mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00

--------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Maxim Lysak <mly@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> Co-authored-by: Maxim Lysak <mly@zurich.ibm.com> Co-authored-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
11 lines
434 B
Python
11 lines
434 B
Python
from docling.document_converter import DocumentConverter
|
|
|
|
source = "https://arxiv.org/pdf/2408.09869" # PDF path or URL
|
|
converter = DocumentConverter()
|
|
result = converter.convert(source)
|
|
print(
|
|
result.document.export_to_markdown()
|
|
) # output: ## Docling Technical Report [...]"
|
|
# if the legacy output is needed, use this version
|
|
# print(result.legacy_document.export_to_markdown()) # output: ## Docling Technical Report [...]"
|