From 27fe903c511691c078942bef5ee9a05a43b15c8f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jes=C3=BAs?= <heckyel@hyperbola.info>
Date: Wed, 9 Jun 2021 17:54:27 -0500
Subject: initial

---
 hypervideo_dl/extractor/kankan.py | 48 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 hypervideo_dl/extractor/kankan.py

(limited to 'hypervideo_dl/extractor/kankan.py')

diff --git a/hypervideo_dl/extractor/kankan.py b/hypervideo_dl/extractor/kankan.py
new file mode 100644
index 0000000..a677ff4
--- /dev/null
+++ b/hypervideo_dl/extractor/kankan.py
@@ -0,0 +1,48 @@
+from __future__ import unicode_literals
+
+import re
+import hashlib
+
+from .common import InfoExtractor
+
+_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
+
+
+class KankanIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
+
+    _TEST = {
+        'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
+        'md5': '29aca1e47ae68fc28804aca89f29507e',
+        'info_dict': {
+            'id': '48863',
+            'ext': 'flv',
+            'title': 'Ready To Go',
+        },
+        'skip': 'Only available from China',
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
+        surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
+        gcids = re.findall(r'http://.+?/.+?/(.+?)/', surls)
+        gcid = gcids[-1]
+
+        info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid
+        video_info_page = self._download_webpage(
+            info_url, video_id, 'Downloading video url info')
+        ip = self._search_regex(r'ip:"(.+?)"', video_info_page, 'video url ip')
+        path = self._search_regex(r'path:"(.+?)"', video_info_page, 'video url path')
+        param1 = self._search_regex(r'param1:(\d+)', video_info_page, 'param1')
+        param2 = self._search_regex(r'param2:(\d+)', video_info_page, 'param2')
+        key = _md5('xl_mp43651' + param1 + param2)
+        video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+        }
-- 
cgit v1.2.3