{ "openapi": "3.0.1", "info": { "title": "Yelp Scraper — Business + Reviews + Menu + Photos in One Call", "description": "Extract a Yelp business profile + all reviews (auto-expanded, ISO dates) + menu + photos + amenities + hours in one call. Worldwide — any Yelp country domain, residential-proxy ready. No Fusion key, no 3-review cap. Pay-per-event: $0.004/business, $0.0008/review.", "version": "0.4", "x-build-id": "rhw82VQYTqpFu7CpO" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/godberry~yelp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-godberry-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/godberry~yelp-scraper/runs": { "post": { "operationId": "runs-sync-godberry-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/godberry~yelp-scraper/run-sync": { "post": { "operationId": "run-sync-godberry-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "urls" ], "properties": { "urls": { "title": "Yelp URLs, slugs, or business searches", "type": "array", "description": "One per line. Easiest: open a Yelp business in your browser and paste its URL. Also accepts business slugs (the-original-pancake-house-portland), Yelp search URLs (yelp.com/search?find_desc=...), and free-text queries (\"Joe's Pizza Bleecker Street\"). Worldwide — works on any Yelp country domain: .com, .ca, .co.uk, .ie, .fr, .de, .at, .ch, .it, .es, .pt, .nl, .be, .pl, .cz, .dk, .fi, .no, .se, .com.au, .co.nz, .com.sg, .com.ph, .com.hk, .com.tw, .co.jp, .com.br, .com.mx, .com.ar, .cl, .com.tr. IMPORTANT: yelp.com and yelp.ca are heavily defended by DataDome and are frequently blocked from cloud platforms even with a residential proxy — the regional domains (.de, .co.uk, .fr, .com.au, .it, .es, …) are the reliable ones today; for yelp.com/.ca, a residential proxy you control gives the best odds. (A search URL or free-text query resolves to the top result only — pass business URLs directly for a multi-business pull. Yelp caps search results at 240.)", "items": { "type": "string" } }, "maxReviewsPerBusiness": { "title": "Max reviews per business", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum reviews to extract per business (Yelp paginates 10 per page). Higher = longer run + higher pay-per-event cost. Note: Yelp's DataDome anti-bot tends to rate-limit deep pagination after a few hundred reviews even with a residential proxy — past that the actor returns what it got rather than failing. 1000 is the hard ceiling.", "default": 100 }, "sortReviews": { "title": "Sort reviews by", "enum": [ "relevant", "newest", "oldest", "highest", "lowest" ], "type": "string", "description": "How to sort the reviews before extracting.", "default": "newest" }, "onlyWithText": { "title": "Only reviews with text", "type": "boolean", "description": "Skip star-only reviews that have no text content.", "default": false }, "includeMenu": { "title": "Include menu (restaurants)", "type": "boolean", "description": "Extract the menu (item name, price, category, photo, description) when the business has a Yelp menu page. Restaurants only — other business types return an empty menu.", "default": true }, "includePhotos": { "title": "Include photos", "type": "boolean", "description": "Include the full photo-gallery URL list (full-resolution) on each business record.", "default": true }, "includeOwnerResponses": { "title": "Include owner responses", "type": "boolean", "description": "Capture the business owner's reply under each review, when present (most reviews don't have one).", "default": true }, "includePersonalData": { "title": "Include reviewer personal data (GDPR)", "type": "boolean", "description": "Reviewer name, profile URL, location, Elite status, and review-count. Default OFF when scraping an EU/EEA + UK + Switzerland domain (.co.uk, .ie, .fr, .de, .at, .ch, .it, .es, .pt, .nl, .be, .pl, .cz, .dk, .fi, .no, .se) for GDPR safety — set true to override. Default ON elsewhere.", "default": true }, "flattenForSpreadsheet": { "title": "Flatten output for spreadsheet (CSV / Excel)", "type": "boolean", "description": "Recommended when exporting to CSV. Array fields (photos, categories, amenities) are joined with ' | '; reviews/menu are pushed as separate row series anchored to businessAlias. Leave off for JSON consumers.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Yelp uses DataDome anti-bot, which blocks datacenter IPs — so this defaults to Apify Residential. Best practice: set the proxy country to match the regional domain you're scraping (e.g. proxy DE for yelp.de, GB for yelp.co.uk). yelp.com / yelp.ca are the hard case — they're often blocked even through a residential proxy on a cloud platform; a residential proxy on an IP you control via proxyUrls is the best option there. You can also disable the proxy for local testing.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }