{ "openapi": "3.0.1", "info": { "title": "Sitemap Change Monitor – New, Updated & Removed Pages", "description": "Watch any websites' XML sitemaps and get only the pages that were added, updated (lastmod) or removed since the last run. Auto-discovers sitemaps via robots.txt, follows sitemap indexes and .gz files.", "version": "0.1", "x-build-id": "QvUzXs1SDEs6SvOGb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/quietjoy~sitemap-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-quietjoy-sitemap-change-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/quietjoy~sitemap-change-monitor/runs": { "post": { "operationId": "runs-sync-quietjoy-sitemap-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/quietjoy~sitemap-change-monitor/run-sync": { "post": { "operationId": "run-sync-quietjoy-sitemap-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sites": { "title": "Websites or sitemap URLs", "type": "array", "description": "Website homepages (e.g. `https://crawlee.dev` – sitemaps are discovered from robots.txt, then /sitemap.xml) or direct sitemap / sitemap-index URLs (e.g. `https://example.com/sitemap_index.xml`). If empty, a demo site is used.", "items": { "type": "string" } }, "onlyChanges": { "title": "Only output changes", "type": "boolean", "description": "Output only new, updated and removed URLs compared with the previous run of the same site (stored in the named key-value store below). The first run of a site is a baseline and outputs all URLs as `new` with `isBaseline: true`. Turn off to output every URL each run (unchanged ones get `changeType: unchanged`).", "default": true }, "outputBaselineUrls": { "title": "Output all URLs on the first (baseline) run", "type": "boolean", "description": "When a site is checked for the first time, output all its URLs as `new`. Turn off to record the baseline silently, so the first run outputs nothing and later runs output only real changes (used with Only output changes).", "default": true }, "reportRemoved": { "title": "Report removed URLs", "type": "boolean", "description": "Output URLs that were in the previous run's sitemaps but are gone now. Skipped automatically when a sitemap failed to load or the URL limit was hit, to avoid false alarms.", "default": true }, "trackLastmod": { "title": "Report updated pages (lastmod)", "type": "boolean", "description": "Report a URL as `updated` when its `` date changes. Turn off for sites whose lastmod changes on every build.", "default": true }, "includeUrlRegex": { "title": "Only URLs matching (regex)", "type": "string", "description": "Optional case-insensitive regular expression; only matching page URLs are tracked, e.g. `/blog/|/news/`.", "default": "" }, "excludeUrlRegex": { "title": "Exclude URLs matching (regex)", "type": "string", "description": "Optional case-insensitive regular expression for page URLs to ignore, e.g. `/tag/|/author/`.", "default": "" }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop collecting after this many page URLs per site. When the limit is hit, removed-URL detection is skipped for that site.", "default": 10000 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Maximum number of sitemap / sitemap-index files to download per site.", "default": 200 }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Name of the key-value store that remembers each site's URLs between runs. Use a different name for separate monitors.", "default": "sitemap-change-monitor-state" }, "requestDelayMs": { "title": "Delay between sitemap requests (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Polite pause between sitemap downloads.", "default": 300 } } }, "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 } } } } } } } } } }