yt_dlp/extractor/podomatic.py

   1 import json
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class PodomaticIE(InfoExtractor):
   8     IE_NAME = 'podomatic'
   9     _VALID_URL = r'''(?x)
  10                     (?P<proto>https?)://
  11                         (?:
  12                             (?P<channel>[^.]+)\.podomatic\.com/entry|
  13                             (?:www\.)?podomatic\.com/podcasts/(?P<channel_2>[^/]+)/episodes
  14                         )/
  15                         (?P<id>[^/?#&]+)
  16                 '''
  17
  18     _TESTS = [{
  19         'url': 'http://scienceteachingtips.podomatic.com/entry/2009-01-02T16_03_35-08_00',
  20         'md5': '84bb855fcf3429e6bf72460e1eed782d',
  21         'info_dict': {
  22             'id': '2009-01-02T16_03_35-08_00',
  23             'ext': 'mp3',
  24             'uploader': 'Science Teaching Tips',
  25             'uploader_id': 'scienceteachingtips',
  26             'title': '64.  When the Moon Hits Your Eye',
  27             'duration': 446,
  28         }
  29     }, {
  30         'url': 'http://ostbahnhof.podomatic.com/entry/2013-11-15T16_31_21-08_00',
  31         'md5': 'd2cf443931b6148e27638650e2638297',
  32         'info_dict': {
  33             'id': '2013-11-15T16_31_21-08_00',
  34             'ext': 'mp3',
  35             'uploader': 'Ostbahnhof / Techno Mix',
  36             'uploader_id': 'ostbahnhof',
  37             'title': 'Einunddreizig',
  38             'duration': 3799,
  39         }
  40     }, {
  41         'url': 'https://www.podomatic.com/podcasts/scienceteachingtips/episodes/2009-01-02T16_03_35-08_00',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         mobj = self._match_valid_url(url)
  47         video_id = mobj.group('id')
  48         channel = mobj.group('channel') or mobj.group('channel_2')
  49
  50         json_url = (('%s://%s.podomatic.com/entry/embed_params/%s'
  51                      + '?permalink=true&rtmp=0') %
  52                     (mobj.group('proto'), channel, video_id))
  53         data_json = self._download_webpage(
  54             json_url, video_id, 'Downloading video info')
  55         data = json.loads(data_json)
  56
  57         video_url = data['downloadLink']
  58         if not video_url:
  59             video_url = '%s/%s' % (data['streamer'].replace('rtmp', 'http'), data['mediaLocation'])
  60         uploader = data['podcast']
  61         title = data['title']
  62         thumbnail = data['imageLocation']
  63         duration = int_or_none(data.get('length'), 1000)
  64
  65         return {
  66             'id': video_id,
  67             'url': video_url,
  68             'title': title,
  69             'uploader': uploader,
  70             'uploader_id': channel,
  71             'thumbnail': thumbnail,
  72             'duration': duration,
  73         }