用python2.7实现复制大量文件及文件夹资料

需求：拷大量数据，发现有2000G，靠系统的复制功能怕是得好几个小时，于是回来学一手操作，话不多说上代码：

说明：CopyFiles1是可以将sourceDir连子目录一起原样复制到targetDir，而CopyFiles2是在sourceDir中筛选特定格式文件，然后将其直接放在targetDir中，会很乱。。。但是很快

 

import os
import time
import shutil
sourceDir = r"D:\copytest\datatest"
targetDir = r"D:\copytest\result"
copyFileCounts = 0
 
def CopyFiles1(sourceDir, targetDir):
#完全连子目录也会复制好，美观
   global copyFileCounts
   print(sourceDir )
   print("%s 当前处理文件夹%s已处理%s 个文件" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), sourceDir,copyFileCounts) )
   for f in os.listdir(sourceDir):
       sourceF = os.path.join(sourceDir, f)
       targetF = os.path.join(targetDir, f)
 
       if os.path.isfile(sourceF):
 
           if not os.path.exists(targetDir):
                os.makedirs(targetDir)
           copyFileCounts += 1
 
 
           if not os.path.exists(targetF) or (os.path.exists(targetF) and (os.path.getsize(targetF) != os.path.getsize(sourceF))):
 
               open(targetF, "wb").write(open(sourceF, "rb").read())
               print ("%s %s 复制完毕" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF))
           else:
               print ("%s %s 已存在，不重复复制" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF))
 
       if os.path.isdir(sourceF):
           copyFiles(sourceF, targetF)
 
def CopyFiles2(dir):
    #会将目录下所有文件都复制在一起，速度快，可以筛选文件
    i=0
    for root,dir1,filename in os.walk(dir):
     #print(filename)
     for index in range(len(filename)):
        #print(os.path.splitext(filename[index])[1])
        #if os.path.splitext(filename[index])[1]=='.':#这里注意filename是个元组，splitext方法的时候只能是字符串
        if 1==1:
            #i+=1
            print('here')
            root1="D:\\copytest\\result3"
            old_path = os.path.join(root, filename[index])
            print(old_path)
            new_path = os.path.join(root1,filename[index])
            shutil.copyfile(old_path,new_path)
 
#print("总共有",i,"图层文件被复制！")
 
if __name__ == "__main__":
  time_start = time.time()
  try:
    import psyco
    psyco.profile()
  except ImportError:
     pass
  #CopyFiles1(sourceDir,targetDir)
  CopyFiles2("D:/copytest/datatest")
  time_end = time.time()
  print('totally cost', time_end - time_start)

#实战代码
#!/usr/bin/python2
# coding=UTF-8
#@author neo_will
#version 2019-04-02 10:39

import os
import os.path
import shutil
import time, datetime

#fpath_2018 = [1207, 1121, 1120, 1119, 1112, 1101, 1025, 1009, 0704, 0608, 0531, 0530, 0517, 0502, 0418, 0330, 0201, 0131]
#sourceDir=r"F:\LEVEL2_shanghai\2018\fpath_2018[0:]"
#des_dir=r"G:\MarketDataSupplement\shanghai\2018\fpath_2018[0:]"
#原始目录和拷贝到的目录地址
sourceDir = r"D:\tools\wj"
targetDir = r"D:\Users\wj"
copyFileCounts = 0

#定义拷贝文件的函数
def copyFiles(sourceDir, targetDir):
	global copyFileCounts
	print (sourceDir )
	print ("%s 当前处理文件夹%s已处理%s 个文件" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), sourceDir,copyFileCounts) )
	for f in os.listdir(sourceDir):
		sourceF = os.path.join(sourceDir, f)
		targetF = os.path.join(targetDir, f)
		if os.path.isfile(sourceF):
			#创建目录
			if not os.path.exists(targetDir):
				os.makedirs(targetDir)
			copyFileCounts += 1

			#文件不存在的话，或者存在但是大小存在差异不同，执行完全覆盖操作
			if not os.path.exists(targetF) or (os.path.exists(targetF) and (os.path.getsize(targetF) != os.path.getsize(sourceF))):
				#二进制文件
				open(targetF, "wb").write(open(sourceF, "rb").read())
				print u"%s %s copy over" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF)
			else:
					print("%s %s is exists,please don't copy more" %(time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())), targetF))

		if os.path.isdir(sourceF):
			copyFiles(sourceF, targetF)

if __name__ == "__main__":
	time_start = time.time()
	try:
		import psyco
		psyco.profile()
	except ImportError:
		pass
	#copyFiles(sourceDir,targetDir)
	copyFiles(r"D:\tools\wj",r"D:\Users\wj")
	time_end = time.time()
	print('totally cost', time_end - time_start)