mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
56 lines
2.0 KiB
Python
56 lines
2.0 KiB
Python
import logging
|
|
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.backend.msword_backend import MsWordDocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.document import DocumentConversionInput
|
|
from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
|
|
from docling.pipeline.simple_model_pipeline import SimpleModelPipeline
|
|
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
|
|
|
|
_log = logging.getLogger(__name__)
|
|
|
|
USE_EXPERIMENTAL = False
|
|
|
|
input_paths = [
|
|
Path("tests/data/wiki_duck.html"),
|
|
Path("tests/data/word_sample.docx"),
|
|
Path("tests/data/lorem_ipsum.docx"),
|
|
Path("tests/data/powerpoint_sample.pptx"),
|
|
Path("tests/data/powerpoint_sample.pptx"),
|
|
Path("tests/data/2206.01062.pdf"),
|
|
]
|
|
input = DocumentConversionInput.from_paths(input_paths)
|
|
|
|
# for defaults use:
|
|
doc_converter = DocumentConverter()
|
|
|
|
# to customize use:
|
|
# doc_converter = DocumentConverter( # all of the below is optional, has internal defaults.
|
|
# formats=[
|
|
# InputFormat.PDF,
|
|
# InputFormat.DOCX,
|
|
# ], # whitelist formats, other files are ignored.
|
|
# format_options={
|
|
# InputFormat.PDF: PdfFormatOption(backend=DoclingParseDocumentBackend),
|
|
# InputFormat.DOCX: FormatOption(
|
|
# pipeline_cls=StandardPdfModelPipeline, backend=MsWordDocumentBackend
|
|
# ),
|
|
# # InputFormat.IMAGE: PdfFormatOption(),
|
|
# },
|
|
# )
|
|
|
|
conv_results = doc_converter.convert(input)
|
|
|
|
for res in conv_results:
|
|
out_path = Path("./scratch") / f"{res.input.file.name}.experimental.md"
|
|
print(
|
|
f"Document {res.input.file.name} converted with status {res.status}."
|
|
f"\nSaved markdown output to: {str(out_path)}"
|
|
)
|
|
# print(res.experimental.export_to_markdown())
|
|
# Export Docling document format to markdown (experimental):
|
|
with out_path.open("w") as fp:
|
|
fp.write(res.experimental.export_to_markdown())
|