_ Git - youtube-dl/blob - 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
  10 class PodomaticIE(InfoExtractor):
  11     IE_NAME = 'podomatic'
  12     _VALID_URL = r'^(?P<proto>https?)://(?P<channel>[^.]+)\.podomatic\.com/entry/(?P<id>[^?]+)'
  13
  14     _TEST = {
  15         "url": "http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00",
  16         "file": "2009-01-02T16_03_35-08_00.mp3",
  17         "md5": "84bb855fcf3429e6bf72460e1eed782d",
  18         "info_dict": {
  19             "uploader": "Science Teaching Tips",
  20             "uploader_id": "scienceteachingtips",
  21             "title": "64.  When the Moon Hits Your Eye",
  22             "duration": 446,
  23         }
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         video_id = mobj.group('id')
  29         channel = mobj.group('channel')
  30
  31         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s' +
  32                      '?permalink=true&rtmp=0') %
  33                     (mobj.group('proto'), channel, video_id))
  34         data_json = self._download_webpage(
  35             json_url, video_id, note=u'Downloading video info')
  36         data = json.loads(data_json)
  37
  38         video_url = data['downloadLink']
  39         uploader = data['podcast']
  40         title = data['title']
  41         thumbnail = data['imageLocation']
  42         duration = int_or_none(data.get('length'), 1000)
  43
  44         return {
  45             'id': video_id,
  46             'url': video_url,
  47             'title': title,
  48             'uploader': uploader,
  49             'uploader_id': channel,
  50             'thumbnail': thumbnail,
  51             'duration': duration,
  52         }