youtube_dl/extractor/rbmaradio.py

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse_urlparse,
   7
   8     ExtractorError,
   9 )
  10
  11
  12 class RBMARadioIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
  14     _TEST = {
  15         u'url': u'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
  16         u'file': u'ford-lopatin-live-at-primavera-sound-2011.mp3',
  17         u'md5': u'6bc6f9bcb18994b4c983bc3bf4384d95',
  18         u'info_dict': {
  19             u"uploader_id": u"ford-lopatin",
  20             u"location": u"Spain",
  21             u"description": u"Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
  22             u"uploader": u"Ford & Lopatin",
  23             u"title": u"Live at Primavera Sound 2011"
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         m = re.match(self._VALID_URL, url)
  29         video_id = m.group('videoID')
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         json_data = self._search_regex(r'window\.gon.*?gon\.show=(.+?);$',
  34             webpage, u'json data', flags=re.MULTILINE)
  35
  36         try:
  37             data = json.loads(json_data)
  38         except ValueError as e:
  39             raise ExtractorError(u'Invalid JSON: ' + str(e))
  40
  41         video_url = data['akamai_url'] + '&cbr=256'
  42         url_parts = compat_urllib_parse_urlparse(video_url)
  43         video_ext = url_parts.path.rpartition('.')[2]
  44         info = {
  45                 'id': video_id,
  46                 'url': video_url,
  47                 'ext': video_ext,
  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         }
  56         return [info]