java PDF转word的初步实现

版权声明： https://blog.csdn.net/weixin_41722928/article/details/88656869

package com.springboot.springboot.util;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.Writer;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

public class Pdf2word {
    public static void main(String[] args) {
        try {
            String pdfFile = "D:/XXX.pdf";
            PDDocument doc = PDDocument.load(new File(pdfFile));
            int pagenumber = doc.getNumberOfPages();
            pdfFile = pdfFile.substring(0, pdfFile.lastIndexOf("."));
            String fileName = pdfFile + ".doc";
            File file = new File(fileName);
            if (!file.exists()) {
                file.createNewFile();
            }
            FileOutputStream fos = new FileOutputStream(fileName);
            Writer writer = new OutputStreamWriter(fos, "UTF-8");
            PDFTextStripper stripper = new PDFTextStripper();
            stripper.setSortByPosition(true);// 排序
            stripper.setStartPage(1);// 设置转换的开始页
            stripper.setEndPage(pagenumber);// 设置转换的结束页
            stripper.writeText(doc, writer);
            writer.close();
            doc.close();
            System.out.println("pdf转换word成功！");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

pom.xml

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.12</version>
</dependency>