Python爬虫入门教程 58-100 python爬虫高级技术之验证码篇4-极验证识别技术之一

import time
import 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

if __name__ == '__main__':
    h = Geek_Huxiu()
    h.run()

    def __init__(self):
        self.driver = webdriver.Chrome()  
        self.driver.set_window_size(1366,768)

    def run(self):
        self.driver.get("https://www.huxiu.com/")  # 打开浏览器
    
        WebDriverWait(self.driver,10).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).until(EC.element_to_be_clickable((By.XPATH,'//div[@class="gt_slider_knob gt_show"]')))

        # 模拟拖动
        self.analog_drag()

driver: 传入WebDriver实例，即我们上例中的driver
timeout: 超时时间，等待的最长时间（同时要考虑隐性等待时间）
poll_frequency: 调用until或until_not中的方法的间隔时间，默认是0.5秒
ignored_exceptions: 忽略的异常，如果在调用until或until_not的过程中抛出这个元组中的异常, 则不中断代码，继续等待；
如果抛出的是这个元组外的异常，则中断代码，抛出异常。默认只有NoSuchElementException。

WebDriverWait(driver, 超时时长, 调用频率, 忽略异常).until(可执行方法, 超时时返回的信息)

    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)


        # 刷新一下极验证图片
        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"]')

        print(cut_image_url)
        print(cut_location)

    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)))
            if not image_url:
                image_url = url
        return image_url, location

    def splicing_image(self,image_url,location):
        res = requests.get(image_url)
        file = BytesIO(res.content)
        img = Image.open(file)
        image_upper = []
        image_down = []
        for pos in location:
            if pos[1] == 0:
                # y值为0的坐标  属于图片上半部分，高度58
                image_upper.append(img.crop((abs(pos[0]), 0, abs(pos[0]) + 10, 58)))
            else:
                # y值为58的坐标 属于图片上半部分，高度58
                image_down.append(img.crop((abs(pos[0]), 58, abs(pos[0]) + 10, img.height)))
        # 画布的x轴偏移量
        x_offset = 0 
        # 创建一张画布
        new_img = Image.new("RGB", (260, img.height))
        for img in image_upper:
            new_img.paste(img, (x_offset, 58))
            x_offset += img.width

        x_offset = 0
        for img in image_down:
            new_img.paste(img, (x_offset, 0))
            x_offset += img.width

        return new_img

        # 将图片存储到本地
        cut_image.save("cut.jpg")
        full_image.save("full.jpg")