Extract text from scanned pdf files using tesseract ocr

how_to_extract_text_from_scanned_pdf_files_using_tesseract_ocr_parse_pdf.py.py

import pytesseract
from pypdfium2 import PdfDocument


def parse_pdf(
    path_or_io: str | bytes,
    pill_scale: int = 2,
    lang: str = "eng",
    page_sep: str = "\n\n",
    config: str = "",
) -> str:
    pdf = PdfDocument(path_or_io)
    pages = []
    total_pages = len(pdf)

    try:
        if not config:
            config = (
                f"-l {lang} --oem 1 --psm 6 "
                "-c preserve_interword_spaces=1 "
                "-c tessedit_do_invert=0 "
                "-c tosp_min_sane_kn_sp=2.8"
            )

        for page_idx in range(total_pages):
            print(f"Processing page {page_idx + 1}/{total_pages}...")

            page = pdf.get_page(page_idx)
            page_img = page.render(scale=pill_scale).to_pil()
            page.close()

            text = pytesseract.image_to_string(page_img, config=config)

            try:
                page_img.close()  # Pillow ≥10
            except AttributeError:
                pass  # Pillow <10 fallback

            del page_img  # Free memory

            pages.append(text)
    finally:
        pdf.close()

    print("OCR complete.")
    return page_sep.join(pages)