python 提取文件的小程序

168 阅读 0 评论 111 点赞

我是靠谱客的博主坦率手链，最近开发中收集的这篇文章主要介绍python 提取文件的小程序，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

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

复制代码代码如下:

<?xml version="1.0" encoding="utf-8"?> 
<config> 
    <srcdir>E:\temp\home\cargill</srcdir> 
    <destdir>E:\temp\dest\cargill</destdir> 
    <notinclude> 
        <dirs> 
            <dir>E:\temp\home\cargill\WEB-INF\lib</dir> 
            <dir>E:\temp\home\cargill\static\cargill\report</dir> 
        </dirs> 
        <files> 
            <file>E:\temp\home\cargill\WEB-INF\classes\myrumba.xml</file> 
            <file>E:\temp\home\cargill\META-INF\context.xml</file> 
        </files> 
    </notinclude> 
    <inittime>2008-10-11 13:15:22</inittime> 
    <rardir>C:\Program Files\WinRAR</rardir> 
</config>

其中
<srcdir>：原始目录，即我们tomcat的发布目录；
<destdir>：文件复制到得目标目录；
<notinclude>：需要忽略的文件夹和文件，具体需要忽略的内容在其子节点中定义，这里不在解释；
<inittime>：这个是初始化需要提取的时间点，在这之后的才会提取，此处需要说明，后来在使用中，我增加了一个功能，就是每次提取完会自动将本次提取时间记录到一个文本文件C_UPGRADETIME.txt中，这就省去每次设置这个值的烦恼，只有C_UPGRADETIME.txt为空或者不存在时，才会用到这个值；
<rardir>：rar压缩程序的地址；
下面是读取配置文件的类：
config.py

复制代码代码如下:

''' 
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> element value of self.config_element 
''' 
srcDir = self.config_element.getElementsByTagName("srcdir")[0] 
return self.getText(srcDir.childNodes) 
def getDestDir(self): 
''' 
return the <destdir> element value of self.config_element 
''' 
destDir = self.config_element.getElementsByTagName("destdir")[0] 
return self.getText(destDir.childNodes) 
def getNotIncludeDirs(self): 
''' 
return a list, it's the <dir> element values of self_config_element 
''' 
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 <file> element values of self.config_element 
''' 
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> element value of self.config_element 
''' 
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> element value 
''' 
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

复制代码代码如下:

''' 
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 < lasttime: 
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()