AI Scraper
ai_scraperTurn any web page into structured JSON by providing natural-language instructions and an optional output schema. Extract specific fields like company names, contacts, or product details.
Instructions
Extract structured information from a web page with Outscraper AI Scraper.
Best for:
scraping one page and turning it into structured JSON
extracting company, people, product, or document metadata from a site
guiding extraction with both a prompt and a JSON-schema-like shape
This tool is best for extracting structured data from a single page.
How schema works:
schema describes the shape of the output you want back
use type="object" with properties for named fields
use type="array" with items when a field should be a list
add required when some fields must be present
Example schema: { "type": "object", "required": [], "properties": { "company_name": { "type": "string" }, "company_description": { "type": "string" }, "people": { "type": "array", "items": { "type": "string" } } } }
Execution notes:
execution_mode="sync" requests a direct response
execution_mode="async" returns a request id for polling with requests_get
if both prompt and schema are provided, prompt guides the extraction and schema shapes the output
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| async | No | Deprecated compatibility flag. Prefer execution_mode. | |
| query | Yes | One URL to scrape, for example https://outscraper.com. | |
| prompt | No | Natural-language extraction instructions, for example what to summarize or pull from the page. | |
| schema | No | Extraction schema describing the shape of the result. This is typically a JSON-schema-like object with type, properties, and optional required fields. | |
| execution_mode | No | Execution strategy. Use auto to let the MCP server choose between sync and async. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| meta | Yes | ||
| async | No |