首页 诗词 字典 板报 句子 名言 友答 励志 学校 网站地图
当前位置: 首页 > 教程频道 > 网站开发 > asp.net >

正则表达式过滤标签解决方法

2012-09-28 
正则表达式过滤标签script/ 清除WORD冗余格式并粘贴function cleanAndPaste( html ) {// Remove all SPA

正则表达式过滤标签
<script>
/ 清除WORD冗余格式并粘贴
function cleanAndPaste( html ) {
 // Remove all SPAN tags
 html = html.replace(/<\/?SPAN[^>]*>/gi, "" );
 // Remove Class attributes
 html = html.replace(/<(\w[^>]*) class=([^ |>]*)([^>]*)/gi, "<$1$3") ;
 // Remove Style attributes
 html = html.replace(/<(\w[^>]*) style="([^"]*)"([^>]*)/gi, "<$1$3") ;
 // Remove Lang attributes
 html = html.replace(/<(\w[^>]*) lang=([^ |>]*)([^>]*)/gi, "<$1$3") ;
 // Remove XML elements and declarations
 html = html.replace(/<\\?\?xml[^>]*>/gi, "") ;
 // Remove Tags with XML namespace declarations: <o:p></o:p>
 html = html.replace(/<\/?\w+:[^>]*>/gi, "") ;
 // Replace the &nbsp;
 html = html.replace(/&nbsp;/, " " );
 // Transform <P> to <DIV>
 var re = new RegExp("(<P)([^>]*>.*?)(<\/P>)","gi") ; // Different because of a IE 5.0 error
 html = html.replace( re, "<div$2</div>" ) ;
 
 insertHTML( html ) ;
}
</script>

怎样用正则表达式在后台写这样一个清除WORD冗余格式并粘贴,类似一下代码,不知道正则怎么在里面写

public static string rep(string html)
  {
  System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" no[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase);
  html = regex1.Replace(html, ""); //过滤<script></script>标记
  html = regex2.Replace(html, ""); //过滤href=javascript: (<A>) 属性
  html = regex3.Replace(html, " _disibledevent="); //过滤其它控件的on...事件
  html = regex4.Replace(html, ""); //过滤iframe
  html = regex5.Replace(html, ""); //过滤frameset
  html = regex6.Replace(html, ""); //过滤frameset
  html = regex7.Replace(html, ""); //过滤frameset
  html = regex8.Replace(html, ""); //过滤frameset
  html = regex9.Replace(html, "");
  html = html.Replace(" ", "");


  html = html.Replace("</strong>", "");
  html = html.Replace("<strong>", "");
  html = html.Replace(@"\<img[^\>]+\>", "");
  html = html.Replace(@"<p>", "");
  html = html.Replace(@"</p>", "");
  return html;
  }

[解决办法]

探讨
怎样用正则表达式在后台写这样一个清除WORD冗余格式并粘贴,类似一下代码,不知道正则怎么在里面写

[解决办法]
C# code
/// <summary>    /// 去掉html标记    /// </summary>    /// <param name="str"></param>    /// <returns></returns>    protected static string ConvertGettext(string str)    {        Regex regex = new Regex(@"\<(.*?)\>", RegexOptions.IgnoreCase);        return regex.Replace(str, "").Replace("&nbsp;", "").Replace("\n", "").Replace("\r", "");    } 

热点排行