mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-08-01 15:02:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Added picture data for pptx pictures

Browse Source 
Signed-off-by: Maksym Lysak <mly@zurich.ibm.com>
This commit is contained in:
Maksym Lysak 2024-11-15 14:35:25 +01:00
parent 364d37ca96
commit a54f583415
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
docling/backend/mspowerpoint_backend.py
View File

@ -10,11 +10,13 @@ from docling_core.types.doc import (
DoclingDocument, DoclingDocument,
DocumentOrigin, DocumentOrigin,
GroupLabel, GroupLabel,
ImageRef,
ProvenanceItem, ProvenanceItem,
Size, Size,
TableCell, TableCell,
TableData, TableData,
) )
from PIL import Image
from pptx import Presentation from pptx import Presentation
from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER from pptx.enum.shapes import MSO_SHAPE_TYPE, PP_PLACEHOLDER
@ -268,9 +270,20 @@ class MsPowerpointDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentB
return return
def handle_pictures(self, shape, parent_slide, slide_ind, doc): def handle_pictures(self, shape, parent_slide, slide_ind, doc):
# Get the image bytes
image = shape.image
image_bytes = image.blob
# Open it with PIL
pil_image = Image.open(BytesIO(image_bytes))
# shape has picture # shape has picture
prov = self.generate_prov(shape, slide_ind, "") prov = self.generate_prov(shape, slide_ind, "")
doc.add_picture(parent=parent_slide, caption=None, prov=prov) doc.add_picture(
parent=parent_slide,
image=ImageRef.from_pil(image=pil_image, dpi=72),
caption=None,
prov=prov,
)
return return
def handle_tables(self, shape, parent_slide, slide_ind, doc): def handle_tables(self, shape, parent_slide, slide_ind, doc):