perfect-postcode/pipeline/download/arcgis.py

38 lines
1.2 KiB
Python

import argparse
import tempfile
import polars as pl
from pathlib import Path
from pipeline.utils import download, extract_zip
URL = "https://www.arcgis.com/sharing/rest/content/items/077631e063eb4e1ab43575d01381ec33/data"
def convert_to_parquet(data_path: Path, parquet_path: Path) -> None:
df = pl.scan_csv(data_path / "Data/NSPL_MAY_2025_UK.csv", try_parse_dates=True)
print(f"Columns: {df.collect_schema().names()}")
parquet_path.parent.mkdir(parents=True, exist_ok=True)
df.sink_parquet(parquet_path, compression="zstd")
print(f"Saved to {parquet_path}")
def main() -> None:
parser = argparse.ArgumentParser(
description="Download and convert ArcGIS postcode data"
)
parser.add_argument(
"--output", type=Path, required=True, help="Output parquet file path"
)
args = parser.parse_args()
with tempfile.TemporaryDirectory() as cache_dir:
download_path = Path(cache_dir) / "arcgis_data.zip"
extract_path = Path(cache_dir) / "arcgis_extracted"
download(URL, download_path)
extract_zip(download_path, extract_path)
convert_to_parquet(extract_path, args.output)
if __name__ == "__main__":
main()