由于个人需要国内所有省市区的ip地址段和经纬度的对应关系，最好是数据库可以直接使用的数据源，经调研发现可以使用百度API来实现这个功能，主要是找到所有的ip地址段然后调用api 查询，

主要是用Tornado 做异步爬虫来实现的，

import time
import json
from datetime import timedelta
from bs4 import BeautifulSoup
import os
from tornado import httpclient, gen, ioloop, queues
from api import map_ip_region_provice

AK = "umG08TkpEwmRWkUPx4MaM0FGW3h4i4L"  # 你可以使用百度开发者账号申请
base_url = 'http://api.map.baidu.com/location/ip?ak={1}&ip={0}'
IP_URL = 'https://github.com/17mon/china_ip_list/blob/master/china_ip_list.txt'

concurrency = 20  # 并发数


def is_file_exist(result=None):
    if result:
        result = result
    else:
        result = []
    with open('iplist.txt', 'w+') as ipfile:
        for i in result:
            ipfile.write(i)
            ipfile.write('\n')
    return result


def get_iplist():
    """
    从github 下载ip 段
    """
    # check ip is exist， 节约时间
    result = list()
    flag = is_file_exist()
    if flag:
        return flag
    else:
        http_client = httpclient.HTTPClient()
        try:
            response = http_client.fetch(IP_URL)
            respone = response.body
        except httpclient.HTTPError as e:
            print("Error: " + str(e))
        except Exception as e:
            # Other errors are possible, such as IOError.
            print("Error: " + str(e))
        http_client.close()
        respone = BeautifulSoup(respone, 'lxml')
        div = respone.find('table',
                           attrs={'class',
                                  'highlight tab-size js-file-line-container'})
        trs = div.find_all('td', attrs={'class': 'blob-code blob-code-inner js-file-line'})
        for tr in trs:
            temp = tr.string
            result.append(temp)
        print('fetch ip .....')
        is_file_exist(result)

具体可以查看

https://fizblog.cn/blog?title…