docling/docs/examples/full_page_ocr.py
Michele Dolfi 41e3dc898b add parent
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
2025-05-14 10:12:47 +02:00

42 lines
1.3 KiB
Python

from pathlib import Path
from docling.datamodel.base_models import InputFormat
from docling.datamodel.pipeline_options import (
PdfPipelineOptions,
TesseractCliOcrOptions,
)
from docling.document_converter import DocumentConverter, PdfFormatOption
def main():
input_doc = Path(__file__).parent / "../../tests/data/pdf/2206.01062.pdf"
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = True
# Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), RapidOcrOptions
# ocr_options = EasyOcrOptions(force_full_page_ocr=True)
# ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
# ocr_options = OcrMacOptions(force_full_page_ocr=True)
# ocr_options = RapidOcrOptions(force_full_page_ocr=True)
ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
pipeline_options.ocr_options = ocr_options
converter = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options,
)
}
)
doc = converter.convert(input_doc).document
md = doc.export_to_markdown()
print(md)
if __name__ == "__main__":
main()