How to build a Black Friday price tracker with Firecrawl Alexandria

Juan Pablo HernandezJuan Pablo Hernandez
Nov 18, 2026

TL;DR

  • I pulled Black Friday prices for 685 products with Firecrawl Alexandria a week before the sale. The Shopify, Walmart and Best Buy providers return the current price and the list price as fields, so there was no page parsing. The whole run cost 80 Firecrawl credits.
  • Most products were already on sale. 52% of Shopify products, 66% at Walmart and 91% at Best Buy sat below their list price, with median markdowns of 38% to 45%.
  • To see which deals stores push hardest, I used the Upspring provider to find live Black Friday ads and their landing pages. Those pages went on a daily Firecrawl /monitor.

P.S. You can run all of this from ChatGPT, Claude or any other AI assistant without writing code. Here's how to set it up.


I wanted to see how far Black Friday prices had already dropped at Shopify stores, Walmart and Best Buy, and whether a deal-alert bot or a shopping agent could get those numbers without parsing product pages. That takes the current price and list price for every product, plus an alert when a sale page I'm watching changes its offer.

A week before Black Friday, I built a Black Friday price tracker with Firecrawl Alexandria, which reads prices straight from store catalogs. Firecrawl /monitor watches the sale pages behind the strongest ads and tells me when an offer moves. I also used Upspring, our partner for ad data, to see which deals stores were advertising.

What I found when I checked 685 products

More than half of the products I checked were already discounted before Black Friday. I ran 16 searches through Firecrawl Alexandria across Shopify stores, Walmart and Best Buy, and compared each product's current price with its list price. The median markdown sat between 38% and 45%.

Where I lookedProductsBelow list priceMedian markdown
Shopify stores, 10 searches from hoodies to coffee makers50052%45%
Walmart: TVs, headphones, laptops12066%38%
Best Buy: TVs, headphones, laptops6591%41%

Clothing had the deepest cuts. Hoodies on Shopify had a median markdown of 59% and winter jackets 50%. Moisturizers sat at 23% and coffee makers at 25%, so the "everything is half off" feeling depends a lot on the category.

Note: each store sets its own list price, so a markdown is the store's own claim. I used the first page of results for each search.

A price tracker needs that baseline, because a 30% deal looks generous until you see that the median product next to it is already at 45%.

How Firecrawl Alexandria gets the prices

Firecrawl Alexandria is Firecrawl's library of data providers. Your code or agent calls any of them with the same Firecrawl API key, and each call costs the Firecrawl credits listed on it. Finding a tool is free.

For this job I needed four providers:

What I wantedProvider and capability
Products and prices across Shopify storesShopify catalog/search_catalog, or catalog/lookup_catalog for URLs I already had
Big-box pricesWalmart and Best Buy products/search
Live Black Friday ads and their landing pagesUpspring ads/search and ads/detail

Going direct would have meant separate Shopify, Walmart and Best Buy integrations plus an ad-data subscription, each with its own account and format. Firecrawl Alexandria put all of it on one key and one bill. The product searches cost 5 Firecrawl credits each, so my 16 searches for 685 products came to 80.

The Firecrawl Alexandria docs cover the full API. If you want the short version of the idea, there's a plain-English explainer.

Pulling prices with the Firecrawl SDK

Firecrawl Alexandria runs through the scrape call you may already use. Instead of a URL, you pass a list of provider calls, up to 10 per request. I put the Upspring ad search and a Shopify product search in the same request:

import { Firecrawl } from "firecrawl";
 
const firecrawl = new Firecrawl({ apiKey: process.env.FIRECRAWL_API_KEY });
 
const result = await firecrawl.scrape({
  alexandria: [
    {
      provider: "upspring",
      capability: "ads/search",
      options: { q: "black friday", vertical: "apparel", recency_days: "14", is_active: "true", limit: "20" },
    },
    {
      provider: "shopify",
      capability: "catalog/search_catalog",
      options: { query: "winter jacket", limit: 50 },
    },
  ],
});
 
const [ads, products] = result.alexandria;
console.log(ads.data?.data?.length, "live Black Friday ads");
console.log(products.data?.products?.length, "Shopify products with price and list price");

When I ran it, it printed 20 live Black Friday ads and 50 Shopify products. Two details tripped me up. Upspring wants its option values as strings, while Shopify takes real numbers. And Shopify prices come back in cents, as { amount, currency } under each product's variants, with list_price right next to price.

Each entry in result.alexandria carries either its data or its own error, so one failing provider doesn't break the rest. Install the Node SDK with npm install firecrawl. The Python SDK, the REST API and the CLI take the same alexandria list.

Finding the deals stores advertise

Ads show which deals a store is betting on, so their landing pages are the ones I track first. The Upspring provider returns live sale ads in a category, and ads/detail gives the landing page behind each ad. An ad search costs 50 Firecrawl credits and each detail 100, so I only open the strongest few.

The landing page doesn't always match the ad. In one of my test runs, an ad promised "up to 70% off" while the page it linked to showed about 50%, which I'd only have caught by reading the page next to the ad.

Firecrawl /scrape reads any of those pages as clean text, and the Shopify provider prices the products on them. Minimal runs nearly six million storefront pages a month through Firecrawl.

Storefronts come to us in every shape imaginable, and no matter the complexity, Firecrawl turns each one into clean, structured data our AI support agents can answer from.

Niek Hogenboom, Co-Founder, Minimal

Upspring wrote up the ad side in more depth in their Black Friday guide, which we built together. For Google ads and podcast sponsorships through the same API, see the competitor ads guide.

