aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-29 23:13:12 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-29 23:13:12 +0200
commit8cda9241d12b1bfb83bd609924f5e215304b9e91 (patch)
treeccc16fe44e739e994558d7e7887a84bdbcc4d314 /youtube_dl/extractor
parentcaeefc29ebce8dbfb0c25a79887719055276c9eb (diff)
Add an extractor for kankan.com (closes #1133)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/kankan.py37
2 files changed, 38 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 9f4dd3c24..c20172a53 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -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
index 000000000..8537ba584
--- /dev/null
+++ b/youtube_dl/extractor/kankan.py
@@ -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),
+ }