How to Clean Messy Product Titles with One API Call (Brand, Size, Color, Tags)

Midwest Design WI — Sun, 08 Nov 2026 23:49:33 +0000

If you've ever imported products from a supplier feed, a marketplace export, or an old spreadsheet, you've seen titles like this:

mens blk nike runing shoe sz 10 NEW!!

Typos, abbreviations, random caps, and hype words. It looks bad on a storefront, it breaks search and filters, and fixing thousands of these by hand is nobody's idea of a good afternoon.

I built a small API that does the cleanup for you. You send it a messy title, and in about 2 seconds you get back clean, structured data.

What goes in

{
  "title": "mens blk nike runing shoe sz 10 NEW!!",
  "description": "lightweight mesh upper"
}

Only title is required. description is optional but helps it fill in details like material.

What comes back

{
  "clean_title": "Nike Men's Running Shoes, Black, Size 10",
  "brand": "Nike",
  "category": "Shoes > Running",
  "color": "Black",
  "size": "10",
  "material": "Mesh",
  "gender": "men",
  "condition": "new",
  "tags": ["nike", "running shoes", "sneakers", "mens shoes", "black", "mesh", "athletic"]
}

Anything it can't figure out comes back as null, so your code doesn't have to guess.

It's not just shoes

Here's what it did with a few completely different products:

Messy title	Clean title	Category
`dewalt 20v max cordless drill driver kit w/ 2 batteries`	Dewalt 20V MAX Cordless Drill Driver Kit with 2 Batteries	Tools > Power Tools > Drills
`apple iphone 13 pro 128gb sierra blu unlocked GREAT COND!!`	Apple iPhone 13 Pro 128GB Sierra Blue Unlocked	Electronics > Cell Phones & Accessories > Smartphones
`ikea malm dresser 6 drawr white used good shape`	IKEA Malm 6-Drawer Dresser, White	Furniture > Dressers

It also picked up that the dresser was used and filled in null for things like size and gender on the drill, instead of making something up.

Try it in JavaScript

const response = await fetch("https://ai-product-data-cleaner.p.rapidapi.com/", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "X-RapidAPI-Key": "YOUR_RAPIDAPI_KEY",
    "X-RapidAPI-Host": "ai-product-data-cleaner.p.rapidapi.com"
  },
  body: JSON.stringify({
    title: "mens blk nike runing shoe sz 10 NEW!!"
  })
});

const product = await response.json();
console.log(product.clean_title);

Try it in Python

import requests

url = "https://ai-product-data-cleaner.p.rapidapi.com/"
headers = {
    "Content-Type": "application/json",
    "X-RapidAPI-Key": "YOUR_RAPIDAPI_KEY",
    "X-RapidAPI-Host": "ai-product-data-cleaner.p.rapidapi.com",
}

product = requests.post(url, json={"title": "mens blk nike runing shoe sz 10 NEW!!"}, headers=headers).json()
print(product["clean_title"], product["tags"])

Cleaning a whole catalog

If you have a CSV export (Shopify, WooCommerce, eBay, etc.), you can loop through it and write the clean data to a new file:

import csv, time, requests

url = "https://ai-product-data-cleaner.p.rapidapi.com/"
headers = {
    "Content-Type": "application/json",
    "X-RapidAPI-Key": "YOUR_RAPIDAPI_KEY",
    "X-RapidAPI-Host": "ai-product-data-cleaner.p.rapidapi.com",
}

with open("products.csv") as f_in, open("products_clean.csv", "w", newline="") as f_out:
    reader = csv.DictReader(f_in)
    fields = ["original_title", "clean_title", "brand", "category", "color", "size", "material", "gender", "condition", "tags"]
    writer = csv.DictWriter(f_out, fieldnames=fields)
    writer.writeheader()

    for row in reader:
        data = requests.post(url, json={"title": row["title"]}, headers=headers).json()
        data["original_title"] = row["title"]
        data["tags"] = ", ".join(data.get("tags") or [])
        writer.writerow({k: data.get(k) for k in fields})
        time.sleep(1)  # stay under the rate limit

Good uses for it

Cleaning up old or imported store catalogs
Standardizing supplier and dropship feeds before they hit your store
Auto-filling filters like brand, color, and size
Generating search tags for listings
Marketplace or inventory apps that accept messy user listings

A couple of honest notes

Results are AI-generated, so for anything critical (pricing pages, legal product claims), give them a quick look before publishing.
Wording can vary slightly between runs, for example "Men's" vs "Mens." If you need strict formatting, add a small cleanup step on your side.

Try it free

There's a free plan with 50 requests a month, which is plenty to test it on your own data:

👉 AI Product Data Cleaner on RapidAPI

If you try it on a weird product and the result is off, drop it in the comments. I'm actively improving it.

Built by Midwest Design WI. This post was written with help from AI.

DEV Community: Midwest Design WI