yt_dlp/extractor/urplay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     dict_get,
   7     int_or_none,
   8     unified_timestamp,
   9 )
  10
  11
  12 class URPlayIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
  14     _TESTS = [{
  15         'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
  16         'md5': 'ff5b0c89928f8083c74bbd5099c9292d',
  17         'info_dict': {
  18             'id': '203704',
  19             'ext': 'mp4',
  20             'title': 'UR Samtiden - Livet, universum och rymdens märkliga musik : Om vetenskap, kritiskt tänkande och motstånd',
  21             'description': 'md5:5344508a52aa78c1ced6c1b8b9e44e9a',
  22             'timestamp': 1513292400,
  23             'upload_date': '20171214',
  24         },
  25     }, {
  26         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
  27         'info_dict': {
  28             'id': '190031',
  29             'ext': 'mp4',
  30             'title': 'Tripp, Trapp, Träd : Sovkudde',
  31             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  32             'timestamp': 1440086400,
  33             'upload_date': '20150820',
  34         },
  35     }, {
  36         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
  37         'only_matching': True,
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         url = url.replace('skola.se/Produkter', 'play.se/program')
  43         webpage = self._download_webpage(url, video_id)
  44         urplayer_data = self._parse_json(self._html_search_regex(
  45             r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
  46             webpage, 'urplayer data'), video_id)['accessibleEpisodes'][0]
  47         episode = urplayer_data['title']
  48
  49         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
  50         formats = []
  51         urplayer_streams = urplayer_data.get('streamingInfo', {})
  52
  53         for k, v in urplayer_streams.get('raw', {}).items():
  54             if not (k in ('sd', 'hd') and isinstance(v, dict)):
  55                 continue
  56             file_http = v.get('location')
  57             if file_http:
  58                 formats.extend(self._extract_wowza_formats(
  59                     'http://%s/%splaylist.m3u8' % (host, file_http),
  60                     video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
  61         self._sort_formats(formats)
  62
  63         subtitles = {}
  64         subs = urplayer_streams.get("sweComplete", {}).get("tt", {}).get("location")
  65         if subs:
  66             subtitles.setdefault('Svenska', []).append({
  67                 'url': subs,
  68             })
  69
  70         image = urplayer_data.get('image') or {}
  71         thumbnails = []
  72         for k, v in image.items():
  73             t = {
  74                 'id': k,
  75                 'url': v,
  76             }
  77             wh = k.split('x')
  78             if len(wh) == 2:
  79                 t.update({
  80                     'width': int_or_none(wh[0]),
  81                     'height': int_or_none(wh[1]),
  82                 })
  83             thumbnails.append(t)
  84
  85         series = urplayer_data.get('series') or {}
  86         series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle'))
  87
  88         return {
  89             'id': video_id,
  90             'subtitles': subtitles,
  91             'title': '%s : %s' % (series_title, episode) if series_title else episode,
  92             'description': urplayer_data.get('description'),
  93             'thumbnails': thumbnails,
  94             'timestamp': unified_timestamp(urplayer_data.get('publishedAt')),
  95             'series': series_title,
  96             'formats': formats,
  97             'duration': int_or_none(urplayer_data.get('duration')),
  98             'categories': urplayer_data.get('categories'),
  99             'tags': urplayer_data.get('keywords'),
 100             'season': series.get('label'),
 101             'episode': episode,
 102             'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
 103         }