{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: all pages from robots.txt & sitemaps", "description": "List every URL a website publishes in its XML sitemaps: auto-discovery via robots.txt, nested sitemap indexes, .gz, text and RSS sitemaps, lastmod/hreflang/image/news fields, include/exclude patterns, date filter and only-new monitoring mode.", "version": "1.0", "x-build-id": "i0mx3PFnzBqzgbilo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/globose_talent_mn9~sitemap-urls/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-globose_talent_mn9-sitemap-urls", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/globose_talent_mn9~sitemap-urls/runs": { "post": { "operationId": "runs-sync-globose_talent_mn9-sitemap-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/globose_talent_mn9~sitemap-urls/run-sync": { "post": { "operationId": "run-sync-globose_talent_mn9-sitemap-urls", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 on the site (https://example.com/blog), or direct sitemap URLs (https://example.com/sitemap.xml, .xml.gz or .txt). For a domain, sitemaps are discovered from robots.txt, then common locations.", "items": { "type": "string" } }, "includePatterns": { "title": "Include URL patterns", "type": "array", "description": "Keep only URLs matching at least one pattern. Use * as a wildcard (e.g. */blog/*), or wrap in slashes for a regex (/\\/products\\/\\d+/).", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Drop URLs matching any of these patterns (same syntax as include).", "items": { "type": "string" } }, "lastmodAfter": { "title": "Modified after (date)", "type": "string", "description": "Keep only URLs whose is on or after this date (YYYY-MM-DD). URLs without lastmod are kept unless 'Require lastmod' is on." }, "requireLastmod": { "title": "Require lastmod", "type": "boolean", "description": "When filtering by date, drop URLs that have no .", "default": false }, "onlyNew": { "title": "Only URLs not seen in previous runs", "type": "boolean", "description": "Monitoring mode: remembers returned URLs (per start-URL list) and outputs only new ones on later runs. Great for tracking new pages, products or articles on a competitor's site.", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add the xhtml:link hreflang alternates listed for each URL.", "default": true }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "0 = no limit.", "default": 0 }, "maxUrlsTotal": { "title": "Max URLs in total", "minimum": 0, "type": "integer", "description": "Safety cap on URLs output per run (default 100,000). Set 0 for no limit. Big sites can list millions of URLs; you can also cap spend with the run's Maximum cost setting.", "default": 100000 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety limit on sitemap files followed per site (indexes included).", "default": 1000 } } }, "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 } } } } } } } } } }