support multi video in one page

add matchall api

matchall: almost same as match1, but it will return a list
of all matches.

src/you_get/common.py

@@ -79,6 +79,24 @@ def match1(text, *patterns):
                 ret.append(match.group(1))
         return ret
 
+def matchall(text, patterns):
+    """Scans through a string for substrings matched some patterns.
+
+    Args:
+        text: A string to be scanned.
+        patterns: a list of regex pattern.
+
+    Returns:
+        a list if matched. empty if not.
+    """
+
+    ret = []
+    for pattern in patterns:
+        match = re.findall(pattern, text)
+        ret += match
+
+    return ret
+
 def launch_player(player, urls):
     import subprocess
     import shlex

src/you_get/extractors/embed.py

@@ -7,35 +7,42 @@ from .qq import qq_download_by_vid
 from .sina import sina_download_by_vid
 from .tudou import tudou_download_by_id
 from .youku import youku_download_by_vid
-from .youku import Youku
 
 """
 refer to http://open.youku.com/tools
 """
-youku_api_pattern = 'YKU.Player\(\'[a-zA-Z0-9]+\',{ client_id: \'[a-zA-Z0-9]+\', vid: \'([a-zA-Z0-9]+)\''
+youku_embed_patterns = [ 'youku\.com/v_show/id_([a-zA-Z0-9=]+)',
+                         'player\.youku\.com/player\.php/sid/([a-zA-Z0-9=]+)/v\.swf',
+                         'loader\.swf\?VideoIDS=([a-zA-Z0-9=]+)',
+                         'player\.youku\.com/embed/([a-zA-Z0-9=]+)',
+                         'YKU.Player\(\'[a-zA-Z0-9]+\',{ client_id: \'[a-zA-Z0-9]+\', vid: \'([a-zA-Z0-9]+)\''
+                       ]
+
 """
 http://www.tudou.com/programs/view/html5embed.action?type=0&code=3LS_URGvl54&lcode=&resourceId=0_06_05_99
 """
-tudou_embed_pattern = 'tudou\.com[a-zA-Z0-9\/\?=\&\.\;]+code=([[a-zA-Z0-9_]+)\&'
+tudou_embed_patterns = [ 'tudou\.com[a-zA-Z0-9\/\?=\&\.\;]+code=([[a-zA-Z0-9_]+)\&'
+                       ]
 
 """
 refer to http://open.tudou.com/wiki/video/info
 """
+tudou_api_patterns = [ ]
 
 def embed_download(url, output_dir = '.', merge = True, info_only = False ,**kwargs):
     content = get_content(url)
     found = False
     title = match1(content, '<title>([^<>]+)</title>')
-    vid = Youku.get_vid_from_url(content) or \
-          match1(content, youku_api_pattern)
-    if vid is not None:
+    vids = matchall(content, youku_embed_patterns)
+    for vid in vids:
         found = True
         youku_download_by_vid(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
 
-    vid = match1(content, tudou_embed_pattern)
-    if vid is not None:
+    vids = matchall(content, tudou_embed_patterns)
+    for vid in vids:
         found = True
         tudou_download_by_id(vid, title=title, output_dir=output_dir, merge=merge, info_only=info_only)
+
     if not found:
         raise NotImplementedError(url)