20 free credits on signup — no card required
Turn any document into structured data
Extract structured data from invoices, receipts, contracts, bank statements, IDs, PDFs and more with Heyyel Data Extractor Document Data Extraction.
Upload your document, choose exactly what you want to extract, and get clean, structured data without reading, searching or copying information by hand.
From PDF data extraction and invoice data extraction to fully custom document extraction, Heyyel Data Extractor helps you turn document content into data you can actually use.
Your data is already in the document.
Extracting it shouldn’t be the hard part.
Invoices, contracts, bank statements, receipts, PDFs and other documents already contain the information your team needs. But getting that information into a usable format often still means:
- ✕Opening documents one by one
- ✕Searching for the right information
- ✕Copying values manually
- ✕Checking formats
- ✕Moving data into spreadsheets or other tools
- ✕Turning unstructured document content into structured data
Heyyel Data Extractor automates this process with document data extraction. Instead of manually searching through documents, you define the information you need and Heyyel Data Extractor finds and structures it.
You choose the data you need. Heyyel Data Extractor finds it.
From document to structured data in three steps
The workflow is simple: upload a document, choose the data you need, then review and export the result. The full How It Works guide walks through the product step by step.
Upload your document
Upload a document from your device or capture it directly from your phone. Heyyel Data Extractor supports PDF data extraction as well as image-based and scanned document processing.
Scanned document? No problem. Heyyel Data Extractor combines OCR data extraction with structured extraction to process both digital and scanned files.
Choose what you need
Start with a ready-made document type or select Custom / Blank to create your own extraction structure. Define the exact fields you want and choose how each value should be structured. This makes it possible to extract specific fields from PDFs, invoices, contracts and other documents instead of returning everything on the page.
Extract, review and export
Run the extraction and get structured results in seconds. Review the extracted values, make corrections when needed, and export your data as:
Whether you need PDF to JSON, PDF to CSV or structured information for another workflow, your extracted data is ready to use.
Start with a preset. Or build your own.
Use ready-made extraction structures for common document types or create a completely custom one.
Invoice Data Extraction
Extract supplier details, invoice numbers, dates, totals, currencies, taxes and line items.
Use invoice OCR and structured invoice processing without manually entering information into your systems.
Receipt Data Extraction
Capture merchant information, purchase dates, totals and payment details from digital or scanned receipts.
Turn receipt OCR results into structured values ready for export.
ID Card / Passport
Extract names, document numbers, dates and other identity information into defined fields.
Business Card
Turn names, companies, job titles, emails and phone numbers into structured contact data.
Contract Data Extraction
Extract parties, dates, amounts, renewal information and other important clauses.
With contract data extraction, you decide which information matters instead of searching manually through entire documents.
Bank Statement Data Extraction
Structure account information, balances, transaction dates, descriptions and amounts.
Transform financial documents into organized data.
✨ Custom Document Extraction
Working with something different? Choose Custom / Blank and define exactly which information should be extracted.
Create your own structure for practically any supported document instead of adapting your workflow to a predefined template.
Your document. Your fields.
Extract what matters to you — not everything on the page.
Different teams can need completely different information from the same document. Traditional document processing often focuses on reading everything first. Heyyel Data Extractor takes a different approach.
With Custom Data Extraction, you tell the extraction system exactly what you want to receive. For example, upload a contract and define:
Heyyel Data Extractor searches the document and returns the requested information according to the structure you’ve defined. This makes unstructured data extraction easier by turning information buried inside documents into defined, structured fields.
You define the fields. Heyyel Data Extractor extracts the data.
More than OCR
OCR gives you text. Heyyel Data Extractor gives you structured data.
Traditional OCR software converts text inside scans, PDFs and images into machine-readable content. That is useful — but raw text often isn’t the final result you actually need.
If you are deciding which approach fits your use case, the guide on OCR vs data extraction explains where each one fits.
Traditional OCR
Document → Raw text
An online OCR tool can help you read a scanned document, but you may still need to search through the output and copy the information you need.
Heyyel Data Extractor
Document → Your selected fields → Structured JSON / CSV
Heyyel Data Extractor combines document understanding, AI OCR and structured extraction to identify the specific information you’re looking for — so instead of a large block of raw text, you directly extract data from documents according to your workflow.
That means going from Document → OCR → Manual search → Copy & paste
Document → Selected fields → Structured data
AI Document Extraction built around your fields
Heyyel Data Extractor uses AI document extraction to find and structure information inside documents according to the fields you define. Rather than relying only on document layout or predefined positions, the extraction process uses the meaning and context of your requested fields.
