pymysql存入数据库时产生的一些问题

应该是逻辑有点问题。4个lis在在循环外叠加的，每次zip都是上一次的叠加，相当于 a = 3 * 第一页数量 + 2* 第二页数量 + 1 * 第三页数量(猜测是页数吧，别介意)。按我这个改法再试试？

def data(value):
    # 执行一组js程序，拉到页面底部
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    sleep(2)
    global shop_name_list, shop_price_list, shop_people_list, shop_location_list, a
    shop_name_list = []
    shop_price_list = []
    shop_people_list = []
    shop_location_list = []
    a = 0
    b = 44
    for i in range(1, 3):
        page = browser.page_source
        soup = BeautifulSoup(page, 'lxml')
        shop_data_list = soup.find('div', class_='grid g-clearfix').find_all_next('div', class_='items')
        for shop_data in shop_data_list:
            # 商品名称
            shop_image_data = shop_data.find_all('div', class_='pic')
            for shop_data_a in shop_image_data:
                shop_data_a = shop_data_a.find_all('a', class_='pic-link J_ClickStat J_ItemPicA')
                for shop_name in shop_data_a:
                    shop_name = shop_name.find_all('img')[0]['alt']
                    shop_name_list.append(shop_name)
            # 商品价格
            shop_price_data = shop_data.find_all('div', class_='price g_price g_price-highlight')
            for shop_price in shop_price_data:
                shop_price_list.append(shop_price.text.strip())
            # 付款人数
            shop_people_number_data = shop_data.find_all('div', class_='deal-cnt')
            for shop_people_number in shop_people_number_data:
                shop_people_list.append(shop_people_number.text)
            # 地址s
            shop_location_data = shop_data.find_all('div', class_='location')
            for shop_location in shop_location_data:
                shop_location_list.append(shop_location.text)
        b += 44
        browser.get(f"https://s.taobao.com/search?q={value}&s={b}")
        sleep(0.5)
    shop_data = zip(shop_name_list, shop_price_list, shop_people_list, shop_location_list)
    for data in shop_data:
        print(data)
        a += 1
    print('已成功爬取：%s条信息' % a)
    print(shop_price_list)
    return shop_name_list, shop_price_list, shop_people_list, shop_location_list, a

print('a: {} len_shop_name_lis: {}'.format(a, len(shop_name_list))) # 加一行打印，看下是不是 a + 1 > len
for i in range(a):
    li_name = shop_name_list[i]

# -*- coding:utf-8 -*-
from time import sleep
from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from bs4 import BeautifulSoup
import pymysql
from matplotlib import pyplot as plt
import lxml

def login_info():
    #通过扫码的形式去登录淘宝账号
    browser.find_element_by_xpath('//*[@id="login"]/div[1]/i').click()
    sleep(5)
    #点击淘宝首页
    taobao_index = browser.find_element_by_xpath('//*[@id="J_SiteNavHome"]/div/a')
    taobao_index.click()
    sleep(1)
def search_product(value):
    # 标签定位
    search_input = browser.find_element_by_id('q')
    # 标签交互
    search_input.send_keys(value)
    # 执行一组js程序，拉到页面底部
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    sleep(2)
    # 点击搜索按钮
    btn = browser.find_element_by_css_selector('.btn-search')
    btn.click()
def data(value):


    # 执行一组js程序，拉到页面底部
    browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
    sleep(2)
    global shop_name_list, shop_price_list, shop_people_list, shop_location_list,a
    shop_name_list = []
    shop_price_list = []
    shop_people_list = []
    shop_location_list = []
    a = 0
    b = 44
    for i in range(1,3):
        page = browser.page_source
        soup = BeautifulSoup(page, 'lxml')
        shop_data_list = soup.find('div', class_='grid g-clearfix').find_all_next('div', class_='items')
        for shop_data in shop_data_list:
            # 商品名称
            shop_image_data = shop_data.find_all('div',class_='pic')
            for shop_data_a in shop_image_data:
                shop_data_a = shop_data_a.find_all('a',class_='pic-link J_ClickStat J_ItemPicA')
                for shop_name in shop_data_a:
                    shop_name = shop_name.find_all('img')[0]['alt']
                    shop_name_list.append(shop_name)
            # 商品价格
            shop_price_data = shop_data.find_all('div',class_='price g_price g_price-highlight')
            for shop_price in shop_price_data:
                shop_price_list.append(shop_price.text.strip())
            # 付款人数
            shop_people_number_data = shop_data.find_all('div',class_='deal-cnt')
            for shop_people_number in shop_people_number_data:
                shop_people_list.append(shop_people_number.text)
            #地址s
            shop_location_data = shop_data.find_all('div',class_='location')
            for shop_location in shop_location_data:
                shop_location_list.append(shop_location.text)

        shop_data = zip(shop_name_list,shop_price_list,shop_people_list,shop_location_list)
        for data in shop_data:
            print(data)
            a += 1
        b += 44
        browser.get(f"https://s.taobao.com/search?q={value}&s={b}")
        sleep(0.5)

    print('已成功爬取：%s条信息'%a)
    print(shop_price_list)
    return shop_name_list, shop_price_list, shop_people_list, shop_location_list,a
def mysql():
    # 连接数据库
    db = pymysql.connect(
        host='localhost',
        user='root',
        password='123456',
        database='dbtest',
        port=3306,
        charset='utf8',
        cursorclass=pymysql.cursors.DictCursor
    )
    cursor = db.cursor()
    # 如果表存在则删除
    cursor.execute("drop table if exists taobao")

    sql = "create table taobao (shop_name char(200) not null,price char(30),people_number char(30),location char(50))"
    cursor.execute(sql)
    for i in range(a):
        li_name = shop_name_list[i]
        li_price = shop_price_list[i]
        li_people = shop_people_list[i]
        li_location = shop_location_list[i]
        sql = f"insert into taobao(shop_name,price,people_number,location) value('{li_name}','{li_price}','{li_people}','{li_location}')"
        # 执行sql语句
        cursor.execute(sql)
        # 提交到数据库执行
        db.commit()
    db.close()



if __name__ == '__main__':
    value = input("请输入你要查询的关键词：")
    browser = webdriver.Chrome(executable_path='./chromedriver')

    taobao_index = browser.get('https://login.taobao.com/member/login.jhtml')
    # 窗口最大化
    browser.maximize_window()
    wait = WebDriverWait(browser, 10)
    login_info()

    search_product(value)
    data(value)
    mysql()