]>
Commit | Line | Data |
---|---|---|
9afa1770 | 1 | # coding: utf-8 |
082c6c86 S |
2 | from __future__ import unicode_literals |
3 | ||
9afa1770 | 4 | import re |
254e64a2 | 5 | import itertools |
082c6c86 | 6 | |
f13b1e7d | 7 | from .common import InfoExtractor |
8683b4d8 | 8 | from ..utils import ( |
97067db2 | 9 | clean_html, |
9fb64c04 | 10 | dict_get, |
8683b4d8 | 11 | ExtractorError, |
9afa1770 | 12 | float_or_none, |
97067db2 | 13 | get_element_by_class, |
8683b4d8 | 14 | int_or_none, |
9afa1770 S |
15 | parse_duration, |
16 | parse_iso8601, | |
9fb64c04 | 17 | try_get, |
dab062fb | 18 | unescapeHTML, |
97067db2 S |
19 | urlencode_postdata, |
20 | urljoin, | |
8683b4d8 | 21 | ) |
36e6f62c JMF |
22 | from ..compat import ( |
23 | compat_etree_fromstring, | |
24 | compat_HTTPError, | |
254e64a2 | 25 | compat_urlparse, |
36e6f62c | 26 | ) |
082c6c86 | 27 | |
d12a1a47 | 28 | |
f13b1e7d | 29 | class BBCCoUkIE(InfoExtractor): |
082c6c86 | 30 | IE_NAME = 'bbc.co.uk' |
2e3fd9ec | 31 | IE_DESC = 'BBC iPlayer' |
53647dfd | 32 | _ID_REGEX = r'[pbw][\da-z]{7}' |
f20a11ed S |
33 | _VALID_URL = r'''(?x) |
34 | https?:// | |
35 | (?:www\.)?bbc\.co\.uk/ | |
36 | (?: | |
37 | programmes/(?!articles/)| | |
38 | iplayer(?:/[^/]+)?/(?:episode/|playlist/)| | |
72d256c4 | 39 | music/(?:clips|audiovideo/popular)[/#]| |
d3d45e0a S |
40 | radio/player/| |
41 | events/[^/]+/play/[^/]+/ | |
f20a11ed | 42 | ) |
ded7511a | 43 | (?P<id>%s)(?!/(?:episodes|broadcasts|clips)) |
f20a11ed | 44 | ''' % _ID_REGEX |
082c6c86 | 45 | |
97067db2 S |
46 | _LOGIN_URL = 'https://account.bbc.com/signin' |
47 | _NETRC_MACHINE = 'bbc' | |
48 | ||
d12a1a47 | 49 | _MEDIASELECTOR_URLS = [ |
26ccc68b S |
50 | # Provides HQ HLS streams with even better quality that pc mediaset but fails |
51 | # with geolocation in some cases when it's even not geo restricted at all (e.g. | |
d781e293 | 52 | # http://www.bbc.co.uk/programmes/b06bp7lf). Also may fail with selectionunavailable. |
d1c694ea | 53 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', |
d12a1a47 S |
54 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', |
55 | ] | |
a8b081a0 | 56 | |
e6174ee9 S |
57 | _MEDIASELECTION_NS = 'http://bbc.co.uk/2008/mp/mediaselection' |
58 | _EMP_PLAYLIST_NS = 'http://bbc.co.uk/2008/emp/playlist' | |
59 | ||
60 | _NAMESPACES = ( | |
61 | _MEDIASELECTION_NS, | |
62 | _EMP_PLAYLIST_NS, | |
63 | ) | |
64 | ||
2e3fd9ec S |
65 | _TESTS = [ |
66 | { | |
f2d0fc68 | 67 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', |
2e3fd9ec | 68 | 'info_dict': { |
f2d0fc68 | 69 | 'id': 'b039d07m', |
b1ea6802 | 70 | 'ext': 'flv', |
679bacf0 | 71 | 'title': 'Leonard Cohen, Kaleidoscope - BBC Radio 4', |
c4914185 | 72 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', |
2e3fd9ec S |
73 | }, |
74 | 'params': { | |
b1ea6802 | 75 | # rtmp download |
2e3fd9ec S |
76 | 'skip_download': True, |
77 | } | |
082c6c86 | 78 | }, |
2e3fd9ec S |
79 | { |
80 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
81 | 'info_dict': { | |
82 | 'id': 'b00yng1d', | |
83 | 'ext': 'flv', | |
84 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
85 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
86 | 'duration': 1800, | |
87 | }, | |
88 | 'params': { | |
89 | # rtmp download | |
90 | 'skip_download': True, | |
c7f0177f S |
91 | }, |
92 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
2e3fd9ec S |
93 | }, |
94 | { | |
95 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
96 | 'info_dict': { | |
97 | 'id': 'b00yng1d', | |
98 | 'ext': 'flv', | |
17968e44 | 99 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', |
611c1dd9 | 100 | '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.', |
17968e44 | 101 | 'duration': 5100, |
2e3fd9ec S |
102 | }, |
103 | 'params': { | |
104 | # rtmp download | |
105 | 'skip_download': True, | |
106 | }, | |
b1ea6802 | 107 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', |
c056efa2 S |
108 | }, |
109 | { | |
110 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
111 | 'info_dict': { | |
112 | 'id': 'b03k3pb7', | |
113 | 'ext': 'flv', | |
114 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
115 | 'description': '2. Invasion', | |
116 | 'duration': 3600, | |
117 | }, | |
118 | 'params': { | |
119 | # rtmp download | |
120 | 'skip_download': True, | |
121 | }, | |
b1ea6802 | 122 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', |
ae6986fb S |
123 | }, { |
124 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
125 | 'info_dict': { | |
126 | 'id': 'b04v209v', | |
127 | 'ext': 'flv', | |
128 | 'title': 'Pete Tong, The Essential New Tune Special', | |
129 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
130 | 'duration': 10800, | |
131 | }, | |
132 | 'params': { | |
133 | # rtmp download | |
134 | 'skip_download': True, | |
a3ef0e1c YCH |
135 | }, |
136 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
c7e67594 | 137 | }, { |
5aa535c3 | 138 | 'url': 'http://www.bbc.co.uk/music/clips/p022h44b', |
c7e67594 S |
139 | 'note': 'Audio', |
140 | 'info_dict': { | |
5aa535c3 | 141 | 'id': 'p022h44j', |
b1ea6802 | 142 | 'ext': 'flv', |
5aa535c3 S |
143 | 'title': 'BBC Proms Music Guides, Rachmaninov: Symphonic Dances', |
144 | 'description': "In this Proms Music Guide, Andrew McGregor looks at Rachmaninov's Symphonic Dances.", | |
145 | 'duration': 227, | |
c7e67594 S |
146 | }, |
147 | 'params': { | |
b1ea6802 | 148 | # rtmp download |
c7e67594 S |
149 | 'skip_download': True, |
150 | } | |
151 | }, { | |
152 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
153 | 'note': 'Video', | |
154 | 'info_dict': { | |
155 | 'id': 'p025c103', | |
b1ea6802 | 156 | 'ext': 'flv', |
c7e67594 S |
157 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', |
158 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
159 | 'duration': 226, | |
160 | }, | |
161 | 'params': { | |
b1ea6802 | 162 | # rtmp download |
c7e67594 S |
163 | 'skip_download': True, |
164 | } | |
e68ae99a S |
165 | }, { |
166 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', | |
167 | 'info_dict': { | |
168 | 'id': 'p02n76xf', | |
169 | 'ext': 'flv', | |
170 | 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', | |
171 | 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', | |
172 | 'duration': 3540, | |
173 | }, | |
174 | 'params': { | |
175 | # rtmp download | |
176 | 'skip_download': True, | |
177 | }, | |
b1ea6802 | 178 | 'skip': 'geolocation', |
25fa8d66 YCH |
179 | }, { |
180 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', | |
181 | 'info_dict': { | |
182 | 'id': 'b05zmgw1', | |
183 | 'ext': 'flv', | |
