python+selenium破解极验验证登录

1、前言：

　　目前很多网站会在正常的账号密码认证之外加一些验证码，以此来明确区分人/机行为，最典型的就是极验滑动验证。（如下图）

这里我们以简单实例说明如何实现自动校验类似验证。

2、步骤：

1）点击验证，弹出验证码图片；

2）操作JS，获取完整验证码图片并截图；

3）操作JS恢复原图，获取带有缺口的验证码图片并截图；

4）对比两张图片所有的像素点，得到要移动的距离；

5）模拟人的行为，把需要拖动的总距离分成一段一段的轨迹；

6）按照轨迹拖动，完成验证；

7）完成登录；

3、准备工作：

1）安装chrome浏览器；

2）配置好python+selenium环境；

3）安装Pillow模块；

4、详细代码：

from selenium import webdriver
from selenium.webdriver import ActionChains  # 破解滑动验证码的时候用的 可以拖动图片
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from PIL import Image
from io import BytesIO
import time

class AccessCode(object):
    def __init__(self,driver):
        self.driver = driver
        self.wait = WebDriverWait(driver, 20)
        self.border = 6 #设置偏差值
    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_window')))
        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
        """
        screenshot = self.driver.get_screenshot_as_png()
        screenshot = Image.open(BytesIO(screenshot))
        return screenshot

    def get_image1(self,filename):
        '''
        获取完整验证码图片
        :return: 图片对象
        '''
        time.sleep(0.2)
        js_code = '''document.getElementsByClassName('geetest_canvas_fullbg')[0].style.display="block";'''
        time.sleep(1)
        self.driver.execute_script(js_code)
        # 截取图片
        top, bottom, left, right = self.get_position()
        screenshot = self.get_screenshot()
        captcha = screenshot.crop((2 * left, 2 * top, 2 * right, 2 * bottom))
        size = 258, 159
        captcha.thumbnail(size)  # 生成缩略图
        captcha.save(filename)
        return captcha

    def get_image2(self,filename):
        '''
        获取有缺口的验证码图片
        :param filename: 图片名称
        :return: 有缺口的验证码图片对象
        '''
        time.sleep(0.2)
        js_code = '''document.getElementsByClassName('geetest_canvas_fullbg')[0].style.display="none";'''
        self.driver.execute_script(js_code)
        time.sleep(1)
        # 截取图片
        top, bottom, left, right = self.get_position()
        screenshot = self.get_screenshot()
        captcha = screenshot.crop((2*left, 2*top, 2*right, 2*bottom))
        size = 258, 159
        captcha.thumbnail(size)  # 生成缩略图
        captcha.save(filename)
        return captcha

    def get_gap(self,image1, image2):
        """
        获取缺口偏移量
        :param img1: 不带缺口图片
        :param img2: 带缺口图片
        :return:缺口偏移量
        """
        left = 57
        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,img1, img2, 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 = img1.getpixel((x, y))
        pixel2 = img2.getpixel((x, y))

        for i in range(0, 3):
            if abs(pixel1[i] - pixel2[i]) >= 60:
                return False
        return True

    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.driver).click_and_hold(slider).perform()
        for x in track:
            ActionChains(self.driver).move_by_offset(xoffset=x, yoffset=0).perform()
        time.sleep(0.5)
        ActionChains(self.driver).release().perform()

    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):
        '''验证操作'''
        #1.针对完整的图片进行截取
        image1 = self.get_image1('snap_full.png')
        #2.针对有缺口的图片进行截取
        image2 = self.get_image2('snap.png')
        #3.对比两张图片,获取滑动距离
        distance = self.get_gap(image1,image2)
        #4减去缺口位移
        distance -= self.border
        #5.获取滑块对象
        slider = self.get_slider()
        #6.模拟人为滑动轨迹
        track = self.get_track(distance)
        #7.拖动滑块
        self.move_to_gap(slider, track)
        time.sleep(0.5)
        #8.失败重试
        try:
            success = self.wait.until(EC.text_to_be_present_in_element((By.XPATH,"//span[@class='geetest_success_radar_tip_content']"), '验证成功'))
            if not success:
                content = self.driver.find_element_by_xpath("//div[@class='geetest_result_content']").text
                if "怪物吃了拼图" in content:
                    # 如果出现"怪物吃了拼图"字样，需要等待3S后继续操作
                    time.sleep(3)
                if "拖动滑块将悬浮图像正确拼合" in content:
                    #距离计算错误，刷新图片验证码重试
                    self.driver.find_element_by_xpath("/html/body/div[3]/div[2]/div[1]/div/div[2]/div/a[2]").click()
                self.crack()
            else:
                #博客园校验成功后自动登录跳转
                time.sleep(5)
                print("------------登录成功--------------")
        except Exception as e:
            content = self.driver.find_element_by_xpath("//div[@class='geetest_result_content']").text
            if "怪物吃了拼图" in content:
                # 如果出现"怪物吃了拼图"字样，需要等待3S后继续操作
                time.sleep(3)
            if "拖动滑块将悬浮图像正确拼合" in content:
                # 距离计算错误，刷新图片验证码重试
                self.driver.find_element_by_xpath("/html/body/div[3]/div[2]/div[1]/div/div[2]/div/a[2]").click()
            self.crack()

if __name__ == '__main__':
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_argument('--start-maximized')  # 指定浏览器分辨率
    chrome_options.add_argument('--disable-gpu')  # 谷歌文档提到需要加上这个属性来规避bug
    driver = webdriver.Chrome(executable_path=DRIVER_PATH, options=chrome_options) #DRIVER_PATH为chromedriver存放路径，自行变更
    crack = AccessCode(driver)
    # 1.打开网页
    driver.get("https://passport.cnblogs.com/user/signin")
    driver.maximize_window() #窗口最大化
    # 2.输入用户名,username自行补全
    driver.find_element_by_xpath("//input[@id='input1']").send_keys(username)
    # 3.输入密码,password自行补全
    driver.find_element_by_xpath("//input[@id='input2']").send_keys(password)
    # 4.点击登录，弹出验证按钮
    driver.find_element_by_xpath("//input[@id='signin']").click()
    # 5.点击验证按钮
    time.sleep(3)
    driver.find_element_by_xpath("//div[@class='modal-content center-block']").click()
    driver.find_element_by_xpath("//div[@class='geetest_radar_tip']").click()
    # 6.调用验证
    crack.crack()