> For the complete documentation index, see [llms.txt](https://docs.scraperapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.scraperapi.com/resources/release-notes/june-2026/introducing-ai-parser-turn-any-web-page-into-structured-data-with-ai.md).
# Introducing AI Parser: Turn Any Web Page Into Structured Data with AI
### What is AI Parser?
AI Parser turns raw HTML into structured data automatically. Feed it a few example URLs of the same page type (say, three product pages from a catalog), and it generates a custom parser that extracts the important fields from any similar page on that site.
## How It Works
* Getting started takes three steps:
1. **Train** — Send up to 3 example URLs of the same page type to `POST /parsers`.
2. **Wait** — The system generates a parser tailored to the page's layout (typically under a minute).
3. **Parse** — Send any similar URL to `GET /parse/{parser_id}` and get structured data back.
### Key Features
**AI-Powered Data Extraction**
No need to write selectors or maintain scraping logic. AI Parser identifies relevant fields and structures data automatically.
**Custom Field Definitions**
Guide extraction by defining exactly which fields you want, including:
* Field names
* Descriptions
* Data types
* Optional CSS or XPath selectors
:bulb: **Parser Versioning**
Every parser maintains a version history:
* Safely iterate on extraction schemas
* Pin production workloads to specific versions
* Update fields without disrupting existing integrations
**Flexible Parser Updates**
Modify existing parsers without starting from scratch:
* Add new fields
* Improve extraction accuracy
* Rename fields
* Remove outdated fields
**Full ScraperAPI Integration**
Pass standard ScraperAPI parameters (render, premium, ultra\_premium, country\_code, and more) when creating a parser or parsing a URL—so JavaScript rendering, proxies, and geotargeting all work out of the box.
### Pricing & Availability
* :tada: Every account receives **one free parser**
* Additional parser generation costs **30,000 API Credits**
* Parsing requests use your existing ScraperAPI infrastructure and standard scraping costs apply
* Available now for all ScraperAPI users
### Why AI Parser?
Traditional scraping requires building and maintaining extraction logic for every site. AI Parser dramatically reduces setup time by learning page structures automatically and adapting extraction schemas through simple API calls.
Get started today by training your first parser with just a few example URLs and start extracting structured data in minutes.
Try your first parser for free
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.scraperapi.com/resources/release-notes/june-2026/introducing-ai-parser-turn-any-web-page-into-structured-data-with-ai.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.