#!/usr/bin/env python3
"""Pull thuisbatterijgids.net's full battery catalogue into a CSV.

The site exposes a JSON REST endpoint at /wp-json/tbg/v1/batteries — no
browser, no scraping, just paginated JSON. Output goes to data/raw/.
"""
from __future__ import annotations

import argparse
import csv
import json
import urllib.request
from pathlib import Path

API = "https://thuisbatterijgids.net/wp-json/tbg/v1/batteries"
HEADERS = {"User-Agent": "Mozilla/5.0 (research; pluginbattery)"}

FIELDS = [
    "brand", "title", "capacity_kwh", "power_w",
    "price_eur", "price_per_kwh", "installation", "review_score",
    "recommended", "url", "id",
]


def fetch_page(page: int, per_page: int = 100) -> dict:
    url = f"{API}?per_page={per_page}&page={page}"
    req = urllib.request.Request(url, headers=HEADERS)
    with urllib.request.urlopen(req, timeout=30) as r:
        return json.load(r)


def main() -> None:
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("--out", default="data/raw/thuisbatterijgids_catalog.csv",
                    help="CSV output path (a parallel .json with all fields is also written)")
    args = ap.parse_args()

    all_batteries = []
    page = 1
    while True:
        data = fetch_page(page)
        all_batteries.extend(data["batteries"])
        print(f"  page {page}/{data['total_pages']}: +{len(data['batteries'])} batteries "
              f"(running total {len(all_batteries)})")
        if page >= data["total_pages"]:
            break
        page += 1

    csv_path = Path(args.out)
    csv_path.parent.mkdir(parents=True, exist_ok=True)
    with csv_path.open("w", newline="") as f:
        writer = csv.DictWriter(f, fieldnames=FIELDS)
        writer.writeheader()
        for b in all_batteries:
            writer.writerow({
                "brand": b.get("brand", ""),
                "title": b.get("title", ""),
                "capacity_kwh": b.get("capacity"),
                "power_w": b.get("power_continuous"),
                "price_eur": b.get("price"),
                "price_per_kwh": b.get("price_per_kwh"),
                "installation": b.get("installation"),
                "review_score": b.get("review_score"),
                "recommended": b.get("recommended"),
                "url": b.get("url", ""),
                "id": b.get("id"),
            })

    json_path = csv_path.with_suffix(".json")
    with json_path.open("w") as f:
        json.dump(all_batteries, f, indent=2, ensure_ascii=False)

    print(f"\nWrote {len(all_batteries)} batteries:")
    print(f"  CSV  → {csv_path}")
    print(f"  JSON → {json_path}")


if __name__ == "__main__":
    main()