SpringBoot实现Word转PDF和TXT的实践分享

        <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>

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");
        }
    }
}