mirror of
https://github.com/DS4SD/docling.git
synced 2025-12-08 12:48:28 +00:00
ff351fd40c
* Update .py examples with clearer guidance, update out of date imports and calls Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com> * Fix minimal.py string error, fix ruff format error Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com> * fix more CI issues Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com> --------- Signed-off-by: Mingxuan Zhao <43148277+mingxzhao@users.noreply.github.com>
33 lines
1.1 KiB
Python
Vendored
33 lines
1.1 KiB
Python
Vendored
# %% [markdown]
|
|
# Simple conversion: one document to Markdown
|
|
# ==========================================
|
|
#
|
|
# What this example does
|
|
# - Converts a single source (URL or local file path) to a unified Docling
|
|
# document and prints Markdown to stdout.
|
|
#
|
|
# Requirements
|
|
# - Python 3.9+
|
|
# - Install Docling: `pip install docling`
|
|
#
|
|
# How to run
|
|
# - Use the default sample URL: `python docs/examples/minimal.py`
|
|
# - To use your own file or URL, edit the `source` variable below.
|
|
#
|
|
# Notes
|
|
# - The converter auto-detects supported formats (PDF, DOCX, HTML, PPTX, images, etc.).
|
|
# - For batch processing or saving outputs to files, see `docs/examples/batch_convert.py`.
|
|
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
# Change this to a local path or another URL if desired.
|
|
# Note: using the default URL requires network access; if offline, provide a
|
|
# local file path (e.g., Path("/path/to/file.pdf")).
|
|
source = "https://arxiv.org/pdf/2408.09869"
|
|
|
|
converter = DocumentConverter()
|
|
result = converter.convert(source)
|
|
|
|
# Print Markdown to stdout.
|
|
print(result.document.export_to_markdown())
|