]>
Commit | Line | Data |
---|---|---|
082c6c86 S |
1 | from __future__ import unicode_literals |
2 | ||
c056efa2 | 3 | import xml.etree.ElementTree |
082c6c86 | 4 | |
f13b1e7d | 5 | from .common import InfoExtractor |
8683b4d8 S |
6 | from ..utils import ( |
7 | ExtractorError, | |
8 | int_or_none, | |
9 | ) | |
c056efa2 | 10 | from ..compat import compat_HTTPError |
082c6c86 S |
11 | |
12 | ||
f13b1e7d | 13 | class BBCCoUkIE(InfoExtractor): |
082c6c86 | 14 | IE_NAME = 'bbc.co.uk' |
2e3fd9ec | 15 | IE_DESC = 'BBC iPlayer' |
0692ef86 | 16 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' |
082c6c86 | 17 | |
2e3fd9ec S |
18 | _TESTS = [ |
19 | { | |
f2d0fc68 | 20 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', |
2e3fd9ec | 21 | 'info_dict': { |
f2d0fc68 | 22 | 'id': 'b039d07m', |
2e3fd9ec | 23 | 'ext': 'flv', |
c4914185 S |
24 | 'title': 'Kaleidoscope, Leonard Cohen', |
25 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', | |
f2d0fc68 | 26 | 'duration': 1740, |
2e3fd9ec S |
27 | }, |
28 | 'params': { | |
29 | # rtmp download | |
30 | 'skip_download': True, | |
31 | } | |
082c6c86 | 32 | }, |
2e3fd9ec S |
33 | { |
34 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
35 | 'info_dict': { | |
36 | 'id': 'b00yng1d', | |
37 | 'ext': 'flv', | |
38 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
39 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
40 | 'duration': 1800, | |
41 | }, | |
42 | 'params': { | |
43 | # rtmp download | |
44 | 'skip_download': True, | |
c7f0177f S |
45 | }, |
46 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
2e3fd9ec S |
47 | }, |
48 | { | |
49 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
50 | 'info_dict': { | |
51 | 'id': 'b00yng1d', | |
52 | 'ext': 'flv', | |
17968e44 S |
53 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', |
54 | '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.", | |
55 | 'duration': 5100, | |
2e3fd9ec S |
56 | }, |
57 | 'params': { | |
58 | # rtmp download | |
59 | 'skip_download': True, | |
60 | }, | |
61 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
c056efa2 S |
62 | }, |
63 | { | |
64 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
65 | 'info_dict': { | |
66 | 'id': 'b03k3pb7', | |
67 | 'ext': 'flv', | |
68 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
69 | 'description': '2. Invasion', | |
70 | 'duration': 3600, | |
71 | }, | |
72 | 'params': { | |
73 | # rtmp download | |
74 | 'skip_download': True, | |
75 | }, | |
76 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
ae6986fb S |
77 | }, { |
78 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
79 | 'info_dict': { | |
80 | 'id': 'b04v209v', | |
81 | 'ext': 'flv', | |
82 | 'title': 'Pete Tong, The Essential New Tune Special', | |
83 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
84 | 'duration': 10800, | |
85 | }, | |
86 | 'params': { | |
87 | # rtmp download | |
88 | 'skip_download': True, | |
89 | } | |
c7e67594 S |
90 | }, { |
91 | 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', | |
92 | 'note': 'Audio', | |
93 | 'info_dict': { | |
94 | 'id': 'p02frcch', | |
95 | 'ext': 'flv', | |
96 | 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', | |
97 | 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', | |
98 | 'duration': 3507, | |
99 | }, | |
100 | 'params': { | |
101 | # rtmp download | |
102 | 'skip_download': True, | |
103 | } | |
104 | }, { | |
105 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
106 | 'note': 'Video', | |
107 | 'info_dict': { | |
108 | 'id': 'p025c103', | |
109 | 'ext': 'flv', | |
110 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', | |
111 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
112 | 'duration': 226, | |
113 | }, | |
114 | 'params': { | |
115 | # rtmp download | |
116 | 'skip_download': True, | |
117 | } | |
e68ae99a S |
118 | }, { |
119 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', | |
120 | 'info_dict': { | |
121 | 'id': 'p02n76xf', | |
122 | 'ext': 'flv', | |
123 | 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', | |
124 | 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', | |
125 | 'duration': 3540, | |
126 | }, | |
127 | 'params': { | |
128 | # rtmp download | |
129 | 'skip_download': True, | |
130 | }, | |
131 | 'skip': 'geolocation', | |
25fa8d66 YCH |
132 | }, { |
133 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', | |
134 | 'info_dict': { | |
135 | 'id': 'b05zmgw1', | |
136 | 'ext': 'flv', | |
137 | '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.', | |
138 | 'title': 'Royal Academy Summer Exhibition', | |
139 | 'duration': 3540, | |
140 | }, | |
141 | 'params': { | |
142 | # rtmp download | |
143 | 'skip_download': True, | |
144 | }, | |
145 | 'skip': 'geolocation', | |
31763975 S |
