{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Auditor & Site Structure Mapper", "description": "Extracts every URL from a sitemap or sitemap index, auto-discovers sitemaps from robots.txt, handles gzipped sitemaps, filters by URL pattern and last-modified date, and reports site structure and content freshness analytics.", "version": "2.0", "x-build-id": "PmqkBntKaiKTKsqq3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapevanta~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapevanta-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapevanta~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-scrapevanta-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapevanta~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-scrapevanta-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sitemapSource" ], "properties": { "sitemapSource": { "title": "Sitemap URL or domain", "type": "string", "description": "A sitemap URL (for example https://example.com/sitemap.xml), a gzipped sitemap (.xml.gz), or just a domain such as example.com. For a domain, sitemaps are auto-discovered from robots.txt with a fallback to well-known sitemap paths." }, "includeUrlPatterns": { "title": "Include only URLs matching", "type": "array", "description": "Optional list of regular expressions. When set, a URL is exported only if it matches at least one pattern. Example: /blog/ to keep only blog pages.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Optional list of regular expressions. Any URL matching one of these is skipped. Example: /tag/ or \\.pdf$", "items": { "type": "string" } }, "modifiedAfter": { "title": "Modified after", "type": "string", "description": "Keep only URLs whose is on or after this date (YYYY-MM-DD). URLs without a lastmod value are skipped when a date window is set." }, "modifiedBefore": { "title": "Modified before", "type": "string", "description": "Keep only URLs whose is on or before this date (YYYY-MM-DD). Useful for finding stale content that needs refreshing." }, "maxUrls": { "title": "Maximum URLs to export", "minimum": 0, "type": "integer", "description": "Stop after exporting this many URLs. Set to 0 for no limit.", "default": 0 }, "maxSitemaps": { "title": "Maximum sitemap files to read", "minimum": 1, "type": "integer", "description": "Upper bound on how many individual sitemap files are fetched when walking a sitemap index. Protects against very large or self-referencing sitemap trees.", "default": 200 }, "emitSummaryReport": { "title": "Append summary report row", "type": "boolean", "description": "Adds one final dataset item with recordType 'summary' containing counts, section breakdown, content-freshness breakdown and any errors encountered.", "default": true }, "requestTimeoutSec": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per-request timeout when downloading sitemap files.", "default": 45 }, "proxyConfig": { "title": "Proxy configuration", "type": "object", "description": "Optional. Sitemaps are static XML and rarely blocked, so no proxy is used by default. Enable this only if the target site restricts direct access.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }