文本过滤

其他 2019-04-03 18:13:21 阅读次数: 0
版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/grq15203514615/article/details/81905278 
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class DelHtmlTagUtils {

    // 普通输入框的过滤
    public static String delHTMLTag(String htmlStr) {
        if (htmlStr != null && htmlStr.length() > 0) {
            String regExscript = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式
            String regExstyle = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式
            String regExHtml = "&lt;script.*?&gt;.*?&lt;/script&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml1 = "&lt;script.*?&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml2 = "&lt;/script&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml3 = "script"; // 定义转义后script标签的正则表达式
            String regExHtml4 = "javascript";
            String regExHtml5 = "eval\\((.*)\\)";
            String regExHtml6 = "<[^>]+>";
            String regExHtml7 = "<>";
            String regExHtml8 = "src[\r\n]*=[\r\n]*\\\'(.*?)\\\'";
            String regExHtml10 = "&lt;[^>]*on.*?&gt;";
            String regExHtml11 = "&lt;/[^>]*on.*&gt;";
            String regExHtml13 = "<a[^>]*?>[\\s\\S]*?<\\/a>";
            String regExHtml14 = "<iframe[^>]*?>[\\s\\S]*?<\\/iframe>";
            String regExHtml15 = "&lt;a.*?&gt;.*?&lt;/a&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml16 = "&lt;iframe.*?&gt;.*?&lt;/iframe&gt;";
            // String reg = "select|update|and|delete|insert|trancate|char|into|substr|ascii"
            // + "|declare|exec|count|master|into|drop|execute|sleep|ELT|extractvalue"
            // + "|concat|procedure|analyse|EXP|XML|MAKE_SET";
            String reg = " (?:')|(?:--)|(/\\*(?:.|[\\n\\r])*?\\*/)|"
                    + "(\\b(select|update|sleep|delete|insert|truncate|substr"
                    + "|ascii|declare|exec|drop|execute"
                    + "|ELT|concat|procedure|analyse|EXP|XML|MAKE_SET)\\b)";

            Pattern pScript = Pattern.compile(regExscript, Pattern.CASE_INSENSITIVE);
            Matcher mScript = pScript.matcher(htmlStr);
            htmlStr = mScript.replaceAll(""); // 过滤

            Pattern pStyle = Pattern.compile(regExstyle, Pattern.CASE_INSENSITIVE);
            Matcher mStyle = pStyle.matcher(htmlStr);
            htmlStr = mStyle.replaceAll(""); // 过滤style标签

            Pattern pHtml = Pattern.compile(regExHtml, Pattern.CASE_INSENSITIVE);
            Matcher mHtml = pHtml.matcher(htmlStr);
            htmlStr = mHtml.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml1 = Pattern.compile(regExHtml1, Pattern.CASE_INSENSITIVE);
            Matcher mHtml1 = pHtml1.matcher(htmlStr);
            htmlStr = mHtml1.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml2 = Pattern.compile(regExHtml2, Pattern.CASE_INSENSITIVE);
            Matcher mHtml2 = pHtml2.matcher(htmlStr);
            htmlStr = mHtml2.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml3 = Pattern.compile(regExHtml3, Pattern.CASE_INSENSITIVE);
            Matcher mHtml3 = pHtml3.matcher(htmlStr);
            htmlStr = mHtml3.replaceAll(""); // 过滤script标签

            Pattern pHtml4 = Pattern.compile(regExHtml4, Pattern.CASE_INSENSITIVE);
            Matcher mHtml4 = pHtml4.matcher(htmlStr);
            htmlStr = mHtml4.replaceAll(""); // 过滤javascript标签

            Pattern pHtml5 = Pattern.compile(regExHtml5, Pattern.CASE_INSENSITIVE);
            Matcher mHtml5 = pHtml5.matcher(htmlStr);
            htmlStr = mHtml5.replaceAll(""); // 过滤eval标签

            Pattern pHtml6 = Pattern.compile(regExHtml6, Pattern.CASE_INSENSITIVE);
            Matcher mHtml6 = pHtml6.matcher(htmlStr);
            htmlStr = mHtml6.replaceAll(""); // 过滤html标签

            Pattern pHtml7 = Pattern.compile(regExHtml7, Pattern.CASE_INSENSITIVE);
            Matcher mHtml7 = pHtml7.matcher(htmlStr);
            htmlStr = mHtml7.replaceAll(""); // 过滤html标签

            Pattern pHtml8 = Pattern.compile(regExHtml8, Pattern.CASE_INSENSITIVE);
            Matcher mHtml8 = pHtml8.matcher(htmlStr);
            htmlStr = mHtml8.replaceAll(""); // 过滤html标签

            Pattern pHtml10 = Pattern.compile(regExHtml10, Pattern.CASE_INSENSITIVE);
            Matcher mHtml10 = pHtml10.matcher(htmlStr);
            htmlStr = mHtml10.replaceAll("");

            Pattern pHtml11 = Pattern.compile(regExHtml11, Pattern.CASE_INSENSITIVE);
            Matcher mHtml11 = pHtml11.matcher(htmlStr);
            htmlStr = mHtml11.replaceAll("");