146 | }, { |
147 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
148 | 'only_matching': True, | |
c7e67594 S |
149 | }, { |
150 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
151 | 'only_matching': True, | |
0692ef86 S |
152 | }, { |
153 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
154 | 'only_matching': True, | |
ae6986fb | 155 | } |
2e3fd9ec S |
156 | ] |
157 | ||
158 | def _extract_asx_playlist(self, connection, programme_id): | |
159 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
160 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
161 | ||
162 | def _extract_connection(self, connection, programme_id): | |
163 | formats = [] | |
164 | protocol = connection.get('protocol') | |
165 | supplier = connection.get('supplier') | |
166 | if protocol == 'http': | |
167 | href = connection.get('href') | |
168 | # ASX playlist | |
169 | if supplier == 'asx': | |
170 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
171 | formats.append({ | |
172 | 'url': ref, | |
173 | 'format_id': 'ref%s_%s' % (i, supplier), | |
174 | }) | |
175 | # Direct link | |
176 | else: | |
177 | formats.append({ | |
178 | 'url': href, | |
179 | 'format_id': supplier, | |
180 | }) | |
181 | elif protocol == 'rtmp': | |
182 | application = connection.get('application', 'ondemand') | |
183 | auth_string = connection.get('authString') | |
184 | identifier = connection.get('identifier') | |
185 | server = connection.get('server') | |
186 | formats.append({ | |
187 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
188 | 'play_path': identifier, | |
189 | 'app': '%s?%s' % (application, auth_string), | |
190 | 'page_url': 'http://www.bbc.co.uk', | |
191 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
192 | 'rtmp_live': False, | |
193 | 'ext': 'flv', | |
194 | 'format_id': supplier, | |
195 | }) | |
196 | return formats | |
197 | ||
198 | def _extract_items(self, playlist): | |
199 | return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') | |
200 | ||
201 | def _extract_medias(self, media_selection): | |
c056efa2 S |
202 | error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') |
203 | if error is not None: | |
204 | raise ExtractorError( | |
205 | '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True) | |
2e3fd9ec S |
206 | return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') |
207 | ||
208 | def _extract_connections(self, media): | |
209 | return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') | |
210 | ||
211 | def _extract_video(self, media, programme_id): | |
212 | formats = [] | |
213 | vbr = int(media.get('bitrate')) | |
214 | vcodec = media.get('encoding') | |
215 | service = media.get('service') | |
216 | width = int(media.get('width')) | |
217 | height = int(media.get('height')) | |
218 | file_size = int(media.get('media_file_size')) | |
219 | for connection in self._extract_connections(media): | |
220 | conn_formats = self._extract_connection(connection, programme_id) | |
221 | for format in conn_formats: | |
222 | format.update({ | |
223 | 'format_id': '%s_%s' % (service, format['format_id']), | |
224 | 'width': width, | |
225 | 'height': height, | |
226 | 'vbr': vbr, | |
227 | 'vcodec': vcodec, | |
228 | 'filesize': file_size, | |
229 | }) | |
230 | formats.extend(conn_formats) | |
231 | return formats | |
232 | ||
233 | def _extract_audio(self, media, programme_id): | |
234 | formats = [] | |
235 | abr = int(media.get('bitrate')) | |
236 | acodec = media.get('encoding') | |
237 | service = media.get('service') | |
238 | for connection in self._extract_connections(media): | |
239 | conn_formats = self._extract_connection(connection, programme_id) | |
240 | for format in conn_formats: | |
241 | format.update({ | |
242 | 'format_id': '%s_%s' % (service, format['format_id']), | |
243 | 'abr': abr, | |
244 | 'acodec': acodec, | |
245 | }) | |
246 | formats.extend(conn_formats) | |
247 | return formats | |
248 | ||
f13b1e7d | 249 | def _get_subtitles(self, media, programme_id): |
2e3fd9ec S |
250 | subtitles = {} |
251 | for connection in self._extract_connections(media): | |
252 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
253 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
f13b1e7d JMF |
254 | subtitles[lang] = [ |
255 | { | |
256 | 'url': connection.get('href'), | |
257 | 'ext': 'ttml', | |
258 | }, | |
f13b1e7d | 259 | ] |
2e3fd9ec | 260 | return subtitles |
082c6c86 | 261 | |
c056efa2 S |
262 | def _download_media_selector(self, programme_id): |
263 | try: | |
264 | media_selection = self._download_xml( | |
265 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, | |
266 | programme_id, 'Downloading media selection XML') | |
267 | except ExtractorError as ee: | |
268 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
