diff --git a/lib/ingest/readability.js b/lib/ingest/readability.js
new file mode 100644
index 0000000..4720e31
--- /dev/null
+++ b/lib/ingest/readability.js
@@ -0,0 +1,16 @@
+import { JSDOM } from 'jsdom';
+import { Readability } from '@mozilla/readability';
+
+export function extract(html, url) {
+  const dom = new JSDOM(html, { url });
+  const reader = new Readability(dom.window.document);
+  const a = reader.parse();
+  if (!a) return { title: null, textContent: '', excerpt: null, byline: null, siteName: null };
+  return {
+    title: a.title || null,
+    textContent: (a.textContent || '').trim(),
+    excerpt: a.excerpt || null,
+    byline: a.byline || null,
+    siteName: a.siteName || null
+  };
+}
diff --git a/tests/ingest/readability.test.js b/tests/ingest/readability.test.js
new file mode 100644
index 0000000..2b8e063
--- /dev/null
+++ b/tests/ingest/readability.test.js
@@ -0,0 +1,25 @@
+import { describe, it, expect } from 'vitest';
+import { extract } from '../../lib/ingest/readability.js';
+
+const HTML = `
+  <html><head><title>Blackflame Notes</title>
+  <meta property="og:site_name" content="Hynesy"/>
+  </head><body><article>
+  <h1>Blackflame Notes</h1>
+  <p>An essay on the Cradle aesthetic and the blackflame motif. This is a longer paragraph that gives readability enough text to consider this the main content of the page.</p>
+  <p>A second paragraph also part of the article.</p>
+  </article></body></html>`;
+
+describe('readability.extract', () => {
+  it('pulls title and text', () => {
+    const out = extract(HTML, 'https://example.com/x');
+    expect(out.title).toMatch(/Blackflame/);
+    expect(out.textContent).toMatch(/Cradle/);
+    expect(out.siteName).toBe('Hynesy');
+  });
+
+  it('returns empty struct when nothing parseable', () => {
+    const out = extract('<html></html>', 'https://example.com');
+    expect(out.textContent).toBe('');
+  });
+});
