{ "openapi": "3.0.1", "info": { "title": "Sitemap Robots Delta Monitor", "description": "Monitor sitemap.xml and robots.txt for URL inventory changes and return new, changed, or removed URLs in normalized JSON.", "version": "0.1", "x-build-id": "DqmnHRf0O3rMNUSxJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tom_the_builder~sitemap-robots-delta-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tom_the_builder-sitemap-robots-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tom_the_builder~sitemap-robots-delta-monitor/runs": { "post": { "operationId": "runs-sync-tom_the_builder-sitemap-robots-delta-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tom_the_builder~sitemap-robots-delta-monitor/run-sync": { "post": { "operationId": "run-sync-tom_the_builder-sitemap-robots-delta-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mode": { "title": "Run mode", "enum": [ "snapshot", "delta" ], "type": "string", "description": "Use snapshot to return the current URL inventory, or delta to return only new, changed, and removed URLs compared with the previous run for the same state key.", "default": "snapshot" }, "changeMode": { "title": "Delta mode", "enum": [ "new_only", "new_and_changed" ], "type": "string", "description": "Choose whether delta runs return only new URLs or both new and changed URLs. Removed URLs are included when includeRemoved is enabled.", "default": "new_and_changed" }, "stateKey": { "title": "State key", "type": "string", "description": "Persistent state namespace. Use a stable key per monitored website group.", "default": "sitemap-robots-default" }, "sites": { "title": "Website base URLs", "type": "array", "description": "Website base URLs. The Actor discovers Sitemap declarations from robots.txt and /sitemap.xml.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Direct sitemap URLs", "type": "array", "description": "Optional direct sitemap.xml or sitemap index URLs.", "default": [], "items": { "type": "string" } }, "includeRobotsSitemaps": { "title": "Read robots.txt Sitemap lines", "type": "boolean", "description": "Discover Sitemap: declarations from /robots.txt.", "default": true }, "includeDefaultSitemap": { "title": "Try /sitemap.xml", "type": "boolean", "description": "Also try the common /sitemap.xml location.", "default": true }, "sameHostOnly": { "title": "Same host only", "type": "boolean", "description": "Keep sitemap URLs and listed pages on the same hostname as the input site.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemaps per site", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum sitemap files to read per site, including sitemap indexes.", "default": 10 }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum sitemap URL records to collect per site before delta filtering.", "default": 1000 }, "maxItems": { "title": "Max output items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum dataset items to write after snapshot or delta selection.", "default": 100 }, "includePatterns": { "title": "Include URL regex patterns", "type": "array", "description": "Optional JavaScript regex patterns. If set, only matching URLs are kept.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URL regex patterns", "type": "array", "description": "Optional JavaScript regex patterns for URLs to exclude.", "default": [], "items": { "type": "string" } }, "checkStatus": { "title": "Check URL HTTP status", "type": "boolean", "description": "Use lightweight HEAD requests for listed URLs. This is slower but useful for sitemap QA.", "default": false }, "includeRemoved": { "title": "Include removed URLs", "type": "boolean", "description": "On delta runs, report URLs that existed in the previous state but no longer appear.", "default": true }, "includeUnchanged": { "title": "Include unchanged URLs", "type": "boolean", "description": "On delta runs, also include unchanged URLs. Usually leave this off for low-noise monitoring.", "default": false }, "webhookMode": { "title": "Webhook payload", "enum": [ "summary", "full" ], "type": "string", "description": "Full includes all output items in WEBHOOK_PAYLOAD. Summary includes the first 20.", "default": "full" }, "userAgent": { "title": "User-Agent", "type": "string", "description": "User-Agent header used for sitemap, robots.txt, and optional status requests.", "default": "sitemap-robots-delta-monitor/0.1 (+https://apify.com)" } } }, "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 } } } } } } } } } }