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             'series': 'UR Samtiden - Livet, universum och rymdens märkliga musik',
  25             'duration': 2269,
  26             'categories': ['Kultur & historia'],
  27             'tags': ['Kritiskt tänkande', 'Vetenskap', 'Vetenskaplig verksamhet'],
  28             'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
  29         },
  30     }, {
  31         'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
  32         'info_dict': {
  33             'id': '190031',
  34             'ext': 'mp4',
  35             'title': 'Tripp, Trapp, Träd : Sovkudde',
  36             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  37             'timestamp': 1440086400,
  38             'upload_date': '20150820',
  39             'series': 'Tripp, Trapp, Träd',
  40             'duration': 865,
  41             'tags': ['Sova'],
  42             'episode': 'Sovkudde',
  43         },
  44     }, {
  45         'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
  46         'only_matching': True,
  47     }]
  48
  49     def _real_extract(self, url):
  50         video_id = self._match_id(url)
  51         url = url.replace('skola.se/Produkter', 'play.se/program')
  52         webpage = self._download_webpage(url, video_id)
  53         vid = int(video_id)
  54         accessible_episodes = self._parse_json(self._html_search_regex(
  55             r'data-react-class="routes/Product/components/ProgramContainer/ProgramContainer"[^>]+data-react-props="({.+?})"',
  56             webpage, 'urplayer data'), video_id)['accessibleEpisodes']
  57         urplayer_data = next(e for e in accessible_episodes if e.get('id') == vid)
  58         episode = urplayer_data['title']
  59
  60         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
  61         formats = []
  62         urplayer_streams = urplayer_data.get('streamingInfo', {})
  63
  64         for k, v in urplayer_streams.get('raw', {}).items():
  65             if not (k in ('sd', 'hd') and isinstance(v, dict)):
  66                 continue
  67             file_http = v.get('location')
  68             if file_http:
  69                 formats.extend(self._extract_wowza_formats(
  70                     'http://%s/%splaylist.m3u8' % (host, file_http),
  71                     video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
  72         self._sort_formats(formats)
  73
  74         subtitles = {}
  75         subs = urplayer_streams.get("sweComplete", {}).get("tt", {}).get("location")
  76         if subs:
  77             subtitles.setdefault('Svenska', []).append({
  78                 'url': subs,
  79             })
  80
  81         image = urplayer_data.get('image') or {}
  82         thumbnails = []
  83         for k, v in image.items():
  84             t = {
  85                 'id': k,
  86                 'url': v,
  87             }
  88             wh = k.split('x')
  89             if len(wh) == 2:
  90                 t.update({
  91                     'width': int_or_none(wh[0]),
  92                     'height': int_or_none(wh[1]),
  93                 })
  94             thumbnails.append(t)
  95
  96         series = urplayer_data.get('series') or {}
  97         series_title = dict_get(series, ('seriesTitle', 'title')) or dict_get(urplayer_data, ('seriesTitle', 'mainTitle'))
  98
  99         return {
 100             'id': video_id,
 101             'subtitles': subtitles,
 102             'title': '%s : %s' % (series_title, episode) if series_title else episode,
 103             'description': urplayer_data.get('description'),
 104             'thumbnails': thumbnails,
 105             'timestamp': unified_timestamp(urplayer_data.get('publishedAt')),
 106             'series': series_title,
 107             'formats': formats,
 108             'duration': int_or_none(urplayer_data.get('duration')),
 109             'categories': urplayer_data.get('categories'),
 110             'tags': urplayer_data.get('keywords'),
 111             'season': series.get('label'),
 112             'episode': episode,
 113             'episode_number': int_or_none(urplayer_data.get('episodeNumber')),
 114         }