{ "openapi": "3.0.1", "info": { "title": "Sitemap & llms.txt URL Extractor", "description": "Get every URL a website publishes. Reads robots.txt, follows all sitemaps including sitemap indexes and gzipped files, probes the usual sitemap paths when robots.txt names none, and reads llms.txt and llms-full.txt. Filter by pattern or last-modified date.", "version": "1.0", "x-build-id": "rQXaekDvgo9MJdWSE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/noclat~sitemap-llms-txt-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-noclat-sitemap-llms-txt-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/noclat~sitemap-llms-txt-extractor/runs": { "post": { "operationId": "runs-sync-noclat-sitemap-llms-txt-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/noclat~sitemap-llms-txt-extractor/run-sync": { "post": { "operationId": "run-sync-noclat-sitemap-llms-txt-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "websites" ], "properties": { "websites": { "title": "Websites", "minItems": 1, "type": "array", "description": "Domains or URLs to read, for example \"stripe.com\" or \"https://vercel.com\". Anything you pass is reduced to its origin, so a deep link works too.", "default": [ "stripe.com", "vercel.com" ], "items": { "type": "string" } }, "includeLlmsTxt": { "title": "Read llms.txt", "type": "boolean", "description": "Also read /llms.txt and /llms-full.txt, the Markdown files sites publish to tell AI agents which pages matter, and return the links they list.", "default": true }, "probeCommonPaths": { "title": "Probe the usual sitemap paths", "type": "boolean", "description": "When robots.txt names no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and a few others.", "default": true }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Regular expressions. A URL is kept when it matches at least one of them. Leave empty to keep everything.", "items": { "type": "string" } }, "excludePatterns": { "title": "Drop URLs matching", "type": "array", "description": "Regular expressions. A URL matching any of them is dropped, and is never charged.", "items": { "type": "string" } }, "lastmodSince": { "title": "Changed since", "type": "string", "description": "Only keep URLs whose sitemap lastmod is on or after this date, for example 2026-01-01. URLs with no date are dropped." }, "maxUrlsPerSite": { "title": "Max URLs per website", "minimum": 1, "type": "integer", "description": "Cap the number of URLs returned per website. Leave empty for no cap." }, "maxUrls": { "title": "Max URLs in total", "minimum": 1, "type": "integer", "description": "Stop after this many URLs in total. Leave empty for no cap." }, "maxSitemapsPerSite": { "title": "Max sitemap files per website", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit for very large sitemap indexes.", "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 } } } } } } } } } }