ytdl-org
/
youtube-dl
1
0
Форкнуть 0
Код Задачи 0 Pull Request'ы 0 Релизы 1077 Вики Активность
Вы не можете выбрать более 25 тем Темы должны начинаться с буквы или цифры, могут содержать дефисы(-) и должны содержать не более 35 символов.
17039 коммитов
9 Ветки
53MB
Дерево: 3089bc748c
Ветки Теги
${ item.name }
Создать ветку ${ searchTerm }
из '3089bc748c'
${ noResults }
youtube-dl/youtube_dl/extractor/nrk.py

678 строки
24KB
Исходник Blame История 

  1. # coding: utf-8

  2. from __future__ import unicode_literals

  3. 

  4. import re

  5. 

  6. from .common import InfoExtractor

  7. from ..compat import (

  8.     compat_str,

  9.     compat_urllib_parse_unquote,

  10. )

  11. from ..utils import (

  12.     ExtractorError,

  13.     int_or_none,

  14.     JSON_LD_RE,

  15.     NO_DEFAULT,

  16.     parse_age_limit,

  17.     parse_duration,

  18.     try_get,

  19. )

  20. 

  21. 

  22. class NRKBaseIE(InfoExtractor):

  23.     _GEO_COUNTRIES = ['NO']

  24. 

  25.     _api_host = None

  26. 

  27.     def _real_extract(self, url):

  28.         video_id = self._match_id(url)

  29. 

  30.         api_hosts = (self._api_host, ) if self._api_host else self._API_HOSTS

  31. 

  32.         for api_host in api_hosts:

  33.             data = self._download_json(

  34.                 'http://%s/mediaelement/%s' % (api_host, video_id),

  35.                 video_id, 'Downloading mediaelement JSON',

  36.                 fatal=api_host == api_hosts[-1])

  37.             if not data:

  38.                 continue

  39.             self._api_host = api_host

  40.             break

  41. 

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

  43.         video_id = data.get('id') or video_id

  44. 

  45.         entries = []

  46. 

  47.         conviva = data.get('convivaStatistics') or {}

  48.         live = (data.get('mediaElementType') == 'Live'

  49.                 or data.get('isLive') is True or conviva.get('isLive'))

  50. 

  51.         def make_title(t):

  52.             return self._live_title(t) if live else t

  53. 

  54.         media_assets = data.get('mediaAssets')

  55.         if media_assets and isinstance(media_assets, list):

  56.             def video_id_and_title(idx):

  57.                 return ((video_id, title) if len(media_assets) == 1

  58.                         else ('%s-%d' % (video_id, idx), '%s (Part %d)' % (title, idx)))

  59.             for num, asset in enumerate(media_assets, 1):

  60.                 asset_url = asset.get('url')

  61.                 if not asset_url:

  62.                     continue

  63.                 formats = self._extract_akamai_formats(asset_url, video_id)

  64.                 if not formats:

  65.                     continue

  66.                 self._sort_formats(formats)

  67. 

  68.                 # Some f4m streams may not work with hdcore in fragments' URLs

  69.                 for f in formats:

  70.                     extra_param = f.get('extra_param_to_segment_url')

  71.                     if extra_param and 'hdcore' in extra_param:

  72.                         del f['extra_param_to_segment_url']

  73. 

  74.                 entry_id, entry_title = video_id_and_title(num)

  75.                 duration = parse_duration(asset.get('duration'))

  76.                 subtitles = {}

  77.                 for subtitle in ('webVtt', 'timedText'):

  78.                     subtitle_url = asset.get('%sSubtitlesUrl' % subtitle)

  79.                     if subtitle_url:

  80.                         subtitles.setdefault('no', []).append({

  81.                             'url': compat_urllib_parse_unquote(subtitle_url)

  82.                         })

  83.                 entries.append({

  84.                     'id': asset.get('carrierId') or entry_id,

  85.                     'title': make_title(entry_title),

  86.                     'duration': duration,

  87.                     'subtitles': subtitles,

  88.                     'formats': formats,

  89.                 })

  90. 

  91.         if not entries:

  92.             media_url = data.get('mediaUrl')

  93.             if media_url:

  94.                 formats = self._extract_akamai_formats(media_url, video_id)

  95.                 self._sort_formats(formats)

  96.                 duration = parse_duration(data.get('duration'))

  97.                 entries = [{

  98.                     'id': video_id,

  99.                     'title': make_title(title),

  100.                     'duration': duration,

  101.                     'formats': formats,

  102.                 }]

  103. 

  104.         if not entries:

  105.             MESSAGES = {

  106.                 'ProgramRightsAreNotReady': 'Du kan dessverre ikke se eller høre programmet',

  107.                 'ProgramRightsHasExpired': 'Programmet har gått ut',

  108.                 'ProgramIsGeoBlocked': 'NRK har ikke rettigheter til å vise dette programmet utenfor Norge',

  109.             }

  110.             message_type = data.get('messageType', '')

  111.             # Can be ProgramIsGeoBlocked or ChannelIsGeoBlocked*

  112.             if 'IsGeoBlocked' in message_type:

  113.                 self.raise_geo_restricted(

  114.                     msg=MESSAGES.get('ProgramIsGeoBlocked'),

  115.                     countries=self._GEO_COUNTRIES)

  116.             raise ExtractorError(

  117.                 '%s said: %s' % (self.IE_NAME, MESSAGES.get(

  118.                     message_type, message_type)),

  119.                 expected=True)

  120. 

  121.         series = conviva.get('seriesName') or data.get('seriesTitle')

  122.         episode = conviva.get('episodeName') or data.get('episodeNumberOrDate')

  123. 

  124.         season_number = None

  125.         episode_number = None

  126.         if data.get('mediaElementType') == 'Episode':

  127.             _season_episode = data.get('scoresStatistics', {}).get('springStreamStream') or \

  128.                 data.get('relativeOriginUrl', '')

  129.             EPISODENUM_RE = [

  130.                 r'/s(?P<season>\d{,2})e(?P<episode>\d{,2})\.',

  131.                 r'/sesong-(?P<season>\d{,2})/episode-(?P<episode>\d{,2})',

  132.             ]

  133.             season_number = int_or_none(self._search_regex(

  134.                 EPISODENUM_RE, _season_episode, 'season number',

  135.                 default=None, group='season'))

  136.             episode_number = int_or_none(self._search_regex(

  137.                 EPISODENUM_RE, _season_episode, 'episode number',

  138.                 default=None, group='episode'))

  139. 

  140.         thumbnails = None

  141.         images = data.get('images')

  142.         if images and isinstance(images, dict):

  143.             web_images = images.get('webImages')

  144.             if isinstance(web_images, list):

  145.                 thumbnails = [{

  146.                     'url': image['imageUrl'],

  147.                     'width': int_or_none(image.get('width')),

  148.                     'height': int_or_none(image.get('height')),

  149.                 } for image in web_images if image.get('imageUrl')]

  150. 

  151.         description = data.get('description')

  152.         category = data.get('mediaAnalytics', {}).get('category')

  153. 

  154.         common_info = {

  155.             'description': description,

  156.             'series': series,

  157.             'episode': episode,

  158.             'season_number': season_number,

  159.             'episode_number': episode_number,

  160.             'categories': [category] if category else None,

  161.             'age_limit': parse_age_limit(data.get('legalAge')),

  162.             'thumbnails': thumbnails,

  163.         }

  164. 

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

  166. 

  167.         for entry in entries:

  168.             entry.update(common_info)

  169.             for f in entry['formats']:

  170.                 f['vcodec'] = vcodec

  171. 

