Files
gerbeur/api/remote/providers/bandcamp.ts
khannurien 2c3ba6ad11 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>
2026-10-09 20:46:32 +00:00

65 lines
1.9 KiB
TypeScript

/**
* Previews Bandcamp links from their page, for `rich-content-service.ts`.
*
* @module
*/
import type { RichContent } from "../../../shared/dump.ts";
import type { RichContentProvider } from "./provider.ts";
import { parsePage } from "../html.ts";
import { fetchPage } from "../fetch.ts";
import { BANDCAMP_HOST_RE } from "../bandcamp-tralbum.ts";
import { genericPreview } from "./generic.ts";
/**
* Returns the embed player's URL a page's `og:video` names, over https; only
* a player on bandcamp.com counts, since the frontend frames it.
*/
function embeddedPlayerUrl(raw: string | undefined): string | undefined {
if (!raw) return undefined;
try {
const url = new URL(raw);
if (
(url.protocol !== "https:" && url.protocol !== "http:") ||
url.hostname !== "bandcamp.com" ||
!url.pathname.startsWith("/EmbeddedPlayer/")
) return undefined;
url.protocol = "https:";
return url.href;
} catch {
return undefined;
}
}
/**
* Claims bandcamp.com and its subdomains, where artists have their pages, and
* takes the embed player's URL from the page's `og:video`. The native player
* fetches the page's streams itself at play time, through
* `GET /api/remote/bandcamp`.
*/
export const bandcampProvider: RichContentProvider = {
name: "bandcamp",
matches(url: string): boolean {
try {
return BANDCAMP_HOST_RE.test(new URL(url).hostname);
} catch {
return false;
}
},
async fetch(url: string): Promise<RichContent> {
const fetched = await fetchPage(url);
if (fetched.html === undefined) {
return { type: "bandcamp", siteName: "Bandcamp", url };
}
const page = parsePage(fetched.html, fetched.url);
return {
...genericPreview(page, url, fetched.url),
type: "bandcamp",
siteName: "Bandcamp",
embedUrl: embeddedPlayerUrl(page.meta("og:video")),
};
},
};