导出去html标签

adc-da-activiti/src/main/java/com/adc/da/common/TableToExcel.java

@@ -1,5 +1,6 @@
 package com.adc.da.common;
 
+import com.adc.da.utils.removeHtml.RemoveHtml;
 import org.apache.commons.beanutils.BeanUtils;
 import org.apache.poi.hssf.usermodel.HSSFCellStyle;
 import org.apache.poi.ss.usermodel.*;
@@ -93,6 +94,10 @@ public class TableToExcel {
                         if (!"commentText".equals(key)) {
                             try {
                                 Object val = BeanUtils.getProperty(t, key);
+                                val= RemoveHtml.getResultsFromHtml(String.valueOf(val));
+                                if ("null".equals(val)){
+                                    val="";
+                                }
                                 if (val instanceof Long) {
                                     dataRow.createCell(v++).setCellValue((Long) val);
                                 } else if (val instanceof Double) {

adc-da-slrs/src/main/java/com/adc/da/slrs/sarStandIdea/controller/SarPublicIdeaAllController.java

@@ -6,6 +6,7 @@ import com.adc.da.http.Result;
 import com.adc.da.slrs.sarStandIdea.dao.SarPublicIdeaAllDao;
 import com.adc.da.slrs.sarStandIdea.entity.*;
 import com.adc.da.slrs.sarStandIdea.service.Impl.SarPublicIdeaAllServiceImpl;
+import com.adc.da.utils.removeHtml.RemoveHtml;
 import com.alibaba.excel.EasyExcel;
 import com.alibaba.fastjson.JSON;
 import com.baomidou.mybatisplus.core.conditions.query.QueryWrapper;
@@ -140,8 +141,8 @@ public class SarPublicIdeaAllController extends BaseController<SarPublicIdeaAll>
                 if ("1".equals(type)) {
                     GetExcelDto2 getExcelDto = GetExcelDto2.builder()
                             .partCode(sarPublicIdeaAll.getPartCode())
-                            .oldText(sarPublicIdeaAll.getOldText())
-                            .newText(sarPublicIdeaAll.getNewText())
+                            .oldText(RemoveHtml.getResultsFromHtml(sarPublicIdeaAll.getOldText()))
+                            .newText(RemoveHtml.getResultsFromHtml(sarPublicIdeaAll.getNewText()))
                             .reason(sarPublicIdeaAll.getReason())
                             .userName(sarPublicIdeaAll.getUserName())
                             .deptName(sarPublicIdeaAll.getDeptName())
@@ -152,8 +153,8 @@ public class SarPublicIdeaAllController extends BaseController<SarPublicIdeaAll>
                 }else {
                     GetExcelDto getExcelDto = GetExcelDto.builder()
                             .partCode(sarPublicIdeaAll.getPartCode())
-                            .oldText(sarPublicIdeaAll.getOldText())
-                            .newText(sarPublicIdeaAll.getNewText())
+                            .oldText(RemoveHtml.getResultsFromHtml(sarPublicIdeaAll.getOldText()))
+                            .newText(RemoveHtml.getResultsFromHtml(sarPublicIdeaAll.getNewText()))
                             .reason(sarPublicIdeaAll.getReason())
                             .userName(sarPublicIdeaAll.getUserName())
                             .deptName(sarPublicIdeaAll.getDeptName())

adc-da-slrs/src/main/java/com/adc/da/utils/removeHtml/RemoveHtml.java

@@ -0,0 +1,100 @@
+package com.adc.da.utils.removeHtml;
+
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+public class RemoveHtml {
+
+
+    /**
+     * 匹配html标签，例如"<p>xxx</p>"这种格式
+     */
+    private static Pattern HTML_TAG_PATTERN = Pattern.compile("<[a-zA-Z]+.*?>([\\s\\S]*?)</[a-zA-Z]*?>");
+
+    /**
+     * 替换掉html标签里面的style内容
+     *
+     * @param content
+     * @return
+     */
+    public static String replaceStyle(String content) {
+        if (content == null || content.length() == 0) {
+            return content;
+        }
+        String regEx = " style=\"(.*?)\"";
+        Pattern p = Pattern.compile(regEx);
+        Matcher m = p.matcher(content);
+        if (m.find()) {
+            content = m.replaceAll("");
+        }
+        return content;
+    }
+
+
+    /**
+     * 移除掉</br>标签
+     *
+     * @param src
+     * @return
+     */
+    public static String removeBrTag(String src) {
+        if (src != null && !src.isEmpty()) {
+            src = src.replaceAll("<br/>", "");
+        }
+        return src;
+    }
+
+
+    /**
+     * 针对多个标签嵌套的情况进行处理
+     * 比如 <p><span style="white-space: normal;">王者荣耀</span></p>
+     * 预处理并且正则匹配完之后结果是 <span>王者荣耀
+     * 需要手工移除掉前面的起始标签
+     * @param content
+     * @return
+     */
+    public static String replaceStartTag(String content) {
+        if (content == null || content.length() == 0) {
+            return content;
+        }
+        String regEx = "<[a-zA-Z]*?>([\\s\\S]*?)";
+        Pattern p = Pattern.compile(regEx);
+        Matcher m = p.matcher(content);
+        if (m.find()) {
+            content = m.replaceAll("");
+        }
+        return content;
+    }
+
+
+
+    /**
+     * 获取html中的数据
+     * @param htmlStr
+     * @return
+     */
+    public static String getResultsFromHtml(String htmlStr) {
+        //定义script的正则表达式，去除js可以防止注入
+        String scriptRegex="<script[^>]*?>[\\s\\S]*?<\\/script>";
+        //定义style的正则表达式，去除style样式，防止css代码过多时只截取到css样式代码
+        String styleRegex="<style[^>]*?>[\\s\\S]*?<\\/style>";
+        //定义HTML标签的正则表达式，去除标签，只提取文字内容
+        String htmlRegex="<[^>]+>";
+        //定义空格,回车,换行符,制表符
+        String spaceRegex = "\\s*|\t|\r|\n";
+
+        // 过滤script标签
+        htmlStr = htmlStr.replaceAll(scriptRegex, "");
+        // 过滤style标签
+        htmlStr = htmlStr.replaceAll(styleRegex, "");
+        // 过滤html标签
+        htmlStr = htmlStr.replaceAll(htmlRegex, "");
+        // 过滤空格等
+        htmlStr = htmlStr.replaceAll(spaceRegex, "");
+        return htmlStr.trim(); // 返回文本字符串
+    }
+
+
+
+
+}