Skip to content

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.

956 B
Raw Blame
import { Actor } from 'apify';
import { Dataset, PlaywrightCrawler } from '@crawlee/playwright';

const mainOptions = {
    exit: Actor.isAtHome(),
    storage:
        process.env.STORAGE_IMPLEMENTATION === 'LOCAL'
            ? new (await import('@apify/storage-local')).ApifyStorageLocal()
            : undefined,
};

await Actor.main(async () => {
    const crawler = new PlaywrightCrawler({
        preNavigationHooks: [
            ({ gotoOptions }) => {
                gotoOptions.waitUntil = 'networkidle';
            },
        ],
        async requestHandler({ page, enqueueLinks, request }) {
            const { url } = request;
            const pageTitle = await page.title();
            await Dataset.pushData({ url, pageTitle });
            await enqueueLinks({
                include: ['**/3.12/examples/*'],
            });
        },
    });

    await crawler.run(['https://crawlee.dev/js/docs/3.12/examples/']);
}, mainOptions);