如何使用Python脚本从FTP服务器上删除超过7天的文件？

发布于 2024-09-02 06:57:05 字数 854 浏览 5 评论 0原文

我想编写一个 Python 脚本，它允许我在文件达到一定年龄后从 FTP 服务器删除文件。我准备了下面的脚本，但它抛出错误消息：WindowsError：[Error 3]系统找不到指定的路径：'/test123/*.*'

有人知道如何解决此问题吗问题？先感谢您！

import os, time
from ftplib import FTP

ftp = FTP('127.0.0.1')
print "Automated FTP Maintainance"
print 'Logging in.'
ftp.login('admin', 'admin')

# This is the directory that we want to go to
path = 'test123'
print 'Changing to:' + path
ftp.cwd(path)
files = ftp.retrlines('LIST')
print 'List of Files:' + files 
#--everything works fine until here!...

#--The Logic which shall delete the files after the are 7 days old--
now = time.time()
for f in os.listdir(path):
  if os.stat(f).st_mtime < now - 7 * 86400:
    if os.path.isfile(f):
        os.remove(os.path.join(path, f))
except:
    exit ("Cannot delete files")

print 'Closing FTP connection'
ftp.close()

原文

I would like to write a Python script which allows me to delete files from a FTP Server after they have reached a certain age. I prepared the scipt below but it throws the error message: WindowsError: [Error 3] The system cannot find the path specified: '/test123/*.*'

Do someone have an idea how to resolve this issue? Thank you in advance!

import os, time
from ftplib import FTP

ftp = FTP('127.0.0.1')
print "Automated FTP Maintainance"
print 'Logging in.'
ftp.login('admin', 'admin')

# This is the directory that we want to go to
path = 'test123'
print 'Changing to:' + path
ftp.cwd(path)
files = ftp.retrlines('LIST')
print 'List of Files:' + files 
#--everything works fine until here!...

#--The Logic which shall delete the files after the are 7 days old--
now = time.time()
for f in os.listdir(path):
  if os.stat(f).st_mtime < now - 7 * 86400:
    if os.path.isfile(f):
        os.remove(os.path.join(path, f))
except:
    exit ("Cannot delete files")

print 'Closing FTP connection'
ftp.close()

分享到QQ

分享到微博

如果你对这篇内容有疑问，欢迎到本站社区发帖提问参与讨论，获取更多帮助，或者扫码二维码加入 Web 技术交流群。

发布评论

需要登录才能够评论，你可以免费注册一个本站的账号。

二货你真萌 2024-09-09 06:57:05

好的。假设您的 FTP 服务器支持 MLSD 命令，请使用以下代码创建一个模块（这是我用来同步远程 FTP 站点与本地目录的脚本中的代码）：

module code

# for python ≥ 2.6
import sys, os, time, ftplib
import collections
FTPDir= collections.namedtuple("FTPDir", "name size mtime tree")
FTPFile= collections.namedtuple("FTPFile", "name size mtime")

class FTPDirectory(object):
    def __init__(self, path='.'):
        self.dirs= []
        self.files= []
        self.path= path

    def getdata(self, ftpobj):
        ftpobj.retrlines('MLSD', self.addline)

    def addline(self, line):
        data, _, name= line.partition('; ')
        fields= data.split(';')
        for field in fields:
            field_name, _, field_value= field.partition('=')
            if field_name == 'type':
                target= self.dirs if field_value == 'dir' else self.files
            elif field_name in ('sizd', 'size'):
                size= int(field_value)
            elif field_name == 'modify':
                mtime= time.mktime(time.strptime(field_value, "%Y%m%d%H%M%S"))
        if target is self.files:
            target.append(FTPFile(name, size, mtime))
        else:
            target.append(FTPDir(name, size, mtime, self.__class__(os.path.join(self.path, name))))

    def walk(self):
        for ftpfile in self.files:
            yield self.path, ftpfile
        for ftpdir in self.dirs:
            for path, ftpfile in ftpdir.tree.walk():
                yield path, ftpfile

class FTPTree(FTPDirectory):
    def getdata(self, ftpobj):
        super(FTPTree, self).getdata(ftpobj)
        for dirname in self.dirs:
            ftpobj.cwd(dirname.name)
            dirname.tree.getdata(ftpobj)
            ftpobj.cwd('..')

