JavaScript Playwright scraper

1/**
2 * This template is a production ready boilerplate for developing with `PlaywrightCrawler`.
3 * Use this to bootstrap your projects using the most up-to-date code.
4 * If you're looking for examples or want to learn more, see README.
5 */
6
7// For more information, see https://crawlee.dev
8import { PlaywrightCrawler } from '@crawlee/playwright';
9// For more information, see https://docs.apify.com/sdk/js
10import { Actor } from 'apify';
11
12// this is ESM project, and as such, it requires you to specify extensions in your relative imports
13// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
14import { router } from './routes.js';
15
16// Initialize the Apify SDK
17await Actor.init();
18
19const { startUrls = ['https://apify.com'] } = (await Actor.getInput()) ?? {};
20
21// `checkAccess` flag ensures the proxy credentials are valid, but the check can take a few hundred milliseconds.
22// Disable it for short runs if you are sure your proxy configuration is correct
23const proxyConfiguration = await Actor.createProxyConfiguration({ checkAccess: true });
24
25const crawler = new PlaywrightCrawler({
26    proxyConfiguration,
27    requestHandler: router,
28    launchContext: {
29        launchOptions: {
30            args: [
31                '--disable-gpu', // Mitigates the "crashing GPU process" issue in Docker containers
32            ],
33        },
34    },
35});
36
37await crawler.run(startUrls);
38
39// Exit successfully
40await Actor.exit();