{ "openapi": "3.0.1", "info": { "title": "URL to Markdown for LLM & RAG (fast, cheap)", "description": "Convert any public web page to clean, LLM-ready Markdown or text: main-content extraction, metadata, optional same-site crawl and RAG chunking. Plain HTTP, no browser, so it is fast and cheap. Respects robots.txt.", "version": "0.1", "x-build-id": "zpjeycV3t3mWruRcc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/liora-tools~url-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-liora-tools-url-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/liora-tools~url-to-markdown/runs": { "post": { "operationId": "runs-sync-liora-tools-url-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/liora-tools~url-to-markdown/run-sync": { "post": { "operationId": "run-sync-liora-tools-url-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Page URLs", "type": "array", "description": "Public web pages to convert.", "items": { "type": "string" } }, "extractMode": { "title": "What to extract", "enum": [ "main", "full" ], "type": "string", "description": "Main content is best for LLMs and RAG.", "default": "main" }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text" ], "type": "string", "description": "Markdown keeps headings, lists, tables and links.", "default": "markdown" }, "crawlDepth": { "title": "Crawl depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "0 = only the given URLs. 1+ = also follow links on the same website up to this many clicks away.", "default": 0 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit on pages visited when crawling.", "default": 100 }, "includeUrlRegex": { "title": "Only follow URLs matching (regex)", "type": "array", "description": "Optional. When crawling, follow only links that match one of these regular expressions, e.g. /docs/.", "items": { "type": "string" } }, "excludeUrlRegex": { "title": "Exclude URLs (regex)", "type": "array", "description": "Crawled links matching any of these regular expressions are skipped, e.g. /tag/ or \\\\?page=", "default": [], "items": { "type": "string" } }, "useSitemap": { "title": "Seed from sitemap.xml", "type": "boolean", "description": "Also queue pages listed in the site's sitemap (found via robots.txt or /sitemap.xml), up to Max pages. Good for whole-site conversion without deep crawling.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "maximum": 50000, "type": "integer", "description": "If above 0, also split the content into chunks on paragraph boundaries (for embeddings). 0 = no chunking.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated at the start of each next chunk.", "default": 200 }, "includeLinks": { "title": "Include list of links", "type": "boolean", "description": "Add all absolute links found on the page.", "default": false }, "includeImages": { "title": "Keep images", "type": "boolean", "description": "Keep images as Markdown image links.", "default": false }, "removeSelectors": { "title": "Remove CSS selectors", "type": "array", "description": "Elements to delete before conversion, e.g. nav, footer, .cookie-banner", "default": [], "items": { "type": "string" } }, "keepSelectors": { "title": "Keep only CSS selectors", "type": "array", "description": "If set, only these elements are converted, e.g. article, main, #content", "default": [], "items": { "type": "string" } }, "saveHtml": { "title": "Save raw HTML", "type": "boolean", "description": "Store each page's raw HTML in the run's key-value store; the record key is in htmlKey.", "default": false }, "generateLlmsTxt": { "title": "Generate llms.txt", "type": "boolean", "description": "Writes llms.txt (index of pages) and llms-full.txt (all content) to the key-value store at the end of the run.", "default": false }, "maxResults": { "title": "Max results", "minimum": 0, "type": "integer", "description": "Stop after this many converted pages (0 = no limit). Caps your cost.", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site disallows for crawlers (skipped pages are free).", "default": true }, "acceptLanguage": { "title": "Accept-Language header", "type": "string", "description": "Preferred page language.", "default": "en-US,en;q=0.8" }, "requestHeaders": { "title": "Custom HTTP headers", "type": "object", "description": "Extra request headers, e.g. for your own staging site. Never logged. Not for bypassing logins or bot protection.", "default": {} }, "onlyChanged": { "title": "Only changed pages", "type": "boolean", "description": "For scheduled monitoring: pages whose HTML did not change since the last run with the same state key are skipped for free.", "default": false }, "stateKey": { "title": "State key", "type": "string", "description": "Name of the memory used by 'Only changed pages'.", "default": "default" }, "maxConcurrency": { "title": "Pages in parallel", "minimum": 1, "maximum": 15, "type": "integer", "description": "How many pages are fetched at the same time.", "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 } } } } } } } } } }