{ "openapi": "3.0.1", "info": { "title": "PCAOB Audit Firm Inspections & Enforcement Actions Scraper", "description": "Scrape PCAOB audit-firm inspection reports (firm ID, inspection year, jurisdiction, network, Part I.A deficiency rate, audits reviewed) and enforcement orders (respondent, order date, sanction type, release number, PDF). Optional PDF detail extraction. JSON, CSV or Excel.", "version": "0.1", "x-build-id": "ebq8bo2xXNdlRspeH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapers_lat~pcaob-inspections-enforcement-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapers_lat-pcaob-inspections-enforcement-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapers_lat~pcaob-inspections-enforcement-scraper/runs": { "post": { "operationId": "runs-sync-scrapers_lat-pcaob-inspections-enforcement-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapers_lat~pcaob-inspections-enforcement-scraper/run-sync": { "post": { "operationId": "run-sync-scrapers_lat-pcaob-inspections-enforcement-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchType": { "title": "What To Scrape", "enum": [ "inspections", "enforcement" ], "type": "string", "description": "Inspections = PCAOB firm inspection reports (deficiency findings on registered audit firms). Enforcement = PCAOB disciplinary orders against firms and individual auditors (fines, bars, censures).", "default": "inspections" }, "firmName": { "title": "Firm / Respondent Name", "type": "string", "description": "Optional keyword. Filters to records matching this audit firm or respondent name (for example 'KPMG', 'BDO', 'Deloitte', or an individual auditor's name). Leave empty to return every record in the selected category." }, "years": { "title": "Years", "type": "array", "description": "Filter by year. For inspections this is the inspection year; for enforcement it is the order year. Four-digit years, for example '2025', '2024'. Leave empty for all years.", "items": { "type": "string" } }, "jurisdictions": { "title": "Firm Jurisdictions / Countries", "type": "array", "description": "Filter by the firm's country, exactly as PCAOB records it (for example 'United States', 'China', 'India', 'United Kingdom'). Leave empty for all jurisdictions.", "items": { "type": "string" } }, "globalNetworks": { "title": "Global Network (inspections only)", "type": "array", "description": "Inspections only. Filter to member firms of a global network, exactly as named by PCAOB (for example 'KPMG International Cooperative', 'Deloitte Touche Tohmatsu Limited', 'BDO International Limited').", "items": { "type": "string" } }, "inspectionTypes": { "title": "Inspection Cadence (inspections only)", "type": "array", "description": "Inspections only. Keep only firms on this inspection cadence.", "items": { "type": "string", "enum": [ "Annually Inspected", "Triennially Inspected" ] } }, "sanctionTypes": { "title": "Sanction / Order Type (enforcement only)", "type": "array", "description": "Enforcement only. Keep only orders of these types.", "items": { "type": "string", "enum": [ "Settled Disciplinary Order", "Adjudicated Disciplinary Order", "Termination of Bars" ] } }, "minDeficiencyRate": { "title": "Minimum Part I.A Deficiency Rate (inspections only)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Inspections only. Keep only inspection reports whose Part I.A deficiency rate is at least this percentage (0-100). Use it to isolate the worst-quality audit engagements." }, "includeDetails": { "title": "Fetch Report / Order PDF Details", "type": "boolean", "description": "Add-on. For every record, fetch the actual PDF (inspection report or disciplinary order) and extract its text: the order summary, any monetary penalty and bar/suspension language for enforcement, and the full report text for inspections. Turn off for a faster, cheaper, metadata-only run.", "default": false }, "maxRecords": { "title": "Max Records To Scrape", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of records to return." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. PCAOB is reachable without a proxy; enable one only if your network needs it." } } }, "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 } } } } } } } } } }