如何去掉HTML代码来获取纯文本？

2018-06-22 07:45:27来源：未知阅读 ()

public string TextNoHTML(string Htmlstring)
{
    //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);
    //替换掉 < 和 > 标记
    Htmlstring.Replace("<", "");
    Htmlstring.Replace(">", "");
    Htmlstring.Replace("/r/n", "");
    //返回去掉html标记的字符串
    return Htmlstring;
}

标签：

版权申明：本站文章部分自网络，如有侵权，请联系：west999com@outlook.com
特别注意：本站所有转载文章言论不代表本站观点，本站所提供的摄影照片，插画，设计作品，如需使用，请与原作者联系，版权归原作者所有