python+selenium爬取淘宝羽毛球拍信息

数据量很大，就爬取前五页偷下懒

from selenium import webdriver
import pandas as pd
import openpyxl
import time
driver = webdriver.Chrome()
url = 'https://s.taobao.com/search?q=羽毛球拍'
driver.get(url)
driver.implicitly_wait(20)
namelist = []
pricelist = []
weblist = []
locationlist = []
numberlist = []

def infor():
    items = driver.find_elements_by_class_name('item.J_MouserOnverReq  ')
    for i in items:
        name = i.find_element_by_class_name('row.row-2.title').find_element_by_class_name('J_ClickStat').text
        price = i.find_element_by_class_name('J_ClickStat').get_attribute('trace-price')
        web = i.find_element_by_class_name('J_ClickStat').get_attribute('href')
        location = i.find_element_by_class_name('location').text
        number = i.find_element_by_class_name('deal-cnt').text
        namelist.append(name)
        pricelist.append(price)
        weblist.append(web)
        locationlist.append(location)
        numberlist.append(number)

if __name__ == '__main__':
    for i in range(1,6):
        driver.implicitly_wait(20)
        driver.find_element_by_class_name('input.J_Input').clear()
        driver.find_element_by_class_name('input.J_Input').send_keys(i)
        driver.find_element_by_class_name('btn.J_Submit').click()
        time.sleep(3)
        driver.get(driver.current_url)
        driver.implicitly_wait(20)
        infor()
        print('第{}页录入成功'.format(i))
    data=pd.DataFrame([namelist,pricelist,locationlist,numberlist,weblist]).T
    data.columns=['name','price','location','number','web']
    data.to_excel('work.xlsx')

爬虫新手 有不规范之处大家多多见谅O(∩_∩)O

本文地址：https://blog.csdn.net/weixin_47128538/article/details/107357109