python基础——fileinput模块_python fileinput-优快云博客

本文深入探讨了Python中fileinput模块的功能与应用，包括对单个或多个文件的迭代读取，以及如何进行文件内容的查找、替换和格式化输出。通过实际案例，展示了fileinput在处理大文件、批量文件操作、正则表达式匹配和替换等方面的强大能力。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

转载：Python中fileinput模块介绍

fileinput模块可以对一个或多个文件中的内容进行迭代、遍历等操作。

该模块的input()函数有点类似文件readlines()方法，区别在于:

前者是一个迭代对象，即每次只生成一行，需要用for循环迭代。

后者是一次性读取所有行。在碰到大文件的读取时，前者无疑效率更高效。

用fileinput对文件进行循环遍历，格式化输出，查找、替换等操作，非常方便。

【典型用法】

import fileinput
for line in fileinput.input():
    process(line)

【基本格式】

fileinput.input([files[, inplace[, backup[, bufsize[, mode[, openhook]]]]]])

【默认格式】

fileinput.input (files=None, inplace=False, backup='', bufsize=0, mode='r', openhook=None)


 
   
    
   
   
    
     files:                  
     #文件的路径列表，默认是stdin方式，多文件['1.txt','2.txt',...]
    
   

   
    
   
   
    
     inplace:                
     #是否将标准输出的结果写回文件，默认不取代
    
   

   
    
   
   
    
     backup:                 
     #备份文件的扩展名，只指定扩展名，如.bak。如果该文件的备份文件已存在，则会自动覆盖。
    
   

   
    
   
   
    
     bufsize:                
     #缓冲区大小，默认为0，如果文件很大，可以修改此参数，一般默认即可
    
   

   
    
   
   
    
     mode:                   
     #读写模式，默认为只读
    
   

   
    
   
   
    
     openhook:               
     #该钩子用于控制打开的所有文件，比如说编码方式等;

【常用函数】


 
   
    
   
   
    
     fileinput.input()       
     #返回能够用于for循环遍历的对象
    
   

   
    
   
   
    
     fileinput.filename()    
     #返回当前文件的名称
    
   

   
    
   
   
    
     fileinput.lineno()      
     #返回当前已经读取的行的数量（或者序号）
    
   

   
    
   
   
    
     fileinput.filelineno()  
     #返回当前读取的行的行号
    
   

   
    
   
   
    
     fileinput.isfirstline() 
     #检查当前行是否是文件的第一行
    
   

   
    
   
   
    
     fileinput.isstdin()     
     #判断最后一行是否从stdin中读取
    
   

   
    
   
   
    
     fileinput.close()       
     #关闭队列

【常见例子】

例子01: 利用fileinput读取一个文件所有行


 
   
    
   
   
    
     >>> 
     import fileinput
    
   

   
    
   
   
    
     >>> 
     for line 
     in fileinput.input(
     'data.txt'):
    
   

   
    
   
   
            
     print line,
    
   

   
    
   
   
    
     #输出结果
    
   

   
    
   
   
    
     Python
    
   

   
    
   
   
    
     Java 
    
   

   
    
   
   
    
     C/C++
    
   

   
    
   
   
    
     Shell

命令行方式:


 
   
    
   
   
    
     #test.py
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input():
    
   

   
    
   
   
        
     print fileinput.filename(),
     '|',
     'Line Number:',fileinput.lineno(),
     '|: ',line
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     c:>python test.py data.txt
    
   

   
    
   
   
    
     data.txt | Line Number: 
     1 |:  Python
    
   

   
    
   
   
    
     data.txt | Line Number: 
     2 |:  Java
    
   

   
    
   
   
    
     data.txt | Line Number: 
     3 |:  C/C++
    
   

   
    
   
   
    
     data.txt | Line Number: 
     4 |:  Shell

例子02: 利用fileinput对多文件操作，并原地修改内容


 
   
    
   
   
    
     #test.py
    
   

   
    
   
   
    
     #---样本文件---
    
   

   
    
   
   
    
     c:\Python27>type 
     1.txt
    
   

   
    
   
   
    
     first
    
   

   
    
   
   
    
     second
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     c:\Python27>type 
     2.txt
    
   

   
    
   
   
    
     third
    
   

   
    
   
   
    
     fourth
    
   

   
    
   
   
    
     #---样本文件---
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     def process(line):
    
   

   
    
   
   
        
     return line.rstrip() + 
     ' line'
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input([
     '1.txt',
     '2.txt'],inplace=
     1):
    
   

   
    
   
   
        
     print process(line)
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---结果输出---
    
   

   
    
   
   
    
     c:\Python27>type 
     1.txt
    
   

   
    
   
   
    
     first line
    
   

   
    
   
   
    
     second line
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     c:\Python27>type 
     2.txt
    
   

   
    
   
   
    
     third line
    
   

   
    
   
   
    
     fourth line
    
   

   
    
   
   
    
     #---结果输出---

命令行方式:


 
   
    
   
   
    
     #test.py
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     def process(line):
    
   

   
    
   
   
    
         return line.rstrip() + ' line'
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line in fileinput.input(inplace = True):
    
   

   
    
   
   
    
         print process(line)
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #执行命令
    
   

   
    
   
   
    
     c:\Python27>python test.py 1.txt 2.txt

例子03: 利用fileinput实现文件内容替换，并将原文件作备份


 
   
    
   
   
    
     #样本文件:
    
   

   
    
   
   
    
     #data.txt
    
   

   
    
   
   
    
     Python
    
   

   
    
   
   
    
     Java
    
   

   
    
   
   
    
     C/C++
    
   

   
    
   
   
    
     Shell
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #FileName: test.py
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(
     'data.txt',backup=
     '.bak',inplace=
     1):
    
   

   
    
   
   
        
     print line.rstrip().replace(
     'Python',
     'Perl')  
     #或者print line.replace('Python','Perl'),
    
   

   
    
   
   
        
    
   

   
    
   
   
    
     #最后结果:
    
   

   
    
   
   
    
     #data.txt
    
   

   
    
   
   
    
     Python
    
   

   
    
   
   
    
     Java
    
   

   
    
   
   
    
     C/C++
    
   

   
    
   
   
    
     Shell
    
   

   
    
   
   
    
     #并生成:
    
   

   
    
   
   
    
     #data.txt.bak文件


 
   
    
   
   
    
     #其效果等同于下面的方式
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
    
     for line 
     in fileinput.input():
    
   

   
    
   
   
        
     print 
     'Tag:',line,
    
   

   
    
   
   
     
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试结果:   
    
   

   
    
   
   
    
     d:\>python Learn.py < data.txt > data_out.txt

例子04: 利用fileinput将CRLF文件转为LF


 
   
    
   
   
    
     import fileinput
    
   

   
    
   
   
    
     import sys
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(inplace=
     True):
    
   

   
    
   
   
        
     #将Windows/DOS格式下的文本文件转为Linux的文件
    
   

   
    
   
   
        
     if line[
     -2:] == 
     "\r\n":  
    
   

   
    
   
   
    
             line = line + 
     "\n"
    
   

   
    
   
   
    
         sys.stdout.write(line)

例子05: 利用fileinput对文件简单处理


 
   
    
   
   
    
     #FileName: test.py
    
   

   
    
   
   
    
     import sys
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(
     r'C:\Python27\info.txt'):
    
   

   
    
   
   
    
         sys.stdout.write(
     '=> ')
    
   

   
    
   
   
    
         sys.stdout.write(line)
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #输出结果   
    
   

   
    
   
   
    
     >>> 
    
   

   
    
   
   
    
     => The Zen of Python, by Tim Peters
    
   

   
    
   
   
    
     => 
    
   

   
    
   
   
    
     => Beautiful 
     is better than ugly.
    
   

   
    
   
   
    
     => Explicit 
     is better than implicit.
    
   

   
    
   
   
    
     => Simple 
     is better than complex.
    
   

   
    
   
   
    
     => Complex 
     is better than complicated.
    
   

   
    
   
   
    
     => Flat 
     is better than nested.
    
   

   
    
   
   
    
     => Sparse 
     is better than dense.
    
   

   
    
   
   
    
     => Readability counts.
    
   

   
    
   
   
    
     => Special cases aren
     't special enough to break the rules.
    
   

   
    
   
   
    
     => Although practicality beats purity.
    
   

   
    
   
   
    
     => Errors should never pass silently.
    
   

   
    
   
   
    
     => Unless explicitly silenced.
    
   

   
    
   
   
    
     => In the face of ambiguity, refuse the temptation to guess.
    
   

   
    
   
   
    
     => There should be one-- and preferably only one --obvious way to do it.
    
   

   
    
   
   
    
     => Although that way may not be obvious at first unless you're Dutch.
    
   

   
    
   
   
    
     => Now 
     is better than never.
    
   

   
    
   
   
    
     => Although never 
     is often better than *right* now.
    
   

   
    
   
   
    
     => If the implementation 
     is hard to explain, it
     's a bad idea.
    
   

   
    
   
   
    
     => If the implementation is easy to explain, it may be a good idea.
    
   

   
    
   
   
    
     => Namespaces are one honking great idea -- let's do more of those!

