python文件操作

#! /usr/bin/python
# -*- coding:utf-8 -*-
'''
Created on 2013-12-11

@author: Java
'''
import os
import MySQLdb
from db.DbUtil import DbUtil
import time
import shutil
import sys
import zipfile
from os.path import  join,getsize
import math


class FileOption():
    #global fileList  类的全局变量  放置位置 
    
    def __init__(self):
        pass
    
    def CreateFloderByList(self,pathList):
        '''
        创建文件夹
        :param pathList:文件夹集合
        '''
        self.pathList = pathList
        for path in pathList:
            if not os.path.isdir(path):
                os.makedirs(path)
                
    def CreateFloder(self,path):
        
        self.path = path
        if not os.path.isdir(path):
            os.makedirs(path)    
            
    def readFileName(self,path):
        fileNames = os.listdir(path)
        return fileNames
    
    def renameFile(self,path):
        '''
        批量修改文件的名称
        :param path:
        '''
        self.path = path
        
    
        allRenameList = os.listdir(path)
        for allRenameItem in allRenameList:
            renamePath =os.path.join(path,allRenameItem)
            if os.path.isfile(renamePath)==True:
                print allRenameItem
                if allRenameItem.find('.')<0:
                    newname = allRenameItem+'index.html'
                    os.renames(os.path.join(path,allRenameItem),os.path.join(path,newname))
                    print allRenameItem,'ok'
                else:
                    os.renames(os.path.join(path,'index.html'))
                    print allRenameItem,'ok'
                    
    def renameFile2(self,path,newName):
        '''
        批量修改文件名称,解决了中文文件名称的问题
    
        :param path:路径
        :param newName:新名称
        '''
    
        allRenameList = os.listdir(path)
        for allRenameItem in allRenameList:
            renamePath =os.path.join(path,allRenameItem)
            if sys.getfilesystemencoding()=='mbcs':
                renamePath=renamePath.decode('mbcs')
                print renamePath
            elif sys.getfilesystemencoding() & 0x800:
                renamePath=renamePath.decode('utf-8')
#                 print renamePath
            if os.path.isfile(renamePath)==True:
                if sys.getfilesystemencoding()=='mbcs':
                    allRenameItem=allRenameItem.decode('mbcs')
                elif sys.getfilesystemencoding() & 0x800:
                    allRenameItem=allRenameItem.decode('utf-8')
                    if allRenameItem.find('.')<0:
                        newname = allRenameItem+newName
                        os.renames(os.path.join(path,newname))
                        print allRenameItem,'ok'
                    else:
                        os.renames(os.path.join(path,newName))
                        print allRenameItem,'ok'
            else:
                option = FileOption()
                option.renameFile2(renamePath,newName)
            
    def IteratrFolder(self,testpath):
        '''
        遍历文件夹 并且解决了中文文件名的问题
        查看系统文件名编码  sys.getfilesystemencoding()
        :param path:
        '''
        listsubDir=[]
        list = os.listdir(testpath)
        for filename in list:
            if sys.getfilesystemencoding()=='mbcs':
                filename=filename.decode('mbcs')
                paths = os.path.join(testpath,filename)
                if os.path.isdir(paths):
                    listSub = os.listdir(paths)
                    for sub in listSub:
                        subDir = os.path.join(paths,sub)
                        listsubDir.append(subDir)
                return listsubDir
                    
    def RemoveFilesByFileType(self,fileType):
        '''
        批量删除指定文件夹下指定文件类型的文件
        :param path:路径
        :param fileType:文件类型
        '''
        fileList = os.listdir(path)
        for one in fileList:
            print one
            removePath =os.path.join(path,one)
            if os.path.isfile(removePath)==True:
                if removePath.find(fileType)>=0:
                    os.remove(removePath)
     
    def isSubString(self,subStrList,string):
        '''
        判断 字符串Str是否包含序列subStrList 中的每一个子字符串
        subStrList =['py','java','txt']
        string = 'nihaojavaandpython.txt'
        isSubString(subStrList,string)
        reutn Treu(or False)
        
        '''  
        flag = True
        for substr in subStrList:
            if not (substr in string):
                flag = False
        
        return flag
    
    def getFileSuffix(self,filePath):
        '''
        得到所有文件的后缀名，用系统的函数os.path.splitext
        '''
        try:
            
            for (dirPath,dirs,files) in os.walk(filePath):
                for filename in files:
                    ext = os.path.splitext(filename)[1] #取得文件类型，注意它还带着点号   
                    print ext
        except os.error,e:
            print 'error e'%e  
    
    def getFileListBySuffix(self,filePath,fileList,suffixStr=[]):
        '''
        获取目录中指定的后缀名的文件     (自己写的方法)  
        '''
        fileNames = os.listdir(filePath)
        for fileName in fileNames:
            findPath = os.path.join(filePath,fileName) 
            if os.path.isfile(findPath):
                if (len(fileNames)>0):
                    if(len(suffixStr)>0):
                        #返回指定类型的文件名
                        option = FileOption()
                        if (option.isSubString(suffixStr,fileName)):
                            fullFileName = os.path.join(filePath,fileName)
                            fileList.append(fullFileName)                        
                   
            elif os.path.isdir(findPath):
                option = FileOption()
                option.getFileListBySuffix(findPath,suffixStr)              
        #对文件名排序           
        if (len(fileList)>0):
            fileList.sort()
            
            return  fileList
        
    def getFileListBySuffix_Better(self,suffixStr=[]):
        '''
        获取目录中指定的后缀名的文件     (自己写的方法速度更快)  
        '''
        for (dirPath,files) in os.walk(filePath):
            for filename in files:
                if (len(files)>0):
                    if(len(suffixStr)>0):
                        #返回指定类型的文件名
                        option = FileOption()
                        if (option.isSubString(suffixStr,filename)):
                            fullFileName = os.path.join(filePath,filename)
                            fileList.append(fullFileName)                        
              
        #对文件名排序           
        if (len(fileList)>0):
            fileList.sort()
            return  fileList    
    def getFileListBySuffix_Best(self,files) in os.walk(filePath):
            for filename in files:
                if (len(files)>0):
                    if(len(suffixStr)>0):
                        #返回指定类型的文件名
                        for suf in suffixStr:
                            if os.path.splitext(filename)[1].find (suf)==0:
                                fullFileName = os.path.join(dirPath,filename)
                                fileList.append(fullFileName)                        
              
        #对文件名排序           
        if (len(fileList)>0):
            fileList.sort()
            return  fileList    

    
    def copyFiles(self,sourceDir,targetDir): 
        '''
        实现对文件的拷贝
        '''

        for file in os.listdir(sourceDir): 
            sourceFile = os.path.join(sourceDir,file) 
            targetFile = os.path.join(targetDir,file) 
            if os.path.isfile(sourceFile): 
                if not os.path.exists(targetDir):  
                    os.makedirs(targetDir)  
                if not os.path.exists(targetFile) or(os.path.exists(targetFile) and (os.path.getsize(targetFile) != os.path.getsize(sourceFile))):  
                    open(targetFile,"wb").write(open(sourceFile,"rb").read()) 
            if os.path.isdir(sourceFile): 
                First_Directory = False
                create = FileOption() 
                create.copyFiles(sourceFile,targetFile)
                
    def moveFiles(self,dir,extName):
        '''
        :param dir:原始数据目录
        :param extName:文件的扩展名
        根据文件名创建文件夹，并将其放入对应的文件夹内
        '''
        self.dir = dir
        self.extName = extName
        for i in os.listdir(dir):
            name = ''.join(i.split(extName)[0:-1])
            print name
            os.mkdir(os.path.join(dir,name))
            os.rename(os.path.join(dir,i),os.path.join(dir,name,i))
                        
    
    def moveDirAndFiles(self,oldPath,newPath):
        '''
        实现对指定文件的迁移
        :param oldPath:源路径
        :param newPath:目的路径
        '''
        self.oldPath = oldPath
        self.newPath = newPath
        try:
            allChangeFileList = os.listdir(oldPath)
            for allChangeItem in allChangeFileList:
                changeFilePath =os.path.join(oldPath,allChangeItem)

                if os.path.isdir(changeFilePath):

                    dstAddPath = os.path.join(newPath,allChangeItem)
                    if os.path.exists(dstAddPath):

