java 解析PDF文件 获取总页数

 

方式一：通过文件对象获取页数

        <!--pdf解析所需jar包-->
        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.9</version>
        </dependency>

 

    public static void main(String[] args) throws IOException {
        //创建需要解析的PDF文件
        File file=new File("C:\\Users\\11\\Desktop\\pdf资料\\Spring SpringBoot常用注解总结.pdf");
        //加载文件
        PDDocument doc = PDDocument.load(file);
        //通过工具类获取页数，打印
        System.out.println(doc.getNumberOfPages());
    }

方式二：通过url地址获取输入流，解析输入流，获取文件页数

    @Test
    public void demo1(){
        String urlStr= "https://certification.squaretogether.cn/etcd/tsign/auth/file/downLoadByFileId/5f16bea656635f3dbc8ee692";
        HttpURLConnection conn = null;
        byte[] bytes=null;
        try {
            URL url = new URL(urlStr);
            conn = (HttpURLConnection) url.openConnection();
            conn.setRequestMethod("GET");
            conn.setConnectTimeout(20 * 1000);
            InputStream in=conn.getInputStream();
            //加载文件
            PDDocument doc = PDDocument.load(in);
            //通过工具类获取页数，打印
            System.out.println(doc.getNumberOfPages());
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                if (conn != null) {
                    conn.disconnect();
                }
            } catch (Exception e) {
            }
        }
    }

方式三：通过解析字节数组，获取页数

    @Test
    public void demo3()throws Exception{
        //url已经失效
        byte[] urlFileData = getUrlFileData("https://certification.squaretogether.cn/etcd/tsign/auth/file/downLoadByFileId/5f179b8a56635f3dbc8ee698");
        //加载文件
        PDDocument doc = PDDocument.load(urlFileData);
        //通过工具类获取页数，打印
        System.out.println(doc.getNumberOfPages());
    }
    //通过url获取字节数组
    public static byte[] getUrlFileData(String fileUrl) throws Exception
    {
        URL url = new URL(fileUrl);
        HttpURLConnection httpConn = (HttpURLConnection) url.openConnection();
        httpConn.connect();
        InputStream cin = httpConn.getInputStream();
        ByteArrayOutputStream outStream = new ByteArrayOutputStream();
        byte[] buffer = new byte[1024*10];
        int len = 0;
        while ((len = cin.read(buffer)) != -1) {
            outStream.write(buffer, 0, len);
        }
        cin.close();
        byte[] fileData = outStream.toByteArray();
        outStream.close();
        return fileData;
    }