Dim a(),b(),c(),n
file1 = "A.txt"
file2 = "B.txt"
file3 = "C.txt"
Set fso = CreateObject("Scripting.FileSystemObject")

i=0
n = InputBox("输入"&file1&"每行重复的次数：",,1)
Set f = fso.OpenTextFile(file1,1)
Do While f.AtEndOfStream <> True
    str = f.ReadLine
    For j=1 to n
        ReDim Preserve a(i)
        a(i) = str
        i = i+1
    Next
Loop
f.Close

i=0
n = InputBox("输入"&file2&"每行重复的次数：",,1)
Set f = fso.OpenTextFile(file2,1)
Do While f.AtEndOfStream <> True
    str = f.ReadLine
    For j=1 to n
        ReDim Preserve b(i)
        b(i) = str
        i = i+1
    Next
Loop
f.Close

i=0
n = InputBox("输入"&file3&"每行重复的次数：",,1)
Set f = fso.OpenTextFile(file3,1)
Do While f.AtEndOfStream <> True
    str = f.ReadLine
    For j=1 to n
        ReDim Preserve c(i)
        c(i) = str
        i = i+1
    Next
Loop
f.Close

On Error Resume Next
Set f = fso.CreateTextFile("合并.txt",2)
For k=0 to UBound(a)
    f.WriteLine a(k)&","&b(k)&","&c(k)
Next
f.Close
Msgbox "完成"
复制代码

ed2k://|file|Black%20Hat%20Python%20-%20Python%20Programming%20For%20Hackers%20And%20Pentesters%20-%20Justin%20Seitz%20(No%20Starch%20Press,%202015).pdf|10527596|AA5C5E3170948C5E8D69A6452E485BCC|/
ed2k://|file|Black%20Hat%20Python%20-%20Python%20Programming%20for%20Hackers%20and%20Pentesters%202014-P2P.pdf|10527371|A2E373D2B0DB8B9C69AED7D4B1C57FE8|h=PVEMBL4LSZGMBIYJMLJFKBM2BSMRK3SZ|/
ed2k://|file|Black%20Hat%20Python,%20Python%20Programming%20for%20Hackers%20_%20Pentesters.pdf|10527370|1EB844B6AFEABBD3E80195880AD905DD|/
ed2k://|file|[No%20Starch%20Press]%20Black%20Hat%20Python%20-%20Python%20programming%20for%20hackers%20and%20pentesters%20(2015).pdf|7334960|C4839361F53A667C5E02BB9C6F419FA6|/
ed2k://|file|[No%20Starch%20Press]%20Black%20Hat%20Python%20-%20Python%20programming%20for%20hackers%20and%20pentesters%20(2015).pdf|7226003|4DBDD55D316316E2BD1756E827B6BD53|/
ed2k://|file|BlackHat%202007%20-%20Reverse%20Engineering%20Automation%20with%20Python.pdf|3701524|DD5F4D61D7C9B086C22E830ADDEA63F1|/
ed2k://|file|Black%20Hat%20Python,%20Python%20Programming%20for%20Hackers.pdf|3167049|58CEE78C549C4F4AC17DF7BB86E5788E|/
复制代码

#python重复行数合并文件
#题目来源: http://www.bathome.net/viewthread.php?tid=38017
#依山居 4:22 2015/11/8

#相关资料 Python按行读文件：
#http://www.cnblogs.com/xuxn/archive/2011/07/27/read-a-file-with-python.html

#相关资料 Python迭代器和生成器：
#http://python.jobbole.com/81881/

#python3 生成器
#http://t.cn/R2GTPBY

#Python关键字yield的解释
#http://pyzh.readthedocs.org/en/latest/the-python-yield-keyword-explained.html

#探寻Python中如何同时迭代多个iterable对象
#http://blog.csdn.net/kxcfzyk/article/details/41380017

