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 { expect, getActorTestDir, initialize, runActor, validateDataset } from '../tools.mjs';
const testActorDirname = getActorTestDir(import.meta.url);
await initialize(testActorDirname);
const { stats, datasetItems } = await runActor(testActorDirname, 16384);
await expect(stats.requestsSucceeded > 15, 'All requests finished');
await expect(datasetItems.length > 15 && datasetItems.length < 30, 'Number of dataset items');
await expect(validateDataset(datasetItems, ['url', 'pageTitle']), 'Dataset items validation');