dvc_api_open_s3_remote_file_read_quickstart.py

1import dvc.api
2
3# Define the path to the data file within your DVC project
4# and the URL of the remote (S3 bucket) or the local git repository
5resource_url = 'data/data.xml'
6repo_url = 'https://github.com/iterative/dataset-registry'
7
8# Open the file directly from the remote storage (S3)
9with dvc.api.open(
10    path=resource_url,
11    repo=repo_url,
12    mode='r'
13) as f:
14    # Read the content (e.g., first 100 characters)
15    content = f.read(100)
16    print(content)