974a6146 | 269 | media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) |
2e3fd9ec | 270 | else: |
c056efa2 | 271 | raise |
082c6c86 S |
272 | |
273 | formats = [] | |
2e3fd9ec S |
274 | subtitles = None |
275 | ||
c056efa2 S |
276 | for media in self._extract_medias(media_selection): |
277 | kind = media.get('kind') | |
278 | if kind == 'audio': | |
279 | formats.extend(self._extract_audio(media, programme_id)) | |
280 | elif kind == 'video': | |
281 | formats.extend(self._extract_video(media, programme_id)) | |
282 | elif kind == 'captions': | |
f13b1e7d | 283 | subtitles = self.extract_subtitles(media, programme_id) |
2e3fd9ec | 284 | |
c056efa2 | 285 | return formats, subtitles |
2e3fd9ec | 286 | |
ae6986fb S |
287 | def _download_playlist(self, playlist_id): |
288 | try: | |
289 | playlist = self._download_json( | |
290 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
291 | playlist_id, 'Downloading playlist JSON') | |
292 | ||
293 | version = playlist.get('defaultAvailableVersion') | |
294 | if version: | |
295 | smp_config = version['smpConfig'] | |
296 | title = smp_config['title'] | |
297 | description = smp_config['summary'] | |
298 | for item in smp_config['items']: | |
299 | kind = item['kind'] | |
300 | if kind != 'programme' and kind != 'radioProgramme': | |
301 | continue | |
302 | programme_id = item.get('vpid') | |
303 | duration = int(item.get('duration')) | |
304 | formats, subtitles = self._download_media_selector(programme_id) | |
305 | return programme_id, title, description, duration, formats, subtitles | |
306 | except ExtractorError as ee: | |
f813928e | 307 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): |
ae6986fb S |
308 | raise |
309 | ||
310 | # fallback to legacy playlist | |
311 | playlist = self._download_xml( | |
931e2d1d PH |
312 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, |
313 | playlist_id, 'Downloading legacy playlist XML') | |
ae6986fb S |
314 | |
315 | no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') | |
316 | if no_items is not None: | |
317 | reason = no_items.get('reason') | |
318 | if reason == 'preAvailability': | |
319 | msg = 'Episode %s is not yet available' % playlist_id | |
320 | elif reason == 'postAvailability': | |
321 | msg = 'Episode %s is no longer available' % playlist_id | |
322 | elif reason == 'noMedia': | |
323 | msg = 'Episode %s is not currently available' % playlist_id | |
324 | else: | |
325 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
326 | raise ExtractorError(msg, expected=True) | |
327 | ||
328 | for item in self._extract_items(playlist): | |
329 | kind = item.get('kind') | |
330 | if kind != 'programme' and kind != 'radioProgramme': | |
331 | continue | |
332 | title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | |
333 | description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | |
334 | programme_id = item.get('identifier') | |
335 | duration = int(item.get('duration')) | |
336 | formats, subtitles = self._download_media_selector(programme_id) | |
337 | ||
338 | return programme_id, title, description, duration, formats, subtitles | |
339 | ||
c056efa2 S |
340 | def _real_extract(self, url): |
341 | group_id = self._match_id(url) | |
342 | ||
343 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
344 | ||
8683b4d8 S |
345 | programme_id = None |
346 | ||
347 | tviplayer = self._search_regex( | |
348 | r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', | |
349 | webpage, 'player', default=None) | |
350 | ||
351 | if tviplayer: | |
352 | player = self._parse_json(tviplayer, group_id).get('player', {}) | |
353 | duration = int_or_none(player.get('duration')) | |
354 | programme_id = player.get('vpid') | |
355 | ||
356 | if not programme_id: | |
357 | programme_id = self._search_regex( | |
358 | r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) | |
359 | ||
c056efa2 | 360 | if programme_id: |
c056efa2 | 361 | formats, subtitles = self._download_media_selector(programme_id) |
8683b4d8 S |
362 | title = self._og_search_title(webpage) |
363 | description = self._search_regex( | |
25fa8d66 | 364 | r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>', |
8683b4d8 | 365 | webpage, 'description', fatal=False) |
c056efa2 | 366 | else: |
ae6986fb | 367 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) |
2e3fd9ec | 368 | |
082c6c86 S |
369 | self._sort_formats(formats) |
370 | ||
371 | return { | |
2e3fd9ec | 372 | 'id': programme_id, |
082c6c86 S |
373 | 'title': title, |
374 | 'description': description, | |
650cfd0c | 375 | 'thumbnail': self._og_search_thumbnail(webpage, default=None), |
082c6c86 S |
376 | 'duration': duration, |
377 | 'formats': formats, | |
2e3fd9ec | 378 | 'subtitles': subtitles, |
5f6a1245 | 379 | } |