |
141 | # rtmp download | |
142 | 'skip_download': True, | |
143 | }, | |
144 | 'skip': 'geolocation', | |
25fa8d66 YCH |
145 | }, { |
146 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', | |
147 | 'info_dict': { | |
148 | 'id': 'b05zmgw1', | |
149 | 'ext': 'flv', | |
150 | '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.', | |
151 | 'title': 'Royal Academy Summer Exhibition', | |
152 | 'duration': 3540, | |
153 | }, | |
154 | 'params': { | |
155 | # rtmp download | |
156 | 'skip_download': True, | |
157 | }, | |
158 | 'skip': 'geolocation', | |
31763975 S |
159 | }, { |
160 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
161 | 'only_matching': True, | |
c7e67594 S |
162 | }, { |
163 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
164 | 'only_matching': True, | |
0692ef86 S |
165 | }, { |
166 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
167 | 'only_matching': True, | |
ae6986fb | 168 | } |
2e3fd9ec S |
169 | ] |
170 | ||
d12a1a47 S |
171 | class MediaSelectionError(Exception): |
172 | def __init__(self, id): | |
173 | self.id = id | |
174 | ||
2e3fd9ec S |
175 | def _extract_asx_playlist(self, connection, programme_id): |
176 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
177 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
178 | ||
179 | def _extract_connection(self, connection, programme_id): | |
180 | formats = [] | |
181 | protocol = connection.get('protocol') | |
182 | supplier = connection.get('supplier') | |
183 | if protocol == 'http': | |
184 | href = connection.get('href') | |
7a896817 | 185 | transfer_format = connection.get('transferFormat') |
2e3fd9ec S |
186 | # ASX playlist |
187 | if supplier == 'asx': | |
188 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
189 | formats.append({ | |
190 | 'url': ref, | |
191 | 'format_id': 'ref%s_%s' % (i, supplier), | |
192 | }) | |
7a896817 S |
193 | # Skip DASH until supported |
194 | elif transfer_format == 'dash': | |
195 | pass | |
d1c694ea S |
196 | elif transfer_format == 'hls': |
197 | m3u8_formats = self._extract_m3u8_formats( | |
198 | href, programme_id, ext='mp4', entry_protocol='m3u8_native', | |
199 | m3u8_id=supplier, fatal=False) | |
200 | if m3u8_formats: | |
201 | formats.extend(m3u8_formats) | |
2e3fd9ec S |
202 | # Direct link |
203 | else: | |
204 | formats.append({ | |
205 | 'url': href, | |
206 | 'format_id': supplier, | |
207 | }) | |
208 | elif protocol == 'rtmp': | |
209 | application = connection.get('application', 'ondemand') | |
210 | auth_string = connection.get('authString') | |
211 | identifier = connection.get('identifier') | |
212 | server = connection.get('server') | |
213 | formats.append({ | |
214 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
215 | 'play_path': identifier, | |
216 | 'app': '%s?%s' % (application, auth_string), | |
217 | 'page_url': 'http://www.bbc.co.uk', | |
218 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
219 | 'rtmp_live': False, | |
220 | 'ext': 'flv', | |
221 | 'format_id': supplier, | |
222 | }) | |
223 | return formats | |
224 | ||
225 | def _extract_items(self, playlist): | |
226 | return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') | |
227 | ||
228 | def _extract_medias(self, media_selection): | |
c056efa2 S |
229 | error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') |
230 | if error is not None: | |
d12a1a47 | 231 | raise BBCCoUkIE.MediaSelectionError(error.get('id')) |
2e3fd9ec S |
232 | return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') |
233 | ||
234 | def _extract_connections(self, media): | |
235 | return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') | |
236 | ||
237 | def _extract_video(self, media, programme_id): | |
238 | formats = [] | |
d97f5cd7 | 239 | vbr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
240 | vcodec = media.get('encoding') |
241 | service = media.get('service') | |
