mirror of
https://github.com/docling-project/docling.git
synced 2025-07-04 15:50:17 +00:00
f9144f2bb6
* chore: Add example for inspection of picture content Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Test case re-generation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Test case re-generation only on CPU Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Add missing GT files Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
30 lines
916 B
Python
30 lines
916 B
Python
from docling_core.types.doc import TextItem
|
|
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
source = "tests/data/amt_handbook_sample.pdf"
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.images_scale = 2
|
|
pipeline_options.generate_page_images = True
|
|
|
|
doc_converter = DocumentConverter(
|
|
format_options={InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)}
|
|
)
|
|
|
|
result = doc_converter.convert(source)
|
|
|
|
doc = result.document
|
|
|
|
for picture in doc.pictures:
|
|
# picture.get_image(doc).show() # display the picture
|
|
print(picture.caption_text(doc), " contains these elements:")
|
|
|
|
for item, level in doc.iterate_items(root=picture, traverse_pictures=True):
|
|
if isinstance(item, TextItem):
|
|
print(item.text)
|
|
|
|
print("\n")
|