#!/usr/bin/env python3
import json
import re
import urllib.request
from datetime import datetime, timezone
from pathlib import Path

REG_PATH = Path('/home/szmyt/.openclaw/workspace/domain-panel/data/registrars.json')
TIMEOUT = 8

MONEY_RE = re.compile(r'(\d{1,4}(?:[\.,]\d{1,2})?)\s*(zł|pln|eur|€|usd|\$)', re.IGNORECASE)

REGISTER_HINTS = ["rejestr", "rejestracja", "new", "first year", "1 rok", "1 rok"]
RENEW_HINTS = ["odnow", "renew", "renewal", "kolejny", "next year", "2 rok"]


def fetch_text(url: str) -> str:
    req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 DomainHunterBot/1.0"})
    with urllib.request.urlopen(req, timeout=TIMEOUT) as resp:
        raw = resp.read()
    text = raw.decode('utf-8', errors='ignore')
    text = re.sub(r'<script[\s\S]*?</script>', ' ', text, flags=re.IGNORECASE)
    text = re.sub(r'<style[\s\S]*?</style>', ' ', text, flags=re.IGNORECASE)
    text = re.sub(r'<[^>]+>', ' ', text)
    text = re.sub(r'\s+', ' ', text)
    return text


def to_float(num: str):
    try:
        return float(num.replace(',', '.'))
    except Exception:
        return None


def find_price(text: str, tld: str, kind: str):
    hints = REGISTER_HINTS if kind == 'register' else RENEW_HINTS
    tld_token = f'.{tld.lower()}'

    # 1) szukaj okna z tld + hint
    for m in re.finditer(re.escape(tld_token), text, flags=re.IGNORECASE):
        start = max(0, m.start() - 240)
        end = min(len(text), m.end() + 240)
        chunk = text[start:end].lower()
        if any(h in chunk for h in hints):
            m2 = MONEY_RE.search(chunk)
            if m2:
                val = to_float(m2.group(1))
                if val is not None:
                    return val, chunk[:220]

    # 2) fallback: hint + cena
    for h in hints:
        for mh in re.finditer(re.escape(h), text, flags=re.IGNORECASE):
            start = max(0, mh.start() - 100)
            end = min(len(text), mh.end() + 200)
            chunk = text[start:end].lower()
            m2 = MONEY_RE.search(chunk)
            if m2:
                val = to_float(m2.group(1))
                if val is not None:
                    return val, chunk[:220]

    return None, None


def main():
    data = json.loads(REG_PATH.read_text(encoding='utf-8'))
    now = datetime.now(timezone.utc).isoformat().replace('+00:00', 'Z')

    updated_count = 0

    for reg in data.get('registrars', []):
        auto = reg.get('autoPricing', {})
        for tld in ['pl', 'com', 'ai']:
            rule = auto.get(tld)
            if not rule or not rule.get('url'):
                continue
            url = rule['url']
            try:
                text = fetch_text(url)
            except Exception as e:
                reg.setdefault('autoMeta', {})[tld] = {
                    'status': 'error',
                    'error': str(e),
                    'checkedAt': now,
                    'url': url,
                }
                continue

            pricing = reg.setdefault('pricing', {}).setdefault(tld, {'register': None, 'renew': None})
            reg_val, reg_ctx = find_price(text, tld, 'register')
            ren_val, ren_ctx = find_price(text, tld, 'renew')

            if reg_val is not None:
                pricing['register'] = reg_val
                updated_count += 1
            if ren_val is not None:
                pricing['renew'] = ren_val
                updated_count += 1

            reg.setdefault('autoMeta', {})[tld] = {
                'status': 'ok',
                'checkedAt': now,
                'url': url,
                'registerFound': reg_val,
                'renewFound': ren_val,
                'registerContext': reg_ctx,
                'renewContext': ren_ctx,
            }

    data['updatedAt'] = now[:10]
    data['autoLastRunAt'] = now
    data['autoUpdatedFields'] = updated_count
    REG_PATH.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding='utf-8')
    print(f'OK: updated fields={updated_count}')


if __name__ == '__main__':
    main()