[SexyKarma] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 5e38d2663011db8bfe40807f26a48588dbdee59a..92f38dcd004c7cb41648191b88cb2c08e8b3727e 100644 (file)
--- 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 (file)
index 0000000..cd26688
--- /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
+        }