Download all objects in a bucket

Use Transfer Manager to download all of the files in a bucket with concurrency.

Explore further

For detailed documentation that includes this code sample, see the following:

• Download objects

Code sample

Java

For more information, see the Cloud Storage Java API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

import com.google.cloud.storage.BlobInfo;
import com.google.cloud.storage.Storage;
import com.google.cloud.storage.StorageOptions;
import com.google.cloud.storage.transfermanager.DownloadResult;
import com.google.cloud.storage.transfermanager.ParallelDownloadConfig;
import com.google.cloud.storage.transfermanager.TransferManager;
import com.google.cloud.storage.transfermanager.TransferManagerConfig;
import java.nio.file.Path;
import java.util.List;
import java.util.stream.Collectors;

class DownloadBucket {

  public static void downloadBucketContents(
      String projectId, String bucketName, Path destinationDirectory) {
    Storage storage = StorageOptions.newBuilder().setProjectId(projectId).build().getService();
    List<BlobInfo> blobs =
        storage
            .list(bucketName)
            .streamAll()
            .map(blob -> blob.asBlobInfo())
            .collect(Collectors.toList());
    TransferManager transferManager = TransferManagerConfig.newBuilder().build().getService();
    ParallelDownloadConfig parallelDownloadConfig =
        ParallelDownloadConfig.newBuilder()
            .setBucketName(bucketName)
            .setDownloadDirectory(destinationDirectory)
            .build();

    List<DownloadResult> results =
        transferManager.downloadBlobs(blobs, parallelDownloadConfig).getDownloadResults();

    for (DownloadResult result : results) {
      System.out.println(
          "Download of "
              + result.getInput().getName()
              + " completed with status "
              + result.getStatus());
    }
  }
}

Python

For more information, see the Cloud Storage Python API reference documentation.

To authenticate to Cloud Storage, set up Application Default Credentials. For more information, see Set up authentication for client libraries.

def download_bucket_with_transfer_manager(
    bucket_name, destination_directory="", workers=8, max_results=1000
):
    """Download all of the blobs in a bucket, concurrently in a process pool.

    The filename of each blob once downloaded is derived from the blob name and
    the `destination_directory `parameter. For complete control of the filename
    of each blob, use transfer_manager.download_many() instead.

    Directories will be created automatically as needed, for instance to
    accommodate blob names that include slashes.
    """

    # The ID of your GCS bucket
    # bucket_name = "your-bucket-name"

    # The directory on your computer to which to download all of the files. This
    # string is prepended (with os.path.join()) to the name of each blob to form
    # the full path. Relative paths and absolute paths are both accepted. An
    # empty string means "the current working directory". Note that this
    # parameter allows accepts directory traversal ("../" etc.) and is not
    # intended for unsanitized end user input.
    # destination_directory = ""

    # The maximum number of processes to use for the operation. The performance
    # impact of this value depends on the use case, but smaller files usually
    # benefit from a higher number of processes. Each additional process occupies
    # some CPU and memory resources until finished. Threads can be used instead
    # of processes by passing `worker_type=transfer_manager.THREAD`.
    # workers=8

    # The maximum number of results to fetch from bucket.list_blobs(). This
    # sample code fetches all of the blobs up to max_results and queues them all
    # for download at once. Though they will still be executed in batches up to
    # the processes limit, queueing them all at once can be taxing on system
    # memory if buckets are very large. Adjust max_results as needed for your
    # system environment, or set it to None if you are sure the bucket is not
    # too large to hold in memory easily.
    # max_results=1000

    from google.cloud.storage import Client, transfer_manager

    storage_client = Client()
    bucket = storage_client.bucket(bucket_name)

    blob_names = [blob.name for blob in bucket.list_blobs(max_results=max_results)]

    results = transfer_manager.download_many_to_path(
        bucket, blob_names, destination_directory=destination_directory, max_workers=workers
    )

    for name, result in zip(blob_names, results):
        # The results list is either `None` or an exception for each blob in
        # the input list, in order.

        if isinstance(result, Exception):
            print("Failed to download {} due to exception: {}".format(name, result))
        else:
            print("Downloaded {} to {}.".format(name, destination_directory + name))

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.