{ "openapi": "3.0.1", "info": { "title": "Yelp Business Scraper", "description": "Fast Yelp business scraper. Search by location and keyword or scrape direct Yelp business URLs. Extracts name, address, phone, website, hours, photos, ratings, review count, price tier, categories, and claimed status. Direct read of Yelp's server-rendered Apollo data, no headless browser.", "version": "0.1", "x-build-id": "nGAaVP6xTpxE5HRwG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cirkit~yelp-business-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cirkit-yelp-business-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cirkit~yelp-business-scraper/runs": { "post": { "operationId": "runs-sync-cirkit-yelp-business-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cirkit~yelp-business-scraper/run-sync": { "post": { "operationId": "run-sync-cirkit-yelp-business-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "searchTerms": { "title": "Search Terms", "uniqueItems": true, "type": "array", "description": "Search query strings (e.g. 'pizza', 'plumber', 'dentist'). One business search per term, per location.", "default": [], "items": { "type": "string" } }, "locations": { "title": "Locations", "uniqueItems": true, "type": "array", "description": "Free-text Yelp locations (city + state, ZIP, neighborhood). Yelp resolves to a geo center.", "default": [], "items": { "type": "string" } }, "categoryAlias": { "title": "Category Alias Filter", "type": "string", "description": "Optional Yelp category alias to filter by (e.g. 'pizza', 'restaurants', 'autorepair'). When set, scraper uses the strict category endpoint instead of the free-text search.", "default": "" }, "directUrls": { "title": "Direct Yelp URLs", "uniqueItems": true, "type": "array", "description": "List of Yelp business URLs to scrape directly (e.g. https://www.yelp.com/biz/pink-onion-san-francisco). Bypasses search.", "default": [], "items": { "type": "string" } }, "maxResults": { "title": "Max Results Per Search", "minimum": 1, "maximum": 240, "type": "integer", "description": "Cap on total businesses per (searchTerm, location) pair. Yelp itself caps results at 240.", "default": 50 }, "enrichWithDetails": { "title": "Fetch Full Details Per Business", "type": "boolean", "description": "When true, the scraper hits each business's detail page to pull website, hours, photos, properties, and full address. Adds time + transfer.", "default": true }, "maxImagesPerBusiness": { "title": "Max Images Per Business", "minimum": 0, "maximum": 100, "type": "integer", "description": "Upper bound on photo URLs returned per business. Only applies when enrichWithDetails=true.", "default": 10 }, "priceFilter": { "title": "Price Tier Filter", "uniqueItems": true, "type": "array", "description": "Filter to Yelp price tiers. Empty means all tiers.", "items": { "type": "string", "enum": [ "1", "2", "3", "4" ], "enumTitles": [ "$", "$$", "$$$", "$$$$" ] }, "default": [] }, "sortBy": { "title": "Sort Order", "enum": [ "recommended", "rating", "review_count" ], "type": "string", "description": "How Yelp orders results before scraping.", "default": "recommended" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "US Residential proxies are required for sustained scraping. Datacenter works for small runs.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }