利用正则表达式除去html得到纯文本

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,@"<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,@"&(cent|#162);","xa2",@"&(pound|#163);","xa3",@"&(copy|#169);","xa9",@"&#(d+);",51); font-family:Arial; font-size:14px; line-height:26px">
Htmlstring.Replace("<",51); font-family:Arial; font-size:14px; line-height:26px"> Htmlstring.Replace(">",51); font-family:Arial; font-size:14px; line-height:26px"> Htmlstring.Replace("rn",51); font-family:Arial; font-size:14px; line-height:26px"> //Htmlstring=HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
#endregion

return Htmlstring;

}

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!