                        moveFiles = FileOption()
                        moveFiles.moveDirAndFiles(oldPath,dstAddPath)
                    else:
                        os.makedirs(newPath)
                        os.rename(oldPath,newPath)
                else:
                    shutil.move(oldPath,newPath)
                return True
        except os.errno,e:
            print 'error e%s'%e
            
            
            
#     def moveDirAndFiles_Better(self,newPath):
#         '''
#         实现对指定文件的迁移
#         :param oldPath:源路径
#         :param newPath:目的路径
#         '''
#         self.oldPath = oldPath
#         self.newPath = newPath
#         try:
#             for (dirPath,files) in os.walk(oldPath):
#                 for filename in files:
#                     dstPath = os.path.join(dirPath,filename)
#                     print dstPath
#                     if os.path.exists(dstPath):
#                         shutil.move(oldPath,newPath)
#                     else:
#                         os.makedirs(newPath)
#                         os.rename(oldPath,newPath)
#         except os.errno,e:
#             print 'error e%s'%e

    def TraverseFolder(self,path):
        '''
        遍历文件夹
        :param path:
        '''
        self.path = path
        print "<----folder&file---->"
        no=0
        for (path,files) in os.walk(path):
            print 
            no += 1
            print "No.%d"%no
            print "path=%s"%path
            if len(dirs)!=0:
#                 print type(dirs)
                subfolders = ''
                for dir in dirs:
                    subfolders += dir+';'
                subfolders = '[' + subfolders + ']'
                print "subfolders=%s"%subfolders
            if len(files)!=0:
                filenames = ''
                for filename in files:
                    filenames += filename+';'
                filenames = '[' + filenames + ']'
                print "files=%s"%filenames
        print "<----folder&file---->"
    

    
    def renameExpendNameOfFile(self,oldexp_name,newexp_name):
        '''
        
        :param path:路径
        :param oldexp_name:旧的扩展名
        :param newexp_name:新的扩展名
        '''
        self.path = path
        self.oldexp_name = oldexp_name
        self.newexp_name = newexp_name
        changedCount = 0          
        for (path,files) in os.walk(path):
            for filename in files:
                ext = os.path.splitext(filename)[1] #取得文件类型，注意它还带着点号            
                if (ext == oldexp_name):
                    changedCount += 1
                    newname = filename.replace(oldexp_name,newexp_name)
                    oldpath = path + "" + filename      
                    newpath = path + "" + newname
                    try:
                        os.rename(oldpath,newpath)
                        print 'No.%d'%changedCount,'change',oldpath,'to',newpath
                    except BaseException,e:  
                        print(str(e))
        
        
    def renameExpendNameOfFile2(self):
        '''
    修改文件的后缀名,有控制台输入参数
    '''
        str = u'请输入要处理的文件夹路径====>'
        path = raw_input(str.encode('utf-8'))
        print path
    
        str = u'请输入源文件类型(不包括.)====>'
        old_ext = "."+raw_input(str.encode('utf-8'))
        print old_ext
    
        str = u'请输入目标文件类型(不包括.)====>'
        new_ext = "."+raw_input(str.encode('utf-8'))    
        print new_ext
    
        print   #输出空行占位
        f = FileOption()
        f.TraverseFolder(path)
        print
    
