#!/usr/bin/env python3
"""Fetch Nasdaq earnings calendar (date + symbol + surprise%) for all weekdays in the DBEQ range,
for a proper PEAD test. Free, no key. Cached per date; gentle pacing + backoff.
"""
import datetime
import json
import os
import time
import urllib.request

OUT = "data/surfer/earnings"
START = datetime.date(2023, 3, 28)
END = datetime.date(2026, 5, 31)


def get(u):
    for a in range(4):
        try:
            req = urllib.request.Request(u, headers={"User-Agent": "Mozilla/5.0", "Accept": "application/json"})
            return json.loads(urllib.request.urlopen(req, timeout=25).read())
        except Exception:
            if a == 3:
                return None
            time.sleep(4 * (a + 1))
    return None


def main():
    os.makedirs(OUT, exist_ok=True)
    d = START
    n = fail = 0
    while d <= END:
        if d.weekday() < 5:
            f = f"{OUT}/{d}.json"
            if not os.path.exists(f):
                r = get(f"https://api.nasdaq.com/api/calendar/earnings?date={d}")
                if r is None:
                    fail += 1
                else:
                    rows = (r.get("data") or {}).get("rows") or []
                    json.dump([(x.get("symbol"), x.get("surprise")) for x in rows], open(f, "w"))
                    n += 1
                time.sleep(1.3)
        d += datetime.timedelta(days=1)
    print(f"DONE: fetched {n} new days, {fail} failed; cache dir {OUT}")


if __name__ == "__main__":
    main()