python--多进程按序号批量修改文件名

说明

文件名命名方式如图，是数字序号开头，但是中间有些文件删掉了，序号不连续，这里将序号连续起来，总的文件量有40w+，故使用多进程

代码

import os
import re
from multiprocessing import Pool

def getAllFilePath(pathFolder,filter=[".jpg",".txt"]):
    #遍历文件夹下所有图片
    result=[]
    #maindir是当前搜索的目录 subdir是当前目录下的文件夹名 file是目录下文件名
    for maindir,subdir,file_name_list in os.walk(pathFolder):
        for filename in file_name_list:
            apath=os.path.join(maindir,filename)
            ext=os.path.splitext(apath)[1]#返回扩展名
            if ext in filter:
                result.append(apath)
    return result

def changName(filePath,changeNum):
    fileName=os.path.basename(filePath)
    dirName=os.path.dirname(filePath)
    pattern = re.compile(r'\d+')
    if len(pattern.findall(filePath))!=0:
        numInFileName=str(int(pattern.findall(fileName)[0])-changeNum)
        newFileName=pattern.sub(numInFileName,fileName)
        os.rename(filePath,os.path.join(dirName,newFileName))
        print('{1} is changed as {0}'.format(newFileName,fileName))

def changeNameByList(fileList,changNum):
    print('fileList len is:{}'.format(len(fileList)))
    for fileName in fileList:
        changName(fileName,changNum)
        print(fileName,' is done!')

if __name__ =='__main__':
    allFilePath=getAllFilePath(r'E:\Numberdata\4')
    n_total=len(allFilePath)
    n_process=8 #8线程

    #每段子列表长度
    length=float(n_total)/float(n_process)
    indices=[int(round(i*length)) for i in range(n_process+1)]

    sublists=[allFilePath[indices[i]:indices[i+1]] for i in range(n_process)]

    #生成进程池  
    p=Pool(n_process)
    for i in sublists:
        print("sublist len is {}".format(len(i)))
        p.apply_async(changeNameByList, args=(i,161130))
    p.close()
    p.join()

注意事项

1. 多进程下python vscode终端debug不报错 注意可能潜在的bug
2. os.rename()无法将文件命名成已经存在的文件，否则会报错