Basic Scraping

import { ReaderClient } from "@vakra-dev/reader";

const reader = new ReaderClient();

const result = await reader.scrape({
  urls: ["https://example.com"],
  formats: ["markdown"],
});

console.log(result.data[0].markdown);

await reader.close();

const result = await reader.scrape({
  urls: ["https://example.com"],
  formats: ["markdown", "html"],
});

const page = result.data[0];
console.log("Markdown:", page.markdown?.length, "chars");
console.log("HTML:    ", page.html?.length, "chars");

const page = result.data[0];

console.log({
  title:       page.metadata.website.title,
  description: page.metadata.website.description,
  author:      page.metadata.website.author,
  canonical:   page.metadata.website.canonical,
  ogImage:     page.metadata.website.openGraph?.image,
  statusCode:  page.metadata.statusCode,
  engine:      page.metadata.engine,     // which engine won the race
  duration:    page.metadata.duration,   // ms
});

await reader.scrape({
  urls: ["https://example.com"],
  onlyMainContent: false,
});

await reader.scrape({
  urls: ["https://blog.example.com/post"],
  includeTags: [".article-content", "#main-body"],
  excludeTags: [".comments", ".related-posts"],
});

await reader.scrape({
  urls: ["https://spa.example.com/dashboard"],
  waitForSelector: ".dashboard-loaded",
  timeoutMs: 45000,
});

// ✅ Good - pool stays warm
const reader = new ReaderClient({ browserPool: { size: 5 } });

for (const url of urls) {
  const result = await reader.scrape({ urls: [url] });
  // handle result
}

await reader.close();

// ❌ Bad - spins up and tears down a browser pool for every URL
for (const url of urls) {
  const reader = new ReaderClient();
  await reader.scrape({ urls: [url] });
  await reader.close();
}