使用json.dump(citys_data, f, ensure_ascii=False)写文件的时候，如果要写入汉字，则要指定ensure_ascii为False

这个代码例子为获取链家网里所有的城市，然后将按照{省名:｛市名:url｝,｛市名:url｝....}的方式

import requests
from lxml import etree
import json


def get_all_city():
    url = "https://www.lianjia.com/city/"  # 全国城市列表
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36'
    }
    try:
        response = requests.get(url=url, headers=headers)
    except requests.exceptions.ConnectionError as e: # 有时网不好，连接错误
        print(e)  # HTTPSConnectionPool(host='www.lianjia.com', port=443): Max retries exceeded with url: /city/ (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001F0143B7810>, 'Connection to www.lianjia.com timed out. (connect timeout=None)'))
        return  # None

    tree = etree.HTML(response.text)

    citys = {}
    province_list = tree.xpath("//div[@class='city_province']")
    for province in province_list:
        province_name = province.xpath(".//div[@class='city_list_tit c_b']/text()")[0]  # 省名, 例：山东
        province_city_name = province.xpath(".//ul/li/a/text()")  # 市名, 例：['菏泽', '济南', '济宁', '临沂', '青岛', '泰安', '潍坊', '威海', '烟台', '淄博']
        province_city_url = province.xpath(".//ul/li/a/@href")  # 对应的url，例：['https://heze.lianjia.com/', 'https://jn.lianjia.com/', 'https://jining.lianjia.com/', 'https://linyi.lianjia.com/', 'https://qd.lianjia.com/', 'https://ta.lianjia.com/', 'https://wf.lianjia.com/', 'https://weihai.lianjia.com/', 'https://yt.lianjia.com/', 'https://zb.lianjia.com/']

        citys[province_name] = dict(zip(province_city_name, province_city_url))  # 将市名和对应的url组成键值对
    return citys


if __name__ == '__main__':
    citys_data = get_all_city()
    with open("citys_data.json", "w", encoding='utf-8') as f:
        json.dump(citys_data, f, ensure_ascii=False)

json.dump(citys_data, f),默认ensure_ascii为True

json.dump(citys_data, f, ensure_ascii=False)，指定ensure_ascii为False，写入中文