app.py

import streamlit as st
from bs4 import BeautifulSoup
import pdfkit
import tempfile

# Set up Streamlit interface
st.title("HTML to PDF Converter")

# Input HTML content
html_input = st.text_area("Paste your HTML content here:", height=300)

if st.button("Convert to PDF"):
    # Parse HTML content
    soup = BeautifulSoup(html_input, "html.parser")
    validated_html = str(soup)  # Convert back to string if needed

    # Specify the path to the wkhtmltopdf executable
    config = pdfkit.configuration(wkhtmltopdf='/path/to/wkhtmltopdf')  # Update this path based on your installation

    # Convert HTML to PDF
    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_pdf:
        pdfkit.from_string(validated_html, tmp_pdf.name, configuration=config)
        st.success("PDF generated successfully!")
        
        # Provide a download button
        with open(tmp_pdf.name, "rb") as pdf_file:
            st.download_button(
                label="Download PDF",
                data=pdf_file,
                file_name="converted_document.pdf",
                mime="application/pdf"
            )