极客验证码破解

很多网站的登陆都有验证码一项，而极客的方案就是应用的非常普遍。更多的场景是反反爬虫的对抗中，极客验证码更是首选。

图片来看一下

点击后就出现上面的滑动图片的窗口。本文亲自尝试代码，来分享其中的坑。

本文是使用selenium自动化测试工具来驱动代码完成验证，因此要有谷歌的driver和谷歌浏览器。以http://www.epicc.com.cn/idprovider/views/login.jsp为例子。

首先

    def get_geetest_button(self):
        """
        获取初始验证按钮
        :return:
        """
        button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'slide-tip')))
        return button
    
    def get_position(self):
        """
        获取验证码位置
        :return: 验证码位置元组
        """

        img=self.wait.until(EC.presence_of_element_located((By.CLASS_NAME ,'captcha-box-content')))
        time.sleep(2)
        location = img.location
        print(location)
        size = img.size
        top, bottom, left, right = location['y'], location['y'] + size['height'], location['x'], location['x'] + size[
            'width']
        print((top, bottom, left, right))
        # return (top, bottom, left, right)
        return (238, 400, 1103, 1473)

    def get_screenshot(self):
        """
        获取网页截图
        :return: 截图对象
        """
        name = int(time.time())
        screenshot = self.browser.get_screenshot_as_png()
        with open("screenshot"+ str(name) + ".png","wb")as f:
            f.write(screenshot)

        screenshot = Image.open(BytesIO(screenshot))

        return screenshot
    
    def get_slider(self):
        """
        获取滑块
        :return: 滑块对象
        """
        slider = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'slide-bar')))
        return slider
    
    def get_geetest_image(self, name='captcha.png'):
        """
        获取验证码图片
        :return: 图片对象
        """
        top, bottom, left, right = self.get_position()
        print('验证码位置', top, bottom, left, right)
        time.sleep(3)
        screenshot = self.get_screenshot()
        # crop函数带的参数为(起始点的横坐标，起始点的纵坐标，宽度，高度）
        captcha = screenshot.crop((left, top, right, bottom))
        captcha.save(name)
        return captcha
    
    def open(self):
        """
        打开网页输入用户名密码
        :return: None
        """
        self.browser.get(self.url)
        time.sleep(1)
        passLoginButton = self.browser.find_element_by_xpath("//ul[@class='login-tab-list']/li[2]")
        passLoginButton.click()
        email = self.wait.until(EC.presence_of_element_located((By.ID, 'entryId')))
        password = self.wait.until(EC.presence_of_element_located((By.ID, 'password')))
        email.send_keys(self.email)
        password.send_keys(self.password)
    
    def get_gap(self, image1, image2):
        """
        获取缺口偏移量
        :param image1: 不带缺口图片
        :param image2: 带缺口图片
        :return:
        """

        for i in range(INIT_LEFT, image1.size[0]):
            for j in range(image1.size[1]):
                if not self.is_pixel_equal(image1, image2, i, j):
                    left = i
                    return left

    def is_pixel_equal(self, image1, image2, x, y):
        """
        判断两个像素是否相同
        :param image1: 图片1
        :param image2: 图片2
        :param x: 位置x
        :param y: 位置y
        :return: 像素是否相同
        """
        # 取两个图片的像素点
        pixel1 = image1.load()[x, y]
        pixel2 = image2.load()[x, y]
        threshold = 60
        if abs(pixel1[0] - pixel2[0]) < threshold and abs(pixel1[1] - pixel2[1]) < threshold and abs(
                pixel1[2] - pixel2[2]) < threshold:
            return True
        else:
            return False
    
    def get_track(self, distance):
        """
        根据偏移量获取移动轨迹
        :param distance: 偏移量
        :return: 移动轨迹
        """
        # 移动轨迹
        track = []
        # 当前位移
        current = 0
        # 减速阈值
        mid = distance * 4 / 5
        # 计算间隔
        t = 0.2
        # 初速度
        v = 0
        
        while current < distance:
            if current < mid:
                # 加速度为正2
                a = 2
            else:
                # 加速度为负3
                a = -3
            # 初速度v0
            v0 = v
            # 当前速度v = v0 + at
            v = v0 + a * t
            # 移动距离x = v0t + 1/2 * a * t^2
            move = v0 * t + 1 / 2 * a * t * t
            # 当前位移
            current += move
            # 加入轨迹
            track.append(round(move))
        return track
    
    def move_to_gap(self, slider, track):
        """
        拖动滑块到缺口处
        :param slider: 滑块
        :param track: 轨迹
        :return:
        """
        ActionChains(self.browser).click_and_hold(slider).perform()
        for x in track:
            ActionChains(self.browser).move_by_offset(xoffset=x, yoffset=0).perform()
        time.sleep(0.5)
        ActionChains(self.browser).release().perform()
    
    def login(self):
        """
        登录
        :return: None
        """
        submit = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'epiccLogin')))
        submit.click()
        time.sleep(10)
        print('登录成功')
    
    def crack(self):
        # 输入用户名密码
        self.open()
        # 点击验证按钮
        button = self.get_geetest_button()
        ActionChains(self.browser).move_to_element(button).perform()
        # button.click()
        time.sleep(5)

        # 获取验证码图片
        image1 = self.get_geetest_image('captcha1.png')

        # 点按呼出缺口
        print("点按呼出缺口")
        slider = self.get_slider()
        slider.click()
        # 获取带缺口的验证码图片
        image2 = self.get_geetest_image('captcha2.png')
        # 获取缺口位置
        gap = self.get_gap(image1, image2)
        print('缺口位置', gap)
        # 减去缺口位移 BORDER指的是待拼合的滑块距离验证码图片左边的距离(经过验证大多数网站滑块验证码这个值是是固定的)
        gap -= BORDER  #滑块要滑动的距离
        print("需要滑动的距离:{}".format(gap))
        gap = gap * 0.8
        # 获取移动轨迹
        track = self.get_track(gap)
        print('滑动轨迹', track)
        # 拖动滑块
        self.move_to_gap(slider, track)

        success = self.wait.until(
            EC.text_to_be_present_in_element((By.CLASS_NAME, 'geetest_success_radar_tip_content'), '验证成功'))
        print(success)
        
        # 失败后重试
        if not success:
            self.crack()
        else:
            self.login()


if __name__ == '__main__':
    crack = CrackGeetest()
    crack.crack()