feat(ingest): readability wrapper
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
16
lib/ingest/readability.js
Normal file
16
lib/ingest/readability.js
Normal file
@@ -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
|
||||
};
|
||||
}
|
||||
Reference in New Issue
Block a user