{ "openapi": "3.0.1", "info": { "title": "Yelp Businesses & Reviews Scraper", "description": "Scrape Yelp business listings and reviews. Search by term + location, or pass business URLs/slugs for full detail. Returns name, rating, review count, price, phone, address, geo and reviews. Real browser beats DataDome; never charges blocked or empty runs.", "version": "0.1", "x-build-id": "ugQKC0IXEMqFlHlFX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~yelp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dami_studio~yelp-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dami_studio~yelp-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "searchQueries": { "title": "Search queries", "type": "array", "description": "Listing searches. Each entry is \"{term} in {location}\", e.g. \"coffee in San Francisco\", \"plumbers in Austin, TX\". Use this OR the single query + location fields below.", "items": { "type": "string" } }, "query": { "title": "Search term (single)", "type": "string", "description": "A single search term, e.g. \"coffee\", \"dentist\", \"pizza\". Combine with the Location field below. Ignored if Search queries is used." }, "location": { "title": "Location (single)", "type": "string", "description": "City / area for the single search term above, e.g. \"San Francisco\", \"Austin, TX\", \"10001\"." }, "businessUrls": { "title": "Business URLs", "type": "array", "description": "Yelp business page URLs (https://www.yelp.com/biz/...) to scrape for full detail + reviews. Use this for detail mode.", "items": { "type": "string" } }, "businessSlugs": { "title": "Business slugs", "type": "array", "description": "Yelp business slugs (the part after /biz/, e.g. \"blue-bottle-coffee-san-francisco-7\") to scrape for full detail + reviews.", "items": { "type": "string" } }, "maxItems": { "title": "Max businesses", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of businesses to collect across all inputs (search paginates in batches of 10). Note: on a search row, only name, yelpUrl and slug are guaranteed — rating, reviewCount, category, price, phone, address, city, state, zip, lat and lng can be null when Yelp's structured data is missing and the DOM fallback is used. Use businessUrls/businessSlugs (detail mode) for complete records.", "default": 50 }, "maxReviews": { "title": "Max reviews per business", "minimum": 0, "maximum": 2000, "type": "integer", "description": "For business URL/slug detail mode: how many reviews to include per business (author, rating, text, date). 0 = no reviews. Listing search rows never include reviews.", "default": 0 }, "countryCode": { "title": "Proxy country", "type": "string", "description": "Residential proxy country (2-letter ISO). Yelp is geo-aware; use US for US searches, GB/CA/etc. for other Yelp regions.", "default": "US" }, "slackConnector": { "title": "Slack connector (optional)", "type": "string", "description": "Optional. Post a summary of the scrape (count + top 5 businesses + dataset link) to Slack when the run finishes. Authorize a Slack connector once in Settings → API & Integrations → MCP connectors, then pick it here. Leave empty to skip (default) — results are always saved to the dataset regardless." }, "slackChannel": { "title": "Slack channel", "type": "string", "description": "Channel for the Slack summary (only used if a Slack connector is set), e.g. \"#leads\". Defaults to #general." }, "notionConnector": { "title": "Notion connector (optional)", "type": "string", "description": "Optional. Write each scraped business as a page into your Notion when the run finishes — great for turning leads into a CRM. Authorize a Notion connector once in Settings → API & Integrations → MCP connectors, then pick it here. Leave empty to skip (default) — results are always saved to the dataset regardless." }, "notionParentId": { "title": "Notion target data source ID", "type": "string", "description": "Optional. The Notion data source ID of the database to write businesses into (only used if a Notion connector is set). Leave empty to create the pages privately in your workspace instead." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Yelp uses DataDome — a RESIDENTIAL proxy is required to get past the bot wall.", "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 } } } } } } } } } }