Files
2026-07-13 13:23:39 +08:00

26 lines
776 B
TypeScript

import { Actor } from 'apify';
import { CheerioCrawler } from 'crawlee';
await Actor.main(async () => {
const crawler = new CheerioCrawler({
async requestHandler({ request, $, enqueueLinks }) {
const { url } = request;
// Extract HTML title of the page.
const title = $('title').text();
console.log(`Title of ${url}: ${title}`);
// Add URLs that match the provided pattern.
await enqueueLinks({
globs: ['https://www.iana.org/*'],
});
// Save extracted data to dataset.
await Actor.pushData({ url, title });
},
});
// Enqueue the initial request and run the crawler
await crawler.run(['https://www.iana.org/']);
});