去除HTML标记修改p标签为br，修改br为br，保留img标签-优快云博客

本文分享了一段用于去除HTML标记的C#代码，该代码可以将p标签转换为br，保留img标签，并移除脚本和HTML标签，适用于从网页中提取纯文本的应用场景。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

贴上代码，自己看

网络上找的，自己做过一点修改，还是蛮不错的。

View Code

///<summary>   
///    去除HTML标记   修改p标签为br，修改br为br，保留img标签
///</summary>   
///<param    name="NoHTML">包括HTML的源码   </param>   
///<returns>已经去除后的文字</returns>
        public static string NoHTML(string Htmlstring)
        {


string[] img = GetIMG(Htmlstring);
for (int i = 0; i < img.Length; i++)
            {
if (img[i] == null)
break;
                Htmlstring=Htmlstring.Replace(img[i], "img无敌"+i);
            }
            Htmlstring = Htmlstring.Replace("</P>", "1234a3211");
            Htmlstring = Htmlstring.Replace("</p>", "1234a3211");
            Htmlstring = Htmlstring.Replace("<br/>", "1234a3211");
//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.Replace("<", "");
            Htmlstring.Replace(">", "");
            Htmlstring.Replace("\r\n", "");
            Htmlstring = Htmlstring.Replace("1234a3211", "<br/>");

for (int i = 0; i < img.Length; i++)
            {
if (img[i] == null)
break;
                Htmlstring = Htmlstring.Replace("img无敌" + i, img[i]);
            }

return Htmlstring;
        }