184 | '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.', | |
185 | 'title': 'Royal Academy Summer Exhibition', | |
186 | 'duration': 3540, | |
187 | }, | |
188 | 'params': { | |
189 | # rtmp download | |
190 | 'skip_download': True, | |
191 | }, | |
b1ea6802 | 192 | 'skip': 'geolocation', |
54914380 S |
193 | }, { |
194 | # iptv-all mediaset fails with geolocation however there is no geo restriction | |
195 | # for this programme at all | |
5aa535c3 | 196 | 'url': 'http://www.bbc.co.uk/programmes/b06rkn85', |
54914380 | 197 | 'info_dict': { |
5aa535c3 | 198 | 'id': 'b06rkms3', |
54914380 | 199 | 'ext': 'flv', |
5aa535c3 S |
200 | 'title': "Best of the Mini-Mixes 2015: Part 3, Annie Mac's Friday Night - BBC Radio 1", |
201 | 'description': "Annie has part three in the Best of the Mini-Mixes 2015, plus the year's Most Played!", | |
54914380 S |
202 | }, |
203 | 'params': { | |
204 | # rtmp download | |
205 | 'skip_download': True, | |
206 | }, | |
b1ea6802 | 207 | 'skip': 'Now it\'s really geo-restricted', |
1ac6e794 S |
208 | }, { |
209 | # compact player (https://github.com/rg3/youtube-dl/issues/8147) | |
210 | 'url': 'http://www.bbc.co.uk/programmes/p028bfkf/player', | |
211 | 'info_dict': { | |
212 | 'id': 'p028bfkj', | |
b1ea6802 | 213 | 'ext': 'flv', |
1ac6e794 S |
214 | 'title': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', |
215 | 'description': 'Extract from BBC documentary Look Stranger - Giant Leeks and Magic Brews', | |
216 | }, | |
217 | 'params': { | |
b1ea6802 | 218 | # rtmp download |
1ac6e794 S |
219 | 'skip_download': True, |
220 | }, | |
31763975 S |
221 | }, { |
222 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
223 | 'only_matching': True, | |
c7e67594 S |
224 | }, { |
225 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
226 | 'only_matching': True, | |
0692ef86 S |
227 | }, { |
228 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
229 | 'only_matching': True, | |
f20a11ed S |
230 | }, { |
231 | 'url': 'http://www.bbc.co.uk/radio/player/p03cchwf', | |
232 | 'only_matching': True, | |
72d256c4 S |
233 | }, { |
234 | 'url': 'https://www.bbc.co.uk/music/audiovideo/popular#p055bc55', | |
235 | 'only_matching': True, | |
53647dfd S |
236 | }, { |
237 | 'url': 'http://www.bbc.co.uk/programmes/w3csv1y9', | |
238 | 'only_matching': True, | |
72d256c4 | 239 | }] |
2e3fd9ec | 240 | |
97eb9bd2 RA |
241 | _USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8' |
242 | ||
97067db2 S |
243 | def _login(self): |
244 | username, password = self._get_login_info() | |
245 | if username is None: | |
246 | return | |
247 | ||
248 | login_page = self._download_webpage( | |
249 | self._LOGIN_URL, None, 'Downloading signin page') | |
250 | ||
251 | login_form = self._hidden_inputs(login_page) | |
252 | ||
253 | login_form.update({ | |
254 | 'username': username, | |
255 | 'password': password, | |
256 | }) | |
257 | ||
258 | post_url = urljoin(self._LOGIN_URL, self._search_regex( | |
259 | r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, | |
260 | 'post url', default=self._LOGIN_URL, group='url')) | |
261 | ||
262 | response, urlh = self._download_webpage_handle( | |
263 | post_url, None, 'Logging in', data=urlencode_postdata(login_form), | |
264 | headers={'Referer': self._LOGIN_URL}) | |
265 | ||
266 | if self._LOGIN_URL in urlh.geturl(): | |
267 | error = clean_html(get_element_by_class('form-message', response)) | |
268 | if error: | |
269 | raise ExtractorError( | |
270 | 'Unable to login: %s' % error, expected=True) | |
271 | raise ExtractorError('Unable to log in') | |
272 | ||
273 | def _real_initialize(self): | |
274 | self._login() | |
275 | ||
d12a1a47 S |
276 | class MediaSelectionError(Exception): |
277 | def __init__(self, id): | |
278 | self.id = id | |
279 | ||
2e3fd9ec S |
280 | def _extract_asx_playlist(self, connection, programme_id): |
281 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
282 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
283 | ||
2e3fd9ec | 284 | def _extract_items(self, playlist): |
e6174ee9 S |
285 | return playlist.findall('./{%s}item' % self._EMP_PLAYLIST_NS) |
286 | ||
287 | def _findall_ns(self, element, xpath): | |
288 | elements = [] | |
289 | for ns in self._NAMESPACES: | |
290 | elements.extend(element.findall(xpath % ns)) | |
291 | return elements | |
2e3fd9ec S |
292 | |
293 | def _extract_medias(self, media_selection): | |
e6174ee9 S |
294 | error = media_selection.find('./{%s}error' % self._MEDIASELECTION_NS) |
295 | if error is None: | |
296 | media_selection.find('./{%s}error' % self._EMP_PLAYLIST_NS) | |
c056efa2 | 297 | if error is not None: |
d12a1a47 | 298 | raise BBCCoUkIE.MediaSelectionError(error.get('id')) |
e6174ee9 | 299 | return self._findall_ns(media_selection, './{%s}media') |
2e3fd9ec S |
300 | |
301 | def _extract_connections(self, media): | |
e6174ee9 | 302 | return self._findall_ns(media, './{%s}connection') |
2e3fd9ec | 303 | |
f13b1e7d | 304 | def _get_subtitles(self, media, programme_id): |
2e3fd9ec S |
305 | subtitles = {} |
306 | for connection in self._extract_connections(media): | |
307 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
308 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
f13b1e7d JMF |
309 | subtitles[lang] = [ |
310 | { | |
311 | 'url': connection.get('href'), | |
312 | 'ext': 'ttml', | |
313 | }, | |
f13b1e7d | 314 | ] |
2e3fd9ec | 315 | return subtitles |
082c6c86 | 316 | |
d12a1a47 S |
317 | def _raise_extractor_error(self, media_selection_error): |
318 | raise ExtractorError( | |
319 | '%s returned error: %s' % (self.IE_NAME, media_selection_error.id), | |
320 | expected=True) | |
321 | ||
c056efa2 | 322 | def _download_media_selector(self, programme_id): |
d12a1a47 S |
323 | last_exception = None |
324 | for mediaselector_url in self._MEDIASELECTOR_URLS: | |
325 | try: | |
326 | return self._download_media_selector_url( | |
327 | mediaselector_url % programme_id, programme_id) | |
328 | except BBCCoUkIE.MediaSelectionError as e: | |
d781e293 | 329 | if e.id in ('notukerror', 'geolocation', 'selectionunavailable'): |
d12a1a47 S |
330 | last_exception = e |
331 | continue | |
332 | self._raise_extractor_error(e) | |
333 | self._raise_extractor_error(last_exception) | |
9afa1770 S |
334 | |
335 | def _download_media_selector_url(self, url, programme_id=None): | |
c056efa2 S |
336 | try: |
337 | media_selection = self._download_xml( | |
9afa1770 | 338 | url, programme_id, 'Downloading media selection XML') |
c056efa2 | 339 | except ExtractorError as ee: |
d781e293 | 340 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404): |
36e6f62c | 341 | media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8')) |
