.py

import fitz
import pytesseract

def convert_to_img(pdf):
  doc = fitz.open(pdf)
  page = doc.loadPage(0)
  pix = page.getPixmap()
  output = f"{pdf.split(".")[0]}.png"
  pix.writePNG(output)

def convert_to_string(image)
  img_cv = cv2.imread(image)
  img_rgb = cv2.cvtColor(img_cv, cv2.COLOR_BGR2RGB)
  print(pytesseract.image_to_string(img_rgb))

if __name__ == '__main__':
  convert_to_img('text.pdf')
  convert_to_string('text.png')