{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: sitemap.xml, index and gzip", "description": "Extract every page URL from the sitemap.xml of any website, in bulk. Give the Actor a domain and it finds the sitemaps through robots.txt, follows sitemap indexes recursively, reads .xml.gz files, removes duplicates and returns one clean row per URL with lastmod, changefreq, priority and the...", "version": "0.1", "x-build-id": "5r6FrrobGcXPNQp7O" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/obligate_castle~robust-sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-obligate_castle-robust-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/obligate_castle~robust-sitemap-extractor/runs": { "post": { "operationId": "runs-sync-obligate_castle-robust-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/obligate_castle~robust-sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-obligate_castle-robust-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "items" ], "properties": { "items": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains (example.com), site URLs (https://example.com) or direct sitemap URLs (https://example.com/sitemap.xml.gz). For a domain, sitemaps are discovered from robots.txt, then from well-known paths. Sitemap indexes and .gz files are followed automatically.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "type": "integer", "description": "Stop extracting a site after this many unique URLs. Each URL is one billed result, so this also caps your cost per site.", "default": 10000 }, "includePattern": { "title": "Only URLs matching (regex)", "type": "string", "description": "Optional regular expression. Only URLs matching it are kept, for example /products/ or \\.html$." }, "excludePattern": { "title": "Skip URLs matching (regex)", "type": "string", "description": "Optional regular expression. URLs matching it are dropped, for example /tag/|/page/\\d+." }, "modifiedSince": { "title": "Modified since", "type": "string", "description": "Optional date (for example 2026-01-31). Keeps URLs whose lastmod is on or after this date. URLs with no lastmod are kept, since their age is unknown." }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety limit on the number of sitemap files fetched for one site (large indexes can list thousands).", "default": 500 }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "Network timeout for each robots.txt or sitemap download.", "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 } } }, "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 } } } } } } } } } }