Docling PDF Extractor

A Streamlit app to extract text, tables, and images from PDFs — organized page-wise.

Features

• Extracts text (.txt), images (.jpg), and tables (.csv)
• Saves per-page output into folders under output/
• Displays extracted data in Streamlit UI
• Generates and downloads metadata.json

Setup

pip install -r requirements.txt
streamlit run app.py