_ Git - youtube-dl/blob - youtube_dl/extractor/nporadio.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7
   8
   9 class NPORadioIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>.*)'
  11     _TEST = {
  12         'url': 'http://www.npo.nl/radio/radio-1',
  13         'info_dict': {
  14             'id': 'radio-1',
  15             'ext': 'mp3',
  16             'title': 'NPO Radio 1',
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         title = self._html_search_regex(
  25             self._html_get_attribute_regex('data-channel'), webpage, 'title')
  26
  27         json_data = json.loads(
  28             self._html_search_regex(
  29                 self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'))
  30
  31         return {
  32             'id': video_id,
  33             'title': title,
  34             'ext': json_data['codec'],
  35             'url': json_data['url']
  36         }
  37
  38     def _html_get_attribute_regex(self, attribute):
  39         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)