This makes it useful for automated data extraction across documents that may not always follow exactly the same format. Whether you’re working with invoices, contracts, statements, receipts or custom documents, the goal remains the same: turn document content into structured information your workflow can use.
Need more precision? Add context.
A field name isn’t always enough.
Use Extraction Hints to give Heyyel Data Extractor additional context about what should be extracted.
Example
Field
billing_address
Hint
“Extract the customer’s billing address, not the supplier’s address.”
Example
Field
renewal_date
Hint
“Extract the next automatic renewal date mentioned in the contract.”
You define what the field means. Heyyel Data Extractor uses that context during extraction — especially useful when you need to extract specific fields from PDF documents containing similar or repeated information.
Structure the data your way
Create extraction fields based on the type of information your workflow needs.
Text
Names, descriptions, addresses and references.
Numbers
Amounts, quantities, percentages and totals.
Dates
Invoice dates, expiry dates and renewal dates.
Booleans
Yes/no information and document conditions.
Enums
Values selected from a predefined set.
Arrays
Repeated information such as products, transactions or services.
Nested objects
Keep related information together in a structured format.
Use simple fields or create more complex structures for tables, line items and repeated information.
From PDF to JSON
Need to turn information inside a PDF into data your application can use? With Heyyel Data Extractor, you define the fields first.
{
"invoice_number": "INV-2026-0417",
"invoice_date": "2026-07-02",
"vendor_name": "Northwind Supplies",
"total_amount": 1284.50,
"currency": "EUR",
"line_items": [
{
"description": "Desk lamp",
"qty": 4,
"total": 159.80
},
{
"description": "Cable kit",
"qty": 10,
"total": 89.00
}
]
}Use PDF to JSON extraction when you need structured output for applications, databases, APIs or automated workflows. Prefer spreadsheets? Export the same extracted information using PDF to CSV. Ready to review, correct and export.
Extract data from scanned PDFs
Scanned documents contain information just like digital PDFs, but the text first needs to be recognized. Heyyel Data Extractor uses OCR as part of the extraction workflow to process scanned files before identifying the fields you requested.
Instead of converting a scanned PDF into raw text and manually searching through it, you can extract data from scanned PDFs directly into structured fields.
Scanned document → OCR → Selected fields → Structured data
One document or a whole batch
Same structure. Multiple documents.
Processing the same type of document repeatedly? Use Batch Extract to apply the same extraction structure across multiple files instead of setting up every document individually.
- ✓Upload your documents.
- ✓Define what you need.
- ✓Run automated document data extraction across the batch.
This can help teams reduce repetitive work when processing invoices, receipts, contracts, statements and other recurring document types. Less repetitive setup. More consistent data.
Build once. Reuse whenever you need it.
Regularly extracting the same fields? Save your setup as a reusable Template. For example, “Supplier Invoice”:
The next time a similar document arrives, your extraction structure is already there. Templates make recurring document processing and automated data extraction easier to standardize.
Document Data Extraction Software built around your workflow
Heyyel Data Extractor isn’t limited to predefined document layouts. Decide what information should be returned and how it should be structured.
Custom field builder
Define exactly which information you want to extract.
Extraction hints
Add instructions and context to individual fields.
77 supported languages
Process documents across a wide range of languages using the same extraction workflow.
Complex data structures
Extract simple values, lists, line items, arrays and nested information.
Review & correct
Check extracted values and make inline corrections before export.
JSON & CSV export
Turn documents and PDFs into structured output ready for spreadsheets, databases and other tools.
Reusable templates
Save extraction configurations for recurring document types.
Batch extraction
Apply the same extraction setup across multiple documents.
REST API
Approved accounts can integrate Heyyel Data Extractor Document Data Extraction directly into their applications and workflows.
Document Extraction API
Need document extraction inside your own application? Approved accounts can use the REST API to connect Heyyel Data Extractor to their existing workflows.
Use the document extraction API to send documents for processing and work with structured extraction results programmatically. For invoice workflows, developers can also use structured extraction as an alternative to building and maintaining their own invoice parsing API workflow.
Extract data across 77 languages
Use the same document data extraction workflow across documents in 77 supported languages. Work with documents in:
Whether you’re processing local or international documents, you can define the same extraction fields and receive structured results.
Built for document-heavy workflows
Finance & Accounting
Automate invoice data extraction, receipt processing and bank statement extraction. Turn financial documents into structured financial data without repetitive manual entry.
Legal & Contracts
Use contract data extraction to identify parties, dates, amounts, renewal information and other relevant fields.
