本文大家整理了一些比较好用的关于python分割文件的方法,方法非常的简单实用。分享给大家供大家参考。具体如下:
例子1 指定分割文件大小
配置文件 config.ini:
#原文件存放目录
dir1=F:\work\python\3595\pyserver\test
#新文件存放目录
dir2=F:\work\python\3595\pyserver\test1
python 代码如下:
# -*- coding: utf-8 -*-
import os,sys,ConfigParser
class file_openate(object):
def __init__(self):
#初如化读取数据库配置
dir_config = ConfigParser.ConfigParser()
file_config=open('config.ini',"rb")
dir_config.readfp(file_config)
self.dir1=str(dir_config.get("global","dir1"))
self.dir1=unicode(self.dir1,'utf8')
self.dir2=str(dir_config.get("global","dir2"))
self.dir2=unicode(self.dir2,'utf8')
file_config.close()
#print self.dir2
#self.dir1="F:\\work\\python\\3595\\pyserver\\test"
def file_list(self):
input_name_han="软件有不确认性,前期使用最好先备份,以免发生数据丢失,确认备份后,请输入要分割的字节大小,按b来计算".decode('utf-8')
print input_name_han
while 1:
input_name=raw_input("number:")
if input_name.isdigit():
input_name=int(input_name)
os.chdir(self.dir1)
for filename in os.listdir(self.dir1):
os.chdir(self.dir1)
#print filename
name, ext = os.path.splitext(filename)
file_size=int(os.path.getsize(filename))
f=open(filename,'r')
chu_nmuber=0
while file_size >= 1:
#print file_size
chu_nmuber=chu_nmuber + 1
if file_size >= input_name:
file_size=file_size - input_name
a=f.read(input_name)
os.chdir(self.dir2)
filename1=name + '-' + str(chu_nmuber) + ext
new_f=open(filename1,'a')
new_f.write(a)
new_f.close()
#print file_size
else:
a=f.read()
os.chdir(self.dir2)
filename1=name + '-' + str(chu_nmuber) + ext
new_f=open(filename1,'a')
new_f.write(a)
new_f.close()
break
print "分割成功".decode('utf-8') + filename
f.close()
else:
print "请输入正确的数字,请重新输入".decode('utf-8')
file_name=file_openate()
file_name.file_list()
例子2,按行分割文件大小
#--*-- coding:utf-8 --*--
import os
class SplitFiles():
"""按行分割文件"""
def __init__(self, file_name, line_count=200):
"""初始化要分割的源文件名和分割后的文件行数"""
self.file_name = file_name
self.line_count = line_count
def split_file(self):
if self.file_name and os.path.exists(self.file_name):
try:
with open(self.file_name) as f : # 使用with读文件
temp_count = 0
temp_content = []
part_num = 1
for line in f:
if temp_count temp_count += 1
else :
self.write_file(part_num, temp_content)
part_num += 1
temp_count = 1
temp_content = []
temp_content.append(line)
else : # 正常结束循环后将剩余的内容写入新文件中
self.write_file(part_num, temp_content)
except IOError as err:
print(err)
else:
print("%s is not a validate file" % self.file_name)
def get_part_file_name(self, part_num):
""""获取分割后的文件名称:在源文件相同目录下建立临时文件夹temp_part_file,然后将分割后的文件放到该路径下"""
temp_path = os.path.dirname(self.file_name) # 获取文件的路径(不含文件名)
part_file_name = temp_path + "temp_part_file"
if not os.path.exists(temp_path) : # 如果临时目录不存在则创建
os.makedirs(temp_path)
part_file_name += os.sep + "temp_file_" + str(part_num) + ".part"
return part_file_name
def write_file(self, part_num, *line_content):
"""将按行分割后的内容写入相应的分割文件中"""
part_file_name = self.get_part_file_name(part_num)
print(line_content)
try :
with open(part_file_name, "w") as part_file:
part_file.writelines(line_content[0])
except IOError as err:
print(err)
if __name__ == "__main__":
sf = SplitFiles(r"F:\multiple_thread_read_file.txt")
sf.split_file()
上面只是进行了分割了,如果我们又要合并怎么办呢?下面这个例子可以实现分割与合并哦,大家一起看看。
例子3, 分割文件与合并函数
##########################################################################
# split a file into a set of parts; join.py puts them back together;
# this is a customizable version of the standard unix split command-line
# utility; because it is written in Python, it also works on Windows and
# can be easily modified; because it exports a function, its logic can
# also be imported and reused in other applications;
##########################################################################
import sys, os
kilobytes = 1024
megabytes = kilobytes * 1000
chunksize = int(1.4 * megabytes) # default: roughly a floppy
def split(fromfile, todir, chunksize=chunksize):
if not os.path.exists(todir): # caller handles errors
os.mkdir(todir) # make dir, read/write parts
else:
for fname in os.listdir(todir): # delete any existing files
os.remove(os.path.join(todir, fname))
partnum = 0
input = open(fromfile, 'rb') # use binary mode on Windows
while 1: # eof=empty string from read
chunk = input.read(chunksize) # get next part if not chunk: break
partnum = partnum+1
filename = os.path.join(todir, ('part%04d' % partnum))
fileobj = open(filename, 'wb')
fileobj.write(chunk)
fileobj.close() # or simply open().write()
input.close()
assert partnum return partnum
if __name__ == '__main__':
if len(sys.argv) == 2 and sys.argv[1] == '-help':
print 'Use: split.py [file-to-split target-dir [chunksize]]'
else:
if len(sys.argv) interactive = 1
fromfile = raw_input('File to be split? ') # input if clicked
todir = raw_input('Directory to store part files? ')
else:
interactive = 0
fromfile, todir = sys.argv[1:3] # args in cmdline
if len(sys.argv) == 4: chunksize = int(sys.argv[3])
absfrom, absto = map(os.path.abspath, [fromfile, todir])
print 'Splitting', absfrom, 'to', absto, 'by', chunksize
try:
parts = split(fromfile, todir, chunksize)
except:
print 'Error during split:'
print sys.exc_info()[0], sys.exc_info()[1]
else:
print 'Split finished:', parts, 'parts are in', absto
if interactive: raw_input('Press Enter key') # pause if clicked
join_file.py
##########################################################################
# join all part files in a dir created by split.py, to recreate file.
# This is roughly like a 'cat fromdir/* > tofile' command on unix, but is
# more portable and configurable, and exports the join operation as a
# reusable function. Relies on sort order of file names: must be same
# length. Could extend split/join to popup Tkinter file selectors.
##########################################################################
import os, sys
readsize = 1024
def join(fromdir, tofile):
output = open(tofile, 'wb')
parts = os.listdir(fromdir)
parts.sort()
for filename in parts:
filepath = os.path.join(fromdir, filename)
fileobj = open(filepath, 'rb')
while 1:
filebytes = fileobj.read(readsize)
if not filebytes: break
output.write(filebytes)
fileobj.close()
output.close()
if __name__ == '__main__':
if len(sys.argv) == 2 and sys.argv[1] == '-help':
print 'Use: join.py [from-dir-name to-file-name]'
else:
if len(sys.argv) != 3:
interactive = 1
fromdir = raw_input('Directory containing part files? ')
tofile = raw_input('Name of file to be recreated? ')
else:
interactive = 0
fromdir, tofile = sys.argv[1:]
absfrom, absto = map(os.path.abspath, [fromdir, tofile])
print 'Joining', absfrom, 'to make', absto
try:
join(fromdir, tofile)
except:
print 'Error joining files:'
print sys.exc_info()[0], sys.exc_info()[1]
else:
print 'Join complete: see', absto
if interactive: raw_input('Press Enter key') # pause if clicked
希望本文所述对大家的Python程序设计有所帮助。

