将图像从PDImageXObject提取到文件中，而不将其加载到内存中

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.util.Matrix;
import org.apache.pdfbox.util.PDFStreamEngine;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;

public class ImageExtractor extends PDFStreamEngine {

    public static void main(String[] args) {
        try {
            PDDocument document = PDDocument.load(new File("input.pdf"));
            ImageExtractor extractor = new ImageExtractor();
            for (PDPage page : document.getPages()) {
                extractor.processPage(page);
            }
            document.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    protected void processOperator(String operator, List<COSBase> operands) throws IOException {
        super.processOperator(operator, operands);
        // 处理图像操作符
        if ("Do".equals(operator)) {
            COSName objectName = (COSName) operands.get(0);
            PDImageXObject image = (PDImageXObject) getResources().getXObject(objectName);
            if (image != null) {
                // 提取图像到文件
                extractImage(image);
            }
        }
    }

    private void extractImage(PDImageXObject image) throws IOException {
        String fileName = "image_" + image.getSuffix();
        FileOutputStream outputStream = new FileOutputStream(fileName);
        IOUtils.copy(image.getStream(), outputStream);
        outputStream.close();
    }
}