{ "openapi": "3.0.1", "info": { "title": "PII Redactor - Detect & Mask Emails, Phones, SSNs, Cards", "description": "Redact or pseudonymously mask PII (emails, phones, SSNs, credit cards, IPs, names, addresses) in user-supplied text, CSV, or JSON. Outputs cleaned data plus a redaction log.", "version": "0.1", "x-build-id": "W5T3i1xMjnxswJdEN" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nibble~pii-redactor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nibble-pii-redactor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nibble~pii-redactor/runs": { "post": { "operationId": "runs-sync-nibble-pii-redactor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nibble~pii-redactor/run-sync": { "post": { "operationId": "run-sync-nibble-pii-redactor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "redact", "mask" ], "type": "string", "description": "How to handle detected PII. 'redact' replaces each match with a type tag like [EMAIL_REDACTED]. 'mask' replaces it with a STABLE pseudonymous token like [EMAIL_3f9a2b1c] — the same value always maps to the same token, so you keep referential integrity without exposing the raw data.", "default": "redact" }, "redactionTypes": { "title": "PII types to detect", "type": "array", "description": "Which categories of PII to detect. Structured types (email, phone, SSN, credit card, IP, IBAN) are high-precision. Names, organizations, and locations are detected with a Microsoft Presidio + spaCy NER model, so real names/places are caught (not just a wordlist). Leave empty to detect the default set. NOTE: 'org' is OPT-IN — the small NER model over-tags label words and brand names as organizations, so it is excluded from the default set; add it explicitly if you need it.", "items": { "type": "string", "enum": [ "email", "phone", "ssn", "credit_card", "ip", "iban", "name", "location", "address", "org" ], "enumTitles": [ "Email addresses", "Phone numbers", "US SSN", "Credit cards", "IP addresses (v4/v6)", "IBAN bank codes", "Names / people (NER)", "Locations / places (NER)", "US postal addresses", "Organizations (NER, opt-in)" ] }, "default": [ "email", "phone", "ssn", "credit_card", "ip", "iban", "name", "location", "address" ] }, "inputFormat": { "title": "Input format", "enum": [ "text", "csv", "json" ], "type": "string", "description": "How to interpret 'Input text' or a fetched 'Input URL' file. 'text' treats the whole blob as one document. 'csv' parses rows (header required) and scans string cells. 'json' parses a JSON array (each item = one record) or object.", "default": "text" }, "inputText": { "title": "Input text", "type": "string", "description": "The content to clean, pasted inline. Interpreted according to 'Input format'. Use this OR 'Input URL' OR 'Records'." }, "inputUrl": { "title": "Input URL (your own file)", "type": "string", "description": "A URL to YOUR OWN text/CSV/JSON file to clean. Fetched only when no inline content is given. This Actor never scrapes third-party sites — supply only data you are authorized to process." }, "records": { "title": "Records (inline array)", "type": "array", "description": "An inline JSON array to clean directly. Each item may be a string or an object; for objects, every string field is scanned (or only those listed in 'Fields to scan'). Takes precedence over 'Input text' / 'Input URL'." }, "fields": { "title": "Fields to scan (objects only)", "type": "array", "description": "For CSV/JSON object records, restrict scanning to these field names. Leave empty to scan every string field.", "items": { "type": "string" } }, "maskSalt": { "title": "Mask salt (optional)", "type": "string", "description": "Optional secret string used when 'mask' mode derives pseudonymous tokens. Use a per-customer salt to make tokens non-correlatable across tenants. Same salt + same value = same token." } } }, "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 } } } } } } } } } }