话不多说,直接上代码!!!
package com.tlw.test.controller;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import java.io.*;
/**
* @author: tlw
* @date: 2021年04月21日
* @Description: PDF转Word
*/
public class PdfToWord {
public static void main(String[] args){
try{
String pdfFile = "本地文件路径.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文件jar包
<!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox -->
<dependency>
<groupId>org.apache.pdfbox</groupId>
<artifactId>pdfbox</artifactId>
<version>1.8.2</version>
</dependency>
运行成功后本地自行查看已转换过来的Wrod文档!