KeCheng/BaiHu/Backup/backupObsFiles.py

# pip install esdk-obs-python --trusted-host pypi.org
# pip install tqdm
# python.exe -m pip install --upgrade pip
# 引入模块
import os
from datetime import datetime
from obs import ObsClient
import time
from tqdm import tqdm
import requests
import urllib.parse

# 替换为你的华为云AK/SK
ak = "WAFBGJACKDOQZDH1MKZ1"
sk = "dlWTUbqgCICaYJG3n0Rot4jXaen2HnfFtMVxiPEo"
server = "https://obs.cn-north-1.myhuaweicloud.com"
bucketName = "dsideal"
prefix = "HuangHai/HuiZhiKeJi/"
localPath = "D:/课程备份/"


def getTime():
    # 获取当前时间
    now = datetime.now()
    # 格式化到秒
    current_time_to_seconds = now.strftime("%H:%M:%S")
    return current_time_to_seconds


# 执行一次
def solve():
    # 创建obsClient实例
    obsClient = ObsClient(access_key_id=ak, secret_access_key=sk, server=server)
    # 使用访问OBS

    max_keys = 1000
    mark = None
    resp = None

    while True:
        fileList = obsClient.listObjects(bucketName=bucketName, prefix=prefix, max_keys=max_keys, marker=mark)
        for file in fileList.body.contents:
            fullName = file.key.replace(prefix, "")
            array = fullName.split("/")
            fileName = array[-1]
            dirStr = ''
            for i in range(len(array) - 1):
                dirStr += array[i] + "/"

            if dirStr == '' or fileName == '':
                continue
            localDirStr = localPath + dirStr
            if not os.path.isdir(localDirStr):
                os.makedirs(localDirStr, exist_ok=True)

            downloadPath = localDirStr + fileName
            # 下载对象
            resp = obsClient.getObject(bucketName=bucketName, objectKey=file.key)

            # 如果已存在，但是，与云存储中文件大小不一样大，那么删除掉
            if os.path.isfile(downloadPath):
                localFileSize = os.path.getsize(downloadPath)
                if file.size != localFileSize:
                    os.remove(downloadPath)
                    print(getTime() + "   " + "发现文件大小不一致，删除本地文件：" + downloadPath)

            if not os.path.isfile(downloadPath):
                print(
                    getTime() + "   下载文件：" + fileName + ",文件大小：" + str(
                        "{:.2f}".format(file.size / 1024 / 1024)) + "MB")

                # 发送HTTP GET请求
                # 对URL进行编码
                url_to_encode = dirStr + fileName
                encoded_url = urllib.parse.quote(url_to_encode, safe='')
                url = "https://dsideal.obs.cn-north-1.myhuaweicloud.com/HuangHai/HuiZhiKeJi/" + encoded_url
                response = requests.get(url, stream=True)
                # 获取文件总大小
                total_size_in_bytes = int(response.headers.get('content-length', 0))
                # 创建一个进度条
                progress_bar = tqdm(total=total_size_in_bytes, unit='iB', unit_scale=True)

                # 定义一个函数来处理数据块
                def callback_chunk(chunk):
                    progress_bar.update(len(chunk))

                # 打开一个本地文件用于写入
                with open(downloadPath, 'wb') as file:
                    # 迭代响应内容
                    for chunk in response.iter_content(chunk_size=1024):
                        file.write(chunk)
                        callback_chunk(chunk)  # 更新进度条
                # 关闭进度条
                progress_bar.close()
            else:
                print(
                    getTime() + "   相同的文件：" + fileName + ",文件大小：" + str(
                        "{:.2f}".format(file.size / 1024 / 1024)) + "MB，跳过...")

        # 是否已经完成了所有任务
        if resp != None and resp.body.is_truncated is True:
            mark = resp.body.next_marker
        else:
            break
    # 关闭obsClient
    obsClient.close()
    print(getTime() + "   同步完成")


if __name__ == '__main__':
    while True:
        solve()
        time.sleep(3600 * 2)  # 每2小时执行一次同步操作