Add video poster frames and rework the media status row

media-scrape/src/download.ts

@@ -5,7 +5,7 @@
 
 import { execFile } from "node:child_process";
 import { createHash } from "node:crypto";
-import { writeFileSync } from "node:fs";
+import { readFileSync, renameSync, rmSync, writeFileSync } from "node:fs";
 import { join } from "node:path";
 import { promisify } from "node:util";
 import type { MediaRow } from "./store.js";
@@ -228,6 +228,54 @@ export async function downloadPreview(
     }
 }
 
+/**
+ * Grab a poster frame from a downloaded video with ffmpeg.
+ * Discord has no server-side thumbnails for uploaded videos, so the archive makes its own.
+ */
+export async function videoPoster(
+    inputPath: string,
+    outDir: string,
+    ffmpeg = process.env.VESKSLOP_FFMPEG ?? "ffmpeg"
+): Promise<{ hash: string; bytes: number } | null> {
+    const temp = join(outDir, `.poster-${Date.now()}-${Math.random().toString(16).slice(2)}.webp`);
+
+    try {
+        await execFileAsync(
+            ffmpeg,
+            [
+                "-v",
+                "error",
+                "-y",
+                "-ss",
+                "0.5",
+                "-i",
+                inputPath,
+                "-frames:v",
+                "1",
+                "-vf",
+                "scale=480:-1",
+                temp
+            ],
+            { timeout: 30_000 }
+        );
+
+        const buffer = readFileSync(temp);
+        if (!buffer.length) return null;
+
+        const hash = createHash("sha256").update(buffer).digest("hex");
+        renameSync(temp, join(outDir, `${hash}.webp`));
+        return { hash, bytes: buffer.length };
+    } catch {
+        return null;
+    } finally {
+        try {
+            rmSync(temp, { force: true });
+        } catch {
+            // already renamed
+        }
+    }
+}
+
 /** The gap before the next file, in milliseconds. */
 export function downloadGapMs(options: DownloadOptions = {}): number {
     const min = options.minGapMs ?? 1000;

media-scrape/src/engine.ts

@@ -10,6 +10,7 @@ import {
     downloadOne,
     downloadPreview,
     probeDimensions,
+    videoPoster,
     type DownloadOptions
 } from "./download.js";
 import {
@@ -324,6 +325,14 @@ export class ScrapeEngine {
                     );
                     if (dimensions) store.updateDimensions(row.id, dimensions.width, dimensions.height);
                 }
+
+                if (row.kind === "video" && !row.preview_hash) {
+                    const poster = await videoPoster(join(targetDir, outcome.path), join(dir, "thumbs"));
+                    if (poster) {
+                        store.markPreview(row.id, poster);
+                        meta.previewed = (meta.previewed ?? 0) + 1;
+                    }
+                }
             } else {
                 store.markDownloadError(row.id, outcome.error ?? outcome.state);
                 if (outcome.state === "failed") meta.downloadErrors = (meta.downloadErrors ?? 0) + 1;

media-scrape/src/index.ts

@@ -19,6 +19,8 @@ export {
     downloadOne,
     downloadPreview,
     previewUrlFor,
+    probeDimensions,
+    videoPoster,
     type DownloadOptions,
     type DownloadOutcome
 } from "./download.js";

media-scrape/test/run.ts

@@ -4,11 +4,12 @@
  */
 
 import assert from "node:assert/strict";
+import { execFileSync } from "node:child_process";
 import { createHash } from "node:crypto";
 import { existsSync, mkdirSync, mkdtempSync, rmSync } from "node:fs";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
-import { downloadOne, downloadPreview, previewUrlFor } from "../src/download.js";
+import { downloadOne, downloadPreview, previewUrlFor, videoPoster } from "../src/download.js";
 import { ScrapeEngine, type FetchPage, type ScrapeBackend } from "../src/engine.js";
 import { extractMedia } from "../src/extract.js";
 import { PuppetBackend } from "../src/puppet-backend.js";
@@ -711,6 +712,33 @@ void (async () => {
         store.close();
     });
 
+    await test("videoPoster extracts a cached frame", async () => {
+        const dir = join(root, "poster-test");
+        mkdirSync(dir, { recursive: true });
+        const videoPath = join(dir, "clip.mp4");
+
+        try {
+            execFileSync("ffmpeg", [
+                "-v",
+                "error",
+                "-y",
+                "-f",
+                "lavfi",
+                "-i",
+                "testsrc=duration=1:size=64x64:rate=5",
+                videoPath
+            ]);
+        } catch {
+            console.log("ok - videoPoster skipped (no ffmpeg)");
+            return;
+        }
+
+        const poster = await videoPoster(videoPath, dir);
+        assert.ok(poster?.hash);
+        assert.ok((poster?.bytes ?? 0) > 0);
+        assert.equal(existsSync(join(dir, `${poster?.hash}.webp`)), true);
+    });
+
     await test("snowflake helpers round-trip dates", () => {
         const id = snowflakeFromIso("2026-09-16T00:00:00.000Z");
         assert.ok(id);