本文实例讲述了python查找指定具有相同内容文件的方法。分享给大家供大家参考。具体如下：
python代码用于查找指定具有相同内容的文件，可以同时指定多个目录
调用方式：python doublesdetector.py c:\;d:\;e:\ > doubles.txt
# 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
where 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
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:\windows\emm386.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
希望本文所述对大家的python程序设计有所帮助。