Scraper starter

The code

Two files, exactly what you get in the editor.

import { createServer } from 'node:http'
import * as cheerio from 'cheerio'

// GET /?url=https://example.com returns the page title and its headings.
const server = createServer(async (req, res) => {
  const target = new URL(req.url ?? '/', 'http://localhost').searchParams.get('url')
    ?? 'https://example.com'
  try {
    const html = await (await fetch(target)).text()
    const $ = cheerio.load(html)
    const headings = $('h1, h2, h3')
      .map((_i, el) => $(el).text().trim())
      .get()
      .filter(Boolean)
      .slice(0, 50)
    res.writeHead(200, { 'content-type': 'application/json' })
    res.end(JSON.stringify({ url: target, title: $('title').text().trim(), headings }, null, 2))
  } catch (error) {
    res.writeHead(502, { 'content-type': 'application/json' })
    res.end(JSON.stringify({ error: String(error) }))
  }
})

const port = Number(process.env.PORT) || 3000
server.listen(port, () => console.log(`Scraper on port ${port}`))

{
  "name": "headline-scraper",
  "private": true,
  "type": "module",
  "dependencies": {
    "cheerio": "^1.1.0"
  }
}