import os, time, hashlib
import shutil
#根据图片像素去重
def getmd5(file):
if not os.path.isfile(file):
return
fd = open(file, 'rb')
md5 = hashlib.md5()
md5.update(fd.read())
fd.close()
return md5.hexdigest()
if __name__ == "__main__":
allfile = []
md5list = []
list_delete = []
start = time.time()
path = r"D:\03_date_work\JPEGImages"
moveFile =r"D:\jpt"
for filepath, dir, filelist in os.walk(path):
for filename in filelist:
allfile.append(os.path.join(filepath, filename))
# print(filename)
for photo in allfile:
md5sum = getmd5(photo)
if md5sum not in md5list:
md5list.append(md5sum)
else:
list_delete.append(photo)
# print(photo)
# print(list_delete)
for i in range(len(list_delete)):
# os.remove(list_delete[i])
print(list_delete[i])
# shutil.move(list_delete[i], moveFile +list_delete[i].split('/')[4])
# shutil.move(list_delete[i], moveFile + list_delete[i])
shutil.move( list_delete[i],moveFile )
002_根据像素查找相同的照片
最新推荐文章于 2024-10-09 21:39:17 发布