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

# Access Sentinel-2 data

> Query Sentinel-2 satellite imagery metadata from a Tilebox dataset, filtering results by geographic area and time range to find exactly the data you need.

This guide assume you already [signed up](https://console.tilebox.com/sign-up) for a Tilebox account (free) and [created an API key](https://console.tilebox.com/settings/api-keys).

## Install Tilebox package

<CodeGroup>
  ```bash uv theme={"system"}
  uv add tilebox
  ```

  ```bash pip theme={"system"}
  pip install tilebox
  ```

  ```bash poetry theme={"system"}
  poetry add tilebox="*"
  ```

  ```bash pipenv theme={"system"}
  pipenv install tilebox
  ```
</CodeGroup>

## Access Sentinel-2 metadata

Query the Sentinel-2A satellite for level 2A data of October 2025 that cover the state of Colorado.

<Note>
  Replace `YOUR_TILEBOX_API_KEY` with your actual API key, or omit the `token` parameter entirely if the `TILEBOX_API_KEY` environment variable is set.
</Note>

<CodeGroup>
  ```python Python theme={"system"}
  from shapely import MultiPolygon
  from tilebox.datasets import Client

  area = MultiPolygon(
      [
          (((-109.05, 41.00), (-109.045, 37.0), (-102.05, 37.0), (-102.05, 41.00), (-109.05, 41.00)),),
      ]
  )

  client = Client(token="YOUR_TILEBOX_API_KEY")
  collection = client.dataset("open_data.copernicus.sentinel2_msi").collection("S2A_S2MSI2A")
  data = collection.query(
      temporal_extent=("2025-10-01", "2025-11-01"),
      spatial_extent=area,
      show_progress=True,
  )
  print(data)
  ```
</CodeGroup>

<CodeGroup>
  ```plaintext Output theme={"system"}
  <xarray.Dataset> Size: 75kB
  Dimensions:                (time: 169)
  Coordinates:
    * time                   (time) datetime64[ns] 1kB 2025-10-02T18:07:51.0240...
  Data variables: (12/23)
      id                     (time) <U36 24kB '0199a61b-e8f0-4028-5db1-6ac962c0...
      ingestion_time         (time) datetime64[ns] 1kB 2025-10-02T23:33:21.4100...
      geometry               (time) object 1kB POLYGON ((-108.635792 40.626649,...
      granule_name           (time) object 1kB 'S2A_MSIL2A_20251002T180751_N051...
      processing_level       (time) uint8 169B 5 5 5 5 5 5 5 5 ... 5 5 5 5 5 5 5 5
      product_type           (time) object 1kB 'S2MSI2A' 'S2MSI2A' ... 'S2MSI2A'
      ...                     ...
      thumbnail              (time) object 1kB 'https://catalogue.dataspace.cop...
      cloud_cover            (time) float64 1kB 0.06321 0.01205 ... 55.23 35.51
      resolution             (time) int64 1kB 0 0 0 0 0 0 0 0 ... 0 0 0 0 0 0 0 0
      flight_direction       (time) uint8 169B 2 2 2 2 2 2 2 2 ... 2 2 2 2 2 2 2 2
      acquisition_mode       (time) uint8 169B 20 20 20 20 20 ... 20 20 20 20 20
      mission_take_id        (time) object 1kB 'GS2A_20251002T180751_053692_N05...
  ```
</CodeGroup>

The output shows that the query returned 169 data points metadata. The metadata is returned as an `xarray.Dataset`.

Now you can check the metadata and decide which data points you want to download.

## Download the data from Copernicus Data Space

Tilebox stores and indexes metadata about datasets but doesn't store the data files.
Sentinel-2 data is stored in the Copernicus Data Space Ecosystem (CDSE). If you never used the CDSE before, [create an account](https://identity.dataspace.copernicus.eu/auth/realms/CDSE/protocol/openid-connect/auth?client_id=cdse-public\&response_type=code\&scope=openid\&redirect_uri=https%3A//dataspace.copernicus.eu/account/confirmed/1) and then generate [S3 credentials here](https://eodata-s3keysmanager.dataspace.copernicus.eu/panel/s3-credentials).

<CodeGroup>
  ```python Python theme={"system"}
  from tilebox.storage import CopernicusStorageClient

  storage_client = CopernicusStorageClient(
      access_key="YOUR_ACCESS_KEY",
      secret_access_key="YOUR_SECRET_ACCESS_KEY",
  )

  for _, datapoint in data.groupby("time"):
      downloaded_data = storage_client.download(datapoint)
      print(f"Downloaded data to {downloaded_data}")
  ```
</CodeGroup>

This code will download all 169 data points to a cache folder. Now you can work with the data, visualize it, and run your custom processor on it.

## Next Steps

<Columns cols={2}>
  <Card title="Open Data" icon="star" href="https://console.tilebox.com/datasets/open-data" horizontal>
    Check out available open data datasets on Tilebox
  </Card>
</Columns>