Python利用模糊哈希实现对比文件相似度

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

import ssdeep
import time
from python_mmdt.mmdt.mmdt import MMDT
from difflib import SequenceMatcher

def difflib_test(file1,file2):
    start_time = time.time()
    with open(file1,'rb') as f:
        s1 = f.read()
    with open(file2,'rb') as f:
        s2 = f.read()
    match_obj =  SequenceMatcher(None,s1,s2)
    print("difflib match:",match_obj.ratio())
    end_time = time.time()
    print('difflib_test cost ：',end_time-start_time)

def mmdt_test(file1,file2):
    start_time = time.time()
    mmdt=MMDT()
    r1 = mmdt.mmdt_hash(file1)
    print(r1)
    r2 = mmdt.mmdt_hash_streaming(file2)
    print(r2)
    # sim1 = mmdt.mmdt_compare(file1, file2)
    # print("mmdt match:",sim1)
    sim2 = mmdt.mmdt_compare_hash(r1, r2)
    print("mmdt match:",sim2)
    end_time = time.time()
    print('mmdt_test cost ：',end_time-start_time)

def ssdeep_test(file1,file2):
    start_time = time.time()
    sig1=ssdeep.hash_from_file(file1)
    sig2=ssdeep.hash_from_file(file2)
    print(sig1)
    print(sig2)
    print("ssdeep match:",ssdeep.compare(sig1,sig2))
    end_time = time.time()
    print('ssdeep_test cost ：',end_time-start_time)

if __name__ == '__main__':
    start_time = time.time()
    file1='/root/test/fstab'
    file2='/root/test/fstab2'
    # file1 = '/root/test/initrd.img-5.4.0-125-generic'
    # file2 = '/root/test/initrd.img-5.4.0-135-generic'
    mmdt_test(file1,file2)    
    ssdeep_test(file1,file2)
    difflib_test(file1,file2)
    end_time = time.time()
    print('总执行时间：',end_time-start_time)

import tlsh
import time

def tlsh_test(file1,file2):
    start_time = time.time()
    with open(file1,'rb') as f:
        s1 = tlsh.hash(f.read())
    with open(file2,'rb') as f:
        s2 = tlsh.hash(f.read())
    match_obj =  tlsh.diff(s1,s2)
    print("tlsh match:",match_obj)
    end_time = time.time()
    print('difflib_test cost ：',end_time-start_time)


if __name__ == '__main__':
    start_time = time.time()
    # file1='/root/test/fstab'
    # file2='/root/test/fstab2'
    file1 = '/root/test/initrd.img-5.4.0-125-generic'
    file2 = '/root/test/initrd.img-5.4.0-135-generic'
    tlsh_test(file1,file2)
    end_time = time.time()
    print('总执行时间：',end_time-start_time)