[转]C#字符串去除html格式

转自：http://www.cnblogs.com/grokyao/archive/2008/12/04/1347512.html

    在使用Freetextbox等流行编辑器后获得的文字内容里会掺杂着一些html标记，有时会需要将它们处理掉，这里给出处理的方法，使用了正则表达式进行规则过滤，由于html标记都是基于<>这种格式，而且还有类似&nbsp;这样的符号，所以分了2次处理将字符串处理为无html格式的字符串。

 简易代码：

string html = @"<span lang="EN-US">&rdquo;</span>，用户可以随时接收喜欢的视频电视内容。<span lang="EN-US"><a target="_blank" href="http://info.tele.hc360.com/list/mobile.shtml"><span lang="EN-US"><span lang="EN-US">手机</span></span></a></span>"; 

string StrNohtml = System.Text.RegularExpressions.Regex.Replace(html, "<[^>]+>", ""); 

StrNohtml=System.Text.RegularExpressions.Regex.Replace(StrNohtml, "&[^;]+;", ""); 

Console.WriteLine(StrNohtml);

 

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;
}