youtube_dl/extractor/thisamericanlife.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class ThisAmericanLifeIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?thisamericanlife\.org/(?:radio-archives/episode/|play_full\.php\?play=)(?P<id>\d+)'
   8     _TESTS = [{
   9         'url': 'http://www.thisamericanlife.org/radio-archives/episode/487/harper-high-school-part-one',
  10         'md5': '8f7d2da8926298fdfca2ee37764c11ce',
  11         'info_dict': {
  12             'id': '487',
  13             'ext': 'm4a',
  14             'title': '487: Harper High School, Part One',
  15             'description': 'md5:ee40bdf3fb96174a9027f76dbecea655',
  16             'thumbnail': r're:^https?://.*\.jpg$',
  17         },
  18     }, {
  19         'url': 'http://www.thisamericanlife.org/play_full.php?play=487',
  20         'only_matching': True,
  21     }]
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25
  26         webpage = self._download_webpage(
  27             'http://www.thisamericanlife.org/radio-archives/episode/%s' % video_id, video_id)
  28
  29         return {
  30             'id': video_id,
  31             'url': 'http://stream.thisamericanlife.org/{0}/stream/{0}_64k.m3u8'.format(video_id),
  32             'protocol': 'm3u8_native',
  33             'ext': 'm4a',
  34             'acodec': 'aac',
  35             'vcodec': 'none',
  36             'abr': 64,
  37             'title': self._html_search_meta(r'twitter:title', webpage, 'title', fatal=True),
  38             'description': self._html_search_meta(r'description', webpage, 'description'),
  39             'thumbnail': self._og_search_thumbnail(webpage),
  40         }