python批量获取电话号码的归属地及来源分类(稳定的360手机卫士接口)

接口：

https://cx.shouji.360.cn/?number=str(电话号码)

接口推荐理由

• 上一篇文章中，我们有用https://www.so.com/s?ie=utf-8&q="+ str(电话号码)尝试获取我们想要的结果，可用，但是接口反爬机制严格，获取不了几条就封停，需要构建代理ip池和间隔访问时间。
• 这个接口非常稳定，基本上没有反爬机制，不用代理ip就可完成我们想要的结果，更简单，稳定，高效。

数据源：

可以座机或者手机，如果是非电话号码会自动剔除

结果展示：

代码

# coding: utf-8
# -*- coding: utf-8 -*-
import urllib.request
import urllib.parse
from urllib.error import  HTTPError ,URLError
import socket  #请求超时异常
from bs4 import BeautifulSoup
import requests
import time
import json
import csv
import re
import random
import datetime
import pandas as pd

def response(url):
    try:
        
        headers = { }
        headers["User-Agent"]="Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"
        #random.seed(datetime.datetime.now())
        req = urllib.request.Request(url, headers=headers)
        bsobj = urllib.request.urlopen(req, timeout=60).read().decode("utf-8")
        #bsobj = BeautifulSoup(html,"html.parser")
        jsonobj = json.loads(bsobj)
        #print(jsonobj)
        provinces = jsonobj.get("data").get("province")
        if len(provinces) > 0:
            province = provinces
        else:
            if len(provinces) < 1 and len(str(re.match('00852', telephone))) != 4:
                province = "香港"
            elif len(provinces) < 1 and len(str(re.match('00886', telephone)))!= 4:
                province = "台湾"
            else:
                province = "未知"
        citys = jsonobj.get("data").get("city")
        if len(citys)>0:
            city = citys
        else:
            city = province
        sps = jsonobj.get("data").get("sp")
        if len(sps)>0:
            sp = sps
        elif len(sps)<1 and len(provinces)>0:
            sp = "座机"
        else:
            sp = province
        print(telephone,province,city,sp)
        writer.writerows([[str(telephone),province,city,sp]])
    except (HTTPError, URLError, socket.timeout, AttributeError,UnicodeEncodeError,TypeError) as e:
        return
if __name__ == '__main__':
    # 创建一个存储数据的表
    file_name = r"D:\Case_data/telephone_r" + ".csv"
    f = open(file_name, "w+", newline='',encoding = 'gb18030')
    writer = csv.writer(f, dialect='excel')
    # 先写入columns_name
    writer.writerow(['电话', '省份', '市级', '分类'])
    
    # 打开数据源
    read_file_path=r'D:/Case_data/telephone.xlsx'
    df = pd.read_excel(read_file_path,encoding='utf-8')
    df["电话"] = df["电话"].replace('-', "", regex=True)  #单个值的替换
    display(df.tail(10))
    for telephone in df["电话"]:
        #print(telephone)
        time.sleep(0)
        urls = r"https://cx.shouji.360.cn/phonearea.php?number=" + str(telephone)
        #print(urls)
        response(urls)
f.close()

扫

码

关

注

更多数据分析与运营知识

干货在此，随时学习！