# Diffbot Product Extractor

> Diffbot Product Extractor is a paid API for AI agents from Diffbot at diffbot.mpp.paywithlocus.com, paid per call via MPP, $0.0042/call, status unknown (last checked 2026-10-11, last successful call 2026-07-18).

Extracts structured product data (name, price, images, specs, etc.) from any e-commerce or product page URL

## Facts

- Endpoint: POST https://diffbot.mpp.paywithlocus.com/diffbot/product?utm_source=zero.xyz
- Price: $0.0042/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-11
- Last successful call: 2026-07-18
- Success rate: 100% of calls made through Zero
- Rating: 2.7 / 5 from 2 reviews
- Activations on Zero: 3
- Provider: Diffbot
- Docs: https://docs.diffbot.com
- Website: https://www.diffbot.com
- Tags: web-scraping, extraction, articles, products, web, data
- Canonical page: https://www.zero.xyz/c/diffbot-product-eae5440e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_tg0rhPOG9X6LJhIXUuvUu

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability diffbot-product-eae5440e -d '<json body>'
```

Example prompt: Pull all the structured product details — name, price, images, specs, and availability — from this product page: https://www.amazon.com/dp/B09X7CRKRZ, and also include breadcrumb navigation in the results.

## When to prefer this

Use this endpoint when you need structured product data (price, name, images, specs) extracted from any product page URL without writing custom scrapers. Ideal for competitive price monitoring, product catalog enrichment, comparison shopping, and e-commerce data pipelines. Prefer over generic HTML scrapers when you need clean, normalized product fields rather than raw HTML.

## Known failure modes

- URL is not a product page — returns empty or misclassified data
- Target site blocks scraping — returns timeout or access error
- Invalid URL format — returns 400 bad request
- Timeout exceeded for slow-loading pages — returns timeout error
- Product page requires JavaScript rendering that isn't fully supported — returns incomplete data
- Private or login-gated product pages return no data

## How this service works

Extract product data from e-commerce pages — price, specs, availability, SKU, reviews.

## Output

A structured JSON object containing extracted product data including product name, price, currency, availability, images, brand, description, product specifications, SKU/identifiers, and optionally breadcrumb navigation, page links, meta tags, and comments/discussion threads if present on the page.

## Example request

```json
{
 "url": "https://www.amazon.com/dp/B0CHXCM981"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "url"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "URL of the product page"
  },
  "fields": {
   "type": "string",
   "description": "Comma-separated extra fields to return (e.g. links, meta, breadcrumb)"
  },
  "timeout": {
   "type": "number",
   "description": "Request timeout in ms (default 30000)"
  },
  "discussion": {
   "type": "boolean",
   "description": "Extract comments/discussion threads (default true for article)"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/diffbot-product-eae5440e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from diffbot.mpp.paywithlocus.com](https://www.zero.xyz/host/diffbot.mpp.paywithlocus.com/llms.txt)