From: Christopher Smith Date: Thu, 29 Jun 2017 19:10:45 +0000 (-0600) Subject: [cjsw] Add extractor X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=d2b9f362fabad8f9490825456d8ed679d7159271;p=youtube-dl [cjsw] Add extractor --- diff --git a/youtube_dl/extractor/cjsw.py b/youtube_dl/extractor/cjsw.py new file mode 100644 index 000000000..087cac9bc --- /dev/null +++ b/youtube_dl/extractor/cjsw.py @@ -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[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']+data-showname=(["\'])(?P(?!\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, + } diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index b83c3aba5..4524fa687 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -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