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

   1 # encoding: utf-8
   2 from .common import InfoExtractor
   3 from ..utils import (
   4     unified_strdate,
   5 )
   6
   7 class LibsynIE(InfoExtractor):
   8     _VALID_URL = r'(?:https?:)?//html5-player\.libsyn\.com/embed/episode/id/(?P<id>[0-9]+)(?:/.*)?'
   9
  10     def _real_extract(self, url):
  11         if url.startswith('//'):
  12             url = 'https:' + url
  13         display_id = self._match_id(url)
  14         webpage = self._download_webpage(url, display_id)
  15
  16         podcast_title         = self._search_regex(r'<h2>(.*?)</h2>', webpage, 'show title')
  17         podcast_episode_title = self._search_regex(r'<h3>(.*?)</h3>', webpage, 'episode title')
  18         podcast_date          = unified_strdate(self._search_regex(r'<div class="release_date">Released: (.*?)</div>', webpage, 'release date'))
  19         podcast_description   = self._search_regex(r'<div id="info_text_body">(.*?)</div>', webpage, 'description')
  20
  21         url0 = self._search_regex(r'var mediaURLLibsyn = "(?P<url0>https?://.*)";', webpage, 'first media URL')
  22         url1 = self._search_regex(r'var mediaURL = "(?P<url1>https?://.*)";', webpage, 'second media URL')
  23
  24         if url0 != url1:
  25             formats = [{
  26                 'url': url0
  27             }, {
  28                 'url': url1
  29             }]
  30         else:
  31             formats = [{
  32                 'url': url0
  33             }]
  34
  35         return {
  36             'id': display_id,
  37             'title': podcast_episode_title,
  38             'description': podcast_description,
  39             'upload_date': podcast_date,
  40             'formats': formats,
  41         }