Update ppt_parser.py

ppt_parser.py

@@ -59,12 +59,15 @@ def transfer_to_structure(pptx_file, images_dir_path):
     prs = Presentation(pptx_file)
     image_path_list = []
 
+    os.makedirs(images_dir_path, exist_ok=True)
+
     for i, slide in enumerate(prs.slides):
         slide_item = {}
 
         for j, shape in enumerate(slide.shapes):
             shape_item = {}
 
+            # Case 1: Normal text box
             if shape.has_text_frame:
                 shape_item['type'] = "text"
                 text_frame = shape.text_frame
@@ -73,10 +76,12 @@ def transfer_to_structure(pptx_file, images_dir_path):
                     if data:
                         shape_item[f'paragraph_{r}'] = data
 
+            # Case 2: Grouped shapes
             elif isinstance(shape, GroupShape):
                 shape_item['type'] = "group"
                 shape_item['group_content'] = transfer_textbox_content_in_group(shape)
 
+            # Case 3: Picture
             elif isinstance(shape, Picture):
                 shape_item['type'] = "picture"
                 image_path = os.path.join(images_dir_path, f"picture_{j}.png")
@@ -91,7 +96,7 @@ def transfer_to_structure(pptx_file, images_dir_path):
                     shape_image = Image.open(image_stream)
                     shape_image.save(image_path)
                 except Exception:
-                    pass
+                    pass  # Could not parse image
 
             slide_item[f"shape_{j}"] = shape_item