> For the complete documentation index, see [llms.txt](https://sentinel-11.gitbook.io/sentinel-scout-ai-data-layer/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://sentinel-11.gitbook.io/sentinel-scout-ai-data-layer/data-retrieval-features.md).

# Data Retrieval Features

#### 1. Geo-Location

Sentinel Scout enables scraping jobs to be executed from specific **countries, cities, or ISPs** by leveraging its distributed proxy network.\
\
This makes it possible to access geo-restricted content, verify localized site versions, and build region-specific datasets.

***

#### 2. Excluding / Including Tags

Scout provides fine control over the content returned from a scrape.\
\
Users can specify which HTML tags to remove or retain, ensuring cleaner outputs and reducing noise for downstream processing.

***

#### 3. Data Formats

Scraped content can be retrieved in different formats depending on the use case.

* **HTML** for preserving structure and layout.
* **JSON** for structured, programmatic consumption.
* **Markdown** (coming soon) for lightweight, human-readable workflows.