python 提取文件的小程序
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()

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

AI Hentai Generator
免费生成ai无尽的。

热门文章

热工具

记事本++7.3.1
好用且免费的代码编辑器

SublimeText3汉化版
中文版,非常好用

禅工作室 13.0.1
功能强大的PHP集成开发环境

Dreamweaver CS6
视觉化网页开发工具

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

手机XML转PDF的速度取决于以下因素:XML结构的复杂性手机硬件配置转换方法(库、算法)代码质量优化手段(选择高效库、优化算法、缓存数据、利用多线程)总体而言,没有绝对的答案,需要根据具体情况进行优化。

不可能直接在手机上用单一应用完成 XML 到 PDF 的转换。需要使用云端服务,通过两步走的方式实现:1. 在云端转换 XML 为 PDF,2. 在手机端访问或下载转换后的 PDF 文件。

C语言中没有内置求和函数,需自行编写。可通过遍历数组并累加元素实现求和:循环版本:使用for循环和数组长度计算求和。指针版本:使用指针指向数组元素,通过自增指针遍历高效求和。动态分配数组版本:动态分配数组并自行管理内存,确保释放已分配内存以防止内存泄漏。

无法找到一款将 XML 直接转换为 PDF 的应用程序,因为它们是两种根本不同的格式。XML 用于存储数据,而 PDF 用于显示文档。要完成转换,可以使用编程语言和库,例如 Python 和 ReportLab,来解析 XML 数据并生成 PDF 文档。

可以将 XML 转换为图像,方法是使用 XSLT 转换器或图像库。XSLT 转换器:使用 XSLT 处理器和样式表,将 XML 转换为图像。图像库:使用 PIL 或 ImageMagick 等库,从 XML 数据创建图像,例如绘制形状和文本。

XML格式化工具可以将代码按照规则排版,提高可读性和理解性。选择工具时,要注意自定义能力、对特殊情况的处理、性能和易用性。常用的工具类型包括在线工具、IDE插件和命令行工具。

XML 转换图片需要先确定 XML 数据结构,再选择合适的图形化库(如 Python 的 matplotlib)和方法,根据数据结构选择可视化策略,考虑数据量和图片格式,进行分批处理或使用高效库,最终根据需求保存为 PNG、JPEG 或 SVG 等格式。

没有APP可以将所有XML文件转成PDF,因为XML结构灵活多样。XML转PDF的核心是将数据结构转换为页面布局,需要解析XML并生成PDF。常用的方法包括使用Python库(如ElementTree)解析XML,并利用ReportLab库生成PDF。对于复杂XML,可能需要使用XSLT转换结构。性能优化时,考虑使用多线程或多进程,并选择合适的库。
