convert.py

import pdfplumber
import streamlit as st

def ExtractPDFText(pdf):
    content = ""
    pdf_bytes = pdf.read()

    try:
        # Using pdfplumber to read the PDF bytes
        with pdfplumber.open(BytesIO(pdf_bytes)) as pdf_document:
            # Iterate through pages and extract text
            for page in pdf_document.pages:
                text = page.extract_text()
                content += text if text else ""
        
    except Exception as e:
        st.error(f"Error extracting text from PDF: {e}")

    return content