Python范围下载

get_object(request: GetObjectRequest, **kwargs) → GetObjectResult

import argparse
import alibabacloud_oss_v2 as oss

# 创建命令行参数解析器
parser = argparse.ArgumentParser(description="Get object range sample")
# 添加必要的命令行参数
parser.add_argument('--region', help='The region in which the bucket is located.', required=True)
parser.add_argument('--bucket', help='The name of the bucket.', required=True)
parser.add_argument('--endpoint', help='The domain names that other services can use to access OSS')
parser.add_argument('--key', help='The name of the object.', required=True)
parser.add_argument('--range', help='Specify the scope of file transfer. Example value: bytes=0-9', required=True)
parser.add_argument('--range_behavior', help='Standard for downloading behavior within a specified range. Example value: standard.')

def main():
    # 解析命令行参数
    args = parser.parse_args()

    # 从环境变量中加载凭证信息
    credentials_provider = oss.credentials.EnvironmentVariableCredentialsProvider()

    # 使用SDK默认配置
    cfg = oss.config.load_default()
    # 设置凭证提供者
    cfg.credentials_provider = credentials_provider
    # 设置区域
    cfg.region = args.region
    # 如果指定了Endpoint，则设置Endpoint
    if args.endpoint is not None:
        cfg.endpoint = args.endpoint

    # 创建OSS客户端
    client = oss.Client(cfg)

    # 发起获取对象请求
    result = client.get_object(oss.GetObjectRequest(
        bucket=args.bucket,  # 指定存储空间名称
        key=args.key,  # 指定对象键名
        range_header=args.range,  # 指定范围头
        range_behavior=args.range_behavior,  # 指定范围内下载行为
    ))

    # 打印响应结果中的多个属性
    print(f'status code: {result.status_code},'
          f' request id: {result.request_id},'
          f' content length: {result.content_length},'
          f' content range: {result.content_range},'
          f' content type: {result.content_type},'
          f' etag: {result.etag},'
          f' last modified: {result.last_modified},'
          f' content md5: {result.content_md5},'
          f' cache control: {result.cache_control},'
          f' content disposition: {result.content_disposition},'
          f' content encoding: {result.content_encoding},'
          f' expires: {result.expires},'
          f' hash crc64: {result.hash_crc64},'
          f' storage class: {result.storage_class},'
          f' object type: {result.object_type},'
          f' version id: {result.version_id},'
          f' tagging count: {result.tagging_count},'
          f' server side encryption: {result.server_side_encryption},'
          f' server side data encryption: {result.server_side_data_encryption},'
          f' next append position: {result.next_append_position},'
          f' expiration: {result.expiration},'
          f' restore: {result.restore},'
          f' process status: {result.process_status},'
          f' delete marker: {result.delete_marker},'
    )

    # ========== 方式1：完整读取 ==========
    # 使用上下文管理器确保资源释放
    with result.body as body_stream:
        data = body_stream.read()
        print(f"文件读取完成，数据长度：{len(data)} bytes")

        path = "./get-object-sample.txt"
        with open(path, 'wb') as f:
            f.write(data)
        print(f"文件下载完成，保存至路径：{path}")

    # # ========== 方式2：分块读取 ==========
    # # 使用上下文管理器确保资源释放
    # with result.body as body_stream:
    #     chunk_path = "./get-object-sample-chunks.txt"
    #     total_size = 0

    #     with open(chunk_path, 'wb') as f:
    #         # 使用256KB块大小（可根据需要调整block_size参数）
    #         for chunk in body_stream.iter_bytes(block_size=256 * 1024):
    #             f.write(chunk)
    #             total_size += len(chunk)
    #             print(f"已接收数据块：{len(chunk)} bytes | 累计：{total_size} bytes")

    #     print(f"文件下载完成，保存至路径：{chunk_path}")

# 当脚本作为主程序运行时调用main函数
if __name__ == "__main__":
    main()