{ "openapi": "3.0.1", "info": { "title": "NYC Restaurant Inspection Results Scraper", "description": "Restaurant inspection violations in New York City from NYC Open Data (DOHMH): name, address, violation, grade and inspection date, filtered by date and borough.", "version": "0.1", "x-build-id": "dkbKfd2i8IF2azyGW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/knotty_mistveil~nyc-restaurant-inspection-results/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-knotty_mistveil-nyc-restaurant-inspection-results", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/knotty_mistveil~nyc-restaurant-inspection-results/runs": { "post": { "operationId": "runs-sync-knotty_mistveil-nyc-restaurant-inspection-results", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/knotty_mistveil~nyc-restaurant-inspection-results/run-sync": { "post": { "operationId": "run-sync-knotty_mistveil-nyc-restaurant-inspection-results", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "daysBack": { "title": "Days back", "minimum": 1, "maximum": 366, "type": "integer", "description": "Look-back window on the INSPECTION date, counted back from the run. Because inspection dates are calendar dates, 7 means today plus the seven previous days. Ignored when Date from / Date to are set. The source publishes about 1 business day behind (measured 2026-10-05), so a 1-day window can occasionally return nothing.", "default": 7 }, "dateFrom": { "title": "Date from", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Earliest inspection date, YYYY-MM-DD (inclusive). Overrides Days back." }, "dateTo": { "title": "Date to", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Latest inspection date, YYYY-MM-DD (inclusive). Defaults to the day the run starts." }, "boroughs": { "title": "Boroughs", "type": "array", "description": "Keep only these NYC boroughs. Empty = every borough, including the small number of rows the source could not geocode to one (borough is null there). Case-sensitive, exact match.", "items": { "type": "string", "enum": [ "Manhattan", "Brooklyn", "Queens", "Bronx", "Staten Island" ] } }, "keywords": { "title": "Keywords (restaurant name or cuisine)", "type": "array", "description": "Case-insensitive substrings matched against the restaurant name (dba) and cuisine description; a row is kept when any term matches. Examples: \"pizza\", \"starbucks\", \"bakery\". Empty = no keyword filter.", "items": { "type": "string" } }, "grades": { "title": "Grades", "type": "array", "description": "Keep only rows whose inspection grade is one of these. A = A, B = B, C = C, N = Not Yet Graded, Z = Grade Pending, P = Grade Pending (issued on reopening). About half of all rows carry no grade at all (the inspection type does not produce one); those are excluded whenever this filter is non-empty. Empty = every grade, including ungraded rows.", "items": { "type": "string", "enum": [ "A", "B", "C", "N", "P", "Z" ], "enumTitles": [ "A", "B", "C", "N - Not Yet Graded", "P - Grade Pending (reopening)", "Z - Grade Pending" ] } }, "onlyCritical": { "title": "Only critical violations", "type": "boolean", "description": "Keep only rows whose violation is flagged Critical (a violation type the NYC Health Code treats as more likely to contribute to foodborne illness). Rows with no violation at all (critical_flag = \"Not Applicable\") are excluded when this is on.", "default": false }, "socrataAppToken": { "title": "Socrata app token (optional)", "type": "string", "description": "Optional free Socrata application token, sent as the X-App-Token header. Not required: the Actor works without one. A token lifts the shared per-IP throttle, which matters only for very large windows. Register at https://evergreen.data.socrata.com/profile/app_tokens." }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many rows. You are charged per row delivered, so this is also the cost cap. Rows come newest-first by inspection date, so a value below the window's volume drops the OLDEST rows. The source produces roughly 300-600 violation rows per weekday citywide (measured 2026-09-21..25) and almost none on weekends, so a gap-free 7-day window needs about 3000.", "default": 500 } } }, "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 } } } } } } } } } }