GPT Scraper

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://news.ycombinator.com/"
14        }
15    ],
16    "instructions": `Gets the post with the most points from the page and returns it as JSON in this format: 
17        postTitle
18        postUrl
19        pointsCount`,
20    "includeUrlGlobs": [],
21    "excludeUrlGlobs": [],
22    "linkSelector": "a[href]",
23    "initialCookies": [],
24    "proxyConfiguration": {
25        "useApifyProxy": true
26    },
27    "targetSelector": "",
28    "removeElementsCssSelector": "script, style, noscript, path, svg, xlink",
29    "schema": {
30        "type": "object",
31        "properties": {
32            "title": {
33                "type": "string",
34                "description": "Page title"
35            },
36            "description": {
37                "type": "string",
38                "description": "Page description"
39            }
40        },
41        "required": [
42            "title",
43            "description"
44        ]
45    },
46    "schemaDescription": ""
47};
48
49// Run the Actor and wait for it to finish
50const run = await client.actor("drobnikj/gpt-scraper").call(input);
51
52// Fetch and print Actor results from the run's dataset (if any)
53console.log('Results from dataset');
54console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
55const { items } = await client.dataset(run.defaultDatasetId).listItems();
56items.forEach((item) => {
57    console.dir(item);
58});
59
60// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs