Google Maps Menu Scraper (No AI Markup) + Allergens

$0.1/1K dishes | Turn a Google Maps place into structured dishes: names, prices, ingredients, dietary type and AI-estimated EU-14 allergens and nutrition. Uses your Gemini key; an Outscraper key is advised for photos. Not affiliated with Google.

Google Maps Menu Bulk Scraper

Our scraper takes a Google Maps place and returns the restaurant's menu as one structured record per dish. It reads the place's Menu photos, falls back to the menu on the restaurant's own website when there are none, and parses the menu with AI. Each dish carries a translated name, the printed price, ingredients, a dietary type, estimated EU-14 allergens and nutrition ranges. It is ideal for allergen-aware food apps, delivery and ordering platforms, menu price research and travel products.

• Already have menu photo URLs? Use AI Restaurant Menu Parser and skip the Maps step.
• Want the place's food photos matched to the dishes? Chain Restaurant Dish Photo Matcher.
• Browse all our scrapers: https://apify.com/traveleat

Key Benefits

• Your key, your AI bill: menu parsing runs on your own Google AI Studio key, so you choose the model and control the quota, and Google bills that part to you directly.
• Low pricing: $0.10 per 1,000 dishes, plus a $0.00005 start fee per run. Your first successful live run waives up to ten dish charges.
• Allergen-aware rows: estimated EU-14 allergens with a confidence score, a dietary type with an explanation, and nutrition ranges.
• 15 output languages: dish names and descriptions come back translated, with the printed name kept in originalName.
• Free to try: the untouched Console run returns one clearly marked demo row, needs no keys and is not billed. A live run with only diagnostic rows has no Actor charge either.

How It Works

1. Paste one or more Google Maps place URLs into placeUrls (e.g., https://www.google.com/maps/place/Katz's+Delicatessen,+205+E+Houston+St,+New+York). Short maps.app.goo.gl links, place IDs and plain place names work too.
2. Add your keys for a live run:
   • (required for live runs) geminiApiKey, a free key from Google AI Studio.
   • (recommended) outscraperApiKey. Google hides the Maps photo gallery from automated browsers, so this is the reliable way to fetch a place's Menu photos. Without it the Actor falls back to browser scraping, which currently reaches only the cover photo.
3. Click Start. With the form untouched you get one marked demo row at no cost. Change the input and add your keys to parse a real menu.

More settings:

• language - Output language for dish names, descriptions and allergen summaries. Default is en.
• maxMenuPhotos - Menu photos sent to the AI, from 1 to 20. Default is 8, which covers most menus.
• geminiModel - Model that reads the photos. Default is gemini-2.5-flash.

Ingredient, allergen, dietary and nutrition fields are AI estimates from the published menu and typical recipes. Verify them with the restaurant or the product label before making allergy, medical or compliance decisions.

A place with no Menu photos and no menu on its website returns a diagnostic row that explains why, with no dish charge.

Data You'll Receive

• Dish: translated name, original printed name, category, price as shown (with currency) and a short description.
• Ingredients: base ingredients with an English database name and a translated display name, each with estimated EU-14 allergens and a confidence.
• Diet and nutrition: Vegan, Vegetarian, Pescetarian or Other with an explanation; estimated serving size, calories, protein, fat and carbs; isAlcoholic for drinks.
• Context: a short cultural story when the model is confident, otherwise null.
• Source: the place URL, the menu photo URLs used and where the menu came from.

Sample output data

Here is the example output of the untouched Console run. It is a marked demo row, not a live extraction:

{
  "recordType": "DEMO",
  "isDemo": true,
  "demoSource": "owned-default-prefill",
  "demoNote": "Deterministic preview only: no live source, photo scrape, or Gemini call occurred, and the row was not billed. Customize the input for live output; BYOK listings also require their provider credentials.",
  "name": "DEMO SAMPLE — Margherita Pizza",
  "originalName": "Margherita Pizza",
  "category": "Pizza",
  "price": "$18.00",
  "composition": "Tomato, mozzarella and basil",
  "description": "Example structured menu record; not a live extraction.",
  "ingredients": [],
  "dietaryType": "Vegetarian",
  "dietaryTypeExplanation": "Example classification for preview only.",
  "allergens": "Milk (preview example)",
  "type": "dish",
  "isAlcoholic": false,
  "story": null,
  "nutritionInfo": null,
  "place": "https://www.google.com/maps/place/Katz's+Delicatessen,+205+E+Houston+St,+New+York",
  "menuPhotoUrls": [],
  "menuPhotosFound": 0,
  "menuSource": "demo"
}

Google Maps Menu API

Results are stored in a dataset that you can export as CSV, JSON or Excel, or read through the Apify API. Connect it to Make, n8n or Zapier, or let an agent call it through the Apify MCP server.

Support and Feedback

We improve these scrapers from your feedback. If something breaks or you need a field:

• Open an issue on the Actor's Issues tab.
• If this Actor saved you time, a short review on the Store helps other people find it.

Run evidence

Start with one input and output

An Apify account is required. Use your Apify API token when calling the API; Console runs do not need that token pasted into the input. The unchanged default preview requires no provider key and makes no live AI or source call. A customized live run requires your own Gemini key; Maps/Outscraper collection also requires your own Outscraper key. Those providers bill separately.

Free-tier event rates checked 2026-10-08: result $0.0001; actor-start $0.00005.

Cost: Total = Actor event charges + platform usage if separately billed + any BYO-provider charges. See “Current costs” for your event rates, plan tiers and a calculation. A sample does not promise future billable volume.

This matching input/output pair is a marked DEMO preview, observed in run Jo6rq2kFzRKxK3oa0 (immutable build gXbU98WkRf2D8aiMn). It demonstrates the output shape and makes no live source or AI-provider call. It does not verify a live parse or synchronization. Keep the preview unchanged; customize it and supply the documented credentials for live work.

Input JSON

{
  "placeUrls": [
    "https://www.google.com/maps/place/Katz's+Delicatessen,+205+E+Houston+St,+New+York"
  ],
  "geminiModel": "gemini-2.5-flash",
  "language": "en",
  "maxMenuPhotos": 8,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "RESIDENTIAL"
    ]
  }
}

Matching output excerpt

Long strings and arrays are shortened for display; this is not a complete dataset fixture.

{
  "recordType": "DEMO",
  "isDemo": true,
  "demoSource": "owned-default-prefill",
  "demoNote": "Deterministic preview only: no live source, photo scrape, or Gemini call occurred, and the row was not billed. Customize the input for live output; BYOK listings also require their provider credentials.",
  "name": "DEMO SAMPLE — Margherita Pizza",
  "originalName": "Margherita Pizza",
  "category": "Pizza",
  "price": "$18.00",
  "composition": "Tomato, mozzarella and basil",
  "description": "Example structured menu record; not a live extraction.",
  "ingredients": [],
  "dietaryType": "Vegetarian",
  "dietaryTypeExplanation": "Example classification for preview only.",
  "allergens": "Milk (preview example)",
  "type": "dish",
  "isAlcoholic": false,
  "story": null,
  "nutritionInfo": null,
  "place": "https://www.google.com/maps/place/Katz's+Delicatessen,+205+E+Houston+St,+New+York",
  "menuPhotoUrls": [],
  "menuPhotosFound": 0,
  "menuSource": "demo"
}

Give it a Google Maps place URL (or place ID/name) and get back the restaurant's menu as structured data. The actor first collects the place's Menu photos; if none are available, it checks the restaurant website for menu images or PDFs. It AI-parses the discovered menu into one record per dish:

• name (translated to your language) + originalName (as printed)
• category, price (with currency, as shown)
• ingredients — AI-inferred base ingredients, each with an English database name, translated display name, and estimated EU-14 allergens with confidence (gluten, crustaceans, eggs, fish, peanuts, soy, milk, nuts, celery, mustard, sesame, sulfites, lupin, molluscs)
• dietaryType — Vegan / Vegetarian / Pescetarian / Other, with explanation
• nutritionInfo — estimated serving size, calories, protein, fat, carbs
• story — well-established cultural context when confident, otherwise null
• isAlcoholic for beverages

Why this actor

Generic Google Maps scrapers focus on reviews and opening hours. This actor turns a published menu into a richer structured research dataset with AI-estimated ingredient and dietary fields, allergen confidence scores, nutrition ranges, and translations in 15 languages.

