cd /tmp/workspace && python3 - <<'EOF' from pptx import Presentation from pptx.util import Pt from pptx.dml.color import RGBColor import json pptx_path = "/tmp/workspace/attachments/bd6e6c97-f2a9-4618-8e55-168e26cb2814/PRINCIPLES AND OBJECTIVES OF SKIN.pptx" prs = Presentation(pptx_path) slides_data = [] for slide_num, slide in enumerate(prs.slides, 1): slide_info = {"slide_num": slide_num, "shapes": []} # Get slide background color if any bg = slide.background fill = bg.fill try: if fill.type is not None: slide_info["bg_fill_type"] = str(fill.type) if hasattr(fill, 'fore_color') and fill.fore_color is not None: try: slide_info["bg_color"] = str(fill.fore_color.rgb) except: pass except: pass for shape in slide.shapes: shape_info = { "shape_name": shape.name, "shape_type": str(shape.shape_type), "left": shape.left, "top": shape.top, "width": shape.width, "height": shape.height, } # Check for fill color on shape try: sfill = shape.fill if sfill.type is not None: shape_info["fill_type"] = str(sfill.type) try: shape_info["fill_color"] = str(sfill.fore_color.rgb) except: pass except: pass if shape.has_text_frame: paragraphs_data = [] for para in shape.text_frame.paragraphs: para_data = { "text": para.text, "alignment": str(para.alignment), "level": para.level, "runs": [] } # Paragraph-level font if para.font: para_data["para_font_size"] = str(para.font.size) para_data["para_font_bold"] = para.font.bold para_data["para_font_italic"] = para.font.italic try: para_data["para_font_color"] = str(para.font.color.rgb) if para.font.color.type else None except: para_data["para_font_color"] = None para_data["para_font_name"] = para.font.name for run in para.runs: run_data = { "text": run.text, "bold": run.font.bold, "italic": run.font.italic, "underline": run.font.underline, "size": str(run.font.size), "name": run.font.name, } try: run_data["color"] = str(run.font.color.rgb) if run.font.color.type else None except: run_data["color"] = None para_data["runs"].append(run_data) paragraphs_data.append(para_data) shape_info["paragraphs"] = paragraphs_data slide_info["shapes"].append(shape_info) slides_data.append(slide_info) # Save to JSON for inspection with open("/tmp/workspace/pptx_data.json", "w") as f: json.dump(slides_data, f, indent=2) print(f"Total slides: {len(slides_data)}") for s in slides_data: print(f"\nSlide {s['slide_num']}:") for shape in s['shapes']: if 'paragraphs' in shape: for p in shape['paragraphs']: if p['text'].strip(): print(f" [{shape['shape_name']}] L{p['level']}: {p['text'][:100]}") EOF

python3 - <<'EOF' # Deep inspection of PPTX - get all formatting details, images, colors from pptx import Presentation from pptx.util import Pt, Emu from pptx.dml.color import RGBColor from pptx.enum.shapes import MSO_SHAPE_TYPE import json pptx_path = "/tmp/workspace/attachments/bd6e6c97-f2a9-4618-8e55-168e26cb2814/PRINCIPLES AND OBJECTIVES OF SKIN.pptx" prs = Presentation(pptx_path) print(f"Slide width: {prs.slide_width}, height: {prs.slide_height}") # Check slide 1 in detail slide = prs.slides[0] print("\n=== SLIDE 1 DETAIL ===") for shape in slide.shapes: print(f"\nShape: {shape.name}, type: {shape.shape_type}") print(f" Position: left={shape.left}, top={shape.top}, w={shape.width}, h={shape.height}") # Fill try: fill = shape.fill print(f" Fill type: {fill.type}") if fill.type is not None: try: print(f" Fill color: {fill.fore_color.rgb}") except Exception as e: print(f" Fill color error: {e}") except Exception as e: print(f" Fill error: {e}") if shape.has_text_frame: for para in shape.text_frame.paragraphs: if not para.text.strip(): continue print(f" Para: '{para.text[:60]}' align={para.alignment} level={para.level}") # Para spacing pf = para._pPr if hasattr(para, '_pPr') else None print(f" Para space before: {para.space_before}, after: {para.space_after}") for run in para.runs: print(f" Run: '{run.text[:40]}' bold={run.font.bold} italic={run.font.italic} size={run.font.size} name={run.font.name}", end="") try: if run.font.color.type: print(f" color={run.font.color.rgb}", end="") except: pass print() # Check if it's an image if shape.shape_type == MSO_SHAPE_TYPE.PICTURE: print(f" IMAGE shape: {shape.name}") # Check all slides for images print("\n=== IMAGES IN PRESENTATION ===") for i, slide in enumerate(prs.slides, 1): for shape in slide.shapes: if shape.shape_type == MSO_SHAPE_TYPE.PICTURE: print(f"Slide {i}: Image '{shape.name}' at L={shape.left} T={shape.top}") # Also check for grouped shapes with images if shape.shape_type == MSO_SHAPE_TYPE.GROUP: print(f"Slide {i}: Group '{shape.name}'") for s in shape.shapes: if s.shape_type == MSO_SHAPE_TYPE.PICTURE: print(f" Sub-image: {s.name}") EOF

