Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/nrk.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_urllib_parse_unquote
   8 from ..utils import (
   9     ExtractorError,
  10     int_or_none,
  11     parse_age_limit,
  12     parse_duration,
  13 )
  14
  15
  16 class NRKBaseIE(InfoExtractor):
  17     _GEO_COUNTRIES = ['NO']
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21
  22         data = self._download_json(
  23             'http://%s/mediaelement/%s' % (self._API_HOST, video_id),
  24             video_id, 'Downloading mediaelement JSON')
  25
  26         title = data.get('fullTitle') or data.get('mainTitle') or data['title']
  27         video_id = data.get('id') or video_id
  28
  29         entries = []
  30
  31         conviva = data.get('convivaStatistics') or {}
  32         live = (data.get('mediaElementType') == 'Live' or
  33                 data.get('isLive') is True or conviva.get('isLive'))
  34
  35         def make_title(t):
  36             return self._live_title(t) if live else t
  37
  38         media_assets = data.get('mediaAssets')
  39         if media_assets and isinstance(media_assets, list):
  40             def video_id_and_title(idx):
  41                 return ((video_id, title) if len(media_assets) == 1
  42                         else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))
  43             for num, asset in enumerate(media_assets, 1):
  44                 asset_url = asset.get('url')
  45                 if not asset_url:
  46                     continue
  47                 formats = self._extract_akamai_formats(asset_url, video_id)
  48                 if not formats:
  49                     continue
  50                 self._sort_formats(formats)
  51
  52                 # Some f4m streams may not work with hdcore in fragments' URLs
  53                 for f in formats:
  54                     extra_param = f.get('extra_param_to_segment_url')
  55                     if extra_param and 'hdcore' in extra_param:
  56                         del f['extra_param_to_segment_url']
  57
  58                 entry_id, entry_title = video_id_and_title(num)
  59                 duration = parse_duration(asset.get('duration'))
  60                 subtitles = {}
  61                 for subtitle in ('webVtt', 'timedText'):
  62                     subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)
  63                     if subtitle_url:
  64                         subtitles.setdefault('no', []).append({
  65                             'url': compat_urllib_parse_unquote(subtitle_url)
  66                         })
  67                 entries.append({
  68                     'id': asset.get('carrierId') or entry_id,
  69                     'title': make_title(entry_title),
  70                     'duration': duration,
  71                     'subtitles': subtitles,
  72                     'formats': formats,
  73                 })
  74
  75         if not entries:
  76             media_url = data.get('mediaUrl')
  77             if media_url:
  78                 formats = self._extract_akamai_formats(media_url, video_id)
  79                 self._sort_formats(formats)
  80                 duration = parse_duration(data.get('duration'))
  81                 entries = [{
  82                     'id': video_id,
  83                     'title': make_title(title),
  84                     'duration': duration,
  85                     'formats': formats,
  86                 }]
  87
  88         if not entries:
  89             MESSAGES = {
  90                 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',
  91                 'ProgramRightsHasExpired': 'Programmet har gått ut',
  92                 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',
  93             }
  94             message_type = data.get('messageType', '')
  95             # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*
  96             if 'IsGeoBlocked' in message_type:
  97                 self.raise_geo_restricted(
  98                     msg=MESSAGES.get('ProgramIsGeoBlocked'),
  99                     countries=self._GEO_COUNTRIES)
 100             raise ExtractorError(
 101                 '%s said: %s' % (self.IE_NAME, MESSAGES.get(
 102                     message_type, message_type)),
 103                 expected=True)
 104
 105         series = conviva.get('seriesName') or data.get('seriesTitle')
 106         episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')
 107
 108         season_number = None
 109         episode_number = None
 110         if data.get('mediaElementType') == 'Episode':
 111             _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \
 112                 data.get('relativeOriginUrl', '')
 113             EPISODENUM_RE = [
 114                 r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',
 115                 r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',
 116             ]
 117             season_number = int_or_none(self._search_regex(
