{ "openapi": "3.0.1", "info": { "title": "Scraper Freshness Watchdog — Dataset Health Monitor", "description": "Detect stale, empty, duplicated, invalid, or sharply reduced scraper output from inline rows or a public JSON feed. Save one deterministic health record and optionally fail unhealthy scheduled runs for native alerts.", "version": "1.0", "x-build-id": "LZZZcVRVyyJ3wfHBJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/convenient_yarn~scraper-freshness-watchdog/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-convenient_yarn-scraper-freshness-watchdog", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/convenient_yarn~scraper-freshness-watchdog/runs": { "post": { "operationId": "runs-sync-convenient_yarn-scraper-freshness-watchdog", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/convenient_yarn~scraper-freshness-watchdog/run-sync": { "post": { "operationId": "run-sync-convenient_yarn-scraper-freshness-watchdog", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "timestampField", "maxAgeMinutes" ], "properties": { "sourceUrl": { "title": "Public JSON URL", "type": "string", "description": "HTTPS URL returning public JSON. Local and private-network hosts are rejected." }, "rows": { "title": "Inline rows", "type": "array", "description": "Use inline rows instead of sourceUrl." }, "rowsPath": { "title": "Rows path", "type": "string", "description": "Dot path to the array inside the JSON response, for example data.items." }, "timestampField": { "title": "Timestamp field", "type": "string", "description": "Dot path to each row's ISO timestamp.", "default": "updatedAt" }, "idField": { "title": "ID field", "type": "string", "description": "Optional dot path used to count duplicate IDs." }, "maxAgeMinutes": { "title": "Maximum age (minutes)", "minimum": 0, "type": "integer", "description": "Flag the dataset when its newest valid timestamp is older than this many minutes.", "default": 1440 }, "minimumRows": { "title": "Minimum rows", "minimum": 0, "type": "integer", "description": "Fail the check when the selected JSON array contains fewer rows than this value.", "default": 1 }, "previousRowCount": { "title": "Previous row count", "minimum": 0, "type": "integer", "description": "Optional manual baseline. When supplied it overrides stored history for this run." }, "autoBaseline": { "title": "Remember row count between runs", "type": "boolean", "description": "Stores this run's row count in a named key-value store and compares it on the next run.", "default": true }, "failOnIssues": { "title": "Fail run when issues are found", "type": "boolean", "description": "Marks the Actor run failed after saving its output when stale, missing, duplicate, invalid, or sharply reduced data is detected. Use Apify task failure notifications or webhooks as the alert destination.", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Stable identity for inline data. Public source URLs are used automatically when this is omitted." } } }, "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 } } } } } } } } } }