dvc_api_open_remote_tracked_file_quickstart.py

1import dvc.api
2
3# Define the location and version of the data
4path = 'data/data.xml'
5repo = 'https://github.com/iterative/dataset-registry'
6rev = 'main'
7
8# Open and read the data file tracked by DVC
9with dvc.api.open(
10    path=path,
11    repo=repo,
12    rev=rev
13) as fd:
14    for line in fd:
15        # Process the data
16        print(line)