以前提取这些文件用的是一同事些的批处理文件;用起来不怎么顺手,刚好最近在学些python,所有就自己动手写了一个python提取文件的小程序;
1、原理
提取文件的原理很简单,就是到一个指定的目录,找出最后修改时间大于给定时间的文件,然后将他们复制到目标目录,目标目录的结构必须和原始目录一致,这样工程人员拿到后就可以直接覆盖整个目录;
2、实现
为了程序的通用,我定义了下面的配置文件
config.xml
代码如下:
其中
下面是读取配置文件的类:
config.py
代码如下:
'''
Created on Mar 3, 2009
@author: alex cheng
'''
from xml.dom.minidom import parse, parseString
import datetime
import time
class config(object):
'''
config.xml
'''
def __init__(self, configfile):
'''
configfile:config files
'''
dom = parse(configfile)
self.config_element = dom.getElementsByTagName("config")[0]
def getSrcDir(self):
'''
return the
'''
srcDir = self.config_element.getElementsByTagName("srcdir")[0]
return self.getText(srcDir.childNodes)
def getDestDir(self):
'''
return the
'''
destDir = self.config_element.getElementsByTagName("destdir")[0]
return self.getText(destDir.childNodes)
def getNotIncludeDirs(self):
'''
return a list, it's the
'''
notinclude_dirs = self.config_element.getElementsByTagName("dir")
dirList = []
for node in notinclude_dirs:
dir = self.getText(node.childNodes)
if dir != '':
dirList.append(dir)
return dirList
def getNotIncludeFiles(self):
'''
return a list, it's the
'''
notinclude_files = self.config_element.getElementsByTagName("file")
fileList = []
for node in notinclude_files:
file = self.getText(node.childNodes)
if file != '':
fileList.append(file)
return fileList
def getText(self, nodeList):
'''
return the text value of the nodeList node
'''
rc = ''
for node in nodeList:
if node.nodeType == node.TEXT_NODE:
rc = rc + node.data
return rc
def getInitTime(self):
'''
return a datetime object,it's the
'''
initTime = self.config_element.getElementsByTagName("inittime")[0]
timeStr = self.getText(initTime.childNodes)
dt = datetime.datetime.strptime(timeStr, "%Y-%m-%d %H:%M:%S")
fdt = time.mktime(dt.utctimetuple())
return fdt
def getWinRarDir(self):
'''
return the value of
'''
rardir = self.config_element.getElementsByTagName('rardir')[0]
return self.getText(rardir.childNodes)
if __name__ == '__main__':
c = config('config.xml')
home = c.getSrcDir()
print('home is ', home)
dest = c.getDestDir()
print('dest is ', dest)
dirlist = c.getNotIncludeDirs()
print('not include directory is:')
for n in dirlist:
print(n)
filelist = c.getNotIncludeFiles()
print('not include files is:')
for n in filelist:
print(n)
inittime = c.getInitTime()
print('inittime is', inittime)
rardir = c.getWinRarDir()
print(rardir)
下面是程序的主体:
fetchfile.py
代码如下:
'''
Created on Mar 3, 2009
@author: alex cheng
'''
from config import config
from os import chdir, listdir, makedirs, system, walk, remove, rmdir, unlink, \
removedirs, stat, getcwd
from os.path import abspath, isfile, isdir, join as join_path, exists
from shutil import copy2
from sys import path
import datetime
import re
import time
def getdestdir(dir):
'''
return the dest directory name;
it's named by date,for example 20090101; if 20090101 has exist the return 20090101(1),if 20090101(1) has exist also,
then return 20090101(2), and then...
'''
today = datetime.datetime.today()
strtoday = today.strftime('%Y%m%d')
dr = join_path(dir, strtoday)
tmp = dr
index = 0
while isdir(tmp):
tmp = dr
index = index + 1
tmp = tmp + '(' + '%d' % index + ')'
return tmp
def fetchFiles(srcdir, destdir, ignoredirs, ignorefiles, lasttime=time.mktime(datetime.datetime(2000, 1, 1).utctimetuple())):
'''
fetch files from srcdir(source directory) to destdir(dest directory) ignore the notcopydires(the ignore directory list)
and notcopyfiles(the ignore file list), and the file and directory's modify time after the lasttime
'''
chdir(srcdir) # change the current directory to the srcdir
dirs = listdir('.') # get all files and directorys in srcdir, but ignore the "." and ".."
dirlist = [] # save all directorys in srcdir
for n in dirs:
if isdir(n):
dirlist.append(n)
for subdir in dirlist:
exist = False
for ignoredir in ignoredirs:
if join_path(srcdir, subdir) == ignoredir:
exist = True
break
if exist:
continue
