2020-10-26

破解极验验证码，且没有背景图，成功率80%左右

import time
from io import BytesIO
from urllib.parse import urlencode
from PIL import Image
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import random
import json, os
import urllib3
from selenium.common import exceptions as ex
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities


class SVC:
    """
    解决滑动验证码，没有原背图
    """

    def __init__(self):
        prefs = {
            'profile.default_content_setting_values': {
                'notifications': 2
            }
        }
        self.url = 'https://www.zhipin.com/user/login.html'
        self.chrome_options = Options()
        self.chrome_options.add_experimental_option('prefs', prefs)  # 禁止弹窗
        self.chrome_options.add_argument("-incognito")  # 无痕模式，不用清理浏览器换缓存
        self.chrome_options.add_experimental_option('excludeSwitches', ['enable-automation'])

        self.driver = webdriver.Chrome(chrome_options=self.chrome_options)
        self.driver.maximize_window()
        self.driverwait = WebDriverWait(self.driver, 30)
        self.user = ''  # 用户名
        self.password = ''  # 密码
        self.location = {}
        self.size = {'width': 260, 'height': 160}  # 验证码图片的宽、高
        self.BORDER = 40

    # def __del__(self):
    #     self.driver.quit()

    def setAttribute(self, elementObj, attributeName, value):
        # 封装设置页面对象的属性值的方法
        # 调用JavaScript代码修改页面元素的属性值，arguments[0]－［2］分别会用后面的
        # element、attributeName和value参数值进行替换，并执行该JavaScript代码
        self.driver.execute_script("arguments[0].setAttribute (arguments[1],arguments[2])", elementObj, attributeName,
                                   value)

    def removeAttribute(self, elementObj, attributeName):
        # 封装删除页面元素属性的方法
        # 调用JavaScript代码删除页面元素的指定的属性，arguments[0]－［1］分别会用后面的
        # element、attributeName参数值进行替换，并执行该JavaScript代码
        self.driver.execute_script("arguments[0].removeAttribute(arguments[1])", elementObj, attributeName)

    def get_geetest_button(self):
        """
        获取初始验证按钮
        :return:
        """

        button = self.driverwait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_radar_tip')))
        return button

    def get_slider(self):
        """
        获取滑块
        :return: 滑块对象
        """
        slider = self.driverwait.until(EC.element_to_be_clickable((By.CLASS_NAME, 'geetest_slider_button')))
        return slider

    def open(self):
        """
        打开网页输入用户名密码
        :return: None
        """
        self.driver.get(self.url)
        self.driver.implicitly_wait(30)  # 隐式等待,知道页面加载完成出现
        self.driver.set_page_load_timeout(5)
        self.driver.set_script_timeout(5)

        user = self.driver.find_element_by_xpath(
            '//*[@id="wrap"]/div[2]/div[1]/div[2]/div[1]/form/div[3]/span[2]/input')

        password = self.driver.find_element_by_xpath(
            '//*[@id="wrap"]/div[2]/div[1]/div[2]/div[1]/form/div[4]/span/input')
        user.send_keys(self.user)
        password.send_keys(self.password)

    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_geetest_image(self, name):
        """
        获取验证码图片 captcha.png
        :return: 图片对象
        """
        left, top, right, bottom = (
            self.location['x'] + 30,
            self.location['y'] + 65,
            self.location['x'] + self.size['width'] + 200,
            self.location['y'] + self.size['height'] + 80)
        screenshot = self.get_screenshot()
        captcha = screenshot.crop((left, top, right, bottom))
        captcha.save(name)
        return captcha

    def getImg(self):
        time.sleep(3)
        ele = self.driver.find_elements_by_tag_name('canvas')
        self.location = ele[0].location
        self.setAttribute(ele[1], 'style', 'display: none;')  # 隐藏滑块
        self.get_geetest_image('captcha_up.png')  # 有缺口的背景图
        self.setAttribute(ele[0], 'style', 'display: none;')  # 隐藏缺口图
        self.removeAttribute(ele[2], 'style')  # 移除隐藏属性，以显示地面图片
        self.get_geetest_image('captcha_down.png')  # 背景原图
        self.removeAttribute(ele[0], 'style')  # 移除缺口图隐藏属性，并显示
        time.sleep(0.5)
        self.removeAttribute(ele[1], 'style')  # 移除滑块隐藏属性，显示
        time.sleep(0.5)
        self.setAttribute(ele[2], 'style', 'display: none;')  # 移除背景图隐藏属性，显示

    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:
        """
        left = 0
        for i in range(left, image1.size[0]):  # 遍历像素值，rgb
            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
        对比，滑块在滑动时，与原图对比的相似程度
        """
        # 取两个图片的像素点
        pixel1 = image1.load()[x, y]
        pixel2 = image2.load()[x, y]
        threshold = 50  # 设置阀值，相似度
        if abs(pixel1[0] - pixel2[0]) < threshold and abs(pixel1[1] - pixel2[1]) < threshold and abs(
                pixel1[2] - pixel2[2]) < threshold:  # pixel[2]=blue

            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
        list1 = []
        list2 = []
        list3 = []

        # 当前位移
        for i in range(round(distance / 4)):
            list1.append(1)
            list2.append(4)
            list3.append(1)
        return list1 + list2 + list3

    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:
            time.sleep(0.1)
            ActionChains(self.driver).move_by_offset(xoffset=x, yoffset=0).perform()
        time.sleep(1)
        ActionChains(self.driver).pause(random.randint(6, 14) / 10).release(slider).perform()

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

    def crack(self):
        self.getImg()
        Image2 = Image.open('captcha_down.png')  # 背景原图
        Image1 = Image.open('captcha_up.png')
        gap = self.get_gap(Image1, Image2)
        print('缺口位置', gap)
        # 减去缺口位移
        if gap <= 30:
            gap += 9

        if gap <= 40:
            gap += 5

        elif gap <= 50:
            gap = 50

        elif gap < 60:
            gap -= 2

        elif gap <= 70:
            gap -= 5

        elif gap <= 80:
            gap -= 8

        elif gap <= 90:
            gap -= 12

        elif gap <= 100:
            gap -= 15

        elif gap <= 110:
            gap -= 20

        elif gap <= 125:
            gap -= 22

        elif gap <= 135:
            gap -= 27

        elif gap <= 145:
            gap -= 30

        elif gap <= 165:
            gap -= 35

        elif gap <= 185:
            gap -= 42

        else:
            gap -= 45
        track = self.get_track(gap)
        slider = self.get_slider()
        self.move_to_gap(slider, track)
        time.sleep(random.randint(3, 30) / 20)
        success = False
        try:
            success = self.driverwait.until(
                EC.text_to_be_present_in_element((By.CLASS_NAME, 'geetest_success_radar_tip_content'), '验证成功'))
        except:
            print('失败')

        if not success:
            self.driver.delete_all_cookies()
            time.sleep(0.5)
            self.start()
            self.crack()
        else:
            self.login()
            time.sleep(1)

    def login(self):
        """
        登录
        :return: None
        """
        submit = self.driverwait.until(
            EC.element_to_be_clickable((By.XPATH, '//*[@id="wrap"]/div[2]/div[1]/div[2]/div[1]/form/div[6]/button')))
        submit.click()
        print('登录成功')
        
if __name__ == '__main__':
    svc = SVC()
    svc.start()
    svc.crack()