> 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/crawl.md).

# Firecrawl Crawl

Blocks for crawling multiple pages of a website using Firecrawl.

## Firecrawl Crawl

### What it is

Firecrawl crawls websites to extract comprehensive data while bypassing blockers.

### How it works

This block uses Firecrawl's API to crawl multiple pages of a website starting from a given URL. It navigates through links, handling JavaScript rendering and bypassing anti-bot measures to extract clean content from each page.

Configure the crawl depth with the limit parameter, choose output formats (markdown, HTML, or raw HTML), and optionally filter to main content only. The block supports caching with configurable max age and wait times for dynamic content.

### Inputs

| Input               | Description                                                                                             | Type                                                                                                                        | Required |
| ------------------- | ------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------- | -------- |
| url                 | The URL to crawl                                                                                        | str                                                                                                                         | Yes      |
| limit               | The number of pages to crawl                                                                            | int                                                                                                                         | No       |
| only\_main\_content | Only return the main content of the page excluding headers, navs, footers, etc.                         | bool                                                                                                                        | No       |
| max\_age            | The maximum age of the page in milliseconds - default is 1 hour                                         | int                                                                                                                         | No       |
| wait\_for           | Specify a delay in milliseconds before fetching the content, allowing the page sufficient time to load. | int                                                                                                                         | No       |
| formats             | The format of the crawl                                                                                 | List\["markdown" \| "html" \| "rawHtml" \| "links" \| "screenshot" \| "screenshot\@fullPage" \| "json" \| "changeTracking"] | No       |

### Outputs

| Output                 | Description                           | Type                   |
| ---------------------- | ------------------------------------- | ---------------------- |
| error                  | Error message if the crawl failed     | str                    |
| data                   | The result of the crawl               | List\[Dict\[str, Any]] |
| markdown               | The markdown of the crawl             | str                    |
| html                   | The html of the crawl                 | str                    |
| raw\_html              | The raw html of the crawl             | str                    |
| links                  | The links of the crawl                | List\[str]             |
| screenshot             | The screenshot of the crawl           | str                    |
| screenshot\_full\_page | The screenshot full page of the crawl | str                    |
| json\_data             | The json data of the crawl            | Dict\[str, Any]        |
| change\_tracking       | The change tracking of the crawl      | Dict\[str, Any]        |

### Possible use case

**Documentation Indexing**: Crawl entire documentation sites to build searchable knowledge bases or training data.

**Competitor Research**: Extract content from competitor websites for market analysis and comparison.

**Content Archival**: Systematically archive website content for backup or compliance purposes.

***


---

# 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/crawl.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.