{ "openapi": "3.0.1", "info": { "title": "Website to Markdown for AI: Clean Content, RAG Chunks", "description": "Turn web pages or whole websites into clean Markdown for LLMs and RAG: main content only (no menus, ads or share buttons), title, author, date, word and token counts, optional chunks. Crawl a site or give a list. Fixed price per page.", "version": "1.0", "x-build-id": "ZXLMjm24XqmyXtXUk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/swiftkit~web-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-swiftkit-web-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/swiftkit~web-to-markdown/runs": { "post": { "operationId": "runs-sync-swiftkit-web-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/swiftkit~web-to-markdown/run-sync": { "post": { "operationId": "run-sync-swiftkit-web-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "URLs", "type": "array", "description": "Pages to convert, or the start page(s) of a site to crawl.", "items": { "type": "string" } }, "crawl": { "title": "Crawl the site", "type": "boolean", "description": "Follow links on the same site (and its subdomains) from the start pages.", "default": false }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after converting this many pages.", "default": 50 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Crawl: how many clicks away from the start pages to go.", "default": 3 }, "includePatterns": { "title": "Only URLs containing (optional)", "type": "array", "description": "Crawl: keep only URLs matching any of these texts or regular expressions, e.g. /docs/ or /blog/", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs containing (optional)", "type": "array", "description": "Crawl: skip URLs matching any of these, e.g. /tag/ or ?page=", "items": { "type": "string" } }, "contentMode": { "title": "Content", "enum": [ "article", "full" ], "type": "string", "description": "Main content uses Mozilla Readability, the engine behind Firefox Reader View.", "default": "article" }, "chunkSize": { "title": "Chunk size (tokens, optional)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Also split each page into chunks of about this many tokens for RAG. 0 = no chunks.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Tokens repeated between neighbouring chunks.", "default": 50 }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Also add the content as plain text.", "default": false }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Add every link found on the page.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site asks bots not to visit.", "default": true }, "maxConcurrency": { "title": "Pages at once", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests. Keep it modest to be polite.", "default": 5 } } }, "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 } } } } } } } } } }