Designer or Developer. What should i call myself?

非常的感谢那些在我学习过程中遇到问题而帮助我的朋友，目前本站已经升级完毕，从之前的使用ASP升级到了ASP.NET，网站采用DIV+CSS框架开发，兼容FF和IE6（其它浏览器未作测试），并且整个版面进行了重新排版，增加了文章留言功能，还有一件值得高兴的事是本站通过了W3C的验证，欢迎大家踊跃的发表评论，想交换友情连接的朋友请PM我。——2008-8-30.by.teamwei

ASP.NET过滤HTML标签的几个函数 来源：网络

——2009/7/5 0:34:09.by.TeamWei

/**/
///   <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

文章留言

Name：
HomePage：
QQ：
Email：
Comment：
验证码 您还未登陆哦。