关于字符串操作小问题

ybblack001 2009-04-12 08:56:24

数据库储存一篇帖子的内容，可能有<b><a><img>等标记。我希望截取前200个字符，但不希望包含HTML元素以及元素中间的内容。应该怎么处理？

...全文

105 8 打赏收藏转发到动态举报

写回复

用AI写文章

8 条回复

切换为时间正序

请发表友善的回复…

发表回复

解释多余的 2009-04-12

打赏
举报

netwar 2009-04-12

打赏
举报

晕，用正则替换掉就可以了
String content="你的文章内容";
Strint pattern="<.*?>";
Regex reg=new Regex(pattern,RegexOptions.Ignorecase);
content=reg.Replace(content,"");

cao_love 2009-04-12

打赏
举报

学习,学习

felix3118 2009-04-12

打赏
举报

3楼正解。

LemIST 2009-04-12

打赏
举报

string htmlStr = "...";

            StringBuilder first200 = new StringBuilder();

            bool skip = false;

            foreach (char ch in htmlStr.ToCharArray())

            {

                switch (ch)

                {

                    case '<':

                        skip = true;

                        break;

                    case '>':

                        skip = false;

                        break;

                    default:

                        if (!skip)

                            first200.Append(ch);

                        break;



                }

                if (first200.Length >= 200)

                    break;

            }

claymore1114 2009-04-12

打赏
举报



public string NoHTML(string Htmlstring) //去除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.Replace(" <", "");

        Htmlstring.Replace(">", "");

        Htmlstring.Replace("\r\n", "");

        Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();



       return Htmlstring;

    }