zoukankan      html  css  js  c++  java
  • 删除脚本 删除HTML标签的方法

     1      public static String RMHTML(String Htmlstring)
     2         {
     3 
     4             // 删除脚本
     5 
     6             Htmlstring = RegexPattern("<\\s*?script[^>]*>[\\s\\S]*?<\\s*?/\\s*?script\\s*?>", "", Htmlstring);
     7 
     8             // 删除HTML
     9 
    10             Htmlstring = RegexPattern("<([^>]*)>", "", Htmlstring);
    11 
    12             Htmlstring = RegexPattern("([\r\n])[\\s]+", "", Htmlstring);
    13 
    14             Htmlstring = RegexPattern("-->", "", Htmlstring);
    15 
    16             Htmlstring = RegexPattern("<!--.*", "", Htmlstring);
    17 
    18             Htmlstring = RegexPattern("&(quot|#34);", "\"", Htmlstring);
    19 
    20             Htmlstring = RegexPattern("&(amp|#38);", "&", Htmlstring);
    21 
    22             Htmlstring = RegexPattern("&(lt|#60);", "<", Htmlstring);
    23 
    24             Htmlstring = RegexPattern("&(gt|#62);", ">", Htmlstring);
    25 
    26             Htmlstring = RegexPattern("&(nbsp|#160);", " ", Htmlstring);
    27 
    28             Htmlstring = RegexPattern("&(iexcl|#161);", "\\xa1", Htmlstring);
    29 
    30             Htmlstring = RegexPattern("&(cent|#162);", "\\xa2", Htmlstring);
    31 
    32             Htmlstring = RegexPattern("&(pound|#163);", "\\xa3", Htmlstring);
    33 
    34             Htmlstring = RegexPattern("&(copy|#169);", "\\xa9", Htmlstring);
    35 
    36             Htmlstring = RegexPattern("&#(\\d+);", "", Htmlstring);
    37 
    38             Htmlstring = RegexPattern("<", "", Htmlstring);
    39 
    40             Htmlstring = RegexPattern(">", "", Htmlstring);
    41 
    42             //Htmlstring.replace("\r\n", "",Htmlstring);
    43 
    44 
    45 
    46             return Htmlstring;
    47 
    48         }
    49         public static String RegexPattern(String pattern, String str, String content)
    50         {
    51 
    52             if (pattern != null && !pattern.Equals(""))
    53             {
    54                 //RegexOptions p = System.Text.RegularExpressions.RegexOptions.Compiled(pattern, 2); //参数2表示大小写不区分
    55                 //Math m = (content);
    56                 //content = m.replaceAll(str);
    57                 content = Regex.Replace(content, pattern, str, RegexOptions.IgnoreCase);
    58             }
    59             return content;
    60         } 

    本文来自博客园,作者:mushishi,转载请注明原文链接:https://www.cnblogs.com/mushishi/archive/2013/05/31/3110005.html

  • 相关阅读:
    2019-1-7 水晶报表
    2018-12-25工作记录 空白行===水晶报表
    2018-7-26-随笔-泛型
    2018-7-20-随笔-转换
    2018-7-18-随笔-接口
    2018-7-17-随笔-params和ref、out用法、事件访问器
    VPS安装metasploit-framework
    Mimiktaz抓取本机密码
    msfvenom生成各类Payload命令
    docker容器开启ssh远程登录
  • 原文地址:https://www.cnblogs.com/mushishi/p/3110005.html
Copyright © 2011-2022 走看看