{ "openapi": "3.0.1", "info": { "title": "Co-Star Real Estate Scraper", "description": "Scrapes publicly accessible pages from CoStar News GB and extracts article, property, and market signals when available.", "version": "0.1", "x-build-id": "8rz5uKmpX41vzFvbm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~co-star-real-estate-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-co-star-real-estate-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~co-star-real-estate-scraper/runs": { "post": { "operationId": "runs-sync-solutionssmart-co-star-real-estate-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~co-star-real-estate-scraper/run-sync": { "post": { "operationId": "run-sync-solutionssmart-co-star-real-estate-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public CoStar listing or section pages to seed the crawl.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max output items", "minimum": 1, "type": "integer", "description": "Maximum number of records to store in the dataset.", "default": 50 }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "minimum": 1, "type": "integer", "description": "Requested cap for total requests, including listing and detail pages. In filtered modes the actor may raise the effective cap so maxItems can be reached.", "default": 200 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of pages processed in parallel.", "default": 3 }, "desiredConcurrency": { "title": "Desired concurrency", "minimum": 1, "type": "integer", "description": "Preferred steady-state parallelism target for the crawler.", "default": 2 }, "maxPaginationPages": { "title": "Max pagination pages", "minimum": 1, "type": "integer", "description": "Requested number of listing pages to follow from seeded sections. In filtered modes the actor may raise the effective value so enough strict records can be found.", "default": 20 }, "includeArticleBody": { "title": "Include article body", "type": "boolean", "description": "Store the full cleaned article text when available.", "default": true }, "includeHtml": { "title": "Include raw HTML", "type": "boolean", "description": "Include raw article HTML in the dataset. This increases output size.", "default": false }, "compactOutput": { "title": "Compact output", "type": "boolean", "description": "Remove null, empty, and static compatibility placeholder fields from dataset items. Disable only if you need the full compatibility schema.", "default": true }, "onlyPropertyArticles": { "title": "Only property articles", "type": "boolean", "description": "Skip generic newsroom articles that do not contain property-specific signals such as addresses, companies, prices, areas, or property types.", "default": true }, "onlyUkArticles": { "title": "Only UK articles", "type": "boolean", "description": "Skip non-UK or globally focused articles when running against the CoStar GB news feed.", "default": true }, "strictStoryMode": { "title": "Strict story mode", "type": "boolean", "description": "Keep only transaction, development, financing, sale, and letting stories. Drop people-moves, commentary, and broader market-analysis articles.", "default": true }, "requireAddress": { "title": "Require address", "type": "boolean", "description": "Skip otherwise valid records when no property address is exposed in the public article metadata.", "default": false }, "includeFailedRecords": { "title": "Include failed records", "type": "boolean", "description": "Store blocked or failed requests in the dataset. Disabled by default so output contains only successfully extracted records.", "default": false }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Optional terms used to add matchedSearchTerms to records that mention specific markets, tenants, or property types.", "default": [], "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify proxy configuration. Recommended if CoStar blocks your requests." }, "proxyInitializationTimeoutSecs": { "title": "Proxy initialization timeout", "minimum": 5, "type": "integer", "description": "Maximum seconds to wait while initializing proxy access before failing or falling back to direct connection.", "default": 30 }, "fallbackToNoProxyOnProxyError": { "title": "Fallback to direct connection on proxy error", "type": "boolean", "description": "If enabled, the Actor continues without proxy when proxy initialization fails or times out. Disable this when proxy usage is mandatory.", "default": true } } }, "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 } } } } } } } } } }