{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler for LLM & RAG (llms.txt)", "description": "Crawl any website and get every page as clean Markdown for LLMs, RAG and AI agents. Main-content extraction, sitemap discovery, RAG chunks, llms.txt and llms-full.txt. Fast HTTP crawler with a flat price per page: no browser, no compute surprises.", "version": "0.1", "x-build-id": "Bh5o0PQ0Q7G4fFYRm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/malmurk~website-to-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-malmurk-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/malmurk~website-to-markdown-crawler/runs": { "post": { "operationId": "runs-sync-malmurk-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/malmurk~website-to-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-malmurk-website-to-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Where the crawl starts. Only links under each start URL's path are followed: https://example.com/docs/ crawls the docs section, https://example.com/ crawls the whole site.", "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 saving this many pages. You pay only for saved pages, so this also caps the cost of a run.", "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 = only the start URLs themselves. Pages found in sitemaps count as depth 1.", "default": 20 }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "Also queue every in-scope URL listed in the site's sitemap.xml (found through robots.txt). Finds pages that no menu links to.", "default": false }, "includeUrlGlobs": { "title": "Include URLs (globs)", "type": "array", "description": "Crawl only URLs that match one of these patterns, instead of the default 'under the start URL' rule. Example: https://example.com/{blog,docs}/** (** matches anything, * matches anything except a slash).", "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "excludeUrlGlobs": { "title": "Exclude URLs (globs)", "type": "array", "description": "Never crawl URLs that match one of these patterns. Example: **/tag/** or https://example.com/blog/page/*", "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site's robots.txt disallows. Turn off only for your own site.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Pages fetched at the same time. Lower it for small or slow sites.", "default": 10 }, "contentMode": { "title": "Content", "enum": [ "main", "full" ], "type": "string", "description": "Main content: the article or documentation text only, without menus, cookie banners, sidebars and footers (best for RAG). Full page: everything in the page body.", "default": "main" }, "includeLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Keep hyperlinks as [text](url). Off gives cleaner text for embeddings.", "default": false }, "includeImages": { "title": "Keep images in Markdown", "type": "boolean", "description": "Keep images as ![alt](src).", "default": false }, "saveText": { "title": "Also save plain text", "type": "boolean", "description": "Add a 'text' field with the content as plain text (no Markdown syntax).", "default": false }, "saveHtml": { "title": "Also save raw HTML", "type": "boolean", "description": "Add an 'html' field with the page's original HTML. Makes the dataset much bigger.", "default": false }, "generateLlmsTxt": { "title": "Generate llms.txt", "type": "boolean", "description": "Write llms.txt (an index of the crawled pages in the llmstxt.org format) and llms-full.txt (every page's Markdown in one file) to the run's key-value store. Free.", "default": true }, "detectLanguage": { "title": "Detect language", "type": "boolean", "description": "Fill 'language' from the text when the page doesn't declare one in its html lang attribute.", "default": true }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 0, "type": "integer", "description": "Also split each page's Markdown into chunks of about this many characters, ready for embeddings (a 'chunks' field). 0 turns chunking off. 1000-2000 suits most embedding models.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "type": "integer", "description": "How many characters neighbouring chunks share, so a sentence cut at a boundary still appears whole in one chunk.", "default": 200 } } }, "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 } } } } } } } } } }