java 实现docx和pdf互转并保留格式

目录

1、引入maven依赖 

在pom文件中增加如下依赖
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-local</artifactId>
    <version>1.0.3</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-transformer-msoffice-word</artifactId>
    <version>1.0.3</version>
</dependency>

2、本地安装office或wps

linux ：

sudo yum install libreoffice

windows：

安装wps或office都行

3、编写转换

IConverter converter = LocalConverter.builder().build();

InputStream docxInputStream = new FileInputStream(inPath); // 读取文件
//设置输出的目录
OutputStream outputStream = new FileOutputStream(pdfFilePath)

// 进行转换 

converter.convert(docxInputStream).as(DocumentType.DOCX).to(outputStream).as(DocumentType.PDF).execute();

工具类如下：

import com.documents4j.api.DocumentType;
import com.documents4j.api.IConverter;
import com.documents4j.job.LocalConverter;

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

public class WordExtractUtils {

    private static IConverter converter;

    /**
     * 需要安装sudo yum install libreoffice
     */
    static {
        converter = LocalConverter.builder().build();
    }
    public static String extract(String inPath,String out,List<Integer> extractPageNum){
        File file = new File(out);
        if(!file.exists() || file.isDirectory()){
            file.mkdirs();
        }
        String pdfFilePath = out+File.separator+UUID.randomUUID().toString()+ ".pdf";
        String finalPdfPath = out+File.separator+UUID.randomUUID().toString()+ ".pdf";
        try (
                InputStream docxInputStream = new FileInputStream(inPath);
                OutputStream outputStream = new FileOutputStream(pdfFilePath)
        ) {
            if(converter == null){
                converter = LocalConverter.builder().build();
            }
            converter.convert(docxInputStream).as(DocumentType.DOCX).to(outputStream).as(DocumentType.PDF).execute();
            System.out.println("word to pdf success");
        } catch (Exception e) {
            e.printStackTrace();
        }finally {
            file.delete();
        }
        return finalPdfPath;
    }

    public static void main(String[] args) throws FileNotFoundException {
        converter.convert(new FileInputStream("F:\\download\\20230912111517毓秀学府施工总承包工程222控制价.docx")).as(DocumentType.DOCX).to(new FileOutputStream("F:\\download\\20230912111517毓秀学府施工总承包工程222控制价1.docx")).as(DocumentType.DOCX).execute();

    }
}