{ "openapi": "3.0.1", "info": { "title": "Companies House Scraper — UK Company Data, Officers & SIC Codes", "description": "Turn Companies House into structured UK company data — no API key, no login. Search 5M+ companies by keyword and filter by status, type, SIC code, location or incorporation date. Each row carries officers, filing dates and registered address. Billed per result", "version": "0.0", "x-build-id": "dm5vrwYGC8GvIcgsE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~companies-house-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-companies-house-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~companies-house-scraper/runs": { "post": { "operationId": "runs-sync-memo23-companies-house-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~companies-house-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-companies-house-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search keywords", "type": "array", "description": "Keywords to search on Companies House, matched against the company name (e.g. 'packaging', 'solar', 'consulting'). Each keyword collects up to Maximum items rows.", "items": { "type": "string" } }, "startUrls": { "title": "Companies House URLs or company numbers (optional)", "type": "array", "description": "Search URLs (https://find-and-update.company-information.service.gov.uk/search/companies?q=...), advanced-search URLs, company profile URLs (/company/{number}), or bare company numbers like 09403356 — all auto-classified.", "items": { "type": "string" } }, "status": { "title": "Company status", "type": "array", "description": "Restrict to these statuses. Allowed: active, dissolved, open, closed, converted-closed, receivership, liquidation, administration, insolvency-proceedings, voluntary-arrangement. Leave empty for all.", "items": { "type": "string" } }, "companyType": { "title": "Company type", "type": "array", "description": "Restrict to these types. Allowed: ltd, plc, llp, limited-partnership, private-unlimited, community-interest-company, royal-charter, private-limited-guarant-nsc, and more. Leave empty for all.", "items": { "type": "string" } }, "sicCodes": { "title": "SIC codes", "type": "array", "description": "Restrict to these Standard Industrial Classification codes (4–5 digit, e.g. 62012 for business software development). Leave empty for all industries.", "items": { "type": "string" } }, "location": { "title": "Registered office location", "type": "string", "description": "Registered office address contains this text — a town, region or postcode (e.g. 'Manchester', 'EC1'). Leave empty for anywhere in the UK." }, "incorporatedFrom": { "title": "Incorporated from (YYYY-MM-DD)", "type": "string", "description": "Only companies incorporated on or after this date. Format YYYY-MM-DD." }, "incorporatedTo": { "title": "Incorporated to (YYYY-MM-DD)", "type": "string", "description": "Only companies incorporated on or before this date. Format YYYY-MM-DD." }, "includeOfficers": { "title": "Include officers (directors + secretaries)", "type": "boolean", "description": "When enabled, each company's officers page is fetched to add an `officers` array — name, role, appointment/resignation dates, date of birth, nationality, country of residence, and correspondence address. Adds one HTTP call per company.", "default": true }, "includePscs": { "title": "Include persons with significant control (PSCs)", "type": "boolean", "description": "When enabled, each company's PSC page is fetched to add a `pscs` array (people/entities with significant control). Adds one HTTP call per company.", "default": false }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of company rows collected across all keywords. Use this to limit billing.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of companies processed in parallel.", "default": 10 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum number of requests processed in parallel.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed request is given up.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Companies House is a public GOV.UK service reachable without a proxy. A UK proxy is optional; residential is the safe default for large runs.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "GB" } } } }, "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 } } } } } } } } } }