hashlib的md5计算

hashlib概述

涉及加密服务：Cryptographic Services

其中 hashlib是涉及 安全散列 和 消息摘要 ，提供多个不同的加密算法借口，如SHA1、SHA224、SHA256、SHA384、SHA512、MD5等。

>>> import hashlib

>>> m = hashlib.md5() #创建hash对象，md5:(message-Digest Algorithm 5)消息摘要算法,得出一个128位的密文

>>> m.update("Nobody inspects") #更新哈希对象以字符串参数

>>> m.update(" the spammish repetition") #更新哈希对象以字符串参数

>>> m.digest() #返回摘要，作为二进制数据字符串值

>>> m.hexdigest() #返回十六进制数字字符串

基本用法

hashlib.md5('hiyang').hexdigest()

'97b21efa4d5de4c1a6a2b332f1e183e5'

>>> m = hashlib.md5()

>>> m.update('hiyang')

>>> m.hexdigest()

'97b21efa4d5de4c1a6a2b332f1e183e5'

使用new指定加密算法 new(name, string='')

hashlib.new('md5','hiyang').hexdigest()

'97b21efa4d5de4c1a6a2b332f1e183e5'

h = hashlib.new('md5')

h.update('hiyang')

hashlib.md5('hiyang').hexdigest()

'97b21efa4d5de4c1a6a2b332f1e183e5'

范例

md5sum() 计算文件的md5
md5sumd() 计算目录下文件的md5
md5sumd2() 计算目录下文件的md5，返回一个生成器
md5CheckFile() 通过md5比较文件内容是否相同

#!/usr/bin/env python

# python 2

# encoding:utf8

import hashlib

import sys

import os

def md5sum(f, readsize=4096):

    """to calculate md5 of a file, readsize default is 4096 bytes

    return result"""

    m = hashlib.md5()

    with open(f, 'rb') as fd:

        data = fd.read(readsize)

        while data:

            m.update(data)

            data = fd.read(readsize)

        else:

            return m.hexdigest()

def md5sumd(filename):

    """to calculate md5 of a directory

    return result"""

    _md5sumd = ''

    for paths, dirs, files in os.walk(filename):

        for f in files:

            fn = os.path.join(paths, f)

            _md5sumd += md5sum(fn)+'  '+fn+'\n'

    return _md5sumd

def md5sumd2(filename):

    """to calculate md5 of a directory

    return generator"""

    for paths, dirs, files in os.walk(filename):

        for f in files:

            fn = os.path.join(paths, f)

            yield md5sum(fn)+'  '+fn

def md5CheckFile(filename='.'):

    """calculate md5 of a directory, to check the same file

    return a directory {md5: [filename,...]}, these file has same md5"""

    dic = {}

    for paths, dirs, files in os.walk(filename):

        for f in files:

            fn = os.path.join(paths, f)

            md5 = md5sum(fn)

            if dic.has_key(md5):

                dic[md5].append(fn)

            else:

                dic[md5] = [fn]

        return {k: v for k, v in dic.items() if len(v) >= 2}

if __name__ == '__main__':

    try:

        filename = sys.argv[1]

    except IndexError:

        filename = '.'

    if os.path.isfile(filename):

        print md5sum(filename)+'  '+filename

    elif os.path.isdir(filename):

        _md5sumd = md5sumd(filename)

        print _md5sumd,

        print '-' * 20, 'total', '-' * 20

        print hashlib.md5(_md5sumd).hexdigest()+'  '+filename

    else:

        print >> sys.stderr, 'file %s is not exist.' % filename