ip-纯真库：批量获取ip归属地

1、所需python包：

from qqwry import QQwry   #pip install qqwry-py3
from IPy import IP
import socket
import threading
import csv
import time
import eventlet
from urllib.parse import urlparse
q = QQwry()
q.load_file('qqwry.dat')

2、多线程处理函数：

threads_ip(参数1，参数2)：

输入：线程数，要处理的csv文件（只有一列netloc）

输出：有ip结果的csv(netloc，ip， address)

3、部分代码示例：

def ip_csv(batch_list, csv_path):
    """
    输入：list的字典 【{列名：值}，.....】
    输出：ip 归属地写入的csv文件
    :param batch_list:
    :return:
    """
    with open(csv_path, "a") as csvfile:    # ip归属地信息保存，可以指定列名
        writer = csv.writer(csvfile)
        #writer.writerow(["country", "server",  "ip"])
        #ip_list = f.read().splitlines()
        for url in batch_list:
            #id = url['html_content_id']
            url_value= url['netloc']
            address =[]
            ip = ''
            if url_value.startswith("http"):
                net = urlparse(url_value).netloc
            try:
                net = url_value
                with eventlet.Timeout(5, False):
                    ip = socket.gethostbyname(net)
                    address = list(q.lookup(ip))
            except Exception as e:
                pass
            res = [url_value, ip, address]
            writer.writerow(res)


def threads_ip(thread_num, txt_path):
    """
    多线程
    :param thread_num:
    :return:分片处理，结果写入csv
    """
   #处理csv文件
    with open(txt_path, "r", encoding='utf-8') as f:
        reader = csv.DictReader(f)
        rows = [row for row in reader]
    per_num = int(len(rows)/thread_num)   #分片
    threads = []
    for i in range(thread_num):
        t = threading.Thread(target=ip_csv, args=(rows[i*per_num:i*per_num+per_num],txt_path))    #多线程
        threads.append(t)
    for t in threads:
        t.setDaemon(True)
        t.start()
    for t in threads:
        t.join()