python通过MD5文件校验来查找重复内容的文件,pythonmd5,网上批量下载下来一堆文件
python通过MD5文件校验来查找重复内容的文件,pythonmd5,网上批量下载下来一堆文件
网上批量下载下来一堆文件,其中有重复的,人工一个一个比对太麻烦~~所以想写个Python脚本,通过MD5值校验来比对重复文件,然后把重复的删除掉```python
!/usr/bin/python
encoding=utf-8
import the modules
import osimport os.pathimport sysimport hashlib
define the functions
def findFile(rootPath, fileSeq, delSeq): dirs = os.listdir(rootPath) #list the directories under the root path for dir in dirs: #traversal all the directories path = rootPath + os.sep + dir #complete the path of current file if os.path.isdir(path): findFile(path, fileSeq, delSeq) #if current file is a directory, recursive the function else: md5Check(path, fileSeq, delSeq) #if not a directory, check the md5
def md5Check(path, fileSeq, delSeq): f = file(path, 'rb') #open the file with 'read-only' and 'binary' md5obj = hashlib.md5() md5obj.update(f.read()) #calculate the md5 if md5obj.hexdigest() in fileSeq: delSeq.append(path) #if md5 of current file is in the fileSeq, put the file path into the delSeq else: fileSeq.append(md5obj.hexdigest()) #if not in the fileSeq, put the md5 into the fileSeq f.close() #close the file
def delList(delSeq): print 'These files are waiting to be removed:' for delFile in delSeq: print delFile #list the file path in the delSeq
the main program
fileSeq = []delSeq = []while True: if len(sys.argv) == 1: rootPath = raw_input('Enter the root path: ') #one parameter means no parameter, ask the root path else: rootPath = sys.argv[1] #or get the second parameter as the root path try: findFile(rootPath, fileSeq, delSeq) #try if the root path is valid except(OSError): print 'The root path is invalid. Please enter again. ' del sys.argv[1:] continue #catch the except and delete all invalid parameters break
if len(delSeq) == 0 : print 'No duplicate file was found! ' #if no files in delSeq, exitelse: delList(delSeq) #or list the delSeq while True: answer = raw_input('Would you want to remove these files? Please answer yes(y) or no(n): ') answer.lower if answer in ('yes', 'y'): #if "yes" for delFile in delSeq: try: os.remove(delFile) #remove all files in delSeq except(OSError): print 'Warning! "%s" is not existed! ' % delFile continue #ignore the files witch are not existed print 'All duplicate files have been removed! ' break elif answer in ('no', 'n'): print 'Process has exited without any change! ' break #if "no", do nothing else: print 'Please enter yes(y) or no(n). 'sys.exit()
```
相关内容
- python通过openpyxl生成Excel文件,pythonopenpyxl,使用前请先安
- python通过pil生成图片验证码,,# -*- coding
- python操作sqlite的CRUD,pythonsqlitecrud,import sqlit
- python操作sqlite的CRUD,pythonsqlitecrud,import sqlit
- python开发的简单窗口界面的倒计时界面,python倒计时
- 用while编代码计算1+2+……+100,while,a=1b=2n=1whi
- 网站搬运工,,# -*- encodi
- python获取当天日期,python获取当天,import datet
- python编程从一个ftp传输文件到另一个ftp服务器,python传
- python提交post数据到远程url,python提交posturl,import sys,
评论关闭