app

app.py

@@ -66,39 +66,67 @@ def apply_theme(theme):
 def scrape_web_content(url, max_images, theme):
     """
     Scrape the web content while preserving its original formatting
+    
+    Args:
+        url (str): URL of the webpage
+        max_images (int): Maximum number of images to download
+        theme (str): Selected theme (Claro/Oscuro)
+    
+    Returns:
+        dict: Extracted content with text, HTML, and images
     """
     try:
+        # Send a request to the URL
         response = requests.get(url)
         response.raise_for_status()
         
+        # Parse the HTML content
         soup = BeautifulSoup(response.content, 'html.parser')
+        
+        # Create a directory to save images if it doesn't exist
         os.makedirs('downloaded_images', exist_ok=True)
         
+        # Download images
         downloaded_images = []
         img_tags = soup.find_all('img', src=True)
         for i, img in enumerate(img_tags[:max_images], 1):
             try:
+                # Get the image source URL
                 img_url = img['src']
+                
+                # Handle relative URLs
                 if not img_url.startswith(('http://', 'https://')):
                     img_url = urljoin(url, img_url)
                 
+                # Download the image
                 img_response = requests.get(img_url)
                 img_response.raise_for_status()
                 
+                # Generate a unique filename
                 filename = f'downloaded_images/image_{i}.{img_url.split(".")[-1].split("?")[0]}'
+                
+                # Save the image
                 with open(filename, 'wb') as f:
                     f.write(img_response.content)
                 
+                # Update the image tag in the soup to point to local file
                 img['src'] = filename
                 downloaded_images.append(filename)
+            
             except Exception as img_error:
                 st.warning(f"Could not download image {i}: {img_error}")
         
+        # Remove unwanted tags
         for tag in soup(["script", "style", "meta", "link", "noscript"]):
             tag.decompose()
         
+        # Apply light theme styling if selected
         theme_prefix = apply_theme(theme) if theme == "Claro" else ""
+        
+        # Convert remaining soup to HTML string with theme prefix
         formatted_html = theme_prefix + str(soup)
+        
+        # Extract plain text for preview
         plain_text = soup.get_text(separator='\n', strip=True)
         
         return {
@@ -115,22 +143,85 @@ def main():
     """
     Main Streamlit application
     """
+    # Set page config
     st.set_page_config(page_title="Web Content Scraper", page_icon=":mag:", layout="wide")
+    
+    # Theme selector
     theme = st.sidebar.radio("Seleccionar Tema:", ["Oscuro", "Claro"])
+    
+    # Apply selected theme
     apply_theme(theme)
+    
     st.title("Web Content Scraper")
+    
+    # Get the URL from the user
     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"])
+    
+    # Option to choose display mode
+    display_mode = st.radio("Display Mode:", 
+                             ["Full HTML", "Plain Text", "Side-by-Side"])
+    
+    # Slider for maximum images (1-40)
     max_images = st.slider("Maximum number of images to download", 1, 40, 10)
     
     if st.button("Scrape Content"):
         if url_input:
+            # Scrape the content
             scraped_content = scrape_web_content(url_input, max_images, theme)
+            
             if scraped_content:
                 st.success("Content successfully scraped!")
-                # Resto del código para mostrar contenido...
+                
+                # Display content based on selected mode
+                if display_mode == "Full HTML":
+                    # Display full HTML with preserved formatting
+                    st.markdown("### Formatted Web Content")
+                    st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
+                
+                elif display_mode == "Plain Text":
+                    # Display plain text
+                    st.markdown("### Plain Text Content")
+                    st.text_area("Scraped Text:", scraped_content['plain_text'], height=400)
+                
+                else:  # Side-by-Side
+                    # Split the screen to show HTML and plain text
+                    col1, col2 = st.columns(2)
+                    
+                    with col1:
+                        st.markdown("### Formatted HTML")
+                        st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
+                    
+                    with col2:
+                        st.markdown("### Plain Text")
+                        st.text_area("Scraped Text:", scraped_content['plain_text'], height=600)
+                
+                # Display images
+                if scraped_content['images']:
+                    st.subheader(f"Downloaded Images ({len(scraped_content['images'])} of {max_images})")
+                    
+                    # Create a grid of image columns
+                    cols = st.columns(4)  # 4 columns for better layout with more images
+                    for i, img_path in enumerate(scraped_content['images']):
+                        with cols[i % 4]:
+                            st.image(img_path, use_column_width=True)
+                    
+                    # Zip and download option for images
+                    with open('downloaded_images.zip', 'wb') as zipf:
+                        import zipfile
+                        with zipfile.ZipFile(zipf, 'w') as zip_file:
+                            for img_path in scraped_content['images']:
+                                zip_file.write(img_path, os.path.basename(img_path))
+                    
+                    st.download_button(
+                        label="Download All Images",
+                        data=open('downloaded_images.zip', 'rb').read(),
+                        file_name='downloaded_images.zip',
+                        mime='application/zip'
+                    )
+            else:
+                st.warning("Failed to scrape content from the URL.")
         else:
             st.warning("Please enter a valid URL.")
 
 if __name__ == "__main__":
-    main()
+    main()