{ "openapi": "3.0.1", "info": { "title": "Ofsted Reports Data Scraper", "description": "Scrapes Ofsted full inspection reports for children's homes from reports.ofsted.gov.uk. Extracts 18 structured fields from PDFs — judgement ratings, provider details, inspectors, home capacity and type — filtered by date range. Exports to Apify dataset and optionally MySQL database.", "version": "0.0", "x-build-id": "eG2Ur0dBYK9WNKuQJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/alkausari_mujahid~ofsted-reports-data-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-alkausari_mujahid-ofsted-reports-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/alkausari_mujahid~ofsted-reports-data-scraper/runs": { "post": { "operationId": "runs-sync-alkausari_mujahid-ofsted-reports-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/alkausari_mujahid~ofsted-reports-data-scraper/run-sync": { "post": { "operationId": "run-sync-alkausari_mujahid-ofsted-reports-data-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "start_urls" ], "properties": { "start_urls": { "title": "Start URLs", "type": "array", "description": "A Search URL or Direct PDFs URLs (Set Max Depth parameter to 1 for direct PDfs scraping)", "default": [ { "url": "https://reports.ofsted.gov.uk/search?q=&location=&radius=&level_1_types=3&level_2_types%5B0%5D=11&latest_report_date_start=11-10-2025&latest_report_date_end=13-10-2025&status%5B0%5D=1&start=0&rows=10" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "latest_report_date_start": { "title": "Report Date From", "type": "string", "description": "Filter inspections from this date (DD-MM-YYYY)" }, "latest_report_date_end": { "title": "Report Date To", "type": "string", "description": "Filter inspections up to this date (DD-MM-YYYY)" }, "only_latest_inspection": { "title": "Only Latest Inspections per URN", "type": "boolean", "description": "Returns only the latest inspection per URN", "default": true }, "include_unsupported": { "title": "Include Unsupported PDFs data", "type": "boolean", "description": "Include unsupported inspection types in results for later processing.", "default": false }, "max_depth": { "title": "Max Depth", "minimum": 1, "type": "integer", "description": "Keep it always 3 otherwise if you want to process PDFs URLs directly then set it to 1. Maximum crawl depth for the Ofsted actor", "default": 3 }, "enable_db_export": { "title": "Enable MySQL Export", "type": "boolean", "description": "When enabled, extracted data is inserted into your MySQL database in addition to the Apify dataset. Two tables are created automatically on first run: 'ofsted_reports' (main output) and 'ofsted_unsupported_reports' (PDFs that could not be fully parsed).", "default": false }, "rescrape": { "title": "Re-process already-scraped PDFs", "type": "boolean", "description": "Normally, PDFs already in the database are skipped. Enable this to re-process them — useful when new data fields have been added and you want to fill them in for existing records. Existing rows are updated, not duplicated.", "default": false }, "db_host": { "title": "Host", "type": "string", "description": "MySQL server hostname or IP address." }, "db_database": { "title": "Database Name", "type": "string", "description": "Name of the MySQL database to connect to." }, "db_user": { "title": "Username", "type": "string", "description": "MySQL username." }, "db_password": { "title": "Password", "type": "string", "description": "MySQL password." } } }, "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 } } } } } } } } } }