Crawler Puppeteer

1import { ApifyClient } from 'apify-client';
2
3// Initialize the ApifyClient with your Apify API token
4// Replace the '<YOUR_API_TOKEN>' with your token
5const client = new ApifyClient({
6    token: '<YOUR_API_TOKEN>',
7});
8
9// Prepare Actor input
10const input = {
11    "startUrls": [
12        {
13            "url": "http://example.com"
14        },
15        {
16            "url": "http://iana.org"
17        }
18    ],
19    "pseudoUrls": [
20        {
21            "purl": "https://www.iana.org/[((?!\\.pdf$).)*]"
22        }
23    ],
24    "linkSelector": "a",
25    "pageFunction": async ({ request, page, keyValueStore, log }) => {
26        const title = await page.title();
27        log.info(`Title of page with url ${request.url} is: ${title}`);
28        await keyValueStore.setValue(Math.random().toString(36), { title });
29        return { title }
30    },
31    "proxyConfiguration": {
32        "useApifyProxy": false
33    }
34};
35
36// Run the Actor and wait for it to finish
37const run = await client.actor("jancurn/crawler-puppeteer").call(input);
38
39// Fetch and print Actor results from the run's dataset (if any)
40console.log('Results from dataset');
41console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
42const { items } = await client.dataset(run.defaultDatasetId).listItems();
43items.forEach((item) => {
44    console.dir(item);
45});
46
47// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs