mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-07-25 19:44:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix/implementing the capture of pptx_image with the same method from docx backend by extracting the drawing blip

Browse Source 
Signed-off-by: Benichou <fbenichou@deloitte.ca>
This commit is contained in:
Benichou 2025-04-08 11:33:52 -04:00
parent dda339397b
commit 82a9d27c96
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docling/backend/mspowerpoint_backend.py
View File

@ -46,6 +46,10 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
self.pptx_obj = None
self.valid = False
self.xpath_expr = etree.XPath(".//a:blip", namespaces={
"a": "http://schemas.openxmlformats.org/drawingml/2006/main",
"r": "http://schemas.openxmlformats.org/officeDocument/2006/relationships",
})
try:
if isinstance(self.path_or_stream, BytesIO):
self.pptx_obj = Presentation(self.path_or_stream)