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 { AdaptivePlaywrightCrawler, KeyValueStore, RenderingTypePredictor } from 'crawlee';
await using renderingTypePredictor = new RenderingTypePredictor({
detectionRatio: 0.1,
persistenceOptions: {
keyValueStore: KeyValueStore.open('rendering-predictions'),
},
});
await renderingTypePredictor.initialize();
const crawler = new AdaptivePlaywrightCrawler({
renderingTypePredictor,
async requestHandler({ request, parseWithCheerio, pushData, enqueueLinks }) {
const $ = await parseWithCheerio('h1');
await pushData({ url: request.loadedUrl, title: $('h1').text() });
await enqueueLinks();
},
});
await crawler.run(['https://crawlee.dev']);