{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: robots.txt, Index & Gzip Sitemaps", "description": "Get every URL from a website's sitemaps. Auto-discovers sitemaps via robots.txt and common paths, follows sitemap indexes, reads .xml, .xml.gz, .txt, RSS and Atom, and de-duplicates. Filter by pattern or lastmod. Pay only per unique URL delivered.", "version": "0.1", "x-build-id": "BwMk3NeQa1dXuieNm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~sitemap-url-extractor-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-sitemap-url-extractor-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~sitemap-url-extractor-pro/runs": { "post": { "operationId": "runs-sync-blond_terrarium-sitemap-url-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~sitemap-url-extractor-pro/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-sitemap-url-extractor-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites or sitemap URLs", "type": "array", "description": "Domains (example.com), any page URL, a robots.txt URL, or a direct sitemap/index/RSS URL (.xml, .xml.gz, .txt). Sitemaps are discovered automatically for domains.", "items": { "type": "string" } }, "discoverFromRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read 'Sitemap:' lines from /robots.txt.", "default": true }, "tryCommonPaths": { "title": "Try common sitemap locations", "type": "boolean", "description": "If robots.txt lists none, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, /sitemap.xml.gz, /sitemap.txt.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt when probing", "type": "boolean", "description": "Skip probing common paths that robots.txt disallows.", "default": true }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Drop URLs whose host is not the input domain or its subdomain.", "default": false }, "includeUrlPatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Keep only URLs matching at least one pattern, e.g. /blog/ or /products/. Filtered URLs are not charged.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop URLs matching any pattern. Not charged.", "default": [], "items": { "type": "string" } }, "modifiedSince": { "title": "Modified since (date)", "type": "string", "description": "Keep only URLs whose lastmod date is on/after this date, e.g. 2026-01-01. URLs without lastmod are dropped when set." }, "maxUrls": { "title": "Max URLs (0 = unlimited)", "minimum": 0, "type": "integer", "description": "Stop after this many unique URLs. Also set 'Max total charge' to cap spend.", "default": 0 }, "includeImages": { "title": "Include image entries", "type": "boolean", "description": "Add image entries from image sitemaps (image:image) to each row.", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add hreflang alternate-language URLs (xhtml:link) to each row.", "default": false }, "maxSitemaps": { "title": "Max sitemap files", "minimum": 1, "type": "integer", "description": "Safety cap on sitemap files fetched per run.", "default": 2000 }, "maxDepth": { "title": "Max index nesting depth", "minimum": 1, "maximum": 20, "type": "integer", "description": "How deep to follow nested sitemap indexes.", "default": 6 }, "maxConcurrency": { "title": "Max parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "Sitemaps fetched in parallel (requests to the same host are still spaced out).", "default": 5 }, "requestDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Politeness delay. A robots.txt Crawl-delay is honored if larger (max 10 s).", "default": 250 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per-sitemap download timeout.", "default": 60 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for timeouts, 429 and 5xx (with backoff).", "default": 2 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Only needed if a site blocks datacenter IPs. Proxy traffic is billed by Apify separately." } } }, "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 } } } } } } } } } }