python_利用selenium 爬取淘宝商品

from  selenium import webdriver
from selenium.webdriver.common.by import  By
from selenium.webdriver.support.ui import WebDriverWait
from  selenium.webdriver.support import expected_conditions as EC
from bs4 import  BeautifulSoup
import re
from  time import  sleep
driver = webdriver.Chrome()
wait = WebDriverWait(driver,10)
def search():
    try:
        driver.get("https://www.taobao.com/")
        intext = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR,"#q"))
        )
        submit = wait.until(
            EC.element_to_be_clickable((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button"))
        )
        intext.send_keys('美食')
        submit.click()
        page_num = wait.until(EC.presence_of_element_located((By.CLASS_NAME,"total")))
        return  page_num.text
    except TimeoutError:
        return search()
def next_page(num):
    try:
        page_text = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.form > input")))
        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')))
        page_text.clear()
        page_text.send_keys(num)
        sleep(2)
        submit.click()
        wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'#mainsrp-pager > div > div > div > ul > li.item.active > span'),str(num)))
        return get_products()
    except TimeoutError:
        next_page(num)

def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))
    html =driver.page_source
    soup = BeautifulSoup(html, 'html.parser')

    items = soup.find_all('div',{'class':'item J_MouserOnverReq '})

    for item in items:
        yield  {'title':item.img.attrs['alt'],'price':item.strong.text}
def main():
    total = search()
    total = int(re.search('\d+',total).group())

    for i  in range(2,total+1):
         ss=next_page(i)
         for s in ss:
             print(s['title'])

   # print(total.split()[1])

if __name__ == '__main__':
    main()