Created
November 23, 2019 14:25
-
-
Save antonyharfield/ff9d47e96bb9a9491bad7df543746a1b to your computer and use it in GitHub Desktop.
Google Cloud Storage list the directories or folders within a given bucket and path (not including objects!)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from google.api_core import page_iterator | |
from google.cloud import storage | |
def _item_to_value(iterator, item): | |
return item | |
def list_directories(bucket_name, path): | |
if not path.endswith('/'): | |
path += '/' | |
extra_params = { | |
"projection": "noAcl", | |
"prefix": path, | |
"delimiter": '/' | |
} | |
gcs = storage.Client() | |
path = "/b/" + bucket_name + "/o" | |
iterator = page_iterator.HTTPIterator( | |
client=gcs, | |
api_request=gcs._connection.api_request, | |
path=path, | |
items_key='prefixes', | |
item_to_value=_item_to_value, | |
extra_params=extra_params, | |
) | |
return [x for x in iterator] | |
bucket_name = 'rfcx-models-dev' | |
path = 'dog-bark/datasets/v2/train_set/' | |
print(list_directories(bucket_name, path)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment