app.py

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

# Ensure Poppler's path is correct
# Set the full path to Poppler's 'bin' directory (update this path according to your system)
poppler_path = r'C:\poppler\bin'  # Update this with your actual Poppler path

def pdf_to_text(pdf_path):
    try:
        # Convert PDF to images
        images = convert_from_path(pdf_path, poppler_path=poppler_path)
        text = ""
        
        # Extract text from each image using pytesseract
        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 save_text_to_word(text, filename="output.docx"):
    # Create a Word document and write the text to it
    doc = Document()
    doc.add_paragraph(text)
    doc.save(filename)

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...")

        # Convert 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"
            save_text_to_word(text, word_file)
            
            st.download_button("Download Word File", word_file)

if __name__ == "__main__":
    main()