app.py

import streamlit as st
import tempfile
import os
# import pyperclip
from langchain.document_loaders import UnstructuredFileLoader
from clipboard import copy



def main():
    st.title("PDF Text Extractor")
    
    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
    
    if uploaded_file is not None:
        st.subheader("PDF Content:")
        st.text("Extracted using langchain:")

        temp_file_path = os.path.join(tempfile.gettempdir(), f"{uploaded_file.name}")
        with open(temp_file_path, "wb") as temp_file:
            temp_file.write(uploaded_file.read())

        loader = UnstructuredFileLoader(temp_file_path)
        data = loader.load()
        txt = ''
        for item in data:
            txt += item.page_content
        text_content = txt
        if st.button("Copy to Clipboard"):
            copy(text_content)
            st.success("Text copied to clipboard!")
        st.text_area("Extracted Text:", value=text_content, height=300)
        
        
        st.text_input("Copy this text:", value=text_content, key="copy_text")



if __name__ == "__main__":
    main()