2e3fd9ec | 342 | else: |
c056efa2 | 343 | raise |
9afa1770 | 344 | return self._process_media_selector(media_selection, programme_id) |
082c6c86 | 345 | |
9afa1770 | 346 | def _process_media_selector(self, media_selection, programme_id): |
082c6c86 | 347 | formats = [] |
2e3fd9ec | 348 | subtitles = None |
b0af1215 | 349 | urls = [] |
2e3fd9ec | 350 | |
c056efa2 S |
351 | for media in self._extract_medias(media_selection): |
352 | kind = media.get('kind') | |
a7e5f274 RA |
353 | if kind in ('video', 'audio'): |
354 | bitrate = int_or_none(media.get('bitrate')) | |
355 | encoding = media.get('encoding') | |
356 | service = media.get('service') | |
357 | width = int_or_none(media.get('width')) | |
358 | height = int_or_none(media.get('height')) | |
359 | file_size = int_or_none(media.get('media_file_size')) | |
360 | for connection in self._extract_connections(media): | |
b0af1215 RA |
361 | href = connection.get('href') |
362 | if href in urls: | |
363 | continue | |
364 | if href: | |
365 | urls.append(href) | |
a7e5f274 RA |
366 | conn_kind = connection.get('kind') |
367 | protocol = connection.get('protocol') | |
368 | supplier = connection.get('supplier') | |
a7e5f274 RA |
369 | transfer_format = connection.get('transferFormat') |
370 | format_id = supplier or conn_kind or protocol | |
371 | if service: | |
372 | format_id = '%s_%s' % (service, format_id) | |
373 | # ASX playlist | |
374 | if supplier == 'asx': | |
375 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
376 | formats.append({ | |
377 | 'url': ref, | |
378 | 'format_id': 'ref%s_%s' % (i, format_id), | |
379 | }) | |
380 | elif transfer_format == 'dash': | |
381 | formats.extend(self._extract_mpd_formats( | |
382 | href, programme_id, mpd_id=format_id, fatal=False)) | |
383 | elif transfer_format == 'hls': | |
384 | formats.extend(self._extract_m3u8_formats( | |
385 | href, programme_id, ext='mp4', entry_protocol='m3u8_native', | |
386 | m3u8_id=format_id, fatal=False)) | |
97eb9bd2 RA |
387 | if re.search(self._USP_RE, href): |
388 | usp_formats = self._extract_m3u8_formats( | |
6b2d8c91 | 389 | re.sub(self._USP_RE, r'/\1.ism/\1.m3u8', href), |
97eb9bd2 RA |
390 | programme_id, ext='mp4', entry_protocol='m3u8_native', |
391 | m3u8_id=format_id, fatal=False) | |
392 | for f in usp_formats: | |
393 | if f.get('height') and f['height'] > 720: | |
394 | continue | |
395 | formats.append(f) | |
a7e5f274 RA |
396 | elif transfer_format == 'hds': |
397 | formats.extend(self._extract_f4m_formats( | |
398 | href, programme_id, f4m_id=format_id, fatal=False)) | |
399 | else: | |
f9622868 | 400 | if not service and not supplier and bitrate: |
aaa42cf0 | 401 | format_id += '-%d' % bitrate |
a7e5f274 RA |
402 | fmt = { |
403 | 'format_id': format_id, | |
404 | 'filesize': file_size, | |
405 | } | |
406 | if kind == 'video': | |
407 | fmt.update({ | |
408 | 'width': width, | |
409 | 'height': height, | |
6240925b | 410 | 'tbr': bitrate, |
a7e5f274 RA |
411 | 'vcodec': encoding, |
412 | }) | |
413 | else: | |
414 | fmt.update({ | |
415 | 'abr': bitrate, | |
416 | 'acodec': encoding, | |
417 | 'vcodec': 'none', | |
418 | }) | |
1af959ef | 419 | if protocol in ('http', 'https'): |
a7e5f274 RA |
420 | # Direct link |
421 | fmt.update({ | |
422 | 'url': href, | |
423 | }) | |
424 | elif protocol == 'rtmp': | |
425 | application = connection.get('application', 'ondemand') | |
426 | auth_string = connection.get('authString') | |
427 | identifier = connection.get('identifier') | |
428 | server = connection.get('server') | |
429 | fmt.update({ | |
430 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
431 | 'play_path': identifier, | |
432 | 'app': '%s?%s' % (application, auth_string), | |
433 | 'page_url': 'http://www.bbc.co.uk', | |
434 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
435 | 'rtmp_live': False, | |
436 | 'ext': 'flv', | |
437 | }) | |
964744af S |
438 | else: |
439 | continue | |
a7e5f274 | 440 | formats.append(fmt) |
c056efa2 | 441 | elif kind == 'captions': |
f13b1e7d | 442 | subtitles = self.extract_subtitles(media, programme_id) |
c056efa2 | 443 | return formats, subtitles |
2e3fd9ec | 444 | |
ae6986fb S |
445 | def _download_playlist(self, playlist_id): |
446 | try: | |
447 | playlist = self._download_json( | |
448 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
449 | playlist_id, 'Downloading playlist JSON') | |
450 | ||
451 | version = playlist.get('defaultAvailableVersion') | |
452 | if version: | |
453 | smp_config = version['smpConfig'] | |
454 | title = smp_config['title'] | |
455 | description = smp_config['summary'] | |
456 | for item in smp_config['items']: | |
457 | kind = item['kind'] | |
40fcba5e | 458 | if kind not in ('programme', 'radioProgramme'): |
ae6986fb S |
459 | continue |
460 | programme_id = item.get('vpid') | |
d97f5cd7 | 461 | duration = int_or_none(item.get('duration')) |
ae6986fb S |
462 | formats, subtitles = self._download_media_selector(programme_id) |
463 | return programme_id, title, description, duration, formats, subtitles | |
464 | except ExtractorError as ee: | |
f813928e | 465 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): |
ae6986fb S |
466 | raise |
467 | ||
468 | # fallback to legacy playlist | |
9afa1770 S |
469 | return self._process_legacy_playlist(playlist_id) |
470 | ||
471 | def _process_legacy_playlist_url(self, url, display_id): | |
472 | playlist = self._download_legacy_playlist_url(url, display_id) | |
473 | return self._extract_from_legacy_playlist(playlist, display_id) | |
474 | ||
475 | def _process_legacy_playlist(self, playlist_id): | |
476 | return self._process_legacy_playlist_url( | |
477 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) | |
478 | ||
479 | def _download_legacy_playlist_url(self, url, playlist_id=None): | |
480 | return self._download_xml( | |
481 | url, playlist_id, 'Downloading legacy playlist XML') | |
ae6986fb | 482 | |
9afa1770 | 483 | def _extract_from_legacy_playlist(self, playlist, playlist_id): |
e6174ee9 | 484 | no_items = playlist.find('./{%s}noItems' % self._EMP_PLAYLIST_NS) |
ae6986fb S |
485 | if no_items is not None: |
486 | reason = no_items.get('reason') | |
487 | if reason == 'preAvailability': | |
488 | msg = 'Episode %s is not yet available' % playlist_id | |
489 | elif reason == 'postAvailability': | |
490 | msg = 'Episode %s is no longer available' % playlist_id | |
491 | elif reason == 'noMedia': | |
492 | msg = 'Episode %s is not currently available' % playlist_id | |
493 | else: | |
494 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
495 | raise ExtractorError(msg, expected=True) | |
496 | ||
497 | for item in self._extract_items(playlist): | |
498 | kind = item.get('kind') | |
40fcba5e | 499 | if kind not in ('programme', 'radioProgramme'): |
ae6986fb | 500 | continue |
e6174ee9 S |
501 | title = playlist.find('./{%s}title' % self._EMP_PLAYLIST_NS).text |
502 | description_el = playlist.find('./{%s}summary' % self._EMP_PLAYLIST_NS) | |
8daeeedc | 503 | description = description_el.text if description_el is not None else None |
9afa1770 S |
504 | |
505 | def get_programme_id(item): | |
506 | def get_from_attributes(item): | |
507 | for p in('identifier', 'group'): | |
508 | value = item.get(p) | |
509 | if value and re.match(r'^[pb][\da-z]{7}$', value): | |
510 | return value | |
511 | get_from_attributes(item) | |
e6174ee9 | 512 | mediator = item.find('./{%s}mediator' % self._EMP_PLAYLIST_NS) |
9afa1770 S |
513 | if mediator is not None: |
514 | return get_from_attributes(mediator) | |
515 | ||
516 | programme_id = get_programme_id(item) | |
d97f5cd7 | 517 | duration = int_or_none(item.get('duration')) |
e6174ee9 S |
518 | |
519 | if programme_id: | |
520 | formats, subtitles = self._download_media_selector(programme_id) | |
521 | else: | |
522 | formats, subtitles = self._process_media_selector(item, playlist_id) | |
523 | programme_id = playlist_id | |
ae6986fb S |
524 | |
525 | return programme_id, title, description, duration, formats, subtitles | |
526 | ||
c056efa2 S |
527 | def _real_extract(self, url): |
528 | group_id = self._match_id(url) | |
529 | ||
530 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
531 | ||
b2ed954f S |
532 | error = self._search_regex( |
533 | r'<div\b[^>]+\bclass=["\']smp__message delta["\'][^>]*>([^<]+)<', | |
534 | webpage, 'error', default=None) | |
535 | if error: | |
536 | raise ExtractorError(error, expected=True) | |
537 | ||
8683b4d8 | 538 | programme_id = None |
679bacf0 | 539 | duration = None |
8683b4d8 S |
540 | |
541 | tviplayer = self._search_regex( | |
542 | r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', | |
543 | webpage, 'player', default=None) | |
544 | ||
545 | if tviplayer: | |
546 | player = self._parse_json(tviplayer, group_id).get('player', {}) | |
547 | duration = int_or_none(player.get('duration')) | |
548 | programme_id = player.get('vpid') | |
549 | ||
550 | if not programme_id: | |
551 | programme_id = self._search_regex( | |
22d7368d | 552 | r'"vpid"\s*:\s*"(%s)"' % self._ID_REGEX, webpage, 'vpid', fatal=False, default=None) |
8683b4d8 | 553 | |
c056efa2 | 554 | if programme_id: |
c056efa2 | 555 | formats, subtitles = self._download_media_selector(programme_id) |
88fb59d9 | 556 | title = self._og_search_title(webpage, default=None) or self._html_search_regex( |
50e989e2 S |
557 | (r'<h2[^>]+id="parent-title"[^>]*>(.+?)</h2>', |
558 | r'<div[^>]+class="info"[^>]*>\s*<h1>(.+?)</h1>'), webpage, 'title') | |
8683b4d8 | 559 | description = self._search_regex( |
a8534274 S |
560 | (r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', |
561 | r'<div[^>]+class="info_+synopsis"[^>]*>([^<]+)</div>'), | |
679bacf0 YCH |
562 | webpage, 'description', default=None) |
563 | if not description: | |
564 | description = self._html_search_meta('description', webpage) | |
c056efa2 | 565 | else: |
ae6986fb | 566 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |
2e3fd9ec | 567 | |
082c6c86 S |
568 | self._sort_formats(formats) |
569 | ||
570 | return { | |
2e3fd9ec | 571 | 'id': programme_id, |
082c6c86 S |
572 | 'title': title, |
573 | 'description': description, | |
650cfd0c | 574 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), |
082c6c86 S |
575 | 'duration': duration, |
576 | 'formats': formats, | |
2e3fd9ec | 577 | 'subtitles': subtitles, |
5f6a1245 | 578 | } |
10273d6e | 579 | |
580 | ||
9afa1770 S |
581 | class BBCIE(BBCCoUkIE): |
582 | IE_NAME = 'bbc' | |
583 | IE_DESC = 'BBC' | |
584 | _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P<id>[^/#?]+)' | |
10273d6e | 585 | |
d12a1a47 | 586 | _MEDIASELECTOR_URLS = [ |
55ebae26 S |
587 | # Provides HQ HLS streams but fails with geolocation in some cases when it's |
588 | # even not geo restricted at all | |
589 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/iptv-all/vpid/%s', | |
d12a1a47 S |
590 | # Provides more formats, namely direct mp4 links, but fails on some videos with |
591 | # notukerror for non UK (?) users (e.g. | |
592 | # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) | |
593 | 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s', | |
594 | # Provides fewer formats, but works everywhere for everybody (hopefully) | |
595 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s', | |
596 | ] | |
10273d6e | 597 | |
598 | _TESTS = [{ | |
6a747190 | 599 | # article with multiple videos embedded with data-playable containing vpids |
10273d6e | 600 | 'url': 'http://www.bbc.com/news/world-europe-32668511', |
601 | 'info_dict': { | |
602 | 'id': 'world-europe-32668511', | |
603 | 'title': 'Russia stages massive WW2 parade despite Western boycott', | |
9afa1770 | 604 | 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', |
10273d6e | 605 | }, |
606 | 'playlist_count': 2, | |
a3bfddfa | 607 | }, { |
6a747190 | 608 | # article with multiple videos embedded with data-playable (more videos) |
10273d6e | 609 | 'url': 'http://www.bbc.com/news/business-28299555', |
610 | 'info_dict': { | |
611 | 'id': 'business-28299555', | |
612 | 'title': 'Farnborough Airshow: Video highlights', | |
9afa1770 | 613 | 'description': 'BBC reports and video highlights at the Farnborough Airshow.', |
10273d6e | 614 | }, |
615 | 'playlist_count': 9, | |
9afa1770 | 616 | 'skip': 'Save time', |
88ed52ae S |
617 | }, { |
618 | # article with multiple videos embedded with `new SMP()` | |
6a747190 | 619 | # broken |
88ed52ae S |
620 | 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', |
621 | 'info_dict': { | |
622 | 'id': '3662a707-0af9-3149-963f-47bea720b460', | |
b7d7674f | 623 | 'title': 'BUGGER', |
88ed52ae S |
624 | }, |
625 | 'playlist_count': 18, | |
a3bfddfa | 626 | }, { |
6a747190 | 627 | # single video embedded with data-playable containing vpid |
10273d6e | 628 | 'url': 'http://www.bbc.com/news/world-europe-32041533', |
10273d6e | 629 | 'info_dict': { |
630 | 'id': 'p02mprgb', | |
55ebae26 | 631 | 'ext': 'mp4', |
10273d6e | 632 | 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', |
55ebae26 | 633 | 'description': 'md5:2868290467291b37feda7863f7a83f54', |
10273d6e | 634 | 'duration': 47, |
9afa1770 | 635 | 'timestamp': 1427219242, |
da92eeae | 636 | 'upload_date': '20150324', |
10273d6e | 637 | }, |
638 | 'params': { | |
9afa1770 | 639 | # rtmp download |
10273d6e | 640 | 'skip_download': True, |
641 | } | |
a3bfddfa | 642 | }, { |
6a747190 S |
643 | # article with single video embedded with data-playable containing XML playlist |
644 | # with direct video links as progressiveDownloadUrl (for now these are extracted) | |
645 | # and playlist with f4m and m3u8 as streamingUrl | |
de939d89 | 646 | 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', |
de939d89 | 647 | 'info_dict': { |
9afa1770 | 648 | 'id': '150615_telabyad_kentin_cogu', |
de939d89 | 649 | 'ext': 'mp4', |
ad152e2d | 650 | 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", |
05087d1b | 651 | 'description': 'md5:33a4805a855c9baf7115fcbde57e7025', |
9afa1770 | 652 | 'timestamp': 1434397334, |
da92eeae | 653 | 'upload_date': '20150615', |
de939d89 | 654 | }, |
655 | 'params': { | |
656 | 'skip_download': True, | |
657 | } | |
c936d8cc | 658 | }, { |
6a747190 | 659 | # single video embedded with data-playable containing XML playlists (regional section) |
de939d89 | 660 | 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 661 | 'info_dict': { |
9afa1770 | 662 | 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', |
de939d89 | 663 | 'ext': 'mp4', |
9afa1770 | 664 | 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', |
05087d1b | 665 | 'description': 'md5:1525f17448c4ee262b64b8f0c9ce66c8', |
9afa1770 | 666 | 'timestamp': 1434713142, |
da92eeae | 667 | 'upload_date': '20150619', |
de939d89 | 668 | }, |
669 | 'params': { | |
670 | 'skip_download': True, | |
671 | } | |
a346b1ff S |
672 | }, { |
673 | # single video from video playlist embedded with vxp-playlist-data JSON | |
674 | 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376', | |
675 | 'info_dict': { | |
676 | 'id': 'p02w6qjc', | |
55ebae26 | 677 | 'ext': 'mp4', |
a346b1ff S |
678 | 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', |
679 | 'duration': 56, | |
0bc4ee60 | 680 | 'description': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', |
a346b1ff S |
681 | }, |
682 | 'params': { | |
683 | 'skip_download': True, | |
684 | } | |
9afa1770 S |
685 | }, { |
686 | # single video story with digitalData | |
687 | 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', | |
688 | 'info_dict': { | |
689 | 'id': 'p02q6gc4', | |
690 | 'ext': 'flv', | |
691 | 'title': 'Sri Lanka’s spicy secret', | |
692 | 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', | |
693 | 'timestamp': 1437674293, | |
694 | 'upload_date': '20150723', | |
695 | }, | |
696 | 'params': { | |
697 | # rtmp download | |
698 | 'skip_download': True, | |
699 | } | |
700 | }, { | |
701 | # single video story without digitalData | |
702 | 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', | |
703 | 'info_dict': { | |
704 | 'id': 'p018zqqg', | |
55ebae26 | 705 | 'ext': 'mp4', |
9afa1770 S |
706 | 'title': 'Hyundai Santa Fe Sport: Rock star', |
707 | 'description': 'md5:b042a26142c4154a6e472933cf20793d', | |
ae8bdfd1 S |
708 | 'timestamp': 1415867444, |
709 | 'upload_date': '20141113', | |
9afa1770 S |
710 | }, |
711 | 'params': { | |
712 | # rtmp download | |
713 | 'skip_download': True, | |
714 | } | |
9fb64c04 S |
715 | }, { |
716 | # single video embedded with Morph | |
717 | 'url': 'http://www.bbc.co.uk/sport/live/olympics/36895975', | |
718 | 'info_dict': { | |
719 | 'id': 'p041vhd0', | |
720 | 'ext': 'mp4', | |
721 | 'title': "Nigeria v Japan - Men's First Round", | |
722 | 'description': 'Live coverage of the first round from Group B at the Amazonia Arena.', | |
723 | 'duration': 7980, | |
724 | 'uploader': 'BBC Sport', | |
725 | 'uploader_id': 'bbc_sport', | |
726 | }, | |
727 | 'params': { | |
728 | # m3u8 download | |
729 | 'skip_download': True, | |
9fb64c04 S |
730 | }, |
731 | 'skip': 'Georestricted to UK', | |
9afa1770 | 732 | }, { |
6a747190 | 733 | # single video with playlist.sxml URL in playlist param |
9afa1770 S |
734 | 'url': 'http://www.bbc.com/sport/0/football/33653409', |
735 | 'info_dict': { | |
736 | 'id': 'p02xycnp', | |
55ebae26 | 737 | 'ext': 'mp4', |
9afa1770 | 738 | 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', |
7033bc1a | 739 | 'description': 'BBC Sport\'s David Ornstein has the latest transfer gossip, including rumours of a Manchester United return for Cristiano Ronaldo.', |
9afa1770 S |
740 | 'duration': 140, |
741 | }, | |
742 | 'params': { | |
743 | # rtmp download | |
744 | 'skip_download': True, | |
745 | } | |
b5d48cb1 | 746 | }, { |
6a747190 | 747 | # article with multiple videos embedded with playlist.sxml in playlist param |
b5d48cb1 S |
748 | 'url': 'http://www.bbc.com/sport/0/football/34475836', |
749 | 'info_dict': { | |
750 | 'id': '34475836', | |
450b233c | 751 | 'title': 'Jurgen Klopp: Furious football from a witty and winning coach', |
8c65e4a5 | 752 | 'description': 'Fast-paced football, wit, wisdom and a ready smile - why Liverpool fans should come to love new boss Jurgen Klopp.', |
b5d48cb1 S |
753 | }, |
754 | 'playlist_count': 3, | |
450b233c S |
755 | }, { |
756 | # school report article with single video | |
757 | 'url': 'http://www.bbc.co.uk/schoolreport/35744779', | |
758 | 'info_dict': { | |
759 | 'id': '35744779', | |
760 | 'title': 'School which breaks down barriers in Jerusalem', | |
761 | }, | |
762 | 'playlist_count': 1, | |
9afa1770 S |
763 | }, { |
764 | # single video with playlist URL from weather section | |
765 | 'url': 'http://www.bbc.com/weather/features/33601775', | |
766 | 'only_matching': True, | |
767 | }, { | |
768 | # custom redirection to www.bbc.com | |
769 | 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', | |
770 | 'only_matching': True, | |
a1cf3e38 S |
771 | }, { |
772 | # single video article embedded with data-media-vpid | |
773 | 'url': 'http://www.bbc.co.uk/sport/rowing/35908187', | |
774 | 'only_matching': True, | |
10273d6e | 775 | }] |
776 | ||
9afa1770 S |
777 | @classmethod |
778 | def suitable(cls, url): | |
ded7511a S |
779 | EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE) |
780 | return (False if any(ie.suitable(url) for ie in EXCLUDE_IE) | |
781 | else super(BBCIE, cls).suitable(url)) | |
9afa1770 S |
782 | |
783 | def _extract_from_media_meta(self, media_meta, video_id): | |
784 | # Direct links to media in media metadata (e.g. | |
785 | # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
786 | # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml | |
787 | source_files = media_meta.get('sourceFiles') | |
788 | if source_files: | |
789 | return [{ | |
790 | 'url': f['url'], | |
791 | 'format_id': format_id, | |
792 | 'ext': f.get('encoding'), | |
793 | 'tbr': float_or_none(f.get('bitrate'), 1000), | |
794 | 'filesize': int_or_none(f.get('filesize')), | |
795 | } for format_id, f in source_files.items() if f.get('url')], [] | |
796 | ||
797 | programme_id = media_meta.get('externalId') | |
798 | if programme_id: | |
799 | return self._download_media_selector(programme_id) | |
800 | ||
801 | # Process playlist.sxml as legacy playlist | |
802 | href = media_meta.get('href') | |
803 | if href: | |
804 | playlist = self._download_legacy_playlist_url(href) | |
805 | _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) | |
806 | return formats, subtitles | |
807 | ||
808 | return [], [] | |
809 | ||
baf39a1a S |
810 | def _extract_from_playlist_sxml(self, url, playlist_id, timestamp): |
811 | programme_id, title, description, duration, formats, subtitles = \ | |
812 | self._process_legacy_playlist_url(url, playlist_id) | |
813 | self._sort_formats(formats) | |
814 | return { | |
815 | 'id': programme_id, | |
816 | 'title': title, | |
817 | 'description': description, | |
818 | 'duration': duration, | |
819 | 'timestamp': timestamp, | |
820 | 'formats': formats, | |
821 | 'subtitles': subtitles, | |
822 | } | |
823 | ||
10273d6e | 824 | def _real_extract(self, url): |
9afa1770 S |
825 | playlist_id = self._match_id(url) |
826 | ||
827 | webpage = self._download_webpage(url, playlist_id) | |
828 | ||
522f6c06 | 829 | json_ld_info = self._search_json_ld(webpage, playlist_id, default={}) |
350e02d4 | 830 | timestamp = json_ld_info.get('timestamp') |
0e832c2c | 831 | |
350e02d4 | 832 | playlist_title = json_ld_info.get('title') |
0e832c2c S |
833 | if not playlist_title: |
834 | playlist_title = self._og_search_title( | |
835 | webpage, default=None) or self._html_search_regex( | |
836 | r'<title>(.+?)</title>', webpage, 'playlist title', default=None) | |
837 | if playlist_title: | |
838 | playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip() | |
839 | ||
840 | playlist_description = json_ld_info.get( | |
841 | 'description') or self._og_search_description(webpage, default=None) | |
ae8bdfd1 S |
842 | |
843 | if not timestamp: | |
844 | timestamp = parse_iso8601(self._search_regex( | |
845 | [r'<meta[^>]+property="article:published_time"[^>]+content="([^"]+)"', | |
846 | r'itemprop="datePublished"[^>]+datetime="([^"]+)"', | |
6f789365 | 847 | r'"datePublished":\s*"([^"]+)'], |
ae8bdfd1 | 848 | webpage, 'date', default=None)) |
9afa1770 | 849 | |
78f9d843 S |
850 | entries = [] |
851 | ||
de665713 S |
852 | # article with multiple videos embedded with playlist.sxml (e.g. |
853 | # http://www.bbc.com/sport/0/football/34475836) | |
854 | playlists = re.findall(r'<param[^>]+name="playlist"[^>]+value="([^"]+)"', webpage) | |
222e11d4 | 855 | playlists.extend(re.findall(r'data-media-id="([^"]+/playlist\.sxml)"', webpage)) |
de665713 | 856 | if playlists: |
baf39a1a S |
857 | entries = [ |
858 | self._extract_from_playlist_sxml(playlist_url, playlist_id, timestamp) | |
859 | for playlist_url in playlists] | |
de939d89 | 860 | |
78f9d843 S |
861 | # news article with multiple videos embedded with data-playable |
862 | data_playables = re.findall(r'data-playable=(["\'])({.+?})\1', webpage) | |
863 | if data_playables: | |
864 | for _, data_playable_json in data_playables: | |
865 | data_playable = self._parse_json( | |
866 | unescapeHTML(data_playable_json), playlist_id, fatal=False) | |
867 | if not data_playable: | |
868 | continue | |
baf39a1a S |
869 | settings = data_playable.get('settings', {}) |
870 | if settings: | |
78f9d843 S |
871 | # data-playable with video vpid in settings.playlistObject.items (e.g. |
872 | # http://www.bbc.com/news/world-us-canada-34473351) | |
baf39a1a S |
873 | playlist_object = settings.get('playlistObject', {}) |
874 | if playlist_object: | |
875 | items = playlist_object.get('items') | |
876 | if items and isinstance(items, list): | |
78f9d843 S |
877 | title = playlist_object['title'] |
878 | description = playlist_object.get('summary') | |
baf39a1a S |
879 | duration = int_or_none(items[0].get('duration')) |
880 | programme_id = items[0].get('vpid') | |
78f9d843 S |
881 | formats, subtitles = self._download_media_selector(programme_id) |
882 | self._sort_formats(formats) | |
883 | entries.append({ | |
884 | 'id': programme_id, | |
885 | 'title': title, | |
886 | 'description': description, | |
887 | 'timestamp': timestamp, | |
888 | 'duration': duration, | |
889 | 'formats': formats, | |
890 | 'subtitles': subtitles, | |
891 | }) | |
892 | else: | |
893 | # data-playable without vpid but with a playlist.sxml URLs | |
894 | # in otherSettings.playlist (e.g. | |
895 | # http://www.bbc.com/turkce/multimedya/2015/10/151010_vid_ankara_patlama_ani) | |
896 | playlist = data_playable.get('otherSettings', {}).get('playlist', {}) | |
897 | if playlist: | |
a7e5f274 RA |
898 | entry = None |
899 | for key in ('streaming', 'progressiveDownload'): | |
05087d1b S |
900 | playlist_url = playlist.get('%sUrl' % key) |
901 | if not playlist_url: | |
902 | continue | |
903 | try: | |
a7e5f274 RA |
904 | info = self._extract_from_playlist_sxml( |
905 | playlist_url, playlist_id, timestamp) | |
906 | if not entry: | |
907 | entry = info | |
908 | else: | |
909 | entry['title'] = info['title'] | |
910 | entry['formats'].extend(info['formats']) | |
05087d1b S |
911 | except Exception as e: |
912 | # Some playlist URL may fail with 500, at the same time | |
913 | # the other one may work fine (e.g. | |
914 | # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) | |
915 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 500: | |
916 | continue | |
917 | raise | |
a7e5f274 RA |
918 | if entry: |
919 | self._sort_formats(entry['formats']) | |
920 | entries.append(entry) | |
78f9d843 S |
921 | |
922 | if entries: | |
78f9d843 S |
923 | return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) |
924 | ||
925 | # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) | |
926 | programme_id = self._search_regex( | |
a1cf3e38 | 927 | [r'data-(?:video-player|media)-vpid="(%s)"' % self._ID_REGEX, |
22d7368d S |
928 | r'<param[^>]+name="externalIdentifier"[^>]+value="(%s)"' % self._ID_REGEX, |
929 | r'videoId\s*:\s*["\'](%s)["\']' % self._ID_REGEX], | |
78f9d843 | 930 | webpage, 'vpid', default=None) |
dab062fb | 931 | |
9afa1770 S |
932 | if programme_id: |
933 | formats, subtitles = self._download_media_selector(programme_id) | |
934 | self._sort_formats(formats) | |
935 | # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) | |
936 | digital_data = self._parse_json( | |
937 | self._search_regex( | |
938 | r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), | |
939 | programme_id, fatal=False) | |
940 | page_info = digital_data.get('page', {}).get('pageInfo', {}) | |
941 | title = page_info.get('pageName') or self._og_search_title(webpage) | |
942 | description = page_info.get('description') or self._og_search_description(webpage) | |
943 | timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp | |
944 | return { | |
945 | 'id': programme_id, | |
946 | 'title': title, | |
947 | 'description': description, | |
948 | 'timestamp': timestamp, | |
949 | 'formats': formats, | |
950 | 'subtitles': subtitles, | |
951 | } | |
a3bfddfa | 952 | |
9fb64c04 S |
953 | # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975) |
954 | # There are several setPayload calls may be present but the video | |
955 | # seems to be always related to the first one | |
956 | morph_payload = self._parse_json( | |
957 | self._search_regex( | |
958 | r'Morph\.setPayload\([^,]+,\s*({.+?})\);', | |
959 | webpage, 'morph payload', default='{}'), | |
960 | playlist_id, fatal=False) | |
961 | if morph_payload: | |
962 | components = try_get(morph_payload, lambda x: x['body']['components'], list) or [] | |
963 | for component in components: | |
964 | if not isinstance(component, dict): | |
965 | continue | |
966 | lead_media = try_get(component, lambda x: x['props']['leadMedia'], dict) | |
967 | if not lead_media: | |
968 | continue | |
969 | identifiers = lead_media.get('identifiers') | |
970 | if not identifiers or not isinstance(identifiers, dict): | |
971 | continue | |
972 | programme_id = identifiers.get('vpid') or identifiers.get('playablePid') | |
973 | if not programme_id: | |
974 | continue | |
975 | title = lead_media.get('title') or self._og_search_title(webpage) | |
976 | formats, subtitles = self._download_media_selector(programme_id) | |
977 | self._sort_formats(formats) | |
978 | description = lead_media.get('summary') | |
979 | uploader = lead_media.get('masterBrand') | |
980 | uploader_id = lead_media.get('mid') | |
981 | duration = None | |
982 | duration_d = lead_media.get('duration') | |
983 | if isinstance(duration_d, dict): | |
984 | duration = parse_duration(dict_get( | |
985 | duration_d, ('rawDuration', 'formattedDuration', 'spokenDuration'))) | |
986 | return { | |
987 | 'id': programme_id, | |
988 | 'title': title, | |
989 | 'description': description, | |
990 | 'duration': duration, | |
991 | 'uploader': uploader, | |
992 | 'uploader_id': uploader_id, | |
993 | 'formats': formats, | |
994 | 'subtitles': subtitles, | |
995 | } | |
996 | ||
88ed52ae S |
997 | def extract_all(pattern): |
998 | return list(filter(None, map( | |
999 | lambda s: self._parse_json(s, playlist_id, fatal=False), | |
1000 | re.findall(pattern, webpage)))) | |
1001 | ||
1002 | # Multiple video article (e.g. | |
1003 | # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) | |
22d7368d | 1004 | EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+%s(?:\b[^"]+)?' % self._ID_REGEX |
88ed52ae S |
1005 | entries = [] |
1006 | for match in extract_all(r'new\s+SMP\(({.+?})\)'): | |
1007 | embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') | |
1008 | if embed_url and re.match(EMBED_URL, embed_url): | |
1009 | entries.append(embed_url) | |
1010 | entries.extend(re.findall( | |
1011 | r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage)) | |
1012 | if entries: | |
1013 | return self.playlist_result( | |
aaa42cf0 | 1014 | [self.url_result(entry_, 'BBCCoUk') for entry_ in entries], |
88ed52ae | 1015 | playlist_id, playlist_title, playlist_description) |
9afa1770 S |
1016 | |
1017 | # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) | |
88ed52ae | 1018 | medias = extract_all(r"data-media-meta='({[^']+})'") |
9afa1770 S |
1019 | |
1020 | if not medias: | |
1021 | # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) | |
a346b1ff S |
1022 | media_asset = self._search_regex( |
1023 | r'mediaAssetPage\.init\(\s*({.+?}), "/', | |
1024 | webpage, 'media asset', default=None) | |
1025 | if media_asset: | |
1026 | media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False) | |
1027 | medias = [] | |
1028 | for video in media_asset_page.get('videos', {}).values(): | |
1029 | medias.extend(video.values()) | |
1030 | ||
1031 | if not medias: | |
1032 | # Multiple video playlist with single `now playing` entry (e.g. | |
1033 | # http://www.bbc.com/news/video_and_audio/must_see/33767813) | |
1034 | vxp_playlist = self._parse_json( | |
9afa1770 | 1035 | self._search_regex( |
a346b1ff S |
1036 | r'<script[^>]+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)</script>', |
1037 | webpage, 'playlist data'), | |
9afa1770 | 1038 | playlist_id) |
a346b1ff S |
1039 | playlist_medias = [] |
1040 | for item in vxp_playlist: | |
1041 | media = item.get('media') | |
1042 | if not media: | |
1043 | continue | |
1044 | playlist_medias.append(media) | |
1045 | # Download single video if found media with asset id matching the video id from URL | |
1046 | if item.get('advert', {}).get('assetId') == playlist_id: | |
1047 | medias = [media] | |
1048 | break | |
1049 | # Fallback to the whole playlist | |
1050 | if not medias: | |
1051 | medias = playlist_medias | |
9afa1770 S |
1052 | |
1053 | entries = [] | |
1054 | for num, media_meta in enumerate(medias, start=1): | |
1055 | formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) | |
1056 | if not formats: | |
1057 | continue | |
10273d6e | 1058 | self._sort_formats(formats) |
1059 | ||
9afa1770 S |
1060 | video_id = media_meta.get('externalId') |
1061 | if not video_id: | |
1062 | video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) | |
1063 | ||
1064 | title = media_meta.get('caption') | |
1065 | if not title: | |
1066 | title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) | |
1067 | ||
1068 | duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) | |
da92eeae | 1069 | |
9afa1770 S |
1070 | images = [] |
1071 | for image in media_meta.get('images', {}).values(): | |
1072 | images.extend(image.values()) | |
1073 | if 'image' in media_meta: | |
1074 | images.append(media_meta['image']) | |
1075 | ||
1076 | thumbnails = [{ | |
1077 | 'url': image.get('href'), | |
1078 | 'width': int_or_none(image.get('width')), | |
1079 | 'height': int_or_none(image.get('height')), | |
1080 | } for image in images] | |
1081 | ||
1082 | entries.append({ | |
1083 | 'id': video_id, | |
10273d6e | 1084 | 'title': title, |
9afa1770 | 1085 | 'thumbnails': thumbnails, |
10273d6e | 1086 | 'duration': duration, |
9afa1770 | 1087 | 'timestamp': timestamp, |
10273d6e | 1088 | 'formats': formats, |
1089 | 'subtitles': subtitles, | |
a3bfddfa | 1090 | }) |
10273d6e | 1091 | |
9afa1770 | 1092 | return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) |
a65402ef YCH |
1093 | |
1094 | ||
1095 | class BBCCoUkArticleIE(InfoExtractor): | |
92519402 | 1096 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/articles/(?P<id>[a-zA-Z0-9]+)' |
a65402ef YCH |
1097 | IE_NAME = 'bbc.co.uk:article' |
1098 | IE_DESC = 'BBC articles' | |
1099 | ||
1100 | _TEST = { | |
1101 | 'url': 'http://www.bbc.co.uk/programmes/articles/3jNQLTMrPlYGTBn0WV6M2MS/not-your-typical-role-model-ada-lovelace-the-19th-century-programmer', | |
1102 | 'info_dict': { | |
1103 | 'id': '3jNQLTMrPlYGTBn0WV6M2MS', | |
1104 | 'title': 'Calculating Ada: The Countess of Computing - Not your typical role model: Ada Lovelace the 19th century programmer - BBC Four', | |
1105 | 'description': 'Hannah Fry reveals some of her surprising discoveries about Ada Lovelace during filming.', | |
1106 | }, | |
1107 | 'playlist_count': 4, | |
1108 | 'add_ie': ['BBCCoUk'], | |
1109 | } | |
1110 | ||
1111 | def _real_extract(self, url): | |
1112 | playlist_id = self._match_id(url) | |
1113 | ||
1114 | webpage = self._download_webpage(url, playlist_id) | |
1115 | ||
1116 | title = self._og_search_title(webpage) | |
1117 | description = self._og_search_description(webpage).strip() | |
1118 | ||
1119 | entries = [self.url_result(programme_url) for programme_url in re.findall( | |
1120 | r'<div[^>]+typeof="Clip"[^>]+resource="([^"]+)"', webpage)] | |
1121 | ||
1122 | return self.playlist_result(entries, playlist_id, title, description) | |
ded7511a S |
1123 | |
1124 | ||
1125 | class BBCCoUkPlaylistBaseIE(InfoExtractor): | |
254e64a2 S |
1126 | def _entries(self, webpage, url, playlist_id): |
1127 | single_page = 'page' in compat_urlparse.parse_qs( | |
1128 | compat_urlparse.urlparse(url).query) | |
1129 | for page_num in itertools.count(2): | |
1130 | for video_id in re.findall( | |
1131 | self._VIDEO_ID_TEMPLATE % BBCCoUkIE._ID_REGEX, webpage): | |
1132 | yield self.url_result( | |
1133 | self._URL_TEMPLATE % video_id, BBCCoUkIE.ie_key()) | |
1134 | if single_page: | |
1135 | return | |
1136 | next_page = self._search_regex( | |
1137 | r'<li[^>]+class=(["\'])pagination_+next\1[^>]*><a[^>]+href=(["\'])(?P<url>(?:(?!\2).)+)\2', | |
1138 | webpage, 'next page url', default=None, group='url') | |
1139 | if not next_page: | |
1140 | break | |
1141 | webpage = self._download_webpage( | |
1142 | compat_urlparse.urljoin(url, next_page), playlist_id, | |
1143 | 'Downloading page %d' % page_num, page_num) | |
1144 | ||
ded7511a S |
1145 | def _real_extract(self, url): |
1146 | playlist_id = self._match_id(url) | |
1147 | ||
1148 | webpage = self._download_webpage(url, playlist_id) | |
1149 | ||
ded7511a S |
1150 | title, description = self._extract_title_and_description(webpage) |
1151 | ||
254e64a2 S |
1152 | return self.playlist_result( |
1153 | self._entries(webpage, url, playlist_id), | |
1154 | playlist_id, title, description) | |
ded7511a S |
1155 | |
1156 | ||
1157 | class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE): | |
1158 | IE_NAME = 'bbc.co.uk:iplayer:playlist' | |
9158af16 | 1159 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX |
ded7511a S |
1160 | _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s' |
1161 | _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)' | |
9158af16 | 1162 | _TESTS = [{ |
ded7511a S |
1163 | 'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v', |
1164 | 'info_dict': { | |
1165 | 'id': 'b05rcz9v', | |
1166 | 'title': 'The Disappearance', | |
1167 | 'description': 'French thriller serial about a missing teenager.', | |
1168 | }, | |
1169 | 'playlist_mincount': 6, | |
c6668e4a | 1170 | 'skip': 'This programme is not currently available on BBC iPlayer', |
9158af16 S |
1171 | }, { |
1172 | # Available for over a year unlike 30 days for most other programmes | |
1173 | 'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32', | |
1174 | 'info_dict': { | |
1175 | 'id': 'p02tcc32', | |
1176 | 'title': 'Bohemian Icons', | |
1177 | 'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7', | |
1178 | }, | |
1179 | 'playlist_mincount': 10, | |
1180 | }] | |
ded7511a S |
1181 | |
1182 | def _extract_title_and_description(self, webpage): | |
1183 | title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False) | |
1184 | description = self._search_regex( | |
1185 | r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>', | |
1186 | webpage, 'description', fatal=False, group='value') | |
1187 | return title, description | |
1188 | ||
1189 | ||
1190 | class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE): | |
1191 | IE_NAME = 'bbc.co.uk:playlist' | |
1192 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/programmes/(?P<id>%s)/(?:episodes|broadcasts|clips)' % BBCCoUkIE._ID_REGEX | |
1193 | _URL_TEMPLATE = 'http://www.bbc.co.uk/programmes/%s' | |
1194 | _VIDEO_ID_TEMPLATE = r'data-pid=["\'](%s)' | |
1195 | _TESTS = [{ | |
1196 | 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', | |
1197 | 'info_dict': { | |
1198 | 'id': 'b05rcz9v', | |
1199 | 'title': 'The Disappearance - Clips - BBC Four', | |
1200 | 'description': 'French thriller serial about a missing teenager.', | |
1201 | }, | |
1202 | 'playlist_mincount': 7, | |
4f640f28 S |
1203 | }, { |
1204 | # multipage playlist, explicit page | |
1205 | 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips?page=1', | |
1206 | 'info_dict': { | |
1207 | 'id': 'b00mfl7n', | |
1208 | 'title': 'Frozen Planet - Clips - BBC One', | |
1209 | 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c', | |
1210 | }, | |
1211 | 'playlist_mincount': 24, | |
1212 | }, { | |
1213 | # multipage playlist, all pages | |
1214 | 'url': 'http://www.bbc.co.uk/programmes/b00mfl7n/clips', | |
1215 | 'info_dict': { | |
1216 | 'id': 'b00mfl7n', | |
1217 | 'title': 'Frozen Planet - Clips - BBC One', | |
1218 | 'description': 'md5:65dcbf591ae628dafe32aa6c4a4a0d8c', | |
1219 | }, | |
1220 | 'playlist_mincount': 142, | |
ded7511a S |
1221 | }, { |
1222 | 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/broadcasts/2016/06', | |
1223 | 'only_matching': True, | |
1224 | }, { | |
1225 | 'url': 'http://www.bbc.co.uk/programmes/b05rcz9v/clips', | |
1226 | 'only_matching': True, | |
1227 | }, { | |
1228 | 'url': 'http://www.bbc.co.uk/programmes/b055jkys/episodes/player', | |
1229 | 'only_matching': True, | |
1230 | }] | |
1231 | ||
1232 | def _extract_title_and_description(self, webpage): | |
1233 | title = self._og_search_title(webpage, fatal=False) | |
1234 | description = self._og_search_description(webpage) | |
1235 | return title, description |