{ "openapi": "3.0.1", "info": { "title": "NPI Registry Scraper - Healthcare Providers & Leads", "description": "Scrape the NPPES NPI Registry: US doctors, clinicians & healthcare organizations by name, NPI, state, city, ZIP or specialty. Get addresses, phone & fax, taxonomies, licenses, org authorized officials, contact leads & lead scores. Monitor new registrations. No key.", "version": "0.1", "x-build-id": "lIwOuqtAj1hk3xl56" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~npi-nppes-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-npi-nppes-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~npi-nppes-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-npi-nppes-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~npi-nppes-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-npi-nppes-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "search", "npiLookup" ], "type": "string", "description": "How to find providers. \"search\" queries the registry by criteria (name, location, specialty…). \"npiLookup\" fetches specific NPI numbers directly.", "default": "search" }, "outputType": { "title": "Output type", "enum": [ "providers", "leads", "both" ], "type": "string", "description": "\"providers\" = full registry records (taxonomies, licenses, addresses, identifiers). \"leads\" = contact-focused B2B leads (named contact, phone, specialty, lead score). \"both\" emits one of each per provider.", "default": "providers" }, "taxonomyDescription": { "title": "Specialty / taxonomy", "type": "string", "description": "Provider type / specialty from the NUCC taxonomy, e.g. \"Dentist\", \"Physical Therapist\", \"Pharmacy\", \"Internal Medicine\", \"Nurse Practitioner\". Partial matches and a trailing * wildcard are supported." }, "specialty": { "title": "Specialty (alias)", "type": "string", "description": "Friendly alias for the specialty / taxonomy field above — use either one." }, "taxonomyDescriptions": { "title": "Multiple specialties", "type": "array", "description": "Run several specialties in one go (combined with each state/city/ZIP below).", "items": { "type": "string" } }, "state": { "title": "State", "type": "string", "description": "Two-letter US state/territory code, e.g. CA, TX, NY, FL." }, "states": { "title": "Multiple states", "type": "array", "description": "Run several states in one go (cross-combined with each specialty/city/ZIP).", "items": { "type": "string" } }, "city": { "title": "City", "type": "string", "description": "City name to match against the provider address." }, "cities": { "title": "Multiple cities", "type": "array", "description": "Run several cities in one go (cross-combined with each specialty/state/ZIP).", "items": { "type": "string" } }, "postalCode": { "title": "ZIP / postal code", "type": "string", "description": "5-digit ZIP. A trailing * wildcard is supported (e.g. 902* for the 902xx area)." }, "postalCodes": { "title": "Multiple ZIPs", "type": "array", "description": "Run several ZIP codes in one go (cross-combined with the other criteria).", "items": { "type": "string" } }, "firstName": { "title": "First name (individuals)", "type": "string", "description": "For NPI-1 individual providers. Trailing * wildcard supported." }, "lastName": { "title": "Last name (individuals)", "type": "string", "description": "For NPI-1 individual providers. Trailing * wildcard supported." }, "organizationName": { "title": "Organization name (orgs)", "type": "string", "description": "For NPI-2 organizations, e.g. \"CVS Pharmacy\", \"Mayo Clinic\". Trailing * wildcard supported." }, "enumerationType": { "title": "Provider type", "enum": [ "", "NPI-1", "NPI-2" ], "type": "string", "description": "Limit to individuals (NPI-1) or organizations (NPI-2). Leave blank for both.", "default": "" }, "addressPurpose": { "title": "Address purpose", "enum": [ "", "LOCATION", "MAILING", "PRIMARY", "SECONDARY" ], "type": "string", "description": "Match the state/city/ZIP against the provider's LOCATION (practice) or MAILING address. Leave blank for the default.", "default": "" }, "countryCode": { "title": "Country code", "type": "string", "description": "Two-letter country code; defaults to US.", "default": "US" }, "npiNumbers": { "title": "NPI numbers (npiLookup mode)", "type": "array", "description": "One or more 10-digit NPI numbers to fetch directly.", "items": { "type": "string" } }, "searchUrls": { "title": "NPPES URLs", "type": "array", "description": "Paste NPPES API or registry URLs — their query parameters (state, taxonomy, name, number…) are parsed and added as searches.", "items": { "type": "string" } }, "enrichContacts": { "title": "Enrich contacts (website crawl)", "type": "boolean", "description": "When building leads, if a provider lists a website endpoint, fetch its homepage to pull emails and social links. Off by default (NPPES rarely lists a marketing website; phone, fax and the org authorized official are always included regardless).", "default": false }, "maxResults": { "title": "Max providers", "minimum": 1, "type": "integer", "description": "Maximum number of providers to scrape. Each NPPES query returns up to 1,200 results; narrow by specialty/state/city to go deeper.", "default": 200 }, "deduplicateResults": { "title": "Deduplicate by NPI", "type": "boolean", "description": "Skip duplicate providers (same NPI) within a run.", "default": true }, "monitorMode": { "title": "Monitor mode (only new)", "type": "boolean", "description": "Remember NPIs seen in previous runs (in a named key-value store) and emit only newly-appearing providers — ideal on a schedule to capture new healthcare registrations as fresh leads.", "default": false }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Name your monitor so different searches keep separate memory (e.g. \"ca-dentists\").", "default": "default" }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 12, "type": "integer", "description": "Number of parallel requests (NPI lookups and contact enrichment).", "default": 6 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "The NPPES API is clean from Apify datacenter proxies; a fresh IP is rotated per request to spread the per-IP rate limit.", "default": { "useApifyProxy": true } }, "urlsFromFile": { "title": "Import URLs from a file", "type": "string", "description": "Paste a list of URLs (one per line), OR one link to a .txt/.csv file, Google Sheet or Google Drive file containing them. Lets you import many Start URLs at once instead of typing each. Google Sheet/Drive share links are handled automatically." } } }, "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 } } } } } } } } } }