Python学习笔记（六）——组织文件

shutil模块

在Python程序中复制移动改名和删除文件

复制文件和文件夹

>>> shutil.copy('def.py','.\\test')
'.\\test\\def.py'
>>> os.listdir('.\\test')
['def.py']

在复制的时候为新复制的文件命名

>>> shutil.copy('def.py','.\\test\\def2.py')
'.\\test\\def2.py'
>>> os.listdir('.\\test')
['def.py', 'def2.py']

文件和文件夹的移动和改名

移动

>>> shutil.move('temp.txt','.\\test')
'.\\test\\temp.txt'

改名

>>> shutil.move('.\\test\\temp.txt','.\\test\\temp2.txt')
'.\\test\\temp2.txt'

构成目的地的文件夹必须已经存在

永久删除文件或文件夹

>>> os.makedirs('.\\test\\001')
>>> os.rmdir('.\\test\\001')  #删除001文件夹（文件夹中没有内容）
>>> os.unlink('.\\test\\def2.py') #删除文件def2.py
>>> os.makedirs('.\\test\\001')
>>> shutil.copy('.\\def.py','.\\test\\001')
'.\\test\\001\\def.py'
>>> os.rmdir('.\\test\\001')     #当文件夹中有文件的时候，os.rmdir()将会报错
Traceback (most recent call last):
  File "<pyshell#17>", line 1, in <module>
    os.rmdir('.\\test\\001')
OSError: [WinError 145] 目录不是空的。: '.\\test\\001'
>>> shutil.rmtree('.\\test\\001')    #使用shutil.rmtree()进行递归删除

用send2trash模块安全的删除

所谓安全的删除，及将要删除的文件放入回收站

>>> import send2trash
>>> send2trash.send2trash('.\\test\\temp2.txt')

判断是是文件还是文件夹

import os
if os.path.isdir(path):
  print "it's a directory"
elif os.path.isfile(path):
  print "it's a normal file"
else:
  print "it's a special file (socket, FIFO, device file)"

遍历目录树

>>> for folder,subfolders,files in os.walk('.'):
    print('  '*len(folder.split('\\'))+os.path.basename(folder))
    for subfolder in subfolders:
        print('  '*len(folder.split('\\'))+subfolder)
    for file in files:
        print('  '*len(folder.split('\\'))+file)

import os
for folder,subfolders,files in os.walk('D:\\python'):
    print('当前文件夹：'+folder)
    for subfolder in subfolders:
        print('子文件夹有：'+folder+'\\'+subfolder)
    for file in files:
        print('下面的文件：'+folder+'\\'+file)
    print('\n')
======================= RESTART: D:\python\os-walk.py =======================
当前文件夹：D:\python
子文件夹有：D:\python\test
下面的文件：D:\python\def.py

当前文件夹：D:\python\test
下面的文件：D:\python\test\def.py
下面的文件：D:\python\test\randomQuizGenerator.py

使用zipfile模块压缩文件

读取zip文件

>>> exampleZip = zipfile.ZipFile('test\\test.zip')
>>> exampleZip.namelist()
['randomQuizGenerator.py', 'def.py']
>>> spamInfo = exampleZip.getinfo('def.py')
>>> spamInfo.file_size
149
>>> spamInfo.compress_size
94
>>> '压缩率为 %s' % (round((spamInfo.file_size-spamInfo.compress_size)/spamInfo.file_size,2)*100)+'%'
'压缩率为 37.0%'
>>> exampleZip.close()

从zip文件中解压缩

解压时支持创建文件夹

>>> exampleZip = zipfile.ZipFile('test.zip')
>>> exampleZip.extractall('.\\temp')     #默认当前文件夹
>>> exampleZip.extractall('.\\temp2\\temp3\\temp4')

可以指定zip内部文件进行解压

>>> exampleZip.extract('def.py')
'D:\\python\\test\\def.py'
>>> exampleZip.extract('def.py','.\\temp')
'temp\\def.py'

