Skip to content

Python tool for converting files and office documents to Markdown.

Add Support For PPTX Shape Groups (Fix in code design to not miss out on slide content) (#331)

Matthew Powerse82e0c137271
diff --git a/packages/markitdown/src/markitdown/converters/_pptx_converter.py b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
index afb37a01..76c481a7 100644
--- a/packages/markitdown/src/markitdown/converters/_pptx_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
@@ -64,7 +64,9 @@ class PptxConverter(HtmlConverter):
md_content += f"\n\n<!-- Slide number: {slide_num} -->\n"
title = slide.shapes.title
- for shape in slide.shapes:
+
+ def get_shape_content(shape, **kwargs):
+ nonlocal md_content
# Pictures
if self._is_picture(shape):
# https://github.com/scanny/python-pptx/pull/512#issuecomment-1713100069
@@ -134,6 +136,14 @@ class PptxConverter(HtmlConverter):
else:
md_content += shape.text + "\n"
+ # Group Shapes
+ if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
+ for subshape in shape.shapes:
+ get_shape_content(subshape, **kwargs)
+
+ for shape in slide.shapes:
+ get_shape_content(shape, **kwargs)
+
md_content = md_content.strip()
if slide.has_notes_slide:
diff --git a/packages/markitdown/tests/test_files/test.pptx b/packages/markitdown/tests/test_files/test.pptx
index ea1bbcb0..e6d16f3c 100644
Binary files a/packages/markitdown/tests/test_files/test.pptx and b/packages/markitdown/tests/test_files/test.pptx differ