docling/docs/examples/export_figures.py
Michele Dolfi 5458a88464
ci: add coverage and ruff (#1383)
* add coverage calculation and push

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* new codecov version and usage of token

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* enable ruff formatter instead of black and isort

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff lint fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff unsafe fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add removed imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* runs 1 on linter issues

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* finalize linter fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update pyproject.toml

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-04-14 18:01:26 +02:00

92 lines
3.3 KiB
Python

import logging
import time
from pathlib import Path
from docling_core.types.doc import ImageRefMode, PictureItem, TableItem
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
_log = logging.getLogger(__name__)
IMAGE_RESOLUTION_SCALE = 2.0
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
# Important: For operating with page images, we must keep them, otherwise the DocumentConverter
# will destroy them for cleaning up memory.
# This is done by setting PdfPipelineOptions.images_scale, which also defines the scale of images.
# scale=1 correspond of a standard 72 DPI image
# The PdfPipelineOptions.generate_* are the selectors for the document elements which will be enriched
# with the image field
pipeline_options = PdfPipelineOptions()
pipeline_options.images_scale = IMAGE_RESOLUTION_SCALE
pipeline_options.generate_page_images = True
pipeline_options.generate_picture_images = True
doc_converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
}
)
start_time = time.time()
conv_res = doc_converter.convert(input_doc_path)
output_dir.mkdir(parents=True, exist_ok=True)
doc_filename = conv_res.input.file.stem
# Save page images
for page_no, page in conv_res.document.pages.items():
page_no = page.page_no
page_image_filename = output_dir / f"{doc_filename}-{page_no}.png"
with page_image_filename.open("wb") as fp:
page.image.pil_image.save(fp, format="PNG")
# Save images of figures and tables
table_counter = 0
picture_counter = 0
for element, _level in conv_res.document.iterate_items():
if isinstance(element, TableItem):
table_counter += 1
element_image_filename = (
output_dir / f"{doc_filename}-table-{table_counter}.png"
)
with element_image_filename.open("wb") as fp:
element.get_image(conv_res.document).save(fp, "PNG")
if isinstance(element, PictureItem):
picture_counter += 1
element_image_filename = (
output_dir / f"{doc_filename}-picture-{picture_counter}.png"
)
with element_image_filename.open("wb") as fp:
element.get_image(conv_res.document).save(fp, "PNG")
# Save markdown with embedded pictures
md_filename = output_dir / f"{doc_filename}-with-images.md"
conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.EMBEDDED)
# Save markdown with externally referenced pictures
md_filename = output_dir / f"{doc_filename}-with-image-refs.md"
conv_res.document.save_as_markdown(md_filename, image_mode=ImageRefMode.REFERENCED)
# Save HTML with externally referenced pictures
html_filename = output_dir / f"{doc_filename}-with-image-refs.html"
conv_res.document.save_as_html(html_filename, image_mode=ImageRefMode.REFERENCED)
end_time = time.time() - start_time
_log.info(f"Document converted and figures exported in {end_time:.2f} seconds.")
if __name__ == "__main__":
main()