            Pattern pHtml13 = Pattern.compile(regExHtml13, Pattern.CASE_INSENSITIVE);
            Matcher mHtml13 = pHtml13.matcher(htmlStr);
            htmlStr = mHtml13.replaceAll("");

            Pattern pHtml14 = Pattern.compile(regExHtml14, Pattern.CASE_INSENSITIVE);
            Matcher mHtml14 = pHtml14.matcher(htmlStr);
            htmlStr = mHtml14.replaceAll("");

            Pattern pHtml15 = Pattern.compile(regExHtml15, Pattern.CASE_INSENSITIVE);
            Matcher mHtml15 = pHtml15.matcher(htmlStr);
            htmlStr = mHtml15.replaceAll("");

            Pattern pHtml16 = Pattern.compile(regExHtml16, Pattern.CASE_INSENSITIVE);
            Matcher mHtml16 = pHtml16.matcher(htmlStr);
            htmlStr = mHtml16.replaceAll("");

            Pattern pHtml17 = Pattern.compile(reg, Pattern.CASE_INSENSITIVE);
            Matcher mHtml17 = pHtml17.matcher(htmlStr);
            htmlStr = mHtml17.replaceAll("");

            return htmlStr.trim(); // 返回文本字符串
        } else {
            return htmlStr;
        }

    }

    // 富文本框的过滤
    public static String delHTMLTag2(String htmlStr) {
        if (htmlStr != null && htmlStr.length() > 0) {
            String regExscript = "<script[^>]*?>[\\s\\S]*?<\\/script>"; // 定义script的正则表达式
            String regExstyle = "<style[^>]*?>[\\s\\S]*?<\\/style>"; // 定义style的正则表达式
            String regExHtml = "&lt;script.*?&gt;.*?&lt;/script&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml1 = "&lt;script.*?&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml2 = "&lt;/script&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml3 = "script"; // 定义转义后script标签的正则表达式
            String regExHtml4 = "javascript";
            String regExHtml5 = "eval\\((.*)\\)";
            String regExHtml6 = "&lt;[^>]*java.*?&gt;";
            String regExHtml7 = "&lt;/[^>]*java.*?&gt;";
            String regExHtml8 = "<on[^>]*?>[\\s\\S]*?<\\/on>";
            String regExHtml9 = "<java[^>]*?>[\\s\\S]*?<\\/java>";
            String regExHtml10 = "&lt;[^>]*on.*?&gt;";
            String regExHtml11 = "&lt;/[^>]*on.*&gt;";
            String regExHtml12 = "&lt;java.*?&gt;.*?&lt;/java&gt;";
            String regExHtml13 = "<a[^>]*?>[\\s\\S]*?<\\/a>";
            String regExHtml14 = "<iframe[^>]*?>[\\s\\S]*?<\\/iframe>";
            String regExHtml15 = "&lt;a.*?&gt;.*?&lt;/a&gt;"; // 定义转义后script标签的正则表达式
            String regExHtml16 = "&lt;iframe.*?&gt;.*?&lt;/iframe&gt;";

            Pattern pScript = Pattern.compile(regExHtml9, Pattern.CASE_INSENSITIVE);
            Matcher mScript = pScript.matcher(htmlStr);
            htmlStr = mScript.replaceAll(""); // 过滤

            Pattern pStyle = Pattern.compile(regExstyle, Pattern.CASE_INSENSITIVE);
            Matcher mStyle = pStyle.matcher(htmlStr);
            htmlStr = mStyle.replaceAll(""); // 过滤style标签

            Pattern pHtml = Pattern.compile(regExHtml, Pattern.CASE_INSENSITIVE);
            Matcher mHtml = pHtml.matcher(htmlStr);
            htmlStr = mHtml.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml1 = Pattern.compile(regExHtml1, Pattern.CASE_INSENSITIVE);
            Matcher mHtml1 = pHtml1.matcher(htmlStr);
            htmlStr = mHtml1.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml2 = Pattern.compile(regExHtml2, Pattern.CASE_INSENSITIVE);
            Matcher mHtml2 = pHtml2.matcher(htmlStr);
            htmlStr = mHtml2.replaceAll(""); // 过滤转义后script标签

            Pattern pHtml3 = Pattern.compile(regExHtml3, Pattern.CASE_INSENSITIVE);
            Matcher mHtml3 = pHtml3.matcher(htmlStr);
            htmlStr = mHtml3.replaceAll(""); // 过滤script标签

            Pattern pHtml4 = Pattern.compile(regExHtml4, Pattern.CASE_INSENSITIVE);
            Matcher mHtml4 = pHtml4.matcher(htmlStr);
            htmlStr = mHtml4.replaceAll(""); // 过滤javascript标签

            Pattern pHtml5 = Pattern.compile(regExHtml5, Pattern.CASE_INSENSITIVE);
            Matcher mHtml5 = pHtml5.matcher(htmlStr);
            htmlStr = mHtml5.replaceAll(""); // 过滤eval标签

