screenclipper/apps/api-daemon/src/youtubePolling.ts

import { execFile } from "node:child_process";
import { promisify } from "node:util";
import { prisma } from "@streamclipper/db";
import { env } from "./env";
import { streamIngestQueue } from "./queues";
import { sendTelegramMessage } from "./telegram";
import { ytdlpAntiBotArgs } from "./ytdlpCookies";

const execFileAsync = promisify(execFile);

/**
 * Live detection failures are kept per channel and surfaced via GET /status
 * for debugging. `at` lets the panel show how stale an error is — a message
 * on its own doesn't say whether it's from the last poll or from hours ago
 * before the channel started passing again.
 */
export interface PollError {
  message: string;
  at: string;
}
export const lastPollErrors = new Map<string, PollError>();

/** Non-error outcomes yt-dlp still reports as a non-zero exit — not worth surfacing as a scary error badge in the panel. */
const BENIGN_POLL_MESSAGE = /is not currently live|will begin in/;

/**
 * A few approaches were tried before landing here:
 *  - A naive regex over the channel /live page HTML grabbed the FIRST
 *    "videoId" anywhere on the page — one of dozens of unrelated ids
 *    (channel video list, recommendations), not the live broadcast.
 *  - Scoping to the page's `videoDetails` object fixed that, but turned out
 *    unreliable for a different reason: YouTube doesn't always embed the
 *    player response server-side (confirmed on a clean, unflagged IP) — the
 *    field is sometimes just absent regardless of bot-check status.
 *  - yt-dlp's own extractor doesn't have that inconsistency (it resolves the
 *    live video correctly every time it isn't blocked), so the check is
 *    back on yt-dlp — this time with every anti-bot layer combined:
 *    authenticated cookies, the bgutil PO-token provider, and a clean
 *    residential/ISP proxy (the Coolify server's own IP got flagged from a
 *    day of heavy testing). No `-f` format selector here — resolving
 *    downloadable formats is a separate, heavier check only needed later,
 *    in the actual capture. `--js-runtimes node` (the n-challenge/EJS
 *    solver) is included too — some channels return "The page needs to be
 *    reloaded" on the plain metadata fetch too, not just format resolution.
 */
async function notifyIfEnabled(key: string, text: string): Promise<void> {
  const setting = await prisma.appSetting.findUnique({ where: { key } });
  if (setting?.value !== "false") await sendTelegramMessage(text);
}

async function findLiveVideoId(channelId: string, channelName: string): Promise<string | null> {
  const liveUrl = `https://www.youtube.com/channel/${channelId}/live`;

  try {
    const { stdout } = await execFileAsync(
      "yt-dlp",
      [
        "--simulate",
        "--no-warnings",
        "--js-runtimes",
        "node",
        ...(await ytdlpAntiBotArgs()),
        "--print",
        "%(id)s",
        liveUrl,
      ],
      { timeout: 20_000 },
    );
    // Only worth a "recovered" message if it was actually failing before —
    // this runs on every successful poll, most of which were never broken.
    if (lastPollErrors.has(channelId)) {
      lastPollErrors.delete(channelId);
      await notifyIfEnabled("notify_poll_error", `✅ *${channelName}* canlı-tespiti tekrar çalışıyor.`);
    }
    const videoId = stdout.trim().split("\n")[0];
    return videoId || null;
  } catch (err) {
    const message = err instanceof Error ? err.message : String(err);
    // yt-dlp reports "not live" / "starts in N minutes" as a non-zero exit
    // too — normal, expected outcomes, not failures worth a red badge.
    if (!BENIGN_POLL_MESSAGE.test(message)) {
      // Alert only on the transition into failing — not every 60s poll
      // while it stays broken, or this would spam constantly.
      const wasAlreadyFailing = lastPollErrors.has(channelId);
      lastPollErrors.set(channelId, { message: message.slice(0, 500), at: new Date().toISOString() });
      if (!wasAlreadyFailing) {
        await notifyIfEnabled(
          "notify_poll_error",
          `⚠️ *${channelName}* canlı-tespiti başarısız oluyor:\n\`${message.slice(0, 300)}\``,
        );
      }
    } else {
      lastPollErrors.delete(channelId);
    }
    return null;
  }
}

