# Scraping

Scraping means the ability to read the contents of a web page. This functionality is built into your workers automatically, if Toolhouse detects your worker needs it. You can also add it manually.

## How scraping works

Your worker will have access to a scraper integration as needed. The scraper will try its best to read the contents of a webpage.

Scraping means reading websites. Scraping is not a technique to perform actions such as filling out forms or logging into websites.

By default, your worker will see an AI friendly version of the website. This means it will only see basic styling, but will not see the actual code of the page. If you need the worker to see the entire page code, edit your agent in [Agent Editor](/toolhouse/toolhouse/agent-editor.md) and tell the editor: "I want my worker to scrape the page in HTML format".

{% hint style="info" %}
Accessing private pages in an automated way often violates the terms of service of the platform you're trying to access. If you are looking to extract data from platforms that require authorization, such as Linkedin or Instagram, you can use our [Integrations](/toolhouse/toolhouse/integrations.md).
{% endhint %}

## Supported countries

Sometimes the contents of a page change when you connect from a different country. Your worker can be instructed to connect to a specific location among the ones we support. This is useful to retrieve the exact contents you need.

Supported countries:

* Australia
* Brazil
* Canada
* Denmark
* France
* Germany
* Italy
* Malaysia
* Mexico
* Norway
* Singapore
* Spain
* United Kingdom
* United States
* Vietnam

{% hint style="info" %}
The list of supported countries may change at any time without prior notice. It is provided solely for reference.
{% endhint %}

## Adding Scraping Manually

* Go to [Agents](https://toolhouse.app/agents) in your Toolhouse
* Click on your worker to edit it
* Select <i class="fa-wrench">:wrench:</i> **Integrations,** then click **Add Integration**
* Choose **Metascraper**
* Click **Save changes**


---

# Agent Instructions: 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:

```
GET https://docs.toolhouse.ai/toolhouse/capabilites/scraping.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.