{ "openapi": "3.0.1", "info": { "title": "Companies House New Companies Scraper: Daily Feed", "description": "Get newly incorporated UK companies from Companies House over a rolling window of recent days, incorporation date on every row. Schedule daily with only new companies on for a feed. One flag drops dormant shells, never charged. Filter by SIC codes, place, name or type, or read numbers from a file.", "version": "0.2", "x-build-id": "RJibjSOkwOx3nYJAT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pradio~new-company-filings/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pradio-new-company-filings", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pradio~new-company-filings/runs": { "post": { "operationId": "runs-sync-pradio-new-company-filings", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pradio~new-company-filings/run-sync": { "post": { "operationId": "run-sync-pradio-new-company-filings", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional. Paste results URLs from the Companies House advanced search to read those filtered lists instead of the default incorporation and dissolution windows. Only that results page is read: any other URL, such as an officer search or appointments page or another site, is not fetched and comes back as an uncharged bad_url row naming it.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "companyNumbers": { "title": "Company Numbers", "type": "array", "description": "Optional. Companies House company numbers or company page URLs (for example 00000006, or a register page URL ending in /company/00000006). Each produces one detailed row, charged per row: a number the register does not know comes back as an uncharged not_found row. When given alone, no window or search is read.", "items": { "type": "string" } }, "companyNumbersFromFile": { "title": "Company Numbers from a File or Sheet", "type": "string", "description": "Optional. Paste company numbers one per line, or one link to a .txt or .csv file, a Google Sheet or a Google Drive file shared so anyone with the link can view it. A column headed like a company-number column (Company number, Company No, CRN, Registration no. and the like) is read; without one, the column holding the most company numbers. Numbers a spreadsheet stripped of leading zeros are padded back. Each number becomes one detailed row like Company Numbers; an entry that is not a company number comes back as an uncharged not_found row naming it." }, "searchQueries": { "title": "SIC Filter (code prefix or description text)", "type": "array", "description": "Optional SIC filter. Each entry matches a SIC code prefix (like 43) or text in the SIC description (like restaurant); companies without a match are dropped. It takes SIC codes or activity words, never company names (use Company Name Includes for a name). Unlike SIC Codes, it filters the companies after they are read and never narrows the register search.", "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify proxy settings. When set, every request to the Companies House register goes through the configured proxy." }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "The most company rows one run returns (default 100, at most 10,000).", "default": 100 }, "maxItemsPerStartUrl": { "title": "Max Items per Start URL", "type": "integer", "description": "Optional. Caps how many companies each pasted startUrls entry may contribute to a run, so one long list cannot spend the whole maxItems budget. Leave unset for one shared cap." }, "daysBack": { "title": "Days Back", "type": "integer", "description": "How many days back the incorporation window (and the dissolution window, when on) reaches (default 7).", "default": 7 }, "onlyNew": { "title": "Only New or Changed Companies", "type": "boolean", "description": "Off by default: every run returns the companies in its window. Turn it on for a daily or weekly schedule: each run then returns only companies that no earlier run of yours returned in the last 31 days, plus any whose status has changed since. Companies you name under Company Numbers are always returned.", "default": false }, "onlyChanged": { "title": "Only Changed Named Companies", "type": "boolean", "description": "The watchlist diff for Company Numbers: with it on, a company you named by number is emitted only when its row content changed since your last run that emitted it (status, address, officers, accounts, charges, SIC, filings and names are diffed). An unchanged watched company is not pushed; the run summary counts it.", "default": false }, "suppress": { "title": "Suppress Companies or Agent Addresses", "type": "array", "description": "Entries to keep out of every run: yours and the stored list's. An entry that reads as a company number (00000006) suppresses that company; any other entry is matched against the registered-office address, so a formation agent's address suppresses every company registered to it. A suppressed company is never read for detail and comes back as one free removed row naming it. The list persists between runs until cleared below.", "items": { "type": "string" } }, "clearSuppressions": { "title": "Clear the Suppression List", "type": "boolean", "description": "Empties the stored suppression list before this run's Suppress entries merge in; that is the way to stop suppressing entries sent on earlier runs.", "default": false }, "companyStatus": { "title": "Company Status", "type": "array", "description": "Keep companies with any of these register statuses in the incorporation window (default Active). Clear it to take every status. The dissolution window always holds dissolved companies.", "items": { "type": "string", "enum": [ "active", "dissolved", "open", "closed", "converted-closed", "removed", "receivership", "liquidation", "administration", "insolvency-proceedings", "voluntary-arrangement" ], "enumTitles": [ "Active", "Dissolved", "Open", "Closed", "Converted / Closed", "Removed", "Receiver action", "Liquidation", "In administration", "Insolvency