Example usage of pdfminer to extract text and images from a PDF

extract_text_and_images_from_pdf.py

from pdfminer.high_level import extract_text_to_fp
from pdfminer.layout import LAParams


def extract_text_from_pdf(input_filename: str, output_filename: str, output_images_dir: str | None = None) -> None:
    with open(input_filename, 'rb') as input_file, open(output_filename, 'w', encoding='utf-8') as output_file:
        extract_text_to_fp(input_file, output_file, output_dir=output_images_dir, laparams=LAParams())


extract_text_from_pdf(
    "C:\\Users\\rolla\\Downloads\\react systems - LLM.pdf",
    'react.txt',
    'C:\\Users\\rolla\\Downloads\\images'
)