AI-Ready Website Crawler
Pricing
Pay per usage
Go to Apify Store
AI-Ready Website Crawler
Crawl websites and convert to clean markdown for AI/RAG, LLM fine-tuning, and document pipelines.
AI-Ready Website Crawler
Pricing
Pay per usage
Crawl websites and convert to clean markdown for AI/RAG, LLM fine-tuning, and document pipelines.
You can access the AI-Ready Website Crawler programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "8RuqAnCnHxdKZ0xDb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/optimus-fulcria~ai-ready-website-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-optimus-fulcria-ai-ready-website-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/optimus-fulcria~ai-ready-website-crawler/runs": { "post": { "operationId": "runs-sync-optimus-fulcria-ai-ready-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/optimus-fulcria~ai-ready-website-crawler/run-sync": { "post": { "operationId": "run-sync-optimus-fulcria-ai-ready-website-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrl" ], "properties": { "startUrl": { "title": "Start URL", "type": "string", "description": "The primary URL to start crawling from. The crawler will follow links within the same domain." }, "additionalUrls": { "title": "Additional URLs", "type": "array", "description": "Optional list of additional URLs to crawl. Each URL will be crawled independently.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl. Set to 0 for unlimited (not recommended).", "default": 50 }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum link depth to follow from the start URL. Depth 0 means only the start URL itself.", "default": 3 }, "requestsPerSecond": { "title": "Requests Per Second", "minimum": 0.1, "maximum": 20, "type": "number", "description": "Maximum number of requests per second. Lower values are more polite to target servers.", "default": 2 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Whether to respect robots.txt rules. Strongly recommended to keep enabled.", "default": true }, "includeUrlPatterns": { "title": "Include URL Patterns", "type": "array", "description": "Only crawl URLs matching these regex patterns. Leave empty to crawl all URLs on the same domain.", "items": { "type": "string" }, "default": [] }, "excludeUrlPatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Skip URLs matching these regex patterns. Common exclusions: login pages, API endpoints, media files.", "items": { "type": "string" }, "default": [ "\\.(pdf|zip|tar|gz|mp4|mp3|avi|mov|wmv|jpg|jpeg|png|gif|svg|ico|woff|woff2|ttf|eot)$", "/api/", "/login", "/logout", "/signin", "/signup", "/auth/" ] }, "removeSelectors": { "title": "Remove CSS Selectors", "type": "array", "description": "CSS selectors for elements to remove before converting to markdown. Defaults remove nav, footer, ads, etc.", "items": { "type": "string" }, "default": [ "nav", "footer", "header", "aside", ".sidebar", ".nav", ".navigation", ".menu", ".footer", ".header", ".advertisement", ".ad", ".ads", ".social-share", ".cookie-banner", ".cookie-consent", ".popup", ".modal", ".breadcrumb", ".pagination", "#comments", ".comments", "script", "style", "noscript", "iframe", "svg" ] }, "contentSelectors": { "title": "Content CSS Selectors", "type": "array", "description": "CSS selectors to target main content. If specified, only content within these selectors is extracted. Leave empty to auto-detect.", "items": { "type": "string" }, "default": [] }, "requestTimeoutSecs": { "title": "Request Timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each HTTP request in seconds.", "default": 30 }, "userAgent": { "title": "User Agent", "type": "string", "description": "Custom User-Agent header. Leave empty for default.", "default": "Mozilla/5.0 (compatible; AIReadyWebsiteCrawler/1.0; +https://apify.com)" } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI-Ready Website Crawler from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: