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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class CJSWIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/\S+/(?P<id>[0-9]+)'
   9     IE_NAME = 'cjsw'
  10     _TEST = {
  11         'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
  12         'md5': 'cee14d40f1e9433632c56e3d14977120',
  13         'info_dict': {
  14             'id': '20170620',
  15             'ext': 'mp3',
  16             'title': 'Freshly Squeezed',
  17             'description': 'Sled Island artists featured // Live session with Phi Pho, followed by a live session with Sinzere & The Late Nights! // Stay Fresh Y\'all!!',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         episode_id = self._match_id(url)
  23
  24         webpage = self._download_webpage(url, episode_id)
  25
  26         title = self._search_regex(
  27             r'<button[^>]+data-showname=(["\'])(?P<title>(?!\1).+?)\1[^>]*>', webpage, 'title', group='title')
  28         description = self._html_search_regex(
  29             r'<p>(?P<description>.+?)</p>', webpage, 'description', fatal=False)
  30         formats = [{
  31             'url': self._search_regex(
  32                 r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>(?!\1).+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'),
  33             'ext': 'mp3',
  34             'vcodec': 'none',
  35         }]
  36         return {
  37             'id': episode_id,
  38             'title': title,
  39             'description': description,
  40             'formats': formats,
  41         }