1. 组织文件笔记（第9章）(代码下载)

1.1 文件与文件路径
通过import shutil调用shutil模块操作目录，shutil模块能够在Python 程序中实现文件复制、移动、改名和删除；同时也介绍部分os操作文件的函数。常用函数如下：

1.2 用zipfile 模块压缩文件
通过import zipfile，利用zipfile模块中的函数，Python 程序可以创建和打开（或解压）ZIP 文件。常用函数如下：

2. 项目练习

2.1 将带有美国风格日期的文件改名为欧洲风格日期

# 导入模块
import shutil
import os
import re
# Renames filenames with American MM-DD-YYYY date format to European DD-MM-YYYY.

# 含美国风格的日期
# Create a regex that matches files with the American date format.
datePattern = re.compile(
    # 匹配文件名开始处、日期出现之前的任何文本
    r"""^(.*?) # all text before the date
        # 匹配月份
        ((0|1)?\d)- # one or two digits for the month
        # 匹配日期
        ((0|1|2|3)?\d)- # one or two digits for the day
        # 匹配年份
        ((19|20)\d\d) # four digits for the year
        (.*?)$ # all text after the date
        """, re.VERBOSE)

# 查找路径
searchPath='d:/'

for amerFilename in os.listdir(searchPath):
    mo = datePattern.search(amerFilename)
    # Skip files without a date.
    if mo == None:
        continue
    # Get the different parts of the filename.
    # 识别日期
    beforePart = mo.group(1)
    monthPart = mo.group(2)
    dayPart = mo.group(4)
    yearPart = mo.group(6)
    afterPart = mo.group(8)

    # Form the European-style filename. 改为欧洲式命名
    euroFilename = beforePart + dayPart + '-' + \
        monthPart + '-' + yearPart + afterPart
    # Get the full, absolute file paths.
    # 返回绝对路径
    absWorkingDir = os.path.abspath(searchPath)
    # 原文件名
    amerFilename = os.path.join(absWorkingDir, amerFilename)
    # 改后文件名
    euroFilename = os.path.join(absWorkingDir, euroFilename)
    # Rename the files.
    print('Renaming "%s" to "%s"...' % (amerFilename, euroFilename))
    shutil.move(amerFilename, euroFilename)  # uncomment after testing

Renaming "d:\今天是06-28-2019.txt" to "d:\今天是28-06-2019.txt"...

2.2 将一个文件夹备份到一个ZIP 文件

import zipfile
import os


# 弄清楚ZIP 文件的名称
def backupToZip(folder):
    # Backup the entire contents of "folder" into a ZIP file.
    # 获得文件夹绝对路径
    folder = os.path.abspath(folder)  # make sure folder is absolute
    # Figure out the filename this code should use based on
    # what files already exist.
    number = 1
    while True:
        # 压缩文件名
        zipFilename = os.path.basename(folder) + '_' + str(number) + '.zip'
        # 如果压缩文件不存在
        if not os.path.exists(zipFilename):
            break
        number = number + 1

    # Create the ZIP file.
    print('Creating %s...' % (zipFilename))
    # 创建新ZIP 文件
    backupZip = zipfile.ZipFile(zipFilename, 'w')
    # TODO: Walk the entire folder tree and compress the files in each folder.
    print('Done.')

    # 提取文件目录
    # 一层一层获得目录
    # Walk the entire folder tree and compress the files in each folder.
    for foldername, subfolders, filenames in os.walk(folder):
        print('Adding files in %s...' % (foldername))

        # 压缩文件夹
        # Add the current folder to the ZIP file.
        backupZip.write(foldername)

        # Add all the files in this folder to the ZIP file.
        for filename in filenames:
            newBase = os.path.basename(folder) + '_'
            # 判断文件是否是压缩文件
            if filename.startswith(newBase) and filename.endswith('.zip'):
                continue  # don't backup the backup ZIP files
            backupZip.write(os.path.join(foldername, filename))
    backupZip.close()
    print('Done.')


backupToZip('image')

Creating image_1.zip...
Done.
Done.

2.3 选择性拷贝

编写一个程序，遍历一个目录树，查找特定扩展名的文件（诸如.pdf 或.jpg）。不论这些文件的位置在哪里，将它们拷贝到一个新的文件夹中。

import shutil
import os


def searchFile(path, savepath):
    # 判断要保存的文件夹路径是否存在
    if not os.path.exists(savepath):
        # 创建要保存的文件夹
        os.makedirs(savepath)
    # 遍历文件夹
    for foldername, subfolders, filenames in os.walk(path):
        for filename in filenames:
            # 判断是不是txt或者pdf文件
            if filename.endswith('txt') or filename.endswith('pdf'):
                inputFile = os.path.join(foldername, filename)
                # 保存文件路径
                outputFile = os.path.join(savepath, filename)
                # 文件保存
                shutil.copy(inputFile, outputFile)


searchFile("mytest", "save")

2.4 删除不需要的文件

编写一个程序，遍历一个目录树，查找特别大的文件或文件夹。将这些文件的绝对路径打印到屏幕上。

import os


def deletefile(path):
    for foldername, subfolders, filenames in os.walk(path):
        for filename in filenames:
            # 绝对路径
            filepath = os.path.join(foldername, filename)
            # 如果文件大于100MB
            if os.path.getsize(filepath)/1024/1024 > 100:
                # 获得绝对路径
                filepath = os.path.abspath(filepath)
                print(filepath)
                # 删除文件
                os.unlink(filepath)


deletefile("mytest")

2.5 消除缺失的编号

编写一个程序，在一个文件夹中，找到所有带指定前缀的文件，诸如spam001.txt,spam002.txt 等，并定位缺失的编号（例如存在spam001.txt 和spam003.txt，但不存在spam002.txt）。让该程序对所有后面的文件改名，消除缺失的编号。

import os
import re
# 路径地址
path = '.'
fileList = []
numList = []
# 寻找文件
pattern = re.compile('spam(\d{3}).txt')
for file in os.listdir(path):
    mo = pattern.search(file)
    if mo != None:
        fileList.append(file)
        numList.append(mo.group(1))

# 对存储的文件排序
fileList.sort()
numList.sort()

# 开始缺失的文件编号
# 编号从1开始
index = 1
# 打印不连续的文件
for i in range(len(numList)):
    # 如果文件编号不连续
    if int(numList[i]) != i+index:
        inputFile = os.path.join(path, fileList[i])
        print("the missing number file is {}:".format(inputFile))
        outputFile = os.path.join(path, 'spam'+'%03d' % (i+1)+'.txt')
        os.rename(inputFile, outputFile)

the missing number file is .\spam005.txt: