Extract PDF data.
Automatically and structured.
DokuScan reads precisely the data from PDFs that you actually need — no wall of text, no manual preparation. You define the fields, the AI finds them. Export as Excel, CSV or JSON.
Try for free10 free scans · No credit card · GDPR compliant
The problem with standard PDF converters.
Standard PDF-to-Excel tools copy the structure of the PDF into Excel. The result is often unstructured: wrong columns, merged cells, text in the wrong place. Then manual preparation begins.
DokuScan does it differently. Instead of converting the PDF, the AI specifically extracts the fields you have defined — regardless of the PDF layout. The result is a clean, immediately usable table.
From which PDFs can DokuScan extract data?
Digital PDFs
PDFs where the text is directly contained in the document — for example invoices generated from accounting software or ERP systems.
Scanned PDFs
Scanned paper documents in PDF format. DokuScan applies OCR and then extracts the desired fields.
Form PDFs
Completed PDF forms — even if the form fields are not machine-readable, they are recognised by AI.
Multi-page PDFs
PDFs with multiple pages are automatically split and fully processed. Each page counts as one credit.
PDFs with tables
Item lists, hour tables, position lists — each row of the table is exported as its own row in Excel.
Handwritten PDFs
Hand-filled forms that have been scanned. OCR + AI recognises handwritten entries as well.
DokuScan vs. PDF-to-Excel converter
| Feature | PDF-to-Excel converter | DokuScan |
|---|---|---|
| Converts PDF to Excel | Yes | Yes |
| Immediately usable table | Rarely | Yes |
| Extract only desired fields | No | Yes |
| Table positions as separate rows | No | Yes |
| Process scanned PDFs | Rarely | Yes |
| No subscription | Usually subscription | Buy once |
| GDPR / German servers | Usually not | Yes |
How it works.
Create a template: define the fields you need from your PDFs — name, type, required field.
Upload PDF — digital or scanned, one or more pages, up to 25 files at once.
AI automatically extracts the defined fields — in 5 to 20 seconds per document.
Download Excel, CSV or JSON — ready to use without further preparation.
Digital and scanned PDFs
Both PDF types are fully supported. OCR for scanned documents is automatically included.
Define custom fields
No predefined fields. You decide what is extracted — separately for each PDF type.
Read tables completely
Item lists and position tables are exported as separate rows — not as totals.
Confidence display
Uncertain fields are highlighted. Only these need to be checked manually.
API for developers
Included in the Business package. Submit PDFs automatically and receive structured data back.
GDPR / German servers
All PDFs and extracted data stay in Germany. No sharing, no training.
Frequently asked questions
What is the difference from a PDF-to-Excel converter?
PDF converters copy the structure of the PDF into Excel — the result is often unstructured and needs manual preparation. DokuScan specifically extracts only the fields you have defined and returns a clean, immediately usable table. Table positions are mapped as separate rows.
Does DokuScan also work with scanned PDFs?
Yes. Scanned PDFs are converted to text via OCR, then the AI extracts the desired fields. Even poor scan quality is processed — a confidence value is shown for uncertain fields.
Can I extract tables from PDFs?
Yes. Tables in PDFs — item lists, hour tables, position lists — are fully mapped as separate rows in the export. Each table row of the PDF becomes its own Excel row with all defined fields.
How are multi-page PDFs billed?
Each page of a PDF uses one credit. A 3-page PDF costs 3 credits. The Starter package (EUR 9 / 100 credits) is sufficient for 100 single-page or 33 three-page PDFs.
Do I need programming skills?
No. DokuScan works entirely without programming. Create a template, upload a PDF, download Excel. The optional API in the Business package is for developers who want to integrate DokuScan into their own systems.
Is there a file size limit?
Individual PDFs can have multiple pages — each page is billed as one credit. Up to 25 files can be uploaded simultaneously.
Use cases for PDF extraction
Extract PDF data automatically now.
10 free scans · GDPR compliant · German servers · No subscription
Start for free