app.py

import streamlit as st
from extract import take_webdata
from PIL import Image
from io import BytesIO
import pandas as pd

def main():
    st.title("Website Content Exctractor")
    
    # Get website URL from user input
    url = st.text_input("Enter a URL:", "")
    if st.button("Proceed"):
        if not url:
            st.warning("URL is empty.")
        else:
            visualize(url)
  

def visualize(url):  
    try:
    # Fetch and display the website content
        with st.spinner("loading website data ..."):
            # innerHTML = get_innerHTML(url)
            html_content, parse_element = take_webdata(url)
            #st.subheader("Website title:")
            if parse_element:
                #st.info(html_content)
                #st.code(html_content, language='html')  
                # Konversi tabel HTML ke DataFrame Pandas
                #df = pd.read_html(str(parse_element))[0]
                #st.dataframe(df)  # tampilkan tabel dengan format rapi Streamlit
                #st.components.v1.html(str(parse_element), height=600, scrolling=True)
                
                
                # === 6. Tampilkan di Streamlit ===
                st.dataframe(parse_element)
            else:
                st.warning("Tabel tidak ditemukan.")
                
                                   
    
    except Exception as e:
        st.error(f"Error: {e}")



if __name__ == "__main__":
    main()