{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Extractor: Clean Text for LLMs and RAG", "description": "Turn a list of web page addresses into clean Markdown and plain text for LLMs and RAG: the main content only, with headings, links, images and tables. robots.txt obeyed, no JavaScript rendering, no author data, pay only per extracted page.", "version": "1.0", "x-build-id": "beMdbHepuGVlhJvnH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowcraft~website-markdown-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowcraft-website-markdown-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowcraft~website-markdown-extractor/runs": { "post": { "operationId": "runs-sync-rowcraft-website-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowcraft~website-markdown-extractor/run-sync": { "post": { "operationId": "run-sync-rowcraft-website-markdown-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Page URLs", "type": "array", "description": "Web pages to convert, one address per line (for example https://docs.apify.com/platform/actors/running). Only the pages you list are read: no links are followed, no site is crawled. Duplicates and invalid entries are skipped and never charged.", "items": { "type": "string" } }, "fullPage": { "title": "Whole page instead of main content", "type": "boolean", "description": "Off (default): only the main content is kept, without navigation, headers, footers, sidebars, forms, ads and cookie banners. On: the whole body of the page is converted (hidden elements and scripts are still left out). Use it for pages without a clear article, such as short landing pages.", "default": false }, "includeLinks": { "title": "Keep links", "type": "boolean", "description": "Write links as Markdown links with absolute addresses and list them in the \"links\" column. Off: only the link text stays. Links that are not web pages (mail, phone, JavaScript) are never kept.", "default": true }, "includeImages": { "title": "Keep images", "type": "boolean", "description": "Write images as Markdown images (alt text and absolute address) and list them in the \"images\" column. Tracking pixels and inline data images are skipped.", "default": true }, "keepTables": { "title": "Keep tables", "type": "boolean", "description": "Convert simple HTML tables to Markdown tables. Off: tables are left out. Tables used for page layout are always read as ordinary text.", "default": true }, "maxChars": { "title": "Maximum characters per page", "minimum": 500, "maximum": 2000000, "type": "integer", "description": "The Markdown and the text of a page are cut at this length, at a line or word boundary, and \"truncated\" is set to true. The word count and character count still describe the whole text.", "default": 100000 }, "removeSelectors": { "title": "Remove these elements first", "type": "array", "description": "Extra elements to cut before the content is chosen, one per line: an id (#promo-box), a class (.related-posts), a tag (figure), a tag with a class (div.newsletter) or an attribute ([data-ad]). Simple selectors only.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum pages delivered", "minimum": 0, "type": "integer", "description": "Stop after this many rows are delivered. 0 = the whole list.", "default": 0 }, "maxConcurrency": { "title": "Pages read at the same time", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages are downloaded in parallel. Requests to the same website are still spaced by the delay below, so a long list from one site is read at the delay's pace. Default 3, maximum 10.", "default": 3 }, "onlyNew": { "title": "Only new rows since the last run", "type": "boolean", "description": "Remember the rows already delivered to you (in a key-value store in your Apify account) and deliver only rows that appeared since the last run with the same state key. The first run delivers everything that matches; later runs cost only the new rows. Ideal for schedules.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Name of the memory used by \"Only new rows\". Use a different name for each schedule or search (for example `stockholm-python`) so they do not share one memory.", "default": "default" }, "notifyUrl": { "title": "Notify this URL when the run ends", "type": "string", "description": "A webhook address that receives one JSON POST with the number of new rows and links to the dataset: a Slack or Discord incoming webhook, a Make, n8n or Zapier catch hook, or your own endpoint. The message is also in the `text` (Slack) and `content` (Discord) fields." }, "notifyWhenEmpty": { "title": "Notify also when there are no new rows", "type": "boolean", "description": "By default the notification is sent only when at least one row was delivered.", "default": false }, "requestIntervalMs": { "title": "Delay between requests to the same site (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Default 1000 ms (one request per second to each website). Each page takes two requests: robots.txt (once per website) and the page (plus redirects). Minimum 250.", "default": 1000 } } }, "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 } } } } } } } } } }