1
0
mirror of https://github.com/l1ving/youtube-dl synced 2025-03-13 01:27:27 +08:00

[cjsw] Add new extractor

This commit is contained in:
Christopher Smith 2017-06-29 13:10:45 -06:00
parent 40fcba5edb
commit 969c0fe31c
2 changed files with 51 additions and 0 deletions

View File

@ -0,0 +1,50 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
unescapeHTML,
)
class CJSWIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cjsw\.com/program/(?P<program_name>[\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)
episode_controls = re.search(r'<div[^>]+class=(["\'])episode-controls\1[^>]*>', webpage)
if not episode_controls:
raise ExtractorError('No streamable podcast', video_id=episode_id, expected=True)
title = unescapeHTML(self._search_regex(
r'<button[^>]+data-showname=(["\'])(?P<title>.*?)\1[^>]*>', webpage, 'title', group='title'))
description = unescapeHTML(self._html_search_regex(
r'<p>(?P<description>.*?)</p>', webpage, 'description', fatal=False))
formats = [{
'url': self._html_search_regex(
r'<button[^>]+data-audio-src=(["\'])(?P<audio_url>.*?)\1[^>]*>', webpage, 'audio_url', group='audio_url'),
'ext': 'mp3',
}]
return {
'id': episode_id,
'title': title,
'description': description,
'formats': formats,
}

View File

@ -178,6 +178,7 @@ from .chirbit import (
ChirbitProfileIE,
)
from .cinchcast import CinchcastIE
from .cjsw import CJSWIE
from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE
from .cliprs import ClipRsIE