JAVA PDF操作之实现截取N页和多个PDF合并

<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itextpdf</artifactId>
    <version>5.5.13</version>
</dependency>

import com.itextpdf.text.Document;
import com.itextpdf.text.pdf.PdfCopy;
import com.itextpdf.text.pdf.PdfImportedPage;
import com.itextpdf.text.pdf.PdfReader;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPageTree;
import org.apache.pdfbox.rendering.PDFRenderer;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;

public class PdfUtil {

    /**
     * 截取pdfFile的第from页至第end页，组成一个新的文件名
     *
     * @param pdfFile 要切割的pdf文件
     * @param newFile 切割后形成的新的pdf文件
     * @param from    从第N页开始
     * @param end     到第N页结束
     */
    public static void partitionPdf(String pdfFile, String newFile, int from, int end) {
        Document document = null;
        PdfCopy copy = null;
        PdfReader reader = null;
        try {
            reader = new PdfReader(pdfFile);
            int pageCount = reader.getNumberOfPages();
            if (from < 1) {
                from = 1;
            }
            if (from > pageCount) {
                from = pageCount;
            }
            if (end == 0 || end > pageCount) {
                end = pageCount;
            }
            document = new Document(reader.getPageSize(1));
            copy = new PdfCopy(document, new FileOutputStream(newFile));
            document.open();
            for (int j = from; j <= end; j++) {
                document.newPage();
                PdfImportedPage page = copy.getImportedPage(reader, j);
                copy.addPage(page);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (document != null) {
                document.close();
            }
            if (copy != null) {
                copy.close();
            }
            if (reader != null) {
                reader.close();
            }
        }
    }

    /**
     * pdf转图片
     *
     * @param pdfFile   PDF 文件
     * @param imageFile 输出的图片文件
     * @param from      开始页 从1开始
     * @param end       结束页 最大为PDF总页数
     * @throws Exception
     */
    public static void pdfToImage(String pdfFile, String imageFile, int from, int end) throws Exception {
        PDDocument doc = null;
        ByteArrayOutputStream os = null;
        InputStream stream = null;
        OutputStream out = null;
        try {
            //pdf路径
            stream = new FileInputStream(pdfFile);
            // 加载解析PDF文件
            doc = PDDocument.load(stream);
            PDFRenderer pdfRenderer = new PDFRenderer(doc);
            PDPageTree pages = doc.getPages();
            int pageCount = pages.getCount();
            if (from < 1) {
                from = 1;
            }
            if (from > pageCount) {
                from = pageCount;
            }
            if (end == 0 || end > pageCount) {
                end = pageCount;
            }
            for (int i = from; i <= end; i++) {
                BufferedImage bim = pdfRenderer.renderImageWithDPI(i - 1, 200); //PDFBOX 是从0开始的，from初始值为1，所以这边要减 i-1
                os = new ByteArrayOutputStream();
                ImageIO.write(bim, "jpg", os);
                byte[] dataList = os.toByteArray(); 
                //只取一页，等于传进来的名称，多页时，加上 页号
                String imageFilePath = from == end ? saveImgFile : saveImgFile.replace(".jpg", "_" + i + ".jpg");
                File file = new File(imageFilePath);
                if (!file.getParentFile().exists()) {
                    // 不存在则创建父目录及子文件
                    file.getParentFile().mkdirs();
                    file.createNewFile();
                }
                out = new FileOutputStream(file);
                out.write(dataList);
            }
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (doc != null) {
                doc.close();
            }
            if (os != null) {
                os.close();
            }
            if (stream != null) {
                stream.close();
            }
            if (out != null) {
                out.close();
            }
        }
    }

    //多个PDF合并成一个
    public static void mergePDFFiles(List<String> pdfFiles, String outputPdf) throws IOException {
        // 创建一个新的 PDF 阅读器对象和一个新的 PDF 写入对象
        PdfReader reader = null;
        PdfCopy copy = null;
        Document document = new Document();
        try {
            // 创建 PDF 阅读器对象和写入对象
            reader = new PdfReader(pdfFiles.get(0));
            copy = new PdfCopy(document, new FileOutputStream(outputPdf));
            // 打开文档准备写入内容
            document.open();

            // 将第一个 PDF 的所有页面复制到输出 PDF 中
            for (int i = 1; i <= reader.getNumberOfPages(); i++) {
                PdfImportedPage page = copy.getImportedPage(reader, i);
                copy.addPage(page);
            }

            // 将其它PDF的所有页，输出到 PDF 中
            for (int i = 1; i < pdfFiles.size(); i++) {
                reader = new PdfReader(pdfFiles.get(i));
                for (int j = 1; j <= reader.getNumberOfPages(); j++) {
                    PdfImportedPage page = copy.getImportedPage(reader, j);
                    copy.addPage(page);
                }
            }

        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            if (document != null) {
                document.close();
            }
            if (copy != null) {
                copy.close();
            }
            if (reader != null) {
                reader.close();
            }
        }
    }
}

@Test
void pdf() throws Exception {
    String pdfFile = "D:\\Desktop\\20220117.pdf";
    String jpgFile = "D:\\Desktop\\20220117.jpg";
    PdfUtil.pdfToImage(pdfFile, jpgFile, 1, 1); 
}

@Test
 void testMerge() throws IOException {
    List<String> pdfFiles = new ArrayList<>();
    pdfFiles.add("D:\\Projects\\20231225180735.pdf");
    pdfFiles.add("D:\\Projects\\20231225182535.pdf");
    pdfFiles.add("D:\\Projects\\20231225184135.pdf");
    PdfUtil.mergePDFFiles(pdfFiles, "D:\\Projects\\New.pdf");
}