python3 - <<'EOF' # Extract images from PPTX and get full text/formatting details per slide from pptx import Presentation from pptx.util import Pt, Emu from pptx.dml.color import RGBColor from pptx.enum.shapes import MSO_SHAPE_TYPE from pptx.enum.text import PP_ALIGN import os, json pptx_path = "/tmp/workspace/attachments/bd6e6c97-f2a9-4618-8e55-168e26cb2814/PRINCIPLES AND OBJECTIVES OF SKIN.pptx" prs = Presentation(pptx_path) # Create output directory os.makedirs("/tmp/workspace/pptx_images", exist_ok=True) # Extract all images image_map = {} # slide_num -> list of (shape_name, filename) for slide_num, slide in enumerate(prs.slides, 1): for shape in slide.shapes: if shape.shape_type == MSO_SHAPE_TYPE.PICTURE: img = shape.image ext = img.ext fname = f"slide{slide_num}_{shape.name.replace(' ','_')}.{ext}" fpath = f"/tmp/workspace/pptx_images/{fname}" with open(fpath, 'wb') as f: f.write(img.blob) if slide_num not in image_map: image_map[slide_num] = [] image_map[slide_num].append({ "shape_name": shape.name, "filename": fname, "filepath": fpath, "left": shape.left, "top": shape.top, "width": shape.width, "height": shape.height }) print("Extracted images:") for sn, imgs in image_map.items(): for img in imgs: print(f" Slide {sn}: {img['filename']}") # Now get full text data per slide with rich formatting def get_rgb(color_obj): try: if color_obj.type: return str(color_obj.rgb) except: pass return None def get_shape_fill(shape): try: fill = shape.fill if fill.type is not None and str(fill.type) in ['SOLID (1)', '1']: try: return str(fill.fore_color.rgb) except: pass except: pass return None slides_rich = [] for slide_num, slide in enumerate(prs.slides, 1): slide_data = { "slide_num": slide_num, "images": image_map.get(slide_num, []), "shapes": [] } # Sort shapes by top position shapes_sorted = sorted(slide.shapes, key=lambda s: (s.top or 0, s.left or 0)) for shape in shapes_sorted: shape_data = { "name": shape.name, "type": str(shape.shape_type), "left": shape.left, "top": shape.top, "width": shape.width, "height": shape.height, "fill_color": get_shape_fill(shape) } if shape.has_text_frame: paras = [] for para in shape.text_frame.paragraphs: runs_data = [] for run in para.runs: runs_data.append({ "text": run.text, "bold": run.font.bold, "italic": run.font.italic, "underline": run.font.underline, "size": run.font.size, "name": run.font.name, "color": get_rgb(run.font.color) }) # Get para-level font info pf = para.font paras.append({ "text": para.text, "alignment": str(para.alignment), "level": para.level, "space_before": para.space_before, "space_after": para.space_after, "para_font_bold": pf.bold if pf else None, "para_font_size": pf.size if pf else None, "para_font_color": get_rgb(pf.color) if pf else None, "para_font_name": pf.name if pf else None, "runs": runs_data }) shape_data["paragraphs"] = paras slide_data["shapes"].append(shape_data) slides_rich.append(slide_data) with open("/tmp/workspace/slides_rich.json", "w") as f: json.dump(slides_rich, f, indent=2) print(f"\nRich data saved. Total slides: {len(slides_rich)}") # Show theme fonts and colors from slide masters print("\n=== Theme / Slide Master Info ===") for layout in prs.slide_layouts[:3]: print(f"Layout: {layout.name}") # Check theme colors try: theme = prs.slide_master.theme_color_map print(f"Theme: {theme}") except: pass # Check default text style in slide master sm = prs.slide_master for shape in sm.shapes: if shape.has_text_frame: for para in shape.text_frame.paragraphs: for run in para.runs: print(f"Master shape text: '{run.text}' font={run.font.name} size={run.font.size} color={get_rgb(run.font.color)}") EOF

python3 - <<'EOF' # Check the slides_rich.json to understand theme colors and fonts used import json with open("/tmp/workspace/slides_rich.json") as f: slides = json.load(f) # Find all unique fonts and colors fonts = set() colors = set() for slide in slides: for shape in slide["shapes"]: if "paragraphs" in shape: for p in shape["paragraphs"]: if p.get("para_font_name"): fonts.add(p["para_font_name"]) if p.get("para_font_color"): colors.add(p["para_font_color"]) for run in p.get("runs", []): if run.get("name"): fonts.add(run["name"]) if run.get("color"): colors.add(run["color"]) print("Fonts used:", fonts) print("Colors used:", colors) # Look at a few slides in detail to understand structure for s in slides[:5]: print(f"\n=== Slide {s['slide_num']} ===") for shape in s["shapes"]: if "paragraphs" in shape: for p in shape["paragraphs"]: if p["text"].strip(): runs_info = [(r["text"], r.get("bold"), r.get("size"), r.get("color"), r.get("name")) for r in p["runs"]] print(f" [{shape['name']}] L{p['level']}: '{p['text'][:80]}' runs={runs_info[:2]}") EOF