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

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6
   7 from .common import InfoExtractor
   8 from ..utils import (
   9     ExtractorError,
  10 )
  11
  12
  13 class RBMARadioIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
  15     _TEST = {
  16         'url': 'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
  17         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
  18         'info_dict': {
  19             'id': 'ford-lopatin-live-at-primavera-sound-2011',
  20             'ext': 'mp3',
  21             "uploader_id": "ford-lopatin",
  22             "location": "Spain",
  23             "description": "Joel Ford and Daniel ’Oneohtrix Point Never’ Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
  24             "uploader": "Ford & Lopatin",
  25             "title": "Live at Primavera Sound 2011",
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         m = re.match(self._VALID_URL, url)
  31         video_id = m.group('videoID')
  32
  33         webpage = self._download_webpage(url, video_id)
  34
  35         json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
  36                                        webpage, 'json data', flags=re.MULTILINE)
  37
  38         try:
  39             data = json.loads(json_data)
  40         except ValueError as e:
  41             raise ExtractorError('Invalid JSON: ' + str(e))
  42
  43         video_url = data['akamai_url'] + '&cbr=256'
  44
  45         return {
  46             'id': video_id,
  47             'url': video_url,
  48             'title': data['title'],
  49             'description': data.get('teaser_text'),
  50             'location': data.get('country_of_origin'),
  51             'uploader': data.get('host', {}).get('name'),
  52             'uploader_id': data.get('host', {}).get('slug'),
  53             'thumbnail': data.get('image', {}).get('large_url_2x'),
  54             'duration': data.get('duration'),
  55         }