VB用正则表达式提取网页中的链接

VBScript code

  

   <!---->
    
   Function
    getUrl(MatchStr 
   As
    
   String
   ) 
   As
    
   String
    
   Dim
    myReg 
   As
    RegExp 
   Dim
    Matches 
   As
    MatchCollection 
   Dim
    myMatch 
   As
    Match 
   Dim
    strtmp 
   As
    
   String
    
   Dim
    strimg 
   As
    
   String
    
   Set
    myReg 
   =
    
   New
    RegExp 
   With
    myReg .IgnoreCase 
   =
    
   True
    .Global 
   =
    
   True
    .Pattern 
   =
    
   "
   http://.+?\s
   "
    
   '
   取出里面的地址
    
   Set
    Matches 
   =
    .Execute(MatchStr) 
   End
    
   With
    
   For
    
   Each
    myMatch In Matches 
   If
    
   Right
   (myMatch.Value, 
   2
   ) 
   =
    
   "
   "" 
   "
    
   Then
    strtmp 
   =
    strtmp 
   &
    
   Left
   (myMatch.Value, 
   Len
   (myMatch.Value) 
   -
    
   2
   ) 
   &
    vbCrLf 
   Else
    strtmp 
   =
    strtmp 
   &
    
   Left
   (myMatch.Value, 
   Len
   (myMatch.Value) 
   -
    
   1
   ) 
   &
    vbCrLf 
   End
    
   If
    
   Next
    getUrl 
   =
    strtmp 
   End Function
    
  

VBScript code

  

   <!---->
    
   Sub
    GetURL(ByVal s 
   As
    
   String
   ) 
   Dim
    re 
   As
    RegExp 
   Dim
    mh 
   As
    Match 
   Dim
    mhs 
   As
    MatchCollection 
   Set
    re 
   =
    
   New
    RegExp re.Global 
   =
    
   True
    re.Pattern 
   =
    
   "
   href= ""(http(s)?://[\s\S]+?)""
   "
    
   If
    re.Test(s) 
   =
    
   False
    
   Then
    
   Exit
    
   Sub
    
   Set
    mhs 
   =
    re.Execute(s) 
   For
    
   Each
    mh In mhs Debug.Print mh.SubMatches(
   0
   ) 
   Next
    
   End Sub
    
  

用正则的方法就是这样，正则的Pattern写法我也初学，如何写更加精确，可以上网搜索。
上面的代码根据你的示例可以测试通过