{ "openapi": "3.0.1", "info": { "title": "URL to Markdown – Clean LLM-Ready Web Page Converter", "description": "URL to Markdown converter for LLMs and RAG: turn any web page into clean Markdown or reader text, or pull its SEO metadata (title, description, Open Graph, hreflang) and schema.org structured data. Export to CSV, JSON, Excel or API.", "version": "0.0", "x-build-id": "gFQxITDtKhrIxtWzR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maged120~url-to-markdown-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maged120-url-to-markdown-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maged120~url-to-markdown-pro/runs": { "post": { "operationId": "runs-sync-maged120-url-to-markdown-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maged120~url-to-markdown-pro/run-sync": { "post": { "operationId": "run-sync-maged120-url-to-markdown-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "markdown", "reader", "metadata", "structuredData" ], "type": "string", "description": "Markdown converts the whole page. Reader keeps just the article text, like a browser reader view, as plain text, HTML or Markdown. Metadata returns one row per page with its SEO and social tags. Structured data returns one row per schema.org item found on the page.", "default": "markdown" }, "urls": { "title": "URLs to scrape", "type": "array", "description": "Pages to convert. Each item: {\"url\": \"...\", \"title\": true, \"clean\": true, \"links\": true} (title adds the page title, clean strips menus and footers, links keeps hyperlinks). In reader mode, plain URL strings work too. In metadata and structured data modes, plain URL strings work too." }, "target_urls": { "title": "Page URLs (reader mode)", "type": "array", "description": "Pages to extract in reader mode. Setting this switches to reader mode automatically.", "items": { "type": "string" } }, "output_format": { "title": "Reader output format", "enum": [ "plain", "html", "markdown" ], "type": "string", "description": "Format of the article text in reader mode.", "default": "plain" }, "target_url": { "title": "Single page URL (legacy)", "type": "string", "description": "One page for reader mode. Kept for existing integrations; use \"Page URLs\" instead." }, "onlyTypes": { "title": "Only these types", "type": "array", "description": "Optional. Keep only these types, e.g. Product, FAQPage, Event. Leave empty for all.", "items": { "type": "string" } }, "includeFullData": { "title": "Include full data object", "type": "boolean", "description": "Turn off to get only the summary columns (name, price, rating…).", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Structured data mode only. Optional. Some shops block datacenter IPs; use residential if pages fail.", "default": { "useApifyProxy": 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 }, "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 } } } } } } } } } }