{ "openapi": "3.0.1", "info": { "title": "PageMark: Website to LLM-Ready Markdown & RAG Chunks", "description": "Crawl any website into clean Markdown for LLMs and RAG: main content only, code blocks and tables intact, token-counted chunks, only-changed pages. HTTP-first, browser only when needed. $0.45 per 1,000 pages.", "version": "1.0", "x-build-id": "v76FmRrFfkLvXslVU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/1701_engage~pagemark-website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-1701_engage-pagemark-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/1701_engage~pagemark-website-to-markdown/runs": { "post": { "operationId": "runs-sync-1701_engage-pagemark-website-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/1701_engage~pagemark-website-to-markdown/run-sync": { "post": { "operationId": "run-sync-1701_engage-pagemark-website-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": "Start URLs", "type": "array", "description": "Pages to start from. PageMark follows links that stay under each start URL (e.g. https://docs.example.com/guide/ crawls only the guide). Set Max crawl depth to 0 to fetch only these exact pages.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many pages are saved. You only pay for saved pages.", "default": 100 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "type": "integer", "description": "How many links deep to follow from the start URLs. 0 = only the start URLs themselves.", "default": 20 }, "includeUrlGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Optional. Only crawl URLs matching one of these patterns, e.g. https://example.com/blog/**. Replaces the default 'under the start URL' rule.", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Skip URLs matching any of these patterns, e.g. **/tag/** or **?page=*.", "items": { "type": "string" } }, "useSitemaps": { "title": "Also use sitemaps", "type": "boolean", "description": "Find pages through the site's sitemap.xml too (from robots.txt). Finds pages that no menu links to.", "default": false }, "renderJs": { "title": "JavaScript rendering", "enum": [ "auto", "never", "always" ], "type": "string", "description": "Auto: fast HTTP first, and a real browser only for pages that come back empty without JavaScript (billed as 'rendered page'). Never: HTTP only, cheapest. Always: every page in a browser.", "default": "auto" }, "outputMode": { "title": "Output", "enum": [ "pages", "pagesWithChunks", "chunks" ], "type": "string", "description": "Pages: one row per page. Pages + chunks: each page also gets a 'chunks' list. Chunks: one row per chunk, ready to load into a vector database.", "default": "pages" }, "outputFormats": { "title": "Page formats", "type": "array", "description": "Which content fields each page row gets.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Clean HTML (main content)" ] }, "default": [ "markdown" ] }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 64, "maximum": 8000, "type": "integer", "description": "Maximum tokens per chunk (OpenAI cl100k tokenizer). Chunks follow headings, and code blocks are never cut in half unless one block alone is larger than this.", "default": 512 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 2000, "type": "integer", "description": "Repeat the last N tokens of a chunk at the start of the next chunk in the same section.", "default": 0 }, "onlyChangedSinceLastRun": { "title": "Only new or changed pages", "type": "boolean", "description": "For scheduled runs: skip pages whose content is the same as in your previous run with the same start URLs. Skipped pages are not charged.", "default": false }, "keepLinks": { "title": "Keep links", "type": "boolean", "description": "Keep [text](url) links in the Markdown. Turn off to save tokens.", "default": true }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Keep ![alt](url) image references in the Markdown.", "default": false }, "removeElementsCssSelector": { "title": "Remove elements (CSS selector)", "type": "string", "description": "Optional extra elements to remove before conversion, e.g. .promo, #cookie-bar. Menus, footers, cookie banners and sidebars are already removed automatically." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Pages fetched at the same time. robots.txt crawl-delay is always respected.", "default": 10 } } }, "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 } } } } } } } } } }