Python爬虫案例

爬取https://www.aqistudy.cn/historydata/中的城市名称
通过xpath表达式解析网站中的城市名称，利用for循环获取全部城市名称，并将获取的城市名称放到列表中。

#  爬取https://www.aqistudy.cn/historydata/中的城市名称

import requests
from lxml import etree

if __name__ =='__main__':
    url = 'https://www.aqistudy.cn/historydata/'
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
    }

    response = requests.get(url=url,headers=headers)
    page_text = response.text
    #爬取热门城市
    tree = etree.HTML(page_text)
    li_list = tree.xpath('//div[@class="bottom"]/ul/li')
    all_city_name=[]
    for li in li_list:
        hot_city_name = li.xpath('./a/text()')[0]
        all_city_name.append(hot_city_name)
    #爬取全部城市
    ul_list = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
    for ul in ul_list:
        city_name = ul.xpath('./a/text()')[0]
        all_city_name.append(city_name)

    print(all_city_name,len(all_city_name))