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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class RTVSIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)'
   9     _TESTS = [{
  10         # radio archive
  11         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
  12         'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
  13         'info_dict': {
  14             'id': '414872',
  15             'ext': 'mp3',
  16             'title': 'Ostrov pokladov 1 časť.mp3'
  17         },
  18         'params': {
  19             'skip_download': True,
  20         }
  21     }, {
  22         # tv archive
  23         'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
  24         'md5': '85e2c55cf988403b70cac24f5c086dc6',
  25         'info_dict': {
  26             'id': '63118',
  27             'ext': 'mp4',
  28             'title': 'Amaro Džives - Náš deň',
  29             'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
  30         },
  31         'params': {
  32             'skip_download': True,
  33         }
  34     }]
  35
  36     def _real_extract(self, url):
  37         video_id = self._match_id(url)
  38
  39         webpage = self._download_webpage(url, video_id)
  40
  41         playlist_url = self._search_regex(
  42             r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
  43             'playlist url', group='url')
  44
  45         data = self._download_json(
  46             playlist_url, video_id, 'Downloading playlist')[0]
  47         return self._parse_jwplayer_data(data, video_id=video_id)