SpringBoot实现Word转PDF和TXT的实践分享_Java

背景

研发工作中难免会遇到一些奇奇怪怪的需求，就比如最近，客户提了个新需求：上传一个word文档，要求通过系统把该文档转换成pdf和txt。客户的需求是没得商量的，必须实现！承载着客户的期望，我开始在网上找相关的资料。没曾想，还真有开源的依赖专门处理这类问题，咱们一起来看看吧！

实践

1、下载和引入jar包

要实现word到pdf/txt的转换，需要引入以下几个jar包：

        <dependency>
            <groupid>com.aspose</groupid>
            <artifactid>aspose-words</artifactid>
            <version>19.1</version>
            <scope>system</scope>
            <systempath>${pom.basedir}/src/main/resources/lib/aspose-words-19.1.jar</systempath>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.pdfbox/pdfbox-tools -->
        <dependency>
            <groupid>org.apache.pdfbox</groupid>
            <artifactid>pdfbox</artifactid>
            <version>3.0.3</version>
        </dependency>

其中，aspose-words包不太好找，在阿里云镜像库中都没有，需要在网上下载后，上传到本地的私服库，或者用上文中的方式直接在lib中加载。我在网上找了这个地址，可以查看和下载相关包：aspose.words 24.4

2、代码实现

将依赖包引入之后，编写以下java代码：

package com.leixi.filetrans.utils;
 
import com.aspose.words.saveformat;
import java.io.bufferedwriter;
import java.io.file;
import java.io.fileinputstream;
import java.io.fileoutputstream;
import java.io.outputstreamwriter;
import com.aspose.words.document;
import org.apache.pdfbox.loader;
import org.apache.pdfbox.pdmodel.pddocument;
import org.apache.pdfbox.text.pdftextstripper;
 
/**
 *
 * @author leixiyueqi
 * @since 2024/08/26 19:39
 */
public class filetransutils {
 
    public static void main(string[] args) throws exception {
        file file = new file("d:\\upload\\saas.docx");
        string output =  "d:\\upload\\saas.pdf";
        doc2pdf(file, output);
        system.out.println("测度结束");
    }
 
 
    public static void doc2pdf(file file, string outpath) throws exception{
        fileinputstream fis = new fileinputstream(file);
        document document = new document(fis);
        if (!checkdirectory(outpath)) {
            throw new exception("创建目录失败");
        }
        document.save(outpath, saveformat.pdf);
        system.out.println(string.format("word转换pdf成功: %s", outpath));
        document.save(outpath.replace(".pdf", ".txt"), saveformat.text);
        system.out.println(string.format("word转换txt成功: %s", outpath.replace(".pdf", ".txt")));
        document.save(outpath.replace(".pdf", ".html"), saveformat.html);
        system.out.println(string.format("word转换html成功: %s", outpath.replace(".pdf", ".html")));
        pdftotxt(new file(outpath), new file(outpath.replace(".pdf", "bypdf.txt")));
        system.out.println(string.format("通过pdf转换txt成功: %s", outpath.replace(".pdf", "bypdf.txt")));
    }
 
    public static boolean checkdirectory(string filepath) {
        file file = new file(filepath);
        if (file.isdirectory()) {
            return true;
        } else {
            file dir = file.getparentfile();
            if (dir != null && !dir.isdirectory() && !dir.mkdirs()) {
                system.out.println(string.format("创建目录%s失败:", dir.getabsolutepath()));
                return false;
            } else {
                return true;
            }
        }
    }
    public static void pdftotxt(file input, file output) {
        bufferedwriter wr = null;
        try {
            pddocument pd = loader.loadpdf(input);
            pd.save("copyof" + input.getname().split("\\.")[0] + ".pdf");
            pdftextstripper stripper = new pdftextstripper();
            wr = new bufferedwriter(new outputstreamwriter(new fileoutputstream(output)));
            stripper.writetext(pd, wr);
            if (pd != null) {
                pd.close();
            }
            wr.close();
        } catch (exception e) {
            e.printstacktrace();
        }finally {
            system.out.println("pdf转换txt成功");
        }
    }
}