#!/usr/bin/env python3
"""HKS-CBF + FIBA LiveStats basketball harvester."""
import sys, re
sys.path.insert(0, '/opt/pgz-sport/scripts/sport_harvesters')
from __base import SportHarvester

class HKSHarvester(SportHarvester):
    SPORT = 'košarka'
    SOURCE = 'hks_cbf'
    
    def scrape_klub(self, page, klub):
        # Discovery: try search hks-cbf.hr by club name
        url = f"https://www.hks-cbf.hr/?s={klub['naziv'].replace(' ','+')}"
        self.log(f"  🏀 Klub {klub['id']} {klub['naziv']} → {url}")
        try:
            page.goto(url, wait_until="domcontentloaded", timeout=20000)
            # Look for /klubovi/ or /klub/ link
            klub_links = page.locator('a[href*="/klubovi/"], a[href*="/klub/"]').all()
            for a in klub_links[:3]:
                href = a.get_attribute('href')
                if href and 'klub' in href:
                    self.log(f"    Found: {href}")
                    # Save URL to klub
                    with self.conn.cursor() as cur:
                        cur.execute("UPDATE pgz_sport.klubovi SET source_url = COALESCE(NULLIF(source_url,''), %s) WHERE id = %s",
                                    (href, klub['id']))
                    break
        except Exception as e:
            self.log(f"    ❌ {e}")

if __name__ == '__main__':
    HKSHarvester().run(limit=int(sys.argv[1]) if len(sys.argv) > 1 else 50)