{ "openapi": "3.0.1", "info": { "title": "GOV.UK Search & Content Scraper", "description": "Scrape GOV.UK search results and page content via the official APIs. Search by keywords or URLs, filter by organisation, and extract metadata, publication dates, links, and full page text with automatic pagination.", "version": "0.0", "x-build-id": "hYme17IphKhbS1mdE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~gov-uk-search-content-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-gov-uk-search-content-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~gov-uk-search-content-scraper/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-gov-uk-search-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~gov-uk-search-content-scraper/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-gov-uk-search-content-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "queries" ], "properties": { "queries": { "title": "Queries (keywords, URLs, or paths)", "type": "array", "description": "Auto-routed: search keywords (`insolvency rules`) hit the Search API; gov.uk URLs or `/paths` (`/government/organisations/companies-house`) fetch structured content.", "default": [ "insolvency" ], "items": { "type": "string" } }, "maxResultsPerSearch": { "title": "Max results per search", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Results to collect per keyword query (paginated automatically, up to 1000).", "default": 20 }, "order": { "title": "Search sort order", "enum": [ "relevance", "newest", "oldest" ], "type": "string", "description": "How the Search API orders results.", "default": "relevance" }, "organisation": { "title": "Filter by organisation (optional)", "type": "string", "description": "GOV.UK organisation slug, e.g. `companies-house`, `hm-revenue-customs`, `home-office`. Empty = all organisations.", "default": "" }, "fetchContentForResults": { "title": "Fetch full content for each search result", "type": "boolean", "description": "After each search, also fetch the structured Content API record (full body text, links, dates) for every hit. One extra request per result.", "default": false }, "maxBodyChars": { "title": "Max body text characters", "minimum": 0, "type": "integer", "description": "Truncate extracted body text of content pages to this many characters. 0 = no limit.", "default": 20000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "GOV.UK's APIs are open; a proxy is essentially never needed.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }