Taro Example: Scraping recent YC job posts

yc-jobs.js

const moment = require('moment');
const request = require('superagent');
const cheerio = require('cheerio');
const _ = require('lodash');

const scraper = async () => {
  const url = 'https://news.ycombinator.com/jobs'
  const {text: html} = await request.get(url);
  const $ = cheerio.load(html);
  const links = $('.storylink').map((i, el) => {
    return {href: $(el).attr('href'), text: $(el).text()};
  });
  const ages = $('.age').map((i, el) => $(el).text());
  const formatted = _.zip(links, ages).map(([link, age]) => {
    return {
      text: link.text,
      link: link.href,
      age: age,
    };
  });
  const recent = formatted.filter((item) => {
    // item.age looks like "16 hours ago", "2 days ago", etc.
    const [num, time] = item.age.split(' ');
    const threshold = moment().subtract(24, 'hours');
    
    return moment().subtract(num, time) > threshold;
  });

  return recent;
};

// Run function and verify output
scraper().then(console.log).catch(console.log);

const main = () => scraper();

// You must have a default export of the function you want to run
// in order for it to be deployed and scheduled
module.exports = main;