使用Redis有序集合实现IP归属地查询详解

# -*- coding:utf-8 -*-


import time
import socket
import struct

IP_REGION_FILE = './data/ip_to_region.db'

SUPER_BLOCK_LENGTH = 8
INDEX_BLOCK_LENGTH = 12
HEADER_INDEX_LENGTH = 8192


def generate_db_file():
  pointer = SUPER_BLOCK_LENGTH + HEADER_INDEX_LENGTH

  region, index = '', ''

  # 文件格式
  # 1.0.0.0|1.0.0.255|澳大利亚|0|0|0|0
  # 1.0.1.0|1.0.3.255|中国|0|福建省|福州市|电信
  with open('./ip.merge.txt', 'r') as f:
    for line in f.readlines():
      item = line.strip().split('|')
      print item[0], item[1], item[2], item[3], item[4], item[5], item[6]
      start_ip = struct.pack('I', struct.unpack('!L', socket.inet_aton(item[0]))[0])
      end_ip = struct.pack('I', struct.unpack('!L', socket.inet_aton(item[1]))[0])
      region_item = '|'.join([item[2], item[3], item[4], item[5], item[6]])
      region += region_item

      ptr = struct.pack('I', int(bin(len(region_item))[2:].zfill(8) + bin(pointer)[2:].zfill(24), 2))
      index += start_ip + end_ip + ptr
      pointer += len(region_item)

  index_start_ptr = pointer
  index_end_ptr = pointer + len(index) - 12
  super_block = struct.pack('I', index_start_ptr) + struct.pack('I', index_end_ptr)

  n = 0
  header_index = ''
  for index_block in range(pointer, index_end_ptr, 8184):
    header_index_block_ip = index[n * 8184:n * 8184 + 4]
    header_index_block_ptr = index_block
    header_index += header_index_block_ip + struct.pack('I', header_index_block_ptr)

    n += 1

  header_index += index[len(index) - 12: len(index) - 8] + struct.pack('I', index_end_ptr)

  with open(IP_REGION_FILE, 'wb') as f:
    f.write(super_block)
    f.write(header_index)
    f.seek(SUPER_BLOCK_LENGTH + HEADER_INDEX_LENGTH, 0)
    f.write(region)
    f.write(index)


if __name__ == '__main__':
  start_time = time.time()
  generate_db_file()

  print 'cost time: ', time.time() - start_time