mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
Improved demo code, that saves output mds to files
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
This commit is contained in:
parent
bea9fc22af
commit
f773d8a621
@ -1,17 +1,27 @@
|
|||||||
|
import json
|
||||||
|
import logging
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
from typing import Iterable
|
||||||
|
|
||||||
|
import yaml
|
||||||
|
|
||||||
from docling.backend.msword_backend import MsWordDocumentBackend
|
from docling.backend.msword_backend import MsWordDocumentBackend
|
||||||
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
||||||
from docling.datamodel.base_models import (
|
from docling.datamodel.base_models import (
|
||||||
|
ConversionStatus,
|
||||||
InputFormat,
|
InputFormat,
|
||||||
PdfPipelineOptions,
|
PdfPipelineOptions,
|
||||||
PipelineOptions,
|
PipelineOptions,
|
||||||
)
|
)
|
||||||
from docling.datamodel.document import DocumentConversionInput
|
from docling.datamodel.document import ConversionResult, DocumentConversionInput
|
||||||
from docling.document_converter import DocumentConverter, FormatOption
|
from docling.document_converter import DocumentConverter, FormatOption
|
||||||
from docling.pipeline.simple_model_pipeline import SimpleModelPipeline
|
from docling.pipeline.simple_model_pipeline import SimpleModelPipeline
|
||||||
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
|
from docling.pipeline.standard_pdf_model_pipeline import StandardPdfModelPipeline
|
||||||
|
|
||||||
|
_log = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
USE_EXPERIMENTAL = False
|
||||||
|
|
||||||
input_paths = [
|
input_paths = [
|
||||||
# Path("tests/data/wiki_duck.html"),
|
# Path("tests/data/wiki_duck.html"),
|
||||||
Path("tests/data/word_sample.docx"),
|
Path("tests/data/word_sample.docx"),
|
||||||
@ -36,7 +46,11 @@ doc_converter = DocumentConverter()
|
|||||||
conv_results = doc_converter.convert(input)
|
conv_results = doc_converter.convert(input)
|
||||||
|
|
||||||
for res in conv_results:
|
for res in conv_results:
|
||||||
|
print("")
|
||||||
print(
|
print(
|
||||||
f"Document {res.input.file.name} converted with status {res.status}. Content:"
|
f"Document {res.input.file.name} converted with status {res.status}. Content:"
|
||||||
)
|
)
|
||||||
print(res.experimental.export_to_markdown())
|
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())
|
||||||
|
Loading…
Reference in New Issue
Block a user