Document Extractor
Extract text and tables from native PDF and Word without AI. The direct way to extract text from pdf in bulk. 1 credit/page.
EU processing · PDF, Word & images · Up to 500 files
Extract and structure data from PDF & Word.
Zero templates.
Upload hundreds of documents in any format. Get clean data in Excel without manual data entry.
PDF DOCX DOC ✕ Excel JSON CSV
Uploading 16 files...
invoice_001.pdf — 3 pages ✓
contract_2024.pdf — 12 pages ✓
payroll_march.docx — 1 page ✓
... 13 more files ✓
Exporting → extraction_2026.xlsx ✓
16 files · 47 pages · 47 credits
Your team wastes hours extracting data manually
Copy-pasting fields from PDF to Excel, one by one. The manual way to extract data from pdf wastes hours and creates errors on every row.
Before
- Copy-pasting from PDFs
- Fragile scripts that break with every new format
- Templates that need reconfiguring for each client
With idpura
- Upload a batch of documents and download structured data in Excel, JSON or CSV
- No templates. No setup. No copy-paste.
Tools
Each tool solves a specific pdf data extraction problem, from native documents to scanned images.
Data Sectioner
Compare similar documents and detect what varies between them. 1 credit/page.
OCR & AI
Process scanned documents and extract specific fields with artificial intelligence. 3 credits/page.
AI Extractor
Extract structured fields from invoices, payslips and contracts with AI. 3 credits/page.
From document to data in 3 steps
Upload your files
Drag & drop or full folder selection. PDF, DOCX, in batch. Up to 500 files at once.
Choose the tool
Text and table extraction, data sectioning between documents, or AI extraction. The system calculates the cost before processing.
Download the result
Excel, JSON or CSV ready to use. With source column per row so you know which document each data point came from.
The system calculates the exact cost before processing. You only pay for what you use: extract data from pdf to Excel at a fixed per-page rate. Credits renew monthly.
See it in action
Simulated extraction flow with sample documents.
facturas_q1_2024/ 47 archivos
Uploading files...
Result ready resultado.xlsx · 4 filas
| File | Pages | Text extracted | Tables |
|---|---|---|---|
| invoice_001.pdf | 3 | 1,247 characters | 2 |
| contract_2024.pdf | 12 | 8,430 characters | 0 |
| payroll_march.docx | 1 | 892 characters | 1 |
| delivery_q1.pdf | 2 | 1,580 characters | 3 |
No AI — direct processing of the document text.
Try it now — no signup
10 free pages to see how it works. No card, no email.
Fair pricing: credits per page, not per document
A 200-page contract shouldn't cost the same as a single invoice. Pay only for what you process.
MonthlyYearly-20%
Free
€0
100 credits/month
Starter
€39/mo
1,200 credits/month
€0.0325 / credit
Most popular
Pro
€79/mo
3,000 credits/month
€0.0263 / credit
Business
€199/mo
10,000 credits/month
€0.0199 / credit
Need more than 10,000 credits or custom functionality? Contact us
Credits renew monthly based on your plan
How much does each tool cost?
| Tool | Credits per page |
|---|---|
| Document Extractor (text + tables) | 1 cr / pág |
| Data Sectioning (multi-doc variance) | 1 cr / pág |
| AI OCR (scanned docs & images) | 3 cr / pág |
| AI Extractor (structured fields) | 3 cr / pág |
Processing invoices manually? See how idpura automates data extraction →
Your documents are processed with guaranteed privacy
Processing on European servers. Your documents are automatically deleted.
Own server in Germany
Non-AI tools process your files entirely on our dedicated server in Germany. AI-powered tools send data through a private API: it is not stored or used to train models, as stated in the providers' public privacy policies.
Your documents are yours
Your files are deleted from the server as soon as processing completes. Export results are available for **24 hours** to download, then automatically removed. We only store your usage history: credits consumed and dates, never document content.
GDPR compliant · Enterprise teams
Architecture designed to comply with GDPR. Coming soon: team management with organization-level access control.
Frequently asked questions
What document types does idpura support?
PDF (native and digital), DOCX (Word 2007 onwards) and images (PNG, JPG, WEBP, TIFF). The .doc format (Word 97-2003) is not supported. The AI Extractor also processes scanned documents by converting pages to images for AI analysis.
What is a credit and how is it calculated?
A credit equals one unit of processing. Basic tools (Document Extractor, Data Sectioning) consume 1 credit per page. AI tools (OCR, AI Extractor) consume 3 credits per page. The system shows you the exact cost before confirming processing.
Are my documents secure?
Yes. The server is in Germany (EU) and files are automatically deleted 24 hours after processing. AI tools send data through a private API that does not store it or use it to train models. Communication is always via HTTPS.
Can I use idpura with my company team?
Currently it is an individual tool. Multi-user team support is on the roadmap for Q4 2026, with roles, shared credits and organization-level access control.
Does it work with scanned documents?
Yes. The AI Extractor (3 credits/page) handles scans and photos. To extract data from pdf files and Word docs natively, the Document Extractor works at 1 credit/page with no AI.
Is there an API to integrate with my system?
Yes. The public REST API is available on all plans, including Free. It includes API keys, OpenAPI documentation and per-plan rate limiting. See the docs at /developers/.
What's next
What's ready and what's coming.
Shipped In progress Up next Planned
Document Extractor
Text + tables from PDF and DOCX to Excel, JSON and CSV. Up to 500 files per job.
Data Sectioning
Automatic extraction of variable fields between identical documents.
ES + EN interface
Full navigation in Spanish and English.
Payment plans (Stripe)
Monthly and annual subscriptions with Stripe. Starter, Pro, Business plans.
Pricing page
Detailed plan comparison, tools and credit table.
Legal pages
Terms of service, privacy policy and GDPR compliance.
AI OCR
Scanned documents and images to structured data. 3 cr/page.
AI Extractor
Specific fields from invoices, payslips and contracts with AI. 3 cr/page.
Public API
REST API with API keys, OpenAPI docs and webhooks. All plans.
Multi-user and teams
Admin/member roles, shared credits, access control. Pro plan+.
Create your account and get 400 credits
Start freeNo credit card required. 100 credits/month + 300 welcome bonus.