解析出所有城市名称

https://www.aqistudy.cn/historydata/

分析思路:
- 先判断是不是动态加载的数据
- 找城市标签的定位,先熟悉源码

url = "https://www.aqistudy.cn/historydata/"
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36"}
url_text = requests.get(url = url,headers=headers).text

tree = etree.HTML(url_text)
# 热门城市: //div[@class="hot"]/ul/li/a/text()
# 全部城市: div[@class="bottom"]/ul/div[2]/li/a/text()
city_name_list = tree.xpath('//div[@class="hot"]/ul/li/a/text()|//div[@class="bottom"]/ul/div[2]/li/a/text()')

print(city_name_list)

import requests
from lxml import etree 
url = 'https://www.aqistudy.cn/historydata/'
headers = {
    'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
#获取页面原始编码格式
print(response.encoding)
page_text = response.text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="bottom"]/ul/li | //div[@class="bottom"]/ul//li')
for li in li_list:
    city_name = li.xpath('./a/text()')[0]
    city_url = 'https://www.aqistudy.cn/historydata/'+li.xpath('./a/@href')[0]
    print(city_name,city_url)