第一种写法:
"""http://www.aqistudy.cn/historydata/
- 爬取热门城市和全部城市的名称"""
import requests
from lxml import etree
url = 'http://www.aqistudy.cn/historydata/'
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'}
response = requests.get(url, headers=headers)
page_html = response.text
# print(page_html)
tree = etree.HTML(page_html)
# 解析热门城市
hot_li_list = tree.xpath('//div[@class="bottom"]//li')
print('————hot city name————')
for li in hot_li_list:
hot_name = li.xpath('./a/text()')[0]
print(hot_name)
# 解析所有城市
all_li_list = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
print("————all city name————")
for li in all_li_list:
all_name