正则表达式，去除所有HTML标签
2010-10-12 12:30 xchit 阅读(11224) 评论(0) 编辑 收藏 举报
string str = "<table><tr><td>sdasasdsdd</td></tr></table><br><p>sds</p><img id='img1' src='http://www.baidu.com/img/baidu_logo.gif' width='100' height='50' alt=''>aaassss<br><img src='http://www.baidu.com/img/baidu_logo.gif' width='100' height='50' alt=''> 说是道 ";
protected void Page_Load(object sender, EventArgs e)
{
//string regexstr = @"<[^>]*>"; //去除所有的标签
//@"<script[^>]*?>.*?</script>" //去除所有脚本，中间部分也删除
// string regexstr = @"<img[^>]*>"; //去除图片的正则
// string regexstr = @"<(?!br).*?>"; //去除所有标签，只剩br
// string regexstr = @"<table[^>]*?>.*?</table>"; //去除table里面的所有内容
string regexstr = @"<(?!img|br|p|/p).*?>"; //去除所有标签，只剩img,br,p
str = Regex.Replace(str, regexstr, string.Empty, RegexOptions.IgnoreCase);
}
ASP.NET 去除所有HTML标记 < type="text/javascript">function StorePage(){d=document;t=d.selection?(d.selection.type!='None'?d.selection.createRange().text:''):(d.getSelection?d.getSelection():'');void(keyit=window.open('http://www.365key.com/storeit.aspx?t='+escape(d.title)+'&u='+escape(d.location.href)+'&c='+escape(t),'keyit','scrollbars=no,width=475,height=575,left=75,top=20,status=no,resizable=yes'));keyit.focus();}
注意:需要先using System.Text.RegularExpressions;
/// <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*(([""'])(http://www.cnblogs.com/xchit/admin/file://[%22%22'tbnr]%7c[%5e/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
