Go homepage(回首页) Upload pictures (上传图片) Write articles (发文字帖)
The author:(作者)归海一刀published in(发表于) 2014/1/30 1:32:03 去除正文中的html标记,但是又想保留其中的<br>_[Asp.Net教程]
先把 替换成别的,然后去掉html的tag,再把 替换回来。
/// /// 去除HTML标记 方法(1)/// /// 包括HTML的源码
/// 已经去除后的文字 public static string NoHTML(string Htmlstring){//删除脚本
Htmlstring = Regex.Replace(Htmlstring,@"","",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;}
/// /// 去除HTML标记 方法(2)///
public static string ParseTags(string HTMLStr) { return System.Text.RegularExpressions.Regex.Replace(HTMLStr, "<[^>]*>", ""); }
赞