{ "openapi": "3.0.1", "info": { "title": "Yelp Scraper — businesses, ratings, hours, phone", "description": "Scrape Yelp business listings past DataDome: name, rating, review count, price range, categories, address, hours, phone and website. Search \"what in where\" or pass business URLs. No browser. Powered by xhr.dev.", "version": "0.1", "x-build-id": "osPrDYtneJKi4OokM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/xhrdev~yelp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-xhrdev-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/xhrdev~yelp-scraper/runs": { "post": { "operationId": "runs-sync-xhrdev-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/xhrdev~yelp-scraper/run-sync": { "post": { "operationId": "run-sync-xhrdev-yelp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Searches", "type": "array", "description": "What to find and where, written as \"what in where\" — e.g. \"pizza in San Francisco, CA\" or \"plumbers in Austin, TX\". Yelp needs a place for every search; a search without one is skipped with a message.", "default": [ "pizza in San Francisco, CA" ], "items": { "type": "string" } }, "startUrls": { "title": "Yelp URLs", "type": "array", "description": "Yelp URLs to scrape. /biz/ URLs are read as businesses; /search URLs are read as result lists — copy one out of your browser to keep Yelp's own filters.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "scrapeDetails": { "title": "Open each business page", "type": "boolean", "description": "Off by default: search results already carry name, rating, review count, price range, categories, street, neighborhood and opening hours. Turn it on to also get phone, website, menu link, full postal address, claimed status and Yelp's one-line summary — one extra page per business.", "default": false }, "maxPagesPerQuery": { "title": "Pages per search", "minimum": 1, "maximum": 24, "type": "integer", "description": "How deep to page through each search, 10 businesses a page. Yelp itself stops at 24 pages (240 results) however many match.", "default": 1 }, "maxItems": { "title": "Maximum businesses", "minimum": 1, "type": "integer", "description": "Stop once this many businesses have been scraped, across everything in this run.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Left off by default: Yelp solves cleanly from the container's own address — search, page 2 and business pages all cleared on the first attempt, every run, when this Actor was verified. If Yelp starts refusing cleared requests for you, try Residential.", "default": { "useApifyProxy": false } }, "maxRetries": { "title": "Attempts per page", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many times to try a page before giving up on it. Each attempt takes a fresh proxy session, so a dead exit node or a burnt IP gets a genuinely new chance.", "default": 3 }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 10, "maximum": 300, "type": "integer", "description": "How long one page — challenge, solve and all — may take before it counts as a failed attempt.", "default": 120 }, "maxConcurrency": { "title": "Concurrent pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages to work on at once. The solve path is HTTP-only and cheap, so this can go higher than a browser scraper would allow, but be a considerate guest on someone else's site.", "default": 4 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }