"""
Fetch real XAUUSD H1 data from Yahoo Finance (GC=F gold futures).
Saves to CSV for training pipeline.
"""

import argparse
from datetime import datetime, timezone
from pathlib import Path

import pandas as pd
import yfinance as yf

ROOT = Path(__file__).resolve().parent.parent
DATA_DIR = ROOT / "data"
DATA_DIR.mkdir(exist_ok=True)
OUT_CSV = DATA_DIR / "xauusd_h1.csv"


def fetch_xauusd(period: str = "2y", interval: str = "1h") -> pd.DataFrame:
    ticker = yf.Ticker("GC=F")
    df = ticker.history(period=period, interval=interval, auto_adjust=True)
    if df.empty:
        raise RuntimeError("No data returned from Yahoo Finance for GC=F")
    df.index = df.index.tz_convert("UTC").tz_localize(None)
    df.index.name = "datetime"
    df.reset_index(inplace=True)
    df.rename(columns={
        "Open": "open", "High": "high", "Low": "low",
        "Close": "close", "Volume": "volume"
    }, inplace=True)
    df = df[["datetime", "open", "high", "low", "close", "volume"]].copy()
    df.dropna(subset=["open", "high", "low", "close"], inplace=True)
    df["volume"] = df["volume"].fillna(0)
    return df


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("--period", default="2y", help="yfinance period (1y, 2y, max)")
    parser.add_argument("--interval", default="1h", help="yfinance interval (1h, 4h, 1d)")
    parser.add_argument("--out", default=str(OUT_CSV))
    args = parser.parse_args()

    print(f"Fetching XAUUSD (GC=F) {args.interval} for {args.period}...")
    df = fetch_xauusd(args.period, args.interval)
    df.to_csv(args.out, index=False)
    print(f"Saved {len(df)} rows -> {args.out}")
    print(df.tail(3).to_string(index=False))


if __name__ == "__main__":
    main()