aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/bbc.py
blob: c8f285165f7d4736d8908d83ae92e60b86c5b0e3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
from __future__ import unicode_literals

import xml.etree.ElementTree

from .common import InfoExtractor
from ..utils import (
    ExtractorError,
    parse_duration,
    int_or_none,
)
from ..compat import compat_HTTPError
import re


class BBCCoUkIE(InfoExtractor):
    IE_NAME = 'bbc.co.uk'
    IE_DESC = 'BBC iPlayer'
    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P<id>[\da-z]{8})'

    mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s'

    _TESTS = [
        {
            'url': 'http://www.bbc.co.uk/programmes/b039g8p7',
            'info_dict': {
                'id': 'b039d07m',
                'ext': 'flv',
                'title': 'Kaleidoscope, Leonard Cohen',
                'description': 'The Canadian poet and songwriter reflects on his musical career.',
                'duration': 1740,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            }
        },
        {
            'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/',
            'info_dict': {
                'id': 'b00yng1d',
                'ext': 'flv',
                'title': 'The Man in Black: Series 3: The Printed Name',
                'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.",
                'duration': 1800,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
            'skip': 'Episode is no longer available on BBC iPlayer Radio',
        },
        {
            'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/',
            'info_dict': {
                'id': 'b00yng1d',
                'ext': 'flv',
                'title': 'The Voice UK: Series 3: Blind Auditions 5',
                '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.",
                'duration': 5100,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
        },
        {
            'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion',
            'info_dict': {
                'id': 'b03k3pb7',
                'ext': 'flv',
                'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction",
                'description': '2. Invasion',
                'duration': 3600,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
            'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only',
        }, {
            'url': 'http://www.bbc.co.uk/programmes/b04v20dw',
            'info_dict': {
                'id': 'b04v209v',
                'ext': 'flv',
                'title': 'Pete Tong, The Essential New Tune Special',
                'description': "Pete has a very special mix - all of 2014's Essential New Tunes!",
                'duration': 10800,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            }
        }, {
            'url': 'http://www.bbc.co.uk/music/clips/p02frcc3',
            'note': 'Audio',
            'info_dict': {
                'id': 'p02frcch',
                'ext': 'flv',
                'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix',
                'description': 'French house superstar Madeon takes us out of the club and onto the after party.',
                'duration': 3507,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            }
        }, {
            'url': 'http://www.bbc.co.uk/music/clips/p025c0zz',
            'note': 'Video',
            'info_dict': {
                'id': 'p025c103',
                'ext': 'flv',
                'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)',
                'description': 'Rae Morris performs Closer for BBC Three at Reading 2014',
                'duration': 226,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            }
        }, {
            'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls',
            'info_dict': {
                'id': 'p02n76xf',
                'ext': 'flv',
                'title': 'Natural World, 2015-2016: 2. Super Powered Owls',
                'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d',
                'duration': 3540,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
            'skip': 'geolocation',
        }, {
            'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition',
            'info_dict': {
                'id': 'b05zmgw1',
                'ext': 'flv',
                '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.',
                'title': 'Royal Academy Summer Exhibition',
                'duration': 3540,
            },
            'params': {
                # rtmp download
                'skip_download': True,
            },
            'skip': 'geolocation',
        }, {
            'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4',
            'only_matching': True,
        }, {
            'url': 'http://www.bbc.co.uk/music/clips#p02frcc3',
            'only_matching': True,
        }, {
            'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo',
            'only_matching': True,
        }
    ]

    def _extract_asx_playlist(self, connection, programme_id):
        asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist')
        return [ref.get('href') for ref in asx.findall('./Entry/ref')]

    def _extract_connection(self, connection, programme_id):
        formats = []
        protocol = connection.get('protocol')
        supplier = connection.get('supplier')
        if protocol == 'http':
            href = connection.get('href')
            # ASX playlist
            if supplier == 'asx':
                for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)):
                    formats.append({
                        'url': ref,
                        'format_id': 'ref%s_%s' % (i, supplier),
                    })
            # Direct link
            else:
                formats.append({
                    'url': href,
                    'format_id': supplier,
                })
        elif protocol == 'rtmp':
            application = connection.get('application', 'ondemand')
            auth_string = connection.get('authString')
            identifier = connection.get('identifier')
            server = connection.get('server')
            formats.append({
                'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string),
                'play_path': identifier,
                'app': '%s?%s' % (application, auth_string),
                'page_url': 'http://www.bbc.co.uk',
                'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf',
                'rtmp_live': False,
                'ext': 'flv',
                'format_id': supplier,
            })
        return formats

    def _extract_items(self, playlist):
        return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item')

    def _extract_medias(self, media_selection):
        error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error')
        if error is not None:
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True)
        return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media')

    def _extract_connections(self, media):
        return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection')

