perfect-postcode/pipeline/download/broadband.py

80 lines
2.9 KiB
Python

import argparse
import zipfile
import httpx
import polars as pl
from pathlib import Path
import tempfile
from tqdm import tqdm
# Ofcom Connected Nations 2025 - Fixed broadband performance (output area & local authority level)
# Source: https://www.ofcom.org.uk/phones-and-broadband/coverage-and-speeds/connected-nations-20252/data-downloads-2025
PERFORMANCE_URL = "https://www.ofcom.org.uk/siteassets/resources/documents/research-and-data/multi-sector/infrastructure-research/connected-nations-2025/202507_fixed_broadband_performance_r01.zip"
def download_with_progress(url: str, output_path: Path) -> None:
with httpx.stream("GET", url, follow_redirects=True, timeout=120) as response:
response.raise_for_status() # pyright: ignore[reportUnusedCallResult]
total = int(response.headers.get("content-length", 0))
with (
open(output_path, "wb") as f,
tqdm(total=total, unit="B", unit_scale=True, desc="Downloading") as pbar,
):
for chunk in response.iter_bytes(chunk_size=8192):
f.write(chunk)
pbar.update(len(chunk))
def extract_zip(zip_path: Path, extract_dir: Path) -> None:
with zipfile.ZipFile(zip_path, "r") as z:
z.extractall(extract_dir)
def convert_to_parquet(extract_dir: Path, parquet_path: Path) -> None:
# Find CSV files in the extracted directory
csv_files = list(extract_dir.rglob("*.csv"))
if not csv_files:
raise FileNotFoundError(f"No CSV files found in {extract_dir}")
print(f"Found CSV files: {[f.name for f in csv_files]}")
# Read and concatenate all CSVs (typically split by geography level)
frames = []
for csv_file in sorted(csv_files):
print(f"Reading {csv_file.name}...")
df = pl.read_csv(csv_file, infer_schema_length=10000, encoding="utf8-lossy")
print(f" Shape: {df.shape}, Columns: {df.columns}")
frames.append((csv_file.stem, df))
# Save each CSV as a separate parquet file in the output directory
parquet_path.mkdir(parents=True, exist_ok=True)
for name, df in frames:
out = parquet_path / f"{name}.parquet"
df.write_parquet(out, compression="zstd")
print(f"Saved {out} ({df.shape[0]} rows)")
def main() -> None:
parser = argparse.ArgumentParser(
description="Download Ofcom broadband performance data"
)
parser.add_argument(
"--output",
type=Path,
required=True,
help="Output directory for parquet files",
)
args = parser.parse_args()
with tempfile.TemporaryDirectory() as cache_dir:
cache = Path(cache_dir)
zip_path = cache / "broadband_performance.zip"
extract_dir = cache / "extracted"
extract_dir.mkdir()
download_with_progress(PERFORMANCE_URL, zip_path)
extract_zip(zip_path, extract_dir)
convert_to_parquet(extract_dir, args.output)
if __name__ == "__main__":
main()