{ "openapi": "3.0.1", "info": { "title": "AI Extraction Agent - Smart Scraper", "description": "AI-powered data extraction using natural language prompts. Describe what you need & let AI extract structured data from any webpage automatically.", "version": "1.0", "x-build-id": "fg3HNFSFC1b4LBalz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/alizarin_refrigerator-owner~ai-extraction-agent/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-alizarin_refrigerator-owner-ai-extraction-agent", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/alizarin_refrigerator-owner~ai-extraction-agent/runs": { "post": { "operationId": "runs-sync-alizarin_refrigerator-owner-ai-extraction-agent", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/alizarin_refrigerator-owner~ai-extraction-agent/run-sync": { "post": { "operationId": "run-sync-alizarin_refrigerator-owner-ai-extraction-agent", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "Target URL", "type": "string", "description": "The starting URL to begin extraction from" }, "objective": { "title": "Extraction Objective", "type": "string", "description": "Natural language description of what data to extract (e.g., 'Find all pricing plans and their features')" }, "schema": { "title": "Output Schema (Optional)", "type": "object", "description": "Optional JSON schema to structure the extracted data. If provided, the AI will conform output to this schema." }, "maxPages": { "title": "Maximum Pages to Scrape", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of pages to crawl and analyze", "default": 5 }, "followLinks": { "title": "Follow Links", "type": "boolean", "description": "Whether to follow links on the page to discover more content", "default": true }, "anthropicApiKey": { "title": "Anthropic API Key", "type": "string", "description": "Your Anthropic API key for Claude AI extraction. Get one at https://console.anthropic.com" }, "demoMode": { "title": "Demo Mode", "type": "boolean", "description": "Run with sample data (no API key required). Useful for testing the actor.", "default": false }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "URL to send extraction results via POST request. Supports Zapier, Make, n8n, and custom webhooks." }, "webhookPlatform": { "title": "Webhook Platform", "enum": [ "zapier", "make", "n8n", "custom" ], "type": "string", "description": "Select your webhook platform for optimized payload formatting", "default": "custom" }, "webhookHeaders": { "title": "Custom Webhook Headers", "type": "object", "description": "Additional HTTP headers to include in webhook requests (e.g., authorization tokens)" } } }, "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 } } } } } } } } } }