  172.         points = data.get('shortIndexPoints')

  173.         if isinstance(points, list):

  174.             chapters = []

  175.             for next_num, point in enumerate(points, start=1):

  176.                 if not isinstance(point, dict):

  177.                     continue

  178.                 start_time = parse_duration(point.get('startPoint'))

  179.                 if start_time is None:

  180.                     continue

  181.                 end_time = parse_duration(

  182.                     data.get('duration')

  183.                     if next_num == len(points)

  184.                     else points[next_num].get('startPoint'))

  185.                 if end_time is None:

  186.                     continue

  187.                 chapters.append({

  188.                     'start_time': start_time,

  189.                     'end_time': end_time,

  190.                     'title': point.get('title'),

  191.                 })

  192.             if chapters and len(entries) == 1:

  193.                 entries[0]['chapters'] = chapters

  194. 

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

  196. 

  197. 

  198. class NRKIE(NRKBaseIE):

  199.     _VALID_URL = r'''(?x)

  200.                         (?:

  201.                             nrk:|

  202.                             https?://

  203.                                 (?:

  204.                                     (?:www\.)?nrk\.no/video/PS\*|

  205.                                     v8[-.]psapi\.nrk\.no/mediaelement/

  206.                                 )

  207.                             )

  208.                             (?P<id>[^?#&]+)

  209.                         '''

  210.     _API_HOSTS = ('psapi.nrk.no', 'v8-psapi.nrk.no')

  211.     _TESTS = [{

  212.         # video

  213.         'url': 'http://www.nrk.no/video/PS*150533',

  214.         'md5': '706f34cdf1322577589e369e522b50ef',

  215.         'info_dict': {

  216.             'id': '150533',

  217.             'ext': 'mp4',

  218.             'title': 'Dompap og andre fugler i Piip-Show',

  219.             'description': 'md5:d9261ba34c43b61c812cb6b0269a5c8f',

  220.             'duration': 262,

  221.         }

  222.     }, {

  223.         # audio

  224.         'url': 'http://www.nrk.no/video/PS*154915',

  225.         # MD5 is unstable

  226.         'info_dict': {

  227.             'id': '154915',

  228.             'ext': 'flv',

  229.             'title': 'Slik høres internett ut når du er blind',

  230.             'description': 'md5:a621f5cc1bd75c8d5104cb048c6b8568',

  231.             'duration': 20,

  232.         }

  233.     }, {

  234.         'url': 'nrk:ecc1b952-96dc-4a98-81b9-5296dc7a98d9',

  235.         'only_matching': True,

  236.     }, {

  237.         'url': 'nrk:clip/7707d5a3-ebe7-434a-87d5-a3ebe7a34a70',

  238.         'only_matching': True,

  239.     }, {

  240.         'url': 'https://v8-psapi.nrk.no/mediaelement/ecc1b952-96dc-4a98-81b9-5296dc7a98d9',

  241.         'only_matching': True,

  242.     }]

  243. 

  244. 

  245. class NRKTVIE(NRKBaseIE):

  246.     IE_DESC = 'NRK TV and NRK Radio'

  247.     _EPISODE_RE = r'(?P<id>[a-zA-Z]{4}\d{8})'

  248.     _VALID_URL = r'''(?x)

  249.                         https?://

  250.                             (?:tv|radio)\.nrk(?:super)?\.no/

  251.                             (?:serie(?:/[^/]+){1,2}|program)/

  252.                             (?![Ee]pisodes)%s

  253.                             (?:/\d{2}-\d{2}-\d{4})?

  254.                             (?:\#del=(?P<part_id>\d+))?

  255.                     ''' % _EPISODE_RE

  256.     _API_HOSTS = ('psapi-ne.nrk.no', 'psapi-we.nrk.no')

  257.     _TESTS = [{

  258.         'url': 'https://tv.nrk.no/serie/20-spoersmaal-tv/MUHH48000314/23-05-2014',

  259.         'md5': '9a167e54d04671eb6317a37b7bc8a280',

  260.         'info_dict': {

  261.             'id': 'MUHH48000314AA',

  262.             'ext': 'mp4',

  263.             'title': '20 spørsmål 23.05.2014',

  264.             'description': 'md5:bdea103bc35494c143c6a9acdd84887a',

  265.             'duration': 1741,

  266.             'series': '20 spørsmål',

  267.             'episode': '23.05.2014',

  268.         },

  269.     }, {

  270.         'url': 'https://tv.nrk.no/program/mdfp15000514',

  271.         'info_dict': {

  272.             'id': 'MDFP15000514CA',

  273.             'ext': 'mp4',

  274.             'title': 'Grunnlovsjubiléet - Stor ståhei for ingenting 24.05.2014',

  275.             'description': 'md5:89290c5ccde1b3a24bb8050ab67fe1db',

  276.             'duration': 4605,

  277.             'series': 'Kunnskapskanalen',

  278.             'episode': '24.05.2014',

  279.         },

  280.         'params': {

  281.             'skip_download': True,

  282.         },

  283.     }, {

  284.         # single playlist video

  285.         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015#del=2',

  286.         'info_dict': {

  287.             'id': 'MSPO40010515-part2',

  288.             'ext': 'flv',

  289.             'title': 'Tour de Ski: Sprint fri teknikk, kvinner og menn 06.01.2015 (del 2:2)',

  290.             'description': 'md5:238b67b97a4ac7d7b4bf0edf8cc57d26',

  291.         },

  292.         'params': {

  293.             'skip_download': True,

  294.         },

  295.         'expected_warnings': ['Video is geo restricted'],

  296.         'skip': 'particular part is not supported currently',

  297.     }, {

  298.         'url': 'https://tv.nrk.no/serie/tour-de-ski/MSPO40010515/06-01-2015',

  299.         'playlist': [{

  300.             'info_dict': {

  301.                 'id': 'MSPO40010515AH',

  302.                 'ext': 'mp4',

  303.                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 1)',

  304.                 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',

  305.                 'duration': 772,

  306.                 'series': 'Tour de Ski',

  307.                 'episode': '06.01.2015',

  308.             },

  309.             'params': {

  310.                 'skip_download': True,

  311.             },

  312.         }, {

  313.             'info_dict': {

  314.                 'id': 'MSPO40010515BH',

  315.                 'ext': 'mp4',

  316.                 'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015 (Part 2)',

  317.                 'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',

  318.                 'duration': 6175,

  319.                 'series': 'Tour de Ski',

  320.                 'episode': '06.01.2015',

  321.             },

  322.             'params': {

  323.                 'skip_download': True,

  324.             },

  325.         }],

  326.         'info_dict': {

  327.             'id': 'MSPO40010515',

  328.             'title': 'Sprint fri teknikk, kvinner og menn 06.01.2015',

  329.             'description': 'md5:1f97a41f05a9486ee00c56f35f82993d',

  330.         },

  331.         'expected_warnings': ['Video is geo restricted'],

  332.     }, {

  333.         'url': 'https://tv.nrk.no/serie/anno/KMTE50001317/sesong-3/episode-13',

  334.         'info_dict': {

  335.             'id': 'KMTE50001317AA',

  336.             'ext': 'mp4',

  337.             'title': 'Anno 13:30',

  338.             'description': 'md5:11d9613661a8dbe6f9bef54e3a4cbbfa',

  339.             'duration': 2340,

  340.             'series': 'Anno',

  341.             'episode': '13:30',

  342.             'season_number': 3,

  343.             'episode_number': 13,

  344.         },

  345.         'params': {

  346.             'skip_download': True,

  347.         },

  348.     }, {

  349.         'url': 'https://tv.nrk.no/serie/nytt-paa-nytt/MUHH46000317/27-01-2017',

  350.         'info_dict': {

  351.             'id': 'MUHH46000317AA',

  352.             'ext': 'mp4',

  353.             'title': 'Nytt på Nytt 27.01.2017',

  354.             'description': 'md5:5358d6388fba0ea6f0b6d11c48b9eb4b',

  355.             'duration': 1796,

  356.             'series': 'Nytt på nytt',

  357.             'episode': '27.01.2017',

  358.         },

  359.         'params': {

  360.             'skip_download': True,

  361.         },

  362.     }, {

  363.         'url': 'https://radio.nrk.no/serie/dagsnytt/NPUB21019315/12-07-2015#',

  364.         'only_matching': True,

  365.     }, {

  366.         'url': 'https://tv.nrk.no/serie/lindmo/2018/MUHU11006318/avspiller',

  367.         'only_matching': True,

  368.     }]

  369. 

  370. 

  371. class NRKTVEpisodeIE(InfoExtractor):

  372.     _VALID_URL = r'https?://tv\.nrk\.no/serie/(?P<id>[^/]+/sesong/\d+/episode/\d+)'

  373.     _TEST = {

  374.         'url': 'https://tv.nrk.no/serie/backstage/sesong/1/episode/8',

  375.         'info_dict': {

  376.             'id': 'MSUI14000816AA',

  377.             'ext': 'mp4',

  378.             'title': 'Backstage 8:30',

  379.             'description': 'md5:de6ca5d5a2d56849e4021f2bf2850df4',

  380.             'duration': 1320,

  381.             'series': 'Backstage',

  382.             'season_number': 1,

  383.             'episode_number': 8,

  384.             'episode': '8:30',

  385.         },

  386.         'params': {

  387.             'skip_download': True,

  388.         },

  389.     }

  390. 

  391.     def _real_extract(self, url):

  392.         display_id = self._match_id(url)

  393. 

  394.         webpage = self._download_webpage(url, display_id)

  395. 

  396.         nrk_id = self._parse_json(

  397.             self._search_regex(JSON_LD_RE, webpage, 'JSON-LD', group='json_ld'),

  398.             display_id)['@id']

  399. 

  400.         assert re.match(NRKTVIE._EPISODE_RE, nrk_id)

  401.         return self.url_result(

  402.             'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id)

  403. 

  404. 

  405. class NRKTVSerieBaseIE(InfoExtractor):

  406.     def _extract_series(self, webpage, display_id, fatal=True):

  407.         config = self._parse_json(

  408.             self._search_regex(

  409.                 (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;',

  410.                  r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),

  411.                 webpage, 'config', default='{}' if not fatal else NO_DEFAULT),

  412.             display_id, fatal=False)

  413.         if not config:

  414.             return

  415.         return try_get(

  416.             config,

  417.             (lambda x: x['initialState']['series'], lambda x: x['series']),

  418.             dict)

  419. 

  420.     def _extract_seasons(self, seasons):

  421.         if not isinstance(seasons, list):

  422.             return []

  423.         entries = []

  424.         for season in seasons:

  425.             entries.extend(self._extract_episodes(season))

  426.         return entries

  427. 

  428.     def _extract_episodes(self, season):

  429.         if not isinstance(season, dict):

  430.             return []

  431.         return self._extract_entries(season.get('episodes'))

  432. 

  433.     def _extract_entries(self, entry_list):

  434.         if not isinstance(entry_list, list):

  435.             return []

  436.         entries = []

  437.         for episode in entry_list:

  438.             nrk_id = episode.get('prfId')

  439.             if not nrk_id or not isinstance(nrk_id, compat_str):

  440.                 continue

  441.             entries.append(self.url_result(

  442.                 'nrk:%s' % nrk_id, ie=NRKIE.ie_key(), video_id=nrk_id))

  443.         return entries

  444. 

  445. 

  446. class NRKTVSeasonIE(NRKTVSerieBaseIE):

  447.     _VALID_URL = r'https?://tv\.nrk\.no/serie/[^/]+/sesong/(?P<id>\d+)'

  448.     _TEST = {

  449.         'url': 'https://tv.nrk.no/serie/backstage/sesong/1',

  450.         'info_dict': {

  451.             'id': '1',

  452.             'title': 'Sesong 1',

  453.         },

  454.         'playlist_mincount': 30,

  455.     }

  456. 

  457.     @classmethod

  458.     def suitable(cls, url):

  459.         return (False if NRKTVIE.suitable(url) or NRKTVEpisodeIE.suitable(url)

  460.                 else super(NRKTVSeasonIE, cls).suitable(url))

  461. 

