1:添加依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>pdfToWord</groupId>
    <artifactId>pdfToWord</artifactId>
    <version>1.0-SNAPSHOT</version>
   <dependencies>
       <dependency>
           <groupId>commons-logging</groupId>
           <artifactId>commons-logging</artifactId>
           <version>1.2</version>
       </dependency>
       <dependency>
           <groupId>org.apache.pdfbox</groupId>
           <artifactId>fontbox</artifactId>
           <version>2.0.11</version>
       </dependency>
       <dependency>
           <groupId>com.levigo.jbig2</groupId>
           <artifactId>levigo-jbig2-imageio</artifactId>
           <version>2.0</version>
       </dependency>
       <dependency>
           <groupId>org.apache.pdfbox</groupId>
           <artifactId>pdfbox-tools</artifactId>
           <version>2.0.11</version>
       </dependency>
       <dependency>
           <groupId>commons-io</groupId>
           <artifactId>commons-io</artifactId>
           <version>2.6</version>
       </dependency>
   </dependencies>
    
</project>

2:编写转换的方法

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

import java.io.*;

/**
 * 把pdf转换为word格式
 *
 * @author Angin
 * @date 2019/3/18 0018.
 */
public class PdfToWord {
    /**
     * 转换
     */
    public void convertText(String pdfPath) {
        PDDocument doc = null;
        OutputStream fos = null;
        Writer writer = null;
        PDFTextStripper stripper = null;
        try {
            doc = PDDocument.load(new File(pdfPath));
            fos = new FileOutputStream(pdfPath.substring(0, pdfPath.indexOf(".")) + ".doc");
            writer = new OutputStreamWriter(fos, "UTF-8");
            stripper = new PDFTextStripper();
            int pageNumber = doc.getNumberOfPages();
            stripper.setSortByPosition(true);
            stripper.setStartPage(1);
            stripper.setEndPage(pageNumber);
            stripper.writeText(doc, writer);
            writer.close();
            doc.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        System.out.println("end..");
    }
}

3:main方法中进行测试

/**
 * main方法测试
 * @author Angin
 * @date 2019/3/18 0018.
 */
public class MainClass {
    public static void main(String[] args) {
   PdfToWord convert=new PdfToWord();
   convert.convertText("E:\\pdfToWord.pdf");
    }
}

此方法只适合文档型的pdf转换,如果图片的话,转换后无法读取。

版权声明:本文为angin-iit原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。
本文链接:https://www.cnblogs.com/angin-iit/p/10551829.html