ExtractFox
Author profile

Dawid Sibinski

Founder and engineer at ExtractFox. Writes about AI document extraction, multimodal models, OCR vs IDP, and structured-output patterns.

About

I build ExtractFox, an AI-native data extraction tool that turns PDFs, images, and scanned documents into structured data — without per-vendor templates. Most of what I write is engineering notes from doing that, plus workflow guides for the people who use it.

For background reading, the glossary covers the terms (OCR, IDP, multimodal AI, MRZ, structured output) that keep coming up in the posts below. More about ExtractFox.

Posts (36)

All posts →
Workflow6 min read
How to extract data from an annual report
Four practical methods to pull financials, tables, and metrics from annual report and 10-K PDFs — from copy-paste to Python to AI-powered extraction.
Workflow7 min read
How to extract data from a contract PDF
How to pull parties, dates, key clauses, and obligations from contract PDFs — Python, regex, CLM tools, and AI extraction for due diligence.
Workflow5 min read
How to extract data from a receipt photo or PDF (3 methods)
Compare OCR apps, Python (easyocr, pytesseract), and AI to pull merchant, line items, tax, and totals from receipt photos — including crumpled thermal receipts.
Workflow7 min read
How to extract data from a bank statement PDF (4 methods)
Compare copy-paste, Tabula, Camelot, pdfplumber, and AI to pull transactions and balances from bank statement PDFs — digital or scanned, any bank layout.
Workflow5 min read
How to extract data from a purchase order PDF (3 methods)
Compare ERP export, Camelot/pdfplumber, and AI to pull PO number, buyer, supplier, line items, and delivery terms from any ERP-generated PO layout.
Workflow5 min read
How to extract data from an ID document (3 methods)
Compare Tesseract OCR, MRZ parsing (TD1/TD2), and AI to pull identity fields from driver's licenses, national IDs, and residence permits — any country.
Workflow6 min read
How to extract data from an invoice PDF or image (4 methods)
Compare copy-paste, Python (pdfplumber, invoice2data), template parsers, and AI to pull vendor, line items, tax, and totals from any invoice — digital PDF, scan, or photo.
Tutorial7 min read
How to decode a QR code from an image or PDF
Decode QR codes from photos, screenshots, and PDFs using pyzbar, OpenCV, and AI. Covers URLs, Wi-Fi configs, vCards, payment requests, and multiple QR codes per image.
Tutorial7 min read
How to extract a clean recipe from a website, video, or image
Pull ingredients and steps from recipe blogs, TikTok, YouTube, and Instagram using schema.org scraping, yt-dlp transcription, and AI extraction — without wading through life stories.
Tutorial7 min read
How to extract and digitize handwritten text
Transcribe handwritten notes, letters, clinical notes, and historical documents using HTR tools, Tesseract with preprocessing, and AI vision models. Includes accuracy expectations by script type.
Tutorial7 min read
How to extract data from a filled form (PDF, scan, or photo)
Pull field values from any filled form — AcroForm PDF fields, printed text, or handwriting — with pypdf, pdfminer, and AI extraction for mixed or handwritten forms.
Workflow7 min read
How to extract data from an insurance policy PDF
Pull coverage limits, premiums, exclusions, and policy dates from any insurance policy PDF — declarations pages, endorsements, and full policies from any carrier.
Tutorial6 min read
How to extract data from a chart or graph (image or PDF)
Reverse-engineer bar, line, pie, and scatter charts back into numbers using WebPlotDigitizer, Python, and AI extraction. Works on screenshots, report PDFs, and dashboard photos.
Tutorial7 min read
How to convert a PDF to Excel
Turn PDF tables and structured data into clean Excel files. Covers Tabula, pdfplumber, pandas, and AI extraction for invoices, statements, and scanned PDFs — with real column headers and numeric values.
Tutorial7 min read
How to convert a PDF to JSON
Turn PDFs into structured JSON for APIs, databases, and AI pipelines. Covers PyMuPDF for raw text, pdfplumber for tables, and AI extraction for any document type with schema output.
Tutorial8 min read
How to extract data from Zillow listings
Three ways to get structured data from Zillow — the Zillow API (Bridge Interactive), Zillow's bulk listing exports, and AI extraction from listing PDFs and screenshots.
Tutorial10 min read
How to extract a table from a PDF with Python
Three Python libraries for PDF table extraction — pdfplumber, Tabula-py, and Camelot — with code, when to use each, and how to handle scanned PDFs where text-based extraction fails.
Engineering8 min read
Passport MRZ format explained: fields, check digits, and parser code
How to parse passport MRZ data under ICAO 9303: TD3 field positions, check digits, example MRZ lines, Python parser code, and when to extract the full passport instead.
Workflow5 min read
How to bulk-clean LinkedIn 'Location' fields into city/country pairs
Recruiters and sales ops teams inherit LinkedIn exports full of "Greater London," "Bay Area," and "remote." A practical workflow to turn those into a clean city/country/region columns — at any scale.
Engineering6 min read
How to remove metadata from a PDF (for privacy)
Author, software, GPS, edit history — every PDF leaks more than you think. The reliable ways to strip metadata before sharing, in any tool you already have.
Tutorial7 min read
Extract every image from a PDF at full quality (pdfimages, pypdf, PDFBox)
Pull embedded images out of a PDF at original resolution — pdfimages for batch, pypdf in Python, PdfPig and PDFBox on .NET and Java — plus scanned pages, masks, and when to render instead.
Tutorial8 min read
Extract data from a pivot table in Excel
Extract data from an Excel PivotTable with Paste Values, GETPIVOTDATA, Show Details, Power Query, or screenshot-to-Excel extraction.
Tutorial7 min read
How to extract photos and frames from a video
Pull a still from a video — on iPhone, Android, in DaVinci Resolve, with FFmpeg, or from a YouTube URL. The right tool depends on whether you want one frame or every frame.
Tutorial9 min read
Extract text from PowerPoint (.pptx): Outline View, python-pptx, speaker notes
Extract all text from a .pptx with Outline View, python-pptx (tables, groups, speaker notes), or OCR for image slides — copy-paste code for automation pipelines.
Tutorial7 min read
Extract EXIF and GPS metadata from a photo with ExifTool or Python
Read GPS coordinates, camera, and capture time out of a photo — one file in Preview, a whole folder to CSV with ExifTool, or in Python. Includes HEIC, RAW, and the timestamp tags that disagree.
Tutorial9 min read
Extract video metadata as JSON with FFprobe, MediaInfo, or yt-dlp
Copy-paste ffprobe, MediaInfo, and yt-dlp commands to extract duration, codecs, resolution, bitrate, chapters, and YouTube metadata as JSON — plus batch scripts for whole folders.
Tutorial8 min read
Extract hyperlinks from Excel and Google Sheets (VBA, Apps Script, Python)
Copy-paste VBA, Office Scripts, Google Apps Script, and Python openpyxl to extract the real URL behind Excel and Sheets hyperlinks — including bulk export from .xlsx XML.
Tutorial6 min read
Extract embedded files and attachments from a PDF
How to extract embedded files and attachments from a PDF with Acrobat, pdfdetach, qpdf, and Python. Works for Excel sheets, source data, and supporting documents.
Engineering8 min read
How to extract city and country from a location string
Parse city, region, and country out of messy location strings — "NYC", "Greater London", "Bay Area", "remote, mostly Lisbon-based" — with copy-paste Python: libpostal first, geocoding second, schema-based AI last.
Tutorial8 min read
How to extract code from a video tutorial
Extract source code from a programming tutorial video with clean screenshots, a code-aware extractor, or an FFmpeg frame pipeline for longer recordings.
Workflow8 min read
How to extract an organization chart from Microsoft Teams
Export a Microsoft Teams organization chart to Excel or CSV with Microsoft Graph, Entra PowerShell, or screenshots when you do not have admin access.
Workflow6 min read
How to extract a chart of accounts from SAP
SAP exposes the chart of accounts through a few transactions and a few APIs — here's the practical map for finance teams who need a clean export, not a consultant's project.
Engineering8 min read
How to extract text from an image using Python
Tesseract via pytesseract, EasyOCR, PaddleOCR, and the API-based path — what each one is best at, what they break on, and the few lines of code to get started.
Workflow9 min read
Extract questions and responses from Google Forms (API, Sheets, Apps Script)
Export Google Forms responses to Excel/CSV, dump the full question schema as JSON via the Forms API, and automate with Apps Script or Python — including forms you don't own.
Engineering8 min read
How to extract data from a PDF in C#
A working engineer's tour of the PDF extraction libraries in the .NET ecosystem — iText, PdfPig, Azure Document Intelligence, and the API-first alternative when you don't want to ship a parser at all.
Workflow6 min read
How to extract data and metadata from PDFs with Power Automate
The built-in actions for PDF text extraction, the AI Builder model for invoices and receipts, and how to wire either one into a flow that drops structured data into Excel or Dataverse.