basic scraper

baseScraper.js

const axios = require('axios');
const cheerio = require('cheerio');

const baseUrl = 'https://www.infomerlo.com';
const urlToScrap = baseUrl + '/noticias';

const numberOfFirstElementsToScrap = 10;

axios(urlToScrap)
  .then(response => {
    const html = response.data;
    const $ = cheerio.load(html);

    const articles = [];
    // cannot be a function expression ↓
    $(`.media:nth-of-type(-n+${numberOfFirstElementsToScrap})`, html).each(
      function () {
        // console.log(`$(this).html()`, $(this).html());

        const jsonWithImages = JSON.parse(
          $(this).find('.img-container').attr('data-media-desktop'),
        );
        const imageUrl = jsonWithImages.imagen.jpg.xs;
        const title = $(this).find('h2').text().trim();
        const url = $(this).find('a').attr('href');

        articles.push({title, url: baseUrl + url, imageUrl});
      },
    );

    console.log(`articles`, JSON.stringify(articles, null, 2));
  })
  .catch(err => console.log(err));

// resources:
// https://github.com/cheeriojs/cheerio#selectors
// https://css-tricks.com/useful-nth-child-recipies/#aa-select-only-the-first-five