add support for Baidu Wangpan, fix #177

README.md

@@ -47,7 +47,8 @@ Fork me on GitHub: <https://github.com/soimort/you-get>
 * Sohu (搜狐视频) <http://tv.sohu.com>
 * 56 (56网) <http://www.56.com>
 * Xiami (虾米) <http://www.xiami.com>
-* Baidu (百度音乐) <http://music.baidu.com>
+* Baidu Music (百度音乐) <http://music.baidu.com>
+* Baidu Wangpan (百度网盘) <http://pan.baidu.com>
 * SongTaste <http://www.songtaste.com>
 
 ## Dependencies
@@ -264,6 +265,7 @@ You-Get基于优酷下载脚本[iambus/youku-lixian](https://github.com/iambus/y
 * 56网 <http://www.56.com>
 * 虾米 <http://www.xiami.com>
 * 百度音乐 <http://music.baidu.com>
+* 百度网盘 <http://pan.baidu.com>
 * SongTaste <http://www.songtaste.com>
 
 ## 依赖

README.txt

@@ -50,7 +50,8 @@ Supported Sites (As of Now)
 * Sohu (搜狐视频) http://tv.sohu.com
 * 56 (56网) http://www.56.com
 * Xiami (虾米) http://www.xiami.com
-* Baidu (百度音乐) http://music.baidu.com
+* Baidu Music (百度音乐) http://music.baidu.com
+* Baidu Wangpan (百度网盘) http://pan.baidu.com
 * SongTaste http://www.songtaste.com
 
 Dependencies

src/you_get/common.py

@@ -136,7 +136,7 @@ def url_info(url, faker = False):
         type = None
         if headers['content-disposition']:
             try:
-                filename = parse.unquote(r1(r'filename="?(.+)"?', headers['content-disposition']))
+                filename = parse.unquote(r1(r'filename="?([^"]+)"?', headers['content-disposition']))
                 if len(filename.split('.')) > 1:
                     ext = filename.split('.')[-1]
                 else:

src/you_get/downloader/baidu.py

@@ -68,12 +68,25 @@ def baidu_download_album(aid, output_dir = '.', merge = True, info_only = False)
         track_nr += 1
 
 def baidu_download(url, output_dir = '.', stream_type = None, merge = True, info_only = False):
-
-    if re.match(r'http://music.baidu.com/album/\d+', url):
+    if re.match(r'http://pan.baidu.com', url):
+        html = get_html(url)
+        
+        title = r1(r'server_filename="([^"]+)"', html)
+        if len(title.split('.')) > 1:
+            title = ".".join(title.split('.')[:-1])
+        
+        real_url = r1(r'href="([^"]+)" id="downFileButtom"', html).replace('&', '&')
+        type, ext, size = url_info(real_url, faker = True)
+        
+        print_info(site_info, title, ext, size)
+        if not info_only:
+            download_urls([real_url], title, ext, size, output_dir, merge = merge)
+    
+    elif re.match(r'http://music.baidu.com/album/\d+', url):
         id = r1(r'http://music.baidu.com/album/(\d+)', url)
         baidu_download_album(id, output_dir, merge, info_only)
 
-    if re.match('http://music.baidu.com/song/\d+', url):
+    elif re.match('http://music.baidu.com/song/\d+', url):
         id = r1(r'http://music.baidu.com/song/(\d+)', url)
         baidu_download_song(id, output_dir, merge, info_only)