22. 极验滑动验证码的识别

22.1 滑动验证码的识别介绍

  • 本节目标:用程序识别极验滑动验证码的验证,包括分析识别思路、识别缺口位置、生成滑块拖动路径、模拟实现滑块拼合通过验证等步骤。
  • 准备工作:本次案例我们使用Python库是Selenium,浏览器为Chrome。请确保已安装Selenium库和ChromeDriver浏览器驱动。
  • 了解极验滑动验证码:
    • 极验滑动验证码官网为:http://www.geetest.com/
    • 验证方式为拖动滑块拼合图像,若图像完全拼合,则验证成功,否则需要重新验证,如图所示:

  • 接下来我们链接地址:https://account.geetest.com/login,打开极验的管理后台登录页面,完成自动化登录操作。

22.2 实现步骤:

① 初始化

  • 初始化链接地址、创建模拟浏览器对象、设置登录账户和密码等信息。
EMAIL = '登录账户'
PASSWORD = '登录密码'

class CrackGeetest():
    def __init__(self):
        self.url = 'https://account.geetest.com/login'
        self.browser = webdriver.Chrome()
        #设置显示等待时间
        self.wait = WebDriverWait(self.browser, 20)
        self.email = EMAIL
        self.password = PASSWORD

    def crack():
        pass

# 程序主入口
if __name__ == '__main__':
    crack = CrackGeetest()
    crack.crack()

② 模拟登录填写,点开滑块验证

  • 在实例化CrackGeetest对象后调用crack()方法开始模拟登录验证...
  • 调用open()方法,打开登录界面,获取账户和密码输入框节点,完成账户和密码的输入。
  • 调用get_geetest_button()方法获取滑动验证按钮,并点击。
class CrackGeetest():
    #...

    def get_geetest_button(self):
        ''' 获取初始验证按钮,return:按钮对象 '''
        button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_tip')))
        return button

    def open(self):
        ''' 打开网页输入用户名密码, return: None '''
        self.browser.get(self.url)
        email = self.wait.until(EC.presence_of_element_located((By.ID, 'email')))
        password = self.wait.until(EC.presence_of_element_located((By.ID, 'password')))
        email.send_keys(self.email)
        password.send_keys(self.password)

    def crack(self):
        # 输入用户名密码
        self.open()
        # 点击验证按钮
        button = self.get_geetest_button()
        button.click()
        #...
    #...

③ 获取并储存有无缺口的两张图片

  • 首先获取无缺口的验证图片,并保存到本地
  • 获取滑块对象,并执行点击,让浏览器中显示有缺口图片
  • 获取有缺口的验证图片,并保存到本地

    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, 'geetest_canvas_img')))
        time.sleep(2)
        location = img.location
        size = img.size
        top,bottom,left,right = location['y'],location['y']+size['height'],location['x'],location['x']+size['width']
        return (top, bottom, left, right)

    def get_screenshot(self):
        ''' 获取网页截图, return: 截图对象 '''
        #浏览器截屏
        screenshot = self.browser.get_screenshot_as_png()
        screenshot = Image.open(BytesIO(screenshot))
        return screenshot

    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)
        screenshot = self.get_screenshot()
        #从网页截屏图片中裁剪处理验证图片
        captcha = screenshot.crop((left, top, right, bottom))
        captcha.save(name)
        return captcha

    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, 'geetest_slider_button')))
        return slider

    def crack(self):
        #...

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

        #...

④ 获取缺口位置

  • 对比两张图片的所有RBG像素点,得到不一样像素点的x值,即要移动的距离

BORDER = 6
INIT_LEFT = 60

class CrackGeetest():  
    def get_gap(self, image1, image2):
        ''' 获取缺口偏移量, 参数:image1不带缺口图片、image2带缺口图片。返回偏移量 '''
        left = 65
        for i in range(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
        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(R、G、B)
        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 crack(self):
        #...

        # 获取缺口位置
        gap = self.get_gap(image1, image2)
        print('缺口位置', gap)
        # 减去缺口位移
        gap -= BORDER

⑤ 获取移动轨迹

  • 模拟人的行为习惯(先匀加速拖动后匀减速拖动),把需要拖动的总距离分成一段一段小的轨迹

    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 crack(self):
        #...

        # 获取移动轨迹
        track = self.get_track(gap)
        print('滑动轨迹', track)

⑥ 按照轨迹拖动,完全验证


    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 crack(self):
        #...

        # 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)

⑦ 完成登录


    def login(self):
        ''' 执行登录 return: None '''
        submit = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'login-btn')))
        submit.click()
        time.sleep(10)
        print('登录成功')

    def crack(self):
        #...

        # 失败后重试
        if not success:
            self.crack()
        else:
            self.login()

22.3 完整代码:

import time
from io import BytesIO
from PIL import Image
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

EMAIL = '122794105@qq.com'
PASSWORD = 'python123'
BORDER = 6

class CrackGeetest():
    def __init__(self):
        self.url = 'https://account.geetest.com/login'
        self.browser = webdriver.Chrome()
        #设置显示等待时间
        self.wait = WebDriverWait(self.browser, 20)
        self.email = EMAIL
        self.password = PASSWORD

    def __del__(self):
        #self.browser.close()
        pass

    def get_geetest_button(self):
        ''' 获取初始验证按钮,return:按钮对象 '''
        button = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_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, 'geetest_canvas_img')))
        time.sleep(2)
        location = img.location
        size = img.size
        top,bottom,left,right = location['y'],location['y']+size['height'],location['x'],location['x']+size['width']
        return (top, bottom, left, right)

    def get_screenshot(self):
        ''' 获取网页截图, return: 截图对象 '''
        #浏览器截屏
        screenshot = self.browser.get_screenshot_as_png()
        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, 'geetest_slider_button')))
        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)
        screenshot = self.get_screenshot()
        #从网页截屏图片中裁剪处理验证图片
        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)
        email = self.wait.until(EC.presence_of_element_located((By.ID, 'email')))
        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, 参数:image1不带缺口图片、image2带缺口图片。返回偏移量 '''
        left = 65
        for i in range(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
        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(R、G、B)
        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):
        ''' 执行登录 return: None '''
        submit = self.wait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'login-btn')))
        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()
        button.click()
        # 获取验证码图片
        image1 = self.get_geetest_image('captcha1.png')
        # 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
        gap -= BORDER
        # 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()

# 程序主入口
if __name__ == '__main__':
    crack = CrackGeetest()
    crack.crack()

results matching ""

    No results matching ""