proceedings", "Voluntary arrangement" ] }, "default": [ "active" ] }, "companyTypes": { "title": "Company Types", "type": "array", "description": "Optional. Keep only these company types, for example Private limited company or Limited liability partnership. Leave empty for every UK type.", "items": { "type": "string", "enum": [ "ltd", "plc", "llp", "community-interest-company", "private-limited-guarant-nsc", "private-limited-guarant-nsc-limited-exemption", "private-limited-shares-section-30-exemption", "private-unlimited", "private-unlimited-nsc", "limited-partnership", "private-fund-limited-partnership", "scottish-partnership", "charitable-incorporated-organisation", "scottish-charitable-incorporated-organisation", "registered-society-non-jurisdictional", "industrial-and-provident-society", "assurance-company", "icvc", "protected-cell-company", "old-public-company", "royal-charter", "further-education-or-sixth-form-college-corporation", "eeig", "european-public-limited-liability-company-se", "unregistered-company", "converted-or-closed", "oversea-company", "uk-establishment", "registered-overseas-entity" ], "enumTitles": [ "Private limited company", "Public limited company", "Limited liability partnership", "Community interest company", "Private limited by guarantee without share capital", "Private limited by guarantee without share capital, use of limited exemption", "Private limited company, use of limited exemption", "Private unlimited company", "Private unlimited company without share capital", "Limited partnership", "Private fund limited partnership", "Scottish qualifying partnership", "Charitable incorporated organisation", "Scottish charitable incorporated organisation", "Registered society", "Industrial and Provident society", "Assurance company", "Investment company with variable capital", "Protected cell company", "Old public company", "Royal charter company", "Further education or sixth form college corporation", "European Economic Interest Grouping (EEIG)", "European public limited liability company (SE)", "Unregistered company", "Converted / Closed", "Overseas company", "UK establishment company", "Overseas entity" ] } }, "ukCompaniesOnly": { "title": "UK Companies Only", "type": "boolean", "description": "Leave out overseas companies, UK establishments of overseas companies and overseas entities (numbers starting FC, NF, SF, BR or OE). Ignored when Company Types is set.", "default": true }, "sicCodes": { "title": "SIC Codes", "type": "array", "description": "Optional. Five-digit SIC codes such as 56101 are searched on the register itself, one search per code, so only those companies are read. A shorter prefix such as 56 turns the whole list into a filter on the returned companies, like SIC Filter. Codes only: for description words such as restaurant, use SIC Filter.", "items": { "type": "string" } }, "location": { "title": "Location", "type": "string", "description": "Optional. Text the registered office address must contain: a town, a county or a postcode fragment such as EC2A or Manchester." }, "companyNameIncludes": { "title": "Company Name Includes", "type": "string", "description": "Optional. Words the company name must contain, such as bakery or consulting. Sent to the register's own search, so only matching names are read. Applies to the built-in windows, not to pasted Start URLs." }, "companyNameExcludes": { "title": "Company Name Excludes", "type": "string", "description": "Optional. Words the company name must not contain, such as holdings. Sent to the register's own search. Applies to the built-in windows, not to pasted Start URLs." }, "excludeDormant": { "title": "Exclude Dormant Companies", "type": "boolean", "description": "Leave out companies the register marks dormant: those that declared SIC 99999 (Dormant Company) or file dormant accounts. They are read and dropped, never charged. Companies you name under Company Numbers are always returned. Off by default.", "default": false }, "incorporatedFrom": { "title": "Incorporated From", "type": "string", "description": "Optional. Earliest incorporation date, YYYY-MM-DD. With Incorporated To it replaces the Days Back window." }, "incorporatedTo": { "title": "Incorporated To", "type": "string", "description": "Optional. Latest incorporation date, YYYY-MM-DD." }, "includeDissolved": { "title": "Include Dissolved", "type": "boolean", "description": "Also read companies dissolved in the same window, tagged dissolved. Off by default: the default run returns newly incorporated companies.", "default": false }, "dissolvedFrom": { "title": "Dissolved From", "type": "string", "description": "Optional. Earliest dissolution date, YYYY-MM-DD. Setting a dissolution date reads the dissolution window; given alone, the run returns dissolutions only." }, "dissolvedTo": { "title": "Dissolved To", "type": "string", "description": "Optional. Latest dissolution date, YYYY-MM-DD." }, "includeOfficers": { "title": "Include Officers", "type": "boolean", "description": "Also read each company's officers tab: fills officers and first_director. Ticking it adds personal data: each officer's name, role, appointment dates and status. One extra request per company. Off by default, in the Console form and over the API.", "default": false }, "includePsc": { "title": "Include PSC", "type": "boolean", "description": "Also read each company's persons-with-significant-control tab: fills persons_with_significant_control. Ticking it adds personal data: each person's name, nature of control, notification date and status. One extra request per company. Off by default.", "default": false }, "includeFilings": { "title": "Include Filings", "type": "boolean", "description": "Also read each company's filing-history tab: fills latest_filing with the newest filing's date, type and description. One extra request per company.", "default": 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 }, "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 } } } } } } } } } }