用C#去除字符串中HTML的格式(清除数据库中html标签)

出自:http://blog.csdn.net/savagelin/article/details/6604884

http://www.cnblogs.com/sophist/archive/2011/05/12/2044380.html

(1)方法一:

public static string DelHTML(string Htmlstring)//将HTML去除
{      
             #region
             //删除脚本

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             //删除HTML

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<(.[^>]*)>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"([\r\n])[\s]+","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"-->","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<!--.*","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
            
             //Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<A>.*</A>","");
        
             //Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=\.[a-zA-Z]*\?[a-zA-Z]+=\d&\w=%[a-zA-Z]*|[A-Z0-9]","");

                        

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(quot|#34);","\"",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(amp|#38);","&",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(lt|#60);","<",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(gt|#62);",">",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(nbsp|#160);"," ",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(iexcl|#161);","\xa1",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring,@"&(cent|#162);","\xa2",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(pound|#163);","\xa3",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(copy|#169);","\xa9",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

             Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring, @"&#(\d+);","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);

            
             Htmlstring.Replace("<","");

             Htmlstring.Replace(">","");

             Htmlstring.Replace("\r\n","");

             #endregion

             return Htmlstring;
}
(2) 简易代码:

public string NoHtml(string html)
{
    string StrNohtml = System.Text.RegularExpressions.Regex.Replace(html, "<[^>]+>", "");
    StrNohtml = System.Text.RegularExpressions.Regex.Replace(StrNohtml, "&[^;]+;", "");
    return StrNohtml;
}
(3) 功能增强代码:

public string NoHTML(string Htmlstring)  //替换HTML标记
{
    //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 = Regex.Replace(Htmlstring, @"<img[^>]*>;", "", RegexOptions.IgnoreCase);
    Htmlstring.Replace("<", "");
    Htmlstring.Replace(">", "");
    Htmlstring.Replace("\r\n", "");
    Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
    return Htmlstring;
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值