{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler for LLM, AI & RAG", "description": "Crawl a website or URL list and return each page's main content as clean Markdown for LLMs and RAG. Use to build a knowledge base from docs or blogs. Input: startUrls, maxPages, optional followLinks, stayUnderStartPath, renderJs. Output per page: url, title, markdown, text, words. Obeys robots.txt.", "version": "0.1", "x-build-id": "s0unx5HKrDeiW7Fa6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phaux~website-to-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phaux-website-to-markdown-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/phaux~website-to-markdown-crawler/runs": { "post": { "operationId": "runs-sync-phaux-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/phaux~website-to-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-phaux-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Website start pages or a list of page URLs. Empty = a small example on crawlee.dev.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many pages are saved (= pages you pay for). Default: 50.", "default": 50 }, "followLinks": { "title": "Follow links", "type": "boolean", "description": "Crawl links found on the pages. Off = convert only the start URLs (a URL list). Default: true.", "default": true }, "sameDomainOnly": { "title": "Stay on the same website", "type": "boolean", "description": "Only follow links on the start URLs' websites (www. ignored). Default: true.", "default": true }, "stayUnderStartPath": { "title": "Stay under the start path", "type": "boolean", "description": "Only follow links under the start URL's folder, e.g. https://example.com/docs/ stays in /docs/. Default: false.", "default": false }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Link depth from the start pages (0 = start pages only). Default: 5.", "default": 5 }, "includeUrlPatterns": { "title": "Only URLs matching", "type": "array", "description": "Regular expressions; when set, only matching URLs are crawled. Example: /blog/", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs matching", "type": "array", "description": "Regular expressions; matching URLs are skipped. Example: /tag/|/login", "items": { "type": "string" } }, "renderJs": { "title": "JavaScript rendering", "enum": [ "auto", "never", "always" ], "type": "string", "description": "auto = render in a browser only when the HTML has almost no text (charged at the JS price); never = plain HTML only (cheapest); always = render every page. Default: \"auto\".", "default": "auto" }, "minWordsBeforeJs": { "title": "Min words before JS (auto mode)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "In auto mode, a page with fewer words than this whose HTML looks like a JavaScript app is rendered in a browser. Default: 50.", "default": 50 }, "outputFormats": { "title": "Output formats", "type": "array", "description": "markdown = main content as markdown; text = plain text; html = raw HTML (large). Example: [\"markdown\", \"text\"]. Default: [\"markdown\", \"text\"].", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Raw HTML" ] }, "default": [ "markdown", "text" ] }, "includeLinksInMarkdown": { "title": "Keep links in markdown", "type": "boolean", "description": "Keep [text](url) links in the markdown output. Default: true.", "default": true }, "requestIntervalSecs": { "title": "Seconds between requests to one host", "minimum": 0.5, "maximum": 30, "type": "number", "description": "Politeness delay per host (0.5–30 s). A longer robots.txt Crawl-delay always wins. Default: 1.", "default": 1 }, "maxConcurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Pages in progress at once across hosts (1–20). One host is always fetched one request at a time. Default: 4.", "default": 4 }, "timeBudgetSecs": { "title": "Time budget (seconds)", "minimum": 0, "maximum": 86400, "type": "integer", "description": "Stop after this many seconds and keep the pages saved (0 = only the run timeout guard). Default: 0.", "default": 0 } } }, "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 } } } } } } } } } }