# LottoEdge FL — Python Scraper
# pip install requests beautifulsoup4 selenium pandas schedule

import requests, json, time, schedule, logging
from datetime import datetime
from bs4 import BeautifulSoup
import pandas as pd

logging.basicConfig(level=logging.INFO, format='%(asctime)s %(message)s')

BASE_URL = "https://floridalottery.com"
GAME_IDS = [1555,1562,1590,1594,1597,1604,1606,
            1608,1618,1619,1620,1621,1622,1623,1627]
HEADERS = {"User-Agent": "LottoEdge/1.0 (educational research)"}

def scrape_game(game_id: int) -> dict:
    url = f"{BASE_URL}/games/scratch-offs/view?id={game_id}"
    r = requests.get(url, headers=HEADERS, timeout=10)
    r.raise_for_status()
    soup = BeautifulSoup(r.text, "html.parser")

    prizes = []
    for row in soup.select("table tr"):
        cells = row.find_all("td")
        if len(cells) < 3: continue
        prize_str = cells[0].get_text().replace("$","").replace(",","").strip()
        odds_str  = cells[1].get_text().replace(",","").strip()
        rem_str   = cells[2].get_text().strip()
        try:
            rem, total = [int(x.replace(",","")) for x in rem_str.split(" of ")]
            odds_val = int(odds_str.split("-in-")[-1])
            prizes.append({"prize": int(prize_str), "odds": odds_val, "rem": rem, "total": total})
        except: continue

    return {"game_id": game_id, "prizes": prizes,
            "scraped_at": datetime.utcnow().isoformat()}

def calc_ev(game: dict) -> float:
    return sum(p["prize"] * (1/p["odds"]) * (p["rem"]/p["total"]) for p in game["prizes"])

def daily_scrape():
    logging.info("Starting daily FL Lottery scrape...")
    results = {}
    for gid in GAME_IDS:
        try:
            results[gid] = scrape_game(gid)
            ev = calc_ev(results[gid])
            logging.info(f"  Game #{gid}: EV=${ev:.2f}, {len(results[gid]['prizes'])} tiers")
            time.sleep(1.5)
        except Exception as e:
            logging.error(f"  Error game #{gid}: {e}")

    fname = f"data/scratch_{int(time.time())}.json"
    with open(fname, "w") as f:
        json.dump(results, f, indent=2)
    logging.info(f"Saved {len(results)} games to {fname}")

# Schedule daily at 6 AM ET
schedule.every().day.at("06:00").do(daily_scrape)
if __name__ == "__main__":
    daily_scrape()  # run once immediately
    while True: schedule.run_pending(); time.sleep(60)

# crontab -e  — add this line for daily 6 AM ET scrape:
# 0 11 * * * cd /app && node scraper.js >> logs/scrape.log 2>&1

# GitHub Actions workflow (.github/workflows/daily-scrape.yml):
---
name: Daily FL Lottery Scrape
on:
  schedule:
    - cron: '0 11 * * *'  # 6 AM ET = 11 UTC
  workflow_dispatch:       # allow manual trigger

jobs:
  scrape:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-node@v4
        with: { node-version: '20' }
      - run: npm ci
      - run: node scraper.js
        env:
          DB_URL: ${{ secrets.DATABASE_URL }}
          WEBHOOK_URL: ${{ secrets.DISCORD_WEBHOOK }}
      - uses: actions/upload-artifact@v4
        with:
          name: scrape-data
          path: data/*.json
          retention-days: 30

# Docker Compose for full stack:
---
version: '3.8'
services:
  api:
    build: .
    ports: ["3000:3000"]
    environment:
      - DB_URL=postgresql://postgres:pass@db:5432/lottoedge
  db:
    image: postgres:16
    volumes: [pgdata:/var/lib/postgresql/data]
  scheduler:
    build: .
    command: node scheduler.js
    depends_on: [db]
volumes:
  pgdata:

// Alert system — sends Discord/Slack/Email when key events occur
const alerts = {
  // Trigger: top prize count drops (someone won!)
  topPrizeClaimed: async (gameId, prizeTier, newCount) => {
    const msg = {
      embeds: [{
        title: `🎰 TOP PRIZE CLAIMED — Game #${gameId}`,
        description: `$${prizeTier.toLocaleString()} prize won! **${newCount} remaining**`,
        color: 0xFF4D6D,
        timestamp: new Date()
      }]
    };
    await axios.post(process.env.DISCORD_WEBHOOK, msg);
  },

  // Trigger: EV crosses threshold (game becomes better value)
  evThreshold: async (gameId, ev, price) => {
    if (ev / price > 0.85) { // 85%+ return threshold
      await axios.post(process.env.SLACK_WEBHOOK, {
        text: `⚡ HIGH EV ALERT: Game #${gameId} at $${ev.toFixed(2)} EV on $${price} ticket`
      });
    }
  },

  // Daily digest email via SendGrid
  dailyDigest: async (topPlays) => {
    await sgMail.send({
      to: process.env.ALERT_EMAIL,
      from: 'alerts@lottoedge.com',
      subject: `LottoEdge Daily Brief — ${new Date().toDateString()}`,
      html: buildEmailHTML(topPlays)
    });
  }
};

// Check for changes after each scrape
async function detectChanges(prev, curr) {
  for (const [id, game] of Object.entries(curr)) {
    const p = prev[id];
    if (!p) continue;
    // Top prize claimed?
    if (p.topPrizeCount > game.topPrizeCount)
      await alerts.topPrizeClaimed(id, game.topPrize, game.topPrizeCount);
    // EV improvement?
    await alerts.evThreshold(id, calcEV(game), game.price);
  }
}