Google Maps Menu Scraper — Allergens, Nutrition & Prices, No API Key

Give it a Google Maps place URL, place ID, or just a place name and get back the restaurant's menu as structured data with no API keys. The actor first collects the place's Menu photos; if none are available, it checks the restaurant website for menu images or PDFs, then AI-parses the 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

Cheaper Google Maps menu scrapers often return plain OCR text: an item name and perhaps a price. This actor adds AI-inferred ingredients, allergen flags, dietary classification, nutrition ranges, and translations. These enriched fields are estimates, not verified restaurant disclosures.

Fair, transparent pricing

• Live runs have a $0.02 actor-start charge. Dish result pricing depends on your Apify plan: $0.015 (Free), $0.014 (Bronze), $0.0135 (Silver), or $0.012 (Gold and above) per extracted dish.
• On your first successful live run, up to 10 dish charges are waived; the $0.02 actor-start charge still applies. The untouched default is a clearly marked deterministic demo and costs $0.
• You only pay when dishes are extracted. A run that produces only diagnostic rows costs $0 in Actor charges. Dishes are saved before any Actor charge is attempted.
• Photo fetching and AI parsing run on our managed keys and their cost is already included in the per-dish price. No Google AI Studio signup, no Outscraper account, no proxy configuration — paste a place, get a menu.
• Duplicate menu pages are deduplicated before billing, and extraction runs at temperature 0 for more consistent output.
• On a budget? The Google Maps Menu Scraper (BYO keys) twin is the exact same scraper with the exact same output at a fraction of the per-dish price — you just bring your own free-tier Gemini and Outscraper keys.

Why this actor

Generic Google Maps scrapers focus on reviews and opening hours. Basic menu OCR gives you raw item names. This actor turns published menus into a richer, structured research dataset with AI-estimated ingredient and dietary fields, allergen confidence scores, nutrition ranges, and dish-name translation in 15 languages.

Use cases

• Food & dietary apps — build allergen-aware and vegan/vegetarian discovery workflows at the dish level, not the venue level.
• Delivery & ordering platforms — draft structured dishes, prices, and estimated allergen annotations for subsequent venue verification.
• Hospitality research — review how a venue's published menu may map to the EU-14 list before obtaining verified information from the venue.
• Market research — compare dish pricing and menu composition across a city or cuisine, in one language.
• Travel products — show travellers what a place serves, translated, with cultural context per dish.

Input example

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

Bare place IDs (ChIJ…) and plain place names (

Katz's Delicatessen New York

FAQ

How is this different from actors advertising "dietary tags"? Those tags are keyword-matched from the menu's description text — if the menu doesn't literally say "vegan", the tag is missing; if it says "vegan option available", everything gets tagged. This actor uses menu text and typical recipe knowledge to infer ingredients, then reports estimated per-ingredient EU-14 allergens with a confidence score, plus an explanation of the dietary classification. Verify critical fields with the venue.

What if the place has no menu photos on Google Maps? The actor falls back to the menu published on the place's own website (including PDF menus). If neither exists, you get a free diagnostic row — never a per-dish charge.

Notes

• The untouched Console defaults return one deterministic row labelled recordType: "DEMO" / isDemo: true. No live source or model call occurs, and the run has $0 in Actor charges. Change any input for a live run.
• Places with no menu photos and no 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. Want the place's food photos matched to these dishes? Chain the Restaurant Dish Photo Matcher actor.
• Prefer to pay Google and Outscraper directly and control your own quota? The Google Maps Menu Scraper (BYO keys) actor is the same scraper at a lower per-dish price, with geminiApiKey / outscraperApiKey inputs.

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.