创建和添加ZIP文件

>>> os.getcwd()
'D:\\python\\test\\temp'
>>> newZip = zipfile.ZipFile('new.zip','w')
#这里的‘w’和使用open（）函数时类似，也可以用‘a’
>>> newZip.write('def.py',compress_type=zipfile.ZIP_DEFLATED)
>>> newZip.close()

小实验——将带有美国风格日期的文件改名为欧洲风格

注：(.*?) 怎么理解？
点 是任意字符
* 是取 0 至 无限长度
问号 是非贪婪模式。
何在一起就是 取尽量少的任意字符，一般不会这么单独写，他大多用在：
.*?a
就是取前面任意长度的字符，到底一个 a 出现，匹配如下
q@wer_qwerqweraljlkjlkjlkj
得到：q@wer_qwerqwera 这部分，如果匹配不到后面的 a 字符，则匹配为空。

#！python3
#renameDates.py - Rename filenames with American MM-DD-YYYY date format to European DD-MM-YYYY

import os,shutil,re
#为美国风格的日期建立一个正则表达式
date = re.compile(r'''
    ^(.*?)
    ((0|1)?\d)-
    ((0|1|2|3)?\d)-
    ((19|20)\d\d)
    (.*?)$
    ''',re.VERBOSE)
#Loop over the file in the working directory.
for filename in os.listdir('.'):
    mo = date.search(filename)
    #Skip files without date.
    if mo == None:
        continue
    #Get the different parts od the filename.
    beforPart = mo.group(1)
    monthPart = mo.group(2)
    dayPart = mo.group(4)
    yearPart = mo.group(6)
    afterPart = mo.group(8)
    """
    date = re.compile(r'''
        ^(1)
        (2(3))-
        (4(5))-
        (6(7))
        (8)$
    ''',re.VERBOSE)
    """
    #Form the European-style filename.
    euroDate = beforPart + dayPart +'-'+ monthPart +'-'+ yearPart + afterPart

    #Get the full,absolute file paths
    absPath = os.path.abspath('.')
    amerPath = os.path.join(absPath,filename)
    EuroPath = os.path.join(absPath,euroDate)

    #Rename the file.
    print('Rename %s to %s'%(amerPath,EuroPath))
    shutil.move(amerPath,EuroPath)

小实验——将一个文件夹备份到一个zip文件

#! python3
#backupToZip.py - Copies an entire folder and its contents into a ZIP file whose filename increments.
#Usage：backupToZip.py <Path> - Compress the file of the abspath to a backup.

#Author : qmeng
#MailTo : qmeng1128@163.com
#QQ     : 1163306125
#Blog   : http://blog.csdn.net/Mq_Go/
#Create : 2018-02-07
#Version: 1.0

import sys,zipfile,os
def backupfile(folder):
    #Backup the entire contents of "folder" into a zip file
    if os.path.isabs(folder) != True:
        folder = os.path.abspath(folder)
    number = 1
    while True:
        zipName = os.path.basename(folder) + '_' + str(number) + '.zip'
        if not os.path.exists(os.path.join(os.path.dirname(folder),zipName)):
            print(os.path.join(os.path.dirname(folder),zipName))
            break
        number = number + 1

    # Create the zip file
    print('Create the %s...'%(zipName))
    backupZip = zipfile.ZipFile(os.path.join(os.path.dirname(folder),zipName),'w')

    #Walk the entire folder tree and compress the files in each folder.
    for folder,subfolders,files in os.walk(folder):
        print('Add file is in %s...'%(folder))
        backupZip.write(folder)
        for file in files:
            newBase = os.path.basename(folder)+'_'
            if file.startswith(newBase) and file.endswith('.zip'):
                continue
            backupZip.write(os.path.join(folder,file))
    backupZip.close()
    print('Done')
if len(sys.argv) == 2:
    if not os.path.exists(sys.argv[1].lower()):
        print('No such file')
    else:
        backupfile(sys.argv[1].lower())

结果：

C:\Users\>backupToZip.py D:\\python\\test
d:\\python\test_2.zip
Create the test_2.zip...
Add file is in d:\\python\\test...
Add file is in d:\\python\\test\temp...
Done