scripts/read_presentation.py

"""
Read and analyze SPARKNET presentation
"""
import sys
from pptx import Presentation

def read_presentation(pptx_path):
    """Read PowerPoint presentation and extract content"""
    try:
        prs = Presentation(pptx_path)

        print(f"Total Slides: {len(prs.slides)}\n")
        print("=" * 80)

        for idx, slide in enumerate(prs.slides, 1):
            print(f"\n{'='*80}")
            print(f"SLIDE {idx}")
            print('='*80)

            # Get slide title
            title = ""
            for shape in slide.shapes:
                if shape.has_text_frame:
                    if shape.is_placeholder:
                        phf = shape.placeholder_format
                        if phf.type == 1:  # Title placeholder
                            title = shape.text
                            break

            print(f"Title: {title if title else '(No title)'}")
            print("-" * 80)

            # Get all text content
            print("Content:")
            for shape in slide.shapes:
                if shape.has_text_frame:
                    for paragraph in shape.text_frame.paragraphs:
                        text = paragraph.text.strip()
                        if text:
                            level = paragraph.level
                            indent = "  " * level
                            print(f"{indent}- {text}")

            # Check for speaker notes
            if slide.has_notes_slide:
                notes_slide = slide.notes_slide
                if notes_slide.notes_text_frame:
                    notes = notes_slide.notes_text_frame.text.strip()
                    if notes:
                        print("\nSpeaker Notes:")
                        print(notes)

        print("\n" + "="*80)

    except Exception as e:
        print(f"Error reading presentation: {e}", file=sys.stderr)
        import traceback
        traceback.print_exc()
        return False

    return True

if __name__ == "__main__":
    pptx_path = "/home/mhamdan/SPARKNET/presentation/SPARKNET_Academic_Presentation.pptx"
    read_presentation(pptx_path)