本文實例講述了python查找指定具有相同內容文件的方法。分享給大家供大家參考。具體如下：
python代碼用於查找指定具有相同內容的文件，可以同時指定多個目錄
調用方式：python doublesdetector.py c:;d:;e: > doubles.txt
?
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 # Hello, this script is written in Python - http://www.python.org # doublesdetector.py 1.0p import os, os.path, string, sys, sha message = """ doublesdetector.py 1.0p This script will search for files that are identical (whatever their name/date/time). Syntax : python %s <directories> where <directories> is a directory or a list of directories separated by a semicolon (;) Examples : python %s c:windows python %s c:;d:;e: > doubles.txt python %s c:program files > doubles.txt This script is public domain. Feel free to reuse and tweak it. The author of this script Sebastien SAUVAGE <sebsauvage at sebsauvage dot net> http://sebsauvage.net/python/ """ % ((sys.argv[0], )*4) def fileSHA ( filepath ) : """ Compute SHA (Secure Hash Algorythm) of a file. Input : filepath : full path and name of file (eg. 'c:windowsemm386.exe') Output : string : contains the hexadecimal representation of the SHA of the file. returns '0' if file could not be read (file not found, no read rights...) """ try: file = open(filepath,'rb') digest = sha.new() data = file.read(65536) while len(data) != 0: digest.update(data) data = file.read(65536) file.close() except: return '0' else: return digest.hexdigest() def detectDoubles( directories ): fileslist = {} # Group all files by size (in the fileslist dictionnary) for directory in directories.split(';'): directory = os.path.abspath(directory) sys.stderr.write('Scanning directory '+directory+'...') os.path.walk(directory,callback,fileslist) sys.stderr.write('n') sys.stderr.write('Comparing files...') # Remove keys (filesize) in the dictionnary which have only 1 file for (filesize,listoffiles) in fileslist.items(): if len(listoffiles) == 1: del fileslist[filesize] # Now compute SHA of files that have the same size, # and group files by SHA (in the filessha dictionnary) filessha = {} while len(fileslist)>0: (filesize,listoffiles) = fileslist.popitem() for filepath in listoffiles: sys.stderr.write('.') sha = fileSHA(filepath) if filessha.has_key(sha): filessha[sha].append(filepath) else: filessha[sha] = [filepath] if filessha.has_key('0'): del filessha['0'] # Remove keys (sha) in the dictionnary which have only 1 file for (sha,listoffiles) in filessha.items(): if len(listoffiles) == 1: del filessha[sha] sys.stderr.write('n') return filessha def callback(fileslist,directory,files): sys.stderr.write('.') for fileName in files: filepath = os.path.join(directory,fileName) if os.path.isfile(filepath): filesize = os.stat(filepath)[6] if fileslist.has_key(filesize): fileslist[filesize].append(filepath) else: fileslist[filesize] = [filepath] if len(sys.argv)>1 : doubles = detectDoubles(" ".join(sys.argv[1:])) print 'The following files are identical:' print 'n'.join(["----n%s" % 'n'.join(doubles[filesha]) for filesha in doubles.keys()]) print '----' else: print message希望本文所述對大家的Python程序設計有所幫助。
