[ku6] Add new extractor

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 72523c54d31a4192700eab77bc9b83a241605853..ace298fb3523253c00de5ed96b2fb4a1509a9123 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -142,6 +142,7 @@ from .khanacademy import KhanAcademyIE
 from .kickstarter import KickStarterIE
 from .keek import KeekIE
 from .kontrtube import KontrTubeIE
+from .ku6 import Ku6IE
 from .la7 import LA7IE
 from .lifenews import LifeNewsIE
 from .liveleak import LiveLeakIE

diff --git a/youtube_dl/extractor/ku6.py b/youtube_dl/extractor/ku6.py
new file mode 100644 (file)
index 0000000..eecbe26
--- /dev/null
+++ b/youtube_dl/extractor/ku6.py
@@ -0,0 +1,38 @@
+from __future__ import unicode_literals
+import re
+from .common import InfoExtractor
+
+class Ku6IE(InfoExtractor):
+    _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
+    _TEST = {
+        'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
+        'info_dict': {
+            'id': 'JG-8yS14xzBr4bCn1pu0xw',
+            'ext': 'f4v',
+            u'title': u'techniques test',
+        }
+    }
+
+
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        #title = self._html_search_meta('title', webpage, 'title')
+        title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
+        self.to_screen('title: '+title)
+
+        dataUrl = 'http://v.ku6.com/fetchVideo4Player/'+video_id+'.html'
+        jsonData = self._download_json(dataUrl, video_id)
+        downloadUrl = jsonData['data']['f']
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': downloadUrl
+            # TODO more properties (see youtube_dl/extractor/common.py)
+
+        }
+