/**
 * Shared by the automatic poll loop and the panel's manual "force-start"
 * action — both just need a channel + a URL to begin capturing. A no-op if
 * that channel already has an open session (covers both callers: the poll
 * loop re-checking a channel it's already recording, and someone hitting
 * force-start on a channel that's already live).
 */
export async function startCaptureSession(
  channel: { id: string; name: string; segmentTimeSec?: number | null },
  youtubeUrl: string,
  liveVideoId: string | null = null,
): Promise<{ started: boolean }> {
  const existing = await prisma.streamSession.findFirst({
    where: { channelId: channel.id, endedAt: null },
  });
  if (existing) return { started: false };

  const session = await prisma.streamSession.create({
    data: { channelId: channel.id, liveVideoId },
  });

  await streamIngestQueue.add("start-capture", {
    sessionId: session.id,
    channelDbId: channel.id,
    youtubeUrl,
    segmentTimeSec: channel.segmentTimeSec ?? undefined,
  });

  await notifyIfEnabled("notify_stream_start", `🔴 *${channel.name}* canlıya geçti, kayıt başlatılıyor.`);
  console.log(`[youtube-polling] started session ${session.id} for channel ${channel.name}`);
  return { started: true };
}

/** Runs the live-check for a single channel and applies its result — the unit both `pollOnce` and the panel's manual "şimdi kontrol et" action reuse. */
export async function checkChannel(channel: {
  id: string;
  name: string;
  channelId: string;
  segmentTimeSec?: number | null;
}): Promise<{
  liveVideoId: string | null;
  error: PollError | null;
}> {
  const liveVideoId = await findLiveVideoId(channel.channelId, channel.name);
  await prisma.channel.update({
    where: { id: channel.id },
    data: { lastCheckedAt: new Date() },
  });

  if (liveVideoId) {
    await startCaptureSession(channel, `https://www.youtube.com/watch?v=${liveVideoId}`, liveVideoId);
  }

  return { liveVideoId, error: lastPollErrors.get(channel.channelId) ?? null };
}

export async function pollOnce(): Promise<void> {
  const channels = await prisma.channel.findMany({ where: { isActive: true } });

  for (const channel of channels) {
    try {
      await checkChannel(channel);
    } catch (err) {
      console.error(`[youtube-polling] error polling channel ${channel.name}:`, err);
    }
  }
}

const POLL_INTERVAL_SETTING_KEY = "poll_interval_ms";

async function getPollIntervalMs(): Promise<number> {
  const setting = await prisma.appSetting.findUnique({ where: { key: POLL_INTERVAL_SETTING_KEY } });
  const parsed = setting ? Number(setting.value) : NaN;
  return Number.isFinite(parsed) && parsed >= 5_000 ? parsed : env.pollIntervalMs;
}

/**
 * Self-rescheduling instead of setInterval so a panel-side change to the
 * poll_interval_ms AppSetting (read fresh on every iteration, same pattern
 * as ytdlpAntiBotArgs()'s cookies) takes effect on the very next cycle
 * without a redeploy.
 */
export function startPollingLoop(): void {
  let stopped = false;

  async function tick() {
    if (stopped) return;
    await pollOnce().catch((err) => console.error("[youtube-polling] poll failed:", err));
    const intervalMs = await getPollIntervalMs().catch(() => env.pollIntervalMs);
    if (!stopped) setTimeout(tick, intervalMs);
  }

  getPollIntervalMs()
    .then((ms) => console.log(`[youtube-polling] polling every ${ms}ms`))
    .catch(() => {});
  tick();
}