Watching the pages with Firecrawl /monitor

A price check only tells me what a page says today. During sale week I want to hear when something changes without checking myself. Firecrawl /monitor checks a list of pages on a schedule, compares each check with the last, and marks every page as same, new, changed or removed.

Sale pages change all day, with countdown timers and rotating banners, so a simple diff would alert me constantly. A goal written in plain language tells the AI judge which changes count:

const landingPages = ["https://example.com/black-friday-sale"];
 
const monitor = await firecrawl.createMonitor({
  name: "Black Friday deal pages",
  schedule: { text: "daily at 9am", timezone: "America/New_York" },
  targets: [{ type: "scrape", urls: landingPages, scrapeOptions: {} }],
  goal: "Alert when the price, the discount percentage or the sale end date changes. Ignore banners, timers and layout changes.",
});
 
console.log(monitor.id, monitor.estimatedCreditsPerMonth);

For one page checked daily, Firecrawl /monitor estimated 60 Firecrawl credits a month. The first check saved a baseline for 1 Firecrawl credit. Alerts can go to a webhook, email or Slack. If you want the full setup, the Firecrawl monitoring tutorial goes through notifications and scaling.

Running the Black Friday price tracker from ChatGPT, Claude or other AI assistants

I did most of this from code, but you don't need to. ChatGPT, Codex, Claude and Grok Bot have a native Firecrawl connector. Claude Code, Cursor and other MCP clients connect to the Firecrawl MCP server.

Sign in, or add an API key from a team with Firecrawl Alexandria enabled. Firecrawl Alexandria doesn't run on keyless access.

For Claude Code, Cursor or any MCP client, add the Firecrawl MCP server with its sign-in URL:

{
  "mcpServers": {
    "firecrawl": { "type": "http", "url": "https://mcp.firecrawl.dev/v2/mcp-oauth" }
  }
}

Give the agent the whole job in one prompt:

Use Firecrawl Alexandria to build me a Black Friday price tracker.
First find the matching Firecrawl Alexandria tools and their prices with firecrawl_search (sources: alexandria) and firecrawl_find_tools, then call them.
1. Search Shopify for "winter jacket" and Best Buy for "headphones". For each product, give the current price, the list price and the markdown.
2. Use the Upspring provider to find live Black Friday ads in apparel and the landing page of the five strongest.
3. Create a Firecrawl monitor on those landing pages, daily at 9am, that alerts me when a price, discount or sale end date changes.
Show the Firecrawl credits each step will use before you run it.

If you'd rather start from working code, I put the whole flow in an open-source Black Friday ad radar. It goes from ad search to a daily digest and a monitor.

What a week of Black Friday price tracking costs

For one category, a full week stays under 1,500 Firecrawl credits. My setup added up like this:

StepFirecrawl credits
20 product searches across Shopify, Walmart and Best Buy100
One Upspring ad search plus 8 landing pages850
Firecrawl /monitor on 20 pages, daily for 10 daysAbout 400
TotalAbout 1,350

A free Firecrawl account comes with 1,000 Firecrawl credits, and the pricing page lists the plans.

With a few days left, I'd start with five products you care about and the five pages behind the strongest ads in your category. One Firecrawl Alexandria request and a daily monitor are enough to see the market move. The Firecrawl Alexandria catalog has the other providers you can add to the same request later.

Use Firecrawl in your agent

Add Firecrawl to ChatGPT, Claude, Cursor and more in one click.

Frequently Asked Questions

How do I build a Black Friday price tracker?

Search products through Firecrawl Alexandria, which returns the current and list price from Shopify stores, Walmart and Best Buy. Then put the key pages on a daily Firecrawl monitor with a goal, so you get an alert when a price or discount changes.

Do I need a Shopify, Walmart or Best Buy account?

No. Firecrawl Alexandria calls each provider for you with one Firecrawl API key and bills every call in Firecrawl credits at the listed price.

How is Firecrawl Alexandria billed?

Finding a tool is free, and running one costs the Firecrawl credits listed on it. A Shopify, Walmart or Best Buy search costs 5, and an Upspring ad search costs 50. Every response reports what it used.

Does Firecrawl Alexandria work without an API key?

Keyless access covers search, scrape and parse within daily limits, but not Firecrawl Alexandria. It needs a signed-in connection or an API key from a team with Firecrawl Alexandria enabled, and a free account includes 1,000 Firecrawl credits.

Can Firecrawl /monitor tell a real price change from a banner change?

It can, once you give it a goal. Name what matters, such as price, discount or sale end date, and the AI judge skips changes that do not match it.

How often should a price tracker check prices during Black Friday week?

A daily check fits most stores. If a store changes offers more often near Black Friday, a Firecrawl monitor can run every few hours, down to every 5 minutes.

What is Firecrawl Alexandria?

Firecrawl Alexandria is Firecrawl's library of data providers and indexes, reached through one Firecrawl API key. Your code or agent finds a provider, sees its price in Firecrawl credits and calls it through the same scrape request it already uses.

//
Get started
//
Ready to build?
Start getting web context for free and scale seamlessly as your project expands. No credit card needed.
Are you an AI agent? See setup options
Juan Pablo Hernandez
Juan Pablo Hernandez @juampitech
Growth Marketer at Firecrawl
About the Author
Juan Pablo Hernandez is a Growth Marketer at Firecrawl. He works on partner content and integrations, helping agent frameworks and developer tools connect to live web data with Firecrawl.