single directory case

If如果您想处理目录中的文件，您可以：

import ftplib, time

quite_old= time.time() - 7*86400 # seven days

site= ftplib.FTP(hostname, username, password)
site.cwd(the_directory_to_work_on) # if it's '.', you can skip this line
folder= FTPDirectory()
folder.getdata(site) # get the filenames
for path, ftpfile in folder.walk():
    if ftpfile.mtime < quite_old:
        site.delete(ftpfile.name)

这应该可以满足您的要求。

目录及其后代

现在，如果这应该递归地工作，您必须在“单目录情况”的代码中进行以下两项更改：

folder= FTPTree()

和

site.delete(os.path.join(path, ftpfile.name))

可能的警告

我使用过的服务器没有任何问题STOR 和 DELE 命令中的相对路径，因此具有相对路径的 site.delete 也可以工作。如果您的 FTP 服务器需要无路径文件名，您应该首先 .cwd 到提供的 path，.delete 普通的 ftpfile.name< /code> 然后 .cwd 返回到基本文件夹。

OK. Assuming your FTP server supports the MLSD command, make a module with the following code (this is code from a script I use to sync a remote FTP site with a local directory):

module code

# for python ≥ 2.6
import sys, os, time, ftplib
import collections
FTPDir= collections.namedtuple("FTPDir", "name size mtime tree")
FTPFile= collections.namedtuple("FTPFile", "name size mtime")

class FTPDirectory(object):
    def __init__(self, path='.'):
        self.dirs= []
        self.files= []
        self.path= path

    def getdata(self, ftpobj):
        ftpobj.retrlines('MLSD', self.addline)

    def addline(self, line):
        data, _, name= line.partition('; ')
        fields= data.split(';')
        for field in fields:
            field_name, _, field_value= field.partition('=')
            if field_name == 'type':
                target= self.dirs if field_value == 'dir' else self.files
            elif field_name in ('sizd', 'size'):
                size= int(field_value)
            elif field_name == 'modify':
                mtime= time.mktime(time.strptime(field_value, "%Y%m%d%H%M%S"))
        if target is self.files:
            target.append(FTPFile(name, size, mtime))
        else:
            target.append(FTPDir(name, size, mtime, self.__class__(os.path.join(self.path, name))))

    def walk(self):
        for ftpfile in self.files:
            yield self.path, ftpfile
        for ftpdir in self.dirs:
            for path, ftpfile in ftpdir.tree.walk():
                yield path, ftpfile

class FTPTree(FTPDirectory):
    def getdata(self, ftpobj):
        super(FTPTree, self).getdata(ftpobj)
        for dirname in self.dirs:
            ftpobj.cwd(dirname.name)
            dirname.tree.getdata(ftpobj)
            ftpobj.cwd('..')

single directory case

If you want to work on the files of a directory, you can:

import ftplib, time

quite_old= time.time() - 7*86400 # seven days

site= ftplib.FTP(hostname, username, password)
site.cwd(the_directory_to_work_on) # if it's '.', you can skip this line
folder= FTPDirectory()
folder.getdata(site) # get the filenames
for path, ftpfile in folder.walk():
    if ftpfile.mtime < quite_old:
        site.delete(ftpfile.name)

This should do what you want.

a directory and its descendants

Now, if this should work recursively, you'll have to do the following two changes in the code for “single directory case”:

folder= FTPTree()

and

site.delete(os.path.join(path, ftpfile.name))

Possible caveat

The servers I've worked with didn't have any issues with relative paths in the STOR and DELE commands, so site.delete with a relative path worked too. If your FTP server requires pathless filenames, you should first .cwd to the path provided, .delete the plain ftpfile.name and then .cwd back to the base folder.

