Update scraper.py

scraper.py

@@ -1,9 +1,7 @@
 from selenium import webdriver
 from selenium.webdriver.chrome.service import Service
-import time
 from bs4 import BeautifulSoup
-
-
+import os
 
 def scrape_website(website):
     print("Launching chrome browser...")
@@ -11,47 +9,39 @@ def scrape_website(website):
     chrome_driver_path = "/usr/bin/chromedriver"
     chrome_binary_path = "/usr/bin/chromium-browser"
 
+    if not os.path.exists(chrome_driver_path):
+        raise FileNotFoundError(f"Chromedriver not found at {chrome_driver_path}")
+    if not os.path.exists(chrome_binary_path):
+        raise FileNotFoundError(f"Chromium not found at {chrome_binary_path}")
+
     options = webdriver.ChromeOptions()
     options.binary_location = chrome_binary_path
     options.add_argument("--headless")
     options.add_argument("--no-sandbox")
     options.add_argument("--disable-dev-shm-usage")
 
-    driver = webdriver.Chrome(service=Service(chrome_driver_path), options=options)
+    service = Service(executable_path=chrome_driver_path)
+    driver = webdriver.Chrome(service=service, options=options)
 
     try:
         driver.get(website)
         print("Page Loaded...")
         html = driver.page_source
-
         return html
-
     finally:
         driver.quit()
 
-
-
 def extract_body_content(html_content):
-    soup = BeautifulSoup(html_content,"html.parser")
+    soup = BeautifulSoup(html_content, "html.parser")
     body_content = soup.body
-    if body_content:
-        return str(body_content)
-    return ""
+    return str(body_content) if body_content else ""
 
 def clean_body_content(body_content):
-    soup = BeautifulSoup(body_content,"html.parser")
-
-    for script_or_style in soup(["script","style"]):
+    soup = BeautifulSoup(body_content, "html.parser")
+    for script_or_style in soup(["script", "style"]):
         script_or_style.extract()
-    
     cleaned_content = soup.get_text(separator="\n")
-    cleaned_content = "\n".join(
-        line.strip() for line in cleaned_content.splitlines() if line.strip()
-    )
-
-    return cleaned_content
+    return "\n".join(line.strip() for line in cleaned_content.splitlines() if line.strip())
 
-def split_dom_content(dom_content,max_length=60000):
-    return [
-        dom_content[i:i+max_length] for i in range(0,len(dom_content),max_length)
-    ]
+def split_dom_content(dom_content, max_length=60000):
+    return [dom_content[i:i + max_length] for i in range(0, len(dom_content), max_length)]