pyhton扒一扒小米热卖的东西

这个熟悉吗？

对，这就是小米官网首页热卖的东西，想不想看看都有啥，来，我的代码满足你

代码展示

from lxml import etree
import urllib3.request
import pandas as pd
urllib3.disable_warnings()

# 生成待解析的对象
def getTree(url):
    pool_manager = urllib3.PoolManager()
    response = pool_manager.request('GET', url)
    r = response.data.decode()
    return etree.HTML(r)

def getInfo(url):
    etree = getTree(url)
    # 得到每一个模块
    block = etree.xpath('//li[@class="category-item"]')
    print(len(block))
    specs = block[0].xpath('//a[@class="title"]/text()')

    temp =[]
    for item in specs:
        item1 = item.strip()
        temp.append(item1)
    specs_final = temp[::2]
    print(specs_final)

    names = []
    lens = []
    for bk in block:
        # 得到每个版块的ul中的li
        lis = bk.xpath('div[@class="children clearfix"]/ul[@class="children-list clearix"]/li/a/span[@class="text"]/text()')
        # print(lis)
        names.append(lis)
        lens.append(len(lis))

    data = {'specs_final':specs_final,'lens':lens,'names':names}
    # 数据框处理
    df = pd.DataFrame(data)
    df.to_excel('midata.xls')
    print('finished!')


url ="https://www.mi.com/"

if __name__ == '__main__':
    getInfo(url)

运行效果

Excel也可以看一下

拿到数据可以分析