  462.     def _real_extract(self, url):

  463.         display_id = self._match_id(url)

  464. 

  465.         webpage = self._download_webpage(url, display_id)

  466. 

  467.         series = self._extract_series(webpage, display_id)

  468. 

  469.         season = next(

  470.             s for s in series['seasons']

  471.             if int(display_id) == s.get('seasonNumber'))

  472. 

  473.         title = try_get(season, lambda x: x['titles']['title'], compat_str)

  474.         return self.playlist_result(

  475.             self._extract_episodes(season), display_id, title)

  476. 

  477. 

  478. class NRKTVSeriesIE(NRKTVSerieBaseIE):

  479.     _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'

  480.     _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'

  481.     _TESTS = [{

  482.         # new layout, seasons

  483.         'url': 'https://tv.nrk.no/serie/backstage',

  484.         'info_dict': {

  485.             'id': 'backstage',

  486.             'title': 'Backstage',

  487.             'description': 'md5:c3ec3a35736fca0f9e1207b5511143d3',

  488.         },

  489.         'playlist_mincount': 60,

  490.     }, {

  491.         # new layout, instalments

  492.         'url': 'https://tv.nrk.no/serie/groenn-glede',

  493.         'info_dict': {

  494.             'id': 'groenn-glede',

  495.             'title': 'Grønn glede',

  496.             'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',

  497.         },

  498.         'playlist_mincount': 10,

  499.     }, {

  500.         # old layout

  501.         'url': 'https://tv.nrksuper.no/serie/labyrint',

  502.         'info_dict': {

  503.             'id': 'labyrint',

  504.             'title': 'Labyrint',

  505.             'description': 'md5:318b597330fdac5959247c9b69fdb1ec',

  506.         },

  507.         'playlist_mincount': 3,

  508.     }, {

  509.         'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',

  510.         'only_matching': True,

  511.     }, {

  512.         'url': 'https://tv.nrk.no/serie/saving-the-human-race',

  513.         'only_matching': True,

  514.     }, {

  515.         'url': 'https://tv.nrk.no/serie/postmann-pat',

  516.         'only_matching': True,

  517.     }]

  518. 

  519.     @classmethod

  520.     def suitable(cls, url):

  521.         return (

  522.             False if any(ie.suitable(url)

  523.                          for ie in (NRKTVIE, NRKTVEpisodeIE, NRKTVSeasonIE))

  524.             else super(NRKTVSeriesIE, cls).suitable(url))

  525. 

  526.     def _real_extract(self, url):

  527.         series_id = self._match_id(url)

  528. 

  529.         webpage = self._download_webpage(url, series_id)

  530. 

  531.         # New layout (e.g. https://tv.nrk.no/serie/backstage)

  532.         series = self._extract_series(webpage, series_id, fatal=False)

  533.         if series:

  534.             title = try_get(series, lambda x: x['titles']['title'], compat_str)

  535.             description = try_get(

  536.                 series, lambda x: x['titles']['subtitle'], compat_str)

  537.             entries = []

  538.             entries.extend(self._extract_seasons(series.get('seasons')))

  539.             entries.extend(self._extract_entries(series.get('instalments')))

  540.             entries.extend(self._extract_episodes(series.get('extraMaterial')))

  541.             return self.playlist_result(entries, series_id, title, description)

  542. 

  543.         # Old layout (e.g. https://tv.nrksuper.no/serie/labyrint)

  544.         entries = [

  545.             self.url_result(

  546.                 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(

  547.                     series=series_id, season=season_id))

  548.             for season_id in re.findall(self._ITEM_RE, webpage)

  549.         ]

  550. 

  551.         title = self._html_search_meta(

  552.             'seriestitle', webpage,

  553.             'title', default=None) or self._og_search_title(

  554.             webpage, fatal=False)

  555.         if title:

  556.             title = self._search_regex(

  557.                 r'NRK (?:Super )?TV\s*[-–]\s*(.+)', title, 'title', default=title)

  558. 

