Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/urplay.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class URPlayIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?urplay\.se/program/(?P<id>[0-9]+)'
   9     _TEST = {
  10         'url': 'http://urplay.se/program/190031-tripp-trapp-trad-sovkudde',
  11         'md5': '15ca67b63fd8fb320ac2bcd854bad7b6',
  12         'info_dict': {
  13             'id': '190031',
  14             'ext': 'mp4',
  15             'title': 'Tripp, Trapp, Träd : Sovkudde',
  16             'description': 'md5:b86bffdae04a7e9379d1d7e5947df1d1',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22
  23         webpage = self._download_webpage(url, video_id)
  24         urplayer_data = self._parse_json(self._search_regex(
  25             r'urPlayer\.init\(({.+?})\);', webpage, 'urplayer data'), video_id)
  26         host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
  27
  28         formats = []
  29         for quality_attr, quality, preference in (('', 'sd', 0), ('_hd', 'hd', 1)):
  30             file_rtmp = urplayer_data.get('file_rtmp' + quality_attr)
  31             if file_rtmp:
  32                 formats.append({
  33                     'url': 'rtmp://%s/urplay/mp4:%s' % (host, file_rtmp),
  34                     'format_id': quality + '-rtmp',
  35                     'ext': 'flv',
  36                     'preference': preference,
  37                 })
  38             file_http = urplayer_data.get('file_http' + quality_attr) or urplayer_data.get('file_http_sub' + quality_attr)
  39             if file_http:
  40                 file_http_base_url = 'http://%s/%s' % (host, file_http)
  41                 formats.extend(self._extract_f4m_formats(
  42                     file_http_base_url + 'manifest.f4m', video_id,
  43                     preference, '%s-hds' % quality, fatal=False))
  44                 formats.extend(self._extract_m3u8_formats(
  45                     file_http_base_url + 'playlist.m3u8', video_id, 'mp4',
  46                     'm3u8_native', preference, '%s-hls' % quality, fatal=False))
  47         self._sort_formats(formats)
  48
  49         subtitles = {}
  50         for subtitle in urplayer_data.get('subtitles', []):
  51             subtitle_url = subtitle.get('file')
  52             kind = subtitle.get('kind')
  53             if subtitle_url or kind and kind != 'captions':
  54                 continue
  55             subtitles.setdefault(subtitle.get('label', 'Svenska'), []).append({
  56                 'url': subtitle_url,
  57             })
  58
  59         return {
  60             'id': video_id,
  61             'title': urplayer_data['title'],
  62             'description': self._og_search_description(webpage),
  63             'thumbnail': urplayer_data.get('image'),
  64             'series': urplayer_data.get('series_title'),
  65             'subtitles': subtitles,
  66             'formats': formats,
  67         }