title view

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from extract import take_screenshot
+from extract import take_webdata
 from PIL import Image
 from io import BytesIO
 
@@ -20,12 +20,18 @@ def visualize(url):
     # Fetch and display the website content
         with st.spinner("loading website data ..."):
             # innerHTML = get_innerHTML(url)
-            innerHTML = take_screenshot(url)
+            html_image, html_content = take_webdata(url)
+            if html_content:
+                st.info(html_content)
+            else:
+                st.error("Error: empty html content")
             st.subheader("Website preview:")
-            if innerHTML:
-                st.image(innerHTML)
+            if html_image:
+                st.image(html_image)
             else:
-                st.error("Error: empty html")
+                st.error("Error: empty html preview")
+            st.subheader("Website title:")
+                       
     
     except Exception as e:
         st.error(f"Error: {e}")

extract.py

@@ -3,7 +3,7 @@ from selenium.common.exceptions import WebDriverException
 from PIL import Image
 from io import BytesIO
 
-def take_screenshot(url):
+def take_webdata(url):
     options = webdriver.ChromeOptions()
     options.add_argument('--headless')
     options.add_argument('--no-sandbox')
@@ -14,11 +14,14 @@ def take_screenshot(url):
         wd.set_window_size(1080, 720)  # Adjust the window size here
         wd.get(url)
         wd.implicitly_wait(5)
+        # Get the page title
+        page_title = wd.title
         screenshot = wd.get_screenshot_as_png()
+
     except WebDriverException as e:
-        return Image.new('RGB', (1, 1))
+        return Image.new('RGB', (1, 1)), page_title
     finally:
         if wd:
             wd.quit()
 
-    return Image.open(BytesIO(screenshot))
+    return Image.open(BytesIO(screenshot)) , page_title