回复收藏 0 原文

谁的年少不轻狂 2024-09-09 06:57:05

我必须这样做，花了一段时间，我想我可以在这里节省别人的时间。我们使用安装了 ftputil 模块的 python：

#! /usr/bin/python
import time
import ftputil
host = ftputil.FTPHost('ftphost.com', 'username', 'password')
mypath = 'ftp_dir'
now = time.time()
host.chdir(mypath)
names = host.listdir(host.curdir)
for name in names:
    if host.path.getmtime(name) < (now - (7 * 86400)):
      if host.path.isfile(name):
         host.remove(name)


print 'Closing FTP connection'
host.close()

I had to do this and it took a while, thought I could save someones time here. We are using python with ftputil module installed:

#! /usr/bin/python
import time
import ftputil
host = ftputil.FTPHost('ftphost.com', 'username', 'password')
mypath = 'ftp_dir'
now = time.time()
host.chdir(mypath)
names = host.listdir(host.curdir)
for name in names:
    if host.path.getmtime(name) < (now - (7 * 86400)):
      if host.path.isfile(name):
         host.remove(name)


print 'Closing FTP connection'
host.close()

回复收藏 0 原文

若能看破又如何 2024-09-09 06:57:05

好吧，与其进一步分析您发布的代码，这里有一个示例，它可能会让您走上正确的轨道。

from ftplib import FTP
import re

pattern = r'.* ([A-Z|a-z].. .. .....) (.*)'

def callback(line):
    found = re.match(pattern, line)
    if (found is not None):
        print found.groups()

ftp = FTP('myserver.wherever.com')
ftp.login('elvis','presley')
ftp.cwd('testing123')
ftp.retrlines('LIST',callback)

ftp.close()
del ftp

运行它，您将得到类似这样的输出，这应该是您想要实现的目标的开始。要完成它，您需要将第一个结果解析为日期时间，将其与“now”进行比较，并使用 ftp.delete() 删除远程文件（如果它太旧）。

>>> 
('May 16 13:47', 'Thumbs.db')
('Feb 16 17:47', 'docs')
('Feb 23  2007', 'marvin')
('May 08  2009', 'notes')
('Aug 04  2009', 'other')
('Feb 11 18:24', 'ppp.xml')
('Jan 20  2010', 'reports')
('Oct 10  2005', 'transition')
>>>

OK, well rather than analyze the code you have posted any further, here's an example instead that might put you on the right track.

from ftplib import FTP
import re

pattern = r'.* ([A-Z|a-z].. .. .....) (.*)'

def callback(line):
    found = re.match(pattern, line)
    if (found is not None):
        print found.groups()

ftp = FTP('myserver.wherever.com')
ftp.login('elvis','presley')
ftp.cwd('testing123')
ftp.retrlines('LIST',callback)

ftp.close()
del ftp

Run it and you'll get output something like this, which should be a start towards what you're trying to achieve. To finish it out you'd need to parse the first result into a datetime, compare it with "now" and use ftp.delete() to get rid of the remote file if it's too old.

>>> 
('May 16 13:47', 'Thumbs.db')
('Feb 16 17:47', 'docs')
('Feb 23  2007', 'marvin')
('May 08  2009', 'notes')
('Aug 04  2009', 'other')
('Feb 11 18:24', 'ppp.xml')
('Jan 20  2010', 'reports')
('Oct 10  2005', 'transition')
>>>

回复收藏 0 原文

摇划花蜜的午后 2024-09-09 06:57:05

好吧，看来您看到的错误与您尝试从本地计算机（而不是 FTP 站点）删除“test123”目录有关。 FTP 文档有一个名为 delete 的方法，这就是您想用它来删除该文件。至于测试某些文件是否已存在 7 天，您实际上可能必须暂时从 FTP 中拉取这些文件，然后在使用 FTP.delete 之前检查修改时间。

回复收藏 0 原文