{ "openapi": "3.0.1", "info": { "title": "Fillable PDF Form Data Extractor: Batch Forms to CSV & Excel", "description": "Merge hundreds of filled PDF forms (AcroForm and XFA) into one spreadsheet: one row per PDF, one column per field. Checkbox and radio values, stable column mapping, per-file status so one bad file never stops the batch, and a template-drift report that flags old form versions.", "version": "0.1", "x-build-id": "7ZFom4A1yYeiv73OC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/naricky~pdf-form-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-naricky-pdf-form-data-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/naricky~pdf-form-data-extractor/runs": { "post": { "operationId": "runs-sync-naricky-pdf-form-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/naricky~pdf-form-data-extractor/run-sync": { "post": { "operationId": "run-sync-naricky-pdf-form-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Direct HTTPS links to your filled PDF forms (e.g. signed storage links or a public folder). Use this, a ZIP URL, a key-value store, or any mix.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "zipUrl": { "title": "ZIP URL", "type": "string", "description": "Optional direct link to one ZIP file of PDFs. Every .pdf inside, including subfolders, is processed." }, "keyValueStoreId": { "title": "Key-value store ID", "type": "string", "description": "Optional ID or name of an Apify key-value store where you uploaded the PDFs." }, "keyPrefix": { "title": "Key prefix", "type": "string", "description": "Only process key-value store records whose key starts with this prefix, e.g. 'intake-2026-10-'. Empty means all records." }, "fieldMapping": { "title": "Field to column mapping", "type": "object", "description": "Optional JSON object: PDF field name -> column name, e.g. {\"topmostSubform[0].Page1[0].f1_01[0]\": \"Name\"}. Map old and new field names to the same column to merge template versions." }, "keepUnmappedFields": { "title": "Keep unmapped fields", "type": "boolean", "description": "When a mapping is given, also output fields that are not in it (under their PDF field name). Turn off to get only the mapped columns.", "default": true }, "columnOrder": { "title": "Column order", "type": "array", "description": "Optional list of column names (after mapping) to put first, in this order. Other columns follow in first-seen order.", "items": { "type": "string" } }, "checkboxMode": { "title": "Checkbox values", "enum": [ "exportValue", "boolean" ], "type": "string", "description": "How checked boxes appear. Radio buttons always output the selected option name.", "default": "exportValue" }, "includeXfa": { "title": "Read XFA form data", "type": "boolean", "description": "Also read the XFA datasets packet (Adobe LiveCycle / dynamic forms) when the AcroForm fields are empty or missing.", "default": true }, "escapeFormulasInCsv": { "title": "Escape formulas in CSV", "type": "boolean", "description": "Prefix values starting with = + - @ with an apostrophe in merged.csv so values typed by form fillers cannot run as spreadsheet formulas. The XLSX always stores them as text.", "default": true }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Optional open password for password-protected PDFs. Files without a password still open normally." } } }, "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 } } } } } } } } } }