{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor & Checker - All URLs, lastmod, Status", "description": "Get all URLs of any website from its sitemaps: auto-discovery via robots.txt, nested sitemap indexes, .gz, RSS/Atom/TXT, image/video/news/hreflang. Date & pattern filters that skip old sub-sitemaps, plus an optional HTTP status check for broken links, redirects and bot-blocked pages.", "version": "1.0", "x-build-id": "O9q2Xox803TOz1c2l" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/paperlinenstudio~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-paperlinenstudio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/paperlinenstudio~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-paperlinenstudio-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/paperlinenstudio~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-paperlinenstudio-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Homepages (sitemaps are discovered via robots.txt and common locations) or direct sitemap URLs (.xml, .xml.gz, .txt, RSS/Atom feeds).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "includePatterns": { "title": "Include URL patterns", "type": "array", "description": "Keep only URLs matching at least one pattern. Plain text = 'contains', wildcards * and ? allowed, or prefix with re: for a regular expression (e.g. re:/blog/\\d{4}/).", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Drop URLs matching any pattern (same syntax as include).", "default": [], "items": { "type": "string" } }, "lastmodWithinDays": { "title": "Only URLs modified in the last N days", "minimum": 0, "type": "integer", "description": "Uses the date from the sitemap. Leave empty to keep all." }, "lastmodAfter": { "title": "Only URLs modified after date", "type": "string", "description": "ISO date, e.g. 2026-01-31. Leave empty to keep all." }, "keepUrlsWithoutLastmod": { "title": "Keep URLs without lastmod when filtering by date", "type": "boolean", "description": "If a date filter is set, URLs that have no are kept when this is on.", "default": true }, "checkStatus": { "title": "Check HTTP status of every URL", "type": "boolean", "description": "Sends a lightweight HEAD request (GET fallback) to each URL and adds statusCode, finalUrl, redirected, contentType and isOk. Finds broken links and redirects in your sitemap.", "default": false }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Drop URLs pointing to other domains (subdomains are kept).", "default": true }, "tryCommonPaths": { "title": "Try common sitemap locations", "type": "boolean", "description": "If robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and others.", "default": true }, "maxUrls": { "title": "Max URLs (total)", "minimum": 1, "type": "integer", "description": "Maximum number of URLs saved in this run.", "default": 100000 }, "maxSitemaps": { "title": "Max sitemap files per website", "minimum": 1, "type": "integer", "description": "Safety limit for huge sitemap indexes.", "default": 1000 }, "concurrency": { "title": "Status-check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests when checking status codes (1–50).", "default": 10 } } }, "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 } } } } } } } } } }