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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_html
   7 )
   8
   9
  10 class RBMARadioIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/[^/]+/episodes/(?P<id>[^/]+)$'
  12     _TEST = {
  13         'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
  14         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
  15         'info_dict': {
  16             'id': 'ford-lopatin-live-at-primavera-sound-2011',
  17             'ext': 'mp3',
  18             'description': 'Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.',
  19             'title': 'Ford & Lopatin - Main Stage',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25
  26         webpage = self._download_webpage(url, video_id)
  27         json_data = self._search_regex(r'<script>window\.__INITIAL_STATE__\s*=\s*(.+?)</script>',
  28                                        webpage, 'json data')
  29         data = self._parse_json(json_data, video_id)
  30
  31         item = None
  32         for episode in data['episodes']:
  33             items = data['episodes'][episode]
  34             if video_id in items:
  35                 item = items[video_id]
  36
  37         video_url = item['audioURL'] + '?cbr=256'
  38
  39         return {
  40             'id': video_id,
  41             'url': video_url,
  42             'title': item.get('title') + ' - ' + item.get('showTitle'),
  43             'description': clean_html(item.get('longTeaser')),
  44             'thumbnail': self._proto_relative_url(item.get('imageURL', {}).get('landscape')),
  45             'duration': item.get('duration'),
  46         }