v3: localization fixes, char counters & limits on all text fields, ux fixes

api/services/providers/generic.ts

@@ -1,6 +1,14 @@
 import type { RichContent } from "../../model/interfaces.ts";
 import type { RichContentProvider } from "../rich-content-service.ts";
-import { extractOgTag, fetchWithTimeout } from "../rich-content-service.ts";
+import {
+  extractBestIcon,
+  extractJsonLd,
+  extractLargeImage,
+  extractMetaName,
+  extractOgTag,
+  extractPageTitle,
+  fetchWithTimeout,
+} from "../rich-content-service.ts";
 
 export const genericProvider: RichContentProvider = {
   name: "generic",
@@ -18,14 +26,39 @@ export const genericProvider: RichContentProvider = {
     }
 
     const html = await res.text();
+    const ld = extractJsonLd(html);
+
+    // Title: og:title → twitter:title → JSON-LD → <title>
+    const title = extractOgTag(html, "title") ??
+      extractMetaName(html, "twitter:title") ??
+      ld.title ??
+      extractPageTitle(html);
+
+    // Description: og:description → twitter:description → JSON-LD → <meta name="description">
+    const description = extractOgTag(html, "description") ??
+      extractMetaName(html, "twitter:description") ??
+      ld.description ??
+      extractMetaName(html, "description");
+
+    // Image: og:image → twitter:image → JSON-LD → first large <img> → best icon → /favicon.ico
+    const thumbnailUrl = extractOgTag(html, "image") ??
+      extractMetaName(html, "twitter:image") ??
+      ld.thumbnailUrl ??
+      extractLargeImage(html, url) ??
+      extractBestIcon(html, url) ??
+      `${new URL(url).origin}/favicon.ico`;
+
+    // Site name: og:site_name → hostname
+    const siteName = extractOgTag(html, "site_name") ??
+      new URL(url).hostname.replace(/^www\./, "");
 
     return {
       type: "generic",
       url,
-      title: extractOgTag(html, "title"),
-      description: extractOgTag(html, "description"),
-      thumbnailUrl: extractOgTag(html, "image"),
-      siteName: extractOgTag(html, "site_name"),
+      title,
+      description,
+      thumbnailUrl,
+      siteName,
     };
   },
 };