Initial commit: ReadLater v1.0

- Save articles via URL or bookmarklet
- Clean dark reader with customizable fonts/sizing
- Text-to-speech with browser + Kokoro support
- Speed control up to 3x
- Favorites and archive
- SQLite database with Drizzle ORM
- Docker deployment ready

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/lib/utils/extract.ts

@@ -0,0 +1,62 @@
+import { Readability } from "@mozilla/readability";
+import { JSDOM } from "jsdom";
+
+export interface ExtractedArticle {
+  title: string;
+  author: string | null;
+  siteName: string | null;
+  excerpt: string | null;
+  content: string;
+  textContent: string;
+  leadImage: string | null;
+  wordCount: number;
+}
+
+export async function extractArticle(url: string): Promise<ExtractedArticle> {
+  // Fetch the page
+  const response = await fetch(url, {
+    headers: {
+      "User-Agent": "Mozilla/5.0 (compatible; ReadLater/1.0)",
+    },
+  });
+
+  if (!response.ok) {
+    throw new Error(`Failed to fetch: ${response.status} ${response.statusText}`);
+  }
+
+  const html = await response.text();
+  const dom = new JSDOM(html, { url });
+  const document = dom.window.document;
+
+  // Extract using Readability
+  const reader = new Readability(document);
+  const article = reader.parse();
+
+  if (!article) {
+    throw new Error("Could not extract article content");
+  }
+
+  // Try to find lead image
+  let leadImage: string | null = null;
+  const ogImage = document.querySelector('meta[property="og:image"]');
+  if (ogImage) {
+    leadImage = ogImage.getAttribute("content");
+  }
+
+  const textContent = article.textContent || "";
+  const content = article.content || "";
+
+  // Calculate word count
+  const wordCount = textContent.split(/\s+/).filter(Boolean).length;
+
+  return {
+    title: article.title || "Untitled",
+    author: article.byline || null,
+    siteName: article.siteName || new URL(url).hostname,
+    excerpt: article.excerpt || null,
+    content,
+    textContent,
+    leadImage,
+    wordCount,
+  };
+}