databank/scripts/test_get_league_match_list.py

"""Executable demo: run GetLeagueMatchListSpider for three requests.

Usage (PowerShell):
  python -m pip install requests pymongo
  $env:DATABANK_DB_URI = "mongodb://localhost:27017"
  $env:DATABANK_DB_NAME = "databank"
  python scripts/test_get_league_match_list.py
"""

from __future__ import annotations

import os
from collections import defaultdict

from databank.db import MongoDB
from databank.spiders.get_league_match_list import GetLeagueMatchListSpider


def pick_tokens(max_tokens: int = 3) -> list[str]:
    """Build up to ``max_tokens`` URL tokens from MongoDB collections."""
    uri = os.getenv("DATABANK_DB_URI", "mongodb://localhost:27017")
    name = os.getenv("DATABANK_DB_NAME", "databank")
    db = MongoDB(uri=uri, name=name)
    db.connect()
    try:
        leagues = db.find("leagues", projection={"_id": 0}, limit=10)
        seasons = db.find("seasons", projection={"_id": 0}, limit=10)
        if not leagues:
            raise RuntimeError("No leagues found. Seed leagues first.")
        if not seasons:
            raise RuntimeError("No seasons found. Seed seasons first.")

        league = sorted(leagues, key=lambda x: x.get("league_id", 0))[0]
        max_round = int(league.get("max_round", 1))
        season_name = seasons[0]["season"]

        tokens: list[str] = []
        rounds = list(range(1, max_round + 1))[:max_tokens]
        for r in rounds:
            tokens.append(f"{league['league_id']}|{season_name}|{r}")
        return tokens[:max_tokens]
    finally:
        db.close()


def main() -> None:
    """Run the demo and print a compact summary to stdout."""
    spider = GetLeagueMatchListSpider()
    urls = pick_tokens()
    docs = spider.run(urls)

    print(f"Fetched {len(docs)} documents in total.")

    per_token = defaultdict(list)
    for d in docs:
        per_token[d.data.get("token", "unknown")].append(d)

    for token, items in per_token.items():
        print(f"Token: {token}, docs: {len(items)}")
        if items:
            print("Sample:", items[0].data.get("match") or items[0].data)


if __name__ == "__main__":
    main()