Update app.py

app.py

@@ -4,19 +4,41 @@ import requests
 from groq import Groq
 
 # Define the Website class added
+#Parse webpages which is designed using JavaScript heavely
+# download the chorme driver from here as per your version of chrome - https://developer.chrome.com/docs/chromedriver/downloads
+from selenium import webdriver
+from selenium.webdriver.chrome.service import Service
+from selenium.webdriver.common.by import By
+from selenium.webdriver.chrome.options import Options
+
+PATH_TO_CHROME_DRIVER = 'chromedriver.exe'
+
 class Website:
+    url: str
+    title: str
+    text: str
+
     def __init__(self, url):
         self.url = url
-        try:
-            response = requests.get(url)
-            soup = BeautifulSoup(response.content, 'html.parser')
-            self.title = soup.title.string if soup.title else "No title found"
-            for irrelevant in soup.body(["script", "style", "img", "input"]):
-                irrelevant.decompose()
-            self.text = soup.body.get_text(separator="\n", strip=True)
-        except Exception as e:
-            self.title = "Error loading page"
-            self.text = str(e)
+
+        options = Options()
+
+        options.add_argument("--no-sandbox")
+        options.add_argument("--disable-dev-shm-usage")
+
+        service = Service(PATH_TO_CHROME_DRIVER)
+        driver = webdriver.Chrome(service=service)
+        driver.get(url)
+
+        # input("Please complete the verification in the browser and press Enter to continue...")
+        page_source = driver.page_source
+        driver.quit()
+
+        soup = BeautifulSoup(page_source, 'html.parser')
+        self.title = soup.title.string if soup.title else "No title found"
+        for irrelevant in soup(["script", "style", "img", "input"]):
+            irrelevant.decompose()
+        self.text = soup.get_text(separator="\n", strip=True)
 
 # Initialize Groq client
 api_key = "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"