d97f5cd7 S |
242 | width = int_or_none(media.get('width')) |
243 | height = int_or_none(media.get('height')) | |
244 | file_size = int_or_none(media.get('media_file_size')) | |
2e3fd9ec S |
245 | for connection in self._extract_connections(media): |
246 | conn_formats = self._extract_connection(connection, programme_id) | |
247 | for format in conn_formats: | |
248 | format.update({ | |
249 | 'format_id': '%s_%s' % (service, format['format_id']), | |
250 | 'width': width, | |
251 | 'height': height, | |
252 | 'vbr': vbr, | |
253 | 'vcodec': vcodec, | |
254 | 'filesize': file_size, | |
255 | }) | |
256 | formats.extend(conn_formats) | |
257 | return formats | |
258 | ||
259 | def _extract_audio(self, media, programme_id): | |
260 | formats = [] | |
d97f5cd7 | 261 | abr = int_or_none(media.get('bitrate')) |
2e3fd9ec S |
262 | acodec = media.get('encoding') |
263 | service = media.get('service') | |
264 | for connection in self._extract_connections(media): | |
265 | conn_formats = self._extract_connection(connection, programme_id) | |
266 | for format in conn_formats: | |
267 | format.update({ | |
268 | 'format_id': '%s_%s' % (service, format['format_id']), | |
269 | 'abr': abr, | |
270 | 'acodec': acodec, | |
271 | }) | |
272 | formats.extend(conn_formats) | |
273 | return formats | |
274 | ||
f13b1e7d | 275 | def _get_subtitles(self, media, programme_id): |
2e3fd9ec S |
276 | subtitles = {} |
277 | for connection in self._extract_connections(media): | |
278 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
279 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
f13b1e7d JMF |
280 | subtitles[lang] = [ |
281 | { | |
282 | 'url': connection.get('href'), | |
283 | 'ext': 'ttml', | |
284 | }, | |
f13b1e7d | 285 | ] |
2e3fd9ec | 286 | return subtitles |
082c6c86 | 287 | |
d12a1a47 S |
288 | def _raise_extractor_error(self, media_selection_error): |
289 | raise ExtractorError( | |
290 | '%s returned error: %s' % (self.IE_NAME, media_selection_error.id), | |
291 | expected=True) | |
292 | ||
c056efa2 | 293 | def _download_media_selector(self, programme_id): |
d12a1a47 S |
294 | last_exception = None |
295 | for mediaselector_url in self._MEDIASELECTOR_URLS: | |
296 | try: | |
297 | return self._download_media_selector_url( | |
298 | mediaselector_url % programme_id, programme_id) | |
299 | except BBCCoUkIE.MediaSelectionError as e: | |
ee3d5a6d | 300 | if e.id in ('notukerror', 'geolocation'): |
d12a1a47 S |
301 | last_exception = e |
302 | continue | |
303 | self._raise_extractor_error(e) | |
304 | self._raise_extractor_error(last_exception) | |
9afa1770 S |
305 | |
306 | def _download_media_selector_url(self, url, programme_id=None): | |
c056efa2 S |
307 | try: |
308 | media_selection = self._download_xml( | |
9afa1770 | 309 | url, programme_id, 'Downloading media selection XML') |
c056efa2 S |
310 | except ExtractorError as ee: |
311 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
974a6146 | 312 | media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) |
2e3fd9ec | 313 | else: |
c056efa2 | 314 | raise |
9afa1770 | 315 | return self._process_media_selector(media_selection, programme_id) |
082c6c86 | 316 | |
9afa1770 | 317 | def _process_media_selector(self, media_selection, programme_id): |
082c6c86 | 318 | formats = [] |
2e3fd9ec S |
319 | subtitles = None |
320 | ||
c056efa2 S |
321 | for media in self._extract_medias(media_selection): |
322 | kind = media.get('kind') | |
323 | if kind == 'audio': | |
324 | formats.extend(self._extract_audio(media, programme_id)) | |
325 | elif kind == 'video': | |
326 | formats.extend(self._extract_video(media, programme_id)) | |
327 | elif kind == 'captions': | |
f13b1e7d | 328 | subtitles = self.extract_subtitles(media, programme_id) |
c056efa2 | 329 | return formats, subtitles |
2e3fd9ec | 330 | |
ae6986fb S |
331 | def _download_playlist(self, playlist_id): |
332 | try: | |
