2017-06-29 13:10:45 -06:00
|
|
|
|
from .common import InfoExtractor
|
2017-07-09 04:00:45 -06:00
|
|
|
|
from ..utils import (
|
|
|
|
|
determine_ext,
|
|
|
|
|
unescapeHTML,
|
|
|
|
|
)
|
2017-06-29 13:10:45 -06:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class CJSWIE(InfoExtractor):
|
2017-07-09 04:00:45 -06:00
|
|
|
|
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program>[^/]+)/episode/(?P<id>\d+)'
|
2017-07-09 04:05:11 -06:00
|
|
|
|
_TESTS = [{
|
2017-06-29 13:10:45 -06:00
|
|
|
|
'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
|
|
|
|
|
'md5': 'cee14d40f1e9433632c56e3d14977120',
|
|
|
|
|
'info_dict': {
|
2017-07-09 04:00:45 -06:00
|
|
|
|
'id': '91d9f016-a2e7-46c5-8dcb-7cbcd7437c41',
|
2017-06-29 13:10:45 -06:00
|
|
|
|
'ext': 'mp3',
|
2017-07-09 04:00:45 -06:00
|
|
|
|
'title': 'Freshly Squeezed – Episode June 20, 2017',
|
|
|
|
|
'description': 'md5:c967d63366c3898a80d0c7b0ff337202',
|
|
|
|
|
'series': 'Freshly Squeezed',
|
|
|
|
|
'episode_id': '20170620',
|
|
|
|
|
},
|
2017-07-09 04:05:11 -06:00
|
|
|
|
}, {
|
|
|
|
|
# no description
|
|
|
|
|
'url': 'http://cjsw.com/program/road-pops/episode/20170707/',
|
|
|
|
|
'only_matching': True,
|
|
|
|
|
}]
|
2017-06-29 13:10:45 -06:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
2021-08-18 19:41:24 -06:00
|
|
|
|
mobj = self._match_valid_url(url)
|
2017-07-09 04:00:45 -06:00
|
|
|
|
program, episode_id = mobj.group('program', 'id')
|
2024-06-11 17:09:58 -06:00
|
|
|
|
audio_id = f'{program}/{episode_id}'
|
2017-06-29 13:10:45 -06:00
|
|
|
|
|
|
|
|
|
webpage = self._download_webpage(url, episode_id)
|
|
|
|
|
|
2017-07-09 04:00:45 -06:00
|
|
|
|
title = unescapeHTML(self._search_regex(
|
|
|
|
|
(r'<h1[^>]+class=["\']episode-header__title["\'][^>]*>(?P<title>[^<]+)',
|
|
|
|
|
r'data-audio-title=(["\'])(?P<title>(?:(?!\1).)+)\1'),
|
|
|
|
|
webpage, 'title', group='title'))
|
|
|
|
|
|
|
|
|
|
audio_url = self._search_regex(
|
|
|
|
|
r'<button[^>]+data-audio-src=(["\'])(?P<url>(?:(?!\1).)+)\1',
|
|
|
|
|
webpage, 'audio url', group='url')
|
|
|
|
|
|
|
|
|
|
audio_id = self._search_regex(
|
|
|
|
|
r'/([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})\.mp3',
|
|
|
|
|
audio_url, 'audio id', default=audio_id)
|
|
|
|
|
|
2017-06-29 13:10:45 -06:00
|
|
|
|
formats = [{
|
2017-07-09 04:00:45 -06:00
|
|
|
|
'url': audio_url,
|
|
|
|
|
'ext': determine_ext(audio_url, 'mp3'),
|
2017-06-29 13:10:45 -06:00
|
|
|
|
'vcodec': 'none',
|
|
|
|
|
}]
|
2017-07-09 04:00:45 -06:00
|
|
|
|
|
|
|
|
|
description = self._html_search_regex(
|
2017-07-09 04:05:11 -06:00
|
|
|
|
r'<p>(?P<description>.+?)</p>', webpage, 'description',
|
|
|
|
|
default=None)
|
2017-07-09 04:00:45 -06:00
|
|
|
|
series = self._search_regex(
|
|
|
|
|
r'data-showname=(["\'])(?P<name>(?:(?!\1).)+)\1', webpage,
|
|
|
|
|
'series', default=program, group='name')
|
|
|
|
|
|
2017-06-29 13:10:45 -06:00
|
|
|
|
return {
|
2017-07-09 04:00:45 -06:00
|
|
|
|
'id': audio_id,
|
2017-06-29 13:10:45 -06:00
|
|
|
|
'title': title,
|
|
|
|
|
'description': description,
|
|
|
|
|
'formats': formats,
|
2017-07-09 04:00:45 -06:00
|
|
|
|
'series': series,
|
|
|
|
|
'episode_id': episode_id,
|
2017-06-29 13:10:45 -06:00
|
|
|
|
}
|