Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.
TypeScript apifyautomationcrawlercrawlingheadlessheadless-chromejavascriptnodejsnpmplaywrightpuppeteerscraperscrapingtypescriptweb-crawlerweb-crawlingweb-scraping
import { PuppeteerCrawler, Dataset } from 'crawlee';
// PuppeteerCrawler crawls the web using a headless
// browser controlled by the Puppeteer library.
const crawler = new PuppeteerCrawler({
// Use the requestHandler to process each of the crawled pages.
async requestHandler({ request, page, enqueueLinks, log }) {
const title = await page.title();
log.info(`Title of ${request.loadedUrl} is '${title}'`);
// Save results as JSON to ./storage/datasets/default
await Dataset.pushData({ title, url: request.loadedUrl });
// Extract links from the current page
// and add them to the crawling queue.
await enqueueLinks();
},
// Uncomment this option to see the browser window.
// headless: false,
// Let's limit our crawls to make our tests shorter and safer.
maxRequestsPerCrawl: 50,
});
// Add first URL to the queue and start the crawl.
await crawler.run(['https://crawlee.dev']);