JAVA多页pdf转换为多张图片

相关jar包

<dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itext-asian</artifactId>
            <version>5.2.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.0</version>
        </dependency>
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>fontbox</artifactId>
            <version>2.0.0</version>
        </dependency>
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itextpdf</artifactId>
            <version>5.5.13</version>
        </dependency>

相关代码

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;
import java.util.UUID;

import javax.imageio.ImageIO;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

    /**
     *   将多页pdf转化为多张图片
     * @param pdfPath 表示pdf的路径
     * @return 转化后的图片的路径集合
     * @throws IOException
     */
    public static List<String> pdfPathToImagePaths(String pdfPath) throws IOException {
        log.info("将多页pdf转化为图片，pdf路径为："+pdfPath);
        File pdfFile = new File(pdfPath);
        PDDocument pdDocument = PDDocument.load(pdfFile);
        int pageCount = pdDocument.getNumberOfPages();
        PDFRenderer pdfRenderer = new PDFRenderer(pdDocument);
        List<String> imagePathList=new ArrayList<>();
        String fileParent = pdfFile.getParent();
        for (int pageIndex=0; pageIndex<pageCount; pageIndex++) {
            String imgPath = fileParent + File.separator +UUID.randomUUID().toString()+".png";
            BufferedImage image = pdfRenderer.renderImageWithDPI(pageIndex, 105, ImageType.RGB);
            ImageIO.write(image, "png", new File(imgPath));
            imagePathList.add(imgPath);
            log.info("第{}张生成的图片路径为：{}",pageIndex,imgPath);
        }
        pdDocument.close();
        return imagePathList;
    }

测试类

    public static void main(String[] args) throws IOException {
        String pdfPath = "E://opt//upFiles\\1《中国武术通史》上册_1635840894961.pdf";
        String bookid = "《中国武术通史》上册";
        log.info("==================================");
        log.info("将多页pdf转化为图片，pdf路径为："+pdfPath);
        log.info("==================================");
        File pdfFile = new File(pdfPath);
        PDDocument pdDocument = PDDocument.load(pdfFile);
        int pageCount = pdDocument.getNumberOfPages();
        PDFRenderer pdfRenderer = new PDFRenderer(pdDocument);
        List<String> imagePathList=new ArrayList<>();
        String fileParent = pdfFile.getParent();
        //带bookid的pdf路径
        String bookidPath = fileParent + File.separator + bookid;

        File file = new File(bookidPath + File.separator );
        if (!file.exists()) {
            file.mkdirs();// 创建文件根目录
        }

        for (int pageIndex=0; pageIndex<pageCount; pageIndex++) {
//            String imgPath = fileParent + File.separator + UUID.randomUUID().toString()+".png";
            String imgPath = bookidPath + File.separator +  pageIndex+".png";
            BufferedImage image = pdfRenderer.renderImageWithDPI(pageIndex, 105, ImageType.RGB);
            ImageIO.write(image, "png", new File(imgPath));
            imagePathList.add(imgPath);
            log.info("第{}张生成的图片路径为：{}",pageIndex,imgPath);
        }
        pdDocument.close();

    }

参考资料