Place search guide / 2026

Place Search API for AI Agents in 2026

Location-aware agents need structured candidates rather than an autocomplete widget. A submitted place query can return names, coordinates, address components, and source attribution in one predictable response.

Quick answer

Turn one place query into structured candidates.

Submit a place query and receive up to 10 provider-neutral place documents with coordinates and address fields when available. Results retain required OpenStreetMap attribution.

curl --get 'https://extractor.sh/api/places' \
  --data-urlencode 'q=Brandenburg Gate Berlin' \
  --data-urlencode 'limit=5' \
  --data-urlencode 'format=json'

Available data

What you can extract

Up to 10 ordered place candidates
Names, coordinates, and address components when available
Provider-neutral schema-v1 JSON or Markdown
OpenStreetMap attribution

AI workflows

Where normalized data helps

Travel and local discovery agents
Place normalization and geocoding
Location-aware RAG
Research and itinerary workflows

AI-ready output

Markdown for models. JSON for systems.

Raw HTML consumes tokens on navigation, scripts, styling, and interface labels. Clean Markdown keeps the readable hierarchy for LLM prompts and RAG chunks. Normalized JSON is better when your application needs an explicit semantic type, source, author, publication date, media, attributes, and collection items.

Always retain the canonical URL from the response. AI-generated summaries should remain traceable to the public source, especially when the underlying page can change.

Boundaries

Public data only

The public service is intended for fair-use submitted searches, not autocomplete traffic.
Results are candidates and should be validated for critical navigation.
Coverage and address detail vary by location.

extractor.sh does not bypass CAPTCHAs, login walls, paywalls, access controls, or regional restrictions. Review the source’s terms and applicable law before collecting or reusing data.