国产探花免费观看_亚洲丰满少妇自慰呻吟_97日韩有码在线_资源在线日韩欧美_一区二区精品毛片,辰东完美世界有声小说,欢乐颂第一季,yy玄幻小说排行榜完本

首頁 > 編程 > Python > 正文

Python中使用md5sum檢查目錄中相同文件代碼分享

2019-11-25 18:00:51
字體:
來源:轉載
供稿:網友

復制代碼 代碼如下:

"""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)

發表評論 共有條評論
用戶名: 密碼:
驗證碼: 匿名發表
主站蜘蛛池模板: 本溪| 洛川县| 宜阳县| 泾阳县| 海林市| 和龙市| 宜宾县| 溆浦县| 册亨县| 军事| 北票市| 九寨沟县| 泗阳县| 九江市| 黎川县| 双辽市| 红桥区| 聂拉木县| 凌云县| 登封市| 镇原县| 龙南县| 香格里拉县| 堆龙德庆县| 绥棱县| 安乡县| 工布江达县| 淮北市| 大冶市| 合水县| 纳雍县| 肥城市| 舞钢市| 宣化县| 疏勒县| 石狮市| 娄底市| 嘉禾县| 大渡口区| 江永县| 大丰市|