extractor.py

from pptx import Presentation
from pypdf import PdfReader


def extract_ppt_text(file):

    prs = Presentation(file)

    text = ""

    for slide in prs.slides:
        for shape in slide.shapes:
            if hasattr(shape, "text"):
                text += shape.text + "\n"

    return text


def extract_pdf_text(file):

    reader = PdfReader(file)

    text = ""

    for page in reader.pages:

        page_text = page.extract_text()

        if page_text:
            text += page_text + "\n"

    return text