{ "openapi": "3.0.1", "info": { "title": "NMLS Consumer Access Scraper — Licenses & Contacts", "description": "Scrape NMLS Consumer Access for mortgage companies, MLOs, and branches — state licenses with statuses and dates, regulatory disclosures with PDF links, trade names, and sponsor/branch relationships. Search by name, NMLS ID, or state; CAPTCHA solved automatically. Clean JSON/CSV output.", "version": "0.0", "x-build-id": "kcgqZhuE8BODFi8ig" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~nmls-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-nmls-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~nmls-scraper/runs": { "post": { "operationId": "runs-sync-memo23-nmls-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~nmls-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-nmls-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Search mode", "enum": [ "by_name", "by_id", "by_state", "by_url", "by_company_employees" ], "type": "string", "description": "How the crawl is seeded. `by_name` searches NMLS for each string in Names. `by_id` fetches each NMLS ID directly. `by_state` searches a whole state (pair with Entity type). `by_url` crawls the Start URLs you paste. `by_company_employees` fetches each sponsoring company, then its sponsored MLOs. Default: `by_name`.", "default": "by_name" }, "names": { "title": "Names / search queries", "type": "array", "description": "Company or person names to search (mode = By name). Add a city, state, or ZIP to narrow — NMLS rejects overly broad searches. Example: `Rocket Mortgage Detroit MI`.", "items": { "type": "string" } }, "nmlsIds": { "title": "NMLS IDs", "type": "array", "description": "Exact NMLS ID numbers to fetch directly (mode = By NMLS ID). Each is tried as a company, individual, then branch (or restricted by the Entity type below).", "items": { "type": "string" } }, "sponsoringCompanyIds": { "title": "Sponsoring company NMLS IDs", "type": "array", "description": "Company NMLS IDs whose sponsored MLOs you want (mode = By company employees). Each company is fetched, then NMLS search is run on its name (per licensed state, or per state in States) and every hit is kept only if its detail page names this company as sponsor. Example: `3030` (Rocket Mortgage). Large sponsors are sampled, not exhaustive — NMLS caps search results.", "items": { "type": "string" } }, "states": { "title": "States", "type": "array", "description": "Two-letter US state codes (e.g. `TX`, `CA`). Used as the query in By-state mode, or as a filter in other modes.", "items": { "type": "string" } }, "entityType": { "title": "Entity type filter", "enum": [ "", "COMPANY", "INDIVIDUAL", "BRANCH" ], "type": "string", "description": "Restrict results to companies, individuals (MLOs), or branches. Leave as `Any` to include all three. Example: `BRANCH`. Default: Any.", "default": "" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Exact nmlsconsumeraccess.org URLs (mode = By URL) — detail pages like `/EntityDetails.aspx/COMPANY/3030` or search URLs `/Home.aspx/SubSearch?searchText=...`.", "items": { "type": "string" } }, "includeDisclosures": { "title": "Include disclosures", "type": "boolean", "description": "Include the disclosures section (regulatory action documents) in each row.", "default": true }, "maxSeedDepth": { "title": "Relationship expansion depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "Follow relationships out from each seed entity: an individual's sponsoring companies and a company's branches and sponsored MLOs. 0 = seeds only (By company employees still expands MLOs), 1 = seeds + their direct relations, etc.", "default": 0 }, "maxSeedExpansions": { "title": "Max related entities", "minimum": 0, "type": "integer", "description": "Hard cap on how many related entities the expansion may add, so a broad seed can't balloon the run.", "default": 100 }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of entities collected (controls billing).", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of detail pages fetched in parallel over the shared session.", "default": 5 }, "enrichEmails": { "title": "Enrich with contact emails (experimental)", "type": "boolean", "description": "When true, each company/branch (and any entity with a self-reported website) is looked up to attach `contact_email`, `contact_website`, and `emailEnrichment`. Adds time per row. Charged $0.05 only when an email is found (currently via `additional-data` units; a named `contact-email` event follows on the next pricing window). Default: false.", "default": false }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "NMLS is behind Cloudflare and blocks datacenter IPs — residential proxies are required. Defaults to Apify RESIDENTIAL.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }