luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Adds support for Shape Groups

Browse source
This commit is contained in:
mpowers 2025-02-12 23:24:52 -05:00
parent dbdf2c0c10
commit f8c14a8928
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
packages/markitdown/src/markitdown/converters/_pptx_converter.py
View file

@ -64,7 +64,9 @@ class PptxConverter(HtmlConverter):
md_content += f"\n\n<!-- Slide number: {slide_num} -->\n" md_content += f"\n\n<!-- Slide number: {slide_num} -->\n"
title = slide.shapes.title title = slide.shapes.title
for shape in slide.shapes:
def get_shape_content(shape, **kwargs):
nonlocal md_content
# Pictures # Pictures
if self._is_picture(shape): if self._is_picture(shape):
# https://github.com/scanny/python-pptx/pull/512#issuecomment-1713100069 # https://github.com/scanny/python-pptx/pull/512#issuecomment-1713100069
@ -125,7 +127,7 @@ class PptxConverter(HtmlConverter):
# Charts # Charts
if shape.has_chart: if shape.has_chart:
md_content += self._convert_chart_to_markdown(shape.chart) self._convert_chart_to_markdown(shape.chart)
# Text areas # Text areas
elif shape.has_text_frame: elif shape.has_text_frame:
@ -134,6 +136,14 @@ class PptxConverter(HtmlConverter):
else: else:
md_content += shape.text + "\n" 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() md_content = md_content.strip()
if slide.has_notes_slide: if slide.has_notes_slide: