{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor — All URLs, lastmod, Images & hreflang", "description": "Get every URL a website lists in its XML sitemaps: found through robots.txt, indexes and .gz followed, with lastmod, images, hreflang and news. Filter by date or pattern, check HTTP status.", "version": "0.0", "x-build-id": "Ih2OHIq3I4bbGfOnj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saliga~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saliga-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/saliga~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-saliga-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/saliga~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-saliga-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "A website (example.com) or a sitemap link (https://example.com/sitemap.xml, .xml.gz, sitemap index or text sitemap). For a website, the sitemaps listed in robots.txt are used; if there are none, the usual locations (/sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml) are tried.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop collecting a site's URLs after this many. Caps cost on very large sites.", "default": 10000 }, "lastmodSince": { "title": "Changed since", "type": "string", "description": "Only URLs whose lastmod is on or after this date, or within the last days, weeks or months (for example \"7 days\" in a daily or weekly schedule). Child sitemaps of an index whose lastmod is older are not even downloaded. Leave empty for all URLs." }, "keepUndated": { "title": "Keep URLs without lastmod", "type": "boolean", "description": "With \"Changed since\", also return URLs that have no lastmod.", "default": false }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Keep only URLs that match at least one of these regular expressions (case-insensitive), for example /blog/ or \\.pdf$.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Drop URLs that match any of these regular expressions, for example /tag/ or \\?page=.", "items": { "type": "string" } }, "includeExtras": { "title": "Images, hreflang and news", "type": "boolean", "description": "Add image links, hreflang alternates, news titles and dates, and video titles when the sitemap has them.", "default": true }, "checkStatus": { "title": "Check HTTP status", "type": "boolean", "description": "Request each returned URL (HEAD, or GET when HEAD is refused) and add its status and the final URL after redirects. URLs that robots.txt disallows are not requested and are marked blockedByRobots.", "default": false }, "maxStatusChecksPerSite": { "title": "Max status checks per site", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Check at most this many URLs per site (the first ones in sitemap order).", "default": 1000 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after reading this many sitemap files for one 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 } } } } } } } } } }