Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cjsw.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     determine_ext,
   9     unescapeHTML,
  10 )
  11
  12
  13 class CJSWIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
  15     _TESTS = [{
  16         'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
  17         'md5': 'cee14d40f1e9433632c56e3d14977120',
  18         'info_dict': {
  19             'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
  20             'ext': 'mp3',
  21             'title': 'Freshly Squeezed – Episode June 20, 2017',
  22             'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
  23             'series': 'Freshly Squeezed',
  24             'episode_id': '20170620',
  25         },
  26     }, {
  27         # no description
  28         'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         program, episode_id = mobj.group('program', 'id')
  35         audio_id = '%s/%s' % (program, episode_id)
  36
  37         webpage = self._download_webpage(url, episode_id)
  38
  39         title = unescapeHTML(self._search_regex(
  40             (r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
  41              r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
  42             webpage, 'title', group='title'))
  43
  44         audio_url = self._search_regex(
  45             r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
  46             webpage, 'audio url', group='url')
  47
  48         audio_id = self._search_regex(
  49             r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
  50             audio_url, 'audio id', default=audio_id)
  51
  52         formats = [{
  53             'url': audio_url,
  54             'ext': determine_ext(audio_url, 'mp3'),
  55             'vcodec': 'none',
  56         }]
  57
  58         description = self._html_search_regex(
  59             r'<p>(?P<description>.+?)</p>', webpage, 'description',
  60             default=None)
  61         series = self._search_regex(
  62             r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
  63             'series', default=program, group='name')
  64
  65         return {
  66             'id': audio_id,
  67             'title': title,
  68             'description': description,
  69             'formats': formats,
  70             'series': series,
  71             'episode_id': episode_id,
  72         }