Api/app/modules/documentHandeler/features/extractText_feature.py

import io
import os

from fastapi import UploadFile
import pdfplumber


class ExtractTextFeature:

    @staticmethod
    async def extract_text_from_pdf(file: UploadFile) -> str:

        content = await file.read()
        with pdfplumber.open(io.BytesIO(content)) as pdf:
            text = ""
            for page in pdf.pages:
                text += page.extract_text()

        return text