Python中使用md5sum检查目录中相同文件代码分享_python教程-查字典教程网
Python中使用md5sum检查目录中相同文件代码分享
Python中使用md5sum检查目录中相同文件代码分享
发布时间:2016-12-28 来源:查字典编辑
摘要:复制代码代码如下:"""ThismodulecontainscodefromThinkPythonbyAllenB.Downeyhttp:/...

复制代码 代码如下:

"""This module contains code from

Think Python by Allen B. Downey

http://thinkpython.com

Copyright 2012 Allen B. Downey

License: GNU GPLv3 http://www.gnu.org/licenses/gpl.html

"""

import os

def walk(dirname):

"""Finds the names of all files in dirname and its subdirectories.

dirname: string name of directory

"""

names = []

for name in os.listdir(dirname):

path = os.path.join(dirname, name)

if os.path.isfile(path):

names.append(path)

else:

names.extend(walk(path))

return names

def compute_checksum(filename):

"""Computes the MD5 checksum of the contents of a file.

filename: string

"""

cmd = 'md5sum ' + filename

return pipe(cmd)

def check_diff(name1, name2):

"""Computes the difference between the contents of two files.

name1, name2: string filenames

"""

cmd = 'diff %s %s' % (name1, name2)

return pipe(cmd)

def pipe(cmd):

"""Runs a command in a subprocess.

cmd: string Unix command

Returns (res, stat), the output of the subprocess and the exit status.

"""

fp = os.popen(cmd)

res = fp.read()

stat = fp.close()

assert stat is None

return res, stat

def compute_checksums(dirname, suffix):

"""Computes checksums for all files with the given suffix.

dirname: string name of directory to search

suffix: string suffix to match

Returns: map from checksum to list of files with that checksum

"""

names = walk(dirname)

d = {}

for name in names:

if name.endswith(suffix):

res, stat = compute_checksum(name)

checksum, _ = res.split()

if checksum in d:

d[checksum].append(name)

else:

d[checksum] = [name]

return d

def check_pairs(names):

"""Checks whether any in a list of files differs from the others.

names: list of string filenames

"""

for name1 in names:

for name2 in names:

if name1 < name2:

res, stat = check_diff(name1, name2)

if res:

return False

return True

def print_duplicates(d):

"""Checks for duplicate files.

Reports any files with the same checksum and checks whether they

are, in fact, identical.

d: map from checksum to list of files with that checksum

"""

for key, names in d.iteritems():

if len(names) > 1:

print 'The following files have the same checksum:'

for name in names:

print name

if check_pairs(names):

print 'And they are identical.'

if __name__ == '__main__':

d = compute_checksums(dirname='.', suffix='.py')

print_duplicates(d)

相关阅读
推荐文章
猜你喜欢
附近的人在看
推荐阅读
拓展阅读
  • 大家都在看
  • 小编推荐
  • 猜你喜欢
  • 最新python学习
    热门python学习
    脚本专栏子分类