TypeScript one-page scraper

1// Apify SDK - toolkit for building Apify Actors (Read more at https://docs.apify.com/sdk/js/).
2import { Actor, log } from 'apify';
3// Axios - Promise based HTTP client for the browser and node.js (Read more at https://axios-http.com/docs/intro).
4import axios from 'axios';
5// Cheerio - The fast, flexible & elegant library for parsing and manipulating HTML and XML (Read more at https://cheerio.js.org/).
6import * as cheerio from 'cheerio';
7
8// this is ESM project, and as such, it requires you to specify extensions in your relative imports
9// read more about this here: https://nodejs.org/docs/latest-v18.x/api/esm.html#mandatory-file-extensions
10// note that we need to use `.js` even when inside TS files
11// import { router } from './routes.js';
12
13// The init() call configures the Actor to correctly work with the Apify-provided environment - mainly the storage infrastructure. It is necessary that every Actor performs an init() call.
14await Actor.init();
15
16interface Input {
17    url: string;
18}
19// Structure of input is defined in input_schema.json
20const input = await Actor.getInput<Input>();
21if (!input) throw new Error('Input is missing!');
22const { url } = input;
23
24// Fetch the HTML content of the page.
25const response = await axios.get(url);
26
27// Parse the downloaded HTML with Cheerio to enable data extraction.
28const $ = cheerio.load(response.data);
29
30// Extract all headings from the page (tag name and text).
31const headings: { level: string; text: string }[] = [];
32$('h1, h2, h3, h4, h5, h6').each((_i, element) => {
33    const headingObject = {
34        level: $(element).prop('tagName')!.toLowerCase(),
35        text: $(element).text(),
36    };
37    log.info('Extracted heading', headingObject);
38    headings.push(headingObject);
39});
40
41// Save headings to Dataset - a table-like storage.
42await Actor.pushData(headings);
43
44// Gracefully exit the Actor process. It's recommended to quit all Actors with an exit().
45await Actor.exit();