用C#去除字符串中HTML的格式(清除数据库中html标签)

来源：互联网发布：编程语言的都有啥编辑：程序博客网时间：2024/05/22 13:14

出自：http://blog.csdn.net/savagelin/article/details/6604884

http://www.cnblogs.com/sophist/archive/2011/05/12/2044380.html

（1）方法一：

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","");             #endregion             return Htmlstring;}

（2）简易代码：

public string NoHtml(string html){    string StrNohtml = System.Text.RegularExpressions.Regex.Replace(html, "<[^>]+>", "");    StrNohtml = System.Text.RegularExpressions.Regex.Replace(StrNohtml, "&[^;]+;", "");    return StrNohtml;}

（3）功能增强代码：

public 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;}

0 0