 118                 EPISODENUM_RE, _season_episode, 'season number',
 119                 default=None, group='season'))
 120             episode_number = int_or_none(self._search_regex(
 121                 EPISODENUM_RE, _season_episode, 'episode number',
 122                 default=None, group='episode'))
 123
 124         thumbnails = None
 125         images = data.get('images')
 126         if images and isinstance(images, dict):
 127             web_images = images.get('webImages')
 128             if isinstance(web_images, list):
 129                 thumbnails = [{
 130                     'url': image['imageUrl'],
 131                     'width': int_or_none(image.get('width')),
 132                     'height': int_or_none(image.get('height')),
 133                 } for image in web_images if image.get('imageUrl')]
 134
 135         description = data.get('description')
 136         category = data.get('mediaAnalytics', {}).get('category')
 137
 138         common_info = {
 139             'description': description,
 140             'series': series,
 141             'episode': episode,
 142             'season_number': season_number,
 143             'episode_number': episode_number,
 144             'categories': [category] if category else None,
 145             'age_limit': parse_age_limit(data.get('legalAge')),
 146             'thumbnails': thumbnails,
 147         }
 148
 149         vcodec = 'none' if data.get('mediaType') == 'Audio' else None
 150
 151         for entry in entries:
 152             entry.update(common_info)
 153             for f in entry['formats']:
 154                 f['vcodec'] = vcodec
 155
 156         points = data.get('shortIndexPoints')
 157         if isinstance(points, list):
 158             chapters = []
 159             for next_num, point in enumerate(points, start=1):
 160                 if not isinstance(point, dict):
 161                     continue
 162                 start_time = parse_duration(point.get('startPoint'))
 163                 if start_time is None:
 164                     continue
 165                 end_time = parse_duration(
 166                     data.get('duration')
 167                     if next_num == len(points)
 168                     else points[next_num].get('startPoint'))
 169                 if end_time is None:
 170                     continue
 171                 chapters.append({
 172                     'start_time': start_time,
 173                     'end_time': end_time,
 174                     'title': point.get('title'),
 175                 })
 176             if chapters and len(entries) == 1:
 177                 entries[0]['chapters'] = chapters
 178
 179         return self.playlist_result(entries, video_id, title, description)
 180
 181
 182 class NRKIE(NRKBaseIE):
 183     _VALID_URL = r'''(?x)
 184                         (?:
 185                             nrk:|
 186                             https?://
 187                                 (?:
 188                                     (?:www\.)?nrk\.no/video/PS\*|
 189                                     v8[-.]psapi\.nrk\.no/mediaelement/
 190                                 )
 191                             )
 192                             (?P<id>[^?#&]+)
 193                         '''
 194     _API_HOST = 'v8-psapi.nrk.no'
 195     _TESTS = [{
 196         # video
 197         'url': 'http://www.nrk.no/video/PS*150533',
 198         'md5': '2f7f6eeb2aacdd99885f355428715cfa',
 199         'info_dict': {
 200             'id': '150533',
 201             'ext': 'mp4',
 202             'title': 'Dompap og andre fugler i Piip-Show',
 203             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',
 204             'duration': 263,
 205         }
 206     }, {
 207         # audio
 208         'url': 'http://www.nrk.no/video/PS*154915',
 209         # MD5 is unstable
 210         'info_dict': {
 211             'id': '154915',
 212             'ext': 'flv',
 213             'title': 'Slik høres internett ut når du er blind',
 214             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',
 215             'duration': 20,
 216         }
 217     }, {
 218         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 219         'only_matching': True,
 220     }, {
 221         'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',
 222         'only_matching': True,
 223     }, {
 224         'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',
 225         'only_matching': True,
 226     }]
 227
 228
 229 class NRKTVIE(NRKBaseIE):
 230     IE_DESC = 'NRK TV and NRK Radio'
 231     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'
 232     _VALID_URL = r'''(?x)
 233                         https?://
 234                             (?:tv|radio)\.nrk(?:super)?\.no/
 235                             (?:serie/[^/]+|program)/
 236                             (?![Ee]pisodes)%s
 237                             (?:/\d{2}-\d{2}-\d{4})?
 238                             (?:\#del=(?P<part_id>\d+))?
