Web Scraping Full Course 2023 | Build and Deploy eCommerce Price Tracker

cron.route.ts

import { NextResponse } from "next/server";

import { getLowestPrice, getHighestPrice, getAveragePrice, getEmailNotifType } from "@/lib/utils";
import { connectToDB } from "@/lib/mongoose";
import Product from "@/lib/models/product.model";
import { scrapeAmazonProduct } from "@/lib/scraper";
import { generateEmailBody, sendEmail } from "@/lib/nodemailer";

export const maxDuration = 300; // This function can run for a maximum of 300 seconds
export const dynamic = "force-dynamic";
export const revalidate = 0;

export async function GET(request: Request) {
  try {
    connectToDB();

    const products = await Product.find({});

    if (!products) throw new Error("No product fetched");

    // ======================== 1 SCRAPE LATEST PRODUCT DETAILS & UPDATE DB
    const updatedProducts = await Promise.all(
      products.map(async (currentProduct) => {
        // Scrape product
        const scrapedProduct = await scrapeAmazonProduct(currentProduct.url);

        if (!scrapedProduct) return;

        const updatedPriceHistory = [
          ...currentProduct.priceHistory,
          {
            price: scrapedProduct.currentPrice,
          },
        ];

        const product = {
          ...scrapedProduct,
          priceHistory: updatedPriceHistory,
          lowestPrice: getLowestPrice(updatedPriceHistory),
          highestPrice: getHighestPrice(updatedPriceHistory),
          averagePrice: getAveragePrice(updatedPriceHistory),
        };

        // Update Products in DB
        const updatedProduct = await Product.findOneAndUpdate(
          {
            url: product.url,
          },
          product
        );

        // ======================== 2 CHECK EACH PRODUCT'S STATUS & SEND EMAIL ACCORDINGLY
        const emailNotifType = getEmailNotifType(
          scrapedProduct,
          currentProduct
        );

        if (emailNotifType && updatedProduct.users.length > 0) {
          const productInfo = {
            title: updatedProduct.title,
            url: updatedProduct.url,
          };
          // Construct emailContent
          const emailContent = await generateEmailBody(productInfo, emailNotifType);
          // Get array of user emails
          const userEmails = updatedProduct.users.map((user: any) => user.email);
          // Send email notification
          await sendEmail(emailContent, userEmails);
        }

        return updatedProduct;
      })
    );

    return NextResponse.json({
      message: "Ok",
      data: updatedProducts,
    });
  } catch (error: any) {
    throw new Error(`Failed to get all products: ${error.message}`);
  }
}

generateEmailBody.ts

export async function generateEmailBody(
  product: EmailProductInfo,
  type: NotificationType
  ) {
  const THRESHOLD_PERCENTAGE = 40;
  // Shorten the product title
  const shortenedTitle =
    product.title.length > 20
      ? `${product.title.substring(0, 20)}...`
      : product.title;

  let subject = "";
  let body = "";

  switch (type) {
    case Notification.WELCOME:
      subject = `Welcome to Price Tracking for ${shortenedTitle}`;
      body = `
        <div>
          <h2>Welcome to PriceWise 🚀</h2>
          <p>You are now tracking ${product.title}.</p>
          <p>Here's an example of how you'll receive updates:</p>
          <div style="border: 1px solid #ccc; padding: 10px; background-color: #f8f8f8;">
            <h3>${product.title} is back in stock!</h3>
            <p>We're excited to let you know that ${product.title} is now back in stock.</p>
            <p>Don't miss out - <a href="${product.url}" target="_blank" rel="noopener noreferrer">buy it now</a>!</p>
            <img src="https://i.ibb.co/pwFBRMC/Screenshot-2023-09-26-at-1-47-50-AM.png" alt="Product Image" style="max-width: 100%;" />
          </div>
          <p>Stay tuned for more updates on ${product.title} and other products you're tracking.</p>
        </div>
      `;
      break;

    case Notification.CHANGE_OF_STOCK:
      subject = `${shortenedTitle} is now back in stock!`;
      body = `
        <div>
          <h4>Hey, ${product.title} is now restocked! Grab yours before they run out again!</h4>
          <p>See the product <a href="${product.url}" target="_blank" rel="noopener noreferrer">here</a>.</p>
        </div>
      `;
      break;

    case Notification.LOWEST_PRICE:
      subject = `Lowest Price Alert for ${shortenedTitle}`;
      body = `
        <div>
          <h4>Hey, ${product.title} has reached its lowest price ever!!</h4>
          <p>Grab the product <a href="${product.url}" target="_blank" rel="noopener noreferrer">here</a> now.</p>
        </div>
      `;
      break;

    case Notification.THRESHOLD_MET:
      subject = `Discount Alert for ${shortenedTitle}`;
      body = `
        <div>
          <h4>Hey, ${product.title} is now available at a discount more than ${THRESHOLD_PERCENTAGE}%!</h4>
          <p>Grab it right away from <a href="${product.url}" target="_blank" rel="noopener noreferrer">here</a>.</p>
        </div>
      `;
      break;

    default:
      throw new Error("Invalid notification type.");
  }

  return { subject, body };
}

globals.css

@tailwind base;
@tailwind components;
@tailwind utilities;

* {
  margin: 0;
  padding: 0;
  box-sizing: border-box;
  scroll-behavior: smooth;
}

@layer base {
  body {
    @apply font-inter;
  }
}

@layer utilities {
  .btn {
    @apply py-4 px-4 bg-secondary hover:bg-opacity-70 rounded-[30px] text-white text-lg font-semibold;
  }

  .head-text {
    @apply mt-4 text-6xl leading-[72px] font-bold tracking-[-1.2px] text-gray-900;
  }

  .section-text {
    @apply text-secondary text-[32px] font-semibold;
  }

  .small-text {
    @apply flex gap-2 text-sm font-medium text-primary;
  }

  .paragraph-text {
    @apply text-xl leading-[30px] text-gray-600;
  }

  .hero-carousel {
    @apply relative sm:px-10 py-5 sm:pt-20 pb-5 max-w-[560px] h-[700px] w-full bg-[#F2F4F7] rounded-[30px] sm:mx-auto;
  }

  .carousel {
    @apply flex flex-col-reverse h-[700px];
  }

  .carousel .control-dots {
    @apply static !important;
  }

  .carousel .control-dots .dot {
    @apply w-[10px] h-[10px] bg-[#D9D9D9] rounded-full bottom-0 !important;
  }

  .carousel .control-dots .dot.selected {
    @apply bg-[#475467] !important;
  }

  .trending-section {
    @apply flex flex-col gap-10 px-6 md:px-20 py-24;
  }

  /* PRODUCT DETAILS PAGE STYLES */
  .product-container {
    @apply flex flex-col gap-16 flex-wrap px-6 md:px-20 py-24;
  }

  .product-image {
    @apply flex-grow xl:max-w-[50%] max-w-full py-16 border border-[#CDDBFF] rounded-[17px];
  }

  .product-info {
    @apply flex items-center flex-wrap gap-10 py-6 border-y border-y-[#E4E4E4];
  }

  .product-hearts {
    @apply flex items-center gap-2 px-3 py-2 bg-[#FFF0F0] rounded-10;
  }

  .product-stars {
    @apply flex items-center gap-2 px-3 py-2 bg-[#FBF3EA] rounded-[27px];
  }

  .product-reviews {
    @apply flex items-center gap-2 px-3 py-2 bg-white-200 rounded-[27px];
  }

  /* MODAL */
  .dialog-container {
    @apply fixed inset-0 z-10 overflow-y-auto bg-black bg-opacity-60;
  }

  .dialog-content {
    @apply p-6  bg-white inline-block w-full max-w-md my-8 overflow-hidden text-left align-middle transition-all transform  shadow-xl rounded-2xl;
  }

  .dialog-head_text {
    @apply text-secondary text-lg leading-[24px] font-semibold mt-4;
  }

  .dialog-input_container {
    @apply px-5 py-3 mt-3 flex items-center gap-2 border border-gray-300 rounded-[27px];
  }

  .dialog-input {
    @apply flex-1 pl-1 border-none text-gray-500 text-base focus:outline-none border border-gray-300 rounded-[27px] shadow-xs;
  }

  .dialog-btn {
    @apply px-5 py-3 text-white text-base font-semibold border border-secondary bg-secondary rounded-lg mt-8;
  }

  /* NAVBAR */
  .nav {
    @apply flex justify-between items-center px-6 md:px-20 py-4;
  }

  .nav-logo {
    @apply font-spaceGrotesk text-[21px] text-secondary font-bold;
  }

  /* PRICE INFO */
  .price-info_card {
    @apply flex-1 min-w-[200px] flex flex-col gap-2 border-l-[3px] rounded-10 bg-white-100 px-5 py-4;
  }

  /* PRODUCT CARD */
  .product-card {
    @apply sm:w-[292px] sm:max-w-[292px] w-full flex-1 flex flex-col gap-4 rounded-md;
  }

  .product-card_img-container {
    @apply flex-1 relative flex flex-col gap-5 p-4 rounded-md;
  }

  .product-card_img {
    @apply max-h-[250px] object-contain w-full h-full bg-transparent;
  }

  .product-title {
    @apply text-secondary text-xl leading-6 font-semibold truncate;
  }

  /* SEARCHBAR INPUT */
  .searchbar-input {
    @apply flex-1 min-w-[200px] w-full p-3 border border-gray-300 rounded-lg shadow-xs text-base text-gray-500 focus:outline-none;
  }

  .searchbar-btn {
    @apply bg-gray-900 border border-gray-900 rounded-lg shadow-xs px-5 py-3 text-white text-base font-semibold hover:opacity-90 disabled:pointer-events-none disabled:cursor-not-allowed disabled:opacity-40;
  }
}

index.scraper.ts

"use server"

import axios from 'axios';
import * as cheerio from 'cheerio';
import { extractCurrency, extractDescription, extractPrice } from '../utils';

export async function scrapeAmazonProduct(url: string) {
  if(!url) return;

  // BrightData proxy configuration
  const username = String(process.env.BRIGHT_DATA_USERNAME);
  const password = String(process.env.BRIGHT_DATA_PASSWORD);
  const port = 22225;
  const session_id = (1000000 * Math.random()) | 0;

  const options = {
    auth: {
      username: `${username}-session-${session_id}`,
      password,
    },
    host: 'brd.superproxy.io',
    port,
    rejectUnauthorized: false,
  }

  try {
    // Fetch the product page
    const response = await axios.get(url, options);
    const $ = cheerio.load(response.data);

    // Extract the product title
    const title = $('#productTitle').text().trim();
    const currentPrice = extractPrice(
      $('.priceToPay span.a-price-whole'),
      $('.a.size.base.a-color-price'),
      $('.a-button-selected .a-color-base'),
    );

    const originalPrice = extractPrice(
      $('#priceblock_ourprice'),
      $('.a-price.a-text-price span.a-offscreen'),
      $('#listPrice'),
      $('#priceblock_dealprice'),
      $('.a-size-base.a-color-price')
    );

    const outOfStock = $('#availability span').text().trim().toLowerCase() === 'currently unavailable';

    const images = 
      $('#imgBlkFront').attr('data-a-dynamic-image') || 
      $('#landingImage').attr('data-a-dynamic-image') ||
      '{}'

    const imageUrls = Object.keys(JSON.parse(images));

    const currency = extractCurrency($('.a-price-symbol'))
    const discountRate = $('.savingsPercentage').text().replace(/[-%]/g, "");

    const description = extractDescription($)

    // Construct data object with scraped information
    const data = {
      url,
      currency: currency || '$',
      image: imageUrls[0],
      title,
      currentPrice: Number(currentPrice) || Number(originalPrice),
      originalPrice: Number(originalPrice) || Number(currentPrice),
      priceHistory: [],
      discountRate: Number(discountRate),
      category: 'category',
      reviewsCount:100,
      stars: 4.5,
      isOutOfStock: outOfStock,
      description,
      lowestPrice: Number(currentPrice) || Number(originalPrice),
      highestPrice: Number(originalPrice) || Number(currentPrice),
      averagePrice: Number(currentPrice) || Number(originalPrice),
    }

    return data;
  } catch (error: any) {
    console.log(error);
  }
}

next.config.js

/** @type {import('next').NextConfig} */
const nextConfig = {
  experimental: {
    serverActions: true,
    serverComponentsExternalPackages: ['mongoose']
  },
  images: {
    domains: ['m.media-amazon.com']
  }
}

module.exports = nextConfig

public

https://drive.google.com/file/d/1v6h993BgYX6axBoIXFbZ9HQAgqbR4PSH/view?usp=sharing

tailwind.config.ts

/** @type {import('tailwindcss').Config} */
module.exports = {
  content: [
    "./pages/**/*.{js,ts,jsx,tsx,mdx}",
    "./components/**/*.{js,ts,jsx,tsx,mdx}",
    "./app/**/*.{js,ts,jsx,tsx,mdx}",
  ],
  theme: {
    extend: {
      colors: {
        primary: {
          DEFAULT: "#E43030",
          "orange": "#D48D3B",
          "green": "#3E9242"
        },
        secondary: "#282828",
        "gray-200": "#EAECF0",
        "gray-300": "D0D5DD",
        "gray-500": "#667085",
        "gray-600": "#475467",
        "gray-700": "#344054",
        "gray-900": "#101828",
        "white-100": "#F4F4F4",
        "white-200": "#EDF0F8",
        "black-100": "#3D4258",
        "neutral-black": "#23263B",
      },
      boxShadow: {
        xs: "0px 1px 2px 0px rgba(16, 24, 40, 0.05)",
      },
      maxWidth: {
        "10xl": '1440px'
      },
      fontFamily: {
        inter: ['Inter', 'sans-serif'],
        spaceGrotesk: ['Space Grotesk', 'sans-serif'],
      },
      borderRadius: {
        10: "10px"
      }
    },
  },
  plugins: [],
};

types.ts

export type PriceHistoryItem = {
  price: number;
};

export type User = {
  email: string;
};

export type Product = {
  _id?: string;
  url: string;
  currency: string;
  image: string;
  title: string;
  currentPrice: number;
  originalPrice: number;
  priceHistory: PriceHistoryItem[] | [];
  highestPrice: number;
  lowestPrice: number;
  averagePrice: number;
  discountRate: number;
  description: string;
  category: string;
  reviewsCount: number;
  stars: number;
  isOutOfStock: Boolean;
  users?: User[];
};

export type NotificationType =
  | "WELCOME"
  | "CHANGE_OF_STOCK"
  | "LOWEST_PRICE"
  | "THRESHOLD_MET";

export type EmailContent = {
  subject: string;
  body: string;
};

export type EmailProductInfo = {
  title: string;
  url: string;
};

utils.ts

import { PriceHistoryItem, Product } from "@/types";

const Notification = {
  WELCOME: 'WELCOME',
  CHANGE_OF_STOCK: 'CHANGE_OF_STOCK',
  LOWEST_PRICE: 'LOWEST_PRICE',
  THRESHOLD_MET: 'THRESHOLD_MET',
}

const THRESHOLD_PERCENTAGE = 40;

// Extracts and returns the price from a list of possible elements.
export function extractPrice(...elements: any) {
  for (const element of elements) {
    const priceText = element.text().trim();

    if(priceText) {
      const cleanPrice = priceText.replace(/[^\d.]/g, '');

      let firstPrice; 

      if (cleanPrice) {
        firstPrice = cleanPrice.match(/\d+\.\d{2}/)?.[0];
      } 

      return firstPrice || cleanPrice;
    }
  }

  return '';
}

// Extracts and returns the currency symbol from an element.
export function extractCurrency(element: any) {
  const currencyText = element.text().trim().slice(0, 1);
  return currencyText ? currencyText : "";
}

// Extracts description from two possible elements from amazon
export function extractDescription($: any) {
  // these are possible elements holding description of the product
  const selectors = [
    ".a-unordered-list .a-list-item",
    ".a-expander-content p",
    // Add more selectors here if needed
  ];

  for (const selector of selectors) {
    const elements = $(selector);
    if (elements.length > 0) {
      const textContent = elements
        .map((_: any, element: any) => $(element).text().trim())
        .get()
        .join("\n");
      return textContent;
    }
  }

  // If no matching elements were found, return an empty string
  return "";
}

export function getHighestPrice(priceList: PriceHistoryItem[]) {
  let highestPrice = priceList[0];

  for (let i = 0; i < priceList.length; i++) {
    if (priceList[i].price > highestPrice.price) {
      highestPrice = priceList[i];
    }
  }

  return highestPrice.price;
}

export function getLowestPrice(priceList: PriceHistoryItem[]) {
  let lowestPrice = priceList[0];

  for (let i = 0; i < priceList.length; i++) {
    if (priceList[i].price < lowestPrice.price) {
      lowestPrice = priceList[i];
    }
  }

  return lowestPrice.price;
}

export function getAveragePrice(priceList: PriceHistoryItem[]) {
  const sumOfPrices = priceList.reduce((acc, curr) => acc + curr.price, 0);
  const averagePrice = sumOfPrices / priceList.length || 0;

  return averagePrice;
}

export const getEmailNotifType = (
  scrapedProduct: Product,
  currentProduct: Product
) => {
  const lowestPrice = getLowestPrice(currentProduct.priceHistory);

  if (scrapedProduct.currentPrice < lowestPrice) {
    return Notification.LOWEST_PRICE as keyof typeof Notification;
  }
  if (!scrapedProduct.isOutOfStock && currentProduct.isOutOfStock) {
    return Notification.CHANGE_OF_STOCK as keyof typeof Notification;
  }
  if (scrapedProduct.discountRate >= THRESHOLD_PERCENTAGE) {
    return Notification.THRESHOLD_MET as keyof typeof Notification;
  }

  return null;
};

export const formatNumber = (num: number = 0) => {
  return num.toLocaleString(undefined, {
    minimumFractionDigits: 0,
    maximumFractionDigits: 0,
  });
};

I am getting error 503 when I try to scrape a product. Anyone else dealing with this?

=> Already connected to MongoDB
 ⨯ lib\actions\index.ts (50:10) @ scrapeAndStoreProduct
 ⨯ Error: Failed to create/update product: Failed to scrape product: Request failed with status code 503
    at scrapeAndStoreProduct (./lib/actions/index.ts:60:15)
  48 |     revalidatePath(`/products/${newProduct._id}`);
  49 |   } catch (error: any) {
> 50 |     throw new Error(`Failed to create/update product: ${error.message}`);
     |          ^
  51 |   }
  52 | }
  53 |

Did you find a solution I am experiencing the same problem right now. It worked the first time, but now I get a 503 error.

Not yet, I will post one here if I find it, or maybe someone will post one here when they find it.

Alright thanks, he mentions in the video that it may not work during development when you are using a localhost, so I am hoping that is what is going wrong and it works in production.

i got its solution. it might be due to the imgUrls it was returning.

image: imgUrls[0]||productImg,

changing to this line helped solve the error

Brother where do you change that line?

After deployment, how can the public open the website? I tried opening the link and it says I am not a member of the team and therefore cant view the page.

Hy Guys i am facing the problem that In DB Image and Descreption is not storing other than all the details are storing

` product = {
...scrapedProduct,
priceHistory : updatePriceHistory,
lowestPrice : getLowestPrice(updatePriceHistory),
highestPrice : getHighestPrice(updatePriceHistory),
averagePrice : getAveragePrice(updatePriceHistory),

        }
        console.log(product); //  here i am getting all the details `   

**When i Console log this i get all the details about the product **

` const newProduct = await Product.findOneAndUpdate(
{ url : scrapedProduct.url},
product,
{ upsert : true , new : true}
)

       console.log(newProduct); // here i am not getting all details `   

**When i log this i am not getting getting details like Images , Descreption and users details **

This is the Db Images what i am getting

this is code and repo link

https://github.com/viibhuGupta/eCommerce-Price-Tracker/blob/main/lib/actions/index.ts

I was able to extract the description and categories!

My next goal is to get all the images of the product and show it similar to how the carousel is on home page but without the autoplay
Here is my repo if anyone want to see how: https://github.com/neelp03/pricetracker

FYI headless UI deprecated a lot of the old components.

It easy to transition to the new version but might be a little tricky to find the correct components since a few have been renamed completely. See my repo linked above to see how to implement the track model with the new version!

MongooseError: Operation products.find()buffering timed out after 10000ms at Timeout.<anonymous> (/vercel/path0/node_modules/mongoose/lib/drivers/node-mongodb-native/collection.js:185:23) at listOnTimeout (node:internal/timers:573:17) at process.processTimers (node:internal/timers:514:7) MongooseError: Operationproducts.find() buffering timed out after 10000ms at Timeout.<anonymous> (/vercel/path0/node_modules/mongoose/lib/drivers/node-mongodb-native/collection.js:185:23) at listOnTimeout (node:internal/timers:573:17) at process.processTimers (node:internal/timers:514:7)

I am getting this error when i try to scrape any product.

Anyone having issues with the logos and favicon? It is not displaying properly on VS Code for me....

I am facing this issue and I am using this in India. Does it create problems due to different country? Please anybody suggest the solution, how you successfully did it?

@vivek9124vivek Maybe you missed "use server" in the file where you made axios request. Or you didn't enable serverActions in next.config.js.