{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All Page URLs from XML Sitemaps", "description": "Extract every page URL from any website's sitemaps. Finds sitemaps in robots.txt, follows sitemap indexes and gzip files, and returns lastmod, priority, hreflang alternates, image counts and optional HTTP status. Filter by pattern or date.", "version": "1.0", "x-build-id": "Kcj9S8kdcsCJdl5Ec" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pistachio_implementation~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pistachio_implementation-sitemap-url-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pistachio_implementation~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-pistachio_implementation-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pistachio_implementation~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-pistachio_implementation-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "One per line. A website (example.com) makes the actor look in robots.txt and then the usual sitemap paths. A sitemap URL (https://example.com/sitemap.xml, .xml.gz, .txt, or a sitemap index) is read directly.", "items": { "type": "string" } }, "includeUrlPatterns": { "title": "Keep URLs matching any of", "type": "array", "description": "Regular expressions or plain text, for example /blog/ or \\.html$. Leave empty to keep every URL.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Drop URLs matching any of", "type": "array", "description": "Regular expressions or plain text, for example /tag/ or \\?page=.", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Changed on or after", "type": "string", "description": "Keep only URLs whose lastmod is on or after this date, for example 2026-09-01. URLs without lastmod are dropped when this is set." }, "sameHostOnly": { "title": "Same host only", "type": "boolean", "description": "Drop URLs on other hosts than the website you entered.", "default": false }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Sends a HEAD request to each saved URL and adds status code, final URL and a redirected flag. Finds broken and redirected pages in your sitemap. Charged as an extra event.", "default": false }, "maxSitemapsPerSite": { "title": "Maximum sitemap files per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Large sites split their sitemap into many files. The actor stops reading new files for a site after this many.", "default": 500 }, "maxUrlsPerSite": { "title": "Maximum URLs per site", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Stop saving URLs for a site after this many.", "default": 50000 }, "maxUrls": { "title": "Maximum URLs in total", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "The run stops after saving this many URLs.", "default": 200000 } } }, "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 } } } } } } } } } }