Python and C each have their own advantages, and the choice should be based on project requirements. 1) Python is suitable for rapid development and data processing due to its concise syntax and dynamic typing. 2)C is suitable for high performance and system programming due to its static typing and manual memory management.

Choosing Python or C depends on project requirements: 1) If you need rapid development, data processing and prototype design, choose Python; 2) If you need high performance, low latency and close hardware control, choose C.

By investing 2 hours of Python learning every day, you can effectively improve your programming skills. 1. Learn new knowledge: read documents or watch tutorials. 2. Practice: Write code and complete exercises. 3. Review: Consolidate the content you have learned. 4. Project practice: Apply what you have learned in actual projects. Such a structured learning plan can help you systematically master Python and achieve career goals.

Methods to learn Python efficiently within two hours include: 1. Review the basic knowledge and ensure that you are familiar with Python installation and basic syntax; 2. Understand the core concepts of Python, such as variables, lists, functions, etc.; 3. Master basic and advanced usage by using examples; 4. Learn common errors and debugging techniques; 5. Apply performance optimization and best practices, such as using list comprehensions and following the PEP8 style guide.

Python is suitable for beginners and data science, and C is suitable for system programming and game development. 1. Python is simple and easy to use, suitable for data science and web development. 2.C provides high performance and control, suitable for game development and system programming. The choice should be based on project needs and personal interests.

Python is more suitable for data science and rapid development, while C is more suitable for high performance and system programming. 1. Python syntax is concise and easy to learn, suitable for data processing and scientific computing. 2.C has complex syntax but excellent performance and is often used in game development and system programming.

It is feasible to invest two hours a day to learn Python. 1. Learn new knowledge: Learn new concepts in one hour, such as lists and dictionaries. 2. Practice and exercises: Use one hour to perform programming exercises, such as writing small programs. Through reasonable planning and perseverance, you can master the core concepts of Python in a short time.

Python is easier to learn and use, while C is more powerful but complex. 1. Python syntax is concise and suitable for beginners. Dynamic typing and automatic memory management make it easy to use, but may cause runtime errors. 2.C provides low-level control and advanced features, suitable for high-performance applications, but has a high learning threshold and requires manual memory and type safety management.


Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

MantisBT
Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

Dreamweaver Mac version
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

PhpStorm Mac version
The latest (2018.2.1) professional PHP integrated development tool

WebStorm Mac version
Useful JavaScript development tools