Chuyển trang web sang Markdown trong Node.js

/**
 * @typedef {Object} Page
 * @property {string} url
 * @property {string} final_url
 * @property {number} status_code
 * @property {boolean} rendered
 * @property {number} credits_used
 * @property {string} [title]
 * @property {string} [author]
 * @property {string} [published_at]
 * @property {string} [language]
 * @property {string} [markdown]
 * @property {number} word_count
 */

/** @returns {Promise<Page>} */
export async function readPage(url, options = {}) {
  const params = new URLSearchParams({ url, ...options });
  const res = await fetch(`https://webreaderapi.com/api/v1/read?${params}`, {
    headers: { Authorization: `Bearer ${process.env.WEBREADER_API_KEY}` },
    signal: AbortSignal.timeout(75_000),
  });
  const body = await res.json();
  if (!res.ok) throw Object.assign(new Error(body.error.message), { code: body.error.code });
  return body;
}

const page = await readPage('https://example.com/docs/getting-started', { max_chars: '20000' });
console.log(page.title, page.word_count, 'words,', page.credits_used, 'credit(s)');

import { readPage } from './read.mjs';

export async function readAll(urls, workers = 8) {
  const queue = [...urls];
  const results = [];
  async function worker() {
    while (queue.length) {
      const url = queue.shift();
      try {
        const page = await readPage(url, { max_chars: '50000' });
        results.push({ url, page });
      } catch (err) {
        results.push({ url, error: err.code ?? err.name });
      }
    }
  }
  await Promise.all(Array.from({ length: workers }, worker));
  return results;
}

const urls = Array.from({ length: 30 }, (_, i) => `https://example.com/blog/post-${i + 1}`);
for (const r of await readAll(urls)) console.log(r.url, '->', r.error ?? r.page.title);

const headers = {
  Authorization: `Bearer ${process.env.WEBREADER_API_KEY}`,
  'Content-Type': 'application/json',
};
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));

const start = await fetch('https://webreaderapi.com/api/v1/crawl', {
  method: 'POST',
  headers,
  body: JSON.stringify({ url: 'https://docs.example.com/', limit: 300, include_paths: ['/docs/*'] }),
});
const { job_id } = await start.json();

const pages = [];
let cursor = '';
let wait = 2000;
for (;;) {
  const url = `https://webreaderapi.com/api/v1/jobs/${job_id}${cursor ? `?cursor=${encodeURIComponent(cursor)}` : ''}`;
  const job = await (await fetch(url, { headers })).json();
  pages.push(...job.results.filter((r) => !r.error));
  if (job.next_cursor) {
    cursor = job.next_cursor;
    wait = 2000;
    continue;
  }
  if (job.status === 'done') break;
  await sleep(wait);
  wait = Math.min(wait * 2, 30000);
}
console.log(pages.length, 'pages read, job', job_id);