基于python的文件操作

0.前言

类似于数据库的基本操作增删改查，工作中会经常出现使用python完成文件操作。
本文作者实现文件操作相关函数。

1.增

1.1 写入内容给文本文件

def writeTextFile(filePath, fileContent, encoding='utf8'):
    with open(filePath, 'w', encoding=encoding) as file:
        file.write(fileContent)

1.2 复制文件夹

函数copyDirectory比shutil.copytree功能更强大，更不容易报错。

import os
import shutil

def copyDirectory(old_dirPath, new_dirPath):
    if not os.path.isdir(old_dirPath):
        print('旧文件夹路径错误，不存在此文件夹')
        return
    fileName_list = list(os.walk(old_dirPath))[0][2]
    if not os.path.isdir(new_dirPath):
        os.makedirs(new_dirPath)
    for fileName in fileName_list:
        old_filePath = os.path.join(old_dirPath, fileName)
        new_filePath = os.path.join(new_dirPath, fileName)
        shutil.copy(old_filePath, new_filePath)
    dirName_list = list(os.walk(old_dirPath))[0][1]
    for dirName in dirName_list:
        old_subDirPath = os.path.join(old_dirPath, dirName)
        new_subDirPath = os.path.join(new_dirPath, dirName)
        copyDirectory(old_subDirPath, new_subDirPath)

2.删

2.1 删除文件夹

本文作者使用过shutil库的rmtree函数， 此函数经常报错OS Error，所以自己编写deleteDirectory函数。

import os
def deleteDirectory(dirPath):
    for walk in os.walk(dirPath):
        dirPath_2 = walk[0]  
        fileName_list = walk[2]
        for fileName in fileName_list:
            filePath = os.path.join(dirPath_2, fileName)
            os.remove(filePath)
    for walk in list(os.walk(dirPath))[::-1]:
        dirPath_2 = walk[0]      
        dirName_list = walk[1]
        for dirName in dirName_list:
            dirPath_3 = os.path.join(dirPath_2, dirName)
            os.rmdir(dirPath_3)
    if os.path.isdir(dirPath):
        os.rmdir(dirPath)

2.2 创建空文件夹

import os
def makeDirectoryEmpty(dirPath):
    if os.path.isdir(dirPath):
        for walk in os.walk(dirPath):
            dirPath_2 = walk[0]  
            fileName_list = walk[2]
            for fileName in fileName_list:
                filePath = os.path.join(dirPath_2, fileName)
                os.remove(filePath)
        for walk in list(os.walk(dirPath))[::-1]:
            dirPath_2 = walk[0]      
            dirName_list = walk[1]
            for dirName in dirName_list:
                dirPath_3 = os.path.join(dirPath_2, dirName)
                os.rmdir(dirPath_3)
    else:
        os.makedirs(dirPath)

3.改

3.1 批量修改图片大小

import os
from PIL import Image

def getFilePathList(dirPath, partOfFileName=''):
    allFileName_list = list(os.walk(dirPath))[0][2]
    fileName_list = [k for k in allFileName_list if partOfFileName in k]
    filePath_list = [os.path.join(dirPath, k) for k in fileName_list]
    return filePath_list

def batchResizeImage(oldDirPath, newDirPath, height, width):
    if not os.path.isdir(newDirPath):
        os.mkdir(newDirPath)
    jpgFilePath_list = getFilePathList(oldDirPath, '.jpg')
    for jpgFilePath in jpgFilePath_list:
        image = Image.open(jpgFilePath)
        resized_image = image.resize((height, weight), Image.ANTIALIAS)
        jpgFileName = os.path.split(jpgFilePath)[1]
        saveFilePath = os.path.join(newDirPath, jpgFileName)
        resized_image.save(saveFilePath)
        
oldDirPath = 'source_images'
newDirPath = 'train_images'
height = 640
width = 640
batchResizeImage(oldDirPath, newDirPath, height, width)

4.查

4.1 查询文件夹中的文件

import os

def getFileNameList(dirPath, partOfFileName=''):
    allFileName_list = list(os.walk(dirPath))[0][2]
    fileName_list = [k for k in allFileName_list if partOfFileName in k]
    return fileName_list
    
def getFilePathList(dirPath, partOfFileName=''):
    allFileName_list = list(os.walk(dirPath))[0][2]
    fileName_list = [k for k in allFileName_list if partOfFileName in k]
    filePath_list = [os.path.join(dirPath, k) for k in fileName_list]
    return filePath_list

def getFilePathList_2(dirPath, partOfFileName=''):
    filePath_list = []
    for walk in os.walk(dirPath):
        subDirPath = walk[0]
        fileName_list = [k for k in walk[2] if partOfFileName in k]
        filePath_list.extend([os.path.join(subDirPath, k) for k in fileName_list])
    return filePath_list

4.2 读取文本文件

def readTextFile(filePath, encoding='utf8'):
    with open(filePath, encoding=encoding) as file:
        return file.read()

4.3 根据文件夹路径dirPath、文件中内容partOfFileContent、文件名partOfFileName得出文件路径

传入3个参数：文件夹路径dirPath、指定内容partOfFileContent、代码文件后缀名suffixOfFileName

import os

def searchFileContent(dirPath, partOfFileContent, partOfFileName=''):
    dirPath = os.path.expanduser(dirPath)
    for walk in os.walk(dirPath):
        fileName_list = walk[2]
        filePath_list = [os.path.join(walk[0], k) for k in fileName_list if partOfFileName in k]
        for filePath in filePath_list:
            try:
                with open(filePath, encoding='gbk') as file:
                    fileContent = file.read()
            except Exception as e:
                try:
                    with open(filePath, encoding='utf8') as file:
                        fileContent = file.read()
                except Exception as e:
                    pass
            if partOfFileContent=='' or partOfFileContent in fileContent:
                print(filePath)