From 474086450808541954e402dd3d58bad38b75b1d5 Mon Sep 17 00:00:00 2001 From: CkuT Date: Wed, 15 Oct 2014 18:24:32 +0200 Subject: [PATCH] [SexyKarma] Add new extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sexykarma.py | 43 +++++++++++++++++++++++++++++++ 2 files changed, 44 insertions(+) create mode 100644 youtube_dl/extractor/sexykarma.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5e38d26630..92f38dcd00 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -316,6 +316,7 @@ from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE +from .sexykarma import SexyKarmaIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py new file mode 100644 index 0000000000..cd2668872b --- /dev/null +++ b/youtube_dl/extractor/sexykarma.py @@ -0,0 +1,43 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class SexyKarmaIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sexykarma\.com/gonewild/video/(?P[a-zA-Z0-9\-]+)(.html)' + _TESTS = [{ + 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html', + 'md5': 'b9798e7d1ef1765116a8f516c8091dbd', + 'info_dict': { + 'id': 'taking-a-quick-pee-yHI70cOyIHt', + 'ext': 'mp4', + 'title': 'Taking a quick pee.', + 'uploader': 'wildginger7', + } + }, { + 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', + 'md5': 'dd216c68d29b49b12842b9babe762a5d', + 'info_dict': { + 'id': 'pot-pixie-tribute-8Id6EZPbuHf', + 'ext': 'mp4', + 'title': 'pot_pixie tribute', + 'uploader': 'banffite', + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + # TODO more code goes here, for example ... + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex(r'

(.*?)', webpage, 'title') + uploader = self._html_search_regex(r'class="aupa">\n*(.*?)', webpage, 'uploader') + url = self._html_search_regex(r'