# CatalogFix AI — Supplier Catalog Parser (`w_met/catalogfix-ai`) Actor

Convert supplier PDF, Excel, and CSV catalogs into structured product data with Ready/Review quality gates, OCR, and an audit trail. Missing supplier SKUs are flagged, not invented.

- **URL**: https://apify.com/w\_met/catalogfix-ai.md
- **Developed by:** [LeadGap AI](https://apify.com/w_met) (community)
- **Categories:** E-commerce, AI
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $4.90 / catalog processed — up to 50 pages

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## CatalogFix AI — Supplier Catalog to Clean Product Data

**Clean supplier catalogs. Nothing invented, nothing guessed.**

CatalogFix AI converts messy supplier PDFs, Excel files, and CSVs into structured product data with a clear **Ready / Needs Review** split.

It is built for one thing most extraction tools handle badly: **uncertainty**.

If a supplier SKU is not printed or cannot be verified, CatalogFix does not fabricate one. If a file is a technical datasheet rather than a product catalog, CatalogFix can intentionally return zero product rows instead of turning technical references into fake products.

### Best for

- supplier catalogs that need to become e-commerce product data;
- image-only PDF catalogs that require OCR;
- mixed catalogs with printed and unprinted supplier codes;
- price lists and order forms;
- teams that need an audit trail instead of a black-box extraction.

### What you get

Every successful catalog run can produce:

- **RESULT.xlsx** — full workbook with Clean Master, Issues Found, Shopify Ready, Needs Review, and Import Report;
- **SHOPIFY\_READY.csv** — only rows that passed the current release gates;
- **SUMMARY.json** — counts, document type, and quality statistics;
- **IMPORT\_REPORT.json** — page/sheet routing and parsing audit;
- **Dataset** — normalized product rows with source and quality context.

### Ready vs Review

CatalogFix does not treat every extracted row as equally trustworthy.

#### Ready

A row is placed in **Ready** only when it passes the current release gates, including required product fields and quality checks.

#### Needs Review

A row is placed in **Needs Review** when something important is uncertain, for example:

- supplier SKU is missing or not confidently verified;
- OCR confidence is low;
- title or product-card boundaries are uncertain;
- required commercial data such as price is missing.

This means a run can legitimately return **zero Ready rows** while still extracting useful product candidates. That is intentional behavior, not a failure.

### Safety behavior

CatalogFix prefers an explicit review state over false certainty.

- Missing supplier SKUs are not invented.
- Internal candidate IDs stay review-only.
- Technical datasheets can be rejected with zero product rows.
- Visual OCR keeps source location and confidence metadata.
- Structured price sources preserve price provenance where available.
- Quality gates keep uncertain records out of Shopify Ready.

**Knowing when not to extract is part of the product.**

### Input

Upload one supplier catalog per run.

Supported formats:

- PDF
- CSV
- XLSX
- XLS

You can also provide a direct HTTP(S) URL.

For URLs that do not preserve a recognizable file extension, use **Filename override**.

### Verified release behavior

CatalogFix AI **v1.9.0** was regression-tested across:

- image-only visual catalogs;
- structured dual-price order forms;
- technical datasheet refusal.

In the image-only Appliances test, the Actor successfully ran RapidOCR on Apify, extracted structured product rows, preserved verified supplier codes such as `DW-01`, `MWO-1`, `FSCR01`, `BIO-01`, `CW-165`, and `CW-46`, and kept uncertain rows in Review.

In the TL972 technical-datasheet test, CatalogFix intentionally returned zero products with a technical-datasheet skip status.

### How it works

1. Upload a catalog.
2. CatalogFix classifies the document and routes pages by content type.
3. Structured parsers handle commercial tables and order forms where possible.
4. Visual pages use adaptive OCR.
5. Quality gates separate Ready rows from review-only rows.
6. Download the structured dataset and audit files.

### Pricing

CatalogFix uses **pay per event** with one charge per completed run:

- **Up to 50 pages:** $4.90
- **51–200 pages:** $12.90
- **201–500 pages:** $24.90
- **Technical/statistical non-catalog screening:** $1.00

The current self-service Store version accepts PDFs up to **500 pages**. Larger catalogs should be split or handled as a managed/custom run.

### Notes and limitations

- OCR-heavy PDFs take longer than text-based catalogs.
- A second OCR pass may be triggered when the first pass is not reliable enough.
- A real supplier SKU can still remain in Needs Review if other required fields are missing.
- CatalogFix does not promise perfect extraction. It makes uncertainty explicit and auditable.

### Current release

**CatalogFix AI v1.9.0**

# Actor input Schema

## `catalogFile` (type: `string`):

Upload a PDF, CSV, XLSX or XLS file, or provide a direct HTTP(S) URL.

## `filenameOverride` (type: `string`):

Use only when the uploaded URL does not preserve a file extension. Example: supplier\_catalog.pdf

## Actor input object example

```json
{}
```

# Actor output Schema

## `productRows` (type: `string`):

Normalized product rows with source and quality context. Run summary is stored separately in SUMMARY.json.

## `resultWorkbook` (type: `string`):

Clean Master, Issues Found, Shopify Ready, Needs Review and Import Report.

## `shopifyReadyCsv` (type: `string`):

Only rows that passed the current CatalogFix release gates.

## `summary` (type: `string`):

Counts, document type, quality statistics and output keys.

## `importReport` (type: `string`):

Per-page or per-sheet routing and parsing audit information.

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {};

// Run the Actor and wait for it to finish
const run = await client.actor("w_met/catalogfix-ai").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {}

# Run the Actor and wait for it to finish
run = client.actor("w_met/catalogfix-ai").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{}' |
apify call w_met/catalogfix-ai --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,w_met/catalogfix-ai"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/QJX8h1Odtl2o8RdVq/builds/TIbUife8alfQB6VuZ/openapi.json