{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor: All URLs from XML Sitemaps for SEO", "description": "Extract URLs from a site's XML sitemaps with lastmod, image counts and hreflang. Capped at 1,000 URLs per site by default (raise maxUrlsPerSite, 0 = no limit). Auto-finds sitemaps, filters by regex and date. $0.20 per 1,000 URLs.", "version": "1.0", "x-build-id": "wzG5W7Zf8YCYFFQNU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fecklesspleb~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fecklesspleb-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fecklesspleb~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-fecklesspleb-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/fecklesspleb~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-fecklesspleb-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": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "A site (https://www.nasa.gov) to auto-discover its sitemaps, or a direct sitemap URL. Leave empty, or keep the sample NASA sitemap, for a default-mode run: up to 40 sample URLs from https://www.nasa.gov/wp-sitemap.xml at the normal per-URL price.", "default": [ "https://www.nasa.gov/wp-sitemap.xml" ], "items": { "type": "string" } }, "includePatterns": { "title": "Include URL patterns (regex)", "type": "array", "description": "Keep URLs matching any of these regular expressions, for example /blog/.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions.", "items": { "type": "string" } }, "sitemapPatterns": { "title": "Only follow child sitemaps matching (regex)", "type": "array", "description": "For big sitemap indexes, follow only child sitemaps matching these, for example post-sitemap.", "items": { "type": "string" } }, "lastmodAfter": { "title": "Changed after (date)", "type": "string", "description": "Keep URLs whose lastmod is on or after this date, YYYY-MM-DD. URLs with no lastmod are dropped unless you turn on Keep URLs without a lastmod." }, "lastmodWithinDays": { "title": "Changed within last N days", "minimum": 0, "type": "integer", "description": "Keep URLs whose lastmod is within the last N days. Overrides the date above. URLs with no lastmod are dropped unless you turn on Keep URLs without a lastmod." }, "keepUndatedUrls": { "title": "Keep URLs without a lastmod", "type": "boolean", "description": "Off by default: when a date filter is set, URLs with no lastmod in the sitemap are dropped, since their age can't be checked. Turn this on to keep them. On sites whose sitemaps have no lastmod, that returns every URL (up to the limits), and each one is billed.", "default": false }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "0 = no limit.", "default": 1000 }, "maxTotalUrls": { "title": "Max URLs in total", "minimum": 0, "type": "integer", "description": "0 = no limit.", "default": 0 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety cap on sitemap files read per site.", "default": 1000 }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add language alternate URLs listed in the sitemap.", "default": false }, "onlyNewUrls": { "title": "Only new URLs (monitoring)", "type": "boolean", "description": "Return only URLs not seen in earlier runs with the same state store.", "default": false }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store for monitoring. Use a different name per monitor.", "default": "sitemap-extractor-state" } } }, "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 } } } } } } } } } }