 239                     ''' % _EPISODE_RE
 240     _API_HOST = 'psapi-we.nrk.no'
 241
 242     _TESTS = [{
 243         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',
 244         'md5': '4e9ca6629f09e588ed240fb11619922a',
 245         'info_dict': {
 246             'id': 'MUHH48000314AA',
 247             'ext': 'mp4',
 248             'title': '20 spørsmål 23.05.2014',
 249             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',
 250             'duration': 1741,
 251             'series': '20 spørsmål - TV',
 252             'episode': '23.05.2014',
 253         },
 254     }, {
 255         'url': 'https://tv.nrk.no/program/mdfp15000514',
 256         'info_dict': {
 257             'id': 'MDFP15000514CA',
 258             'ext': 'mp4',
 259             'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',
 260             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',
 261             'duration': 4605,
 262             'series': 'Kunnskapskanalen',
 263             'episode': '24.05.2014',
 264         },
 265         'params': {
 266             'skip_download': True,
 267         },
 268     }, {
 269         # single playlist video
 270         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',
 271         'info_dict': {
 272             'id': 'MSPO40010515-part2',
 273             'ext': 'flv',
 274             'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',
 275             'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',
 276         },
 277         'params': {
 278             'skip_download': True,
 279         },
 280         'expected_warnings': ['Video is geo restricted'],
 281         'skip': 'particular part is not supported currently',
 282     }, {
 283         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',
 284         'playlist': [{
 285             'info_dict': {
 286                 'id': 'MSPO40010515AH',
 287                 'ext': 'mp4',
 288                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',
 289                 'description': 'md5:c03aba1e917561eface5214020551b7a',
 290                 'duration': 772,
 291                 'series': 'Tour de Ski',
 292                 'episode': '06.01.2015',
 293             },
 294             'params': {
 295                 'skip_download': True,
 296             },
 297         }, {
 298             'info_dict': {
 299                 'id': 'MSPO40010515BH',
 300                 'ext': 'mp4',
 301                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',
 302                 'description': 'md5:c03aba1e917561eface5214020551b7a',
 303                 'duration': 6175,
 304                 'series': 'Tour de Ski',
 305                 'episode': '06.01.2015',
 306             },
 307             'params': {
 308                 'skip_download': True,
 309             },
 310         }],
 311         'info_dict': {
 312             'id': 'MSPO40010515',
 313             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',
 314             'description': 'md5:c03aba1e917561eface5214020551b7a',
 315         },
 316         'expected_warnings': ['Video is geo restricted'],
 317     }, {
 318         'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',
 319         'info_dict': {
 320             'id': 'KMTE50001317AA',
 321             'ext': 'mp4',
 322             'title': 'Anno 13:30',
 323             'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',
 324             'duration': 2340,
 325             'series': 'Anno',
 326             'episode': '13:30',
 327             'season_number': 3,
 328             'episode_number': 13,
 329         },
 330         'params': {
 331             'skip_download': True,
 332         },
 333     }, {
 334         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',
 335         'info_dict': {
 336             'id': 'MUHH46000317AA',
 337             'ext': 'mp4',
 338             'title': 'Nytt på Nytt 27.01.2017',
 339             'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',
 340             'duration': 1796,
 341             'series': 'Nytt på nytt',
 342             'episode': '27.01.2017',
 343         },
 344         'params': {
 345             'skip_download': True,
 346         },
 347     }, {
 348         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',
 349         'only_matching': True,
 350     }]
 351
 352
 353 class NRKTVDirekteIE(NRKTVIE):
 354     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'
 355     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'
 356
 357     _TESTS = [{
 358         'url': 'https://tv.nrk.no/direkte/nrk1',
 359         'only_matching': True,
 360     }, {
 361         'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',
 362         'only_matching': True,
 363     }]
 364
 365
 366 class NRKPlaylistBaseIE(InfoExtractor):
 367     def _extract_description(self, webpage):
 368         pass
 369
 370     def _real_extract(self, url):
 371         playlist_id = self._match_id(url)
 372
 373         webpage = self._download_webpage(url, playlist_id)
 374
 375         entries = [
 376             self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
 377             for video_id in re.findall(self._ITEM_RE, webpage)
 378         ]
 379
 380         playlist_title = self. _extract_title(webpage)
