Python中使用md5sum检查目录中相同文件代码分享

概述复制代码代码如下:\"\"\"ThismodulecontainscodefromThinkPythonbyAllenB.Downeyhttp://thinkpython.com

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)

您可能感兴趣的文章:Python MD5文件生成码python 计算文件的md5值实例python文件的md5加密方法利用Python生成文件md5校验值函数的方法Python基于hashlib模块的文件MD5一致性加密验证示例Python简单计算文件MD5值的方法示例Python使用MD5加密字符串示例Python的加密模块md5、sha、crypt使用实例Python常见加密模块用法分析【MD5,crypt模块】Python实现检测文件MD5值的方法示例 总结

以上是内存溢出为你收集整理的Python中使用md5sum检查目录中相同文件代码分享全部内容，希望文章能够帮你解决Python中使用md5sum检查目录中相同文件代码分享所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。