Python 执行 Rsync 备份磁盘

本文最后更新于：2024年5月7日下午

在 Rsync 数据同步工具中介绍了 rsync 的使用方法，本文记录：使用python语言执行备份磁盘命令，并记录日志。

实现目标

自动执行对指定文件夹的 rsync 备份
自动记录日志
可以调整命令

功能实现

核心函数

输入源文件夹、目标文件夹、日志路径、是否删除作为参数

import os
from mtutils import log_init
from mtutils import OS_isdir
from mtutils import multi_process
from mtutils import vvd_round
from functools import partial
from tqdm import tqdm
from pathlib import Path
import random
import time


def rsync_folder(source_dir, target_dir, log_path, delete=False):
    logger = log_init(log_path)
    time.sleep(random.random() * 10)
    try:
        source_dir = str(source_dir)
        target_dir = str(target_dir)

        logger(f"@@ start to rsync {source_dir} to {target_dir}, delete {delete}")

        assert OS_isdir(source_dir), f"source_dir {source_dir} is not a dir."
        assert OS_isdir(target_dir), f"target_dir {target_dir} is not a dir."
        
        if delete:
            logger("@@ this is a rsync with backup target cleaning.")
            delete_str = '--delete'
        else:
            delete_str = ''
        logger("")
        sync_cmd = "rsync -azrvhP " + delete_str + " " + source_dir + " " + target_dir + ' >> ' + log_path
        logger("")
        logger(f"@@ rsync command: {sync_cmd}")
        logger("@@ rsync start !!")

        start = time.time()
        
        os.system(sync_cmd)
        
        passed = time.time() - start

        seconds = passed % 60
        total_minutes = vvd_round((passed - seconds) / 60)
        minusts = total_minutes % 60
        hours = vvd_round((total_minutes - minusts) / 60)

        logger("@@ rsync finish !!")
        logger(f"@@ running time: {hours}h {minusts}m {seconds}s")
        return 0

    except Exception as e:
        logger('@@ rsync failed!')
        logger('@@ error message: {e}')
    
        return -1

调用方法

通过 single_infer 函数接收 task 作为输入文件夹参数进行封装

def single_infer(task, log_path, delete=False):
    assert len(task) == 2
    source, target = task
    return rsync_folder(source, target, log_path, delete)

顺序执行

if __name__ == '__main__':

    log_path = 'log/rsync.log'

    task_list = [
        ['source_dir1', 'target_dir1'], 
        ['source_dir2', 'target_dir2'], 
        ['source_dir3', 'target_dir3'], 
    ]

    # 每月 1 号删除已经删除的源文件在备份盘的备份资料
    cur_time = time.localtime(time.time())
    if cur_time.tm_mday == 1:
        delete_arg = True
    else:
        delete_arg = False

    rsync_infer = partial(single_infer, log_path=log_path, delete=delete_arg)

    for task in tqdm(task_list):
        rsync_infer(task)