# Oxylabs

Oxylabs is a web scraping service that retrieves public web data at scale, with tools designed to navigate regional restrictions.

<figure><img src="/files/RTvOZBPaSa1rV5jIlkDS" alt="" width="260"><figcaption><p>Oxylabs Docuemnt Loader Node</p></figcaption></figure>

### Features

* Retrieve data from Google, Amazon and any other website
* Set geolocation
* Utilize the browser rendering
* Parse the data
* Specify User Agent types
* Process content with text splitters

### Required Parameters

* **Connect Credential**: Oxylabs API credentials
* **Query**: Search query or URL
* **Source**: One of the available sources:
  * Universal - scrape any website
  * Google Search - scrape Google Search results
  * Amazon Product - scrape Amazon Product information
  * Amazon Search - scrape Amazon Search results

### Optional Parameters

* **Geolocation**: Sets the proxy's geo location to retrieve data. See [documentation](https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiwDdoZGfMbUe5cRL2417%2Fuploads%2FxoQb19qSyodB2D4no0DZ%2FList%20of%20supported%20geo_location%20values_sapi.json?alt=media\&token=d2e2df7b-10ba-4399-a547-0c4a99e62293) for more details.
* **Render**: Enables JavaScript rendering when set to true.
* **Parse**: Returns parsed data when set to true, as long as a dedicated parser exists for the submitted URL's page type.
* **User Agent Type**: Device type and browser.

### Outputs

* **Document**: Array of document objects containing metadata and pageContent
* **Text**: Concatenated string from pageContent of documents

## Document Structure

Each document contains:

* **pageContent**: Extracted page content


---

# 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.flowiseai.com/integrations/langchain/document-loaders/oxylabs.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.