<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
html = html.replace(/ /, " " );
// 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;
}
/ 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
html = html.replace(/ /, " " );
// 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;
}
解决方案 »
- 求助各位帮帮忙!
- 在winServer2003上安装vs2008出现Runtime to terminate it in an unusual way
- SQL 2005中一个表里删除记录的同时把这条记录插入到另外一个历史记录表中,该怎么做??
- 这是要逆天啊。。。。。浏览器不兼容的一个问题
- 急急急,怎么在事件里动态调用已定义的方法
- 关于登录验证的问题
- 找不到可安装的 ISAM问题..在线等待
- 怎摸判断数据库中的值是否存在
- [求助]跟page_load有关的初学者的问题,动态下拉列表无法选值的问题(选了后再重新载入时又还原了)?
- showModalDialog和TreeView的结合问题
- 一次HTTP请求,在请求中的内容全部到达服务器之前,服务器能处理吗
- 谁用过internetsecure这个支付接口啊。。。
/// 去除HTML标记
/// </summary>
/// <param name="Htmlstring"></param>
/// <returns></returns>
public static 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;
}
/// <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(" ", "").Replace("\n", "").Replace("\r", "");
}