pip install selenium

import time
import re
import csv

from selenium import webdriver
from selenium.webdriver import ActionChains

from 淘宝爬虫 import constans

def search_product(key):
    """模拟搜索商品，登陆账户，获取最大页数"""
    driver.get(‘http://www.taobao.com‘)
    driver.find_element_by_id(‘q‘).send_keys(key)  # 输入框输入商品关键字
    driver.find_element_by_class_name(‘btn-search‘).click()  # 点击搜索按钮
    driver.implicitly_wait(10)  # 隐式等待
    driver.maximize_window()  # 最大化浏览器

def main()
   search_product(keyword)
    
if __name__ == ‘__main__‘:
    keyword = input(‘请输入你要查询的商品数据：‘)
    driver = webdriver.Chrome()
    main()

    driver.find_element_by_xpath(‘//*[@id="fm-login-id"]‘).send_keys(constans.USERNAME)  # 找到用户名输入账号
    time.sleep(1)
    driver.find_element_by_xpath(‘//*[@id="fm-login-password"]‘).send_keys(constans.PASSWORD)  # 找到密码框输入密码
    time.sleep(2)
    
    login = driver.find_element_by_xpath("//span[contains(@class, ‘btn_slide‘)]")  # 找到滑动验证码滑块  手写
    action = ActionChains(driver)  # 创建动作连对象
    action.click_and_hold(on_element=login)  # 点击滑块维持动作
    action.move_by_offset(xoffset=258, yoffset=0) # 设置动作链坐标长度
    action.pause(0.5).release().perform()  # 设置动作链执行时间  释放鼠标  执行动作链
    driver.find_element_by_xpath(‘//*[@id="login-form"]/div[4]/button‘).click()  # 找到登陆按钮点击
    driver.implicitly_wait(10)  # 隐式等待

def get_product(): 
  
    for div in divs:
        info = div.find_element_by_xpath(‘.//div[@class="row row-2 title"]/a‘).text  # 商品名称
        price = div.find_element_by_xpath(‘.//strong‘).text + ‘元‘  # 商品价格
        deal = div.find_element_by_xpath(‘.//div[@class="deal-cnt"]‘).text  # 付款人数
        name = div.find_element_by_xpath(‘.//div[@class="shop"]/a‘).text  # 店铺名称
        print(info, price, deal, name, sep=‘|‘)  # 分隔符
        with open(‘data2.csv‘, ‘a‘, newline=‘‘) as csvfile:  # newline=‘‘  指定一行一行写入
            csvwriter = csv.writer(csvfile, delimiter=‘,‘)  # delimiter=‘,‘  csv数据的分隔符
            csvwriter.writerow([info, price, deal, name])

 page = driver.find_element_by_xpath(‘//*[@id="mainsrp-pager"]/div/div/div/div[1]‘).text  # 找到页码标签
    page = re.findall(‘(\d+)‘, page)[0]
    # print(‘商品页数：‘, page)
    return int(page)

def main():
    """程序的入口"""
    print(‘正在爬取第1页的数据‘)
    page = search_product(keyword)
    get_product()

    page_num = 1
    while page_num != page:
        print(‘*‘ * 100)
        print(‘正在爬取第{}页的数据‘.format(page_num + 1))
        print(‘*‘ * 100)
        driver.get(‘https://s.taobao.com/search?q={}&s={}‘.format(keyword, 44 * page_num))  # 拼接产品url地址
        driver.implicitly_wait(10)  # 浏览器等待方法
        get_product()
        page_num += 1

    driver.quit()