selenium+java爬取图片

看很多大佬都在用python爬取图片，其实java也可以啦，这里就通过一个例子来跑一把啦

 话不多说，上代码

private final static String driver = "webdriver.chrome.driver";
    private final static String chromeDriver = "C:\\Users\\d\\AppData\\Local\\Google\\Chrome\\Application\\chromedriver.exe";


    //网址
    private final static String emojiWebAddress = "https://www.dbbqb.com/";

    static {
        // 引入谷歌驱动 控制浏览器
        System.setProperty(driver, chromeDriver);
    }

    public static void main(String[] args) {
        System.out.println("正在打开浏览器");
        //1、获取谷歌浏览器控制 打开浏览器
        WebDriver driver = new ChromeDriver();
        driver.manage().window().maximize();//浏览器最大化
        //2、超时等待30秒
        Duration duration = Duration.ofSeconds(3);
        driver.manage().timeouts().implicitlyWait(duration);
        //3、跳转到表情包网址
        driver.get(emojiWebAddress);


        while (true){
            driver.navigate().refresh();
            try {
                //4、获取到元素
                WebElement bqbEle = driver.findElement(By.xpath("//*[@id=\"root\"]/div[4]"));
                //5、获取到最大的排和列的元素
                WebElement bigDivEle = bqbEle.findElement(By.xpath("div"));
                //6、获取到所有的49
                List<WebElement> jss49DivList = bqbEle.findElements(By.className("jss49"));
                //7、循环49拿到50
                for (WebElement rowEle : jss49DivList) {
                    //拿到单个的div
                    List<WebElement> js50DivList = rowEle.findElements(By.xpath("div"));
                    //循环下获取到链接
                    for (WebElement js50 : js50DivList) {
                        String src = js50.findElement(By.className("lazyload-wrapper"))
                                .findElement(By.xpath("a"))
                                .findElement(By.xpath("img")).getAttribute("src");
                        //获取到当前时间戳
                        Long l = System.currentTimeMillis();
                        //生成4位随机数
                        Integer i =(Integer)new Random().nextInt(9999);
                        //提供一个网址下载
                        TuPianXiaZai.downloadPicture(src,"E:\\Download\\"+l.toString()+i.toString()+".jpg");
                    }
                    System.out.println("下载了一排");
                }
            }catch (Exception e){
                e.printStackTrace();
                System.err.println("报错了！！！");
            }
        }


    }


    /**
     * @Description: 下载图片到本地
     * @Param: [urlList图片地址, path本地地址]
     * @return: void
     * @Author: xjx
     * @Date: 2022/9/21
     */
    private static void downloadPicture(String urlList, String path) {
        URL url = null;
        try {
            url = new URL(urlList);
            DataInputStream dataInputStream = new DataInputStream(url.openStream());

            FileOutputStream fileOutputStream = new FileOutputStream(new File(path));
            ByteArrayOutputStream output = new ByteArrayOutputStream();

            byte[] buffer = new byte[1024];
            int length;

            while ((length = dataInputStream.read(buffer)) > 0) {
                output.write(buffer, 0, length);
            }
            fileOutputStream.write(output.toByteArray());
            dataInputStream.close();
            fileOutputStream.close();
        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

我运行后，发现这个网址是有反爬机制的，这里用了一种无限循环的方式来解决，反正每次刷新图都不一样，代码仅供学习嗷，这里建议大家千万别去恶意爬取人家的资源，容易被逮。