JAVA parses docx documents to extract text and pictures

<dependency>
      <groupId>fr.opensagres.xdocreport</groupId>
      <artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
      <version>1.0.6</version>
  </dependency>

package docxAnalyze;

import java.io.*;
import java.util.List;

import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFPictureData;

public class Word {
    
    

    public static String textPath = "src/main/resources/test.txt";
    public static String docPath = "src/main/resources/test.docx";
    public static String imagePath = "src/main/resources/test.docx";

    public static void main(String args[]) {
    
    
        readDocxTextAndImage();
    }

    public static String readDocxTextAndImage() {
    
    

        File file = new File(docPath);
        try {
    
    
            // 用XWPFWordExtractor来获取文字
            FileInputStream fis = new FileInputStream(file);
            XWPFDocument document = new XWPFDocument(fis);
            XWPFWordExtractor xwpfWordExtractor = new XWPFWordExtractor(document);
            String text = xwpfWordExtractor.getText();
            System.out.println(text);
            //将获取到的文字存放到对应文件名中的txt文件中
            PrintStream ps = new PrintStream(textPath);
            ps.println(text);


            // 用XWPFDocument的getAllPictures来获取所有的图片
            List<XWPFPictureData> picList = document.getAllPictures();
            for (XWPFPictureData pic : picList) {
    
    
                byte[] bytev = pic.getData();
                // 大于1000bites的图片我们才弄下来，消除word中莫名的小图片的影响
                if (bytev.length > 300) {
    
    
                    FileOutputStream fos = new FileOutputStream(imagePath + pic.getFileName());
                    fos.write(bytev);
                }
            }
            fis.close();
            return text;
        } catch (IOException e) {
    
    
            e.printStackTrace();
        }
        return null;
    }
}

You can see that the bodyelements object in a document object stores the content of the entire docx document. Other objects are to make statistics on each object of the document document.

word document content

Analysis effect