mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
43 lines
1.4 KiB
Python
43 lines
1.4 KiB
Python
import logging
|
|
from pathlib import Path
|
|
|
|
from docling.datamodel.document import DocumentConversionInput
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
_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/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],
|
|
# format_options={
|
|
# InputFormat.PDF: FormatOption(pipeline_cls=StandardPdfModelPipeline, backend=PyPdfiumDocumentBackend),
|
|
# InputFormat.DOCX: FormatOption(pipeline_cls=SimpleModelPipeline, backend=MsWordDocumentBackend)
|
|
# }
|
|
# )
|
|
|
|
conv_results = doc_converter.convert(input)
|
|
|
|
for res in conv_results:
|
|
print("")
|
|
print(
|
|
f"Document {res.input.file.name} converted with status {res.status}. Content:"
|
|
)
|
|
print(res.experimental.export_to_markdown())
|
|
# Export Docling document format to markdown (experimental):
|
|
with (Path("./scratch") / f"{res.input.file.name}.experimental.md").open("w") as fp:
|
|
fp.write(res.experimental.export_to_markdown())
|