{ "openapi": "3.0.1", "info": { "title": "Yelp B2b Lead Extractor", "description": "Extract publicly visible Yelp business fields without bypassing access controls.", "version": "1.3", "x-build-id": "LaKhIFN4KaceRqAhg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/w3crawler~yelp-b2b-lead-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-w3crawler-yelp-b2b-lead-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/w3crawler~yelp-b2b-lead-extractor/runs": { "post": { "operationId": "runs-sync-w3crawler-yelp-b2b-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/w3crawler~yelp-b2b-lead-extractor/run-sync": { "post": { "operationId": "run-sync-w3crawler-yelp-b2b-lead-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search keyword", "maxLength": 300, "type": "string", "description": "Keyword used with location when startUrls is omitted.", "default": "restaurants" }, "location": { "title": "Search location", "maxLength": 300, "type": "string", "description": "City, region, or locality used with query when startUrls is omitted.", "default": "New York, NY" }, "sourceMode": { "title": "Source mode", "enum": [ "public", "yelpFusionApi" ], "type": "string", "description": "Use public for Yelp page extraction, or yelpFusionApi for the official Yelp Places/Fusion API. API mode never falls back to public pages.", "default": "public" }, "yelpApiKey": { "title": "Yelp Fusion API key", "type": "string", "description": "Optional secret Yelp Places/Fusion API key. Required when sourceMode is yelpFusionApi; it is sent only as an Authorization header and never written to output or logs. Fusion does not provide email addresses." }, "startUrls": { "title": "Yelp search or business URLs", "minItems": 1, "maxItems": 20, "type": "array", "description": "Optional public Yelp search, city/location, or business-profile URLs. When supplied, these URLs control the source pages; query and location remain search-context values.", "items": { "type": "object", "properties": { "url": { "title": "URL", "type": "string", "description": "HTTPS URL on yelp.com." } }, "required": [ "url" ] } }, "keyword": { "title": "Record keyword filter", "maxLength": 300, "type": "string", "description": "Optional case-insensitive filter over business name, description, categories, and address. It does not change the Yelp source query.", "default": "" }, "minRating": { "title": "Minimum rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Keep records with an observed rating at or above this value. Missing ratings do not pass a positive minimum.", "default": 0 }, "minReviewCount": { "title": "Minimum review count", "minimum": 0, "maximum": 1000000000, "type": "integer", "description": "Keep records with an observed Yelp review count at or above this value.", "default": 0 }, "hasWebsite": { "title": "Require public website", "type": "boolean", "description": "Keep only businesses with an explicitly published non-Yelp website URL.", "default": false }, "hasPhone": { "title": "Require public phone", "type": "boolean", "description": "Keep only businesses with an explicitly published phone number.", "default": false }, "hasEmail": { "title": "Require public email", "type": "boolean", "description": "Keep only businesses with an explicitly published email address. The Actor never infers or guesses email addresses.", "default": false }, "sortBy": { "title": "Sort records", "enum": [ "relevance", "name_asc", "rating_desc", "reviews_desc" ], "type": "string", "description": "Sort the collected, filtered records across the bounded page set before maxItems is applied.", "default": "relevance" }, "maxItems": { "title": "Maximum businesses", "minimum": 1, "maximum": 100, "type": "integer", "description": "Global maximum number of normal business records emitted across all sources and pages.", "default": 20 }, "maxPages": { "title": "Maximum pages per source", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of source pages requested for each start URL. Yelp next links are preferred; a bounded start-offset fallback is used only for search pages.", "default": 1 }, "deduplicate": { "title": "Deduplicate businesses", "type": "boolean", "description": "Deduplicate across pages and start URLs by Yelp business ID, alias, or canonical business URL.", "default": true }, "includeDetails": { "title": "Enrich business details", "type": "boolean", "description": "Fetch bounded public business-profile pages for selected records and merge fields that are explicitly available there.", "default": true }, "maxDetailItems": { "title": "Maximum detail pages", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum selected business profiles to request for detail enrichment. 0 disables detail requests.", "default": 5 }, "includeDiagnostics": { "title": "Include diagnostic rows", "type": "boolean", "description": "Emit minimal {url,error,errorCode,scrapedAt} rows for blocks, request failures, redirects, or no public data. Operational counts remain in OUTPUT_SUMMARY.", "default": true }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Respectful delay before each public request. Use 0 only for fixture QA or carefully bounded testing.", "default": 250 }, "maxRequestRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Bounded retries for network failures only; access blocks are not retried indefinitely.", "default": 1 }, "timeoutMs": { "title": "Request timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Maximum time for each public request.", "default": 30000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration wired to got-scraping. It does not bypass access controls; direct access is used by default.", "default": { "useApifyProxy": false } }, "fixturePath": { "title": "Local fixture path", "maxLength": 500, "type": "string", "description": "Repository-relative HTML fixture for deterministic QA. Fixture mode makes no network request and must never be used as a silent live fallback.", "default": "" } } }, "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 } } } } } } } } } }