想去掉除了段落标记之外的所有html标记,只要页面的文字,好比是我把代码贴到记事本里面的效果,去掉了链接等代码。 可以试试。
public static string DelHTML(string Htmlstring)//将HTML去除
{
#region
//删除脚本
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<script[^>]*?>.*?</script>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//删除HTML
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<(.[^>]*)>","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"([/r/n])[/s]+","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"-->","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<!--.*","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
//Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<A>.*</A>","");
//Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"<[a-zA-Z]*=/.[a-zA-Z]*/?[a-zA-Z]+=/d&/w=%[a-zA-Z]*|[A-Z0-9]","");
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(quot|#34);","/"",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(amp|#38);","&",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(lt|#60);","<",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(gt|#62);",">",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(nbsp|#160);"," ",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(iexcl|#161);","/xa1",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring = System.Text.RegularExpressions.Regex.Replace(Htmlstring,@"&(cent|#162);","/xa2",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(pound|#163);","/xa3",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring,@"&(copy|#169);","/xa9",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring =System.Text.RegularExpressions. Regex.Replace(Htmlstring, @"&#(/d+);","",System.Text.RegularExpressions.RegexOptions.IgnoreCase);
Htmlstring.Replace("<","");
Htmlstring.Replace(">","");
Htmlstring.Replace("/r/n","");
//Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
#endregion
return Htmlstring;
}
调用时传入原数据.返回的就是除去后的.
C#中利用正则表达式去除HTML中的格式
最新推荐文章于 2026-04-30 13:39:26 发布
本文介绍了一种使用C#编程语言去除HTML标签的方法,该方法通过正则表达式来清除HTML标签和特殊字符,保留纯文本内容。具体包括删除脚本、注释、特殊实体等,并替换了一些HTML实体为对应的字符。
4579

被折叠的 条评论
为什么被折叠?



