Update app.py

app.py

@@ -45,7 +45,7 @@ PLAYWRIGHT_STATE: Dict = {}
 REVOLVER = CredentialRevolver(os.getenv("PROXY_LIST", ""))
 
 SEARCH_ENGINES = {
-    "Google": "https://www.google.com/search?q={query}",
+    "Google": "https://www.google.com/search?q={query}&hl=en",
     "DuckDuckGo": "https://duckduckgo.com/html/?q={query}",
     "Bing": "https://www.bing.com/search?q={query}",
     "Brave": "https://search.brave.com/search?q={query}",
@@ -151,9 +151,7 @@ async def perform_web_browse(query: str, browser_name: str, search_engine: str):
     
     context_args = {
         'user_agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36',
-        'java_script_enabled': True,
-        'ignore_https_errors': True,
-        'bypass_csp': True
+        'java_script_enabled': True, 'ignore_https_errors': True, 'bypass_csp': True
     }
     if proxy_config:
         context_args['proxy'] = proxy_config
@@ -162,27 +160,31 @@ async def perform_web_browse(query: str, browser_name: str, search_engine: str):
     page = await context.new_page()
 
     try:
-        response = await page.goto(url, wait_until='networkidle', timeout=35000)
-        
+        response = await page.goto(url, wait_until='domcontentloaded', timeout=25000)
         final_url = page.url
-        title = await page.title() or "No Title"
+        
         html_content = await page.content()
         soup = BeautifulSoup(html_content, 'lxml')
-        
         converter = HTML_TO_MARKDOWN_CONVERTER(soup, base_url=final_url)
         markdown_text = converter.convert()
-        status_code = response.status if response else 0
 
-        if status_code not in {200, 204} and not markdown_text:
-            error_info = f"Page loaded with non-2xx status code: {status_code}. Content may be empty or an error page."
-            return {"status": "error", "query": query, "final_url": final_url, "http_status": status_code, "error_message": error_info}
+        # HYBRID STRATEGY: If content is empty/trivial, wait briefly for JS to render.
+        if len(markdown_text.split()) < 20:
+            await page.wait_for_timeout(3000)
+            html_content = await page.content()
+            soup = BeautifulSoup(html_content, 'lxml')
+            converter = HTML_TO_MARKDOWN_CONVERTER(soup, base_url=final_url)
+            markdown_text = converter.convert()
+
+        title = await page.title() or "No Title"
+        status_code = response.status if response else 0
 
         return {
             "status": "success", "query": query, "final_url": final_url, "page_title": title,
             "http_status": status_code, "proxy_used": proxy_server_used, "markdown_content": markdown_text,
         }
     except PlaywrightTimeoutError:
-        return {"status": "error", "query": query, "proxy_used": proxy_server_used, "error_message": f"Navigation timed out after 35s. The site may be slow, blocking automation, or the proxy ({proxy_server_used}) may have failed."}
+        return {"status": "error", "query": query, "proxy_used": proxy_server_used, "error_message": f"Navigation timed out after 25s. Site is likely too slow or blocking requests."}
     except Exception as e:
         return {"status": "error", "query": query, "proxy_used": proxy_server_used, "error_message": str(e).splitlines()[0]}
     finally: