{ "openapi": "3.0.1", "info": { "title": "RAG Website Crawler — Markdown & AI Chunks", "description": "Crawl websites into clean Markdown, deterministic RAG chunks, canonical metadata, content hashes, and deduplicated AI-ready datasets for vector databases and agents.", "version": "0.1", "x-build-id": "v302k8tkjtZo3WNbN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/joaosbp~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-joaosbp-website-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/joaosbp~website-content-crawler/runs": { "post": { "operationId": "runs-sync-joaosbp-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/joaosbp~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-joaosbp-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites to crawl", "type": "array", "description": "Add one or more public HTTP(S) pages. The crawler follows same-host links from each starting page.", "default": [ { "url": "https://example.com" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard run-wide request budget. Start small, then increase after checking output quality.", "default": 100 }, "maxCrawlDepth": { "title": "Maximum link depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many same-host link levels to follow. Use 0 to process only the starting URLs.", "default": 3 }, "chunkForRag": { "title": "Create RAG chunks", "type": "boolean", "description": "Emit chunks with stable IDs and page metadata for direct vector-database ingestion.", "default": true }, "chunkSize": { "title": "Target chunk size (estimated tokens)", "minimum": 100, "maximum": 2000, "type": "integer", "description": "Target maximum size of each RAG chunk. Token counts are estimated from characters.", "default": 500 }, "chunkOverlap": { "title": "Chunk overlap (estimated tokens)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Context copied between consecutive chunks. Must be smaller than chunkSize.", "default": 50 }, "deduplicateContent": { "title": "Deduplicate identical content", "type": "boolean", "description": "Keep a traceable row for duplicate pages but emit chunks only for the first matching content hash.", "default": true }, "includeUrlPatterns": { "title": "Include URL patterns (advanced)", "type": "array", "description": "Optional case-insensitive regular expressions. A URL must match at least one when supplied (maximum 20).", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (advanced)", "type": "array", "description": "Optional case-insensitive regular expressions for pages to skip (maximum 20).", "default": [], "items": { "type": "string" } }, "useBrowser": { "title": "Render JavaScript in a browser", "type": "boolean", "description": "Enable only for JS-heavy sites. HTTP mode is faster and cheaper; browser concurrency is capped at 5.", "default": false }, "downloadAssets": { "title": "Download images and PDFs", "type": "boolean", "description": "Optionally save up to 20 discovered assets per useful page. Assets are capped at 10 MB each.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify or custom proxy settings. Disabled by default for lower cost on public sites.", "default": { "useApifyProxy": false, "apifyProxyGroups": [] } }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests. Browser mode is automatically limited to 5 to control memory and cost.", "default": 10 }, "requestDelay": { "title": "Delay after each page (ms)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Politeness delay after successfully processing a page.", "default": 500 }, "maxContentBytes": { "title": "Maximum page content bytes", "minimum": 100000, "maximum": 10000000, "type": "integer", "description": "Reject pages larger than this limit. The default is 1 MB; allowed range is 100 KB to 10 MB.", "default": 1000000 }, "allowPrivateUrls": { "title": "Allow private/internal URLs (unsafe)", "type": "boolean", "description": "Advanced trusted-run override. By default localhost, private networks, metadata endpoints and special IP ranges are blocked.", "default": false } } }, "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 } } } } } } } } } }