107 lines
3.1 KiB
TypeScript
107 lines
3.1 KiB
TypeScript
/**
|
||
* Previews any page no other provider claims, for `rich-content-service.ts`,
|
||
* from whatever metadata its HTML carries.
|
||
*
|
||
* @module
|
||
*/
|
||
|
||
import type { RichContent } from "../../../shared/dump.ts";
|
||
import type { RichContentProvider } from "./provider.ts";
|
||
import {
|
||
extractBestIcon,
|
||
extractFirstContentImage,
|
||
extractJsonLd,
|
||
extractLargeImage,
|
||
extractMaskIconColor,
|
||
extractMetaName,
|
||
extractOgTag,
|
||
extractPageTitle,
|
||
extractThemeColor,
|
||
normalizeCssColor,
|
||
} from "../html.ts";
|
||
import { fetchWithTimeout, readTextCapped } from "../fetch.ts";
|
||
|
||
/**
|
||
* Matches every URL, so it comes last in the service's list. Each field falls
|
||
* back from OG tags to Twitter tags, JSON-LD and the markup itself. The icon
|
||
* and brand color feed the placeholder the frontend draws when there is no
|
||
* thumbnail.
|
||
*/
|
||
export const genericProvider: RichContentProvider = {
|
||
name: "generic",
|
||
|
||
matches(_url: string): boolean {
|
||
return true;
|
||
},
|
||
|
||
async fetch(url: string): Promise<RichContent> {
|
||
const res = await fetchWithTimeout(url);
|
||
const contentType = res.headers.get("content-type") ?? "";
|
||
|
||
if (!contentType.startsWith("text/html")) {
|
||
await res.body?.cancel();
|
||
return { type: "generic", url };
|
||
}
|
||
|
||
const html = await readTextCapped(res);
|
||
const ld = extractJsonLd(html);
|
||
|
||
// An og:url naming another page (often the home page) means the OG tags
|
||
// are the site's defaults, not this page's: its title and image are
|
||
// skipped.
|
||
const ogUrl = extractOgTag(html, "url");
|
||
const useOg = !ogUrl || (() => {
|
||
try {
|
||
const ogPath = new URL(ogUrl).pathname.replace(/\/+$/, "") || "/";
|
||
const pagePath = new URL(url).pathname.replace(/\/+$/, "") || "/";
|
||
return ogPath === pagePath;
|
||
} catch {
|
||
return true;
|
||
}
|
||
})();
|
||
|
||
const title = (useOg ? extractOgTag(html, "title") : undefined) ??
|
||
extractMetaName(html, "twitter:title") ??
|
||
ld.title ??
|
||
extractPageTitle(html);
|
||
|
||
const siteName = extractOgTag(html, "site_name") ??
|
||
new URL(url).hostname.replace(/^www\./, "");
|
||
|
||
const description = extractOgTag(html, "description") ??
|
||
extractMetaName(html, "twitter:description") ??
|
||
ld.description ??
|
||
extractMetaName(html, "description");
|
||
|
||
// Never the favicon: a 16×16 icon cropped into a thumbnail looks broken,
|
||
// and the placeholder drawn instead shows the icon properly.
|
||
const thumbnailUrl = (useOg ? extractOgTag(html, "image") : undefined) ??
|
||
extractMetaName(html, "twitter:image") ??
|
||
ld.thumbnailUrl ??
|
||
extractLargeImage(html, url) ??
|
||
extractFirstContentImage(html, url);
|
||
|
||
// `/favicon.ico` is a guess. When it doesn't load, the placeholder shows
|
||
// the site's initial.
|
||
const faviconUrl = extractBestIcon(html, url) ??
|
||
`${new URL(url).origin}/favicon.ico`;
|
||
|
||
const accentColor = normalizeCssColor(
|
||
extractThemeColor(html) ??
|
||
extractMetaName(html, "msapplication-TileColor") ??
|
||
extractMaskIconColor(html),
|
||
);
|
||
|
||
return {
|
||
type: "generic",
|
||
url,
|
||
title,
|
||
description,
|
||
thumbnailUrl,
|
||
faviconUrl,
|
||
accentColor,
|
||
siteName,
|
||
};
|
||
},
|
||
};
|