java提取pdf对应的目录及页码实践

 <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.24</version>
        </dependency>

public static void main(String[] args) throws IOException {
//        File file = new File("E:\\navicat.pdf");
        File file = new File("C:\\Users\\msi\\Desktop\\max.pdf");
        PDDocument document = PDDocument.load(file);


        // 获取PDF文件的结构树根对象
//        PDStructureTreeRoot structureTree = document.getDocumentCatalog().getStructureTreeRoot();

        // 获取PDF文件的文档目录对象
        PDDocumentOutline documentOutline = document.getDocumentCatalog().getDocumentOutline();

        // 输出目录内容
        if (documentOutline != null) {

            printOutline(documentOutline, "",0);
        }


        // 创建PDFTextStripper对象，用于提取文本
//        PDFTextStripper pdfStripper = new PDFTextStripper();
//        // 提取文本
//        String text = pdfStripper.getText(document);
//        // 输出文本内容
//        System.out.println(text);

        // 关闭PDDocument对象
        document.close();

    }

    // 递归输出目录内容
    private static void printOutline(PDOutlineNode documentOutline, String indent,int i) throws IOException {
        PDOutlineItem item = documentOutline.getFirstChild();
        i++;
        indent = indent + "    ";
        while (item != null){
            //        PDPageDestination destination = (PDPageDestination) item.getDestination();
//        int pageNumber = destination.retrievePageNumber();

            int pages = 0;
            if(item.getDestination() instanceof PDPageDestination){
                PDPageDestination pd = (PDPageDestination) item.getDestination();
                pages = pd.retrievePageNumber() + 1;
            }
            if (item.getAction()  instanceof PDActionGoTo) {
                PDActionGoTo gta = (PDActionGoTo) item.getAction();
                if (gta.getDestination() instanceof PDPageDestination) {
                    PDPageDestination pd = (PDPageDestination) gta.getDestination();
                    pages = pd.retrievePageNumber() + 1;
                }
            }
            System.out.println("------" +indent + item.getTitle() + "----"+pages+"   层级:"+i );
            // 递归处理子项
            printOutline(item, indent ,i);
//        获取同级
            item= item.getNextSibling();
        }

    }