#!/usr/bin/env python3
"""Point-in-time crypto fetch: broad live universe + KNOWN-DEAD perps, WITH volume.

For a survivorship-free test: delisted Binance perps still return klines up to delisting,
so including them lets a date-by-date "top-N by trailing dollar-volume" universe contain
dead coins while they traded and drop them when they die. Saves day, close, qvol, funding
to data/surfer/crypto_pit/ (gitignored).
"""
import json
import os
import time
import urllib.request

import numpy as np

OUT = "data/surfer/crypto_pit"
DAY_MS = 86_400_000
TOP_N = 120
# famous delisted / dead Binance USDT perps (the survivorship risk); klines available post-delist
DEAD = ["LUNAUSDT", "ANCUSDT", "SRMUSDT", "HNTUSDT", "MATICUSDT", "FTTUSDT", "RAYUSDT",
        "WAVESUSDT", "BNXUSDT", "SCUSDT", "OCEANUSDT", "AGIXUSDT", "CVCUSDT", "TLMUSDT",
        "DENTUSDT", "KEYUSDT", "CTKUSDT", "TOMOUSDT", "AKROUSDT", "BLZUSDT", "COMBOUSDT",
        "FTMUSDT", "DGBUSDT", "REEFUSDT", "SLPUSDT", "IDEXUSDT", "LINAUSDT", "NEBLUSDT",
        "RADUSDT", "BTSUSDT", "STMXUSDT", "MDTUSDT", "AMBUSDT", "GTCUSDT", "DARUSDT"]


def get(url):
    try:
        return json.load(urllib.request.urlopen(urllib.request.Request(url, headers={"User-Agent": "curl/8"}), timeout=30))
    except Exception:
        return None


def universe(n):
    info = get("https://fapi.binance.com/fapi/v1/exchangeInfo")
    perps = {s["symbol"] for s in info["symbols"]
             if s.get("contractType") == "PERPETUAL" and s.get("quoteAsset") == "USDT" and s.get("status") == "TRADING"}
    tick = get("https://fapi.binance.com/fapi/v1/ticker/24hr")
    vol = {t["symbol"]: float(t["quoteVolume"]) for t in tick if t["symbol"] in perps}
    return sorted(vol, key=lambda s: -vol[s])[:n]


def klines(sym):
    out, end = [], None
    for _ in range(20):
        u = f"https://fapi.binance.com/fapi/v1/klines?symbol={sym}&interval=1d&limit=1500"
        if end:
            u += f"&endTime={end}"
        k = get(u)
        if not k:
            break
        out = k + out
        end = k[0][0] - 1
        if len(k) < 1500:
            break
        time.sleep(0.15)
    d = {int(r[0]): (float(r[4]), float(r[7])) for r in out}  # close, quote-volume
    days = np.array(sorted(d))
    cl = np.array([d[t][0] for t in days]); qv = np.array([d[t][1] for t in days])
    return days // DAY_MS, cl, qv


def funding(sym, start_ms):
    out, st = [], start_ms
    for _ in range(80):
        f = get(f"https://fapi.binance.com/fapi/v1/fundingRate?symbol={sym}&startTime={st}&limit=1000")
        if not f:
            break
        out += f
        st = f[-1]["fundingTime"] + 1
        if len(f) < 1000:
            break
        time.sleep(0.12)
    daily = {}
    for r in out:
        daily.setdefault(int(r["fundingTime"]) // DAY_MS, 0.0)
        daily[int(r["fundingTime"]) // DAY_MS] += float(r["fundingRate"])
    return daily


def main():
    os.makedirs(OUT, exist_ok=True)
    syms = sorted(set(universe(TOP_N)) | set(DEAD))
    ok = 0
    for sym in syms:
        outp = f"{OUT}/{sym}.npz"
        if os.path.exists(outp):
            ok += 1; continue
        kd, cl, qv = klines(sym)
        if len(kd) < 200:
            print(f"  {sym}: short/none ({len(kd)}d), skip"); continue
        fmap = funding(sym, int(kd.min()) * DAY_MS)
        fund = np.array([fmap.get(int(d), 0.0) for d in kd])
        np.savez(outp, day=kd, close=cl, qvol=qv, funding=fund)
        alive = "DEAD" if qv[-30:].mean() == 0 else "live"
        print(f"  {sym}: {len(kd)}d ({kd.min()}..{kd.max()}) {alive}")
        ok += 1
        time.sleep(0.2)
    print(f"DONE: {ok}/{len(syms)} -> {OUT}/")


if __name__ == "__main__":
    main()