{ "openapi": "3.0.1", "info": { "title": "Website to Markdown for RAG & LLMs: Fast Crawler", "description": "Crawl any website and turn every page into clean Markdown for LLMs, RAG and AI agents. Fast HTTP crawler, main-content extraction, GFM tables, RAG chunks, llms.txt per domain, robots.txt respected. Flat price per page.", "version": "0.1", "x-build-id": "cbls0mPLpmHJ5EPZ9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rod_analytics~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rod_analytics-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rod_analytics~website-to-markdown/runs": { "post": { "operationId": "runs-sync-rod_analytics-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rod_analytics~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-rod_analytics-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 where the crawl starts. By default only pages under the same path are crawled: https://example.com/docs crawls /docs and everything below it.", "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 pay per saved page, so this is also your cost cap.", "default": 100 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 1000, "type": "integer", "description": "How many links away from a start URL the crawler may go. 0 crawls only the start URLs (plus sitemap URLs, if enabled).", "default": 20 }, "includeGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Only crawl URLs matching at least one pattern. Use ** for any path, for example https://example.com/blog/**. When set, this replaces the \"Stay within start path\" rule.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Never crawl URLs matching any of these patterns, for example **/tag/** or https://example.com/login**.", "default": [], "items": { "type": "string" } }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Follow links only on the start URL hosts. www.example.com and example.com count as the same host.", "default": true }, "stayWithinStartPath": { "title": "Stay within start path", "type": "boolean", "description": "Only follow links under the start URL path. Turn off to crawl the whole site.", "default": true }, "useSitemaps": { "title": "Also use sitemap.xml", "type": "boolean", "description": "Find sitemaps via robots.txt and /sitemap.xml and queue the URLs they list (still filtered by the rules above). Finds pages that are not linked from anywhere.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "WARNING: keep this on. Pages disallowed by the site robots.txt are skipped and never charged. Turning it off logs a warning, and you alone are responsible for having permission to crawl the site.", "default": true }, "extractionMode": { "title": "Content extraction", "enum": [ "readability", "main", "full" ], "type": "string", "description": "Readability: finds the main article like Firefox Reader View and drops menus, sidebars, footers and cookie banners (best for RAG). Main element: only removes known boilerplate and keeps the main or article element. Full page: keeps everything except scripts and cookie banners.", "default": "readability" }, "removeSelectors": { "title": "Remove CSS selectors", "type": "string", "description": "Extra elements to drop before conversion, as one CSS selector list. Example: .newsletter, #comments, .related-posts" }, "dedupeContent": { "title": "Skip duplicate pages", "type": "boolean", "description": "Skip pages whose canonical URL was already saved or whose Markdown is identical to a saved page. Duplicates are not charged.", "default": true }, "saveLlmsTxt": { "title": "Save llms.txt per domain", "type": "boolean", "description": "Write llms-.txt (index of pages) and llms-full-.txt (all Markdown in one file) to the key-value store at the end of the run.", "default": true }, "includeChunks": { "title": "Split into RAG chunks", "type": "boolean", "description": "Add a chunks array to each page, split at headings, paragraphs and code blocks, ready for embeddings and a vector database.", "default": false }, "chunkSize": { "title": "Chunk size (tokens)", "minimum": 50, "maximum": 8000, "type": "integer", "description": "Target size of one chunk in estimated tokens (about 4 characters per token).", "default": 500 }, "chunkOverlap": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "How many tokens of the previous chunk are repeated at the start of the next one. Capped at half the chunk size.", "default": 50 }, "jsRenderingFallback": { "title": "JavaScript rendering fallback", "type": "boolean", "description": "Off by default. When a page has almost no text over HTTP (a JavaScript app shell), open it once in headless Chrome and extract the rendered content. Rendered pages are billed as a separate, more expensive event. Use at least 2048 MB memory.", "default": false }, "minWordsForHttp": { "title": "Render when fewer words than", "minimum": 0, "maximum": 10000, "type": "integer", "description": "With the fallback on, pages with fewer words than this over HTTP are rendered in the browser.", "default": 30 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests in total.", "default": 10 }, "maxConcurrencyPerDomain": { "title": "Max concurrency per domain", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests to one host. Lower it for small sites.", "default": 5 }, "delayBetweenRequestsMs": { "title": "Delay between requests per domain (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Minimum time between two request starts to the same host. 0 means no delay.", "default": 0 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Give up on a page after this many seconds.", "default": 30 }, "maxRequestRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries for network errors and blocked responses. Failed pages are not charged.", "default": 2 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Most sites work without a proxy. Use Apify datacenter proxy or your own proxy URLs if a site blocks you. Residential and SERP proxies are not supported.", "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 } } } } } } } } } }