Update app.py

app.py

@@ -67,10 +67,24 @@ def extract_website_content(url, max_images=2):
     headers = {
         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
     }
-    response = requests.get(url, headers=headers, timeout=10)
-    response.raise_for_status()
     
-    soup = BeautifulSoup(response.content, 'html.parser')
+    html_content = ""
+    try:
+        from playwright.sync_api import sync_playwright
+        with sync_playwright() as p:
+            browser = p.chromium.launch(headless=True)
+            page = browser.new_page(user_agent=headers['User-Agent'])
+            # Wait until there are no network connections for at least 500 ms (so JS can finish)
+            page.goto(url, timeout=30000, wait_until="networkidle")
+            html_content = page.content()
+            browser.close()
+    except Exception as e:
+        print(f"Playwright headless fetch failed: {e}. Falling back to requests...")
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        html_content = response.content
+        
+    soup = BeautifulSoup(html_content, 'html.parser')
     
     for script in soup(["script", "style", "nav", "footer", "header", "noscript"]):
         script.extract()
@@ -863,7 +877,7 @@ def create_demo():
         
         with gr.Row():
             with gr.Column(scale=1):
-                url_input = gr.Textbox(label="Enter a Website URL 🌐", placeholder="e.g. https://www.bbc.com/korean", value="https://www.bbc.com/korean")
+                url_input = gr.Textbox(label="Enter a Website URL 🌐", placeholder=r"e.g. https://storykorean.com/stories?level=beginner&story=tiger", value=r"https://storykorean.com/stories?level=beginner&story=tiger")
                 pdf_input = gr.File(label="Or Upload Book PDF 📚", file_types=[".pdf"], value=example_pdf)
                 
                 gr.Markdown("### ⚙️ Customization Settings")