{ "openapi": "3.0.1", "info": { "title": "NYS DOCCS Basic Snapshot", "description": "Scrapes the NYS DOCCS public incarcerated person lookup by last-name prefixes and outputs a resumable, structured basic snapshot with DIN, name, status, facility, age, race, DOB, source, page, and scrape provenance fields.", "version": "0.3", "x-build-id": "C3NfCWejratLvLOc1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jippylong12~nys-doccs-basic-snapshot/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jippylong12-nys-doccs-basic-snapshot", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jippylong12~nys-doccs-basic-snapshot/runs": { "post": { "operationId": "runs-sync-jippylong12-nys-doccs-basic-snapshot", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jippylong12~nys-doccs-basic-snapshot/run-sync": { "post": { "operationId": "run-sync-jippylong12-nys-doccs-basic-snapshot", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "prefixes": { "title": "Last-name prefixes", "uniqueItems": true, "type": "array", "description": "Optional explicit prefixes to send as lastName in the SearchByName JSON request. Leave empty to auto-generate AA-ZZ from prefixDepth by default.", "items": { "type": "string", "minLength": 1 } }, "prefixDepth": { "title": "Auto-generated prefix depth", "minimum": 1, "maximum": 3, "type": "integer", "description": "Used only when prefixes is empty. Set 1 for A-Z. Set 2 for AA-ZZ. Because the API does not expose a total-result count, 2 is the safer default for broader recurring scrapes.", "default": 2 }, "requestDelayMs": { "title": "Delay between requests per worker (ms)", "minimum": 0, "type": "integer", "description": "Conservative pacing between the homepage session GET and the JSON POST requests. This delay is applied independently inside each worker session.", "default": 3000 }, "maxPagesPerPrefix": { "title": "Max pages per prefix", "minimum": 0, "type": "integer", "description": "Maximum pages to fetch for each prefix. Use 0 to paginate until the endpoint returns no persons or repeats the last DIN cursor.", "default": 0 }, "workerCount": { "title": "Worker count", "minimum": 1, "maximum": 12, "type": "integer", "description": "Number of parallel prefix workers to run inside one Actor. Each worker uses its own cookie-backed session and pacing window.", "default": 4 }, "proxyMode": { "title": "Proxy mode", "enum": [ "none", "datacenter", "residential" ], "type": "string", "description": "Use Apify datacenter proxy first for the production basic scrape. Switch to residential only if the target starts throttling or blocking too aggressively.", "default": "datacenter" }, "proxyCountryCode": { "title": "Residential proxy country code", "pattern": "^[A-Za-z]{2}$", "minLength": 2, "maxLength": 2, "type": "string", "description": "Optional 2-letter country code used only when proxyMode is residential." }, "resumeMode": { "title": "Resume mode", "enum": [ "auto", "forceNew" ], "type": "string", "description": "Auto resumes the current unfinished logical scrape run from named storage. Force new abandons the previous unfinished logical run and starts a fresh one.", "default": "auto" }, "logicalRunId": { "title": "Logical run ID", "minLength": 1, "maxLength": 100, "type": "string", "description": "Optional stable logical run identifier for manual recovery or testing. Leave empty for an automatic timestamp-based run ID." }, "retainedCompletedRuns": { "title": "Retained completed runs", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many completed named final datasets to keep after cleanup. Older retained copies are deleted automatically.", "default": 2 }, "sampleRowLimit": { "title": "Sample rows in OUTPUT", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many sample dataset rows to include in the final OUTPUT summary record.", "default": 10 } } }, "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 } } } } } } } } } }