> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zenrows.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Introduction to Extract
> Turn any web page into structured JSON in a single request with Zenrows Extract, which builds a tailored extraction for each website and keeps it working when the site's layout changes.
Extract is in **Beta**. It works on any domain once that domain has been prepared, and you can ask for a new one to be prepared yourself. Any active Zenrows API key can use it, with no extra setup needed.
Zenrows Extract turns a web page into structured JSON in a single request. Add `extract=auto` to your Fetch call, and Zenrows identifies the meaningful data on the page and returns it as clean JSON, together with the raw HTML. There are no selectors to write, no schema to define, and no parser to maintain, and the extraction adapts automatically when a website changes its layout.
## How It Works
Unlike general-purpose parsing rules that apply the same logic to every website, Extract builds and maintains an extraction that's tailored to each individual site. Zenrows analyzes a domain's pages, identifies its meaningful data points, and keeps that extraction working as the site evolves, so you get richer and more complete fields than a one-size-fits-all approach can offer.
## Basic Usage
Enable Extract by adding the `extract=auto` parameter to your Zenrows request:
```bash cURL theme={"dark"}
curl "https://api.zenrows.com/v1/?apikey=YOUR_ZENROWS_API_KEY&url=https%3A%2F%2Fwww.scrapingcourse.com%2Fecommerce%2F&extract=auto"
```
The response returns `Content-Type: application/json` with a `parsed` field containing the structured data, and an `html` field with the raw page for validation during Beta.
Two optional parameters shape what comes back: [`extract_fields`](/extract/setup#selecting-the-fields-you-need) narrows `parsed` to the fields you name, and [`extract=standard`](/extract/setup#extraction-modes) swaps each website's own field names for a canonical schema shared across a vertical, on the API and currently for real estate only.
## Next Steps
Full parameter reference: response shape, domain coverage, pricing, and FAQ.
The deprecated general-purpose parser, and how to migrate an integration off it.
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.