整理几个用Python写的比较两文件差异的程序【推荐】

def cmpstr(str1, str2):
    col = 0
    for c1, c2 in zip(str1, str2):
        if c1 == c2:
            col += 1
            continue
        else :
            break
       
    #判断是怎样退出循环的，还有一种情况是串长度不同
    if c1 != c2 or len(str1) != len(str2):
        return col+1
    else :
        return 0
   
file1 = open("a.txt",'r')
file2 = open("b.txt",'r')

fa = file1.readlines()
fb = file2.readlines()
file1.close()
file2.close()

#用GBK解码，这样可以处理中文字符
fa = [ str.decode("gbk") for str in fa]
fb = [ str.decode("gbk") for str in fb]

row = 0
col = 0

#学习Python上玩蛇网 www.iplaypython.com！
#开始比较内容
for str1, str2 in zip(fa, fb):
    col = cmpstr(str1,str2)
    # col=0则说明两行相等
    if col == 0 :
        row += 1
        continue
    else:
        break

#如果有一行不同，或者文件长度不一样
if str1 != str2 or len(fa) != len(fb):
    #打印出不同的行序和列序，并把不同的前一句后本句打印出来
    #最后两个字符是不同的地方
    print "row:", row+1, "col:", col
    print "file a is:n", fa[row-1],fa[row][:col+1], "n"
    print "file b is:n", fb[row-1],fb[row][:col+1], "n"
else :
    print "All are same!"

#获取用户输入。   
raw_input("Press Enter to exit.")  

f1 = open(sys.argv[1], "r")
f2 = open(sys.argv[2], "r")

fileOne = f1.readlines()
fileTwo = f2.readlines()

f1.close()
f2.close()

outFile1 = open(sys.argv[3], "w")
outFile2 = open(sys.argv[4], "w")

for i in fileOne:
        if not i in fileTwo:
                outFile1.write(i)

for i in fileTwo:
        if not i in fileOne:
                outFile2.write(i)

outFile1.close()
outFile2.close()

#first time refacotring
import sys
from operator import attrgetter,itemgetter

#verify inputs
USAGE='''
%s file1 file2 output1 output2
'''% __file__

if len(sys.argv)<5:
        print USAGE
        sys.exit(2)

#open files with try
try:
        f1 = open(sys.argv[1], "r")
        f2 = open(sys.argv[2], "r")
except Exception,e:
        print 'encounter issues %s, while opening in files: %s %s' % (str(e),itemgetter(1)(sys.argv),itemgetter(2)(sys.argv))
        sys.exit(1)

fileOne = f1.readlines()
fileTwo = f2.readlines()

f1.close()
f2.close()

#open files with try
try:
        outFile1 = open(sys.argv[3], "w")
        outFile2 = open(sys.argv[4], "w")
except Exception,e:
        print 'encounter issues %s, while opening out files: %s %s' % (str(e),itemgetter(3)(sys.argv),itemgetter(4)(sys.argv))
        sys.exit(1)

l_minus=lambda x,y:list(set(x)-set(y))

outFile1.write('n'.join(l_minus(fileOne,fileTwo)))
outFile2.write('n'.join(l_minus(fileTwo,fileOne)))

outFile1.close()
outFile2.close()

#2nd time refactoring
import sys
from operator import attrgetter,itemgetter

#verify inputs
USAGE='''
%s file1 file2 output1 output2
'''% __file__

if len(sys.argv)<5:
        print USAGE
        sys.exit(2)

#open files with try
with open(itemgetter(1)(sys.argv), "r") as f1, open(itemgetter(2)(sys.argv), "r") as f2:
        fileOne = f1.readlines()
        fileTwo = f2.readlines()

#list subset
l_minus=lambda x,y:list(set(x)-set(y))
#open files with try
with open(itemgetter(3)(sys.argv), "w") as outFile1, open(itemgetter(4)(sys.argv), "w") as outFile2:
        outFile1.write('n'.join(l_minus(fileOne,fileTwo)))
        outFile2.write('n'.join(l_minus(fileTwo,fileOne)))

#系统模块
import sys
import os
import shutil
#用于文件查找的模块
from os.path import walk, join, normpath

#这个是完整的文件夹
PathA = "F:FullData"
#这个是缺文件的文件夹
PathB = "F:IncomplData"

#这个是目标文件夹
PathC = "F:DiffData"

#============================================================
#这个函数是用来递归处理PathA，对PathA里的每个文件和文件夹在PathB中找是否有对应的文件或文件夹
#若找不到，则在PathC中创建目录并拷贝文件
#拷贝文件时使用了shutil模块的copy2函数，以保留文件原来的创建时间和最后更新时间
def visit(arg, dirname, names):
    #把目录打印出来，以监视进度
    print dirname
  
    #得到路径名后，把前面的主路径名去掉
    dir=dirname.replace(PathA,"")
  
    dirnameB = os.path.join(PathB,dir)
    dirnameC = os.path.join(PathC,dir)
  
    if os.path.isdir(dirnameB):
        #若PathB里存在对应的文件夹，再逐个文件判断是否存在
        for file in names:
            if os.path.isfile(os.path.join(dirname