{ "openapi": "3.0.1", "info": { "title": "Building Permits Scraper - Socrata Open Data (Multi-City)", "description": "Scrape building and construction permits from any Socrata open-data portal (NYC, SF, Chicago, LA, and hundreds more). Pull issue date, permit and work type, status, address, contractor, owner, coordinates and every column the dataset exposes. HTTP-first, multi-city in one run.", "version": "1.2", "x-build-id": "snWgWTnXCW0zEml69" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bujhmml~building-permits-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bujhmml-building-permits-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bujhmml~building-permits-scraper/runs": { "post": { "operationId": "runs-sync-bujhmml-building-permits-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bujhmml~building-permits-scraper/run-sync": { "post": { "operationId": "run-sync-bujhmml-building-permits-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "domain": { "title": "Socrata domain", "type": "string", "description": "Open-data host, e.g. data.cityofnewyork.us, data.sfgov.org, data.cityofchicago.org. Leave empty if you use the Datasets list below." }, "datasetId": { "title": "Dataset id (4x4)", "pattern": "^[a-z0-9]{4}-[a-z0-9]{4}$", "type": "string", "description": "Socrata dataset identifier, the 4x4 code from the dataset URL (e.g. ipu4-2q9a for NYC DOB Permit Issuance)." }, "searchQuery": { "title": "Keyword search", "maxLength": 2000, "type": "string", "description": "Full-text search across all text columns, e.g. solar, roofing, HVAC, demolition. Matches any permit whose text mentions the keyword. Applied to every dataset in the run." }, "dateField": { "title": "Date column", "type": "string", "description": "Column to filter by date, e.g. issuance_date, issued_date, status_date. Required if you set Date from / Date to. Column names differ per dataset — check the dataset's columns." }, "dateFrom": { "title": "Date from", "type": "string", "description": "Keep permits with Date column on or after this date. Format YYYY-MM-DD (e.g. 2024-01-01). Needs Date column set." }, "dateTo": { "title": "Date to", "type": "string", "description": "Keep permits with Date column on or before this date. Format YYYY-MM-DD (e.g. 2024-12-31). Needs Date column set." }, "whereClause": { "title": "Filter (SoQL $where)", "maxLength": 2000, "type": "string", "description": "Optional raw SoQL filter, e.g. borough='MANHATTAN' or estimated_cost > 50000. AND-merged with the date filter above. Leave empty for everything." }, "select": { "title": "Columns to keep (SoQL $select)", "maxLength": 2000, "type": "string", "description": "Comma-separated columns to return, e.g. issuance_date, permit_type, address. Slims output and lowers cost. Leave empty for all columns. :id is added automatically for deduplication on column projections. Raw SoQL scoped to this single public dataset; aggregates like count(*) or borough, count(*) as n with a GROUP BY are passed through as-is (no :id injection, no dedup)." }, "datasets": { "title": "Datasets (multi-city)", "type": "array", "description": "Scrape several cities/datasets in one run. Each item: { \"domain\": \"data.sfgov.org\", \"datasetId\": \"i98e-djp9\", \"whereClause\": \"...\", \"dateField\": \"...\", \"dateFrom\": \"...\", \"dateTo\": \"...\" }. Per-item filters override the global ones; if omitted, the global values apply. Runs in addition to the single domain/datasetId above." }, "maxItems": { "title": "Max results", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Stop after this many permit records across all datasets. 0 = no limit.", "default": 100 }, "order": { "title": "Sort order (SoQL $order)", "maxLength": 2000, "type": "string", "description": "Column(s) to sort by, e.g. issuance_date DESC for newest first. :id is always appended to keep pagination stable. Defaults to :id." }, "appToken": { "title": "Socrata app token", "type": "string", "description": "Optional X-App-Token. Not required for moderate volume; raises Socrata's per-IP rate limits if you have one. A wrong token makes every request fail with 403." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy. The Socrata API has no anti-bot, so proxies are optional; datacenter is plenty if you want one.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }