Java使用PDFBox处理PDF的完全指南

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>3.0.5</version>
</dependency>

 @Test
void test01() throws IOException {
    try (PDDocument pdDocument = Loader.loadPDF(ResourceUtils.getFile("classpath:pdf/wyc-fp.pdf"))){
        PDFTextStripper textStripper = new PDFTextStripper();
        String text = textStripper.getText(pdDocument);
        System.out.println(text);
    }
}

@Test
void test02() throws IOException {
    PDFMergerUtility pdfMerger = new PDFMergerUtility();
    pdfMerger.addSource(ResourceUtils.getFile("classpath:pdf/wyc-fp.pdf"));
    pdfMerger.addSource(ResourceUtils.getFile("classpath:pdf/wyc-fp2.pdf"));

    // 设置合并后的pdf名称
     pdfMerger.setDestinationFileName("merge-fp.pdf");
//        pdfMerger.setDestinationStream(new FileOutputStream(file));

    pdfMerger.mergeDocuments(MemoryUsageSetting.setupMainMemoryOnly().streamCache);
    System.out.println("PDF文件合并完成");
}

@Test
void test03() throws Exception {
    try (PDDocument pdDocument = Loader.loadPDF(ResourceUtils.getFile("classpath:pdf/wyc-fp.pdf"));) {
        // 获取第一页：因为只有一页
        PDPage page = pdDocument.getPage(0);

        PDResources resources = page.getResources();
        Iterable<COSName> xObjectNames = resources.getXObjectNames();
        for (COSName xObjectName : xObjectNames) {
            // 判断是否包含图片对象
            if (resources.isImageXObject(xObjectName)) {
                PDImageXObject imageObject = (PDImageXObject) resources.getXObject(xObjectName);
                BufferedImage bImage = imageObject.getImage();
                // 将图像保存为 PNG 格式
                try (ByteArrayOutputStream baos = new ByteArrayOutputStream()) {
                    // 将图片写入输出流里面
                    ImageIO.write(bImage, "png", baos);
                    byte[] imageBytes = baos.toByteArray();
                    String imageFilePath = "image_" + System.currentTimeMillis() + ".png";
                    try (FileOutputStream fos = new FileOutputStream(imageFilePath)) {
                        fos.write(imageBytes);
                        System.out.println("Page Image path: " + imageFilePath);
                    }
                }
            }
        }
    }
}

@Test
void test04() throws Exception {
    PDDocument pdDocument = Loader.loadPDF(ResourceUtils.getFile("classpath:pdf/wyc-fp.pdf"));
    PDImageXObject pdImage = PDImageXObject.createFromFile("src/main/resources/pdf/apache-logo.jpg", pdDocument);
    // 设置logo的宽度和高度
    float imageWidth = 100;
    float imageHeight = 100;

    if (pdDocument != null) {
        PDPage page = pdDocument.getPage(pdDocument.getNumberOfPages() - 1);
        float pageWidth = page.getMediaBox().getWidth();;

        // 计算logo位置：页面右下角
        float x = pageWidth - imageWidth - 20; // 右边距20
        float y = 20; // 下边距20

        // 为最后一页创建一个新的内容流以添加logo
        try (PDPageContentStream contentStream = new PDPageContentStream(pdDocument, page,
                PDPageContentStream.AppendMode.APPEND, true, true)) {
            // 绘制logo图片
            contentStream.drawImage(pdImage, x, y, imageWidth, imageHeight);
        }
        pdDocument.save("logo_" + System.currentTimeMillis() + ".pdf"); // 保存修改后的PDF
    }
}

try (PDDocument pdDocument = Loader.loadPDF(file)){
     // ***  
}

// 2.0.x 加载文件
PDDocument.load(file)
    
// 3.0 加载文件
Loader.loadPDF(file)   

# 2.0.x 最低要求：JDK1.6

# 3.0 最低要求：JDK1.8