            Pattern pHtml6 = Pattern.compile(regExHtml6, Pattern.CASE_INSENSITIVE);
            Matcher mHtml6 = pHtml6.matcher(htmlStr);
            htmlStr = mHtml6.replaceAll(""); // 过滤转义后的javascript标签

            Pattern pHtml7 = Pattern.compile(regExHtml7, Pattern.CASE_INSENSITIVE);
            Matcher mHtml7 = pHtml7.matcher(htmlStr);
            htmlStr = mHtml7.replaceAll(""); // 过滤转义后的javascript标签

            Pattern pHtml8 = Pattern.compile(regExHtml8, Pattern.CASE_INSENSITIVE);
            Matcher mHtml8 = pHtml8.matcher(htmlStr);
            htmlStr = mHtml8.replaceAll(""); // 过滤on标签

            Pattern pHtml9 = Pattern.compile(regExscript, Pattern.CASE_INSENSITIVE);
            Matcher mHtml9 = pHtml9.matcher(htmlStr);
            htmlStr = mHtml9.replaceAll("");

            Pattern pHtml10 = Pattern.compile(regExHtml10, Pattern.CASE_INSENSITIVE);
            Matcher mHtml10 = pHtml10.matcher(htmlStr);
            htmlStr = mHtml10.replaceAll("");

            Pattern pHtml11 = Pattern.compile(regExHtml11, Pattern.CASE_INSENSITIVE);
            Matcher mHtml11 = pHtml11.matcher(htmlStr);
            htmlStr = mHtml11.replaceAll("");

            Pattern pHtml12 = Pattern.compile(regExHtml12, Pattern.CASE_INSENSITIVE);
            Matcher mHtml12 = pHtml12.matcher(htmlStr);
            htmlStr = mHtml12.replaceAll("");

            Pattern pHtml13 = Pattern.compile(regExHtml13, Pattern.CASE_INSENSITIVE);
            Matcher mHtml13 = pHtml13.matcher(htmlStr);
            htmlStr = mHtml13.replaceAll("");

            Pattern pHtml14 = Pattern.compile(regExHtml14, Pattern.CASE_INSENSITIVE);
            Matcher mHtml14 = pHtml14.matcher(htmlStr);
            htmlStr = mHtml14.replaceAll("");

            Pattern pHtml15 = Pattern.compile(regExHtml15, Pattern.CASE_INSENSITIVE);
            Matcher mHtml15 = pHtml15.matcher(htmlStr);
            htmlStr = mHtml15.replaceAll("");

            Pattern pHtml16 = Pattern.compile(regExHtml16, Pattern.CASE_INSENSITIVE);
            Matcher mHtml16 = pHtml16.matcher(htmlStr);
            htmlStr = mHtml16.replaceAll("");

            return htmlStr.trim(); // 返回文本字符串
        } else {
            return htmlStr;
        }

    }
}


    /**
     * 防xss漏洞参数处理
     * 
     * @param param
     * @return
     */
    public String dealParamsForXss(String param) {
        if (param == null) {
            return null;
        }
        return param.replaceAll("<", " &lt;").replaceAll(">", "    &gt;").replaceAll("\"", "&quot;")
                .replaceAll("'", "&apos;").replaceAll("&", "&amp;");
    }

猜你喜欢

转载自blog.csdn.net/grq15203514615/article/details/81905278
今日推荐
开源日报 | Chrome内置Gemini的意义不在于Gemini；中国AI追随之路的五大误区；ECharts创始人“下海”养鱼；谷歌I/O开发者大会什么都有，只是没有惊喜
微软回应中国区AI团队“打包赴美”传闻
基于大语言模型的开源知识库问答系统 MaxKB GitHub Star 数量突破 5,000 个！
美国拟限制 AI 大模型出口中国和俄罗斯
苹果将与 OpenAI 达成协议，将 ChatGPT 应用于 iPhone
openKylin 社区生态委员会第六次会议圆满召开
阿里云正式发布通义千问 2.5
Python 3.13 发布首个 Beta：实验性自由线程模式和 JIT、改进交互式解释器
Stack Overflow 拿我的代码去训练 AI 大模型，还封了我的账号
Pop!_OS 的 COSMIC 桌面完成 App Store 上架工作
《2024 年一季度互联网投融资运行情况》研究报告
报告：Django 仍然是 74% 开发者的首选
周排行
laravle中orm简单的增删改查
文本分类 特征选取之CHI开方检验
Spark核心编程-WordCount
大数据开发实战系列之电信客服(1)
读书笔记 - 把时间当作朋友 by 李笑来
python 笔记--if else
SpringBoot/Mybatis/Druid, 多数据源MultiDataSource配置思路
排序三个整数
redis集群搭建【2】-Windows中Redis集群搭建
STM32F030驱动TM1650点亮4联数码管
每日归档
更多
2024-05-16(6)
2024-05-15(24)
2024-05-14(0)
2024-05-13(18)
2024-05-12(0)
2024-05-11(38)
2024-05-10(38)
2024-05-09(35)
2024-05-08(42)
2024-05-07(14)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022