Skip to content

Python tool for converting files and office documents to Markdown.

feat: sort pptx shapes to be parsed in top-to-bottom, left-to-right order (#1104)

Richard Ye0229ff6cb75a
diff --git a/README.md b/README.md
index 0aa788c6..40f4b827 100644
--- a/README.md
+++ b/README.md
@@ -14,7 +14,7 @@ MarkItDown is a lightweight Python utility for converting various files to Markd
At present, MarkItDown supports:
- PDF
-- PowerPoint
+- PowerPoint (reading in top-to-bottom, left-to-right order)
- Word
- Excel
- Images (EXIF metadata and OCR)
diff --git a/packages/markitdown/src/markitdown/converters/_pptx_converter.py b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
index bea12267..bcde6c95 100644
--- a/packages/markitdown/src/markitdown/converters/_pptx_converter.py
+++ b/packages/markitdown/src/markitdown/converters/_pptx_converter.py
@@ -6,6 +6,7 @@ import re
import html
from typing import BinaryIO, Any
+from operator import attrgetter
from ._html_converter import HtmlConverter
from ._llm_caption import llm_caption
@@ -160,10 +161,12 @@ class PptxConverter(DocumentConverter):
# Group Shapes
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.GROUP:
- for subshape in shape.shapes:
+ sorted_shapes = sorted(shape.shapes, key=attrgetter("top", "left"))
+ for subshape in sorted_shapes:
get_shape_content(subshape, **kwargs)
- for shape in slide.shapes:
+ sorted_shapes = sorted(slide.shapes, key=attrgetter("top", "left"))
+ for shape in sorted_shapes:
get_shape_content(shape, **kwargs)
md_content = md_content.strip()