PPT Analysis, .pptx / .ppt

Environment

from pptx import Presentation
from pptx.util import Inches
import os, subprocess, json

# python-pptx is available
# For .ppt (old binary format): convert via libreoffice
def load_pptx(path):
    if path.lower().endswith('.ppt'):
        import subprocess
        out_dir = os.path.dirname(path)
        subprocess.run(
            ['libreoffice', '--headless', '--convert-to', 'pptx', '--outdir', out_dir, path],
            check=True, capture_output=True
        )
        path = path.rsplit('.', 1)[0] + '.pptx'
    return Presentation(path), path

---

Core Method 1: Full Text Extraction (ALL slides)

def extract_all_slides_text(pptx_path):
    """
    Extract text from every slide: text frames, tables, chart titles.
    For slides with no extractable text, flag them for image captioning.
    """
    prs, _ = load_pptx(pptx_path)
    slides_data = []

    for slide_num, slide in enumerate(prs.slides, start=1):
        slide_texts = []
        has_text = False

        for shape in slide.shapes:
            # Text frame (most common)
            if shape.has_text_frame:
                for para in shape.text_frame.paragraphs:
                    text = para.text.strip()
                    if text:
                        slide_texts.append(text)
                        has_text = True

            # Table
            if shape.has_table:
                tbl = shape.table
                for row in tbl.rows:
                    row_text = '\t'.join(cell.text.strip() for cell in row.cells)
                    if row_text.strip():
                        slide_texts.append(row_text)
                        has_text = True