yt_dlp/extractor/cjsw.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     determine_ext,
   4     unescapeHTML,
   5 )
   6
   7
   8 class CJSWIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
  10     _TESTS = [{
  11         'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
  12         'md5': 'cee14d40f1e9433632c56e3d14977120',
  13         'info_dict': {
  14             'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
  15             'ext': 'mp3',
  16             'title': 'Freshly Squeezed – Episode June 20, 2017',
  17             'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
  18             'series': 'Freshly Squeezed',
  19             'episode_id': '20170620',
  20         },
  21     }, {
  22         # no description
  23         'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
  24         'only_matching': True,
  25     }]
  26
  27     def _real_extract(self, url):
  28         mobj = self._match_valid_url(url)
  29         program, episode_id = mobj.group('program', 'id')
  30         audio_id = '%s/%s' % (program, episode_id)
  31
  32         webpage = self._download_webpage(url, episode_id)
  33
  34         title = unescapeHTML(self._search_regex(
  35             (r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
  36              r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
  37             webpage, 'title', group='title'))
  38
  39         audio_url = self._search_regex(
  40             r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
  41             webpage, 'audio url', group='url')
  42
  43         audio_id = self._search_regex(
  44             r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
  45             audio_url, 'audio id', default=audio_id)
  46
  47         formats = [{
  48             'url': audio_url,
  49             'ext': determine_ext(audio_url, 'mp3'),
  50             'vcodec': 'none',
  51         }]
  52
  53         description = self._html_search_regex(
  54             r'<p>(?P<description>.+?)</p>', webpage, 'description',
  55             default=None)
  56         series = self._search_regex(
  57             r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
  58             'series', default=program, group='name')
  59
  60         return {
  61             'id': audio_id,
  62             'title': title,
  63             'description': description,
  64             'formats': formats,
  65             'series': series,
  66             'episode_id': episode_id,
  67         }