    def _extract_video(self, media, programme_id):
        formats = []
        vbr = int(media.get('bitrate'))
        vcodec = media.get('encoding')
        service = media.get('service')
        width = int(media.get('width'))
        height = int(media.get('height'))
        file_size = int(media.get('media_file_size'))
        for connection in self._extract_connections(media):
            conn_formats = self._extract_connection(connection, programme_id)
            for format in conn_formats:
                format.update({
                    'format_id': '%s_%s' % (service, format['format_id']),
                    'width': width,
                    'height': height,
                    'vbr': vbr,
                    'vcodec': vcodec,
                    'filesize': file_size,
                })
            formats.extend(conn_formats)
        return formats

    def _extract_audio(self, media, programme_id):
        formats = []
        abr = int(media.get('bitrate'))
        acodec = media.get('encoding')
        service = media.get('service')
        for connection in self._extract_connections(media):
            conn_formats = self._extract_connection(connection, programme_id)
            for format in conn_formats:
                format.update({
                    'format_id': '%s_%s' % (service, format['format_id']),
                    'abr': abr,
                    'acodec': acodec,
                })
            formats.extend(conn_formats)
        return formats

    def _get_subtitles(self, media, programme_id):
        subtitles = {}
        for connection in self._extract_connections(media):
            captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions')
            lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en')
            subtitles[lang] = [
                {
                    'url': connection.get('href'),
                    'ext': 'ttml',
                },
            ]
        return subtitles

    def _download_media_selector(self, programme_id):
        try:
            media_selection = self._download_xml(
                self.mediaselector_url % programme_id,
                programme_id, 'Downloading media selection XML')
        except ExtractorError as ee:
            if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
                media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8'))
            else:
                raise

        formats = []
        subtitles = None

        for media in self._extract_medias(media_selection):
            kind = media.get('kind')
            if kind == 'audio':
                formats.extend(self._extract_audio(media, programme_id))
            elif kind == 'video':
                formats.extend(self._extract_video(media, programme_id))
            elif kind == 'captions':
                subtitles = self.extract_subtitles(media, programme_id)

        return formats, subtitles

    def _download_playlist(self, playlist_id):
        try:
            playlist = self._download_json(
                'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id,
                playlist_id, 'Downloading playlist JSON')

            version = playlist.get('defaultAvailableVersion')
            if version:
                smp_config = version['smpConfig']
                title = smp_config['title']
                description = smp_config['summary']
                for item in smp_config['items']:
                    kind = item['kind']
                    if kind != 'programme' and kind != 'radioProgramme':
                        continue
                    programme_id = item.get('vpid')
                    duration = int(item.get('duration'))
                    formats, subtitles = self._download_media_selector(programme_id)
                return programme_id, title, description, duration, formats, subtitles
        except ExtractorError as ee:
            if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404):
                raise

        # fallback to legacy playlist
        playlist = self._download_xml(
            'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id,
            playlist_id, 'Downloading legacy playlist XML')

        no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems')
        if no_items is not None:
            reason = no_items.get('reason')
            if reason == 'preAvailability':
                msg = 'Episode %s is not yet available' % playlist_id
            elif reason == 'postAvailability':
                msg = 'Episode %s is no longer available' % playlist_id
            elif reason == 'noMedia':
                msg = 'Episode %s is not currently available' % playlist_id
            else:
                msg = 'Episode %s is not available: %s' % (playlist_id, reason)
            raise ExtractorError(msg, expected=True)

        for item in self._extract_items(playlist):
            kind = item.get('kind')
            if kind != 'programme' and kind != 'radioProgramme':
                continue
            title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text
            description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text
            programme_id = item.get('identifier')
            duration = int(item.get('duration'))
            formats, subtitles = self._download_media_selector(programme_id)

        return programme_id, title, description, duration, formats, subtitles

    def _real_extract(self, url):
        group_id = self._match_id(url)

        webpage = self._download_webpage(url, group_id, 'Downloading video page')

        programme_id = None

        tviplayer = self._search_regex(
            r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById',
            webpage, 'player', default=None)

        if tviplayer:
            player = self._parse_json(tviplayer, group_id).get('player', {})
            duration = int_or_none(player.get('duration'))
            programme_id = player.get('vpid')

        if not programme_id:
            programme_id = self._search_regex(
                r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None)

        if programme_id:
            formats, subtitles = self._download_media_selector(programme_id)
            title = self._og_search_title(webpage)
            description = self._search_regex(
                r'<p class="[^"]*medium-description[^"]*">([^<]+)</p>',
                webpage, 'description', fatal=False)
        else:
            programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id)

        self._sort_formats(formats)

        return {
            'id': programme_id,
            'title': title,
            'description': description,
            'thumbnail': self._og_search_thumbnail(webpage, default=None),
            'duration': duration,
            'formats': formats,
            'subtitles': subtitles,
        }


class BBCNewsIE(BBCCoUkIE):
    IE_NAME = 'bbc.com'
    IE_DESC = 'BBC news'
    _VALID_URL = r'https?://(?:www\.)?bbc\.com/.+?/(?P<id>[^/]+)$'

    mediaselector_url = 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s'

