js-harvester/examples/src/playwright/amazon.js

Harvester is a lightweight and highly optimized javascript library for extracting data from the DOM tree. It supports extraction of tag texts with specified types and attributes. it's tiny and has no dependencies and also works with Puppeteer

import { harvestPageAll } from 'js-harvester/playwright.js'
import { open } from './utils.js'

const PRODUCTS_QUERY = '[role="listitem"] .s-card-container .a-section > [class=puisg-row]:nth-of-type(1)'
const TPL = `
div
  div
    span
      a
        img[img=src]
div
  div
    div
      a
        h2
          span{title}
    div
    div
    div
      div
        div
          div
            div
              div
                a
                  span
                    span{price:func:price}`
const page = await open()

await page.goto('https://www.amazon.com/s?k=laptops', { waitUntil: 'load' })
await page.waitForSelector(PRODUCTS_QUERY)
await page.evaluate(() => {
  window.price = function price (t, el) { return el?.className === 'a-offscreen' && t?.indexOf('$') > -1 }
})
const products = await harvestPageAll(page, TPL, PRODUCTS_QUERY, { inject: true, dataOnly: true, minDepth: 60 })
console.log(products, '\nPress Ctrl-C to stop...')