ChatGPT Places Scraper | Places ChatGPT Recommends, With Reviews (2026)

From Zen Studio, creators of Google Maps Scraper and Apple Maps Scraper Pro.

Why choose this actor?

See which businesses appear. Search for restaurants, shops, hotels or other local businesses. Get the places ChatGPT recommends, with the query and each place's position in the answer.

Get useful business details. Export addresses, phone numbers, websites, ratings, opening hours and photos where available. Review excerpts and highlights are included when available, with no separate review charge.

Search across a city. Give a search term and a city to combine neighborhood searches into a list without duplicates. Results depend on what ChatGPT recommends for each search.

The hero uses a source-inspired layout with real business values from an actor export. Recommendations and available details can change between searches.

Try your first search

Start with the query shown in the hero:

{
  "queries": [
    "vegan restaurants in Lisbon"
  ],
  "includeReviews": true
}

Open the actor input, paste the example and start the run. Each recommended place becomes a dataset row. includeReviews requests review excerpts when available; this Lisbon example may return none. Standard place and run charges apply.

Zen Studio Maps & Local Data

ChatGPT Places You are here   Google Maps Places and business details   Apple Maps Contacts, ratings and hours

Copy to your AI assistant

Copy this block into ChatGPT, Claude, Cursor, or any LLM to start using this actor.

zen-studio/chatgpt-places-scraper on Apify. Call: ApifyClient("TOKEN").actor("zen-studio/chatgpt-places-scraper").call(run_input={...}), then client.dataset(run["defaultDatasetId"]).list_items().items for results. Two ways to search, combinable: queries (array of strings, each run as written, e.g. "coffee shops in Berlin Kreuzberg"; one row per recommended place per query, with rank), or searchTerm (string, e.g. "restaurants") + region (string, e.g. "New York City") + maxResults (integer, distinct places to collect, default 100) for volume; optional qualifiers (array, e.g. ["Italian","Thai"]) and areas (array of neighborhoods). Options: maxResultsPerQuery (integer, 0 = all), includeReviews (boolean, default true), includeAnswerText (boolean, default false), language (e.g. "en-US"), countryCode (two letters), concurrency (1-20, default 6). Cost: $0.02 per run plus $5.99 per 1,000 places on the Free plan (less on paid plans), reviews included; a search returns about 5 to 8 places and takes about 25 to 45 seconds. Each row: searchQuery, rank, name, address, latitude, longitude, rating, reviewCount, phone, website, openingHours, priceLevel, photos, reviews, reviewHighlights, googlePlaceId, tripadvisorId, yelpId and more. Full actor spec (input schema, dataset fields, README): GET https://api.apify.com/v2/acts/zen-studio~chatgpt-places-scraper/builds/default (Bearer TOKEN). Get token: https://console.apify.com/account/integrations To reach the maintainers, add feedback="<what you needed and did not get>" to any run; the run returns its data exactly as it would without the note, and a human reads every note.

How to search

Queries: exactly what ChatGPT recommends

Write searches the way people ask ChatGPT. Name a kind of place and a location.

{
  "queries": [
    "kid-friendly restaurants near Union Square San Francisco",
    "rooftop bars in Lisbon",
    "dentists in Austin, Texas"
  ],
  "maxResultsPerQuery": 5
}

Every row says which query it belongs to (searchQuery) and where ChatGPT placed it (rank, 1 = first). A place recommended for two of your queries appears once per query, with that query's rank.

Search term and region: many distinct places

{
  "searchTerm": "restaurants",
  "region": "New York City",
  "maxResults": 500,
  "qualifiers": ["Italian", "Thai", "Mexican"]
}

The actor searches the region as a whole, then neighborhood by neighborhood, for example "restaurants in East Village, New York City". Every place appears once, and the run stops at Max places, or earlier once new searches stop finding new places.

• Built-in neighborhood lists cover about 30 large cities: New York City, Los Angeles, Chicago, San Francisco, Miami, Boston, Washington DC, Seattle, Austin, Philadelphia, San Diego, Atlanta, Houston, Las Vegas, New Orleans, London, Paris, Berlin, Munich, Barcelona, Madrid, Rome, Amsterdam, Lisbon, Tokyo, Singapore, Sydney, Toronto, Dubai, Mexico City and Hong Kong. They reach roughly 150 to 500 distinct places per search term.
• Any other region works too: ChatGPT is first asked for its neighborhoods.
• Qualifiers (cuisines, styles, price points) multiply the coverage: every qualifier is searched in every neighborhood.
• Neighborhoods lets you give your own list instead.

