{ "openapi": "3.0.1", "info": { "title": "UK Companies House Bulk Scraper", "description": "Extract UK companies from the official Companies House register. 5M+ businesses by industry (SIC code), location, age, status. Monthly bulk snapshot. No API key. B2B lead-gen, KYC, recruitment, market research. $1/1K companies.", "version": "0.0", "x-build-id": "rvTvcLcNGtcntrCJ2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~uk-companies-house-bulk-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-uk-companies-house-bulk-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/logiover~uk-companies-house-bulk-scraper/runs": { "post": { "operationId": "runs-sync-logiover-uk-companies-house-bulk-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/logiover~uk-companies-house-bulk-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-uk-companies-house-bulk-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": { "snapshotMonth": { "title": "Snapshot month (YYYY-MM)", "type": "string", "description": "Which monthly snapshot to use. Leave blank to use the latest available. Companies House publishes a new snapshot around the 1st of each month.", "default": "" }, "sicCodePrefixes": { "title": "SIC code prefixes", "type": "array", "description": "Filter by Standard Industrial Classification (SIC) code prefix. E.g. [\"62\"] for all IT companies, [\"58\"] for publishing, [\"70\"] for management consulting. Multiple prefixes are OR-ed. See https://resources.companieshouse.gov.uk/sic/ for the full list.", "default": [], "items": { "type": "string" } }, "sicKeywords": { "title": "SIC keywords", "type": "array", "description": "Filter by free-text substring inside the SIC description (case-insensitive). E.g. [\"software\", \"consulting\"]. Multiple keywords are OR-ed.", "default": [], "items": { "type": "string" } }, "nameContains": { "title": "Company name contains", "type": "string", "description": "Substring filter on company name (case-insensitive). E.g. \"TECH\" matches \"FINTECH LTD\", \"TECHWAVE LIMITED\", etc.", "default": "" }, "companyStatuses": { "title": "Company statuses", "type": "array", "description": "Which company statuses to include. Most users want only \"Active\" companies for lead-gen.", "default": [ "Active" ], "items": { "type": "string" } }, "companyCategories": { "title": "Company categories", "type": "array", "description": "E.g. \"Private Limited Company\", \"Public Limited Company\", \"Limited Liability Partnership\". Leave empty for all categories.", "default": [], "items": { "type": "string" } }, "postCodePrefixes": { "title": "Post-code prefixes", "type": "array", "description": "UK postcode prefix match. E.g. [\"SW1\", \"EC1\"] matches central London. [\"M\"] matches all Manchester postcodes. [\"E1\"] matches East London.", "default": [], "items": { "type": "string" } }, "postTowns": { "title": "Post towns", "type": "array", "description": "Exact match on the post town (case-insensitive). E.g. [\"LONDON\", \"MANCHESTER\"].", "default": [], "items": { "type": "string" } }, "counties": { "title": "Counties", "type": "array", "description": "Substring match on county. E.g. [\"GREATER LONDON\", \"WEST MIDLANDS\"].", "default": [], "items": { "type": "string" } }, "countries": { "title": "Countries", "type": "array", "description": "Substring match on registered country. E.g. [\"ENGLAND\", \"SCOTLAND\", \"WALES\", \"NORTHERN IRELAND\"].", "default": [], "items": { "type": "string" } }, "incorporatedSince": { "title": "Incorporated on or after (YYYY-MM-DD)", "type": "string", "description": "Only include companies incorporated on or after this date. Useful for finding fresh/new companies. E.g. \"2024-01-01\" for companies less than ~16 months old.", "default": "" }, "incorporatedBefore": { "title": "Incorporated on or before (YYYY-MM-DD)", "type": "string", "description": "Only include companies incorporated on or before this date. Useful for finding established companies.", "default": "" }, "maxResults": { "title": "Maximum results to save", "minimum": 0, "maximum": 5000000, "type": "integer", "description": "Hard cap on saved rows. The scraper will still scan the full snapshot but stop pushing to the dataset once this number is reached. Set to a high value (e.g. 100000) if you want everything that matches your filters." }, "logEveryNRows": { "title": "Progress log frequency (rows)", "minimum": 1000, "maximum": 1000000, "type": "integer", "description": "Print a progress line every N CSV rows. Lower = more verbose. The bulk snapshot has ~5M rows.", "default": 100000 } } }, "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 } } } } } } } } } }