youtube_dl/extractor/podomatic.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import int_or_none
   8
   9 class PodomaticIE(InfoExtractor):
  10     IE_NAME = 'podomatic'
  11     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
  12
  13     _TESTS = [
  14         {
  15             'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
  16             'md5': '84bb855fcf3429e6bf72460e1eed782d',
  17             'info_dict': {
  18                 'id': '2009-01-02T16_03_35-08_00',
  19                 'ext': 'mp3',
  20                 'uploader': 'Science Teaching Tips',
  21                 'uploader_id': 'scienceteachingtips',
  22                 'title': '64.  When the Moon Hits Your Eye',
  23                 'duration': 446,
  24             }
  25         },
  26         {
  27             'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
  28             'md5': 'd2cf443931b6148e27638650e2638297',
  29             'info_dict': {
  30                 'id': '2013-11-15T16_31_21-08_00',
  31                 'ext': 'mp3',
  32                 'uploader': 'Ostbahnhof / Techno Mix',
  33                 'uploader_id': 'ostbahnhof',
  34                 'title': 'Einunddreizig',
  35                 'duration': 3799,
  36             }
  37         },
  38     ]
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('id')
  43         channel = mobj.group('channel')
  44
  45         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
  46                      '?permalink=true&rtmp=0') %
  47                     (mobj.group('proto'), channel, video_id))
  48         data_json = self._download_webpage(
  49             json_url, video_id, 'Downloading video info')
  50         data = json.loads(data_json)
  51
  52         video_url = data['downloadLink']
  53         if not video_url:
  54             video_url = '%s/%s' % (data['streamer'].replace('rtmp', 'http'), data['mediaLocation'])
  55         uploader = data['podcast']
  56         title = data['title']
  57         thumbnail = data['imageLocation']
  58         duration = int_or_none(data.get('length'), 1000)
  59
  60         return {
  61             'id': video_id,
  62             'url': video_url,
  63             'title': title,
  64             'uploader': uploader,
  65             'uploader_id': channel,
  66             'thumbnail': thumbnail,
  67             'duration': duration,
  68         }