China Mobiles to MD5

本篇讲解基于 Python 脚本,穷举所有中国境内的手机号,并生成对应的 MD5 值。
国内的运营商分为:移动、联通和电信。 每家运营商在不同的时间节点上线了多个手机号码段,每个号码段对应 1 亿个手机号码。 单个手机号段,生成的 手机号,MD5 值,文件占用空间为 2GB 左右。

手机号号段大致如下

  130,131,132,133,134,135,136,137,138,139,145,147,150,151,152,153,155,156,157,158,159,170,171,176,177,178,180,181,182,183,184,185,186,187,188,189

穷举手机号段,并生成对应的 MD5 值

#coding=utf-8

import sys
import hashlib


def generate_md5_mobiles():
    mobiles = [131,132,133,134,135,136,137,138,139,145,147,150,151,152,153,155,156,157,158,159,170,171,176,177,178,180,181,182,183,184,185,186,187,188,189]
    for m in mobiles:
        base_num = str(m)

        result_file = open('YOUR-PATH/md5mobiles/' + base_num + '.txt', "wb")

        zero = '00000000'
        for i in range(0, 100000000):
            num_left = zero + str(i)
            num_len = len(num_left)
            num_left = num_left[num_len-8:num_len]
            num = base_num + num_left

            hash_md5 = hashlib.md5(num)
            md5num = hash_md5.hexdigest()

            result_file.write('%s,%s\n' % (md5num, num))

        result_file.close()


def main():
    generate_md5_mobiles()

if __name__ == '__main__':
    main()

# 执行脚本生成所有号段的 MD5 值
# python generate_md5_mobile.py

使用 MD5 的加密值,依据对应关系,查找到明文的手机号

#coding=utf-8

import sys
from sets import Set


def prepare_md5_sets(input_file):
    md5_sets = Set([])
    with open(input_file) as f:
        for line in f:
            content = line.rstrip('\n')
            if content != '' and content != None:
                if content not in md5_sets:
                    md5_sets.add(content)
    return md5_sets


def main(base_num):
    # base_num = '130'

    input_file = '/YOUR-PATH/inputs.txt'
    origin_md5_file = '/YOUR-PATH/md5mobiles/' + base_num + '.txt'
    result_file = open('/YOUR-PATH/results/' + base_num  + '.txt', "wb")

    md5_sets = prepare_md5_sets(input_file)

    with open(origin_md5_file) as f:
        for line in f:
            content = line.rstrip('\n')
            if content != '' and content != None:
                items = content.split(',')
                if items[0] in md5_sets:
                    result_file.write('%s,%s\n' % (items[0], items[1]))
    result_file.close()


if __name__ == '__main__':
    base_num = sys.argv[1].strip()
    main(base_num)


# cd /YOUR-PATH/results/
# rm *.txt

# cd /YOUR-PATH/

# 执行脚本从 130 段搜索 MD5 值
# python search_md5_to_mobile.py 130

# 合并多个 txt 文件
# cd /YOUR-PATH/results/
# cat *.txt > all_mobiles.txt

2017-11-28