使用 Java 实现点触验证码识别与处理

目标
本节的目标是使用 Java 语言实现点触验证码的识别与验证，不依赖第三方验证码识别平台。

准备工作
我们将使用 Selenium 库来驱动 Chrome 浏览器，并借助一些图像处理库来进行验证码识别。在此之前，请确保已正确安装了 Selenium 库、Chrome 浏览器，并配置好了 ChromeDriver。

了解点触验证码更多内容联系1436423940
点触验证码是一种需要点击图像中指定区域来完成验证的方式。常见的点触验证码样式如下图所示：

识别思路
识别此类验证码的难点主要在于文字和图像的识别。我们将使用 OCR 技术结合图像处理算法，来识别验证码中的文字和目标区域。

实现步骤
1. 导入依赖
在项目的 pom.xml 文件中添加以下依赖：

xml

<dependencies>
    <dependency>
        <groupId>org.seleniumhq.selenium</groupId>
        <artifactId>selenium-java</artifactId>
        <version>4.1.0</version>
    </dependency>
    <dependency>
        <groupId>org.apache.commons</groupId>
        <artifactId>commons-io</artifactId>
        <version>1.4</version>
    </dependency>
    <dependency>
        <groupId>org.bytedeco</groupId>
        <artifactId>javacv-platform</artifactId>
        <version>1.5.6</version>
    </dependency>
</dependencies>
2. 初始化 WebDriver
java
复制代码
import org.openqa.selenium.By;
import org.openqa.selenium.WebDriver;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.chrome.ChromeDriver;
import org.openqa.selenium.chrome.ChromeOptions;
import org.openqa.selenium.support.ui.ExpectedConditions;
import org.openqa.selenium.support.ui.WebDriverWait;

import java.time.Duration;

public class CaptchaSolver {
    private static final String CHROME_DRIVER_PATH = "/path/to/chromedriver";
    private static final String URL = "http://admin.touclick.com/login.html";
    private WebDriver driver;
    private WebDriverWait wait;

    public CaptchaSolver() {
        System.setProperty("webdriver.chrome.driver", CHROME_DRIVER_PATH);
        ChromeOptions options = new ChromeOptions();
        driver = new ChromeDriver(options);
        wait = new WebDriverWait(driver, Duration.ofSeconds(20));
    }

    public void openPage() {
        driver.get(URL);
    }

    public void login(String email, String password) {
        WebElement emailField = wait.until(ExpectedConditions.presenceOfElementLocated(By.id("email")));
        WebElement passwordField = wait.until(ExpectedConditions.presenceOfElementLocated(By.id("password")));
        emailField.sendKeys(email);
        passwordField.sendKeys(password);
    }

    public void close() {
        driver.quit();
    }
}
3. 获取验证码图像

import org.apache.commons.io.FileUtils;
import org.openqa.selenium.WebElement;
import org.openqa.selenium.interactions.Actions;

import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;

public class CaptchaSolver {
    // ... previous code ...

    public File captureCaptcha() throws IOException {
        WebElement captchaElement = wait.until(ExpectedConditions.presenceOfElementLocated(By.className("touclick-pub-content")));
        File screenshot = ((TakesScreenshot) driver).getScreenshotAs(OutputType.FILE);
        File captchaFile = new File("captcha.png");
        FileUtils.copyFile(screenshot, captchaFile);
        return captchaFile;
    }

    public static void main(String[] args) {
        CaptchaSolver solver = new CaptchaSolver();
        solver.openPage();
        solver.login("your-email@example.com", "your-password");

        try {
            File captcha = solver.captureCaptcha();
            // TODO: Implement OCR and image processing to solve captcha
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            solver.close();
        }
    }
}
4. 识别验证码文字和点击
为了进行验证码的识别，我们可以使用 Tesseract OCR 和 OpenCV。以下是一个简单的示例，演示如何使用这些工具：

java

import org.bytedeco.javacpp.BytePointer;
import org.bytedeco.javacpp.lept.PIX;
import org.bytedeco.javacpp.tesseract.TessBaseAPI;
import org.bytedeco.opencv.opencv_core.Mat;
import org.bytedeco.opencv.opencv_imgcodecs;

import java.util.ArrayList;
import java.util.List;

public class CaptchaSolver {
    // ... previous code ...

    public List<int[]> recognizeText(File imageFile) {
        List<int[]> coordinates = new ArrayList<>();
        TessBaseAPI tessBaseAPI = new TessBaseAPI();

        if (tessBaseAPI.Init("tessdata", "eng") != 0) {
            System.err.println("Could not initialize tesseract.");
            return coordinates;
        }

        PIX image = lept.pixRead(imageFile.getAbsolutePath());
        tessBaseAPI.SetImage(image);

        BytePointer outText = tessBaseAPI.GetUTF8Text();
        String text = outText.getString();

        System.out.println("OCR output: " + text);

        // TODO: Implement logic to extract coordinates from text
        // Dummy coordinates for demonstration
        coordinates.add(new int[]{100, 200});
        coordinates.add(new int[]{150, 250});

        outText.deallocate();
        tessBaseAPI.End();

        return coordinates;
    }

    public void clickCaptcha(List<int[]> coordinates) {
        WebElement captchaElement = wait.until(ExpectedConditions.presenceOfElementLocated(By.className("touclick-pub-content")));

        Actions actions = new Actions(driver);
        for (int[] coordinate : coordinates) {
            actions.moveToElement(captchaElement, coordinate[0], coordinate[1]).click().perform();
            try {
                Thread.sleep(1000); // pause between clicks
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }
    }

    public static void main(String[] args) {
        CaptchaSolver solver = new CaptchaSolver();
        solver.openPage();
        solver.login("your-email@example.com", "your-password");

        try {
            File captcha = solver.captureCaptcha();
            List<int[]> coordinates = solver.recognizeText(captcha);
            solver.clickCaptcha(coordinates);
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            solver.close();
        }
    }
}