app

app.py

@@ -5,105 +5,130 @@ import re
 import os
 from urllib.parse import urljoin
 
-# Resto del código se mantiene igual...
+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
     """
-    # 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:", "")
-    
-    # Option to choose display mode
-    display_mode = st.radio("Display Mode:", 
-                             ["Full HTML", "Plain Text", "Side-by-Side"])
-    
-    # Slider for maximum images (1-40)
+    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:
-            # Scrape the content
             scraped_content = scrape_web_content(url_input, max_images, theme)
-            
             if scraped_content:
                 st.success("Content successfully scraped!")
-                
-                # 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")
-                    # Text area to show scraped content
-                    text_area = st.text_area("Scraped Text:", scraped_content['plain_text'], height=400)
-                    # Add a button to copy all text
-                    st.download_button(
-                        label="Copy All Text",
-                        data=scraped_content['plain_text'],
-                        file_name="scraped_text.txt",
-                        mime="text/plain",
-                        help="Click to copy all extracted text"
-                    )
-                
-                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")
-                        text_area = st.text_area("Scraped Text:", scraped_content['plain_text'], height=600)
-                        st.download_button(
-                            label="Copy All Text",
-                            data=scraped_content['plain_text'],
-                            file_name="scraped_text.txt",
-                            mime="text/plain",
-                            help="Click to copy all extracted text"
-                        )
-                
-                # 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.")
+                # Resto del código para mostrar contenido...
         else:
             st.warning("Please enter a valid URL.")