{ "openapi": "3.0.1", "info": { "title": "Web Page to Markdown for AI: $1/1K Pages, No Login", "description": "Turn any list of web pages into clean Markdown for LLMs, RAG and AI agents: main content without menus and ads, tables kept, plus title, description, language, dates and links. Plain HTTP first, JavaScript only when a page needs it. $1 per 1,000 pages, failures free.", "version": "0.0", "x-build-id": "9nX3dqDngFGr2zkQy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/conserving_celerytop~web-page-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-conserving_celerytop-web-page-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/conserving_celerytop~web-page-to-markdown/runs": { "post": { "operationId": "runs-sync-conserving_celerytop-web-page-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/conserving_celerytop~web-page-to-markdown/run-sync": { "post": { "operationId": "run-sync-conserving_celerytop-web-page-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": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "Enter the web pages to read, one per line, as full addresses (https://example.com/page) or domains. Up to 10,000 per run. Each page gives one row.", "items": { "type": "string" } }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Pick the formats to return for each page. Markdown keeps headings, lists, links, images and tables. Text is plain text with line breaks. HTML is the cleaned content HTML.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Clean HTML" ] }, "default": [ "markdown" ] }, "contentScope": { "title": "Content", "enum": [ "main", "full" ], "type": "string", "description": "Main content keeps the article or main part of the page and drops menus, headers, footers, sidebars and cookie notices. Whole page keeps everything in the body except scripts and forms.", "default": "main" }, "renderJavaScript": { "title": "JavaScript rendering", "enum": [ "auto", "never", "always" ], "type": "string", "description": "Auto reads each page with a plain HTTP request and opens it in a browser only when it shows no content without JavaScript. Never uses plain HTTP only. Always opens every page in a browser. Browser pages cost more.", "default": "auto" }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "Add a list of the links on each page, with their text, up to 1,000 per page.", "default": false }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Keep images in the Markdown as ![alt](address). Turn it off for text-only output.", "default": true }, "maxCharacters": { "title": "Maximum characters per page", "minimum": 1000, "maximum": 2000000, "type": "integer", "description": "Cut each output field at this many characters. The row then has truncated set to true.", "default": 200000 }, "maxConcurrency": { "title": "Pages at a time", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages to read in parallel, 1 to 20. At most 2 at a time go to the same site.", "default": 5 }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for one page, 5 to 120 seconds.", "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 } } } } } } } } } }