app.py

import streamlit as st
import os
from pdf2image import convert_from_path
from PIL import Image
import pytesseract

# Ensure Poppler is in the PATH (you might need to adjust this for your server)
os.environ["PATH"] += ":/usr/local/bin"  # Update this with the correct Poppler path if needed

def pdf_to_text(pdf_path):
    try:
        # Convert PDF to images
        images = convert_from_path(pdf_path)
        text = ""
        
        for image in images:
            text += pytesseract.image_to_string(image)
        
        return text
    except Exception as e:
        st.error(f"Error during PDF to image conversion: {e}")
        return None

def main():
    st.title("PDF to Text Converter")
    
    # Upload PDF file
    uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
    
    if uploaded_file is not None:
        # Save uploaded file temporarily
        with open("uploaded_file.pdf", "wb") as f:
            f.write(uploaded_file.getbuffer())
        
        st.text("Converting PDF to text...")
        
        text = pdf_to_text("uploaded_file.pdf")
        
        if text:
            st.text_area("Extracted Text", text, height=300)
            
            # Create downloadable Word file
            word_file = "output.docx"
            with open(word_file, "w") as f:
                f.write(text)
                
            st.download_button("Download Word File", word_file)
    
if __name__ == "__main__":
    main()