例子06: 利用fileinput批处理文件


 
   
    
   
   
    
     #---测试文件: test.txt test1.txt test2.txt test3.txt---
    
   

   
    
   
   
    
     #---脚本文件: test.py---
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
    
     import glob
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(glob.glob(
     "test*.txt")):
    
   

   
    
   
   
        
     if fileinput.isfirstline():
    
   

   
    
   
   
            
     print 
     '-'*
     20, 
     'Reading %s...' % fileinput.filename(), 
     '-'*
     20
    
   

   
    
   
   
        
     print str(fileinput.lineno()) + 
     ': ' + line.upper(),
    
   

   
    
   
   
        
    
   

   
    
   
   
        
    
   

   
    
   
   
    
     #---输出结果:
    
   

   
    
   
   
    
     >>> 
    
   

   
    
   
   
    
     -------------------- Reading test.txt... --------------------
    
   

   
    
   
   
    
     1: AAAAA
    
   

   
    
   
   
    
     2: BBBBB
    
   

   
    
   
   
    
     3: CCCCC
    
   

   
    
   
   
    
     4: DDDDD
    
   

   
    
   
   
    
     5: FFFFF
    
   

   
    
   
   
    
     -------------------- Reading test1.txt... --------------------
    
   

   
    
   
   
    
     6: FIRST LINE
    
   

   
    
   
   
    
     7: SECOND LINE
    
   

   
    
   
   
    
     -------------------- Reading test2.txt... --------------------
    
   

   
    
   
   
    
     8: THIRD LINE
    
   

   
    
   
   
    
     9: FOURTH LINE
    
   

   
    
   
   
    
     -------------------- Reading test3.txt... --------------------
    
   

   
    
   
   
    
     10: THIS IS LINE 
     1
    
   

   
    
   
   
    
     11: THIS IS LINE 
     2
    
   

   
    
   
   
    
     12: THIS IS LINE 
     3
    
   

   
    
   
   
    
     13: THIS IS LINE 
     4

例子07: 利用fileinput及re做日志分析: 提取所有含日期的行


 
   
    
   
   
    
     #--样本文件--
    
   

   
    
   
   
    
     aaa
    
   

   
    
   
   
    
     1970
     -01
     -01 
     13:
     45:
     30  Error: **** Due to System Disk spacke 
     not enough...
    
   

   
    
   
   
    
     bbb
    
   

   
    
   
   
    
     1970
     -01
     -02 
     10:
     20:
     30  Error: **** Due to System Out of Memory...
    
   

   
    
   
   
    
     ccc
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试脚本---
    
   

   
    
   
   
    
     import re
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
    
     import sys
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     pattern = 
     '\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}'
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(
     'error.log',backup=
     '.bak',inplace=
     1):
    
   

   
    
   
   
        
     if re.search(pattern,line):
    
   

   
    
   
   
    
             sys.stdout.write(
     "=> ")
    
   

   
    
   
   
    
             sys.stdout.write(line)
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试结果---
    
   

   
    
   
   
    
     => 
     1970
     -01
     -01 
     13:
     45:
     30  Error: **** Due to System Disk spacke 
     not enough...
    
   

   
    
   
   
    
     => 
     1970
     -01
     -02 
     10:
     20:
     30  Error: **** Due to System Out of Memory...

例子08: 利用fileinput及re做分析: 提取符合条件的电话号码


 
   
    
   
   
    
     #---样本文件: phone.txt---
    
   

   
    
   
   
    
     010
     -110
     -12345
    
   

   
    
   
   
    
     800
     -333
     -1234
    
   

   
    
   
   
    
     010
     -99999999
    
   

   
    
   
   
    
     05718888888
    
   

   
    
   
   
    
     021
     -88888888
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试脚本: test.py---
    
   

   
    
   
   
    
     import re
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     pattern = 
     '[010|021]-\d{8}'  
     #提取区号为010或021电话号码，格式:010-12345678
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(
     'phone.txt'):
    
   

   
    
   
   
        
     if re.search(pattern,line):
    
   

   
    
   
   
            
     print 
     '=' * 
     50
    
   

   
    
   
   
            
     print 
     'Filename:'+ fileinput.filename()+
     ' | Line Number:'+str(fileinput.lineno())+
     ' | '+line,
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---输出结果:---
    
   

   
    
   
   
    
     >>> 
    
   

   
    
   
   
    
     ==================================================
    
   

   
    
   
   
    
     Filename:phone.txt | Line Number:
     3 | 
     010
     -99999999
    
   

   
    
   
   
    
     ==================================================
    
   

   
    
   
   
    
     Filename:phone.txt | Line Number:
     5 | 
     021
     -88888888
    
   

   
    
   
   
    
     >>>

例子09: 利用fileinput实现类似于grep的功能


 
   
    
   
   
    
     import sys
    
   

   
    
   
   
    
     import re
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     pattern= re.compile(sys.argv[
     1])
    
   

   
    
   
   
    
     for line 
     in fileinput.input(sys.argv[
     2]):
    
   

   
    
   
   
        
     if pattern.match(line):
    
   

   
    
   
   
            
     print fileinput.filename(), fileinput.filelineno(), line
    
   

   
    
   
   
    
     $ ./test.py 
     import.*re *.py
    
   

   
    
   
   
    
     #查找所有py文件中，含import re字样的
    
   

   
    
   
   
    
     addressBook.py  
     2   
     import re
    
   

   
    
   
   
    
     addressBook1.py 
     10  
     import re
    
   

   
    
   
   
    
     addressBook2.py 
     18  
     import re
    
   

   
    
   
   
    
     test.py         
     238 
     import re

例子10: 利用fileinput做正则替换


 
   
    
   
   
    
     #---测试样本: input.txt
    
   

   
    
   
   
    
     * [Learning Python](
     #author:Mark Lutz)
    
   

   
    
   
   
        
    
   

   
    
   
   
    
     #---测试脚本: test.py
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
    
     import re
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input():
    
   

   
    
   
   
    
         line = re.sub(
     r'\* \[(.*)\]\(#(.*)\)', 
     r'<h2 id="\2">\1</h2>', line.rstrip())
    
   

   
    
   
   
    
         print(line)
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---输出结果:
    
   

   
    
   
   
    
     c:\Python27>python test.py input.txt
    
   

   
    
   
   
    
     <h2 id=
     "author:Mark Lutz">Learning Python</h2>

例子11: 利用fileinput做正则替换，不同字模块之间的替换


 
   
    
   
   
    
     #---测试样本:test.txt
    
   

   
    
   
   
    
     [@!$First]&[*%-Second]&[Third]
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试脚本:test.py
    
   

   
    
   
   
    
     import re
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     regex = re.compile(
     r'^([^&]*)(&)([^&]*)(&)([^&]*)')
    
   

   
    
   
   
    
     #整行以&分割，要实现[@!$First]与[*%-Second]互换
    
   

   
    
   
   
    
     for line 
     in fileinput.input(
     'test.txt',inplace=
     1,backup=
     '.bak'):
    
   

   
    
   
   
        
     print regex.sub(
     r'\3\2\1\4\5',line),
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---输出结果:
    
   

   
    
   
   
    
     [*%-Second]&[@!$First]&[Third]

例子12: 利用fileinput根据argv命令行输入做替换


 
   
    
   
   
    
     #---样本数据: host.txt
    
   

   
    
   
   
    
     # localhost is used to configure the loopback interface
    
   

   
    
   
   
    
     # when the system is booting.  Do not change this entry.
    
   

   
    
   
   
    
     127.0
     .0
     .1      localhost
    
   

   
    
   
   
    
     192.168
     .100
     .2  www.test2.com
    
   

   
    
   
   
    
     192.168
     .100
     .3  www.test3.com
    
   

   
    
   
   
    
     192.168
     .100
     .4  www.test4.com
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     #---测试脚本: test.py
    
   

   
    
   
   
    
     import sys
    
   

   
    
   
   
    
     import fileinput
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     source = sys.argv[
     1]
    
   

   
    
   
   
    
     target = sys.argv[
     2]
    
   

   
    
   
   
    
     files  = sys.argv[
     3:]
    
   

   
    
   
   
     
    
   

   
    
   
   
    
     for line 
     in fileinput.input(files,backup=
     '.bak',openhook=fileinput.hook_encoded(
     "gb2312")):
    
   

   
    
   
   
        
     #对打开的文件执行中文字符集编码
    
   

   
    
   
   
    
         line = line.rstrip().replace(source,target)
    
   

   
    
   
   
        
     print line
    
   

   
    
   
   
        
    
   

   
    
   
   
    
     #---输出结果:    
    
   

   
    
   
   
    
     c:\>python test.py 
     192.168
     .100 
     127.0
     .0 host.txt
    
   

   
    
   
   
    
     #将host文件中，所有192.168.100转换为:127.0.0
    
   

   
    
   
   
    
     127.0
     .0
     .1  localhost
    
   

   
    
   
   
    
     127.0
     .0
     .2  www.test2.com
    
   

   
    
   
   
    
     127.0
     .0
     .3  www.test3.com
    
   

   
    
   
   
    
     127.0
     .0
     .4  www.test4.com