  559.         description = self._html_search_meta(

  560.             'series_description', webpage,

  561.             'description', default=None) or self._og_search_description(webpage)

  562. 

  563.         return self.playlist_result(entries, series_id, title, description)

  564. 

  565. 

  566. class NRKTVDirekteIE(NRKTVIE):

  567.     IE_DESC = 'NRK TV Direkte and NRK Radio Direkte'

  568.     _VALID_URL = r'https?://(?:tv|radio)\.nrk\.no/direkte/(?P<id>[^/?#&]+)'

  569. 

  570.     _TESTS = [{

  571.         'url': 'https://tv.nrk.no/direkte/nrk1',

  572.         'only_matching': True,

  573.     }, {

  574.         'url': 'https://radio.nrk.no/direkte/p1_oslo_akershus',

  575.         'only_matching': True,

  576.     }]

  577. 

  578. 

  579. class NRKPlaylistBaseIE(InfoExtractor):

  580.     def _extract_description(self, webpage):

  581.         pass

  582. 

  583.     def _real_extract(self, url):

  584.         playlist_id = self._match_id(url)

  585. 

  586.         webpage = self._download_webpage(url, playlist_id)

  587. 

  588.         entries = [

  589.             self.url_result('nrk:%s' % video_id, NRKIE.ie_key())

  590.             for video_id in re.findall(self._ITEM_RE, webpage)

  591.         ]

  592. 

  593.         playlist_title = self. _extract_title(webpage)

  594.         playlist_description = self._extract_description(webpage)

  595. 

  596.         return self.playlist_result(

  597.             entries, playlist_id, playlist_title, playlist_description)

  598. 

  599. 

  600. class NRKPlaylistIE(NRKPlaylistBaseIE):

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

  602.     _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'

  603.     _TESTS = [{

  604.         'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',

  605.         'info_dict': {

  606.             'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',

  607.             'title': 'Gjenopplev den historiske solformørkelsen',

  608.             'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',

  609.         },

  610.         'playlist_count': 2,

  611.     }, {

  612.         'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',

  613.         'info_dict': {

  614.             'id': 'rivertonprisen-til-karin-fossum-1.12266449',

  615.             'title': 'Rivertonprisen til Karin Fossum',

  616.             'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',

  617.         },

  618.         'playlist_count': 2,

  619.     }]

  620. 

  621.     def _extract_title(self, webpage):

  622.         return self._og_search_title(webpage, fatal=False)

  623. 

  624.     def _extract_description(self, webpage):

  625.         return self._og_search_description(webpage)

  626. 

  627. 

  628. class NRKTVEpisodesIE(NRKPlaylistBaseIE):

  629.     _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'

  630.     _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE

  631.     _TESTS = [{

  632.         'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',

  633.         'info_dict': {

  634.             'id': '69031',

  635.             'title': 'Nytt på nytt, sesong: 201210',

  636.         },

  637.         'playlist_count': 4,

  638.     }]

  639. 

  640.     def _extract_title(self, webpage):

  641.         return self._html_search_regex(

  642.             r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)

  643. 

  644. 

  645. class NRKSkoleIE(InfoExtractor):

  646.     IE_DESC = 'NRK Skole'

  647.     _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'

  648. 

  649.     _TESTS = [{

  650.         'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',

  651.         'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',

  652.         'info_dict': {

  653.             'id': '6021',

  654.             'ext': 'mp4',

  655.             'title': 'Genetikk og eneggede tvillinger',

  656.             'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',

  657.             'duration': 399,

  658.         },

  659.     }, {

  660.         'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',

  661.         'only_matching': True,

  662.     }]

  663. 

  664.     def _real_extract(self, url):

  665.         video_id = self._match_id(url)

  666. 

  667.         webpage = self._download_webpage(

  668.             'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,

  669.             video_id)

  670. 

  671.         nrk_id = self._parse_json(

  672.             self._search_regex(

  673.                 r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',

  674.                 webpage, 'application json'),

  675.             video_id)['activeMedia']['psId']

  676. 

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