A powerful tool to extract Multiple Choice Questions (MCQs) from text, DOCX, and PDF files, converting them into organized Excel format.

1. Install dependencies:

   pip install -r requirements_etl.txt

2. Run the web app:

   streamlit run app.py

3. Use the tool:

   • Paste MCQ text directly
   • Upload DOCX or PDF files
   • Edit extracted data
   • Download as Excel file

• Multi-format Support: Text, DOCX, PDF files
• Smart Parsing: Extracts questions, options, and solutions
• Interactive Editing: Edit data before export
• Excel Export: Download organized data
• Page/Paragraph Selection: Process specific sections of large documents

• app.py - Main web application
• extract_mcqs.py - Core extraction logic
• test_extraction.py - Testing script
• PROJECT_DOCUMENTATION.md - Detailed documentation

The tool generates Excel files with:

• Question text
• 4 multiple choice options
• Solution/answer
• Serial numbers

• Numbered options: (1), 1), ( 1 )
• Lettered options: (a), A), (A)
• Various solution formats: Sol., Solution, Answer, Ans.

For detailed information, see PROJECT_DOCUMENTATION.md