import streamlit as st
import requests
from bs4 import BeautifulSoup
import re
import os
from urllib.parse import urljoin

def apply_theme(theme):
    """
    Apply custom CSS based on the selected theme
    """
    if theme == "Claro":
        st.markdown("""
        <style>
        body {
            color: black;
            background-color: white;
        }
        .stTextInput > div > div > input {
            color: black;
            background-color: white;
        }
        .stMarkdown {
            color: black;
        }
        /* Light theme for HTML content */
        .light-theme {
            background-color: white !important;
            color: black !important;
        }
        .light-theme a {
            color: #0066cc !important;
        }
        .light-theme h1, .light-theme h2, .light-theme h3, 
        .light-theme h4, .light-theme h5, .light-theme h6 {
            color: #333 !important;
        }
        </style>
        """, unsafe_allow_html=True)
        return """
        <div style="background-color: white; color: black; padding: 20px;">
        <style>
            body { background-color: white !important; color: black !important; }
            a { color: #0066cc; }
            h1, h2, h3, h4, h5, h6 { color: #333; }
        </style>
        """
    else:
        st.markdown("""
        <style>
        body {
            color: white;
            background-color: #0E1117;
        }
        .stTextInput > div > div > input {
            color: white;
            background-color: #262730;
        }
        .stMarkdown {
            color: white;
        }
        </style>
        """, unsafe_allow_html=True)
        return ""

def scrape_web_content(url, max_images, theme):
    """
    Scrape the web content while preserving its original formatting
    """
    try:
        response = requests.get(url)
        response.raise_for_status()
        
        soup = BeautifulSoup(response.content, 'html.parser')
        os.makedirs('downloaded_images', exist_ok=True)
        
        downloaded_images = []
        img_tags = soup.find_all('img', src=True)
        for i, img in enumerate(img_tags[:max_images], 1):
            try:
                img_url = img['src']
                if not img_url.startswith(('http://', 'https://')):
                    img_url = urljoin(url, img_url)
                
                img_response = requests.get(img_url)
                img_response.raise_for_status()
                
                filename = f'downloaded_images/image_{i}.{img_url.split(".")[-1].split("?")[0]}'
                with open(filename, 'wb') as f:
                    f.write(img_response.content)
                
                img['src'] = filename
                downloaded_images.append(filename)
            except Exception as img_error:
                st.warning(f"Could not download image {i}: {img_error}")
        
        for tag in soup(["script", "style", "meta", "link", "noscript"]):
            tag.decompose()
        
        theme_prefix = apply_theme(theme) if theme == "Claro" else ""
        formatted_html = theme_prefix + str(soup)
        plain_text = soup.get_text(separator='\n', strip=True)
        
        return {
            'html': formatted_html,
            'plain_text': plain_text,
            'images': downloaded_images
        }
    
    except Exception as e:
        st.error(f"Error occurred while scraping the content: {e}")
        return None

def main():
    """
    Main Streamlit application
    """
    st.set_page_config(page_title="Web Content Scraper", page_icon=":mag:", layout="wide")
    theme = st.sidebar.radio("Seleccionar Tema:", ["Oscuro", "Claro"])
    apply_theme(theme)
    st.title("Web Content Scraper")
    url_input = st.text_input("Enter the URL of the web page:", "")
    display_mode = st.radio("Display Mode:", ["Full HTML", "Plain Text", "Side-by-Side"])
    max_images = st.slider("Maximum number of images to download", 1, 40, 10)
    
    if st.button("Scrape Content"):
        if url_input:
            scraped_content = scrape_web_content(url_input, max_images, theme)
            if scraped_content:
                st.success("Content successfully scraped!")
                # Resto del código para mostrar contenido...
        else:
            st.warning("Please enter a valid URL.")

if __name__ == "__main__":
    main()