Deduplicate media across scrapes and polish the viewer controls

media-scrape/src/download.ts

@@ -12,23 +12,41 @@ import type { MediaRow } from "./store.js";
 
 const execFileAsync = promisify(execFile);
 
-/** Read pixel dimensions with ffprobe. Null when the tool is missing or the file is not media. */
+/** Read dimensions and duration with ffprobe. Null when nothing usable is found. */
 export async function probeDimensions(
     path: string,
     ffprobe = process.env.VESKSLOP_FFPROBE ?? "ffprobe"
-): Promise<{ width: number; height: number } | null> {
+): Promise<{ width: number | null; height: number | null; durationSecs: number | null } | null> {
     try {
         const { stdout } = await execFileAsync(
             ffprobe,
-            ["-v", "error", "-select_streams", "v:0", "-show_entries", "stream=width,height", "-of", "json", path],
+            [
+                "-v",
+                "error",
+                "-select_streams",
+                "v:0",
+                "-show_entries",
+                "stream=width,height:format=duration",
+                "-of",
+                "json",
+                path
+            ],
             { timeout: 15_000 }
         );
-        const stream = JSON.parse(stdout)?.streams?.[0];
-        if (Number.isFinite(stream?.width) && Number.isFinite(stream?.height)) {
-            return { width: stream.width, height: stream.height };
-        }
+
+        const parsed = JSON.parse(stdout);
+        const stream = parsed?.streams?.[0];
+        const duration = Number(parsed?.format?.duration);
+
+        const width = Number.isFinite(stream?.width) ? stream.width : null;
+        const height = Number.isFinite(stream?.height) ? stream.height : null;
+        const durationSecs =
+            Number.isFinite(duration) && duration > 0 ? Math.round(duration * 10) / 10 : null;
+
+        if (width === null && height === null && durationSecs === null) return null;
+        return { width, height, durationSecs };
     } catch {
-        // missing ffprobe, a timeout, or a non-visual file
+        // missing ffprobe, a timeout, or a non-media file
     }
     return null;
 }

media-scrape/src/engine.ts

@@ -59,8 +59,10 @@ export interface ScrapeEngineOptions {
     download?: DownloadOptions;
     /** Cache Discord-hosted image previews after every walk. Default true. */
     previews?: boolean;
-    /** Read dimensions from a downloaded file. Defaults to ffprobe. */
-    probe?: (path: string) => Promise<{ width: number; height: number } | null>;
+    /** Read dimensions and duration from a downloaded file. Defaults to ffprobe. */
+    probe?: (
+        path: string
+    ) => Promise<{ width: number | null; height: number | null; durationSecs: number | null } | null>;
     /** Called when a scrape fails. */
     onError?: (scrapeId: string, message: string) => void;
 }
@@ -320,11 +322,11 @@ export class ScrapeEngine {
                 });
                 meta.downloaded = (meta.downloaded ?? 0) + 1;
 
-                if (row.width === null || row.height === null) {
-                    const dimensions = await (this.options.probe ?? probeDimensions)(
+                if (row.width === null || row.height === null || row.duration_secs === null) {
+                    const info = await (this.options.probe ?? probeDimensions)(
                         join(targetDir, outcome.path)
                     );
-                    if (dimensions) store.updateDimensions(row.id, dimensions.width, dimensions.height);
+                    if (info) store.updateMediaInfo(row.id, info);
                 }
 
                 if (row.kind === "video" && !row.preview_hash) {

media-scrape/src/extract.ts

@@ -151,7 +151,11 @@ function extractFrom(message: MediaMessage): ExtractedMedia[] {
             size: attachment.size,
             width: attachment.width,
             height: attachment.height,
-            durationSecs: attachment.durationSecs,
+            // Discord sends 0 for non-audio attachments; treat it as unknown.
+            durationSecs:
+                Number.isFinite(attachment.durationSecs) && (attachment.durationSecs as number) > 0
+                    ? attachment.durationSecs
+                    : null,
             downloaded: false,
             previewUrl: null
         });

media-scrape/src/store.ts

@@ -362,11 +362,25 @@ export class ScrapeStore {
         this.db.prepare("UPDATE media SET preview_error = ? WHERE id = ?").run(error.slice(0, 200), id);
     }
 
-    /** Fill in dimensions after a download probe. */
-    updateDimensions(id: number, width: number, height: number): void {
-        this.db
-            .prepare("UPDATE media SET width = ?, height = ?, aspect_ratio = ? WHERE id = ?")
-            .run(width, height, aspectRatioOf(width, height), id);
+    /** Fill in dimensions and duration after a download probe. */
+    updateMediaInfo(
+        id: number,
+        info: { width?: number | null; height?: number | null; durationSecs?: number | null }
+    ): void {
+        const sets: string[] = [];
+        const values: Array<number | null> = [];
+
+        if (info.width != null && info.height != null) {
+            sets.push("width = ?", "height = ?", "aspect_ratio = ?");
+            values.push(info.width, info.height, aspectRatioOf(info.width, info.height));
+        }
+        if (info.durationSecs != null) {
+            sets.push("duration_secs = ?");
+            values.push(info.durationSecs);
+        }
+
+        if (!sets.length) return;
+        this.db.prepare(`UPDATE media SET ${sets.join(", ")} WHERE id = ?`).run(...values, id);
     }
 
     /** Distinct posters with their item counts, biggest first. */

media-scrape/test/run.ts

@@ -103,7 +103,7 @@ void (async () => {
                 attachments: [
                     attachment({ filename: "cat.png", contentType: "image/png" }),
                     attachment({ filename: "loop.gif" }),
-                    attachment({ filename: "clip.mp4", contentType: "video/mp4", size: 1234 }),
+                    attachment({ filename: "clip.mp4", contentType: "video/mp4", size: 1234, durationSecs: 0 }),
                     attachment({ filename: "note.ogg", durationSecs: 3.2 })
                 ],
                 embeds: [
@@ -143,6 +143,7 @@ void (async () => {
         assert.equal(items.find(item => item.url.endsWith("/stickers/55.gif"))?.kind, "gif");
         assert.equal(items.some(item => item.url.includes("lottie")), false);
         assert.equal(items.find(item => item.kind === "audio")?.durationSecs, 3.2);
+        assert.equal(items.find(item => item.url.endsWith("clip.mp4"))?.durationSecs, null);
     });
 
     await test("extract finds media in forwarded snapshots", () => {
@@ -491,7 +492,7 @@ void (async () => {
             random: () => 0,
             log: () => {},
             previews: false,
-            probe: async () => ({ width: 1080, height: 1920 }),
+            probe: async () => ({ width: 1080, height: 1920, durationSecs: 12.3 }),
             download: {
                 fetchImpl: async () =>
                     new Response("png-bytes", { status: 200, headers: { "content-type": "image/png" } }),
@@ -509,6 +510,7 @@ void (async () => {
         assert.equal(row.width, 1080);
         assert.equal(row.height, 1920);
         assert.equal(row.aspect_ratio, 0.563);
+        assert.equal(row.duration_secs, 12.3);
         store.close();
     });