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

   1 import json
   2 import re
   3
   4 from .common import InfoExtractor
   5
   6
   7 class PodomaticIE(InfoExtractor):
   8     IE_NAME = 'podomatic'
   9     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
  10
  11     _TEST = {
  12         u"url": u"http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
  13         u"file": u"2009-01-02T16_03_35-08_00.mp3",
  14         u"md5": u"84bb855fcf3429e6bf72460e1eed782d",
  15         u"info_dict": {
  16             u"uploader": u"Science Teaching Tips",
  17             u"uploader_id": u"scienceteachingtips",
  18             u"title": u"64.  When the Moon Hits Your Eye",
  19             u"duration": 446,
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26         channel = mobj.group('channel')
  27
  28         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
  29                      '?permalink=true&rtmp=0') %
  30                     (mobj.group('proto'), channel, video_id))
  31         data_json = self._download_webpage(
  32             json_url, video_id, note=u'Downloading video info')
  33         data = json.loads(data_json)
  34
  35         video_url = data['downloadLink']
  36         uploader = data['podcast']
  37         title = data['title']
  38         thumbnail = data['imageLocation']
  39         duration = int(data['length'] / 1000.0)
  40
  41         return {
  42             'id': video_id,
  43             'url': video_url,
  44             'title': title,
  45             'uploader': uploader,
  46             'uploader_id': channel,
  47             'thumbnail': thumbnail,
  48             'duration': duration,
  49         }