Extracting Structured Product Data Using Amazon Bedrock

In today’s fast-paced e-commerce world, having structured product data is essential for everything from price comparisons to building sophisticated recommendation systems. One powerful tool for extracting and processing this data is Amazon Bedrock, a machine learning service that simplifies building and deploying applications with AI. In this blog post, we’ll explore how to use Node.js to extract product data from a webpage, specifically from an e-commerce site like Noel Leeming.

We’ll focus on the LG 65″ UR78 4K Smart UHD TV product page, found at this URL: https://www.noelleeming.co.nz/p/lg-65-ur78-4k-smart-uhd-tv-2023/N220470.html.

Prerequisites

Before we dive in, make sure you have the following:

1. Node.js installed on your machine.
2. An AWS account with access to Amazon Bedrock.
3. Basic knowledge of JavaScript and web scraping.

Here, we’re installing axios for making HTTP requests, cheerio for parsing HTML, and aws-sdk for interacting with Amazon Bedrock.

Step 2: Fetching the Webpage

Next, we’ll write a script to fetch the HTML content of the product page. Create a file named index.js and add the following code:

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

const url = 'https://www.noelleeming.co.nz/p/lg-65-ur78-4k-smart-uhd-tv-2023/N220470.html';

async function fetchHTML(url) {
  try {
    const { data } = await axios.get(url);
    return data;
  } catch (error) {
    console.error('Error fetching the HTML:', error);
  }
}

fetchHTML(url).then((html) => {
  console.log(html);
});