{ "openapi": "3.0.1", "info": { "title": "Website to Markdown – Clean LLM & RAG Content Extractor", "description": "Convert any public web page to clean, LLM-ready Markdown with metadata — by URL, a list of URLs, or a whole-site crawl. Strips nav/ads/boilerplate, keeps headings/lists/tables/code. Respects robots.txt. No API key.", "version": "0.0", "x-build-id": "xVZvLslVTu6RrYQDy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dataquarry~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dataquarry-website-to-markdown", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dataquarry~website-to-markdown/runs": { "post": { "operationId": "runs-sync-dataquarry-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dataquarry~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-dataquarry-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs", "type": "array", "description": "Web page URLs to convert to Markdown. In crawl mode these are the starting pages.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "single", "list", "crawl" ], "type": "string", "description": "single = first URL only; list = every URL given; crawl = follow same-domain links from each start URL.", "default": "list" }, "contentMode": { "title": "Content", "enum": [ "main", "full" ], "type": "string", "description": "main = extract the primary article/content and strip nav, ads and boilerplate; full = convert the whole page.", "default": "main" }, "maxResults": { "title": "Max results (pages)", "minimum": 1, "type": "integer", "description": "Maximum number of pages to return.", "default": 50 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "type": "integer", "description": "Crawl mode only: how many link-hops from each start URL to follow.", "default": 1 }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "type": "integer", "description": "Crawl mode only: hard cap on pages visited.", "default": 50 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Crawl mode only: only follow links on the same domain as the start URL.", "default": true }, "includeLinks": { "title": "Include links list", "type": "boolean", "description": "Also output the list of links found on each page.", "default": false }, "includeImages": { "title": "Include images list", "type": "boolean", "description": "Also output the list of image URLs found on each page.", "default": false }, "computeTokenEstimate": { "title": "Estimate token count", "type": "boolean", "description": "Add an approximate LLM token count for each page's Markdown (a heuristic estimate, not exact).", "default": true }, "chunkForRag": { "title": "Chunk for RAG", "type": "boolean", "description": "Also split each page's Markdown into overlapping chunks for retrieval-augmented generation.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "type": "integer", "description": "Target chunk size in characters when chunking for RAG.", "default": 2000 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "type": "integer", "description": "Overlap between consecutive chunks when chunking for RAG.", "default": 200 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by the site's robots.txt for our user-agent.", "default": true }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 0, "type": "integer", "description": "Optional politeness delay between pages, in milliseconds (pages are fetched one at a time).", "default": 0 } } }, "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 } } } } } } } } } }