333 | playlist = self._download_json( | |
334 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
335 | playlist_id, 'Downloading playlist JSON') | |
336 | ||
337 | version = playlist.get('defaultAvailableVersion') | |
338 | if version: | |
339 | smp_config = version['smpConfig'] | |
340 | title = smp_config['title'] | |
341 | description = smp_config['summary'] | |
342 | for item in smp_config['items']: | |
343 | kind = item['kind'] | |
344 | if kind != 'programme' and kind != 'radioProgramme': | |
345 | continue | |
346 | programme_id = item.get('vpid') | |
d97f5cd7 | 347 | duration = int_or_none(item.get('duration')) |
ae6986fb S |
348 | formats, subtitles = self._download_media_selector(programme_id) |
349 | return programme_id, title, description, duration, formats, subtitles | |
350 | except ExtractorError as ee: | |
f813928e | 351 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): |
ae6986fb S |
352 | raise |
353 | ||
354 | # fallback to legacy playlist | |
9afa1770 S |
355 | return self._process_legacy_playlist(playlist_id) |
356 | ||
357 | def _process_legacy_playlist_url(self, url, display_id): | |
358 | playlist = self._download_legacy_playlist_url(url, display_id) | |
359 | return self._extract_from_legacy_playlist(playlist, display_id) | |
360 | ||
361 | def _process_legacy_playlist(self, playlist_id): | |
362 | return self._process_legacy_playlist_url( | |
363 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) | |
364 | ||
365 | def _download_legacy_playlist_url(self, url, playlist_id=None): | |
366 | return self._download_xml( | |
367 | url, playlist_id, 'Downloading legacy playlist XML') | |
ae6986fb | 368 | |
9afa1770 | 369 | def _extract_from_legacy_playlist(self, playlist, playlist_id): |
ae6986fb S |
370 | no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') |
371 | if no_items is not None: | |
372 | reason = no_items.get('reason') | |
373 | if reason == 'preAvailability': | |
374 | msg = 'Episode %s is not yet available' % playlist_id | |
375 | elif reason == 'postAvailability': | |
376 | msg = 'Episode %s is no longer available' % playlist_id | |
377 | elif reason == 'noMedia': | |
378 | msg = 'Episode %s is not currently available' % playlist_id | |
379 | else: | |
380 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
381 | raise ExtractorError(msg, expected=True) | |
382 | ||
383 | for item in self._extract_items(playlist): | |
384 | kind = item.get('kind') | |
385 | if kind != 'programme' and kind != 'radioProgramme': | |
386 | continue | |
387 | title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | |
388 | description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | |
9afa1770 S |
389 | |
390 | def get_programme_id(item): | |
391 | def get_from_attributes(item): | |
392 | for p in('identifier', 'group'): | |
393 | value = item.get(p) | |
394 | if value and re.match(r'^[pb][\da-z]{7}$', value): | |
395 | return value | |
396 | get_from_attributes(item) | |
397 | mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') | |
398 | if mediator is not None: | |
399 | return get_from_attributes(mediator) | |
400 | ||
401 | programme_id = get_programme_id(item) | |
d97f5cd7 | 402 | duration = int_or_none(item.get('duration')) |
9afa1770 S |
403 | # TODO: programme_id can be None and media items can be incorporated right inside |
404 | # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
405 | # as f4m and m3u8 | |
ae6986fb S |
406 | formats, subtitles = self._download_media_selector(programme_id) |
407 | ||
408 | return programme_id, title, description, duration, formats, subtitles | |
409 | ||
c056efa2 S |
410 | def _real_extract(self, url): |
411 | group_id = self._match_id(url) | |
412 | ||
413 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
414 | ||
8683b4d8 S |
415 | programme_id = None |
416 | ||
417 | tviplayer = self._search_regex( | |
