Python web自動化爬蟲-selenium/處理驗證碼/Xpath

# coding:utf-8
import time
import random
from time import sleep
from csv import writer
from selenium import webdriver
from selenium.webdriver.common.by import By
from chaojiying import Chaojiying_Client
from selenium.webdriver import ActionChains


driver = webdriver.Chrome()

#開啟網頁
def open_web(search_name):
    driver.get("https://www.izaiwen.cn/pro/sonE-stwE08?psnname={}".format(search_name))
    time.sleep(6)
#載入cookie
#    with open("cookies.json", "r") as file:
#        cookies = json.load(file)
    cookies = [{'name': 'HMACCOUNT', 'value': 'xxxxxxxxx'},
    {'name': 'heiheihei', 'value': 'xxxxxxxxx'},
    {'name': 'hahaha', 'value': 'xxxxxxx'},
    {'name': '_', 'value': 'xxxxxxxxxxx'},
    {'name': 'acw', 'value': 'xxxxxxxxxxxx'},
    {'name': 'cer', 'value': 'xxxxxxxxxx'},
    {'name': 'ession', 'value': 'xxxxxxxxxx'},
    {'name': 'userId', 'value': 'xxxxx'},
    {'name': 'uuid', 'value': 'xxxxxxxxxxxxxxxxxxx'},
    ] 
    for cookie in cookies:
        driver.add_cookie(cookie)
    time.sleep(5)
    driver.refresh()
    time.sleep(random.randrange(5,10))

#檢測是否在驗證碼頁面
def check_condition():
    header=driver.title#提取頁面標題
#    header=driver.find_element(By.XPATH,'/html/head/title').text  此方法無效，只能取出空字串
    print(header)
    if header == '請完成安全驗證': #如果在驗證碼頁面返回f值
        return 'f'
    else:
        return 't'

#基於xpath定位標籤獲取資料
def get_information():
    parent_element=driver.find_elements(By.XPATH,'.//div[@class="item-box layui-card "]')
    for child_element in parent_element:
        target_element=child_element.find_elements(By.XPATH,'.//div[@class="layui-col-xs4"]')
        print(name)
        info=''
        for n in target_element:
            info+=n.text#提取標籤中的資料
            info+=','
        print(info)
        list_data=[name,info]
        #儲存資料
        with open("資訊.csv", "a", newline="") as f_object:
            writer_object = writer(f_object)
            writer_object.writerow(list_data)
        time.sleep(5)
#自動識別驗證碼並提交至超級鷹打碼平臺識別
def anti_anti_spider():
    #找到包含驗證碼的元素
    img=driver.find_element(By.XPATH,'.//div[@id="aliyunCaptcha-window-embed"]')
    #對此元素進行截圖
    img.screenshot('D:/SeleniumX/yzm.png')
    #由於新版本的selenium的點選定位是從元素中心點開始，因此計算元素的尺寸來使點選從左上角開始
    img_half_width = float(img.rect['width'])/2
    img_half_height = float(img.rect['height'])/2
    #初始化超級鷹程式碼，需要從其官網下載程式碼放到此檔案相同資料夾中並匯入
    chaojiying = Chaojiying_Client('', '', '')#賬號，密碼，軟體ID
    #提交到平臺並獲得結果
    im = open('D:/SeleniumX/yzm.png', 'rb').read()
    yzm_result=chaojiying.PostPic(im, 9101)['pic_str']
    time.sleep(10)
    print(yzm_result)
#    for index in result.split('|'): #以"|"進行分割，得到一個列表，並迴圈出每一個字的座標，在這裡因為只返回一個結果所以不需要
    x = float(yzm_result.split(',')[0]) # 得到x軸的座標
    y = float(yzm_result.split(',')[1]) # 得到y軸的座標
    #使用動作鏈模擬點選操作
    action = ActionChains(driver) #建立動作鏈,y).click().perform()
    action.move_to_element_with_offset(img,x-img_half_width,y-img_half_height).click().perform()
    time.sleep(10)

    

#主程式
list_name=[]#需要爬取的人名，用於構建頁面url
for name in list_name:
    open_web(name)#開啟該網頁
    flag=check_condition()#檢測是否觸發了驗證碼
    print(flag)
    if flag == 'f':#若觸發了驗證碼，開始識別並點選驗證碼
        time.sleep(30)
        anti_anti_spider()
        time.sleep(15)
        get_information()
    else:
        time.sleep(5)
        get_information()
    time.sleep(random.randrange(10,30))
    print(name)