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()

ForhandlinglargedatasetsinPython,useNumPyarraysforbetterperformance.1)NumPyarraysarememory-efficientandfasterfornumericaloperations.2)Avoidunnecessarytypeconversions.3)Leveragevectorizationforreducedtimecomplexity.4)Managememoryusagewithefficientdata

Inpython,ListSusedynamicMemoryAllocationWithOver-Asalose,而alenumpyArraySallaySallocateFixedMemory.1)listssallocatemoremoremoremorythanneededinentientary上,respizeTized.2)numpyarsallaysallaysallocateAllocateAllocateAlcocateExactMemoryForements,OfferingPrediCtableSageButlessemageButlesseflextlessibility。

Inpython,YouCansspecthedatatAtatatPeyFelemereModeRernSpant.1)Usenpynernrump.1)Usenpynyp.dloatp.dloatp.ploatm64,formor professisconsiscontrolatatypes。

NumPyisessentialfornumericalcomputinginPythonduetoitsspeed,memoryefficiency,andcomprehensivemathematicalfunctions.1)It'sfastbecauseitperformsoperationsinC.2)NumPyarraysaremorememory-efficientthanPythonlists.3)Itoffersawiderangeofmathematicaloperation

Contiguousmemoryallocationiscrucialforarraysbecauseitallowsforefficientandfastelementaccess.1)Itenablesconstanttimeaccess,O(1),duetodirectaddresscalculation.2)Itimprovescacheefficiencybyallowingmultipleelementfetchespercacheline.3)Itsimplifiesmemorym

SlicingaPythonlistisdoneusingthesyntaxlist[start:stop:step].Here'showitworks:1)Startistheindexofthefirstelementtoinclude.2)Stopistheindexofthefirstelementtoexclude.3)Stepistheincrementbetweenelements.It'susefulforextractingportionsoflistsandcanuseneg

numpyallowsforvariousoperationsonArrays:1)basicarithmeticlikeaddition,減法,乘法和division; 2)evationAperationssuchasmatrixmultiplication; 3)element-wiseOperations wiseOperationswithOutexpliitloops; 4)

Arresinpython,尤其是Throughnumpyandpandas,weessentialFordataAnalysis,offeringSpeedAndeffied.1)NumpyArseNable efflaysenable efficefliceHandlingAtaSetSetSetSetSetSetSetSetSetSetSetsetSetSetSetSetsopplexoperationslikemovingaverages.2)


熱AI工具

Undresser.AI Undress
人工智慧驅動的應用程序,用於創建逼真的裸體照片

AI Clothes Remover
用於從照片中去除衣服的線上人工智慧工具。

Undress AI Tool
免費脫衣圖片

Clothoff.io
AI脫衣器

Video Face Swap
使用我們完全免費的人工智慧換臉工具,輕鬆在任何影片中換臉!

熱門文章

熱工具

SublimeText3漢化版
中文版,非常好用

MantisBT
Mantis是一個易於部署的基於Web的缺陷追蹤工具,用於幫助產品缺陷追蹤。它需要PHP、MySQL和一個Web伺服器。請查看我們的演示和託管服務。

MinGW - Minimalist GNU for Windows
這個專案正在遷移到osdn.net/projects/mingw的過程中,你可以繼續在那裡關注我們。 MinGW:GNU編譯器集合(GCC)的本機Windows移植版本,可自由分發的導入函式庫和用於建置本機Windows應用程式的頭檔;包括對MSVC執行時間的擴展,以支援C99功能。 MinGW的所有軟體都可以在64位元Windows平台上運作。

mPDF
mPDF是一個PHP庫,可以從UTF-8編碼的HTML產生PDF檔案。原作者Ian Back編寫mPDF以從他的網站上「即時」輸出PDF文件,並處理不同的語言。與原始腳本如HTML2FPDF相比,它的速度較慢,並且在使用Unicode字體時產生的檔案較大,但支援CSS樣式等,並進行了大量增強。支援幾乎所有語言,包括RTL(阿拉伯語和希伯來語)和CJK(中日韓)。支援嵌套的區塊級元素(如P、DIV),

Atom編輯器mac版下載
最受歡迎的的開源編輯器