selenium模拟爬取淘宝指定类商品

import pymysql
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from urllib.parse import quote
from pyquery import PyQuery as pq

browser = webdriver.Chrome()


wait = WebDriverWait(browser,10)
KEYWORD = 'iPad'

def index_page(page):
    """
    抓取索引页
    :param page:页码
    """
    print('正在爬去第',page,'页')
    try:
        url = 'https://s.taobao.com/search?q=' + quote(KEYWORD)
        browser.get(url)
        if page > 1:
            input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager div.form > input')))
            submit = wait.until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager div.form > span.btn.J_Submit')))
            input.clear()
            input.send_keys(page)
            submit.click()
        wait.until(
            EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#mainsrp-pager li.item.active > span'), str(page)))
        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-itemlist .items .item')))
        get_products()
    except TimeoutException:
        index_page(page)


def get_products():
    """
    提取商品数据
    """
    html = browser.page_source
    # print(html)
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'title': item.find('.title').text(),
            'deal': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'price':item.find('.price').text(),
            'location':item.find('.location').text(),
            'image': item.find('.pic .img').attr('data-src'),
        }
        print(product)
        conn = pymysql.connect(
           """数据库连接"""

MAX_PAGE = 40
def main():
    """
    遍历每一页
    :return:
    """
    for i in range(1,MAX_PAGE+1):
        index_page(i)
        # browser.close()


if __name__ == '__main__':
    main()