    _TESTS = [{
        'url': 'http://www.bbc.com/news/world-europe-32668511',
        'info_dict': {
            'id': 'world-europe-32668511',
            'title': 'Russia stages massive WW2 parade despite Western boycott',
        },
        'playlist_count': 2,
    }, {
        'url': 'http://www.bbc.com/news/business-28299555',
        'info_dict': {
            'id': 'business-28299555',
            'title': 'Farnborough Airshow: Video highlights',
        },
        'playlist_count': 9,
    }, {
        'url': 'http://www.bbc.com/news/world-europe-32041533',
        'note': 'Video',
        'info_dict': {
            'id': 'p02mprgb',
            'ext': 'mp4',
            'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
            'description': 'Germanwings plane crash site in aerial video - Aerial footage showed the site of the crash in the Alps - courtesy BFM TV',
            'duration': 47,
            'upload_date': '20150324',
            'uploader': 'BBC News',
        },
        'params': {
            'skip_download': True,
        }
    }, {
        'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu',
        'note': 'Video',
        'info_dict': {
            'id': 'NA',
            'ext': 'mp4',
            'title': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
            'description': 'YPG: Tel Abyad\'\u0131n tamam\u0131 kontrol\xfcm\xfczde',
            'duration': 47,
            'upload_date': '20150615',
            'uploader': 'BBC News',
        },
        'params': {
            'skip_download': True,
        }
    }, {
        'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw',
        'note': 'Video',
        'info_dict': {
            'id': '39275083',
            'ext': 'mp4',
            'title': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
            'description': 'Honduras militariza sus hospitales por nuevo esc\xe1ndalo de corrupci\xf3n',
            'duration': 87,
            'upload_date': '20150619',
            'uploader': 'BBC News',
        },
        'params': {
            'skip_download': True,
        }
    }]

    def _real_extract(self, url):
        list_id = self._match_id(url)
        webpage = self._download_webpage(url, list_id)

        list_title = self._html_search_regex(r'<title>(.*?)(?:\s*-\s*BBC [^ ]+)?</title>', webpage, 'list title')

        pubdate = self._html_search_regex(r'"datePublished":\s*"(\d+-\d+-\d+)', webpage, 'date', default=None)
        if pubdate:
            pubdate = pubdate.replace('-', '')

        ret = []
        jsent = []

        # works with bbc.com/news/something-something-123456 articles
        jsent = map(
            lambda m: self._parse_json(m, list_id),
            re.findall(r"data-media-meta='({[^']+})'", webpage)
        )

        if len(jsent) == 0:
            # http://www.bbc.com/news/video_and_audio/international
            # and single-video articles
            masset = self._html_search_regex(r'mediaAssetPage\.init\(\s*({.+?}), "/', webpage, 'mediaassets', default=None)
            if masset:
                jmasset = self._parse_json(masset, list_id)
                for key, val in jmasset.get('videos', {}).items():
                    for skey, sval in val.items():
                        sval['id'] = skey
                        jsent.append(sval)

        if len(jsent) == 0:
            # stubbornly generic extractor for {json with "image":{allvideoshavethis},etc}
            # in http://www.bbc.com/news/video_and_audio/international
            # prone to breaking if entries have sourceFiles list
            jsent = map(
                lambda m: self._parse_json(m, list_id),
                re.findall(r"({[^{}]+image\":{[^}]+}[^}]+})", webpage)
            )

        if len(jsent) == 0:
            raise ExtractorError('No video found', expected=True)

        for jent in jsent:
            programme_id = jent.get('externalId')
            xml_url = jent.get('href')

            title = jent.get('caption', '')
            if title == '':
                title = list_title

            duration = parse_duration(jent.get('duration'))
            description = list_title
            if jent.get('caption', '') != '':
                description += ' - ' + jent.get('caption')
            thumbnail = None
            if jent.get('image') is not None:
                thumbnail = jent['image'].get('href')

            formats = []
            subtitles = []

            if programme_id:
                formats, subtitles = self._download_media_selector(programme_id)
            elif jent.get('sourceFiles') is not None:
                # mediaselector not used at
                # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu
                for key, val in jent['sourceFiles'].items():
                    formats.append({
                        'ext': val.get('encoding'),
                        'url': val.get('url'),
                        'filesize': int(val.get('filesize')),
                        'format_id': key
                    })
            elif xml_url:
                # Cheap fallback
                # http://playlists.bbc.co.uk/news/(list_id)[ABC..]/playlist.sxml
                xml = self._download_webpage(xml_url, programme_id, 'Downloading playlist.sxml for externalId (fallback)')
                programme_id = self._search_regex(r'<mediator [^>]*identifier="(.+?)"', xml, 'playlist.sxml (externalId fallback)')
                formats, subtitles = self._download_media_selector(programme_id)

            if len(formats) == 0:
                raise ExtractorError('unsupported json media entry.\n    ' + str(jent) + '\n')

            self._sort_formats(formats)

            id = jent.get('id') if programme_id is None else programme_id
            if id is None:
                id = 'NA'

            ret.append({
                'id': id,
                'uploader': 'BBC News',
                'upload_date': pubdate,
                'title': title,
                'description': description,
                'thumbnail': thumbnail,
                'duration': duration,
                'formats': formats,
                'subtitles': subtitles,
            })

        if len(ret) > 0:
            return self.playlist_result(ret, list_id, list_title)
        raise ExtractorError('No video found', expected=True)