aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/nrk.py
blob: 1f2204833acceb8fb39e2b3731d156438451dc98 (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
# coding: utf-8
from __future__ import unicode_literals

import random
import re

from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
    ExtractorError,
    int_or_none,
    parse_age_limit,
    parse_duration,
)


class NRKBaseIE(InfoExtractor):
    _faked_ip = None

    def _download_webpage_handle(self, *args, **kwargs):
        # NRK checks X-Forwarded-For HTTP header in order to figure out the
        # origin of the client behind proxy. This allows to bypass geo
        # restriction by faking this header's value to some Norway IP.
        # We will do so once we encounter any geo restriction error.
        if self._faked_ip:
            # NB: str is intentional
            kwargs.setdefault(str('headers'), {})['X-Forwarded-For'] = self._faked_ip
        return super(NRKBaseIE, self)._download_webpage_handle(*args, **kwargs)

    def _fake_ip(self):
        # Use fake IP from 37.191.128.0/17 in order to workaround geo
        # restriction
        def octet(lb=0, ub=255):
            return random.randint(lb, ub)
        self._faked_ip = '37.191.%d.%d' % (octet(128), octet())

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

        data = self._download_json(
            'http://%s/mediaelement/%s' % (self._API_HOST, video_id),
            video_id, 'Downloading mediaelement JSON')

        title = data.get('fullTitle') or data.get('mainTitle') or data['title']
        video_id = data.get('id') or video_id

        http_headers = {'X-Forwarded-For': self._faked_ip} if self._faked_ip else {}

        entries = []

        media_assets = data.get('mediaAssets')
        if media_assets and isinstance(media_assets, list):
            def video_id_and_title(idx):
                return ((video_id, title) if len(media_assets) == 1
                        else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
            for num, asset in enumerate(media_assets, 1):
                asset_url = asset.get('url')
                if not asset_url:
                    continue
                formats = self._extract_akamai_formats(asset_url, video_id)
                if not formats:
                    continue
                self._sort_formats(formats)
                entry_id, entry_title = video_id_and_title(num)
                duration = parse_duration(asset.get('duration'))
                subtitles = {}
                for subtitle in ('webVtt', 'timedText'):
                    subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
                    if subtitle_url:
                        subtitles.setdefault('no', []).append({
                            'url': compat_urllib_parse_unquote(subtitle_url)
                        })
                entries.append({
                    'id': asset.get('carrierId') or entry_id,
                    'title': entry_title,
                    'duration': duration,
                    'subtitles': subtitles,
                    'formats': formats,
                    'http_headers': http_headers,
                })

        if not entries:
            media_url = data.get('mediaUrl')
            if media_url:
                formats = self._extract_akamai_formats(media_url, video_id)
                self._sort_formats(formats)
                duration = parse_duration(data.get('duration'))
                entries = [{
                    'id': video_id,
                    'title': title,
                    'duration': duration,
                    'formats': formats,
                }]

        if not entries:
            message_type = data.get('messageType')
            if message_type == 'ProgramIsGeoBlocked' and not self._faked_ip:
                self.report_warning(
                    'Video is geo restricted, trying to fake IP')
                self._fake_ip()
                return self._real_extract(url)

            MESSAGES = {
                'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
                'ProgramRightsHasExpired': 'Programmet har gått ut',
                'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
            }
            raise ExtractorError(
                '%s said: %s' % (self.IE_NAME, MESSAGES.get(
                    message_type, message_type)),
                expected=True)

        conviva = data.get('convivaStatistics') or {}
        series = conviva.get('seriesName') or data.get('seriesTitle')
        episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')

        thumbnails = None
        images = data.get('images')
        if images and isinstance(images, dict):
            web_images = images.get('webImages')
            if isinstance(web_images, list):
                thumbnails = [{
                    'url': image['imageUrl'],
                    'width': int_or_none(image.get('width')),
                    'height': int_or_none(image.get('height')),
                } for image in web_images if image.get('imageUrl')]

        description = data.get('description')

        common_info = {
            'description': description,
            'series': series,
            'episode': episode,
            'age_limit': parse_age_limit(data.get('legalAge')),
            'thumbnails': thumbnails,
        }

        vcodec = 'none' if data.get('mediaType') == 'Audio' else None

        # TODO: extract chapters when https://github.com/rg3/youtube-dl/pull/9409 is merged

        for entry in entries:
            entry.update(common_info)
            for f in entry['formats']:
                f['vcodec'] = vcodec

        return self.playlist_result(entries, video_id, title, description)


class NRKIE(NRKBaseIE):
    _VALID_URL = r'''(?x)
                        (?:
                            nrk:|
                            https?://
                                (?:
                                    (?:www\.)?nrk\.no/video/PS\*|
                                    v8-psapi\.nrk\.no/mediaelement/
                                )
                            )
                            (?P<id>[^/?#&]+)
                        '''
    _API_HOST = 'v8.psapi.nrk.no'
    _TESTS = [{
        # video
        'url': 'http://www.nrk.no/video/PS*150533',
        'md5': '2f7f6eeb2aacdd99885f355428715cfa',
        'info_dict': {
            'id': '150533',
            'ext': 'mp4',
            'title': 'Dompap og andre fugler i Piip-Show',
            'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
            'duration': 263,
        }
    }, {
        # audio
        'url': 'http://www.nrk.no/video/PS*154915',
        # MD5 is unstable
        'info_dict': {
            'id': '154915',
            'ext': 'flv',
            'title': 'Slik høres internett ut når du er blind',
            'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
            'duration': 20,
        }
    }, {
        'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
        'only_matching': True,
    }, {
        'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
        'only_matching': True,
    }]


class NRKTVIE(NRKBaseIE):
    IE_DESC = 'NRK TV and NRK Radio'
    _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/(?:serie/[^/]+|program)/(?P<id>[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P<part_id>\d+))?'
    _API_HOST = 'psapi-we.nrk.no'

    _TESTS = [{
        'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
        'md5': '4e9ca6629f09e588ed240fb11619922a',
        'info_dict': {
            'id': 'MUHH48000314AA',
            'ext': 'mp4',
            'title': '20 spørsmål 23.05.2014',
            'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
            'duration': 1741,
        },
    }, {
        'url': 'https://tv.nrk.no/program/mdfp15000514',
        'md5': '43d0be26663d380603a9cf0c24366531',
        'info_dict': {
            'id': 'MDFP15000514CA',
            'ext': 'mp4',
            'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
            'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
            'duration': 4605,
        },
    }, {
        # single playlist video
        'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
        'md5': 'adbd1dbd813edaf532b0a253780719c2',
        'info_dict': {
            'id': 'MSPO40010515-part2',
            'ext': 'flv',
            'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
            'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
        },
        'skip': 'Only works from Norway',
    }, {
        'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
        'playlist': [{
            'md5': '9480285eff92d64f06e02a5367970a7a',
            'info_dict': {
                'id': 'MSPO40010515-part1',
                'ext': 'flv',
                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
            },
        }, {
            'md5': 'adbd1dbd813edaf532b0a253780719c2',
            'info_dict': {
                'id': 'MSPO40010515-part2',
                'ext': 'flv',
                'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
                'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
            },
        }],
        'info_dict': {
            'id': 'MSPO40010515',
            'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
            'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
            'duration': 6947.52,
        },
        'skip': 'Only works from Norway',
    }, {
        'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
        'only_matching': True,
    }]


class NRKPlaylistIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'

    _TESTS = [{
        'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
        'info_dict': {
            'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
            'title': 'Gjenopplev den historiske solformørkelsen',
            'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
        },
        'playlist_count': 2,
    }, {
        'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
        'info_dict': {
            'id': 'rivertonprisen-til-karin-fossum-1.12266449',
            'title': 'Rivertonprisen til Karin Fossum',
            'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
        },
        'playlist_count': 5,
    }]

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

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result('nrk:%s' % video_id, 'NRK')
            for video_id in re.findall(
                r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
                webpage)
        ]

        playlist_title = self._og_search_title(webpage)
        playlist_description = self._og_search_description(webpage)

        return self.playlist_result(
            entries, playlist_id, playlist_title, playlist_description)


class NRKSkoleIE(InfoExtractor):
    IE_DESC = 'NRK Skole'
    _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'

    _TESTS = [{
        'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
        'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
        'info_dict': {
            'id': '6021',
            'ext': 'mp4',
            'title': 'Genetikk og eneggede tvillinger',
            'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
            'duration': 399,
        },
    }, {
        'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
        'only_matching': True,
    }]

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

        webpage = self._download_webpage(
            'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
            video_id)

        nrk_id = self._parse_json(
            self._search_regex(
                r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
                webpage, 'application json'),
            video_id)['activeMedia']['psId']

        return self.url_result('nrk:%s' % nrk_id)