From de32807995f76f81607f70c3a1dadc06a3559b8b Mon Sep 17 00:00:00 2001
From: Gigi <dergigi@pm.me>
Date: Thu, 2 Oct 2025 23:32:00 +0200
Subject: [PATCH] feat(reader): add lightweight readability fetcher via
 r.jina.ai proxy

- Provide fetchReadableContent(url) returning simplified HTML
- Avoid heavy deps and CORS issues using proxy
- Extract <title> best-effort
---
 src/services/readerService.ts | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 src/services/readerService.ts

diff --git a/src/services/readerService.ts b/src/services/readerService.ts
new file mode 100644
index 00000000..8b2b97ab
--- /dev/null
+++ b/src/services/readerService.ts
@@ -0,0 +1,32 @@
+// Lightweight readability-style fetcher using r.jina.ai proxy
+// Returns simplified HTML for a given URL. This avoids CORS and heavy deps.
+
+export interface ReadableContent {
+  url: string
+  title?: string
+  html: string
+}
+
+function toProxyUrl(url: string): string {
+  // Ensure the target URL has a protocol and build the proxy URL
+  const normalized = /^https?:\/\//i.test(url) ? url : `https://${url}`
+  return `https://r.jina.ai/http://${normalized.replace(/^https?:\/\//, '')}`
+}
+
+export async function fetchReadableContent(targetUrl: string): Promise<ReadableContent> {
+  const proxyUrl = toProxyUrl(targetUrl)
+  const res = await fetch(proxyUrl)
+  if (!res.ok) {
+    throw new Error(`Failed to fetch readable content (${res.status})`)
+  }
+  const html = await res.text()
+  // Best-effort title extraction
+  const match = html.match(/<title[^>]*>(.*?)<\/title>/i)
+  return {
+    url: targetUrl,
+    title: match?.[1],
+    html
+  }
+}
+
+