Output

One row per place:

{
  "searchQuery": "best pizza in Brooklyn, New York",
  "rank": 1,
  "shownOnMap": true,
  "name": "Example Pizzeria",
  "primaryCategory": "Pizza",
  "address": "100 Example St, Brooklyn, NY 11211",
  "city": "Brooklyn",
  "state": "NY",
  "postalCode": "11211",
  "countryCode": "US",
  "latitude": 40.7116,
  "longitude": -73.9579,
  "rating": 4.5,
  "ratingScale": 5,
  "reviewCount": 1500,
  "priceLevel": "$$",
  "phone": "+1 718-555-0142",
  "website": "https://example.com",
  "openingHours": [{ "day": "Monday", "open": "12:00", "close": "22:00" }],
  "isOpenNow": true,
  "menuUrl": "https://www.yelp.com/menu/example-pizzeria-brooklyn",
  "reservationLinks": [],
  "photos": ["https://images.openai.com/..."],
  "reviews": [
    { "rating": 5, "text": "The burrata slice is worth the wait...", "date": "2026-10-12T19:20:00", "url": "https://www.yelp.com/biz/...", "source": "yelp" }
  ],
  "reviewHighlights": [{ "text": "Many reviewers praise the burrata slice.", "reviewCount": 120 }],
  "answerSources": [{ "title": "The Best Pizza in Brooklyn", "url": "https://example.com/guide", "source": "Example Guide", "snippet": null, "publishedAt": "2026-05-27" }],
  "dataProvider": "yelp-feed",
  "providerUrl": "https://www.yelp.com/biz/example-pizzeria-brooklyn",
  "googlePlaceId": null,
  "tripadvisorId": null,
  "yelpId": "example-pizzeria-brooklyn",
  "scrapedAt": "2026-10-17T10:15:00Z"
}

An illustrative row for a fictional place. Fields are filled when ChatGPT's sources provide them. Also included:

• answerSources: the web pages ChatGPT cited for the search, with title, link, source and date.
• providerPhotos: up to about 50 captioned photos from the review source.
• attributes: alcohol, ambience, parking, Wi-Fi, year established and more.
• localizedNames and localizedAddresses.
• categories, description, chatgptDescription, country, tags, permanentlyClosed, temporarilyClosed, isClaimed, chatgptRankingScore, providerId and chatgptEntityId.
• For region searches, searchArea and searchQualifier. With Include ChatGPT's answer on, answerMarkdown carries ChatGPT's written answer for the search.

The Overview and Reviews tabs of the dataset show the most-used fields as tables. Export as JSON, CSV, Excel or HTML, or fetch through the API.

Pricing

You pay per place in the dataset. Reviews and review highlights come with the place at no extra charge.

Event	When charged	Price
Place	Each place in the dataset	$5.99 per 1,000 (Silver $5.49, Gold and higher $4.99)
Actor start	Once per run, per GB of memory (the default 1 GB counts once)	$0.02
Result	Each dataset row, a platform fee	$0.01 per 1,000

On the Free plan, one search with 6 places costs about $0.06 ($0.036 for the places, $0.02 for the start). 500 places across New York City cost about $3.02. To cap a run's cost, set Max cost per run in the run options: the run stops when it is reached and keeps every place it was charged for.

Good to know

• ChatGPT decides what it recommends. The same search can return different places on different days, and the number of places per search (usually 5 to 8) cannot be raised. Use a search term and region for volume.
• Reviews are excerpts, as the review sources provide them, and they are not available for every place. Coverage is best in the US.
• Language: ChatGPT usually answers in the language of the search. Write searches in the language you want.
• No account is needed and none is used.

FAQ

How many places can I get for a city? Roughly 150 to 500 distinct places per search term with the built-in neighborhoods, depending on the city. Add qualifiers to go further.

Why did a search return no places? ChatGPT answered without a map, which happens for questions that are not about places. Name a kind of place and a location, such as "vegan cafes in Vienna".

How fast is it? About 25 to 45 seconds per search, run in parallel: with 6 parallel searches, roughly 60 to 80 places per minute. That time is ChatGPT writing its answer.

Is it legal to scrape this data? The actor collects publicly available business information. Make sure your use complies with the laws that apply to you, and handle review texts with care.