python五步教你如何浏览器自动化并保存商品数据信息~

1、系统分析目标网页

2、html标签数据解析方法

3、海量数据一键保存

• python 3.8
• pycharm 2021专业版
• selenium >>> pip install selenium==3.141.0

from selenium import webdriver
import time
import csv

driver = webdriver.Chrome()

for page in range(0, 38):
    print(f'------------------------正在爬取第{page+1}页------------------------')

    driver.get(f'https://search.suning.com/%E4%B8%9D%E8%A2%9C%E6%83%85%E8%B6%A3/&iy=0&isNoResult=0&cp={page}')
    # 灵活等待
    driver.implicitly_wait(1)
    drop_down()
    get_next()

    # 网页 html: 茅台1 茅台2 茅台3   茅台2   
    # :
    divs = driver.find_elements_by_css_selector('.item-bg')

    for div in divs:

        title = div.find_element_by_css_selector('.title-selling-point a').text

        price = div.find_element_by_css_selector('.def-price').text

        try:
            comment_num = div.find_element_by_css_selector('.info-evaluate a').text
        except:
            comment_num = 0

        store_name = div.find_element_by_css_selector('.store-stock a').text

get_attribute: 获取标签属性名

       detail_url = div.find_element_by_css_selector('.title-selling-point a').get_attribute('href')
        print(title, price, comment_num, store_name, detail_url)

        # a: 追加写入
        # wb: 以二进制方式覆盖写入
        with open('苏宁.csv', mode='a', encoding='utf-8', newline='') as f:
            csv_writer = csv.writer(f)
            csv_writer.writerow([title, price, comment_num, store_name, detail_url])

with open('苏宁.csv', mode='a', encoding='utf-8', newline='') as f:
    csv_writer = csv.writer(f)
    csv_writer.writerow(['title', 'price', 'comment_num', 'store_name', 'detail_url'])

def drop_down():
    """执行页面滚动的操作"""
    for x in range(1, 12, 2):
        time.sleep(1)
        j = x / 9
        js = 'document.documentElement.scrollTop = document.documentElement.scrollHeight * %f' % j
        driver.execute_script(js)

def get_next():

好了，我的这篇文章写到这里就结束啦！

有更多建议或问题可以评论区或私信我哦！一起加油努力叭(ง •_•)ง

喜欢就关注一下博主，或点赞收藏评论一下我的文章叭！！！