Update app.py

app.py

@@ -4,6 +4,12 @@ from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.chrome.service import Service
 from webdriver_manager.chrome import ChromeDriverManager
 import time
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
 # Fix huggingface_hub cached_download
 import huggingface_hub
 if not hasattr(huggingface_hub, "cached_download"):
@@ -21,14 +27,21 @@ def scrape_with_selenium(url: str):
     chrome_options.add_argument("--no-sandbox")
     chrome_options.add_argument("--disable-dev-shm-usage")
     chrome_options.binary_location = "/usr/bin/chromium"
-    service = Service(ChromeDriverManager().install())
-    driver = webdriver.Chrome(service=service, options=chrome_options)
-    driver.get(url)
-    time.sleep(2)
-    paragraphs = driver.find_elements("tag name", "p")
-    text_data = [p.text for p in paragraphs if p.text.strip()]
-    driver.quit()
-    return text_data
+    try:
+        # Use webdriver-manager to get the correct ChromeDriver
+        logger.info("Installing ChromeDriver with webdriver-manager")
+        service = Service(ChromeDriverManager(driver_version=None).install())
+        driver = webdriver.Chrome(service=service, options=chrome_options)
+        logger.info(f"Navigating to {url}")
+        driver.get(url)
+        time.sleep(2)
+        paragraphs = driver.find_elements("tag name", "p")
+        text_data = [p.text for p in paragraphs if p.text.strip()]
+        driver.quit()
+        return text_data
+    except Exception as e:
+        logger.error(f"Selenium error: {str(e)}")
+        raise
 
 # 2️⃣ Build FAISS Index
 def build_faiss_index(text_data):
@@ -74,4 +87,4 @@ if "scraped_text" in st.session_state:
             st.subheader("💡 Answer")
             st.write(answer)
         except Exception as e:
-            st.error(f"Error processing question: {str(e)}") 
+            st.error(f"Error processing question: {str(e)}")