fetchFiles(join_path(srcdir, subdir), join_path(destdir, subdir), ignoredirs, ignorefiles, lasttime)
copyfiles(srcdir, destdir, ignorefiles, lasttime)
def copyfiles(srcdir, destdir, ignorefiles, lasttime):
'''
copy the files from srcdir(source directory) to destdir(dest directory, if dest directory not exist then create is)
ignore the notcopyfiles(the ignore file list) and the file's modify time must after lasttime
'''
chdir(srcdir)
files = filter(isfile, listdir('.'))
for file in files:
if isdir(file): # ignore the directory
continue
lastmodify = stat(file).st_mtime
if lastmodify continue
exist = False
for ignorefile in ignorefiles:
if join_path(srcdir, file) == ignorefile:
exist = True
if not exist:
if isdir(destdir) is False:
try:
makedirs(destdir)
print('success create directory:', destdir)
except:
raise Exception('failed create directory: ' + destdir)
try:
copy2(file, join_path(destdir, file))
print('success copy file from', join_path(srcdir, file), 'to', join_path(destdir, file))
except:
raise Exception('failed copy file from ' + join_path(srcdir, file) + ' to ' + join_path(destdir, file))
def tarfiles(dir, todir, winrardir, tarfilename):
'''
tar all files in dir(a directory) to todir(dest directory) and the tar file named tarfilename
'''
if isdir(dir) is False:
print('the directory', dir, 'not exist')
return
chdir(dir)
commond = '\"' + winrardir + '\\rar.exe\" a -r ' + todir + '\\' + tarfilename + ' *.*'
print(commond)
if system(commond) == 0:
print('success tar files')
else:
print('failed tar files')
def removeDir(dir_file, currentdir):
'''
delete the dir_file
'''
if isdir(currentdir) is False:
print()
return
chdir(currentdir)
if not exists(dir_file):
return
if isdir(dir_file):
for root, dirs, files in walk(dir_file, topdown=False):
for name in files:
remove(join_path(root, name))
for name in dirs:
rmdir(join_path(root, name))
rmdir(dir_file) # remove the main dir
else:
unlink(dir_file)
return
def getlasttime():
'''
get last modify time from txt files
'''
try:
mypath = abspath(path[0]) #get current path
file = join_path(mypath, 'C_UPGRADETIME.txt')
if isfile(file) is False:
return 0
f = open(join_path(mypath, 'C_UPGRADETIME.txt'), 'r')
lines = f.readlines()
if len(lines) == 0:
return 0
line = lines[ - 1]
dt = datetime.datetime.strptime(line, "%Y-%m-%d %H:%M:%S")
lasttime = time.mktime(dt.utctimetuple())
f.close()
return lasttime
except:
print('failed to get last modify time from txt file')
return 0
def registtime():
nowstr = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
nowfloat = time.time()
mypath = abspath(path[0]) # get current path
f = open(join_path(mypath, 'C_UPGRADETIME.txt'), 'a')
f.write('\n' + nowstr)
f.close()
def main():
c = config('config.xml')
home = c.getSrcDir()
dest = c.getDestDir()
ignoreDirs = c.getNotIncludeDirs()
ignoreFiles = c.getNotIncludeFiles()
winRarDir = c.getWinRarDir()
dest = getdestdir(dest)# get current dest directory
print ('copy all files to the temp directory ignore last fetch time')
fetchFiles(home, join_path(dest, 'temp'), ignoreDirs, ignoreFiles)
print('tar the all files')
tarfiles(join_path(dest, 'temp'), dest, winRarDir, 'CargillUpdate_ALL.rar')
print('program sleep 20 seconds to finish the tar thread')
time.sleep(20)
print('remove the temp directory...')
removeDir(join_path(dest, 'temp'), dest)
print('success remove the temp directory')
lasttime = getlasttime() # get last modify time from txt files
if lasttime == 0:
lasttime = c.getInitTime()
print ('copy all files to the temp2 directory last modify time after last fetch time')
fetchFiles(home, join_path(dest, 'temp2'), ignoreDirs, ignoreFiles, lasttime)
print('tar the all files')
tarfiles(join_path(dest, 'temp2'), dest, winRarDir, 'CargillUpdate.rar')
print('program sleep 20 seconds to finish the tar thread')
time.sleep(20)
print('remove the temp2 directory...')
removeDir(join_path(dest, 'temp2'), dest)
print('success remove the temp2 directory')
registtime() # regist current time
if __name__ == '__main__':
main()

Python和C 各有优势,选择应基于项目需求。1)Python适合快速开发和数据处理,因其简洁语法和动态类型。2)C 适用于高性能和系统编程,因其静态类型和手动内存管理。

选择Python还是C 取决于项目需求:1)如果需要快速开发、数据处理和原型设计,选择Python;2)如果需要高性能、低延迟和接近硬件的控制,选择C 。

通过每天投入2小时的Python学习,可以有效提升编程技能。1.学习新知识:阅读文档或观看教程。2.实践:编写代码和完成练习。3.复习:巩固所学内容。4.项目实践:应用所学于实际项目中。这样的结构化学习计划能帮助你系统掌握Python并实现职业目标。

在两小时内高效学习Python的方法包括:1.回顾基础知识,确保熟悉Python的安装和基本语法;2.理解Python的核心概念,如变量、列表、函数等;3.通过使用示例掌握基本和高级用法;4.学习常见错误与调试技巧;5.应用性能优化与最佳实践,如使用列表推导式和遵循PEP8风格指南。

Python适合初学者和数据科学,C 适用于系统编程和游戏开发。1.Python简洁易用,适用于数据科学和Web开发。2.C 提供高性能和控制力,适用于游戏开发和系统编程。选择应基于项目需求和个人兴趣。

Python更适合数据科学和快速开发,C 更适合高性能和系统编程。1.Python语法简洁,易于学习,适用于数据处理和科学计算。2.C 语法复杂,但性能优越,常用于游戏开发和系统编程。

每天投入两小时学习Python是可行的。1.学习新知识:用一小时学习新概念,如列表和字典。2.实践和练习:用一小时进行编程练习,如编写小程序。通过合理规划和坚持不懈,你可以在短时间内掌握Python的核心概念。

Python更易学且易用,C 则更强大但复杂。1.Python语法简洁,适合初学者,动态类型和自动内存管理使其易用,但可能导致运行时错误。2.C 提供低级控制和高级特性,适合高性能应用,但学习门槛高,需手动管理内存和类型安全。


热AI工具

Undresser.AI Undress
人工智能驱动的应用程序,用于创建逼真的裸体照片

AI Clothes Remover
用于从照片中去除衣服的在线人工智能工具。

Undress AI Tool
免费脱衣服图片

Clothoff.io
AI脱衣机

Video Face Swap
使用我们完全免费的人工智能换脸工具轻松在任何视频中换脸!

热门文章

热工具

ZendStudio 13.5.1 Mac
功能强大的PHP集成开发环境

适用于 Eclipse 的 SAP NetWeaver 服务器适配器
将Eclipse与SAP NetWeaver应用服务器集成。

DVWA
Damn Vulnerable Web App (DVWA) 是一个PHP/MySQL的Web应用程序,非常容易受到攻击。它的主要目标是成为安全专业人员在合法环境中测试自己的技能和工具的辅助工具,帮助Web开发人员更好地理解保护Web应用程序的过程,并帮助教师/学生在课堂环境中教授/学习Web应用程序安全。DVWA的目标是通过简单直接的界面练习一些最常见的Web漏洞,难度各不相同。请注意,该软件中

VSCode Windows 64位 下载
微软推出的免费、功能强大的一款IDE编辑器

SublimeText3 Mac版
神级代码编辑软件(SublimeText3)