{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler (llms.txt)", "description": "Crawl a website or docs section into clean, LLM-ready markdown: sitemap first, then links, one row per page with title, depth, word and token counts, plus llms.txt and llms-full.txt files for AI agents and RAG. Polite, no browser needed. $1.50 per 1,000 pages.", "version": "0.1", "x-build-id": "ifmtN8Irr0UfPAFL7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sfoln~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sfoln-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sfoln~website-to-markdown/runs": { "post": { "operationId": "runs-sync-sfoln-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/sfoln~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-sfoln-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": "Websites or site sections to crawl, one per line, e.g. https://docs.example.com or https://example.com/blog. Accounts on the Apify free plan can process up to 10 start URLs per run (20 pages each).", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Max pages per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Pages with content to deliver per start URL (1–10,000). Pages without content, duplicates and filtered pages do not count.", "default": 50 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many links away from the start page to follow (0–20). Sitemap URLs count as depth 1; 0 reads only the start page.", "default": 5 }, "crawlScope": { "title": "Crawl scope", "enum": [ "auto", "path", "host", "domain" ], "type": "string", "description": "auto: under the start URL's path when it has one, else the whole domain. path: the start URL's host, under its path. host: the start URL's host only. domain: every subdomain of the start URL's registrable domain.", "default": "auto" }, "useSitemap": { "title": "Use the sitemap", "type": "boolean", "description": "Queue the site's sitemap URLs that are in scope before the links found on pages (sitemap from robots.txt or /sitemap.xml).", "default": true }, "includePatterns": { "title": "Include URL patterns", "type": "array", "description": "Deliver only pages whose URL matches one of these, one per line: a glob where * matches anything (e.g. */blog/*) or a regular expression in slashes (e.g. /\\/docs\\/v2\\//). Other pages are still read for their links. A regular expression that backtracks catastrophically is refused (prefer globs or character classes).", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Do not deliver pages whose URL matches one of these (same syntax as the include patterns), e.g. */tag/* or */page/*.", "items": { "type": "string" } }, "maxCharsPerPage": { "title": "Max characters per page", "minimum": 1000, "maximum": 200000, "type": "integer", "description": "Markdown kept per page (1,000–200,000 characters), cut at a paragraph boundary. About 4 characters make one LLM token.", "default": 50000 }, "llmsTxt": { "title": "Write llms.txt and llms-full.txt", "type": "boolean", "description": "Write llms.txt (an index of the delivered pages) and llms-full.txt (all their markdown, up to 8 MB) per start URL to the run's key-value store. Free.", "default": true }, "maxSites": { "title": "Max start URLs", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety cap on how many start URLs are crawled in this run; the rest are ignored and counted in the OUTPUT record.", "default": 100 }, "concurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 5, "type": "integer", "description": "Start URLs crawled at the same time (1–5). Each site is read at most 2 requests per second.", "default": 2 } } }, "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 } } } } } } } } } }