python2.7實現複製大量檔案及資料夾資料
阿新 • • 發佈:2020-01-09
需求:拷大量資料,發現有2000G,靠系統的複製功能怕是得好幾個小時,於是回來學一手操作,話不多說上程式碼:
說明:CopyFiles1是可以將sourceDir連子目錄一起原樣複製到targetDir,而CopyFiles2是在sourceDir中篩選特定格式檔案,然後將其直接放在targetDir中,會很亂。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): #完全連子目錄也會複製好,美觀 global copyFileCounts print(sourceDir ) print("%s 當前處理資料夾%s已處理%s 個檔案" %(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 複製完畢" %(time.strftime('%Y-%m-%d %H:%M:%S',targetF)) else: print ("%s %s 已存在,不重複複製" %(time.strftime('%Y-%m-%d %H:%M:%S',targetF)) if os.path.isdir(sourceF): copyFiles(sourceF,targetF) def CopyFiles2(dir): #會將目錄下所有檔案都複製在一起,速度快,可以篩選檔案 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]=='.':#這裡注意filename是個元組,splitext方法的時候只能是字串 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("總共有",i,"圖層檔案被複制!") 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) #實戰程式碼 #!/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:]" #原始目錄和拷貝到的目錄地址 sourceDir = r"D:\tools\wj" targetDir = r"D:\Users\wj" copyFileCounts = 0 #定義拷貝檔案的函式 def copyFiles(sourceDir,targetDir): global copyFileCounts print (sourceDir ) print ("%s 當前處理資料夾%s已處理%s 個檔案" %(time.strftime('%Y-%m-%d %H:%M:%S',copyFileCounts) ) for f in os.listdir(sourceDir): sourceF = os.path.join(sourceDir,f) targetF = os.path.join(targetDir,f) if os.path.isfile(sourceF): #建立目錄 if not os.path.exists(targetDir): os.makedirs(targetDir) copyFileCounts += 1 #檔案不存在的話,或者存在但是大小存在差異不同,執行完全覆蓋操作 if not os.path.exists(targetF) or (os.path.exists(targetF) and (os.path.getsize(targetF) != os.path.getsize(sourceF))): #二進位制檔案 open(targetF,"rb").read()) print u"%s %s copy over" %(time.strftime('%Y-%m-%d %H:%M:%S',targetF) else: print("%s %s is exists,please don't copy more" %(time.strftime('%Y-%m-%d %H:%M:%S',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)
以上就是本文的全部內容,希望對大家的學習有所幫助,也希望大家多多支援我們。