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.

1.1 KB
Raw Blame
import { Actor } from 'apify';
import { CheerioCrawler, Dataset } from '@crawlee/cheerio';

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 CheerioCrawler({
        statusMessageCallback: async (ctx) => {
            return ctx.crawler.setStatusMessage(`this is status message from ${new Date().toISOString()}`, {
                level: 'INFO',
            });
        },
        statusMessageLoggingInterval: 1,
        async requestHandler({ $, enqueueLinks, request, log }) {
            const { url } = request;
            await enqueueLinks({
                include: ['https://crawlee.dev/js/docs/**'],
            });

            const pageTitle = $('title').first().text();
            log.info(`URL: ${url} TITLE: ${pageTitle}`);

            await Dataset.pushData({ url, pageTitle });
        },
    });

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