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。

本篇文章给大家带来了关于Python的相关知识,其中主要介绍了关于Seaborn的相关问题,包括了数据可视化处理的散点图、折线图、条形图等等内容,下面一起来看一下,希望对大家有帮助。

本篇文章给大家带来了关于Python的相关知识,其中主要介绍了关于进程池与进程锁的相关问题,包括进程池的创建模块,进程池函数等等内容,下面一起来看一下,希望对大家有帮助。

本篇文章给大家带来了关于Python的相关知识,其中主要介绍了关于简历筛选的相关问题,包括了定义 ReadDoc 类用以读取 word 文件以及定义 search_word 函数用以筛选的相关内容,下面一起来看一下,希望对大家有帮助。

VS Code的确是一款非常热门、有强大用户基础的一款开发工具。本文给大家介绍一下10款高效、好用的插件,能够让原本单薄的VS Code如虎添翼,开发效率顿时提升到一个新的阶段。

pythn的中文意思是巨蟒、蟒蛇。1989年圣诞节期间,Guido van Rossum在家闲的没事干,为了跟朋友庆祝圣诞节,决定发明一种全新的脚本语言。他很喜欢一个肥皂剧叫Monty Python,所以便把这门语言叫做python。

本篇文章给大家带来了关于Python的相关知识,其中主要介绍了关于数据类型之字符串、数字的相关问题,下面一起来看一下,希望对大家有帮助。

本篇文章给大家带来了关于Python的相关知识,其中主要介绍了关于numpy模块的相关问题,Numpy是Numerical Python extensions的缩写,字面意思是Python数值计算扩展,下面一起来看一下,希望对大家有帮助。


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

AI Hentai Generator
Generate AI Hentai for free.

Hot Article

Hot Tools

DVWA
Damn Vulnerable Web App (DVWA) is a PHP/MySQL web application that is very vulnerable. Its main goals are to be an aid for security professionals to test their skills and tools in a legal environment, to help web developers better understand the process of securing web applications, and to help teachers/students teach/learn in a classroom environment Web application security. The goal of DVWA is to practice some of the most common web vulnerabilities through a simple and straightforward interface, with varying degrees of difficulty. Please note that this software

Atom editor mac version download
The most popular open source editor

Dreamweaver Mac version
Visual web development tools

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

SecLists
SecLists is the ultimate security tester's companion. It is a collection of various types of lists that are frequently used during security assessments, all in one place. SecLists helps make security testing more efficient and productive by conveniently providing all the lists a security tester might need. List types include usernames, passwords, URLs, fuzzing payloads, sensitive data patterns, web shells, and more. The tester can simply pull this repository onto a new test machine and he will have access to every type of list he needs.