418 | r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', | |
419 | webpage, 'player', default=None) | |
420 | ||
421 | if tviplayer: | |
422 | player = self._parse_json(tviplayer, group_id).get('player', {}) | |
423 | duration = int_or_none(player.get('duration')) | |
424 | programme_id = player.get('vpid') | |
425 | ||
426 | if not programme_id: | |
427 | programme_id = self._search_regex( | |
428 | r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) | |
429 | ||
c056efa2 | 430 | if programme_id: |
c056efa2 | 431 | formats, subtitles = self._download_media_selector(programme_id) |
8683b4d8 S |
432 | title = self._og_search_title(webpage) |
433 | description = self._search_regex( | |
25fa8d66 | 434 | r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', |
8683b4d8 | 435 | webpage, 'description', fatal=False) |
c056efa2 | 436 | else: |
ae6986fb | 437 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |
2e3fd9ec | 438 | |
082c6c86 S |
439 | self._sort_formats(formats) |
440 | ||
441 | return { | |
2e3fd9ec | 442 | 'id': programme_id, |
082c6c86 S |
443 | 'title': title, |
444 | 'description': description, | |
650cfd0c | 445 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), |
082c6c86 S |
446 | 'duration': duration, |
447 | 'formats': formats, | |
2e3fd9ec | 448 | 'subtitles': subtitles, |
5f6a1245 | 449 | } |
10273d6e | 450 | |
451 | ||
9afa1770 S |
452 | class BBCIE(BBCCoUkIE): |
453 | IE_NAME = 'bbc' | |
454 | IE_DESC = 'BBC' | |
455 | _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)' | |
10273d6e | 456 | |
d12a1a47 S |
457 | _MEDIASELECTOR_URLS = [ |
458 | # Provides more formats, namely direct mp4 links, but fails on some videos with | |
459 | # notukerror for non UK (?) users (e.g. | |
460 | # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) | |
461 | 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s', | |
462 | # Provides fewer formats, but works everywhere for everybody (hopefully) | |
463 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s', | |
464 | ] | |
10273d6e | 465 | |
466 | _TESTS = [{ | |
9afa1770 S |
467 | # article with multiple videos embedded with data-media-meta containing |
468 | # playlist.sxml, externalId and no direct video links | |
10273d6e | 469 | 'url': 'http://www.bbc.com/news/world-europe-32668511', |
470 | 'info_dict': { | |
471 | 'id': 'world-europe-32668511', | |
472 | 'title': 'Russia stages massive WW2 parade despite Western boycott', | |
9afa1770 | 473 | 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', |
10273d6e | 474 | }, |
475 | 'playlist_count': 2, | |
a3bfddfa | 476 | }, { |
9afa1770 | 477 | # article with multiple videos embedded with data-media-meta (more videos) |
10273d6e | 478 | 'url': 'http://www.bbc.com/news/business-28299555', |
479 | 'info_dict': { | |
480 | 'id': 'business-28299555', | |
481 | 'title': 'Farnborough Airshow: Video highlights', | |
9afa1770 | 482 | 'description': 'BBC reports and video highlights at the Farnborough Airshow.', |
10273d6e | 483 | }, |
484 | 'playlist_count': 9, | |
9afa1770 | 485 | 'skip': 'Save time', |
88ed52ae S |
486 | }, { |
487 | # article with multiple videos embedded with `new SMP()` | |
488 | 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', | |
489 | 'info_dict': { | |
490 | 'id': '3662a707-0af9-3149-963f-47bea720b460', | |
491 | 'title': 'BBC Blogs - Adam Curtis - BUGGER', | |
492 | }, | |
493 | 'playlist_count': 18, | |
a3bfddfa | 494 | }, { |
9afa1770 | 495 | # single video embedded with mediaAssetPage.init() |
10273d6e | 496 | 'url': 'http://www.bbc.com/news/world-europe-32041533', |
10273d6e | 497 | 'info_dict': { |
498 | 'id': 'p02mprgb', | |
cb23bcba | 499 | 'ext': 'mp4', |
10273d6e | 500 | 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', |
10273d6e | 501 | 'duration': 47, |
9afa1770 | 502 | 'timestamp': 1427219242, |
da92eeae | 503 | 'upload_date': '20150324', |
10273d6e | 504 | }, |
505 | 'params': { | |
9afa1770 | 506 | # rtmp download |
10273d6e | 507 | 'skip_download': True, |
508 | } | |
a3bfddfa | 509 | }, { |
9afa1770 S |
510 | # article with single video embedded with data-media-meta containing |
511 | # direct video links (for now these are extracted) and playlist.xml (with | |
512 | # media items as f4m and m3u8 - currently unsupported) | |
de939d89 | 513 | 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', |
de939d89 | 514 | 'info_dict': { |
9afa1770 | 515 | 'id': '150615_telabyad_kentin_cogu', |
de939d89 | 516 | 'ext': 'mp4', |
9afa1770 | 517 | 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", |
de939d89 | 518 | 'duration': 47, |
9afa1770 | 519 | 'timestamp': 1434397334, |
da92eeae | 520 | 'upload_date': '20150615', |
de939d89 | 521 | }, |
522 | 'params': { | |
523 | 'skip_download': True, | |
524 | } | |
a3bfddfa | 525 | }, { |
9afa1770 | 526 | # single video embedded with mediaAssetPage.init() (regional section) |
de939d89 | 527 | 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 528 | 'info_dict': { |
9afa1770 | 529 | 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 530 | 'ext': 'mp4', |
9afa1770 | 531 | 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', |
de939d89 | 532 | 'duration': 87, |
9afa1770 | 533 | 'timestamp': 1434713142, |
da92eeae | 534 | 'upload_date': '20150619', |
de939d89 | 535 | }, |
536 | 'params': { | |
537 | 'skip_download': True, | |
538 | } | |
a346b1ff S |
539 | }, { |
540 | # single video from video playlist embedded with vxp-playlist-data JSON | |
541 | 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376', | |
542 | 'info_dict': { | |
543 | 'id': 'p02w6qjc', | |
544 | 'ext': 'mp4', | |
545 | 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', | |
546 | 'duration': 56, | |
547 | }, | |
548 | 'params': { | |
549 | 'skip_download': True, | |
550 | } | |
9afa1770 S |
551 | }, { |
552 | # single video story with digitalData | |
553 | 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', | |
554 | 'info_dict': { | |
555 | 'id': 'p02q6gc4', | |
556 | 'ext': 'flv', | |
557 | 'title': 'Sri Lanka’s spicy secret', | |
558 | 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', | |
559 | 'timestamp': 1437674293, | |
560 | 'upload_date': '20150723', | |
561 | }, | |
562 | 'params': { | |
563 | # rtmp download | |
564 | 'skip_download': True, | |
565 | } | |
566 | }, { | |
567 | # single video story without digitalData | |
568 | 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', | |
569 | 'info_dict': { | |
570 | 'id': 'p018zqqg', | |
cb23bcba | 571 | 'ext': 'mp4', |
9afa1770 S |
572 | 'title': 'Hyundai Santa Fe Sport: Rock star', |
573 | 'description': 'md5:b042a26142c4154a6e472933cf20793d', | |
574 | 'timestamp': 1368473503, | |
575 | 'upload_date': '20130513', | |
576 | }, | |
577 | 'params': { | |
578 | # rtmp download | |
579 | 'skip_download': True, | |
580 | } | |
581 | }, { | |
582 | # single video with playlist.sxml URL | |
583 | 'url': 'http://www.bbc.com/sport/0/football/33653409', | |
584 | 'info_dict': { | |
585 | 'id': 'p02xycnp', | |
cb23bcba | 586 | 'ext': 'mp4', |
9afa1770 S |
587 | 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', |
588 | 'description': 'md5:398fca0e2e701c609d726e034fa1fc89', | |
589 | 'duration': 140, | |
590 | }, | |
591 | 'params': { | |
592 | # rtmp download | |
593 | 'skip_download': True, | |
594 | } | |
595 | }, { | |
596 | # single video with playlist URL from weather section | |
597 | 'url': 'http://www.bbc.com/weather/features/33601775', | |
598 | 'only_matching': True, | |
599 | }, { | |
600 | # custom redirection to www.bbc.com | |
601 | 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', | |
602 | 'only_matching': True, | |
10273d6e | 603 | }] |
604 | ||
9afa1770 S |
605 | @classmethod |
606 | def suitable(cls, url): | |
607 | return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) | |
