#coding:utf-8
import os
import hashlib #hash函数
import shutil
def makesDir(filepath): #判断如果文件不存在,则创建
if not os.path.exists(filepath):
os.makedirs(filepath)
if __name__ == '__main__':
A=r'/home/jy/xl/workstation/Datasets/Car/Nighttime_Vehicle_ReID/Query'#代表是目录A
B=r'/home/jy/xl/workstation/Datasets/Car/Nighttime_Vehicle_ReID/Gallery' #代表是目录B
C=r'/home/jy/xl/workstation/Datasets/Car/Nighttime_Vehicle_ReID/Same' #代表是目录A和目录B的差集放在目录C
makesDir(C)
md5dict={}
for filename in os.listdir(A):#返回的是一个一个的文件名
hashvalue=hashlib.md5(filename.encode( 'utf-8' )).hexdigest()
md5dict[hashvalue]=os.path.join(A, filename)
for filename in os.listdir(B):
hashvalue=hashlib. md5(filename.encode( 'utf-8' )).hexdigest()
if hashvalue in md5dict:
shutil.copy(os.path. join(B, filename),os.path.join(C,filename))
我的思考
用hash查找,速度真的好快,👍