text_extractor.py

from pptx import Presentation
from PyPDF2 import PdfReader
from docx import Document


def extract_txt(file):
    return file.read().decode()


def extract_pdf(file):

    reader = PdfReader(file)

    text = ""

    for page in reader.pages:

        page_text = page.extract_text()

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

    return text


def extract_docx(file):

    doc = Document(file)

    paragraphs = [p.text for p in doc.paragraphs if p.text.strip() != ""]

    return paragraphs


def extract_ppt(file):

    prs = Presentation(file)

    slides = []

    for slide in prs.slides:

        slide_text = ""

        for shape in slide.shapes:

            if hasattr(shape, "text"):
                slide_text += shape.text + "\n"

        slides.append(slide_text)

    return slides