        str = u'开始批量更名'
        print str
        print '<-----------------'
        changedCount = 0          
        for (path,files) in os.walk(path):
            for filename in files:
                ext = os.path.splitext(filename)[1] #取得文件类型，注意它还带着点号            
                if (ext == old_ext):
                    changedCount += 1
                    newname = filename.replace(old_ext,new_ext)
                    oldpath = path + "" + filename      
                    newpath = path + "" + newname
                    try:
                        os.rename(oldpath,e:  
                        print(str(e))
        print '----------------->'


    def deleteFolder(self,path):
        '''
        删除指定目录下的文件
        :param path:
        '''
        self.path = path
        
        for root,files in os.walk(path,False):
            for name in files:
                os.remove(os.path.join(root,name))
            for name in dirs:
                os.rmdir(os.path.join(root,name))
                
                
                
    def remove_empty_dir(self,path):
        '''
        删除目录下所有的空文件夹
        :param path:
        '''
        self.path = path
        
        while(path[-1] == ""):
            path = path[:-1]
            print path
 
        a = {}
        for root,False):
            print dirs
            if len(files) == 0:
                a[root] = 0
            else:
                for file in files:
                    try:
                        fn = os.path.join(root,file)
                        size = os.path.getsize(fn)
                        if size != 0:
                            b = root
                            while(b != path):
                                a[b] = 1
                                b = b.rpartition("")[0]
                            a[path] = 1
                        else:
                            try:
                                os.remove(fn)
                                a[root] = 0
                            except (WindowsError):
                                b = root
                                while(b != path):
                                    a[b] = 1
                                    b = b.rpartition("")[0]
                                a[path] = 1
                    except (WindowsError):
                        b = root
                        while(b != path):
                            a[b] = 1
                            b = b.rpartition("")[0]
                        a[path] = 1
                     
                    if a[root]:
                        break;
        empty_dirs = []
        for i,j in a.iteritems():
            if j == 0:
                print i
                empty_dirs.insert(0,i)
        del a
        empty_dirs.sort(reverse = True)    
        for i in empty_dirs:
            try:
                os.rmdir(i)
                print "%s 删掉了!!" % (i)
            except (WindowsError):
                print "%s 删不掉!!" % (i)
                
    def zipAllFiles(self,startdir,zipPath):
        '''
    实现批量压缩文件
        :param startdir: 压缩包的层次  比如download.zip解压开是：download/1/1.html   所以startdir 就是‘f:/download/’
        :param zipPath:  download/1/ 文件的上次层次
        '''
        self.startdir = startdir
        self.zipPath = zipPath
        
        for dirpath,dirnames,filenames in os.walk(startdir):
            for filename in filenames:
                newp = dirpath+''

                if newp.find('F:'+zipPath)==0:
                    print os.path.join(newp,filename)
             
#                     f = zipfile.ZipFile('F:pythonTestzipTest'+'download'+str(DownID)+'.zip','a',zipfile.ZIP_DEFLATED)
#                     f.write(os.path.join(newp,filename))
#                     print os.path.join(newp,filename)
#                     f.close()
                    
                    
    def getAllFileSize(self,size):
        '''
        得到整个文件所在文件夹的大小
        1B = 8 bit
        1KB = 1024 B
        1MB = 1024 KB
        1MB = 1024*1024 B
        1GB = 1024 MB
        :param path:
        '''
        self.path = path
        for dirpath,files in os.walk(path):
            size += sum([getsize(join(dirpath,name)) for name in files])
        return size
    
    def getFileSize(self,path):
        '''
        得到每个文件的大小，以字典方式存入list中
        :param path:
        '''
        self.path = path
        
        sizeDic={}
        sizeList = []
        for dirpath,files in os.walk(path):
            
            for file in files:
                fileSize = getsize(join(dirpath,file))
                sizeDic={file:fileSize}
                sizeList.append(sizeDic)
        return sizeList

    
            
        
        
if __name__=='__main__':
    db = DbUtil()
    create =FileOption()
    size1 = create.getFileSize('F:pythonTestdelete')