{ "openapi": "3.0.1", "info": { "title": "Website to Markdown for LLM & RAG: Fast Crawler, No Browser", "description": "Crawl any public website and get clean, LLM-ready Markdown: main content only, tables and code kept, metadata, token estimates and optional RAG chunks. Fast HTTP crawling, robots.txt respected. Pay only per page converted; failed or empty pages are free.", "version": "0.1", "x-build-id": "zwvDgy07bMqwjxcjB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~website-to-markdown-llm/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-website-to-markdown-llm", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~website-to-markdown-llm/runs": { "post": { "operationId": "runs-sync-blond_terrarium-website-to-markdown-llm", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~website-to-markdown-llm/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-website-to-markdown-llm", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or sites to convert. 'example.com' is fine; https:// is added automatically.", "items": { "type": "string" } }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "0 = convert only the start URLs. 1 = also pages linked from them, and so on.", "default": 1 }, "maxPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "Stop after this many converted pages in total (0 = no limit). Your max total charge also stops the run cleanly.", "default": 100 }, "crawlScope": { "title": "Crawl scope", "enum": [ "samePath", "sameHostname", "sameDomain" ], "type": "string", "description": "Which discovered links to follow.", "default": "samePath" }, "useSitemaps": { "title": "Also discover pages from sitemaps", "type": "boolean", "description": "Reads robots.txt / sitemap.xml (incl. indexes and .gz) to find pages that aren't linked.", "default": false }, "includeUrlPatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Only follow/convert URLs matching at least one pattern, e.g. '/blog/'.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Skip URLs matching any pattern, e.g. '/tag/' or '\\?page='.", "default": [], "items": { "type": "string" } }, "contentMode": { "title": "Content extraction", "enum": [ "article", "fullPage" ], "type": "string", "description": "How to pick the content to convert.", "default": "article" }, "removeSelectors": { "title": "Extra CSS selectors to remove", "type": "string", "description": "Comma-separated, e.g. '.related-posts, #comments'." }, "keepImages": { "title": "Keep images in Markdown", "type": "boolean", "description": "Image references as ![alt](absolute-url).", "default": true }, "keepLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Turn off to get plain text without link URLs (fewer tokens).", "default": true }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "If > 0, each page also gets a 'chunks' array split on headings/paragraphs. Free: chunks don't add charges.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Characters repeated between consecutive chunks.", "default": 200 }, "includeText": { "title": "Include plain text", "type": "boolean", "description": "Adds a 'text' field.", "default": false }, "includeHtml": { "title": "Include cleaned HTML", "type": "boolean", "description": "Adds an 'html' field with the extracted content HTML.", "default": false }, "includeLinksList": { "title": "Include list of links on page", "type": "boolean", "description": "Adds a 'links' array (absolute URLs).", "default": false }, "minContentChars": { "title": "Min content length (characters)", "minimum": 0, "type": "integer", "description": "Pages with less text are treated as empty and are not charged.", "default": 100 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip disallowed URLs and honor Crawl-delay (max 10 s).", "default": true }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "Across all hosts. Requests to one host are always spaced by the delay below.", "default": 10 }, "requestDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Politeness per host.", "default": 200 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Per request.", "default": 30 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "For timeouts, resets, 429 and 5xx (with backoff and Retry-After).", "default": 2 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Leave empty for the default browser-compatible UA." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Apify datacenter proxy or your own proxy URLs. Residential proxy isn't supported (it would raise the price for everyone)." } } }, "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 } } } } } } } } } }