A script to scrape Digital Content Lists from Amazon

amazon_books_scraper.js

// NOTE: It's supposed to be used in DevTools console only, depends on `copy`, `$`, `$$`, etc.
// NOTE: these backups needed cause after a new page loaded $, $$, etc. are undefined for the script running 🤷‍♂️
const selector = $
const selectorAll = $$
const clipboardCopy = copy

let allBooksList = []

function scrapBooks() {
	const titles = selectorAll('.digital_entity_title').map((b)=>{ return b.innerText })
	const authors = selectorAll('div[id^="content-author"]').map((a)=>{ return a.innerText })
	// NOTE: for Audible use this instead...
	// const authors = selectorAll('.digital_entity_details > .information_row').map((a)=>{ return a.innerText }).filter((e) => { return e != '' })
	let books = []
	
	for (const [i, title] of titles.entries()) {
	    console.log(`'${title}' by ${authors[i]}`)
	    books.push(`- '${title}' by ${authors[i]}`)
	}
	
	return books
}

function sleep(ms) {
  return new Promise(resolve => setTimeout(resolve, ms))
}

let maxPage = Number($$('a[id^="page-"]').pop().textContent)
let currentPage = 0
while (currentPage < maxPage) {
	currentPage += 1
	selector(`#page-${currentPage}`).click()
	await sleep(2000)
	
	console.log(`Handling page #${currentPage}`)
	allBooksList.push(...scrapBooks())
	console.log(`Scrapped ${allBooksList.length} books so far...`)
}

clipboardCopy(allBooksList.join("\n"))