2 from __future__ import unicode_literals
7 from .common import InfoExtractor
8 from ..compat import compat_urllib_parse_unquote
17 class NRKBaseIE(InfoExtractor):
20 def _download_webpage(self, *args, **kwargs):
21 # NRK checks X-Forwarded-For HTTP header in order to figure out the
22 # origin of the client behind proxy. This allows to bypass geo
23 # restriction by faking this header's value to some Norway IP.
24 # We will do so once we encounter any geo restriction error.
26 kwargs.setdefault('headers', {})['X-Forwarded-For'] = self._faked_ip
27 return super(NRKBaseIE, self)._download_webpage(*args, **kwargs)
30 # Use fake IP from 37.191.128.0/17 in order to workaround geo
32 def octet(lb=0, ub=255):
33 return random.randint(lb, ub)
34 self._faked_ip = '37.191.%d.%d' % (octet(128), octet())
36 def _real_extract(self, url):
37 video_id = self._match_id(url)
39 data = self._download_json(
40 'http://%s/mediaelement/%s' % (self._API_HOST, video_id),
41 video_id, 'Downloading mediaelement JSON')
43 title = data.get('fullTitle') or data.get('mainTitle') or data['title']
44 video_id = data.get('id') or video_id
48 media_assets = data.get('mediaAssets')
49 if media_assets and isinstance(media_assets, list):
50 def video_id_and_title(idx):
51 return ((video_id, title) if len(media_assets) == 1
52 else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
53 for num, asset in enumerate(media_assets, 1):
54 asset_url = asset.get('url')
57 formats = self._extract_akamai_formats(asset_url, video_id)
60 self._sort_formats(formats)
61 entry_id, entry_title = video_id_and_title(num)
62 duration = parse_duration(asset.get('duration'))
64 for subtitle in ('webVtt', 'timedText'):
65 subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
67 subtitles.setdefault('no', []).append({
68 'url': compat_urllib_parse_unquote(subtitle_url)
71 'id': asset.get('carrierId') or entry_id,
74 'subtitles': subtitles,
79 media_url = data.get('mediaUrl')
81 formats = self._extract_akamai_formats(media_url, video_id)
82 self._sort_formats(formats)
83 duration = parse_duration(data.get('duration'))
92 message_type = data.get('messageType')
93 if message_type == 'ProgramIsGeoBlocked' and not self._faked_ip:
95 'Video is geo restricted, trying to fake IP')
97 return self._real_extract(url)
100 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
101 'ProgramRightsHasExpired': 'Programmet har gått ut',
102 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
104 raise ExtractorError(
105 '%s said: %s' % (self.IE_NAME, MESSAGES.get(
106 message_type, message_type)),
109 conviva = data.get('convivaStatistics') or {}
110 series = conviva.get('seriesName') or data.get('seriesTitle')
111 episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
114 images = data.get('images')
115 if images and isinstance(images, dict):
116 web_images = images.get('webImages')
117 if isinstance(web_images, list):
119 'url': image['imageUrl'],
120 'width': int_or_none(image.get('width')),
121 'height': int_or_none(image.get('height')),
122 } for image in web_images if image.get('imageUrl')]
124 description = data.get('description')
127 'description': description,
130 'age_limit': parse_age_limit(data.get('legalAge')),
131 'thumbnails': thumbnails,
134 vcodec = 'none' if data.get('mediaType') == 'Audio' else None
136 # TODO: extract chapters when https://github.com/rg3/youtube-dl/pull/9409 is merged
138 for entry in entries:
139 entry.update(common_info)
140 for f in entry['formats']:
143 return self.playlist_result(entries, video_id, title, description)
146 class NRKIE(NRKBaseIE):
147 _VALID_URL = r'''(?x)
152 (?:www\.)?nrk\.no/video/PS\*|
153 v8-psapi\.nrk\.no/mediaelement/
158 _API_HOST = 'v8.psapi.nrk.no'
161 'url': 'http://www.nrk.no/video/PS*150533',
162 'md5': '2f7f6eeb2aacdd99885f355428715cfa',
166 'title': 'Dompap og andre fugler i Piip-Show',
167 'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
172 'url': 'http://www.nrk.no/video/PS*154915',
177 'title': 'Slik høres internett ut når du er blind',
178 'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
182 'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
183 'only_matching': True,
185 'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
186 'only_matching': True,
190 class NRKTVIE(NRKBaseIE):
191 IE_DESC = 'NRK TV and NRK Radio'
192 _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+))?'
193 _API_HOST = 'psapi-we.nrk.no'
196 'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
197 'md5': '4e9ca6629f09e588ed240fb11619922a',
199 'id': 'MUHH48000314AA',
201 'title': '20 spørsmål 23.05.2014',
202 'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
206 'url': 'https://tv.nrk.no/program/mdfp15000514',
207 'md5': '43d0be26663d380603a9cf0c24366531',
209 'id': 'MDFP15000514CA',
211 'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
212 'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
216 # single playlist video
217 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
218 'md5': 'adbd1dbd813edaf532b0a253780719c2',
220 'id': 'MSPO40010515-part2',
222 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
223 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
225 'skip': 'Only works from Norway',
227 'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
229 'md5': '9480285eff92d64f06e02a5367970a7a',
231 'id': 'MSPO40010515-part1',
233 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 1:2)',
234 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
237 'md5': 'adbd1dbd813edaf532b0a253780719c2',
239 'id': 'MSPO40010515-part2',
241 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
242 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
246 'id': 'MSPO40010515',
247 'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn',
248 'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
251 'skip': 'Only works from Norway',
253 'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
254 'only_matching': True,
258 class NRKPlaylistIE(InfoExtractor):
259 _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
262 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
264 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
265 'title': 'Gjenopplev den historiske solformørkelsen',
266 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
270 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
272 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
273 'title': 'Rivertonprisen til Karin Fossum',
274 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
279 def _real_extract(self, url):
280 playlist_id = self._match_id(url)
282 webpage = self._download_webpage(url, playlist_id)
285 self.url_result('nrk:%s' % video_id, 'NRK')
286 for video_id in re.findall(
287 r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"',
291 playlist_title = self._og_search_title(webpage)
292 playlist_description = self._og_search_description(webpage)
294 return self.playlist_result(
295 entries, playlist_id, playlist_title, playlist_description)
298 class NRKSkoleIE(InfoExtractor):
299 IE_DESC = 'NRK Skole'
300 _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
303 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
304 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
308 'title': 'Genetikk og eneggede tvillinger',
309 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
313 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
314 'only_matching': True,
317 def _real_extract(self, url):
318 video_id = self._match_id(url)
320 webpage = self._download_webpage(
321 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
324 nrk_id = self._parse_json(
326 r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
327 webpage, 'application json'),
328 video_id)['activeMedia']['psId']
330 return self.url_result('nrk:%s' % nrk_id)