> For the complete documentation index, see [llms.txt](https://agpt.co/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://agpt.co/docs/integrations/block-integrations/extract-1.md).

# Firecrawl Extract

Blocks for extracting structured data from web pages using Firecrawl's AI extraction.

## Firecrawl Extract

### What it is

Firecrawl crawls websites to extract comprehensive data while bypassing blockers.

### How it works

This block uses Firecrawl's extraction API to pull structured data from web pages based on a prompt or schema. It crawls the specified URLs and uses AI to extract information matching your requirements.

Define the data structure you want using a JSON schema for precise extraction, or use natural language prompts for flexible extraction. Wildcards in URLs allow extracting data from multiple pages matching a pattern.

### Inputs

| Input               | Description                                                                       | Type            | Required |
| ------------------- | --------------------------------------------------------------------------------- | --------------- | -------- |
| urls                | The URLs to crawl - at least one is required. Wildcards are supported. (/\*)      | List\[str]      | Yes      |
| prompt              | The prompt to use for the crawl                                                   | str             | No       |
| output\_schema      | A Json Schema describing the output structure if more rigid structure is desired. | Dict\[str, Any] | No       |
| enable\_web\_search | When true, extraction can follow links outside the specified domain.              | bool            | No       |

### Outputs

| Output | Description                            | Type            |
| ------ | -------------------------------------- | --------------- |
| error  | Error message if the extraction failed | str             |
| data   | The result of the crawl                | Dict\[str, Any] |

### Possible use case

**Product Data Extraction**: Extract structured product information (prices, specs, reviews) from e-commerce sites.

**Contact Scraping**: Pull business contact information from company websites in a structured format.

**Data Pipeline Input**: Automatically extract and structure web data for analysis or database population.

***


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://agpt.co/docs/integrations/block-integrations/extract-1.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.