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

   1 from __future__ import unicode_literals
   2
   3 import re
   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     _TEST = {
  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
  27     def _real_extract(self, url):
  28         mobj = re.match(self._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', fatal=False)
  55         series = self._search_regex(
  56             r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
  57             'series', default=program, group='name')
  58
  59         return {
  60             'id': audio_id,
  61             'title': title,
  62             'description': description,
  63             'formats': formats,
  64             'series': series,
  65             'episode_id': episode_id,
  66         }