1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-24 02:15:55 +01:00

[cjsw] Add extractor

This commit is contained in:
Christopher Smith 2017-06-29 13:10:45 -06:00 committed by Sergey M․
parent 4328ddf82b
commit d2b9f362fa
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
2 changed files with 42 additions and 0 deletions

View File

@ -0,0 +1,41 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CJSWIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/\S+/(?P<id>[0-9]+)'
IE_NAME = 'cjsw'
_TEST = {
'url': 'http://cjsw.com/program/freshly-squeezed/episode/20170620',
'md5': 'cee14d40f1e9433632c56e3d14977120',
'info_dict': {
'id': '20170620',
'ext': 'mp3',
'title': 'Freshly Squeezed',
'description': 'Sled Island artists featured // Live session with Phi Pho, followed by a live session with Sinzere & The Late Nights! // Stay Fresh Y\'all!!',
}
}
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
title = self._search_regex(
r'<button[^>]+data-showname=(["\'])(?P<title>(?!\1).+?)\1[^>]*>', webpage, 'title', group='title')
description = self._html_search_regex(
r'<p>(?P<description>.+?)</p>', webpage, 'description', fatal=False)
formats = [{
'url': self._search_regex(
r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>(?!\1).+?)\1[^>]*>', webpage, 'audio_url', group='audio_url'),
'ext': 'mp3',
'vcodec': 'none',
}]
return {
'id': episode_id,
'title': title,
'description': description,
'formats': formats,
}

View File

@ -185,6 +185,7 @@ from .chirbit import (
ChirbitProfileIE,
)
from .cinchcast import CinchcastIE
from .cjsw import CJSWIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .cliprs import ClipRsIE