#以下三个函数逐行读取对应文件,n为默认重复次数。
def txta(txta="a.txt",n=6):
    with open(txta) as fa:
        for la in fa:
            la=la.rstrip()+","
            for r in range(n):
                yield la
        
def txtb(txtb="b.txt",n=3):
    with open(txtb) as fb:
        for lb in fb:
            lb=lb.rstrip()+","
            for r in range(n):
                yield lb

def txtc(txt="c.txt",n=1):
    with open(txt) as f:
        for l in f:
            l=l.rstrip()+"\n"
            for r in range(n):
                yield l

def merge(a,b,c,txt="test.txt"):
    with open(txt,"a+") as f:
        f.write(a+b+c)
        #f.flush()
        
bt=txtb()
at=txta()
for c in txtc():
    b=next(bt)
    a=next(at)
    merge(a,b,c)

try:
    input("执行完成,按回车退出")
except SyntaxError:
    pass
复制代码

"""
生成测试数据
依山居 19:46 2015/11/13
python列表解析真好玩~
"""
import time
start=time.time()

an=1
bn=3
cn=6
x=1000000
al=["%012d\n" % r for r in range(an*x)]
bl=["%012d\n" % r for r in range(bn*x)]
end=time.time()
pt=end-start
print("运行耗时1：",pt)
cl=["%012d\n" % r for r in range(cn*x)]
end=time.time()
pt=end-start
print("运行耗时2：",pt)

atxt=open("aa.txt","w+")
atxt.writelines(al)
atxt.close()

btxt=open("bb.txt","w+")
btxt.writelines(bl)
btxt.close()

end=time.time()
pt=end-start
print("运行耗时3：",pt)

ctxt=open("cc.txt","w+")
ctxt.writelines(cl)
ctxt.close()

end=time.time()
pt=end-start
print("运行耗时：",pt)

try:
    input("按回车退出")
except SyntaxError:
    pass
复制代码

"""
每行数据重复N次合并生成新文件
依山居 0:54 2015/11/14
太困了,回头再改，6百万行，大约17秒。。。
非常流氓地使用了sorted排序数据。实际数据中估计不能使用.
"""

import time
start=time.time()

an=6
with open("aa.txt") as f:
    ta=f.read()
    ta=ta.rsplit()
    al=[(r+",") for r in ta]*an
    al=sorted(al)
print(len(al))   
bn=3
with open("bb.txt") as f:
    tb=f.read()
    tb=tb.rsplit()
    bl=[(r+",") for r in tb]*bn
    bl=sorted(bl)
    
print(len(bl))    
cn=1
with open("cc.txt") as f:
    tc=f.read()
    tc=tc.rsplit()
    cl=[r+"\n" for r in tc]
print(len(cl))
end=time.time()
pt=end-start
print("运行耗时：",pt)

rn=len(cl)
tal=[]
for r in range(rn):
    tal.append(al[r]+bl[r]+cl[r])
    
end=time.time()
pt=end-start
print("运行耗时：",pt)

with open("out.txt","w+") as f:
    f.writelines(tal)
    f.close()
    
end=time.time()
pt=end-start
print("运行耗时：",pt)
try:
    input("按回车退出")
except SyntaxError:
    pass
复制代码

"""
每行数据重复N次合并生成新文件
题目来源 http://www.bathome.net/thread-38017-2-1.html
依山居 0:54 2015/11/14
这个版本可以使用来处理实际数据。。。6百万行，大约17秒。。。
总结：几百万行数据真不算多。不需要逐行读取处理。python列表解析是个好东西~

使用重复列表中元素更好的方法 http://www.oschina.net/question/96078_2141454
python笔记_列表解析 http://www.jianshu.com/p/c635d3c798c2
"""

import time
start=time.time()

an=6
with open("aa.txt") as f:
    ta=f.read()
    ta=ta.rsplit()
    al=[r+"," for r in ta for i in range(an)]
print("al长度:",len(al))

bn=3
with open("bb.txt") as f:
    tb=f.read()
    tb=tb.rsplit()
    bl=[r+"," for r in tb for i in range(bn)]
print("bl长度:",len(bl))

cn=1
with open("cc.txt") as f:
    tc=f.read()
    tc=tc.rsplit()
    cl=[r+"\n" for r in tc for i in range(cn)]
print("cl长度:",len(cl))

end=time.time()
pt=end-start
print("运行耗时：",pt)

rn=len(cl)
tal=[al[r]+bl[r]+cl[r] for r in range(rn)]
#还是用列表解析好~
#for r in range(rn):
#   tal.append(al[r]+bl[r]+cl[r])
    
end=time.time()
pt=end-start
print("运行耗时：",pt)

with open("out.txt","w+") as f:
    f.writelines(tal)
    f.close()
    
end=time.time()
pt=end-start
print("运行耗时：",pt)
try:
    input("按回车退出")
except SyntaxError:
    pass
复制代码