feat(baoyu-url-to-markdown): add browser fallback strategy, content cleaner, and data URI support

- Browser strategy: headless first with automatic retry in visible Chrome on failure - New --browser auto|headless|headed flag with --headless/--headed shortcuts - Content cleaner module for HTML preprocessing (remove ads, base64 images, scripts) - Media localizer now handles base64 data URIs alongside remote URLs - Capture finalUrl from browser to track redirects for output path - Agent quality gate documentation for post-capture validation - Upgrade defuddle ^0.12.0 → ^0.14.0 - Add unit tests for content-cleaner, html-to-markdown, legacy-converter, media-localizer
2026-07-23 02:29:48 +08:00 · 2026-03-24 22:39:17 -05:00
parent 40f9f05c22
commit e99ce744cd
12 changed files with 909 additions and 67 deletions
@@ -0,0 +1,28 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+
+import { extractContent } from "./html-to-markdown.js";
+
+const EMBEDDED_IMAGE_HTML = `<!doctype html>
+<html>
+  <body>
+    <main>
+      <article>
+        <h1>Embedded Image Story</h1>
+        <p>
+          This paragraph is intentionally long enough to satisfy the extractor thresholds so the
+          resulting markdown keeps the main article body and the embedded image reference.
+        </p>
+        <img src="data:image/png;base64,AAAA" alt="inline">
+      </article>
+    </main>
+  </body>
+</html>`;
+
+test("extractContent preserves base64 images when requested for media download", async () => {
+  const result = await extractContent(EMBEDDED_IMAGE_HTML, "https://example.com/embedded", {
+    preserveBase64Images: true,
+  });
+
+  assert.match(result.markdown, /!\[inline\]\(data:image\/png;base64,AAAA\)/);
+});