{ "openapi": "3.0.1", "info": { "title": "Site Discovery: sitemaps, robots.txt, RSS & llms.txt", "description": "Map any website in seconds without crawling: robots.txt rules for your user agent (incl. AI-bot blocks), every sitemap and sitemap index (.gz too), RSS/Atom/JSON feeds, llms.txt and llms-full.txt, plus a filtered URL list with lastmod. By Steadyline Data.", "version": "0.1", "x-build-id": "kYo1hpMtSB2IrYsvU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/steadyline~site-discovery/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-steadyline-site-discovery", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/steadyline~site-discovery/runs": { "post": { "operationId": "runs-sync-steadyline-site-discovery", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/steadyline~site-discovery/run-sync": { "post": { "operationId": "run-sync-steadyline-site-discovery", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "domains" ], "properties": { "domains": { "title": "Domains or URLs", "type": "array", "description": "Domains (example.com) or URLs. Each origin is analyzed once.", "items": { "type": "string" } }, "outputUrls": { "title": "Output URL records", "type": "boolean", "description": "Write one dataset row per discovered URL (charged per URL). Off = domain summaries only.", "default": true }, "maxUrls": { "title": "Max URLs per domain", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop collecting URLs for a domain after this many (after filters).", "default": 1000 }, "includePatterns": { "title": "Include patterns", "type": "array", "description": "Only keep URLs whose path matches one of these. Glob on path (/blog/**, /docs/*/intro) or regex with re: prefix (re:^/p/\\d+).", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude patterns", "type": "array", "description": "Drop URLs whose path matches (same syntax).", "default": [], "items": { "type": "string" } }, "lastmodSince": { "title": "Last modified since", "type": "string", "description": "Only keep URLs with a sitemap lastmod on/after this date. URLs without lastmod are dropped when set." }, "followSitemapIndexes": { "title": "Follow sitemap indexes", "type": "boolean", "description": "Recurse into sitemap index files (including gzipped .xml.gz).", "default": true }, "maxSitemaps": { "title": "Max sitemap files per domain", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety cap on sitemap files fetched per domain.", "default": 50 }, "discoverFeeds": { "title": "Discover RSS/Atom feeds", "type": "boolean", "description": "From on the homepage, else common paths (/feed, /rss.xml, /atom.xml...).", "default": true }, "fetchLlmsTxt": { "title": "Fetch llms.txt", "type": "boolean", "description": "Check /llms.txt and /llms-full.txt and include an excerpt.", "default": true }, "llmsExcerptChars": { "title": "llms.txt excerpt length", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Characters of llms.txt content to include.", "default": 2000 }, "userAgent": { "title": "Robots user agent", "type": "string", "description": "User-agent token whose robots.txt rules are evaluated (e.g. GPTBot, Googlebot, MyAgent).", "default": "SteadylineBot" }, "respectRobots": { "title": "Respect robots.txt", "type": "boolean", "description": "Drop URLs disallowed for the user agent above (counted in urlCounts.disallowedByRobots). Off = output them with allowedByRobots=false.", "default": true }, "maxConcurrency": { "title": "Domains in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Max 20.", "default": 5 }, "timeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per request.", "default": 20 } } }, "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 } } } } } } } } } }