python3文件比较_python3:基于文件内容递归比较两个目录

开始了。虽然还需要更多的测试,但在小测试之后,这似乎是可行的。同样,这可能非常长,这取决于文件的数量和大小:

import filecmp

import os

from collections import defaultdict

from sys import argv

def compareDirs(d1,d2):

files1 = defaultdict(set)

files2 = defaultdict(set)

subd1 = set()

subd2 = set()

for entry in os.scandir(d1):

if entry.is_dir(): subd1.add(entry)

else: files1[os.path.getsize(entry)].add(entry)

#Collecting first to compare length since we are guessing no

#match is more likely. Can compare files directly if this is

# not true.

for entry in os.scandir(d2):

if entry.is_dir(): subd2.add(entry)

else: files2[os.path.getsize(entry)].add(entry)

#Structure not the same. Checking prior to content.

if len(subd1) != len(subd2) or len(files1) != len(files2): return False

for size in files2:

<