Java如何实现PDF转HTML/Word/Excel/PPT/PNG

从 maven 下载 aspose.pdf

通过将以下配置添加到 pom.xml， 您可以直接从基于Maven的项目 轻松地使用Aspose.PDF for Java 。

<repository>
    <id>AsposeJavaAPI</id>
    <name>Aspose Java API</name>
    <url>https://repository.aspose.com/repo/</url>
</repository>
<dependency>
    <groupId>com.aspose</groupId>
    <artifactId>aspose-pdf</artifactId>
    <version>22.4</version>
</dependency>

核心代码实现（单类）

 import com.aspose.pdf.Document;
import com.aspose.pdf.SaveFormat;
import com.aspose.pdf.devices.PngDevice;
import com.aspose.pdf.devices.Resolution;
 
import java.io.*;
 
public class PDFHelper3 {
 
    public static void main(String[] args) throws IOException {
        pdf2image("C:\\Users\\liuya\\Desktop\\pdf\\示例文件.pdf");
    }
 
 
    //转word
    public static void pdf2word(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            String wordPath=pdfPath.substring(0,pdfPath.lastIndexOf("."))+".docx";
            FileOutputStream os = new FileOutputStream(wordPath);
            Document doc = new Document(pdfPath);
            doc.save(os, SaveFormat.DocX);
            os.close();
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 Word 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 Word 失败...");
            e.printStackTrace();
        }
    }
 
    //转ppt
    public static void pdf2ppt(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            String wordPath=pdfPath.substring(0,pdfPath.lastIndexOf("."))+".ppt";
            FileOutputStream os = new FileOutputStream(wordPath);
            Document doc = new Document(pdfPath);
            doc.save(os, SaveFormat.Pptx);
            os.close();
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 PPT 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 PPT 失败...");
            e.printStackTrace();
        }
    }
 
    //转excel
    public static void pdf2excel(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            String wordPath=pdfPath.substring(0,pdfPath.lastIndexOf("."))+".xlsx";
            FileOutputStream os = new FileOutputStream(wordPath);
            Document doc = new Document(pdfPath);
            doc.save(os, SaveFormat.Excel);
            os.close();
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 EXCEL 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 EXCEL 失败...");
            e.printStackTrace();
        }
    }
 
    //转html
    public static void pdf2Html(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            String htmlPath=pdfPath.substring(0,pdfPath.lastIndexOf("."))+".html";
            Document doc = new Document(pdfPath);
            doc.save(htmlPath,SaveFormat.Html);
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 HTML 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 HTML 失败...");
            e.printStackTrace();
        }
    }
 
    //转图片
    public static void pdf2image(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            Resolution resolution = new Resolution(300);
            String dataDir=pdfPath.substring(0,pdfPath.lastIndexOf("."));
            File imageDir = new File(dataDir+"_images");
            imageDir.mkdirs();
            Document doc = new Document(pdfPath);
            PngDevice pngDevice = new PngDevice(resolution);
            for (int pageCount = 1; pageCount <= doc.getPages().size(); pageCount++) {
                OutputStream imageStream = new FileOutputStream(imageDir+"/"+pageCount+".png");
                pngDevice.process(doc.getPages().get_Item(pageCount), imageStream);
                imageStream.close();
            }
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 PNG 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 PNG 失败...");
            e.printStackTrace();
        }
    }
 
 
}

运行方法，idea里右键运行，如果要做成web系统可以将代码封装程web服务，调用方法就行。

转换文件结果

以一个十四的pdf文件转化为例，大部分转换时间在10-12s，只有转ppt花费的时间久一点需要20s.可能pdf里面不是表格类的内容，所以转换excel文件后，样式差别会有点大，其他文件转换后样式和之前是保持一样的。