Operations
Capture information from incoming documents and transform it into structured data for operational workflows.
Administration
Reduce the time spent opening documents, searching for information and copying values into other systems.
Developers
Turn PDF to JSON, export structured data and integrate document extraction into applications through the REST API.
Your own workflow
Have a document that doesn’t fit a standard category? Choose Custom / Blank and create the extraction structure your workflow needs.
Frequently asked questions
What is document data extraction?▾
Document data extraction identifies information inside PDFs, scans and images and converts it into structured data that can be reviewed, exported or used in another system. Instead of simply reading the document, structured extraction organizes the information into defined fields.
What is structured data extraction?▾
Structured data extraction turns information found inside documents into predefined values such as names, dates, amounts, categories, line items and other fields. With Heyyel Data Extractor, you define the structure you want and the system extracts the matching information.
What’s the difference between OCR and structured data extraction?▾
OCR converts document content into machine-readable text. Structured data extraction goes further by identifying specific information and organizing it into defined fields. An OCR tool might give you all the text from an invoice — Heyyel Data Extractor can instead return invoice_number, supplier, invoice_date, total, currency and line_items.
Is Heyyel Data Extractor an OCR tool?▾
Heyyel Data Extractor includes OCR capabilities for processing scanned documents and images, but it goes beyond traditional OCR software. The goal isn’t only to retrieve text — it is to transform document information into structured fields you can use.
Can Heyyel Data Extractor extract data from PDF files?▾
Yes. You can use Heyyel Data Extractor to extract data from PDF documents, including specific fields such as names, dates, totals, identifiers, transactions and line items.
How can I extract specific fields from a PDF?▾
Upload the PDF, select Custom / Blank, create the fields you want and run the extraction. For example, you can ask Heyyel Data Extractor to extract only customer_name, invoice_number, invoice_date and total_amount — rather than returning all the document text.
Can I extract data from scanned PDFs?▾
Yes. OCR is used to recognize the document content before Heyyel Data Extractor identifies and structures the requested fields. This means you can turn scanned documents into structured data without manually converting and searching the OCR output first.
Can I convert PDF to JSON?▾
Yes. Define the information you want to extract and export the structured result as JSON. This PDF to JSON workflow is useful for applications, databases and automated processes.
Can I convert PDF to CSV?▾
Yes. Extract the fields you need and export the results as CSV for spreadsheets and other data workflows.
Can Heyyel Data Extractor automate invoice data entry?▾
Heyyel Data Extractor can extract invoice numbers, suppliers, dates, totals, taxes, currencies, line items and other fields from invoice documents. The structured results can then be reviewed and exported, reducing the amount of manual invoice data entry required.
Can Heyyel Data Extractor extract invoice line items?▾
Yes. Arrays and nested objects can be used to capture repeated information such as products, quantities, prices and invoice line items.
Can I choose exactly what Heyyel Data Extractor extracts?▾
Yes. Choose Custom / Blank and create the fields that match your document and workflow. This is what makes Heyyel Data Extractor suitable for custom document extraction rather than only predefined document templates.
Do I have to create the fields myself?▾
No. You can start with presets for invoices, receipts, contracts, bank statements, IDs and business cards, then modify the suggested fields as needed.
Can I give instructions for individual fields?▾
Yes. Extraction Hints let you add context and explain more precisely what information should be extracted.
What field types are supported?▾
Heyyel Data Extractor supports Text, Numbers, Dates, Booleans, Enums, Arrays and Nested objects.
What file formats are supported?▾
You can upload PDF, PNG, JPG, WebP and TIFF files. Files can be up to 20 MB.
Which languages are supported?▾
Heyyel Data Extractor supports document data extraction across 77 languages, including English, French, Arabic, Spanish, German, Chinese, Japanese and many more.
Can I process multiple documents?▾
Yes. Batch Extract lets you apply the same extraction setup across multiple documents.
Can I reuse my extraction setup?▾
Yes. Save your configuration as a Template and reuse it for recurring documents.
Which export formats are available?▾
Extracted data can be exported as JSON or CSV.
Is there a document extraction API?▾
Yes. REST API access is available for approved accounts, allowing developers to integrate document data extraction into their applications and workflows.
How are credits calculated?▾
Each processed page uses 1 credit. You can review the current plans and credit options on the pricing page.
Stop turning documents into data by hand.
Upload your document.
Choose exactly what you need.
Let Heyyel Data Extractor turn it into structured data ready for your workflow.
From OCR and PDF data extraction to invoices, contracts, bank statements and fully custom documents, you control what gets extracted.