{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Delta Monitor", "description": "Monitor public sitemap.xml files for new URLs, removed URLs, lastmod changes, and clean stateful deltas for SEO, RAG indexing, and content operations.", "version": "0.2", "x-build-id": "qAa0V0VtKUksWX0Ba" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/stellar_ballet_0bu~sitemap-delta-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-stellar_ballet_0bu-sitemap-delta-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/stellar_ballet_0bu~sitemap-delta-monitor/runs": { "post": { "operationId": "runs-sync-stellar_ballet_0bu-sitemap-delta-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/stellar_ballet_0bu~sitemap-delta-monitor/run-sync": { "post": { "operationId": "run-sync-stellar_ballet_0bu-sitemap-delta-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "sitemapUrls" ], "properties": { "sitemapUrls": { "title": "Sitemap URLs (or root domains if discoverSitemaps is true)", "type": "array", "description": "Public sitemap.xml or sitemap index URLs. When discoverSitemaps is enabled, root domains (e.g. https://example.com) are also accepted — the actor will fetch /robots.txt and enqueue Sitemap entries from it.", "items": { "type": "string" } }, "discoverSitemaps": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "If true, fetch each start URL's robots.txt and enqueue any Sitemap entries found there. Only works on sites that publish a robots.txt.", "default": false }, "urlFilterRegex": { "title": "URL filter regex", "type": "string", "description": "Optional JavaScript-compatible regex applied to discovered URLs. Matched URLs are included in the output and the persisted snapshot; non-matches are ignored. Applies to final URLs, not intermediate sitemaps.", "default": "" }, "changeTypes": { "title": "Change types to emit", "type": "array", "description": "Which change types to emit as dataset rows. Defaults to ['new_url', 'updated_url', 'removed_url'] (delta-only). Add 'unchanged' to also include rows that did not change since the previous snapshot.", "default": [ "new_url", "updated_url", "removed_url" ], "items": { "type": "string" } }, "addRemovedUrlsToKvs": { "title": "Add removed URLs to key-value store", "type": "boolean", "description": "When true, also write a REMOVED-URLS key to the state key-value store with the full list of URLs that disappeared since the last snapshot, in addition to emitting 'removed_url' rows in the dataset.", "default": false }, "previousItems": { "title": "Previous items", "type": "array", "description": "Optional previous sitemap URL rows from an earlier run (overrides persisted state if provided).", "default": [] }, "onlyChanged": { "title": "Only output changed URLs (legacy alias for changeTypes)", "type": "boolean", "description": "If true (default), only emit rows whose status is not 'unchanged'. Equivalent to changeTypes excluding 'unchanged'.", "default": true }, "persistState": { "title": "Persist state between runs", "type": "boolean", "description": "Store the latest sitemap snapshot in a named key-value store.", "default": true }, "stateStoreName": { "title": "State store name", "type": "string", "description": "Named key-value store used for snapshots when persistState is enabled.", "default": "sitemap-delta-monitor-state" }, "stateKey": { "title": "State key override", "type": "string", "description": "Optional snapshot key. Leave empty to derive from input sitemap URLs.", "default": "" }, "maxSitemapUrls": { "title": "Max nested sitemaps", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum nested sitemap URLs to fetch from sitemap indexes (and from robots.txt discovery).", "default": 25 }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum URLs to track per run.", "default": 5000 }, "requestTimeoutMs": { "title": "Request timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Per-request timeout in milliseconds for sitemap and robots.txt fetches.", "default": 30000 } } }, "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 } } } } } } } } } }