{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor Plus", "description": "Lists every URL from a site's robots.txt and nested or gzipped sitemaps with lastmod, a changed-since filter, per-section counts and optional HTTP status checks.", "version": "0.1", "x-build-id": "SthTGggdJJ5yBoWh1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gmanner~sitemap-extractor-plus/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gmanner-sitemap-extractor-plus", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gmanner~sitemap-extractor-plus/runs": { "post": { "operationId": "runs-sync-gmanner-sitemap-extractor-plus", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gmanner~sitemap-extractor-plus/run-sync": { "post": { "operationId": "run-sync-gmanner-sitemap-extractor-plus", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Sites or sitemap URLs", "type": "array", "description": "Site homepages (the Actor reads robots.txt and falls back to /sitemap.xml and friends) or direct sitemap URLs (.xml, .xml.gz, .txt, sitemap indexes).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "changedSince": { "title": "Only URLs changed since", "type": "string", "description": "Keep only URLs whose is at or after this moment. Accepts an ISO date (2026-10-01), an ISO datetime, or a relative period: 24h, 7d, 2w, 1m. Child sitemaps whose own lastmod is older are skipped entirely, which makes incremental runs fast. Leave empty to list everything." }, "keepUrlsWithoutLastmod": { "title": "Keep URLs without lastmod when filtering by date", "type": "boolean", "description": "When 'Only URLs changed since' is set, URLs that have no are dropped by default. Enable this to keep them.", "default": false }, "includeUrlPattern": { "title": "Include URL pattern (regex)", "type": "string", "description": "Only list URLs matching this case-insensitive regular expression, e.g. ^https://www\\.example\\.com/blog/" }, "excludeUrlPattern": { "title": "Exclude URL pattern (regex)", "type": "string", "description": "Skip URLs matching this case-insensitive regular expression, e.g. \\.(jpg|png|pdf)$" }, "checkStatus": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send a HEAD request (GET fallback) to every listed URL, 5 at a time, and add status, finalUrl, redirected and contentType. Charged as a separate 'status-checked' event.", "default": false }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many unique URLs have been listed. The run cost is bounded by this number.", "default": 10000 }, "maxSitemaps": { "title": "Maximum sitemap files", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Stop fetching sitemap files after this many (indexes and leaves combined).", "default": 500 }, "maxDepth": { "title": "Maximum index nesting depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many levels of sitemap indexes to follow. 0 reads only the sitemaps named in robots.txt or the input.", "default": 5 }, "discoverFromRobots": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "For site URLs, read /robots.txt 'Sitemap:' lines first. If disabled or nothing is listed, common paths such as /sitemap.xml and /sitemap_index.xml are tried.", "default": true }, "skipUnchangedSitemaps": { "title": "Skip child sitemaps older than the date filter", "type": "boolean", "description": "When filtering by date, do not download child sitemaps whose in the index is older than the cutoff.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Per-request timeout for sitemap downloads and status checks.", "default": 60 }, "userAgent": { "title": "User-Agent header", "type": "string", "description": "Sent with every request. The default is a plain desktop browser string.", "default": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36" } } }, "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 } } } } } } } } } }