My Actor 32

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    "runMode": "DEVELOPMENT",
12    "startUrls": [
13        {
14            "url": "https://apify.com"
15        }
16    ],
17    "globs": [],
18    "linkSelector": "a[href]",
19    "pseudoUrls": [
20        {
21            "purl": "https://apify.com[(/[\\w-]+)?]"
22        }
23    ],
24    "pageFunction": `// The function accepts a single argument: the "context" object.
25        // For a complete list of its properties and functions,
26        // see https://apify.com/apify/web-scraper#page-function 
27        async function pageFunction(context) {
28            // This statement works as a breakpoint when you're trying to debug your code. Works only with Run mode: DEVELOPMENT!
29            // debugger; 
30        
31            // jQuery is handy for finding DOM elements and extracting data from them.
32            // To use it, make sure to enable the "Inject jQuery" option.
33            const $ = context.jQuery;
34            const pageTitle = $('title').first().text();
35        
36            // Print some information to actor log
37            context.log.info(`URL: ${context.request.url}, TITLE: ${pageTitle}`);
38        
39            // Manually add a new page to the queue for scraping.
40           await context.enqueueRequest({ url: 'http://www.example.com' });
41        
42            // Return an object with the data extracted from the page.
43            // It will be stored to the resulting dataset.
44            return {
45                url: context.request.url,
46                pageTitle
47            };
48        }`,
49    "proxyConfiguration": {
50        "useApifyProxy": true
51    },
52    "initialCookies": [],
53    "waitUntil": [
54        "networkidle2"
55    ],
56    "preNavigationHooks": `// We need to return array of (possibly async) functions here.
57        // The functions accept two arguments: the "crawlingContext" object
58        // and "gotoOptions".
59        [
60            async (crawlingContext, gotoOptions) => {
61                // ...
62            },
63        ]`,
64    "postNavigationHooks": `// We need to return array of (possibly async) functions here.
65        // The functions accept a single argument: the "crawlingContext" object.
66        [
67            async (crawlingContext) => {
68                // ...
69            },
70        ]`,
71    "breakpointLocation": "NONE",
72    "customData": {}
73};
74
75// Run the Actor and wait for it to finish
76const run = await client.actor("honzakirchner43/my-actor-32").call(input);
77
78// Fetch and print Actor results from the run's dataset (if any)
79console.log('Results from dataset');
80console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
81const { items } = await client.dataset(run.defaultDatasetId).listItems();
82items.forEach((item) => {
83    console.dir(item);
84});
85
86// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs