The Scenario
You are a wholesale buyer. A supplier sent you links to twelve of their product category pages two days ago. Your job is to review their catalog and identify which products fit your inventory criteria before the buying call on Friday.
You opened the first category page. It had 47 products on it. You started copying product names into a workbook. By the third page you had 180 rows, inconsistent SKU formatting across suppliers, and a growing suspicion that the fourth page had products that overlapped with the second.
The bad version:
- Open each category page, scroll through all products, manually copy each product name and price into the workbook one by one — except page seven has infinite scroll and stops loading at product 34 unless you keep scrolling
- Discover mid-way that SKU formats vary by supplier division, so your "SKU" column now has three different formats that will not sort correctly
- Finish all twelve pages and find you have 400 rows, but you cannot tell which ones came from which page because you forgot to note the source URL for rows 140 through 210
Your inventory import system expects a clean flat file. What you have is a 400-row mess you are not confident is complete.
The Easy Way: One Prompt in SheetXAI
SheetXAI is an AI agent that lives inside your Excel workbook. It reads your category page URLs, understands the structure you need, and through its built-in ScrapingAnt integration it scrapes every product listed on each page — including JavaScript-rendered products — and compiles them into a single flat catalog worksheet.
Open the SheetXAI sidebar and ask:
Scrape the 12 category pages in column A with ScrapingAnt and compile all products found across all pages into a single Product Catalog worksheet — one row per product with name, SKU, price, and description
SheetXAI processes each category page through ScrapingAnt's headless Chrome renderer — which handles JavaScript-rendered product listings and infinite scroll — and writes every product as its own row in the Product Catalog worksheet. Source URL is tracked so you always know which supplier page each product came from.
What You Get
- A new worksheet named "Product Catalog" with one row per product across all twelve category pages
- Columns: Source URL, Product Name, SKU, Price, Description
- Products from pages with JavaScript-rendered listings captured fully, not truncated at the static HTML boundary
- Total row count accurate to what each page actually listed
What If the Data Is Not Quite Ready
Some category pages paginate — only the first 20 products appear without clicking "Load more"
For each URL in column A, use ScrapingAnt with headless Chrome and simulate scrolling to trigger lazy-loaded products before extracting; write all products found — not just the above-the-fold ones — into the Product Catalog worksheet
SKU formats vary by supplier — you need them normalized to uppercase alphanumeric only
After compiling the Product Catalog worksheet, clean the SKU column so all values are uppercase and contain only letters and numbers — remove any dashes, spaces, or special characters
Two category pages are from the same supplier but have overlapping products — deduplicate
After building the Product Catalog worksheet, check the SKU column for duplicates and in a new column called "Duplicate" write "YES" for any row whose SKU appears more than once; keep the first occurrence and flag the rest
Full catalog pull with dedup and import readiness check in one pass
Scrape all 12 category pages in column A with ScrapingAnt headless Chrome, compile all products into a Product Catalog worksheet with columns: Source URL, Product Name, SKU, Price, Description; normalize SKUs to uppercase alphanumeric; flag duplicate SKUs in a Duplicate column; then in an Import Ready column write "Yes" for rows with all five fields populated and "No" for rows with any blank field
One combined prompt handles the scraping, normalization, deduplication, and quality check.
Try It
Open your supplier URL list in an Excel workbook and Get the 7-day free trial of SheetXAI. Ask it to compile every product from those twelve category pages into a clean Product Catalog worksheet using ScrapingAnt. Also worth reading: how to scrape competitor pricing, and the hub overview for all ScrapingAnt use cases.