v4: link previews are read once, in one place, and no longer take an error page, a relative image or a mask icon for the page's — each provider fetched its page and scanned it with regular expressions of its own, the generic one some fifteen times, and Bandcamp and SoundCloud read only OG tags. fetchPage (remote/fetch.ts) now fetches every page, follows redirects to the address it was served from, and refuses an error status, so a 404 or a bot challenge is unreachable rather than a preview titled "Just a moment...", and a refresh no longer overwrites good metadata with it. parsePage (remote/html.ts) reads it in one linear pass with a real attribute reader: unquoted values, a > inside quotes, og: tags under name as well as property, and nothing from comments or scripts. Every URL a page names is resolved against where it was served from, so a relative og:image works; entities are decoded in one pass, &eacute; and &rsquo; included, and one that names no character no longer fails the preview (bandcamp-tralbum.ts shares the decoder). The mask icon is no longer the favicon, JSON-LD prefers the page's node over the site's, tracking pixels and lazy placeholders aren't thumbnails, an og:url with a slug keeps the OG tags, and a <title> loses its site suffix. genericPreview is the base of the Bandcamp, SoundCloud and YouTube channel previews; SoundCloud takes www., m. and on.soundcloud.com short links, embedding the page they lead to, and Bandcamp keeps only its own player. The service tidies every preview: text on one line, titles and descriptions capped, only http(s) images and players. RichContent.type is now RichContentType, and the unused videoId is gone.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

api/test/remote/providers/soundcloud.test.ts

@@ -1,16 +1,69 @@
 import { html, stubNetwork } from "../../helpers.ts";
-import { assertEquals, assertStringIncludes } from "@std/assert";
+import { assert, assertEquals, assertFalse } from "@std/assert";
 import { fetchRichContent } from "../../../services/rich-content-service.ts";
+import { soundcloudProvider } from "../../../remote/providers/soundcloud.ts";
+
+const embedOf = (url: string) =>
+  `https://w.soundcloud.com/player/?url=${
+    encodeURIComponent(url)
+  }&visual=true&auto_play=false`;
 
 Deno.test("soundcloud provider", async () => {
   using _ = stubNetwork(() =>
-    html(`<meta property="og:title" content="Album">
-          <meta property="og:video" content="https://bandcamp.com/EmbeddedPlayer/album=1">`)
+    html(`<meta property="og:title" content="Track">
+          <meta property="og:image" content="https://i1.sndcdn.com/a.jpg">
+          <meta name="description" content="Listen to Track">`)
   );
   const sc = await fetchRichContent("https://soundcloud.com/artist/track");
   assertEquals(sc?.type, "soundcloud");
-  assertStringIncludes(
-    sc?.embedUrl ?? "",
-    encodeURIComponent("https://soundcloud.com/artist/track"),
+  assertEquals(sc?.siteName, "SoundCloud");
+  assertEquals(sc?.title, "Track");
+  assertEquals(sc?.description, "Listen to Track");
+  assertEquals(sc?.embedUrl, embedOf("https://soundcloud.com/artist/track"));
+});
+
+Deno.test("soundcloud provider: a short link embeds the page it leads to", async () => {
+  using _ = stubNetwork((url) =>
+    url.hostname === "on.soundcloud.com"
+      ? new Response(null, {
+        status: 302,
+        headers: {
+          location: "https://m.soundcloud.com/artist/track?si=abc&utm_source=x",
+        },
+      })
+      : html(`<meta property="og:title" content="Track">`)
+  );
+  const sc = await fetchRichContent("https://on.soundcloud.com/AbCd");
+  assertEquals(sc?.type, "soundcloud");
+  assertEquals(sc?.url, "https://on.soundcloud.com/AbCd");
+  assertEquals(sc?.embedUrl, embedOf("https://soundcloud.com/artist/track"));
+});
+
+Deno.test("soundcloud provider: the page's og:url names what is embedded", async () => {
+  using _ = stubNetwork(() =>
+    html(
+      `<meta property="og:url" content="https://soundcloud.com/artist/real">`,
+    )
+  );
+  const sc = await fetchRichContent("https://soundcloud.com/artist/real?in=x");
+  assertEquals(sc?.embedUrl, embedOf("https://soundcloud.com/artist/real"));
+});
+
+Deno.test("soundcloud provider: SoundCloud's hosts only", () => {
+  for (
+    const url of [
+      "https://soundcloud.com/a/t",
+      "https://www.soundcloud.com/a/t",
+      "https://m.soundcloud.com/a/t",
+      "https://on.soundcloud.com/AbCd",
+    ]
+  ) {
+    assert(soundcloudProvider.matches(url), url);
+  }
+  assertFalse(
+    soundcloudProvider.matches("https://soundcloud.com.evil.example/"),
+  );
+  assertFalse(
+    soundcloudProvider.matches("https://api.soundcloud.com/tracks/1"),
   );
 });