yt_dlp/extractor/urplay.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     dict_get,
   4     ExtractorError,
   5     int_or_none,
   6     ISO639Utils,
   7     parse_age_limit,
   8     try_get,
   9     unified_timestamp,
  10 )
  11
  12
  13 class URPlayIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
  15     _TESTS = [{
  16         'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
  17         'md5': 'ff5b0c89928f8083c74bbd5099c9292d',
  18         'info_dict': {
  19             'id': '203704',
  20             'ext': 'mp4',
  21             'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd',
  22             'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
  23             'timestamp': 1513292400,
  24             'upload_date': '20171214',
  25             'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
  26             'duration': 2269,
  27             'categories': ['Vetenskap & teknik'],
  28             'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
  29             'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
  30             'age_limit': 15,
  31         },
  32     }, {
  33         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
  34         'info_dict': {
  35             'id': '190031',
  36             'ext': 'mp4',
  37             'title': 'Tripp, Trapp, Träd : Sovkudde',
  38             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  39             'timestamp': 1440086400,
  40             'upload_date': '20150820',
  41             'series': 'Tripp, Trapp, Träd',
  42             'duration': 865,
  43             'tags': ['Sova'],
  44             'episode': 'Sovkudde',
  45         },
  46     }, {
  47         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
  48         'only_matching': True,
  49     }]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53         url = url.replace('skola.se/Produkter', 'play.se/program')
  54         webpage = self._download_webpage(url, video_id)
  55         urplayer_data = self._search_nextjs_data(webpage, video_id, fatal=False) or {}
  56         if urplayer_data:
  57             urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict)
  58             if not urplayer_data:
  59                 raise ExtractorError('Unable to parse __NEXT_DATA__')
  60         else:
  61             accessible_episodes = self._parse_json(self._html_search_regex(
  62                 r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
  63                 webpage, 'urplayer data'), video_id)['accessibleEpisodes']
  64             urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
  65         episode = urplayer_data['title']
  66
  67         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
  68         formats = []
  69         urplayer_streams = urplayer_data.get('streamingInfo', {})
  70
  71         for k, v in urplayer_streams.get('raw', {}).items():
  72             if not (k in ('sd', 'hd') and isinstance(v, dict)):
  73                 continue
  74             file_http = v.get('location')
  75             if file_http:
  76                 formats.extend(self._extract_wowza_formats(
  77                     'http://%s/%splaylist.m3u8' % (host, file_http),
  78                     video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
  79         self._sort_formats(formats)
  80
  81         subtitles = {}
  82
  83         def parse_lang_code(code):
  84             "3-character language code or None (utils candidate)"
  85             if code is None:
  86                 return
  87             lang = code.lower()
  88             if not ISO639Utils.long2short(lang):
  89                 lang = ISO639Utils.short2long(lang)
  90             return lang or None
  91
  92         for k, v in (urplayer_data['streamingInfo'].get('sweComplete') or {}).items():
  93             if (k in ('sd', 'hd') or not isinstance(v, dict)):
  94                 continue
  95             lang, sttl_url = (v.get(kk) for kk in ('language', 'location', ))
  96             if not sttl_url:
  97                 continue
  98             lang = parse_lang_code(lang)
  99             if not lang:
 100                 continue
 101             sttl = subtitles.get(lang) or []
 102             sttl.append({'ext': k, 'url': sttl_url, })
 103             subtitles[lang] = sttl
 104
 105         image = urplayer_data.get('image') or {}
 106         thumbnails = []
 107         for k, v in image.items():
 108             t = {
 109                 'id': k,
 110                 'url': v,
 111             }
 112             wh = k.split('x')
 113             if len(wh) == 2:
 114                 t.update({
 115                     'width': int_or_none(wh[0]),
 116                     'height': int_or_none(wh[1]),
 117                 })
 118             thumbnails.append(t)
 119
 120         series = urplayer_data.get('series') or {}
 121         series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle'))
 122
 123         return {
 124             'id': video_id,
 125             'title': '%s : %s' % (series_title, episode) if series_title else episode,
 126             'description': urplayer_data.get('description'),
 127             'thumbnails': thumbnails,
 128             'timestamp': unified_timestamp(urplayer_data.get('publishedAt')),
 129             'series': series_title,
 130             'formats': formats,
 131             'duration': int_or_none(urplayer_data.get('duration')),
 132             'categories': urplayer_data.get('categories'),
 133             'tags': urplayer_data.get('keywords'),
 134             'season': series.get('label'),
 135             'episode': episode,
 136             'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
 137             'age_limit': parse_age_limit(min(try_get(a, lambda x: x['from'], int) or 0
 138                                              for a in urplayer_data.get('ageRanges', []))),
 139             'subtitles': subtitles,
 140         }