1. # 项目需求：解析出所有城市名称https://www.aqistudy.cn/historydata/
    2. if __name__ == "__main__":
    3.     # headers = {
    4.     #     'User-Agent':'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
    5.     # }
    6.     # url = 'https://www.aqistudy.cn/historydata/'
    7.     # page_text = requests.get(url=url,headers=headers).text
    8.     #
    9.     # tree = etree.HTML(page_text)
    10.     # host_li_list = tree.xpath('//div[@class="bottom"]/ul/li')
    11.     # all_city_names = []
    12.     # #解析到了热门城市的城市名称
    13.     # for li in host_li_list:
    14.     #     hot_city_name = li.xpath('./a/text()')[0]
    15.     #     all_city_names.append(hot_city_name)
    16.     #
    17.     # #解析的是全部城市的名称
    18.     # city_names_list = tree.xpath('//div[@class="bottom"]/ul/div[2]/li')
    19.     # for li in city_names_list:
    20.     #     city_name = li.xpath('./a/text()')[0]
    21.     #     all_city_names.append(city_name)
    22.     #
    23.     # print(all_city_names,len(all_city_names))
    25.     headers = {
    26.         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
    27.     }
    28.     url = 'https://www.aqistudy.cn/historydata/'
    29.     page_text = requests.get(url=url, headers=headers).text
    31.     tree = etree.HTML(page_text)
    32.     # 解析到热门城市和所有城市对应的a标签
    33.     # //div[@class="bottom"]/ul/li/          热门城市a标签的层级关系
    34.     # //div[@class="bottom"]/ul/div[2]/li/a  全部城市a标签的层级关系
    35.     a_list = tree.xpath('//div[@class="bottom"]/ul/li/a | //div[@class="bottom"]/ul/div[2]/li/a')
    36.     all_city_names = []
    37.     for a in a_list:
    38.         city_name = a.xpath('./text()')[0]
    39.         all_city_names.append(city_name)
    40.     print(all_city_names, len(all_city_names))