add extrator for: http://video.cnfol.com/

README.md

@@ -374,6 +374,7 @@ Use `--url`/`-u` to get a list of downloadable resource URLs extracted from the
 | 花瓣     | <http://huaban.com/>           | |✓| |
 | 东方财富  | <http://video.eastmoney.com/>          |✓| | |
 | 第一财经  | <http://www.yicai.com/video/>          |✓| | |
+| 中金在线  | <http://video.cnfol.com/>          |✓| | |
 
 
 For all other sites not on the list, the universal extractor will take care of finding and downloading interesting resources from the page.

src/you_get/common.py

@@ -88,7 +88,8 @@ SITES = {
     'youtube'          : 'youtube',
     'zhanqi'           : 'zhanqi',
     'eastmoney'   : 'eastmoney',
-    'yicai'   : 'yicai'
+    'yicai'   : 'yicai',
+    'cnfol'   : 'cnfol'
 }
 
 import getopt

src/you_get/extractors/__init__.py

@@ -77,3 +77,4 @@ from .ted import *
 from .khan import *
 from .eastmoney import *
 from .yicai import *
+from .cnfol import *

src/you_get/extractors/cnfol.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+
+__all__ = ['cnfol_download']
+
+from ..common import *
+
+def cnfol_download(url, output_dir = '.', merge = True, info_only = False, **kwargs):
+    if "video.cnfol.com" in url:
+        html = get_content(url)
+        title = match1(html, r'<h1>(.+)</h1>')
+        url = match1(html, r"{f:'([^']+)'")
+        _, ext, size = url_info(url)
+        print_info(site_info, title, ext, size)
+        if not info_only:
+            download_urls([url], title, ext, size, output_dir = output_dir, merge = merge)
+
+site_info = "video.cnfol.com"
+download = cnfol_download
+download_playlist = playlist_not_supported('cnfol')