dataset-scout 0.1.0

Find open climate & weather datasets for any research topic — searches across NOAA, Copernicus, NASA, ECMWF, and more.

Dataset Scout

Find open climate & weather datasets for any research topic. Searches across NOAA, Copernicus, NASA Earthdata, ECMWF, NSIDC, PANGAEA, and more.

Install

pip install dataset-scout

For the web interface:

pip install dataset-scout[web]

Usage

CLI

dataset-scout "Antarctic sea ice thickness"
dataset-scout "Indian Ocean SST reanalysis" --export results.json
dataset-scout "Arctic temperature trends" --limit 15

Python API

from dataset_scout import search_datasets

results = search_datasets("Antarctic blizzard frequency")
for r in results:
    print(f"{r.source} | {r.title}")
    print(f"  {r.url}")

Web App (Streamlit)

dataset-scout-web
# or
streamlit run app.py

What it does

1. Takes your research topic
2. Generates multiple targeted search queries (dataset download, reanalysis, open access, site-specific)
3. Searches DuckDuckGo across 12+ known climate/weather data repositories
4. Deduplicates results
5. Tags each result by type: Direct Download, Data Catalog, Documentation, Publication
6. Identifies the source repository (NOAA, ERA5, NASA, etc.)
7. Sorts known data repositories to the top

Repositories searched

• NOAA
• Copernicus Climate Data Store (ERA5)
• NASA Earthdata
• ECMWF
• NSIDC
• PANGAEA
• Zenodo
• British Antarctic Survey
• India Meteorological Department
• Arctic Data Center
• Australian Antarctic Data Centre
• World Meteorological Organization

License

MIT