{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All URLs, Lastmod, Images & Status", "description": "Extract every URL from any website's XML sitemaps. Auto-discovers sitemaps from robots.txt, follows nested sitemap indexes, reads .gz, text and RSS sitemaps, returns lastmod, priority, hreflang, image, video and news tags, with URL filters and optional status-code check. $0.20 per 1,000 URLs.", "version": "1.0", "x-build-id": "eZNYcX6iOuUPczWWK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/best_apis~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-best_apis-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/best_apis~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-best_apis-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/best_apis~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-best_apis-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", "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "A website (example.com, https://example.com) to auto-discover its sitemaps from robots.txt and common paths, or a direct sitemap URL (sitemap.xml, sitemap_index.xml, .xml.gz, sitemap.txt, RSS/Atom feed). Leave empty for a demo on crawlee.dev.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "type": "integer", "description": "Stop reading a site's sitemaps after this many matching URLs.", "default": 10000 }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Optional. Keep only URLs containing one of these patterns. Use * as a wildcard, e.g. */blog/* or *.html. Case-insensitive.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Optional. Drop URLs containing any of these patterns, e.g. */tag/* or *?page=*.", "items": { "type": "string" } }, "lastmodAfter": { "title": "Modified after", "type": "string", "description": "Optional. Only URLs whose is newer than this: a date (2026-01-01) or a relative time like \"24 hours\", \"7 days\", \"3 months\". URLs without lastmod are skipped when set." }, "includeExtras": { "title": "Include hreflang, image, video and news tags", "type": "boolean", "description": "Add alternates (hreflang), images, videos and Google News fields when the sitemap has them.", "default": true }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send a HEAD request (GET fallback) to every URL and add statusCode and redirectTo. Finds 404s and redirects listed in your sitemap. Priced as a 'checked URL'.", "default": false }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety cap on how many sitemap files (incl. nested indexes) are read per site.", "default": 500 }, "maxItems": { "title": "Max URLs in total", "minimum": 1, "type": "integer", "description": "Hard cap for the whole run, so cost stays predictable.", "default": 100000 } } }, "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 } } } } } } } } } }