Spaces:
Paused
Paused
| """Download a bounded set of real T20 JSON matches from Cricsheet. | |
| Usage: | |
| python scripts/download_cricsheet.py --count 12 | |
| The source is Cricsheet (https://cricsheet.org/), which provides structured | |
| historical ball-by-ball data. The files are intentionally kept outside source | |
| control and loaded by MatchRepository at startup. | |
| """ | |
| import argparse | |
| import json | |
| import shutil | |
| import tempfile | |
| import urllib.request | |
| import zipfile | |
| from pathlib import Path | |
| URL = "https://cricsheet.org/downloads/ipl_json.zip" | |
| def main() -> None: | |
| parser = argparse.ArgumentParser() | |
| parser.add_argument("--count", type=int, default=12) | |
| parser.add_argument("--output", type=Path, default=Path("app/data/matches")) | |
| args = parser.parse_args() | |
| if args.count < 1: | |
| raise SystemExit("--count must be at least 1") | |
| args.output.mkdir(parents=True, exist_ok=True) | |
| with tempfile.TemporaryDirectory() as temp_dir: | |
| archive = Path(temp_dir) / "cricsheet.zip" | |
| urllib.request.urlretrieve(URL, archive) | |
| with zipfile.ZipFile(archive) as source: | |
| candidates = [] | |
| for name in source.namelist(): | |
| if not name.endswith(".json") or name.endswith("README.txt"): | |
| continue | |
| with source.open(name) as stream: | |
| payload = json.load(stream) | |
| info = payload.get("info", {}) | |
| if info.get("match_type") == "T20" and len(payload.get("innings", [])) >= 2: | |
| candidates.append(name) | |
| for name in candidates[:args.count]: | |
| destination = args.output / Path(name).name | |
| with source.open(name) as source_file, destination.open("wb") as target: | |
| shutil.copyfileobj(source_file, target) | |
| print(f"Downloaded {min(args.count, len(candidates))} T20 matches to {args.output}") | |
| if __name__ == "__main__": | |
| main() | |