java docx根据标题读取标题中的内容

1.需要引入jar包

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.14</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.17</version>
</dependency>
<!--      docx生成html-->
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>org.apache.poi.xwpf.converter.core</artifactId>
    <version>1.0.5</version>
</dependency>
<!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/org.apache.poi.xwpf.converter.xhtml -->
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>
    <version>1.0.5</version>
</dependency>
<dependency>
    <groupId>org.apache.xmlbeans</groupId>
    <artifactId>xmlbeans</artifactId>
    <version>2.6.0</version>
</dependency>

2.对应代码

package com.sdyy.pd.duplicatecheck.common.utils.file;

/**
 * @Title word文档读取处理
 * @Desc
 * @Date 2020/5/19
 * @Author liuch
 **/

import com.sdyy.pd.duplicatecheck.common.utils.StringUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.poi.xwpf.usermodel.*;
import org.openxmlformats.schemas.wordprocessingml.x2006.main.*;

import java.io.*;
import java.math.BigInteger;
import java.util.HashMap;
import java.util.List;
import java.util.Map;


public class WordUtils {
    private static Map<String, Map<String, Object>> orderMap = new HashMap<String, Map<String, Object>>();
    // 日志记录器
    public final Log logger = LogFactory.getLog(this.getClass());

    public void init(String targetPath, String sourcePath) {
        InputStream is = null;
        XWPFDocument doc = null;
        OutputStream out = null;
        try {
            XWPFDocument createDoc = new XWPFDocument();

            is = new FileInputStream(sourcePath);
            doc = new XWPFDocument(is);
            //获取段落
            List<XWPFParagraph> paras = doc.getParagraphs();

            for (XWPFParagraph para : paras) {
                //             System.out.println(para.getCTP());//得到xml格式
                System.out.println(para.getStyleID());//段落级别
                System.out.println(para.getParagraphText());//段落内容

                String titleLvl = getTitleLvl(doc, para);//获取段落级别
                if ("a5".equals(titleLvl) || "HTML".equals(titleLvl) || "".equals(titleLvl) || null == titleLvl) {
                    titleLvl = "8";
                }
                System.out.println(titleLvl + "-----");//0,1,2
                if (!"8".equals(titleLvl)) {
                    System.out.println(titleLvl + "====" + para.getParagraphText());
                }


                XWPFParagraph ctPara = createDoc.createParagraph();
                //一个XWPFRun代表具有相同属性的一个区域。
                XWPFRun ctRun = ctPara.createRun();
                String ctText = para.getParagraphText();
                ctRun.setFontFamily("宋体");//字体
                ctRun.setFontSize(12);

                if (null != titleLvl && !"".equals(titleLvl) && !"8".equals(titleLvl)) {