Extract data from a document
Skip the copy-and-paste. Common fields are recognised and collected into a structured list you can export as JSON for another system, or as plain text to read.
How to extract data from a document
Upload the PDF or image holding the data.
Run the extraction to find emails, phones, tax IDs, dates and amounts.
Export the results as JSON, a text report or a Word document.
Frequently asked questions
Does it work on scans?
Run OCR first so there is recognised text to search — then extraction will find the fields.
Which formats can I export?
JSON for feeding another system, a plain-text report, or a Word document.
Related tools
- OCR — make a scanned PDF searchableRecognise text in scanned PDFs and images. Output a searchable PDF, PDF/A, plain text or Word, with deskew and auto-rotate. Free online.
- Convert PDF to ExcelPull tables and text out of a PDF into an Excel workbook (.xlsx) you can sort and calculate with. Free online, no account.
- Convert PDF to textExtract all the text from a PDF into a plain .txt file — fast, clean and free. Ideal for copying, searching or feeding into other tools.
- Redact a PDFPermanently delete sensitive content from a PDF — search terms, auto-detected personal data, or areas you draw. Free online.
Your files stay private
Files you upload without an account are processed and then deleted automatically — they are never added to anyone's storage and are not used to train anything. Transfers are encrypted in both directions. Create a free account if you would rather keep your documents in a private vault, or see the pricing plans for unlimited use.