]>
Commit | Line | Data |
---|---|---|
1 | from __future__ import unicode_literals | |
2 | ||
3 | import xml.etree.ElementTree | |
4 | ||
5 | from .subtitles import SubtitlesInfoExtractor | |
6 | from ..utils import ExtractorError | |
7 | from ..compat import compat_HTTPError | |
8 | ||
9 | ||
10 | class BBCCoUkIE(SubtitlesInfoExtractor): | |
11 | IE_NAME = 'bbc.co.uk' | |
12 | IE_DESC = 'BBC iPlayer' | |
13 | _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})' | |
14 | ||
15 | _TESTS = [ | |
16 | { | |
17 | 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', | |
18 | 'info_dict': { | |
19 | 'id': 'b039d07m', | |
20 | 'ext': 'flv', | |
21 | 'title': 'Kaleidoscope, Leonard Cohen', | |
22 | 'description': 'The Canadian poet and songwriter reflects on his musical career.', | |
23 | 'duration': 1740, | |
24 | }, | |
25 | 'params': { | |
26 | # rtmp download | |
27 | 'skip_download': True, | |
28 | } | |
29 | }, | |
30 | { | |
31 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', | |
32 | 'info_dict': { | |
33 | 'id': 'b00yng1d', | |
34 | 'ext': 'flv', | |
35 | 'title': 'The Man in Black: Series 3: The Printed Name', | |
36 | 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", | |
37 | 'duration': 1800, | |
38 | }, | |
39 | 'params': { | |
40 | # rtmp download | |
41 | 'skip_download': True, | |
42 | }, | |
43 | 'skip': 'Episode is no longer available on BBC iPlayer Radio', | |
44 | }, | |
45 | { | |
46 | 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', | |
47 | 'info_dict': { | |
48 | 'id': 'b00yng1d', | |
49 | 'ext': 'flv', | |
50 | 'title': 'The Voice UK: Series 3: Blind Auditions 5', | |
51 | '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.", | |
52 | 'duration': 5100, | |
53 | }, | |
54 | 'params': { | |
55 | # rtmp download | |
56 | 'skip_download': True, | |
57 | }, | |
58 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
59 | }, | |
60 | { | |
61 | 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', | |
62 | 'info_dict': { | |
63 | 'id': 'b03k3pb7', | |
64 | 'ext': 'flv', | |
65 | 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", | |
66 | 'description': '2. Invasion', | |
67 | 'duration': 3600, | |
68 | }, | |
69 | 'params': { | |
70 | # rtmp download | |
71 | 'skip_download': True, | |
72 | }, | |
73 | 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', | |
74 | }, { | |
75 | 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', | |
76 | 'info_dict': { | |
77 | 'id': 'b04v209v', | |
78 | 'ext': 'flv', | |
79 | 'title': 'Pete Tong, The Essential New Tune Special', | |
80 | 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", | |
81 | 'duration': 10800, | |
82 | }, | |
83 | 'params': { | |
84 | # rtmp download | |
85 | 'skip_download': True, | |
86 | } | |
87 | }, { | |
88 | 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', | |
89 | 'note': 'Audio', | |
90 | 'info_dict': { | |
91 | 'id': 'p02frcch', | |
92 | 'ext': 'flv', | |
93 | 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', | |
94 | 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', | |
95 | 'duration': 3507, | |
96 | }, | |
97 | 'params': { | |
98 | # rtmp download | |
99 | 'skip_download': True, | |
100 | } | |
101 | }, { | |
102 | 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', | |
103 | 'note': 'Video', | |
104 | 'info_dict': { | |
105 | 'id': 'p025c103', | |
106 | 'ext': 'flv', | |
107 | 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', | |
108 | 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', | |
109 | 'duration': 226, | |
110 | }, | |
111 | 'params': { | |
112 | # rtmp download | |
113 | 'skip_download': True, | |
114 | } | |
115 | }, { | |
116 | 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', | |
117 | 'only_matching': True, | |
118 | }, { | |
119 | 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', | |
120 | 'only_matching': True, | |
121 | }, { | |
122 | 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', | |
123 | 'only_matching': True, | |
124 | } | |
125 | ] | |
126 | ||
127 | def _extract_asx_playlist(self, connection, programme_id): | |
128 | asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') | |
129 | return [ref.get('href') for ref in asx.findall('./Entry/ref')] | |
130 | ||
131 | def _extract_connection(self, connection, programme_id): | |
132 | formats = [] | |
133 | protocol = connection.get('protocol') | |
134 | supplier = connection.get('supplier') | |
135 | if protocol == 'http': | |
136 | href = connection.get('href') | |
137 | # ASX playlist | |
138 | if supplier == 'asx': | |
139 | for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): | |
140 | formats.append({ | |
141 | 'url': ref, | |
142 | 'format_id': 'ref%s_%s' % (i, supplier), | |
143 | }) | |
144 | # Direct link | |
145 | else: | |
146 | formats.append({ | |
147 | 'url': href, | |
148 | 'format_id': supplier, | |
149 | }) | |
150 | elif protocol == 'rtmp': | |
151 | application = connection.get('application', 'ondemand') | |
152 | auth_string = connection.get('authString') | |
153 | identifier = connection.get('identifier') | |
154 | server = connection.get('server') | |
155 | formats.append({ | |
156 | 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), | |
157 | 'play_path': identifier, | |
158 | 'app': '%s?%s' % (application, auth_string), | |
159 | 'page_url': 'http://www.bbc.co.uk', | |
160 | 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', | |
161 | 'rtmp_live': False, | |
162 | 'ext': 'flv', | |
163 | 'format_id': supplier, | |
164 | }) | |
165 | return formats | |
166 | ||
167 | def _extract_items(self, playlist): | |
168 | return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') | |
169 | ||
170 | def _extract_medias(self, media_selection): | |
171 | error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') | |
172 | if error is not None: | |
173 | raise ExtractorError( | |
174 | '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True) | |
175 | return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') | |
176 | ||
177 | def _extract_connections(self, media): | |
178 | return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') | |
179 | ||
180 | def _extract_video(self, media, programme_id): | |
181 | formats = [] | |
182 | vbr = int(media.get('bitrate')) | |
183 | vcodec = media.get('encoding') | |
184 | service = media.get('service') | |
185 | width = int(media.get('width')) | |
186 | height = int(media.get('height')) | |
187 | file_size = int(media.get('media_file_size')) | |
188 | for connection in self._extract_connections(media): | |
189 | conn_formats = self._extract_connection(connection, programme_id) | |
190 | for format in conn_formats: | |
191 | format.update({ | |
192 | 'format_id': '%s_%s' % (service, format['format_id']), | |
193 | 'width': width, | |
194 | 'height': height, | |
195 | 'vbr': vbr, | |
196 | 'vcodec': vcodec, | |
197 | 'filesize': file_size, | |
198 | }) | |
199 | formats.extend(conn_formats) | |
200 | return formats | |
201 | ||
202 | def _extract_audio(self, media, programme_id): | |
203 | formats = [] | |
204 | abr = int(media.get('bitrate')) | |
205 | acodec = media.get('encoding') | |
206 | service = media.get('service') | |
207 | for connection in self._extract_connections(media): | |
208 | conn_formats = self._extract_connection(connection, programme_id) | |
209 | for format in conn_formats: | |
210 | format.update({ | |
211 | 'format_id': '%s_%s' % (service, format['format_id']), | |
212 | 'abr': abr, | |
213 | 'acodec': acodec, | |
214 | }) | |
215 | formats.extend(conn_formats) | |
216 | return formats | |
217 | ||
218 | def _extract_captions(self, media, programme_id): | |
219 | subtitles = {} | |
220 | for connection in self._extract_connections(media): | |
221 | captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') | |
222 | lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') | |
223 | ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}')) | |
224 | srt = '' | |
225 | for pos, p in enumerate(ps): | |
226 | srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), | |
227 | p.text.strip() if p.text is not None else '') | |
228 | subtitles[lang] = srt | |
229 | return subtitles | |
230 | ||
231 | def _download_media_selector(self, programme_id): | |
232 | try: | |
233 | media_selection = self._download_xml( | |
234 | 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, | |
235 | programme_id, 'Downloading media selection XML') | |
236 | except ExtractorError as ee: | |
237 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
238 | media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().encode('utf-8')) | |
239 | else: | |
240 | raise | |
241 | ||
242 | formats = [] | |
243 | subtitles = None | |
244 | ||
245 | for media in self._extract_medias(media_selection): | |
246 | kind = media.get('kind') | |
247 | if kind == 'audio': | |
248 | formats.extend(self._extract_audio(media, programme_id)) | |
249 | elif kind == 'video': | |
250 | formats.extend(self._extract_video(media, programme_id)) | |
251 | elif kind == 'captions': | |
252 | subtitles = self._extract_captions(media, programme_id) | |
253 | ||
254 | return formats, subtitles | |
255 | ||
256 | def _download_playlist(self, playlist_id): | |
257 | try: | |
258 | playlist = self._download_json( | |
259 | 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, | |
260 | playlist_id, 'Downloading playlist JSON') | |
261 | ||
262 | version = playlist.get('defaultAvailableVersion') | |
263 | if version: | |
264 | smp_config = version['smpConfig'] | |
265 | title = smp_config['title'] | |
266 | description = smp_config['summary'] | |
267 | for item in smp_config['items']: | |
268 | kind = item['kind'] | |
269 | if kind != 'programme' and kind != 'radioProgramme': | |
270 | continue | |
271 | programme_id = item.get('vpid') | |
272 | duration = int(item.get('duration')) | |
273 | formats, subtitles = self._download_media_selector(programme_id) | |
274 | return programme_id, title, description, duration, formats, subtitles | |
275 | except ExtractorError as ee: | |
276 | if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): | |
277 | raise | |
278 | ||
279 | # fallback to legacy playlist | |
280 | playlist = self._download_xml( | |
281 | 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, | |
282 | playlist_id, 'Downloading legacy playlist XML') | |
283 | ||
284 | no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') | |
285 | if no_items is not None: | |
286 | reason = no_items.get('reason') | |
287 | if reason == 'preAvailability': | |
288 | msg = 'Episode %s is not yet available' % playlist_id | |
289 | elif reason == 'postAvailability': | |
290 | msg = 'Episode %s is no longer available' % playlist_id | |
291 | elif reason == 'noMedia': | |
292 | msg = 'Episode %s is not currently available' % playlist_id | |
293 | else: | |
294 | msg = 'Episode %s is not available: %s' % (playlist_id, reason) | |
295 | raise ExtractorError(msg, expected=True) | |
296 | ||
297 | for item in self._extract_items(playlist): | |
298 | kind = item.get('kind') | |
299 | if kind != 'programme' and kind != 'radioProgramme': | |
300 | continue | |
301 | title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text | |
302 | description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text | |
303 | programme_id = item.get('identifier') | |
304 | duration = int(item.get('duration')) | |
305 | formats, subtitles = self._download_media_selector(programme_id) | |
306 | ||
307 | return programme_id, title, description, duration, formats, subtitles | |
308 | ||
309 | def _real_extract(self, url): | |
310 | group_id = self._match_id(url) | |
311 | ||
312 | webpage = self._download_webpage(url, group_id, 'Downloading video page') | |
313 | ||
314 | programme_id = self._search_regex( | |
315 | r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) | |
316 | if programme_id: | |
317 | player = self._download_json( | |
318 | 'http://www.bbc.co.uk/iplayer/episode/%s.json' % group_id, | |
319 | group_id)['jsConf']['player'] | |
320 | title = player['title'] | |
321 | description = player['subtitle'] | |
322 | duration = player['duration'] | |
323 | formats, subtitles = self._download_media_selector(programme_id) | |
324 | else: | |
325 | programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) | |
326 | ||
327 | if self._downloader.params.get('listsubtitles', False): | |
328 | self._list_available_subtitles(programme_id, subtitles) | |
329 | return | |
330 | ||
331 | self._sort_formats(formats) | |
332 | ||
333 | return { | |
334 | 'id': programme_id, | |
335 | 'title': title, | |
336 | 'description': description, | |
337 | 'duration': duration, | |
338 | 'formats': formats, | |
339 | 'subtitles': subtitles, | |
340 | } |