> ## Documentation Index
> Fetch the complete documentation index at: https://docs.phidata.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Firecrawl

**FirecrawlTools** enable an Agent to perform web crawling and scraping tasks.

## Prerequisites

The following example requires the `firecrawl-py` library and an API key which can be obtained from [Firecrawl](https://firecrawl.dev).

```shell theme={null}
pip install -U firecrawl-py
```

```shell theme={null}
export FIRECRAWL_API_KEY=***
```

## Example

The following agent will scrape the content from [https://finance.yahoo.com/](https://finance.yahoo.com/) and return a summary of the content:

```python cookbook/tools/firecrawl_tools.py theme={null}
from phi.agent import Agent
from phi.tools.firecrawl import FirecrawlTools

agent = Agent(tools=[FirecrawlTools(scrape=False, crawl=True)], show_tool_calls=True, markdown=True)
agent.print_response("Summarize this https://finance.yahoo.com/")
```

## Toolkit Params

| Parameter | Type        | Default | Description                                                   |
| --------- | ----------- | ------- | ------------------------------------------------------------- |
| `api_key` | `str`       | `None`  | Optional API key for authentication purposes.                 |
| `formats` | `List[str]` | `None`  | Optional list of formats to be used for the operation.        |
| `limit`   | `int`       | `10`    | Maximum number of items to retrieve. The default value is 10. |
| `scrape`  | `bool`      | `True`  | Enables the scraping functionality. Default is True.          |
| `crawl`   | `bool`      | `False` | Enables the crawling functionality. Default is False.         |

## Toolkit Functions

| Function         | Description                                                                                                                                                                                                                                             |
| ---------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `scrape_website` | Scrapes a website using Firecrawl. Parameters include `url` to specify the URL to scrape. The function supports optional formats if specified. Returns the results of the scraping in JSON format.                                                      |
| `crawl_website`  | Crawls a website using Firecrawl. Parameters include `url` to specify the URL to crawl, and an optional `limit` to define the maximum number of pages to crawl. The function supports optional formats and returns the crawling results in JSON format. |

## Information

* View on [Github](https://github.com/agno-agi/phidata/blob/main/phi/tools/firecrawl.py)