Selenium+Tesseract-OCR智能識別驗證碼爬取網頁數據的實例

System.setProperty(瀏覽器驅動, 瀏覽器驅動安裝位置);
ChromeOptions options = new ChromeOptions();
options.addArguments("--headless");                            // 無窗口模式
options.addArguments("--disable-infobars");                    // 禁言消息條
options.addArguments("--disable-extensions");                  // 禁用插件
options.addArguments("--disable-gpu");                         // 禁用GPU
options.addArguments("--no-sandbox");                          // 禁用沙盒模式
options.addArguments("--disable-dev-shm-usage");
options.addArguments("--hide-scrollbars");                     // 隱藏滾動條

WebDriver driver = new ChromeDriver(options);
driver.get(爬取網站URL);
driver.manage().window().setSize(new Dimension(450, 260));     // 設置遊覽器打開後調整大小
try {
    // 保存IMG圖片到本地
    saveImgToLocal(driver);
    Thread.sleep(2000);
    // OCR智能識別驗證碼
    String codeByOCR = getCodeByOCR();
    if (codeByOCR != null) {
        try {
            WebElement input1 = driver.findElement(By.id(TEXTBOX1));
            input1.sendKeys(code);
            WebElement input2 = driver.findElement(By.id(TEXTBOX2));
            input2.sendKeys(codeByOCR);
            // 獲取table數據
            WebElement addButton = driver.findElement(By.id(SELECT_BUTTON));
            addButton.click();
            List<WebElement> tRCollection = driver.findElement(By.id(TABLE_ID)).findElements(By.tagName("tr"));
            for (int t = 1; t < tRCollection.size(); t++) {
                List<WebElement> tDCollection = tRCollection.get(t).findElements(By.tagName("td"));
                VipLogisticsMinHangDetailVo minHangDetailVo = new VipLogisticsMinHangDetailVo();
                minHangDetailVo.setLogistics_number(code);
                for (int i = 0; i < tDCollection.size(); i++) {
                    String text = tDCollection.get(i).getText();
                    switch (i) {
                        case 0:
                            minHangDetailVo.setTime(text);
                        case 1:
                            minHangDetailVo.setOutlet(text);
                        case 2:
                            minHangDetailVo.setOrganization(text);
                        case 3:
                            minHangDetailVo.setEvent(text);
                        case 4:
                            minHangDetailVo.setDetail(text);
                    }
                }
                list.add(minHangDetailVo);
            }
            log.info("驗證碼識別成功！");
        } catch (Exception e) {
            if (e.toString().contains("錯誤提示：驗證碼錯誤或已過期！")) {
                log.error("驗證碼識別錯誤！" + e.toString());
            } else if (e.toString().contains("錯誤提示：請輸入驗證碼！")) {
                log.error("未輸入驗證碼！：" + e.toString());
            } else {
                log.error("其他異常：" + e.toString());
            }
        }
    }
    driver.quit();
} catch (Exception e) {
    e.printStackTrace();
}

private void saveImgToLocal(WebDriver driver) {
    WebElement element = driver.findElement(By.id(img元素ID));
    //創建全屏截圖
    WrapsDriver wrapsDriver = (WrapsDriver) element;
    File screen = ((TakesScreenshot) wrapsDriver.getWrappedDriver()).getScreenshotAs(OutputType.FILE);
    try {
        BufferedImage image = ImageIO.read(screen);
        //創建一個矩形使用上面的高度，和寬度
        Point p = element.getLocation();
        //元素坐標
        BufferedImage img = image.getSubimage(p.getX(), p.getY(), element.getSize().getWidth(), element.getSize().getHeight());
        ImageIO.write(img, "png", screen);

        FileUtils.copyFile(screen, new File(保存本地地址 + "imgname.png"));
    } catch (IOException e) {
        e.printStackTrace();
    }
}

private static void saveImgToLocal1(WebDriver driver) {
    Actions action = new Actions(driver);
    action.contextClick(driver.findElement(By.id(img元素ID))).build().perform();
    try {
        Robot robot = new Robot();
        Thread.sleep(1000);

        robot.keyPress(KeyEvent.VK_DOWN);
        Thread.sleep(1000);

        robot.keyPress(KeyEvent.VK_DOWN);
        Thread.sleep(1000);

        robot.keyPress(KeyEvent.VK_ENTER);
        Thread.sleep(1000);
        //釋放向下鍵，不然在此之前的條目將起作用
        robot.keyRelease(KeyEvent.VK_DOWN);
        Thread.sleep(1000);
        //運行保存
        Runtime.getRuntime().exec(SAVE_IMG_EXE);
        Thread.sleep(10000);
    } catch (Exception e) {
        e.printStackTrace();
    }
}

private String getCodeByOCR() {
    String result = null;
    File file = new File(本地圖片地址);
    if (!file.exists()) {
        if (systemFalg != 1) {
            file.setWritable(true, false);
        }
        file.mkdirs();
    }
    File imageFile = new File(本地圖片地址 + "imgname.png");
    if (imageFile.exists()) {
        ITesseract instance = new Tesseract();
        instance.setDatapath(tessdata存放地址);
        try {
            String doOCR = instance.doOCR(imageFile);
            result = replaceBlank(doOCR);
            log.info("解析的驗證碼為:{}", result != null ? result : "為空！");
        } catch (Exception e) {
            e.printStackTrace();
            log.error("解析驗證碼異常！");
        }
    } else {
        log.error("解析驗證碼的文件不存在！");
    }
    return result;
}