yt_dlp/extractor/urplay.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     ISO639Utils,
   5     dict_get,
   6     int_or_none,
   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': '5ba36643c77cc3d34ffeadad89937d1e',
  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             'thumbnail': r're:^https?://.+\.jpg',
  24             'timestamp': 1513292400,
  25             'upload_date': '20171214',
  26             'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
  27             'duration': 2269,
  28             'categories': ['Vetenskap & teknik'],
  29             'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
  30             'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
  31             'age_limit': 15,
  32         },
  33     }, {
  34         'url': 'https://urplay.se/program/222967-en-foralders-dagbok-mitt-barn-skadar-sig-sjalv',
  35         'info_dict': {
  36             'id': '222967',
  37             'ext': 'mp4',
  38             'title': 'En förälders dagbok : Mitt barn skadar sig själv',
  39             'description': 'md5:9f771eef03a732a213b367b52fe826ca',
  40             'thumbnail': r're:^https?://.+\.jpg',
  41             'timestamp': 1629676800,
  42             'upload_date': '20210823',
  43             'series': 'En förälders dagbok',
  44             'duration': 1740,
  45             'age_limit': 15,
  46             'episode_number': 3,
  47             'categories': 'count:2',
  48             'tags': 'count:7',
  49             'episode': 'Mitt barn skadar sig själv',
  50         },
  51     }, {
  52         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
  53         'info_dict': {
  54             'id': '190031',
  55             'ext': 'mp4',
  56             'title': 'Tripp, Trapp, Träd : Sovkudde',
  57             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  58             'thumbnail': r're:^https?://.+\.jpg',
  59             'timestamp': 1440086400,
  60             'upload_date': '20150820',
  61             'series': 'Tripp, Trapp, Träd',
  62             'duration': 865,
  63             'age_limit': 1,
  64             'episode_number': 1,
  65             'categories': [],
  66             'tags': ['Sova'],
  67             'episode': 'Sovkudde',
  68             'season': 'Säsong 1',
  69         },
  70     }, {
  71         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
  72         'only_matching': True,
  73     }]
  74
  75     def _real_extract(self, url):
  76         video_id = self._match_id(url)
  77         url = url.replace('skola.se/Produkter', 'play.se/program')
  78         webpage = self._download_webpage(url, video_id)
  79         urplayer_data = self._search_nextjs_data(webpage, video_id, fatal=False) or {}
  80         if urplayer_data:
  81             urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict)
  82             if not urplayer_data:
  83                 raise ExtractorError('Unable to parse __NEXT_DATA__')
  84         else:
  85             accessible_episodes = self._parse_json(self._html_search_regex(
  86                 r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
  87                 webpage, 'urplayer data'), video_id)['accessibleEpisodes']
  88             urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
  89         episode = urplayer_data['title']
  90
  91         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
  92         formats = []
  93         urplayer_streams = urplayer_data.get('streamingInfo', {})
  94
  95         for k, v in urplayer_streams.get('raw', {}).items():
  96             if not (k in ('sd', 'hd', 'mp3', 'm4a') and isinstance(v, dict)):
  97                 continue
  98             file_http = v.get('location')
  99             if file_http:
 100                 formats.extend(self._extract_wowza_formats(
 101                     'http://%s/%splaylist.m3u8' % (host, file_http),
 102                     video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
 103
 104         subtitles = {}
 105
 106         def parse_lang_code(code):
 107             "3-character language code or None (utils candidate)"
 108             if code is None:
 109                 return
 110             lang = code.lower()
 111             if not ISO639Utils.long2short(lang):
 112                 lang = ISO639Utils.short2long(lang)
 113             return lang or None
 114
 115         for stream in urplayer_data['streamingInfo'].values():
 116             for k, v in stream.items():
 117                 if (k in ('sd', 'hd') or not isinstance(v, dict)):
 118                     continue
 119                 lang, sttl_url = (v.get(kk) for kk in ('language', 'location', ))
 120                 if not sttl_url:
 121                     continue
 122                 lang = parse_lang_code(lang)
 123                 if not lang:
 124                     continue
 125                 sttl = subtitles.get(lang) or []
 126                 sttl.append({'ext': k, 'url': sttl_url, })
 127                 subtitles[lang] = sttl
 128
 129         image = urplayer_data.get('image') or {}
 130         thumbnails = []
 131         for k, v in image.items():
 132             t = {
 133                 'id': k,
 134                 'url': v,
 135             }
 136             wh = k.split('x')
 137             if len(wh) == 2:
 138                 t.update({
 139                     'width': int_or_none(wh[0]),
 140                     'height': int_or_none(wh[1]),
 141                 })
 142             thumbnails.append(t)
 143
 144         series = urplayer_data.get('series') or {}
 145         series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle'))
 146
 147         return {
 148             'id': video_id,
 149             'title': '%s : %s' % (series_title, episode) if series_title else episode,
 150             'description': urplayer_data.get('description'),
 151             'thumbnails': thumbnails,
 152             'timestamp': unified_timestamp(urplayer_data.get('publishedAt')),
 153             'series': series_title,
 154             'formats': formats,
 155             'duration': int_or_none(urplayer_data.get('duration')),
 156             'categories': urplayer_data.get('categories'),
 157             'tags': urplayer_data.get('keywords'),
 158             'season': series.get('label'),
 159             'episode': episode,
 160             'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
 161             'age_limit': parse_age_limit(min(try_get(a, lambda x: x['from'], int) or 0
 162                                              for a in urplayer_data.get('ageRanges', []))),
 163             'subtitles': subtitles,
 164         }