]> gitweb @ CieloNegro.org - youtube-dl.git/commitdiff
Add an extractor for kankan.com (closes #1133)
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Mon, 29 Jul 2013 21:13:12 +0000 (23:13 +0200)
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>
Mon, 29 Jul 2013 21:13:12 +0000 (23:13 +0200)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/kankan.py [new file with mode: 0644]

index 9f4dd3c243aaf8fa962ab3b42e674177f14621af..c20172a53a0372c09810b1a0ba1c0d99c8899d7c 100644 (file)
@@ -38,6 +38,7 @@ from .infoq import InfoQIE
 from .instagram import InstagramIE
 from .jukebox import JukeboxIE
 from .justintv import JustinTVIE
+from .kankan import KankanIE
 from .keek import KeekIE
 from .liveleak import LiveLeakIE
 from .livestream import LivestreamIE
diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py
new file mode 100644 (file)
index 0000000..8537ba5
--- /dev/null
@@ -0,0 +1,37 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import determine_ext
+
+
+class KankanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
+    
+    _TEST = {
+        u'url': u'http://yinyue.kankan.com/vod/48/48863.shtml',
+        u'file': u'48863.flv',
+        u'md5': u'29aca1e47ae68fc28804aca89f29507e',
+        u'info_dict': {
+            u'title': u'Ready To Go',
+        },
+    }
+
+    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._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title')
+        gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid')
+
+        video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
+                                                 video_id, u'Downloading video url info')
+        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, u'video url ip')
+        path = self._search_regex(r'path:"(.+?)"', video_info_page, u'video url path')
+        video_url = 'http://%s%s' % (ip, path)
+
+        return {'id': video_id,
+                'title': title,
+                'url': video_url,
+                'ext': determine_ext(video_url),
+                }