Bring your own Gemini key

Menu parsing runs on your Google AI Studio key (get one free) — you control the AI cost and quota. A typical menu runs a few cents on Gemini 2.5 Flash, or a fraction of that on Flash-Lite.

Input example

{
  "placeUrls": ["https://www.google.com/maps/place/Katz's+Delicatessen,+205+E+Houston+St,+New+York"],
  "geminiApiKey": "AIza…",
  "language": "en",
  "maxMenuPhotos": 8
}

Photo source: add an Outscraper key (recommended)

Since 2026 Google's signed-out "limited view" hides the Maps photo gallery from automated browsers, so set the outscraperApiKey input (free tier available) — the actor then fetches the place's full tagged photo set (including the Menu photos) via Outscraper's API, no browser or proxy involved. Without it, the actor falls back to browser scraping, which currently reaches only the cover photo.

Notes

• The untouched keyless Console run returns one deterministic row labelled recordType: "DEMO" / isDemo: true. It makes no Maps, Outscraper or Gemini call and is not billed. Customize the input and add your Gemini key (plus an Outscraper key for reliable place-photo retrieval) for live output.
• Live pricing is listed in “Current costs” below. The first successful live run waives up to ten dish events; the actor-start event still applies.
• A live run that produces only diagnostic rows has $0 in Actor charges. Dishes are saved before any Actor charge is attempted.
• In browser-fallback mode, use the Apify residential proxy (default) — Google rate-limits datacenter IPs.
• Places with neither Google Maps menu photos nor a website menu yield a non-billed diagnostic row explaining why.
• maps.app.goo.gl short links are resolved to a trusted Google Maps URL. Output keeps the original place and exposes the canonical URL as resolvedPlaceUrl when resolution was needed.
• Ingredient, allergen, dietary, and nutrition fields are AI estimates from the published menu and typical recipes. Verify them with the restaurant or product label before making allergy, medical, or compliance decisions.
• Already have menu photo URLs? Use the companion AI Restaurant Menu Parser actor and skip the browser. Want the place's food photos matched to these dishes? Chain the Restaurant Dish Photo Matcher actor.
• Don't want to manage API keys at all? The managed twin is the same scraper with photo fetching and AI cost included in its per-dish price — zero setup.

Support & links

• Questions, bug reports and FAQ: github.com/Exdenta/traveleat-support
• This actor runs the same menu pipeline as Travel Eat — scan a menu, get allergens, ingredients and dietary filters in 36 languages.

Product guides and related tools

• Product overview and public links
• Public setup guide
• Travel Eat menu API guide
• Menu API documentation and support
• AI Restaurant Menu Parser — Dishes, Prices & Allergens
• Restaurant Dish Photo Matcher — Photos to Menu Items

Current costs

Current Actor event rates, checked 2026-10-08. USD; use the Pricing tab for your plan and later changes.

Event	Free	Bronze	Silver	Gold	Platinum	Diamond
Dish extracted (result)	$0.0001	$0.0001	$0.0001	$0.0001	$0.0001	$0.0001
Actor start (actor-start)	$0.00005	$0.00005	$0.00005	$0.00005	$0.00005	$0.00005

For example, 100 × result, 1 × actor-start totals $0.01005 in Actor event charges on Free. This is an arithmetic example, before any waiver; actual charged events depend on the run and selected options. It is not a promise of output or a charge for simply setting an item cap.

Your total is the charged Actor events, plus platform usage only if this Actor’s Pricing tab bills it separately, plus any external provider you use with your own key. Do not add platform usage twice when it is included. Apify credits and plan discounts affect your invoice. Set a run cost limit in Console before starting.

As documented, the first successful live run waives up to ten per-dish events; the actor-start event still applies. The untouched prefilled sample is a marked demo, not a live parse. Empty/failed diagnostic output creates no Actor billing events.

Agent setup skill

Use the maintained SKILL.md to configure the documented inputs, select latest, record the immutable build and distinguish source results from preview or diagnostic rows. Check the current Pricing tab before starting a run.

---

Independent tool. We built and run this Actor ourselves. Google does not operate, sponsor or endorse it, and its name is used only to say which service the data comes from.