{ "openapi": "3.0.1", "info": { "title": "Website to Markdown [💰$1.5/1K] | Clean HTML for AI & RAG", "description": "Convert any website into clean, noise-free Markdown for LLM training, RAG pipelines and Custom GPTs. Strip HTML junk, keep the content, and cut OpenAI token costs. From $2.80 per 1K results.", "version": "1.0", "x-build-id": "G4mIOkxc1MrL0lCMk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed_jasarevic~website-to-clean-markdown-ai-rag-ready/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed_jasarevic-website-to-clean-markdown-ai-rag-ready", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed_jasarevic~website-to-clean-markdown-ai-rag-ready/runs": { "post": { "operationId": "runs-sync-ahmed_jasarevic-website-to-clean-markdown-ai-rag-ready", "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/ahmed_jasarevic~website-to-clean-markdown-ai-rag-ready/run-sync": { "post": { "operationId": "run-sync-ahmed_jasarevic-website-to-clean-markdown-ai-rag-ready", "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": [ "urls" ], "properties": { "urls": { "title": "URLs to convert", "type": "array", "description": "One or more web page URLs. Each URL produces one dataset item. If crawling or sitemap discovery is enabled, these are the starting points.", "items": { "type": "string" } }, "crawl": { "title": "Crawl website", "type": "boolean", "description": "Follow links found on the start pages to convert a whole website (or section) into Markdown, not just the URLs you pasted.", "default": false }, "maxPages": { "title": "Max pages per run", "minimum": 1, "type": "integer", "description": "Upper limit on how many pages will be processed when crawling or reading a sitemap. Keeps runs fast and predictable.", "default": 50 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "type": "integer", "description": "How many link levels deep to follow from the start pages. 0 = only the start pages, 1 = their direct links, and so on.", "default": 2 }, "sameDomainOnly": { "title": "Stay on the same domain", "type": "boolean", "description": "When crawling, only follow links that stay on the same hostname. Disable to let the crawler follow external links too.", "default": true }, "useSitemap": { "title": "Read from sitemap", "type": "boolean", "description": "Automatically discover pages from /sitemap.xml on each start URL and convert all of them (up to Max pages). Great for docs sites and blogs.", "default": false }, "onlyMainContent": { "title": "Extract only main content", "type": "boolean", "description": "Use Mozilla Readability to keep only the article/body content and drop menus, sidebars, and footers. Disable to convert the entire page body.", "default": true }, "removeLinks": { "title": "Remove links", "type": "boolean", "description": "Keep the anchor text but remove the URLs. Useful for saving tokens in RAG and embedding use cases.", "default": false }, "chunk": { "title": "Return RAG chunks", "type": "boolean", "description": "Also split each page's Markdown into overlapping chunks (heading/line aware) ready to embed into a vector database.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "type": "integer", "description": "Maximum length of each RAG chunk in characters. Used only when 'Return RAG chunks' is enabled.", "default": 1200 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "type": "integer", "description": "How many characters consecutive chunks share, for better retrieval context. Used only when 'Return RAG chunks' is enabled.", "default": 200 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Use Apify Proxy to avoid blocks and rate limits on protected sites. Leave it disabled for the fastest, cheapest runs.", "default": { "useApifyProxy": false } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "How many pages to process in parallel. Higher is faster but uses more memory.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "type": "integer", "description": "Maximum time to wait for a page to respond before giving up. Failed pages are reported in the output with an error message.", "default": 30 } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }