pdf转word方法,仅限于纯文字转换

    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.27</version>
    </dependency>

    <!-- Apache POI -->
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi</artifactId>
        <version>5.0.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>5.0.0</version>
    </dependency>

=

package com.mmtrix.newsInfo.controller.test;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.*;

/**
 * pdf转word方法,仅限于纯文字转换
 * @author zhusongtao
 */
public class PdfToWordConverter {

    public static void main(String[] args)
    {
        try
        {
            String pdfFile = "D:\\word\\zqq 2.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();
            // 排序
            stripper.setSortByPosition(true);
            // 设置转换的开始页
            stripper.setStartPage(1);
            // 设置转换的结束页
            stripper.setEndPage(pagenumber);
            stripper.writeText(doc, writer);
            writer.close();
            doc.close();
            System.out.println("pdf转换word成功！");
        }
        catch (IOException e)
        {
            e.printStackTrace();
        }
    }

}