"""下载样本外验证用的新币种数据，存成与 freqtrade 一致的 feather。

现有结论全部建立在 BTC/ETH/SOL 三个币上，参数（级别对、tol、SL/TP）也是
在这三个币上挑的，存在选择偏差。本脚本补齐一批完全没参与过调参的品种。

只拉 30m/2h：那是实测最强的一对，用它做样本外足够，且请求量只有全级别的四成。

限速要点（踩过的坑）：
  klines(limit=1500) 权重 30，上限 2400/分钟 = 80 次/分钟 = 0.75s/次，
  0.8s 间隔正好卡在边缘，一旦触发 429，短退避跨不过计数窗口就会连续失败。
  故间隔放到 1.3s、权重阈值压到 1400、429 时等满一个窗口。
  另外分页失败不再丢弃整只币，已抓到的部分照样落盘。
"""
from __future__ import annotations

import sys
import time
from pathlib import Path

import pandas as pd
import requests

OUT = Path(__file__).resolve().parents[1] / "data" / "binance" / "futures"
BASE = "https://fapi.binance.com/fapi/v1/klines"
PROXY = {"http": "http://127.0.0.1:7897", "https": "http://127.0.0.1:7897"}
SYMBOLS = ["BNB", "XRP", "DOGE", "ADA", "AVAX", "LINK", "LTC", "TRX"]
TFS = ["2h", "30m"]
START_MS = int(pd.Timestamp("2019-01-01", tz="UTC").timestamp() * 1000)
COLS = ["date", "open", "high", "low", "close", "volume"]
GAP = 1.3
WEIGHT_CAP = 1400


def fetch(sess: requests.Session, symbol: str, tf: str) -> pd.DataFrame | None:
    rows: list[list] = []
    cur = START_MS
    while True:
        batch = None
        for attempt in range(6):
            try:
                r = sess.get(BASE, params={"symbol": f"{symbol}USDT", "interval": tf,
                                           "startTime": cur, "limit": 1500}, timeout=40)
                if r.status_code in (418, 429):
                    time.sleep(65)
                    continue
                if r.status_code == 400:
                    return None
                r.raise_for_status()
                batch = r.json()
                if int(r.headers.get("X-MBX-USED-WEIGHT-1M", 0) or 0) > WEIGHT_CAP:
                    time.sleep(40)
                break
            except Exception:
                time.sleep(5 * (attempt + 1))
        if not batch:
            break                      # 抓不动或抓完了，保留已有部分
        rows.extend(batch)
        nxt = int(batch[-1][0]) + 1
        if nxt <= cur or len(batch) < 1500:
            break
        cur = nxt
        time.sleep(GAP)
    if len(rows) < 1000:
        return None
    df = pd.DataFrame(rows).iloc[:, :6]
    df.columns = ["ts", "open", "high", "low", "close", "volume"]
    df["date"] = pd.to_datetime(pd.to_numeric(df["ts"]), unit="ms", utc=True)
    for c in ("open", "high", "low", "close", "volume"):
        df[c] = pd.to_numeric(df[c])
    return df[COLS].drop_duplicates("date").sort_values("date").reset_index(drop=True)


def main() -> None:
    OUT.mkdir(parents=True, exist_ok=True)
    sess = requests.Session()
    sess.proxies.update(PROXY)
    jobs = [(s, tf) for tf in TFS for s in SYMBOLS]
    print(f"[下载] {len(jobs)} 个任务，单线程 {GAP}s 间隔", flush=True)
    for i, (sym, tf) in enumerate(jobs, 1):
        path = OUT / f"{sym}_USDT_USDT-{tf}-futures.feather"
        if path.exists():
            print(f"  [{i}/{len(jobs)}] {sym} {tf} 已存在", flush=True)
            continue
        df = fetch(sess, sym, tf)
        if df is None:
            print(f"  [{i}/{len(jobs)}] {sym} {tf} 失败", flush=True)
            continue
        df.to_feather(path)
        print(f"  [{i}/{len(jobs)}] {sym} {tf} {len(df)} 根 "
              f"{df['date'].min():%Y-%m-%d}~{df['date'].max():%Y-%m-%d}", flush=True)


if __name__ == "__main__":
    sys.exit(main())