两种方法 1、geolite22、外部接口3、资源下载
1、geolite2
需要准备的有三个文件
后两个相当于小型数据库，已经存放了ip和地理信息，由我们写代码查询即可
python里的代码如下
import reimport geoip2.databasereader = geoip2.database.Reader('GeoLite2-City.mmdb')# 查询IP地址对应的物理地址def ip_get_location(ip_address): # 载入指定IP相关数据 response = reader.city(ip_address) #读取国家代码 Country_IsoCode = response.country.iso_code #读取国家名称 Country_Name = response.country.name #读取国家名称(中文显示) Country_NameCN = response.country.names['zh-CN'] #读取州(国外)/省(国内)名称 Country_SpecificName = response.subdivisions.most_specific.name #读取州(国外)/省(国内)代码 Country_SpecificIsoCode = response.subdivisions.most_specific.iso_code #读取城市名称 City_Name = response.city.name #读取邮政编码 City_PostalCode = response.postal.code #获取纬度 Location_Latitude = response.location.latitude #获取经度 Location_Longitude = response.location.longitude if(Country_IsoCode == None): Country_IsoCode = "None" if(Country_Name == None): Country_Name = "None" if(Country_NameCN == None): Country_NameCN = "None" if(Country_SpecificName == None): Country_SpecificName = "None" if(Country_SpecificIsoCode == None): Country_SpecificIsoCode = "None" if(City_Name == None): City_Name = "None" if(City_PostalCode == None): City_PostalCode = "None" if(Location_Latitude == None): Location_Latitude = "None" if(Location_Longitude == None): Location_Longitude = "None" print('================Start===================') print('[*] Target: ' + ip_address + ' GeoLite2-Located ') print(u' [+] 国家编码: ' + Country_IsoCode) print(u' [+] 国家名称: ' + Country_Name) print(u' [+] 国家中文名称: ' + Country_NameCN) print(u' [+] 省份或州名称: ' + Country_SpecificName) print(u' [+] 省份或州编码: ' + Country_SpecificIsoCode) print(u' [+] 城市名称 : ' + City_Name) print(u' [+] 城市邮编 : ' + City_PostalCode) print(u' [+] 纬度: ' + str(Location_Latitude)) print(u' [+] 经度 : ' + str(Location_Longitude)) print('===============End======================')# 检验和处理ip地址def seperate_ip(ip_address): ip_match = r"^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|0?[0-9]?[1-9]|0?[1-9]0).)(?:(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?).){2}(?:25[0-4]|2[0-4][0-9]|1[0-9][0-9]|0?[0-9]?[1-9]|0?[1-9]0)$" ip_match_list = r"^(?:(?:25[0-5]|2[0-4][0-9]|1[0-9][0-9]|0?[0-9]?[1-9]|0?[1-9]0).)(?:(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?).){2}(?:25[0-4]|2[0-4][0-9]|1[0-9][0-9]|0?[0-9]?[1-9])-(?:25[0-4]|2[0-4][0-9]|1[0-9][0-9]|0?[0-9]?[1-9]|0?[1-9]0)$" if re.match(ip_match, ip_address): try: ip_get_location(ip_address) except Exception as e: print(e) elif re.match(ip_match_list, ip_address): ip_start = ip_address.split('-')[0].split('.')[3] ip_end = ip_address.split('-')[1] # 如果ip地址范围一样，则直接执行 if(ip_start == ip_end): try: seperate_ip(ip_address.split('-')[0]) except Exception as e: print(e) elif ip_start > ip_end: print('the value of ip, that you input, has been wrong! try again!') exit(0) else: ip_num_list = ip_address.split('-')[0].split('.') ip_num_list.pop() for ip_last in range(int(ip_start), int(ip_end)+1): ip_add = '.'.join(ip_num_list)+'.'+str(ip_last) try: ip_get_location(ip_add) except Exception as e: print(e) else: print('Wrong type of ip address!') print('100.8.11.58 100.8.11.58-100 alike!') if __name__ == '__main__': seperate_ip('113.248.151.48')
当然这不是我写的，从哪儿来的也忘了，但亲测可用
不过也有问题，就是不准确，不信的可以试试
2、外部接口
另一个替代方案是使用其他网站作为接口，每次就用爬虫post查询，源码如下
import requestsfrom bs4 import BeautifulSoupimport reip = '113.248.151.48'url = "https://www.ip138.com/iplookup.asp?ip={}&action=2".format(ip)headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.100 Safari/537.36'}# 获取响应response = requests.get(url=url, headers=headers)response.encoding = "gb2312"html = response.textfor match in re.finditer('"(prov|city|ct)":"(.*?)"',html): print(match.group())
类似地你就可以把它嵌入在你的网站里了
打个补丁，可以把结果放到字典里供查询
import requestsfrom bs4 import BeautifulSoupimport reip = '113.248.151.48'url = "https://www.ip138.com/iplookup.asp?ip={}&action=2".format(ip)headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.100 Safari/537.36'}# 获取响应response = requests.get(url=url, headers=headers)response.encoding = "gb2312"html = response.textinfo = dict()for match in re.finditer('"(prov|city|ct)":"(.*?)"',html): divide = match.group().split(":") info["{}".format(divide[0].strip('"'))] = divide[1].strip('"')print(info)
3、资源下载
geolite