C#从HTML代码中提取文本内容

发布于:2014年10月08日    浏览:1514 次    属于:软件开发 > C#程序开发 原创作者:张晓栋

 

从HTML代码中提取文本内容,常用作截取文章内容做摘要,本方法只要传入string类型的HTML编码即可处理并返回HTML中的文本内容,筛选掉所有的HTML标记。


    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;

    }