# Website

This loader collects raw text from websites, ignoring images and code blocks. It can refresh and track URLs similar to other data loaders, identifying changes in the website structure and prompting the user accordingly. Future features include parsing media (images, videos, code blocks) and flagging data conflicts or unwanted elements like PII.

{% hint style="info" %}
You cannot have multiple website agents attached to the same URL.
{% endhint %}

Website Agents can be linked to a direct URL, or a sitemap. If you provide a link to a sitemap, we'll only scrape the pages defined in the sitemap, and the scraping depth will not be used.

{% embed url="<https://seocrawl.com/en/how-to-find-a-sitemap/>" %}
How to find the sitemap of a website
{% endembed %}


---

# 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.katara.ai/about/agents/loaders/website.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.