过滤html

net过滤HTML标签
2009-05-12 23:33
/**/
///   <summary>
///   去除HTML标记
///   </summary>
///   <param   name="NoHTML">包括HTML的源码   </param>
///   <returns>已经去除后的文字</returns>
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "",
    RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", "   ",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9",
    RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "",
    RegexOptions.IgnoreCase);

Htmlstring.Replace("<", "");
Htmlstring.Replace(">", "");
Htmlstring.Replace("\r\n", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();

return Htmlstring;
}

/**/ ///提取HTML代码中文字的C#函数
///   <summary>
///   去除HTML标记
///   </summary>
///   <param   name="strHtml">包括HTML的源码   </param>
///   <returns>已经去除后的文字</returns>
using System;
using System.Text.RegularExpressions;
public class StripHTMLTest
{
public static void Main()
{
    string s = StripHTML(
      "<HTML><HEAD><TITLE>中国石龙信息平台</TITLE></HEAD><BODY>faddfs龙信息平台</BODY></HTML>");
    Console.WriteLine(s);
}

public static string StripHTML(string strHtml)
{
    string[]aryReg =
    {
      @"<script[^>]*?>.*?</script>",

      @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\["
        "'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", @"([\r\n])[\s]+", @
        "&(quot|#34);", @"&(amp|#38);", @"&(lt|#60);", @"&(gt|#62);", @
        "&(nbsp|#160);", @"&(iexcl|#161);", @"&(cent|#162);", @"&(pound|#163);",
        @"&(copy|#169);", @"&#(\d+);", @"-->", @"<!--.*\n"
    };

    string[]aryRep =
    {
      "", "", "", "\"", "&", "<", ">", "   ", "\xa1", //chr(161),
      "\xa2", //chr(162),
      "\xa3", //chr(163),
      "\xa9", //chr(169),
      "", "\r\n", ""
    };

    string newReg = aryReg[0];
    string strOutput = strHtml;
    for (int i = 0; i < aryReg.Length; i++)
    {
      Regex regex = new Regex(aryReg[i], RegexOptions.IgnoreCase);
      strOutput = regex.Replace(strOutput, aryRep[i]);
    }
    strOutput.Replace("<", "");
    strOutput.Replace(">", "");
    strOutput.Replace("\r\n", "");
    return strOutput;
}
}

写一个静态方法移除HTML标签
#region
///移除HTML标签
/**/ ///   <summary>
///   移除HTML标签
///   </summary>
///   <param   name="HTMLStr">HTMLStr</param>
public static string ParseTags(string HTMLStr)
{
return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", "");
}

#endregion
   
///   取出文本中的图片地址
#region
///   取出文本中的图片地址
/**/ ///   <summary>
///   取出文本中的图片地址
///   </summary>
///   <param   name="HTMLStr">HTMLStr</param>
public static string GetImgUrl(string HTMLStr)
{
string str = string.Empty;
string sPattern = @"^<img\s+[^>]*>";
Regex r = new Regex(@"<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>",
    RegexOptions.Compiled);
Match m = r.Match(HTMLStr.ToLower());
if (m.Success)
    str = m.Result("${url}");
return str;
}

#endregion

===========================================================

 ''' 去除HTML标记
        ''' </summary>
        ''' <param name="Htmlstring">包括HTML的源码 </param>
        ''' <returns>已经去除后的文字</returns>
        Public Shared Function NoHTML(ByVal Htmlstring As String) As String
            '删除脚本
            Htmlstring = Regex.Replace(Htmlstring, "<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase)
            '删除HTML
            Htmlstring = Regex.Replace(Htmlstring, "<(.[^>]*)>", "", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "([\r\n])[\s]+", "", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "-->", "", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "<!--.*", "", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(quot|#34);", """", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(amp|#38);", "&", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(lt|#60);", "<", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(gt|#62);", ">", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(nbsp|#160);", "   ", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(iexcl|#161);", "¡", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(cent|#162);", "¢", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(pound|#163);", "£", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&(copy|#169);", "©", RegexOptions.IgnoreCase)
            Htmlstring = Regex.Replace(Htmlstring, "&#(\d+);", "", RegexOptions.IgnoreCase)
            Htmlstring.Replace("<", "")
            Htmlstring.Replace(">", "")
            Htmlstring.Replace("" & Chr(13) & "" & Chr(10) & "", "")
            Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim()
            Return Htmlstring
        End Function

        '''提取HTML代码中文字的C#函数    
        '''   <summary>  
        '''   去除HTML标记  
        '''   </summary>  
        '''   <param   name="strHtml">包括HTML的源码   </param>  
        '''   <returns>已经去除后的文字</returns>  
        Public Shared Function StripHTML(ByVal strHtml As String) As String

            Dim aryReg As String() = {"<script[^>]*?>.*?</script>", "<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", "([\r\n])[\s]+", "&(quot|#34);", "&(amp|#38);", "&(lt|#60);", _
             "&(gt|#62);", "&(nbsp|#160);", "&(iexcl|#161);", "&(cent|#162);", "&(pound|#163);", "&(copy|#169);", _
             "&#(\d+);", "-->", "<!--.*\n"}

            'chr(161),  
            'chr(162),  
            'chr(163),  
            'chr(169),  
            Dim aryRep As String() = {"", "", "", """", "&", "<", _
             ">", "   ", "¡", "¢", "£", "©", _
             "", "" & Chr(13) & "" & Chr(10) & "", ""}

            Dim newReg As String = aryReg(0)
            Dim strOutput As String = strHtml
            For i As Integer = 0 To aryReg.Length - 1
                Dim regex As New Regex(aryReg(i), RegexOptions.IgnoreCase)
                strOutput = regex.Replace(strOutput, aryRep(i))
            Next
            strOutput.Replace("<", "")
            strOutput.Replace(">", "")
            strOutput.Replace("" & Chr(13) & "" & Chr(10) & "", "")
            Return strOutput
        End Function

        '''取出文本中的图片地址
        '''   <summary>
        '''   取出文本中的图片地址
        '''   </summary>
        '''   <param   name="HTMLStr">HTMLStr</param>
        Public Shared Function GetImgUrl(ByVal HTMLStr As String) As String
            Dim str As String = String.Empty
            Dim sPattern As String = "^<img\s+[^>]*>"
            Dim r As New Regex("<img\s+[^>]*\s*src\s*=\s*([']?)(?<url>\S+)'?[^>]*>", RegexOptions.Compiled)
            Dim m As Match = r.Match(HTMLStr.ToLower())
            If m.Success Then
                str = m.Result("${url}")
            End If
            Return str
        End Function

 

 

运用：
        str = Regex.Replace(str, "([\r\n])[\s]+", "", RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "</p>", Chr(13), RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "<(.[^>]*)>", "", RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "<br>", Chr(13), RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "<br/>", Chr(13), RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "&nbsp;", " ", RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "&lt;", "<", RegexOptions.IgnoreCase)
        str = Regex.Replace(str, "&gt;", ">", RegexOptions.IgnoreCase)

 

posted @ 2009-12-01 23:44  ggbbeyou  阅读(253)  评论(0)  编辑  收藏  举报