一个python的文件对比脚本

脚本主要用来给游戏客户端做热更的。

处理方式就是针对每个文件求其MD5值，再根据文件的目录和名字对比两个版本的MD5值，如果不一样，则这次热更就需要更新这个文件。

用法很简单。

1，生成MD5码列表

参数有-i,针对某个目录下的指定路径下的所有文件生成MD5的列表。-v 当前版本号多少

2，对比两个路径的文件，并且将不同MD5的文件输出到指定路径下。

参数有-l,-r,-o.

-l就是左边的文件，为比较旧版本的目录。

-r就是右边的文件，为最新版本的目录。

-o就是不同文件的输出目录。

对比会优先查找左边文件夹下是否有.md5，如果有的话，会优先使用文件里的md5记录。

import sys, getopt
import os
import os.path
import hashlib
import shutil

searchFolders = ["\\src\\", "\\res\\"]

def usage():
print "this is useage"

def getmd5(filename, parentName, folderName):
m = hashlib.md5()
mfile = open(filename, 'rb')
m.update(mfile.read())
mfile.close()
md5value = m.hexdigest()

#get last part of file name
subStr = filename[len(parentName) - len(folderName):len(filename)]
return md5value+"\t"+ subStr

def getCurDir():
path = sys.path[0]
if os.path.isdir(path):
return path
elif os.path.isfile(path):
return os.path.dirname(path)

def saveFile(str, ver):
f = open(getCurDir() + "/" + ver + ".md5", 'w')
f.write(str)
f.close()

def getDescOfUrl(url):
saveStr = ""
descList = []
index = 0
for parent,dirnames,filenames in os.walk(url):
for filename in filenames:
for i, val in enumerate(searchFolders):
targParent = url + val
if targParent in parent:
fullPath = os.path.join(parent, filename)
md5 = getmd5(fullPath, targParent, val)
#print "file is: " + md5
saveStr = saveStr + md5 + "\n"
descList.append(md5)

return saveStr, descList

def onIArg(url, ver):
saveStr, descList = getDescOfUrl(url)
saveFile(saveStr, ver)

def getDicByFile(url):
file = open(url)
line = f.readline()
retDic = {}
while line:
md5, filename = line.split("\t")
retDic[filename] = md5

return retDic

def getDicByUrl(url):
saveStr, splitArr = getDescOfUrl(url)
retDic = {}

for value in splitArr:
md5, filename = value.split("\t")
retDic[filename] = md5

return retDic

def getDicOfUrl(url):
fileList = os.listdir(url)
version = ""
for value in fileList:
if os.path.splitext(value)[1] == '.md5':
version = os.path.splitext(value)[0]
break

if version != "":
return getDicByFile(url + "/" + version + ".md5")
else:
return getDicByUrl(url)

opts,args = getopt.getopt(sys.argv[1:], "hi:l:r:v:o:")

inputFile = ""
leftFile = ""
rightFile = ""
outFile = ""
version = ""
showHelp = False

for op, value in opts:
if op == "-i":
inputFile = value
elif op == "-v":
version = value
elif op == "-l":
leftFile = value
elif op == "-r":
rightFile = value
elif op == "-o":
outFile = value
elif op == "-h":
showHelp = True

if showHelp:
usage()
sys.exit()
elif inputFile != "":

if version == "":
print "you must input the version value using -v"
sys.exit()

onIArg(inputFile, version)
elif leftFile != "":
if rightFile == "":
print "you must input the right file url using -r"
sys.exit()
elif outFile == "":
print "you must input the out direct using -o"
sys.exit()
else:
print "on diff .."
diffDic = {}
leftDic = getDicOfUrl(leftFile)
rightDic = getDicOfUrl(rightFile)
for (filename, md5) in rightDic.items():
if not leftDic.has_key(filename):
diffDic[filename] = True
elif leftDic.get(filename) != md5:
diffDic[filename] = True

for (filename, val) in diffDic.items():
#if the folder exit
inUrl = rightFile + filename
outUrl = outFile + filename
folderIndex = outUrl.rfind("\\")

outFolder = outUrl[0:folderIndex]

if not os.path.isdir(outFolder):
os.makedirs(outFolder)

print("copy from " + rightFile + filename)
print("to " + outUrl)

shutil.copy(inUrl, outUrl)

脚本里的

searchFolders 是表示获取当前路径下这些子目录的所有文件。可以根据自己项目的情况，自己修改。