_ Git - youtube-dl/blob - youtube_dl/extractor/stitcher.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class StitcherIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?stitcher\.com/podcast/[\/a-z\-]+(?P<id>\d+)'
   9     _TEST = {
  10         'url': 'http://www.stitcher.com/podcast/the-talking-machines/e/40789481?autoplay=true',
  11         'md5': '391dd4e021e6edeb7b8e68fbf2e9e940',
  12         'info_dict': {
  13             'id': '40789481',
  14             'ext': 'mp3',
  15             'title': 'Machine Learning Mastery and Cancer Clusters from Talking Machines',
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         audio_id = self._match_id(url)
  21
  22         webpage = self._download_webpage(url, audio_id)
  23
  24         title = self._og_search_title(webpage)
  25         url = self._search_regex(r'episodeURL: "(.+?)"', webpage, 'url')
  26         episode_image = self._search_regex(r'episodeImage: "(.+?)"', webpage, 'episode_image', fatal=False)
  27         duration = int_or_none(self._search_regex(r'duration: (\d+?),', webpage, 'duration', fatal=False))
  28
  29         return {
  30             'id': audio_id,
  31             'url': url,
  32             'title': title,
  33             'duration': duration,
  34             'thumbnail': episode_image,
  35             'ext': 'mp3',
  36             'vcodec': 'none',
  37         }