logo

youtube-dl

[mirror] Download/Watch videos from video hostersgit clone https://hacktivis.me/git/mirror/youtube-dl.git

urplay.py (6174B)

    

  1. # coding: utf-8
  2. from __future__ import unicode_literals
  4. from .common import InfoExtractor
  5. from ..utils import (
  6.     dict_get,
  7.     ExtractorError,
  8.     int_or_none,
  9.     ISO639Utils,
  10.     parse_age_limit,
  11.     try_get,
  12.     unified_timestamp,
  13. )
  16. class URPlayIE(InfoExtractor):
  17.     _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
  18.     _TESTS = [{
  19.         'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
  20.         'md5': 'ff5b0c89928f8083c74bbd5099c9292d',
  21.         'info_dict': {
  22.             'id': '203704',
  23.             'ext': 'mp4',
  24.             'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd',
  25.             'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
  26.             'timestamp': 1513292400,
  27.             'upload_date': '20171214',
  28.             'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
  29.             'duration': 2269,
  30.             'categories': ['Vetenskap & teknik'],
  31.             'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
  32.             'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
  33.             'age_limit': 15,
  34.         },
  35.     }, {
  36.         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
  37.         'info_dict': {
  38.             'id': '190031',
  39.             'ext': 'mp4',
  40.             'title': 'Tripp, Trapp, Träd : Sovkudde',
  41.             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  42.             'timestamp': 1440086400,
  43.             'upload_date': '20150820',
  44.             'series': 'Tripp, Trapp, Träd',
  45.             'duration': 865,
  46.             'tags': ['Sova'],
  47.             'episode': 'Sovkudde',
  48.         },
  49.     }, {
  50.         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
  51.         'only_matching': True,
  52.     }]
  54.     def _real_extract(self, url):
  55.         video_id = self._match_id(url)
  56.         url = url.replace('skola.se/Produkter', 'play.se/program')
  57.         webpage = self._download_webpage(url, video_id)
  58.         urplayer_data = self._search_regex(
  59.             r'(?s)\bid\s*=\s*"__NEXT_DATA__"[^>]*>\s*({.+?})\s*</script',
  60.             webpage, 'urplayer next data', fatal=False) or {}
  61.         if urplayer_data:
  62.             urplayer_data = self._parse_json(urplayer_data, video_id, fatal=False)
  63.             urplayer_data = try_get(urplayer_data, lambda x: x['props']['pageProps']['program'], dict)
  64.             if not urplayer_data:
  65.                 raise ExtractorError('Unable to parse __NEXT_DATA__')
  66.         else:
  67.             accessible_episodes = self._parse_json(self._html_search_regex(
  68.                 r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
  69.                 webpage, 'urplayer data'), video_id)['accessibleEpisodes']
  70.             urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
  71.         episode = urplayer_data['title']
  72.         raw_streaming_info = urplayer_data['streamingInfo']['raw']
  73.         host = self._download_json(
  74.             'http://streaming-loadbalancer.ur.se/loadbalancer.json',
  75.             video_id)['redirect']
  77.         formats = []
  78.         for k, v in raw_streaming_info.items():
  79.             if not (k in ('sd', 'hd') and isinstance(v, dict)):
  80.                 continue
  81.             file_http = v.get('location')
  82.             if file_http:
  83.                 formats.extend(self._extract_wowza_formats(
  84.                     'http://%s/%splaylist.m3u8' % (host, file_http),
  85.                     video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
  86.         self._sort_formats(formats)
  88.         subtitles = {}
  90.         def parse_lang_code(code):
  91.             "3-character language code or None (utils candidate)"
  92.             if code is None:
  93.                 return
  94.             lang = code.lower()
  95.             if not ISO639Utils.long2short(lang):
  96.                 lang = ISO639Utils.short2long(lang)
  97.             return lang or None
  99.         for k, v in (urplayer_data['streamingInfo'].get('sweComplete') or {}).items():
  100.             if (k in ('sd', 'hd') or not isinstance(v, dict)):
  101.                 continue
  102.             lang, sttl_url = (v.get(kk) for kk in ('language', 'location', ))
  103.             if not sttl_url:
  104.                 continue
  105.             lang = parse_lang_code(lang)
  106.             if not lang:
  107.                 continue
  108.             sttl = subtitles.get(lang) or []
  109.             sttl.append({'ext': k, 'url': sttl_url, })
  110.             subtitles[lang] = sttl
  112.         image = urplayer_data.get('image') or {}
  113.         thumbnails = []
  114.         for k, v in image.items():
  115.             t = {
  116.                 'id': k,
  117.                 'url': v,
  118.             }
  119.             wh = k.split('x')
  120.             if len(wh) == 2:
  121.                 t.update({
  122.                     'width': int_or_none(wh[0]),
  123.                     'height': int_or_none(wh[1]),
  124.                 })
  125.             thumbnails.append(t)
  127.         series = urplayer_data.get('series') or {}
  128.         series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle'))
  130.         return {
  131.             'id': video_id,
  132.             'title': '%s : %s' % (series_title, episode) if series_title else episode,
  133.             'description': urplayer_data.get('description'),
  134.             'thumbnails': thumbnails,
  135.             'timestamp': unified_timestamp(urplayer_data.get('publishedAt')),
  136.             'series': series_title,
  137.             'formats': formats,
  138.             'duration': int_or_none(urplayer_data.get('duration')),
  139.             'categories': urplayer_data.get('categories'),
  140.             'tags': urplayer_data.get('keywords'),
  141.             'season': series.get('label'),
  142.             'episode': episode,
  143.             'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
  144.             'age_limit': parse_age_limit(min(try_get(a, lambda x: x['from'], int) or 0
  145.                                              for a in urplayer_data.get('ageRanges', []))),
  146.             'subtitles': subtitles,
  147.         }