Web Scraper new

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": "https://apify.com"
14        }
15    ],
16    "linkSelector": "a[href]",
17    "pseudoUrls": [
18        {
19            "purl": "https://apify.com[(/[\\w-]+)?]"
20        }
21    ],
22    "pageFunction": // The function accepts a single argument: the "context" object.
23    // For a complete list of its properties and functions,
24    // see https://apify.com/apify/web-scraper#page-function 
25    async function pageFunction(context) {
26        // jQuery is handy for finding DOM elements and extracting data from them.
27        // To use it, make sure to enable the "Inject jQuery" option.
28        const $ = context.jQuery;
29        const pageTitle = $('title').first().text();
30    
31        // Print some information to actor log
32        context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
33    
34        // Manually add a new page to the queue for scraping.
35        // To make this work, make sure the "Use request queue" option is enabled.
36        context.enqueueRequest({ url: 'http://www.example.com' });
37    
38        // Return an object with the data extracted from the page.
39        // It will be stored to the resulting dataset.
40        return {
41            url: context.request.url,
42            pageTitle
43        };
44    },
45    "proxyConfiguration": {
46        "useApifyProxy": false
47    },
48    "initialCookies": [],
49    "waitUntil": [
50        "networkidle2"
51    ],
52    "customData": {}
53};
54
55// Run the Actor and wait for it to finish
56const run = await client.actor("honzakirchner43/web-scraper-new").call(input);
57
58// Fetch and print Actor results from the run's dataset (if any)
59console.log('Results from dataset');
60console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
61const { items } = await client.dataset(run.defaultDatasetId).listItems();
62items.forEach((item) => {
63    console.dir(item);
64});
65
66// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs