add support for Douban, fix #112

README.md

@@ -26,6 +26,7 @@ Fork me on GitHub: <https://github.com/soimort/you-get>
 * AcFun <http://www.acfun.tv>
 * bilibili <http://www.bilibili.tv>
 * CNTV (中国网络电视台) <http://www.cntv.cn>
+* Douban (豆瓣) <http://douban.com>
 * ifeng (凤凰视频) <http://v.ifeng.com>
 * iQIYI (爱奇艺) <http://www.iqiyi.com>
 * Joy.cn (激动网) <http://www.joy.cn>
@@ -203,7 +204,7 @@ You-Get基于优酷下载脚本[iambus/youku-lixian](https://github.com/iambus/y
 
 ### 支持的站点（截至目前）
 
-已实现对以下视频站点的支持，以后会陆续增加（・∀・）
+已实现对以下站点的支持，以后会陆续增加（・∀・）
 
 * YouTube <http://www.youtube.com>
 * Vimeo <http://vimeo.com>
@@ -221,6 +222,7 @@ You-Get基于优酷下载脚本[iambus/youku-lixian](https://github.com/iambus/y
 * AcFun <http://www.acfun.tv>
 * bilibili <http://www.bilibili.tv>
 * CNTV <http://www.cntv.cn>
+* 豆瓣 <http://douban.com>
 * 凤凰视频 <http://v.ifeng.com>
 * 爱奇艺 <http://www.iqiyi.com>
 * 激动网 <http://www.joy.cn>

README.txt

@@ -29,6 +29,7 @@ Supported Sites (As of Now)
 * AcFun http://www.acfun.tv
 * bilibili http://www.bilibili.tv
 * CNTV (中国网络电视台) http://www.cntv.cn
+* Douban (豆瓣) http://douban.com
 * ifeng (凤凰视频) http://v.ifeng.com
 * iQIYI (爱奇艺) http://www.iqiyi.com
 * Joy.cn (激动网) http://www.joy.cn

src/you_get/__main__.py

@@ -24,6 +24,7 @@ def url_to_module(url):
         'bilibili': bilibili,
         'cntv': cntv,
         'dailymotion': dailymotion,
+        'douban': douban,
         'facebook': facebook,
         'google': googleplus,
         'iask': sina,

src/you_get/downloader/__init__.py

@@ -4,6 +4,7 @@ from .acfun import *
 from .bilibili import *
 from .cntv import *
 from .dailymotion import *
+from .douban import *
 from .facebook import *
 from .googleplus import *
 from .ifeng import *

src/you_get/downloader/douban.py

@@ -0,0 +1,25 @@
+#!/usr/bin/env python
+
+__all__ = ['douban_download']
+
+from ..common import *
+
+def douban_download(url, output_dir = '.', merge = True, info_only = False):
+    html = get_html(url)
+    
+    titles = re.findall(r'"name":"([^"]*)"', html)
+    real_urls = [re.sub('\\\\/', '/', i) for i in re.findall(r'"rawUrl":"([^"]*)"', html)]
+    
+    for i in range(len(titles)):
+        title = titles[i]
+        real_url = real_urls[i]
+        
+        type, ext, size = url_info(real_url)
+        
+        print_info(site_info, title, type, size)
+        if not info_only:
+            download_urls([real_url], title, ext, size, output_dir, merge = merge)
+
+site_info = "Douban.com"
+download = douban_download
+download_playlist = playlist_not_supported('douban')

tests/test.py

@@ -33,6 +33,12 @@ class YouGetTests(unittest.TestCase):
         ]:
             url_to_module(url).download(url, info_only = True)
     
+    def test_douban(self):
+        for url in [
+            "http://site.douban.com/caofang/",
+        ]:
+            url_to_module(url).download(url, info_only = True)
+    
     def test_xiami(self):
         for url in [
             "http://www.xiami.com/song/1769835121",