{ "openapi": "3.0.1", "info": { "title": "Website to Markdown – URL & Site Crawler for LLM/RAG", "description": "Convert any URL, sitemap or whole website to clean Markdown for LLMs, RAG and AI agents. Removes nav, footers and cookie banners, keeps headings, tables and code, adds RAG-ready chunks with token counts, llms.txt generation and an only-changed-pages mode. No browser: fast and cheap.", "version": "0.1", "x-build-id": "gcIT08Nc2SKhr5v8p" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gazidev~website-to-markdown/runs": { "post": { "operationId": "runs-sync-gazidev-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gazidev~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-gazidev-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 convert. In 'Same-domain crawl' mode these are the crawl entry points; in 'Sitemap' mode give a sitemap URL (e.g. https://example.com/sitemap.xml) or just the site URL and the sitemap is found via robots.txt.", "default": [ { "url": "https://docs.apify.com/academy/scraping-basics-javascript" }, { "url": "https://www.paulgraham.com/greatwork.html" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlMode": { "title": "Crawl mode", "enum": [ "single", "sameDomain", "sitemap" ], "type": "string", "description": "'Only these URLs' converts exactly the start URLs. 'Same-domain crawl' follows links on the same site up to Max depth. 'Sitemap' converts the URLs listed in the site's sitemap(s).", "default": "single" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on pages fetched in this run (start URLs included). Keeps cost predictable: at most maxPages x the page price.", "default": 20 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Same-domain crawl only: how many clicks away from a start URL to follow (0 = start URLs only).", "default": 2 }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Only crawl / take from the sitemap URLs that match one of these globs, e.g. https://docs.example.com/guides/**. ** = anything, * = anything except '/'. Empty = all URLs on the domain.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Skip URLs matching any of these globs, e.g. **/tag/**, **/page/*, **?replytocom=*.", "default": [], "items": { "type": "string" } }, "chunkSize": { "title": "RAG chunk size (tokens)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Split each page's Markdown into chunks of at most this many tokens (estimated as characters / 4) on heading and paragraph boundaries. Every chunk carries its heading path. 0 = no chunks. Included in the page price.", "default": 800 }, "contentMode": { "title": "Content", "enum": [ "main", "full" ], "type": "string", "description": "'Main content' removes navigation, headers, footers, sidebars, cookie banners and share widgets and keeps the article / docs body. 'Full page' converts the whole .", "default": "main" }, "keepLinksInMarkdown": { "title": "Keep links in Markdown", "type": "boolean", "description": "Render links as [text](absolute URL). Turn off for plain text-only Markdown (fewer tokens).", "default": true }, "includeImages": { "title": "Keep images in Markdown", "type": "boolean", "description": "Render images as ![alt](absolute URL). Off by default to save tokens.", "default": false }, "outputLinks": { "title": "Output links[] list", "type": "boolean", "description": "Add every absolute link found on the page (including PDFs and other files, which are listed but not fetched) to the dataset row.", "default": true }, "removeSelectors": { "title": "Extra CSS selectors to remove", "type": "string", "description": "Optional comma-separated CSS selectors removed before conversion, e.g. .newsletter-box, #comments." }, "generateLlmsTxt": { "title": "Generate llms.txt + llms-full.txt", "type": "boolean", "description": "Build an llms.txt index (llmstxt.org format: sections with - [title](url): description) and an llms-full.txt with all Markdown, one pair per site, saved to the key-value store. Charged once per site.", "default": false }, "onlyChanged": { "title": "Only new or changed pages", "type": "boolean", "description": "For scheduled re-indexing: remembers each page's ETag / Last-Modified / content hash in a named key-value store and outputs (and charges) only pages that are new or changed since the previous run with the same start URLs.", "default": false }, "stateKey": { "title": "Change-tracking state key", "type": "string", "description": "Optional name for the change-tracking state (letters, digits, dashes). By default it is derived from the start URLs and crawl mode." }, "respectRobots": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by robots.txt and honour Crawl-delay (max 10 s).", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests in total.", "default": 10 }, "maxConcurrencyPerHost": { "title": "Max concurrency per host", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel requests to one host. Keep it low to be polite.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout.", "default": 30 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for timeouts, connection errors, 429 and 5xx responses (with backoff).", "default": 2 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Custom User-Agent header. Leave empty for the default, which identifies this Actor with a contact address." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Not needed for most sites.", "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 } } } } } } } } } }