diff options
author | CkuT <s3cu@hotmail.fr> | 2014-10-15 18:24:32 +0200 |
---|---|---|
committer | CkuT <s3cu@hotmail.fr> | 2014-10-15 18:24:32 +0200 |
commit | 474086450808541954e402dd3d58bad38b75b1d5 (patch) | |
tree | a8f26d0a0bdfc01f9e5bbe7c9fe48b6a3193f48a /youtube_dl/extractor | |
parent | 09a42738fc5a060208cad5fa5579688225e53464 (diff) |
[SexyKarma] Add new extractor
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 1 | ||||
-rw-r--r-- | youtube_dl/extractor/sexykarma.py | 43 |
2 files changed, 44 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5e38d2663..92f38dcd0 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -316,6 +316,7 @@ from .sbs import SBSIE 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 000000000..cd2668872 --- /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<id>[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'<h2 class="he2"><span>(.*?)</span>', webpage, 'title') + uploader = self._html_search_regex(r'class="aupa">\n*(.*?)</a>', webpage, 'uploader') + url = self._html_search_regex(r'<p><a href="(.*?)" ?\n*target="_blank"><font color', webpage, 'url') + + return { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'url': url + } |