extract text from pdf when the text isn't easy to copy

text_to_pdf.py

from PIL import Image
import pytesseract
from pdf2image import convert_from_path

# Convert the PDF to a list of images
images = convert_from_path('path_to_pdf.pdf')

# Process each image with Tesseract
for i, img in enumerate(images):
    text = pytesseract.image_to_string(img, lang='eng')
    with open(f'page_{i+1}.txt', 'w') as f:
        f.write(text)