app.py

import streamlit as st
import PyPDF2
import pytesseract
from PIL import Image
from pdf2image import convert_from_path

def pdf_to_text(pdf_file):
    # Open the PDF file
    pdf = PyPDF2.PdfFileReader(pdf_file)

    # Extract the text from each page
    text = ''
    for page in range(pdf.numPages):
        page_obj = pdf.getPage(page)
        text += page_obj.extractText()

    # If the text is empty, use OCR to extract the text
    if not text:
        # Convert the PDF to images
        images = convert_from_path(pdf_file)

        # Perform OCR on each image
        for image in images:
            text += pytesseract.image_to_string(image)

    return text

def main():
    st.title("PDF Text Extractor")
    st.write("Upload a PDF file to extract the text")

    pdf_file = st.file_uploader("Upload PDF file", type=["pdf"])

    if pdf_file is not None:
        text = pdf_to_text(pdf_file)
        st.write("Extracted Text:")
        st.code(text)

        # Save the text to a .txt file
        txt_file = pdf_file.name.replace('.pdf', '.txt')
        with open(txt_file, 'w') as f:
            f.write(text)
        st.write(f"Text saved to {txt_file}")

if __name__ == "__main__":
    main()