根据日期时间同步文件夹

Question

I am very new to python and trying to work on this script which recieves data from multiple ftp sites and download yesterday data according to date directory to my local folder. but if the receives fails on any day it would not update that day records and would go to the next day. I want to sync the files that even if it is missed on particular it should complete sync teh new files to local folder I have tried looking at rsync but need your help to process it on the script.this is my script.

MAX_CHILDREN = 16
    ftp_site_prog = "/usr/local/bin/ftp_site.py"

    class SpawnQ:
        def __init__(self, max_pids):
            self.max_pids = max_pids 
            self.queue = []
            tmp = re.split("/", ftp_site_prog)
            self.my_name = tmp[-1]


        def addQ(self, site_id):
            self.queue.append(site_id)
            return

        def runQ(self):
            while (len(self.queue) != 0):
                # Check how many sessions are running
                cmd = """ps -ef | grep "%s" | grep -v grep""" % self.my_name
                num_pids = 0
                for line in os.popen(cmd).readlines():
                    num_pids = num_pids + 1

                if (num_pids < self.max_pids):
                    site_id = self.queue.pop()
                    # print site_id
                    # print "Forking........"
                    fpid = os.fork()
                    if fpid:
                        # print "Created child: ", fpid
                        os.waitpid(fpid, os.WNOHANG)
                    else:
                        # print "This is the Child"

                        # Exec the ftp_site
                        arg_string = "%s" % site_id
                        args = [arg_string]


           os.execvp(ftp_site_prog, (ftp_site_prog,) + tuple(args))
    how to  call rsync on my py script.//os.system("rsync -ftp_site_prog, (ftp_site_prog,)+ tuple(args))
        sys.exit(0)
                else:
                    # print "Waiting for a spare process...."
                    time.sleep(10)
            return

    # Get a list of the sites
    db_obj = nprint.celDb()
    site_list = db_obj.get_all_site_ids()

    myQ = SpawnQ(MAX_CHILDREN)

    for site_id in site_list:
        myQ.addQ(site_id)

    myQ.runQ()

    # Wait until we only have the parent left
    # Check how many sessions are running
    tmp = re.split("/",ftp_site_prog)
    ftp_name = tmp[-1]
    cmd = """ps -ef | grep "%s" | grep -v grep""" % ftp_name

    num_pids = MAX_CHILDREN
    while (num_pids > 0):
        num_pids = 0
        for line in os.popen(cmd).readlines():
            num_pids = num_pids + 1

        time.sleep(60)

    today = datetime.date.today()
    daydelta = datetime.timedelta(days=1)
    yesterday = today - daydelta

Answer 1

Much of this can be accomplished with the ftplib module for the retrieval of files from standard FTP servers. If you are dealing with SFTP servers you can use the paramiko library.