src/extractor.js

import { JSDOM } from 'jsdom'
import { Readability } from '@mozilla/readability'

export async function extractContent(page, format = 'text') {
  const [html, title, url] = await Promise.all([
    page.content(),
    page.title(),
    Promise.resolve(page.url()),
  ])

  const dom = new JSDOM(html, { url })
  const reader = new Readability(dom.window.document)
  const article = reader.parse()

  if (!article) {
    // Readability gave up — grab raw body text as fallback
    const text = await page.evaluate(() => document.body?.innerText ?? '')
    if (format === 'json') {
      return { url, title, text, excerpt: text.slice(0, 300), source: 'fallback' }
    }
    return text
  }

  if (format === 'json') {
    return {
      url,
      title: article.title,
      byline: article.byline,
      siteName: article.siteName,
      excerpt: article.excerpt,
      length: article.length,
      content: article.textContent.trim(),
      html: article.content,
      publishedTime: article.publishedTime ?? null,
      source: 'readability',
    }
  }

  return article.textContent.trim()
}