{ "openapi": "3.0.1", "info": { "title": "Firecrawl Pro Advanced Web Scraping Full Firecrawl Features", "description": "Professional scraping using Firecrawl's complete feature set / exposes all Firecrawl capabilities Markdown/HTML Content Filtering Include/Exclude Screenshots Stealth Mode Fast Mode Caching Location Proxies JSON Prompt-Based Branding Link Extraction Image Extraction Autonomous Multi-Page Discovery", "version": "1.0", "x-build-id": "ZsNuQGIhHihHWWLcK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/alizarin_refrigerator-owner~firecrawl-pro-advanced-web-scraping-full-firecrawl-features/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-alizarin_refrigerator-owner-firecrawl-pro-advanced-web-scraping-full-firecrawl-features", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/alizarin_refrigerator-owner~firecrawl-pro-advanced-web-scraping-full-firecrawl-features/runs": { "post": { "operationId": "runs-sync-alizarin_refrigerator-owner-firecrawl-pro-advanced-web-scraping-full-firecrawl-features", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/alizarin_refrigerator-owner~firecrawl-pro-advanced-web-scraping-full-firecrawl-features/run-sync": { "post": { "operationId": "run-sync-alizarin_refrigerator-owner-firecrawl-pro-advanced-web-scraping-full-firecrawl-features", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs to Scrape", "type": "array", "description": "List of URLs to scrape. Each URL will be processed with the configured options.", "items": { "type": "string" } }, "mode": { "title": "Scraping Mode", "enum": [ "basic", "agent" ], "type": "string", "description": "Basic: Single page scrape. Agent: Autonomous multi-page navigation with AI.", "default": "basic" }, "formats": { "title": "Output Formats", "type": "array", "description": "Content formats to extract from each page", "items": { "type": "string", "enum": [ "markdown", "html", "rawHtml", "links", "screenshot", "extract" ] }, "default": [ "markdown" ] }, "onlyMainContent": { "title": "Only Main Content", "type": "boolean", "description": "Extract only the main content, removing headers, footers, and navigation", "default": true }, "includeTags": { "title": "Include Tags", "type": "array", "description": "HTML tags to include in the extraction (e.g., article, main, div.content)", "items": { "type": "string" } }, "excludeTags": { "title": "Exclude Tags", "type": "array", "description": "HTML tags to exclude from extraction (e.g., nav, footer, aside)", "items": { "type": "string" } }, "actions": { "title": "Page Actions", "type": "array", "description": "Actions to perform before scraping (click buttons, type text, scroll, wait). Actions execute in order." }, "extractionSchema": { "title": "Extraction Schema", "type": "object", "description": "JSON schema for structured data extraction. Define the fields you want to extract." }, "extractionPrompt": { "title": "Extraction Prompt", "type": "string", "description": "Natural language prompt for AI extraction (alternative to JSON schema)" }, "screenshotOptions": { "title": "Screenshot Options", "type": "object", "description": "Options for screenshot capture", "default": { "fullPage": true, "format": "png" } }, "enableCaching": { "title": "Enable Caching", "type": "boolean", "description": "Use cached results if available (reduces costs on repeated requests)", "default": false }, "cacheMaxAge": { "title": "Cache Max Age (seconds)", "minimum": 60, "maximum": 604800, "type": "integer", "description": "Maximum age of cached results in seconds (default: 172800 = 2 days)", "default": 172800 }, "fastMode": { "title": "Fast Mode", "type": "boolean", "description": "Enable fast mode for quicker scraping (may reduce accuracy on complex pages)", "default": false }, "stealthMode": { "title": "Stealth Mode", "type": "boolean", "description": "Enable stealth mode for better success on protected sites (uses anti-detection techniques)", "default": false }, "proxyLocation": { "title": "Proxy Location", "enum": [ "", "US", "UK", "DE", "FR", "JP", "AU", "BR", "IN" ], "type": "string", "description": "Geographic location for the proxy (affects content localization)", "default": "" }, "waitFor": { "title": "Wait For", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Wait time in milliseconds before extracting content (for dynamic pages)", "default": 0 }, "timeout": { "title": "Timeout", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Maximum time in milliseconds to wait for page load", "default": 30000 }, "extractBranding": { "title": "Extract Branding", "type": "boolean", "description": "Extract branding profile (colors, fonts, logos, typography)", "default": false }, "extractLinks": { "title": "Extract Links", "type": "boolean", "description": "Extract all links from the page with metadata", "default": false }, "extractImages": { "title": "Extract Images", "type": "boolean", "description": "Extract all images from the page with alt text and dimensions", "default": false }, "agentPrompt": { "title": "Agent Prompt", "type": "string", "description": "Instructions for the autonomous agent (when mode=agent). Describe what data to find." }, "agentMaxCredits": { "title": "Agent Max Credits", "minimum": 10, "maximum": 500, "type": "integer", "description": "Maximum Firecrawl credits to use per agent session", "default": 50 }, "firecrawlApiKey": { "title": "Firecrawl API Key", "type": "string", "description": "Your Firecrawl API key (get one at https://firecrawl.dev)" }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "URL to send results via POST request (Zapier, Make, n8n compatible)" }, "demoMode": { "title": "Demo Mode", "type": "boolean", "description": "Run with sample data (no actual scraping, no API key required). Disable to use real Firecrawl API.", "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 } } } } } } } } } }