608 | ||
609 | def _extract_from_media_meta(self, media_meta, video_id): | |
610 | # Direct links to media in media metadata (e.g. | |
611 | # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
612 | # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml | |
613 | source_files = media_meta.get('sourceFiles') | |
614 | if source_files: | |
615 | return [{ | |
616 | 'url': f['url'], | |
617 | 'format_id': format_id, | |
618 | 'ext': f.get('encoding'), | |
619 | 'tbr': float_or_none(f.get('bitrate'), 1000), | |
620 | 'filesize': int_or_none(f.get('filesize')), | |
621 | } for format_id, f in source_files.items() if f.get('url')], [] | |
622 | ||
623 | programme_id = media_meta.get('externalId') | |
624 | if programme_id: | |
625 | return self._download_media_selector(programme_id) | |
626 | ||
627 | # Process playlist.sxml as legacy playlist | |
628 | href = media_meta.get('href') | |
629 | if href: | |
630 | playlist = self._download_legacy_playlist_url(href) | |
631 | _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) | |
632 | return formats, subtitles | |
633 | ||
634 | return [], [] | |
635 | ||
10273d6e | 636 | def _real_extract(self, url): |
9afa1770 S |
637 | playlist_id = self._match_id(url) |
638 | ||
639 | webpage = self._download_webpage(url, playlist_id) | |
640 | ||
641 | timestamp = parse_iso8601(self._search_regex( | |
642 | [r'"datePublished":\s*"([^"]+)', | |
643 | r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"', | |
644 | r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], | |
645 | webpage, 'date', default=None)) | |
646 | ||
647 | # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) | |
648 | playlist = self._search_regex( | |
649 | r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', | |
650 | webpage, 'playlist', default=None) | |
651 | if playlist: | |
652 | programme_id, title, description, duration, formats, subtitles = \ | |
653 | self._process_legacy_playlist_url(playlist, playlist_id) | |
654 | self._sort_formats(formats) | |
655 | return { | |
656 | 'id': programme_id, | |
657 | 'title': title, | |
658 | 'description': description, | |
659 | 'duration': duration, | |
660 | 'timestamp': timestamp, | |
661 | 'formats': formats, | |
662 | 'subtitles': subtitles, | |
663 | } | |
de939d89 | 664 | |
9afa1770 S |
665 | # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) |
666 | programme_id = self._search_regex( | |
667 | [r'data-video-player-vpid="([\da-z]{8})"', | |
668 | r'<param[^>]+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], | |
669 | webpage, 'vpid', default=None) | |
670 | if programme_id: | |
671 | formats, subtitles = self._download_media_selector(programme_id) | |
672 | self._sort_formats(formats) | |
673 | # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) | |
674 | digital_data = self._parse_json( | |
675 | self._search_regex( | |
676 | r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), | |
677 | programme_id, fatal=False) | |
678 | page_info = digital_data.get('page', {}).get('pageInfo', {}) | |
679 | title = page_info.get('pageName') or self._og_search_title(webpage) | |
680 | description = page_info.get('description') or self._og_search_description(webpage) | |
681 | timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp | |
682 | return { | |
683 | 'id': programme_id, | |
684 | 'title': title, | |
685 | 'description': description, | |
686 | 'timestamp': timestamp, | |
687 | 'formats': formats, | |
688 | 'subtitles': subtitles, | |
689 | } | |
a3bfddfa | 690 | |
9afa1770 S |
691 | playlist_title = self._html_search_regex( |
692 | r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'playlist title') | |
88ed52ae S |
693 | playlist_description = self._og_search_description(webpage, default=None) |
694 | ||
695 | def extract_all(pattern): | |
696 | return list(filter(None, map( | |
697 | lambda s: self._parse_json(s, playlist_id, fatal=False), | |
698 | re.findall(pattern, webpage)))) | |
699 | ||
700 | # Multiple video article (e.g. | |
701 | # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) | |
d247a2c8 | 702 | EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' |
88ed52ae S |
703 | entries = [] |
704 | for match in extract_all(r'new\s+SMP\(({.+?})\)'): | |
705 | embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') | |
706 | if embed_url and re.match(EMBED_URL, embed_url): | |
707 | entries.append(embed_url) | |
708 | entries.extend(re.findall( | |
709 | r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage)) | |
710 | if entries: | |
711 | return self.playlist_result( | |
712 | [self.url_result(entry, 'BBCCoUk') for entry in entries], | |
713 | playlist_id, playlist_title, playlist_description) | |
9afa1770 S |
714 | |
715 | # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) | |
88ed52ae | 716 | medias = extract_all(r"data-media-meta='({[^']+})'") |
9afa1770 S |
717 | |
718 | if not medias: | |
719 | # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) | |
a346b1ff S |
720 | media_asset = self._search_regex( |
721 | r'mediaAssetPage\.init\(\s*({.+?}), "/', | |
722 | webpage, 'media asset', default=None) | |
723 | if media_asset: | |
724 | media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False) | |
725 | medias = [] | |
726 | for video in media_asset_page.get('videos', {}).values(): | |
727 | medias.extend(video.values()) | |
728 | ||
729 | if not medias: | |
730 | # Multiple video playlist with single `now playing` entry (e.g. | |
731 | # http://www.bbc.com/news/video_and_audio/must_see/33767813) | |
732 | vxp_playlist = self._parse_json( | |
9afa1770 | 733 | self._search_regex( |
a346b1ff S |
734 | r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>', |
735 | webpage, 'playlist data'), | |
9afa1770 | 736 | playlist_id) |
a346b1ff S |
737 | playlist_medias = [] |
738 | for item in vxp_playlist: | |
739 | media = item.get('media') | |
740 | if not media: | |
741 | continue | |
742 | playlist_medias.append(media) | |
743 | # Download single video if found media with asset id matching the video id from URL | |
744 | if item.get('advert', {}).get('assetId') == playlist_id: | |
745 | medias = [media] | |
746 | break | |
747 | # Fallback to the whole playlist | |
748 | if not medias: | |
749 | medias = playlist_medias | |
9afa1770 S |
750 | |
751 | entries = [] | |
752 | for num, media_meta in enumerate(medias, start=1): | |
753 | formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) | |
754 | if not formats: | |
755 | continue | |
10273d6e | 756 | self._sort_formats(formats) |
757 | ||
9afa1770 S |
758 | video_id = media_meta.get('externalId') |
759 | if not video_id: | |
760 | video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) | |
761 | ||
762 | title = media_meta.get('caption') | |
763 | if not title: | |
764 | title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) | |
765 | ||
766 | duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) | |
da92eeae | 767 | |
9afa1770 S |
768 | images = [] |
769 | for image in media_meta.get('images', {}).values(): | |
770 | images.extend(image.values()) | |
771 | if 'image' in media_meta: | |
772 | images.append(media_meta['image']) | |
773 | ||
774 | thumbnails = [{ | |
775 | 'url': image.get('href'), | |
776 | 'width': int_or_none(image.get('width')), | |
777 | 'height': int_or_none(image.get('height')), | |
778 | } for image in images] | |
779 | ||
780 | entries.append({ | |
781 | 'id': video_id, | |
10273d6e | 782 | 'title': title, |
9afa1770 | 783 | 'thumbnails': thumbnails, |
10273d6e | 784 | 'duration': duration, |
9afa1770 | 785 | 'timestamp': timestamp, |
10273d6e | 786 | 'formats': formats, |
787 | 'subtitles': subtitles, | |
a3bfddfa | 788 | }) |
10273d6e | 789 | |
9afa1770 | 790 | return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) |