高阶爬虫实战：破解极验滑动验证码

# -*- coding: utf-8 -*-
import random
import time, re
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.action_chains import ActionChains
from PIL import Image
import requests
from io import BytesIO

class HuXiu(object):
    def __init__(self):
        chrome_option = webdriver.ChromeOptions()
        # chrome_option.set_headless()

        self.driver = webdriver.Chrome(executable_path=r"/usr1/webdrivers/chromedriver", chrome_options=chrome_option)
        self.driver.set_window_size(1440, 900)

    def visit_index(self):
        self.driver.get("https://www.huxiu.com/")

        WebDriverWait(self.driver, 10, 0.5).until(EC.element_to_be_clickable((By.XPATH, '//*[@class="js-register"]')))
        reg_element = self.driver.find_element_by_xpath('//*[@class="js-register"]')
        reg_element.click()

        WebDriverWait(self.driver, 10, 0.5).until(EC.element_to_be_clickable((By.XPATH, '//div[@class="gt_slider_knob gt_show"]')))

        # 进入模拟拖动流程
        self.analog_drag()

    def analog_drag(self):
        #鼠标移动到拖动按钮，显示出拖动图片
        element = self.driver.find_element_by_xpath('//div[@class="gt_slider_knob gt_show"]')
        ActionChains(self.driver).move_to_element(element).perform()
        time.sleep(3)

        # 刷新一下极验图片
        element = self.driver.find_element_by_xpath('//a[@class="gt_refresh_button"]')
        element.click()
        time.sleep(1)

        # 获取图片地址和位置坐标列表
        cut_image_url, cut_location = self.get_image_url('//div[@class="gt_cut_bg_slice"]')
        full_image_url, full_location = self.get_image_url('//div[@class="gt_cut_fullbg_slice"]')

        # 根据坐标拼接图片
        cut_image = self.mosaic_image(cut_image_url, cut_location)
        full_image = self.mosaic_image(full_image_url, full_location)

        # 保存图片方便查看
        cut_image.save("cut.jpg")
        full_image.save("full.jpg")

        # 根据两个图片计算距离
        distance = self.get_offset_distance(cut_image, full_image)

        # 开始移动
        self.start_move(distance)

        # 如果出现error
        try:
            WebDriverWait(self.driver, 5, 0.5).until(EC.element_to_be_clickable((By.XPATH, '//div[@class="gt_ajax_tip gt_error"]')))
            print("验证失败")
            return
        except TimeoutException as e:
            pass

        # 判断是否验证成功
        try:
            WebDriverWait(self.driver, 10, 0.5).until(EC.element_to_be_clickable((By.XPATH, '//div[@class="gt_ajax_tip gt_success"]')))
        except TimeoutException:
            print("again times")
            time.sleep(5)
            # 失败后递归执行拖动
            self.analog_drag()
        else:
            # 成功后输入手机号，发送验证码
            self.register()

    # 获取图片和位置列表
    def get_image_url(self, xpath):
        link = re.compile('background-image: url\("(.*?)"\); background-position: (.*?)px (.*?)px;')
        elements = self.driver.find_elements_by_xpath(xpath)
        image_url = None
        location = list()
        for element in elements:
            style = element.get_attribute("style")
            groups = link.search(style)
            url = groups[1]
            x_pos = groups[2]
            y_pos = groups[3]
            location.append((int(x_pos), int(y_pos)))
            image_url = url
        return image_url, location

 (部分代码)