javis_bot/bot/scripts/stream-test/browse-search.mjs

// Browser action core. Prefers the on-screen Chrome (CDP at CDP_PORT, default
// 9222) so the action is visible on the Go-Live broadcast, and prints a JSON
// result on stdout for the Python `browseAndSearch` tool to wrap.
//
//   node browse-search.mjs "<query>" [search|youtube]
//
// - search  : Google-search the query, return the top organic results.
// - youtube : search YouTube and play the first result.
//
// When no broadcast Chrome is reachable on CDP (e.g. a plain text conversation
// with no active broadcast), `search` falls back to a headless Chromium we
// launch ourselves, so browser-based Google search still works at zero API
// cost. `youtube` only makes sense on the visible broadcast Chrome, so it never
// uses the headless fallback.
import { chromium } from 'playwright';

const CDP = process.env.CDP_PORT || '9222';
// Use 127.0.0.1, not "localhost": in containers localhost can resolve to IPv6
// (::1) first while Chrome's CDP listens on IPv4, giving ECONNREFUSED ::1.
const CDP_HOST = process.env.CDP_HOST || '127.0.0.1';
const query = process.argv[2] || '';
const mode = (process.argv[3] || 'search').toLowerCase();
const out = (o) => { process.stdout.write(JSON.stringify(o)); };

if (!query) { out({ ok: false, error: 'no query' }); process.exit(1); }

let browser;          // playwright Browser: connected (CDP) or launched (headless)
let launched = false; // true when we launched our own headless browser
let page;

// Acquire a page from the broadcast Chrome over CDP, or — for search mode only —
// from a headless Chromium we launch when no broadcast Chrome is reachable.
async function acquirePage() {
  try {
    browser = await chromium.connectOverCDP(`http://${CDP_HOST}:${CDP}`);
    const ctx = browser.contexts()[0];
    page = ctx.pages()[0] || (await ctx.newPage());
    return;
  } catch (e) {
    // YouTube playback must be on the visible broadcast Chrome; no fallback.
    if (mode === 'youtube') throw e;
  }
  // Prefer the system Chrome the host already has (channel: 'chrome') so the
  // fallback needs no extra Playwright browser download; degrade to Playwright's
  // bundled chromium if no system Chrome is installed.
  launched = true;
  let launchErr;
  for (const opts of [{ headless: true, channel: 'chrome' }, { headless: true }]) {
    try {
      browser = await chromium.launch(opts);
      break;
    } catch (e) {
      launchErr = e;
      browser = undefined;
    }
  }
  if (!browser) throw launchErr;
  const ctx = await browser.newContext({
    locale: 'ko-KR',
    userAgent:
      'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 ' +
      '(KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',
  });
  page = await ctx.newPage();
}

try {
  await acquirePage();
  page.setDefaultTimeout(20000);
  await page.bringToFront().catch(() => {});

  if (mode === 'youtube') {
    await page.goto(`https://www.youtube.com/results?search_query=${encodeURIComponent(query)}`, { waitUntil: 'domcontentloaded' });
    await page.waitForSelector('ytd-video-renderer a#video-title, a#video-title', { timeout: 20000 });
    const first = page.locator('ytd-video-renderer a#video-title, a#video-title').first();
    const title = (await first.getAttribute('title').catch(() => '')) || (await first.innerText().catch(() => ''));
    await first.click();
    await page.waitForSelector('#movie_player', { timeout: 20000 });
    await page.evaluate(() => { const v = document.querySelector('video'); if (v && v.paused) v.play(); });
    out({ ok: true, mode, title: (title || '').trim(), url: page.url() });
  } else {
    await page.goto(`https://www.google.com/search?q=${encodeURIComponent(query)}&hl=ko`, { waitUntil: 'domcontentloaded' });
    await page.waitForTimeout(1500);
    // Google serves its bot-detection interstitial (/sorry/index) to sessions it
    // suspects are automated. Detect it structurally (by URL, locale-independent)
    // and fail fast so the Python caller fail-opens to the DDG cascade instead of
    // treating an empty challenge page as "no results".
    if (page.url().includes('/sorry/')) {
      await browser.close();
      out({ ok: false, error: 'google-bot-challenge', headless: launched });
      process.exit(1);
    }
    const results = await page.evaluate(() => {
      const seen = new Set();
      const items = [];
      for (const h of Array.from(document.querySelectorAll('a h3'))) {
        const a = h.closest('a');
        const url = a?.href || '';
        if (!url || seen.has(url) || url.includes('google.com')) continue;
        const block = h.closest('div[data-hveid], div.g') || a.parentElement;
        let snippet = '';
        const sn = block?.querySelector('div[data-sncf], div[style*="webkit-line-clamp"], .VwiC3b');
        snippet = (sn?.innerText || '').trim();
        seen.add(url);
        items.push({ title: h.innerText.trim(), url, snippet });
        if (items.length >= 6) break;
      }
      return items;
    });
    out({ ok: true, mode, query, count: results.length, results, headless: launched });
  }
  await browser.close();
} catch (e) {
  try { await browser?.close(); } catch { /* ignore */ }
  out({ ok: false, error: String(e?.message || e) });
  process.exit(1);
}