docling/docs/examples/export_tables.py
Michele Dolfi 5458a88464
ci: add coverage and ruff (#1383)
* add coverage calculation and push

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* new codecov version and usage of token

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* enable ruff formatter instead of black and isort

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff lint fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* apply ruff unsafe fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* add removed imports

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* runs 1 on linter issues

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* finalize linter fixes

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>

* Update pyproject.toml

Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>

---------

Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Michele Dolfi <97102151+dolfim-ibm@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
2025-04-14 18:01:26 +02:00

52 lines
1.4 KiB
Python

import logging
import time
from pathlib import Path
import pandas as pd
from docling.document_converter import DocumentConverter
_log = logging.getLogger(__name__)
def main():
logging.basicConfig(level=logging.INFO)
input_doc_path = Path("./tests/data/pdf/2206.01062.pdf")
output_dir = Path("scratch")
doc_converter = DocumentConverter()
start_time = time.time()
conv_res = doc_converter.convert(input_doc_path)
output_dir.mkdir(parents=True, exist_ok=True)
doc_filename = conv_res.input.file.stem
# Export tables
for table_ix, table in enumerate(conv_res.document.tables):
table_df: pd.DataFrame = table.export_to_dataframe()
print(f"## Table {table_ix}")
print(table_df.to_markdown())
# Save the table as csv
element_csv_filename = output_dir / f"{doc_filename}-table-{table_ix + 1}.csv"
_log.info(f"Saving CSV table to {element_csv_filename}")
table_df.to_csv(element_csv_filename)
# Save the table as html
element_html_filename = output_dir / f"{doc_filename}-table-{table_ix + 1}.html"
_log.info(f"Saving HTML table to {element_html_filename}")
with element_html_filename.open("w") as fp:
fp.write(table.export_to_html(doc=conv_res.document))
end_time = time.time() - start_time
_log.info(f"Document converted and tables exported in {end_time:.2f} seconds.")
if __name__ == "__main__":
main()