From 50446e427365a9aabdf70247582d16e04ad7b1c2 Mon Sep 17 00:00:00 2001
From: Vito Van <awesomevito@live.com>
Date: Wed, 11 May 2016 09:47:58 +0800
Subject: [PATCH] add extrator for: http://video.eastmoney.com

---
 README.md                           |  2 ++
 src/you_get/common.py               |  1 +
 src/you_get/extractors/__init__.py  |  1 +
 src/you_get/extractors/eastmoney.py | 22 ++++++++++++++++++++++
 4 files changed, 26 insertions(+)
 create mode 100644 src/you_get/extractors/eastmoney.py

diff --git a/README.md b/README.md
index ddfac26d..183d65ac 100644
--- a/README.md
+++ b/README.md
@@ -372,6 +372,8 @@ Use `--url`/`-u` to get a list of downloadable resource URLs extracted from the
 | 战旗TV   | <http://www.zhanqi.tv/lives>   |✓| | |
 | 央视网   | <http://www.cntv.cn/>          |✓| | |
 | 花瓣     | <http://huaban.com/>           | |✓| |
+| 东方财富  | <http://video.eastmoney.com/>          |✓| | |
+
 
 For all other sites not on the list, the universal extractor will take care of finding and downloading interesting resources from the page.
 
diff --git a/src/you_get/common.py b/src/you_get/common.py
index 284b1660..5bc5870b 100755
--- a/src/you_get/common.py
+++ b/src/you_get/common.py
@@ -87,6 +87,7 @@ SITES = {
     'youtu'            : 'youtube',
     'youtube'          : 'youtube',
     'zhanqi'           : 'zhanqi',
+    'eastmoney'   : 'eastmoney'
 }
 
 import getopt
diff --git a/src/you_get/extractors/__init__.py b/src/you_get/extractors/__init__.py
index 6c3864fd..f691f26c 100755
--- a/src/you_get/extractors/__init__.py
+++ b/src/you_get/extractors/__init__.py
@@ -75,3 +75,4 @@ from .youku import *
 from .youtube import *
 from .ted import *
 from .khan import *
+from .eastmoney import *
diff --git a/src/you_get/extractors/eastmoney.py b/src/you_get/extractors/eastmoney.py
new file mode 100644
index 00000000..1c309df1
--- /dev/null
+++ b/src/you_get/extractors/eastmoney.py
@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+
+__all__ = ['eastmoney_download']
+
+from ..common import *
+
+def eastmoney_download(url, output_dir = '.', merge = True, info_only = False, **kwargs):
+    if "video.eastmoney.com" in url:
+        html = get_content(url)
+        title = match1(html, r'<h1>(.+)</h1>')
+        src = match1(html, r'src="http://player.kankanews.com/embed/([^"]+)"')
+        frame_url = 'http://player.kankanews.com/embed/' + src
+        frame_html = get_content(frame_url)
+        url = match1(frame_html, r'var mp4 = "([^"]+)"')
+        _, 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.eastmoney.com"
+download = eastmoney_download
+download_playlist = playlist_not_supported('eastmoney')