PDF to Excel Extractor
Pricing
from $4.80 / 1,000 document extracteds
Go to Apify Store
PDF to Excel Extractor
Extract user-defined fields from repeated-layout text PDFs into XLSX with page provenance and missing-field warnings.
PDF to Excel Extractor
Pricing
from $4.80 / 1,000 document extracteds
Extract user-defined fields from repeated-layout text PDFs into XLSX with page provenance and missing-field warnings.
You can access the PDF to Excel Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "AMYvQ7aXmVeH12toh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/automation-lab~schema-guided-pdf-to-excel-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-automation-lab-schema-guided-pdf-to-excel-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/automation-lab~schema-guided-pdf-to-excel-extractor/runs": { "post": { "operationId": "runs-sync-automation-lab-schema-guided-pdf-to-excel-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/automation-lab~schema-guided-pdf-to-excel-extractor/run-sync": { "post": { "operationId": "run-sync-automation-lab-schema-guided-pdf-to-excel-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", "required": [ "documents", "fields" ], "properties": { "documents": { "title": "PDF documents", "minItems": 1, "maxItems": 50, "type": "array", "description": "One to 50 text-based PDF files. Provide exactly one public URL or base64 payload per document.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "Public PDF URL", "description": "Direct HTTP or HTTPS URL of a text-based PDF." }, "base64": { "type": "string", "title": "Base64 PDF", "description": "Base64-encoded content of a text-based PDF." }, "name": { "type": "string", "title": "Document name", "description": "Optional label used in the dataset and workbook." } } }, "default": [ { "url": "https://pdfobject.com/pdf/sample.pdf", "name": "sample.pdf" } ] }, "fields": { "title": "Field mapping", "minItems": 1, "maxItems": 100, "type": "array", "description": "Regex mappings. The first capture group becomes the value; otherwise the full match is used.", "items": { "type": "object", "required": [ "key", "pattern" ], "properties": { "key": { "type": "string", "title": "Output key", "description": "Stable field name used in dataset values." }, "label": { "type": "string", "title": "Excel header", "description": "Human-readable workbook column heading." }, "pattern": { "type": "string", "title": "Regular expression", "description": "Regex whose first capture group is the extracted value." }, "type": { "type": "string", "title": "Value type", "description": "Normalize the captured value as text, number, or date.", "enum": [ "string", "number", "date" ], "default": "string" }, "required": { "type": "boolean", "title": "Required", "description": "Add a warning when no value is found.", "default": false }, "page": { "type": "integer", "minimum": 1, "title": "Only search this page", "description": "Optional one-based page restriction." }, "column": { "type": "string", "title": "Template column (A, B, BC...)", "description": "Optional target column in a supplied workbook template." } } }, "default": [ { "key": "title", "label": "Document title", "pattern": "^(Sample PDF)", "type": "string", "required": true }, { "key": "opening", "label": "Opening sentence", "pattern": "(This is a simple PDF file\\.)", "type": "string", "required": true } ] }, "templateUrl": { "title": "XLSX template URL", "type": "string", "description": "Optional public URL of an XLSX template. Use field column mappings to place values." }, "templateBase64": { "title": "Base64 XLSX template", "type": "string", "description": "Optional base64-encoded XLSX template. Do not combine with templateUrl." }, "worksheetName": { "title": "Worksheet name", "type": "string", "description": "Worksheet to update or create.", "default": "Extracted data" }, "startRow": { "title": "First data row", "minimum": 1, "type": "integer", "description": "Optional one-based row where extracted records begin.", "default": 2 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for PDF to Excel Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: