#!/usr/bin/env bun

/**
 * Scrape Cal-SuWers COVID Dashboard
 *
 * Uses Puppeteer to scrape the dynamic CalSuWers dashboard
 * since it's an R Shiny app that loads data via JavaScript
 */

import puppeteer from 'puppeteer';
import { writeFileSync } from 'fs';
import { join } from 'path';

const DASHBOARD_URL = 'https://skylab.cdph.ca.gov/calwws/';
const OUTPUT_PATH = join(__dirname, 'latest-dashboard-data.json');

async function scrapeDashboard() {
  console.log('🌐 Launching browser...\n');

  const browser = await puppeteer.launch({
    headless: true,
    args: ['--no-sandbox', '--disable-setuid-sandbox']
  });

  try {
    const page = await browser.newPage();

    console.log('📡 Navigating to CalSuWers dashboard...\n');
    await page.goto(DASHBOARD_URL, {
      waitUntil: 'networkidle2',
      timeout: 60000
    });

    // Wait for Shiny app to load
    console.log('⏳ Waiting for dashboard data to load...\n');
    await page.waitForTimeout(5000);

    // Extract data from the page
    const data = await page.evaluate(() => {
      // This will need to be customized based on the actual dashboard structure
      // Look for specific elements that contain the data

      const result: any = {
        scrapedAt: new Date().toISOString(),
        url: window.location.href
      };

      // Try to find the latest update date
      const updateDateElement = document.querySelector('[data-testid="last-update"]') ||
                               Array.from(document.querySelectorAll('*')).find(el =>
                                 el.textContent?.includes('Last update') ||
                                 el.textContent?.includes('October')
                               );

      if (updateDateElement) {
        result.lastUpdate = updateDateElement.textContent?.trim();
      }

      // Try to find California statewide data
      const dataElements = document.querySelectorAll('.value, .metric, [class*="data"]');
      result.elements = Array.from(dataElements).map(el => ({
        className: el.className,
        text: el.textContent?.trim()
      }));

      // Get all text content for analysis
      result.bodyText = document.body.innerText;

      return result;
    });

    console.log('✅ Dashboard data extracted\n');

    // Save raw scraped data
    writeFileSync(OUTPUT_PATH, JSON.stringify(data, null, 2));
    console.log(`📁 Raw data saved to: ${OUTPUT_PATH}\n`);

    // Print summary
    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━');
    console.log('📊 DASHBOARD SCRAPE COMPLETE');
    console.log('━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n');

    if (data.lastUpdate) {
      console.log(`📅 Last Update: ${data.lastUpdate}`);
    }
    console.log(`📁 Data file: ${OUTPUT_PATH}\n`);
    console.log('⚠️  This is a raw scrape - manual parsing may be needed\n');

  } catch (error) {
    console.error('❌ Error scraping dashboard:', error);
    throw error;
  } finally {
    await browser.close();
  }
}

scrapeDashboard().catch(error => {
  console.error('Failed to scrape dashboard:', error);
  process.exit(1);
});