广州.NET培训
达内广州.NET培训中心

18087159764

热门课程

用.net对HTML标签中的函数进行过滤

  • 时间:2015-11-19
  • 发布:dn
  • 来源:dn

using System;

using System.Data;
using System.Configuration;
using System.Web;
using System.Web.Security;
using System.Web.UI;
using System.Web.UI.WebControls;
using System.Web.UI.WebControls.WebParts;
using System.Web.UI.HtmlControls;
using System.Text.RegularExpressions;


/// <summary>
/// FiterHtml 的摘要说明
/// </summary>
public class FiterHtml
{
public FiterHtml() { }
///   <summary>
///   去除HTML标记
///   </summary>
public static string NoHTML(string Htmlstring)
{
//删除脚本
Htmlstring = Regex.Replace(Htmlstring, "<script[^>]*>[\s\S]*?</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;
}
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;
}
///   <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, "<[^>]*>", "");
}
///   <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;
}

}

上一篇:熟知asp.net 中Request的各种应
下一篇: .NET Core 和 ASP.Net 添加 'go live' 协议,用户可生产环境!

.NET对于新手该如何下手

电脑编程入门学什么?5分钟让你掌握core技术!

[达内知识].NET技巧集锦

选择城市和中心
贵州省

广西省

海南省