{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – All Page URLs + Lastmod", "description": "Sitemap extractor: get every page URL of a site from robots.txt and sitemap.xml, with sitemap indexes and .gz files followed. Input: websites or sitemap URLs. Output: URLs + lastmod, changefreq, priority, HTTP status. $0.30/1k URLs.", "version": "0.1", "x-build-id": "EteiWBXRfqUQbUWA4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/glidepath~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-glidepath-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/glidepath~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-glidepath-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/glidepath~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-glidepath-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", "properties": { "urls": { "title": "Websites or sitemap URLs", "type": "array", "description": "One per line. A website (https://example.com) is looked up through its robots.txt 'Sitemap:' lines, then /sitemap.xml and /sitemap_index.xml. A sitemap URL (…/sitemap.xml, …/post-sitemap.xml.gz, a sitemap index, a text, RSS or Atom sitemap) is read directly. Up to 100 per run.", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after saving this many URLs in total (each saved URL is charged). Sitemaps are not read further once it is reached.", "default": 1000 }, "maxUrlsPerSite": { "title": "Max URLs per website (0 = no limit)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Cap for each website, so one large site doesn't use up the whole run.", "default": 0 }, "includePatterns": { "title": "Only URLs matching (regex)", "type": "array", "description": "Keep only URLs that match at least one of these regular expressions, e.g. '/blog/' or '/products/'. Up to 20. Filtered-out URLs are not charged.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching (regex)", "type": "array", "description": "Drop URLs that match any of these regular expressions, e.g. '/tag/' or '\\?page='. Up to 20.", "items": { "type": "string" } }, "lastmodAfter": { "title": "Only pages modified on or after", "type": "string", "description": "Keep only URLs whose sitemap 'lastmod' is on or after this date (YYYY-MM-DD, UTC). URLs without a lastmod are skipped when this is set." }, "checkStatus": { "title": "Check each URL's HTTP status", "type": "boolean", "description": "Send a HEAD request to every saved URL (GET without the body if HEAD isn't supported) and add httpStatus and finalUrl, to find broken links and redirects in a sitemap. Slower: at most two requests per second per website. URLs that robots.txt disallows are listed but not checked.", "default": false } } }, "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 } } } } } } } } } }