 381         playlist_description = self._extract_description(webpage)
 382
 383         return self.playlist_result(
 384             entries, playlist_id, playlist_title, playlist_description)
 385
 386
 387 class NRKPlaylistIE(NRKPlaylistBaseIE):
 388     _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
 389     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
 390     _TESTS = [{
 391         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
 392         'info_dict': {
 393             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
 394             'title': 'Gjenopplev den historiske solformørkelsen',
 395             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
 396         },
 397         'playlist_count': 2,
 398     }, {
 399         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
 400         'info_dict': {
 401             'id': 'rivertonprisen-til-karin-fossum-1.12266449',
 402             'title': 'Rivertonprisen til Karin Fossum',
 403             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
 404         },
 405         'playlist_count': 5,
 406     }]
 407
 408     def _extract_title(self, webpage):
 409         return self._og_search_title(webpage, fatal=False)
 410
 411     def _extract_description(self, webpage):
 412         return self._og_search_description(webpage)
 413
 414
 415 class NRKTVEpisodesIE(NRKPlaylistBaseIE):
 416     _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
 417     _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
 418     _TESTS = [{
 419         'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
 420         'info_dict': {
 421             'id': '69031',
 422             'title': 'Nytt på nytt, sesong: 201210',
 423         },
 424         'playlist_count': 4,
 425     }]
 426
 427     def _extract_title(self, webpage):
 428         return self._html_search_regex(
 429             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
 430
 431
 432 class NRKTVSeriesIE(InfoExtractor):
 433     _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
 434     _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
 435     _TESTS = [{
 436         'url': 'https://tv.nrk.no/serie/groenn-glede',
 437         'info_dict': {
 438             'id': 'groenn-glede',
 439             'title': 'Grønn glede',
 440             'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
 441         },
 442         'playlist_mincount': 9,
 443     }, {
 444         'url': 'http://tv.nrksuper.no/serie/labyrint',
 445         'info_dict': {
 446             'id': 'labyrint',
 447             'title': 'Labyrint',
 448             'description': 'md5:58afd450974c89e27d5a19212eee7115',
 449         },
 450         'playlist_mincount': 3,
 451     }, {
 452         'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
 453         'only_matching': True,
 454     }, {
 455         'url': 'https://tv.nrk.no/serie/saving-the-human-race',
 456         'only_matching': True,
 457     }, {
 458         'url': 'https://tv.nrk.no/serie/postmann-pat',
 459         'only_matching': True,
 460     }]
 461
 462     @classmethod
 463     def suitable(cls, url):
 464         return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url)
 465
 466     def _real_extract(self, url):
 467         series_id = self._match_id(url)
 468
 469         webpage = self._download_webpage(url, series_id)
 470
 471         entries = [
 472             self.url_result(
 473                 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
 474                     series=series_id, season=season_id))
 475             for season_id in re.findall(self._ITEM_RE, webpage)
 476         ]
 477
 478         title = self._html_search_meta(
 479             'seriestitle', webpage,
 480             'title', default=None) or self._og_search_title(
 481             webpage, fatal=False)
 482
 483         description = self._html_search_meta(
 484             'series_description', webpage,
 485             'description', default=None) or self._og_search_description(webpage)
 486
 487         return self.playlist_result(entries, series_id, title, description)
 488
 489
 490 class NRKSkoleIE(InfoExtractor):
 491     IE_DESC = 'NRK Skole'
 492     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
 493
 494     _TESTS = [{
 495         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
 496         'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
 497         'info_dict': {
 498             'id': '6021',
 499             'ext': 'mp4',
 500             'title': 'Genetikk og eneggede tvillinger',
 501             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
 502             'duration': 399,
 503         },
 504     }, {
 505         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
 506         'only_matching': True,
 507     }]
 508
 509     def _real_extract(self, url):
 510         video_id = self._match_id(url)
 511
 512         webpage = self._download_webpage(
 513             'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
 514             video_id)
 515
 516         nrk_id = self._parse_json(
 517             self._search_regex(
 518                 r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
 519                 webpage, 'application json'),
 520             video_id)['activeMedia']['psId']
 521
 522         return self.url_result('nrk:%s' % nrk_id)