yt_dlp/extractor/cjsw.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     unescapeHTML,
   9 )
  10
  11
  12 class CJSWIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
  14     _TESTS = [{
  15         'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
  16         'md5': 'cee14d40f1e9433632c56e3d14977120',
  17         'info_dict': {
  18             'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
  19             'ext': 'mp3',
  20             'title': 'Freshly Squeezed – Episode June 20, 2017',
  21             'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
  22             'series': 'Freshly Squeezed',
  23             'episode_id': '20170620',
  24         },
  25     }, {
  26         # no description
  27         'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
  28         'only_matching': True,
  29     }]
  30
  31     def _real_extract(self, url):
  32         mobj = self._match_valid_url(url)
  33         program, episode_id = mobj.group('program', 'id')
  34         audio_id = '%s/%s' % (program, episode_id)
  35
  36         webpage = self._download_webpage(url, episode_id)
  37
  38         title = unescapeHTML(self._search_regex(
  39             (r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
  40              r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
  41             webpage, 'title', group='title'))
  42
  43         audio_url = self._search_regex(
  44             r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
  45             webpage, 'audio url', group='url')
  46
  47         audio_id = self._search_regex(
  48             r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
  49             audio_url, 'audio id', default=audio_id)
  50
  51         formats = [{
  52             'url': audio_url,
  53             'ext': determine_ext(audio_url, 'mp3'),
  54             'vcodec': 'none',
  55         }]
  56
  57         description = self._html_search_regex(
  58             r'<p>(?P<description>.+?)</p>', webpage, 'description',
  59             default=None)
  60         series = self._search_regex(
  61             r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
  62             'series', default=program, group='name')
  63
  64         return {
  65             'id': audio_id,
  66             'title': title,
  67             'description': description,
  68             'formats': formats,
  69             'series': series,
  70             'episode_id': episode_id,
  71         }