get all direct links from a soundcloud playlist

scrapecloud.js

/* eslint no-await-in-loop: off, no-console: off */

// scrapecloud.js | 02/18
// get all direct links from soundcloud playlists

const puppeteer = require('puppeteer');

const scBaseUrl = 'https://soundcloud.com';
const scPlaylistUrl = `${scBaseUrl}/alex-humenyuk/sets/street-workout`;


// function executed in browser
function extractItems() {
  const extLinks = Array.from(document.querySelectorAll('a.trackItem__trackTitle.sc-link-dark.sc-font-light'));
  return extLinks.map(a => a.getAttribute('href'));
}

// scroll & extract
async function scrapePlaylist(page, extractItemsFunc, itemTargetCount, scrollDelay = 1000) {
  let items = [];
  try {
    let previousHeight;
    while (items.length < itemTargetCount) {
      items = await page.evaluate(extractItemsFunc);
      previousHeight = await page.evaluate('document.body.scrollHeight');
      await page.evaluate('window.scrollTo(0, document.body.scrollHeight)');
      await page.waitForFunction(`document.body.scrollHeight > ${previousHeight}`);
      await page.waitFor(scrollDelay);
    }
  } catch (e) { console.error(e); }
  return items;
}


(async () => {
  // set up the browser and a page
  const browser = await puppeteer.launch();
  const page = await browser.newPage();

  page.setViewport({ width: 1280, height: 926 });
  await page.goto(scPlaylistUrl);

  // scroll and extract items from the page.
  const items = await scrapePlaylist(page, extractItems, 100);
  const trackLinks = items.map((item) => {
    const link = /^(\/.*)\?in.*/.exec(item);
    return `${scBaseUrl}${link[1]}`;
  });

  // output
  console.log(trackLinks);

  // close browser
  await browser.close();
})();