changes for the refresh jwt token of site

title_creator_app/views.py

@@ -215,7 +215,7 @@ def extract_title_or_error(product, selected_pt):
             val = attr.get("attributeValue")
             
             if desc == "Capacity":
-                extracted_data[desc] = f"Capacity {val}"
+                extracted_data[desc] = f"Capacity {val}".replace(" in", "")
             elif desc in ["Door Type", "Color"]:
                 extracted_data[desc] = val
             elif desc in ["Width", "Depth", "Height"]:
@@ -295,13 +295,14 @@ def construct_dynamic_title(raw_data,selected_pt):
         return "Could not found attribute name on product details page"
 
 @login_required
-def title_creator_view(request):
+async def title_creator_view(request):
     if request.method == 'POST' and request.FILES.get('file'):
         excel_file = request.FILES['file']
         selected_pt = request.POST.get('product_type')
         fs = FileSystemStorage()
         filename = fs.save(excel_file.name, excel_file)
         file_path = fs.path(filename)
+        scraper = cloudscraper.create_scraper()
 
         try:
             # 1. Read Excel
@@ -312,11 +313,13 @@ def title_creator_view(request):
                 df['New_Generated_Title'] = ""
 
             headers = {"User-Agent": "Mozilla/5.0"}
+            dynamic_token = await get_fresh_token(scraper)
             results_for_ui = []
             # Specific Headers for the Item# API
             api_headers = {
                 "accept": "application/json, text/plain, */*",
-                "authorization": "Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJERVYifQ.uOFB7h7_Aw6jbA1HSqVJ44tKMO7E1ljz1kV_JddeKL64YCOH57-l1ZX2Lly-Jnhdnxk3xMAeW5FawAgymEaMKA",
+                "authorization": f"Bearer {dynamic_token}",
+                # "authorization": "Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJERVYifQ.uOFB7h7_Aw6jbA1HSqVJ44tKMO7E1ljz1kV_JddeKL64YCOH57-l1ZX2Lly-Jnhdnxk3xMAeW5FawAgymEaMKA",
                 "client_id": "GEC",
                 "referer": "https://www.globalindustrial.com/"
             }
@@ -391,7 +394,36 @@ def title_creator_view(request):
     return render(request, 'title_creator_index.html', {'product_types': product_types})
     # return render(request, 'title_creator_index.html')
 
-def process_excel_task(file_path, selected_pt, task_id):
+async def get_fresh_token(scraper):
+    """Hits the homepage once to extract the latest Bearer token."""
+    base_url = "https://www.globalindustrial.com"
+    try:
+        # One-time hit to the base URL
+        response = scraper.get(base_url, timeout=15)
+        
+        # 1. Check Cookies for 'Authorization'
+        token = scraper.cookies.get('Authorization')
+        print("token found in cookies:----- ",token)
+        if token:
+            return token.replace('Bearer ', '').strip()
+
+        # 2. Check __NEXT_DATA__ script in HTML
+        soup = BeautifulSoup(response.content, 'html.parser')
+        script_tag = soup.find('script', id='__NEXT_DATA__')
+        if script_tag:
+            data = json.loads(script_tag.string)
+            # Standard Next.js path for auth tokens
+            token = data.get('props', {}).get('pageProps', {}).get('token')
+            if token:
+                return token
+                
+    except Exception as e:
+        print(f"Token retrieval failed: {e}")
+    
+    # Fallback to your hardcoded token if extraction fails
+    return "eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJERVYifQ.uOFB7h7_Aw6jbA1HSqVJ44tKMO7E1ljz1kV_JddeKL64YCOH57-l1ZX2Lly-Jnhdnxk3xMAeW5FawAgymEaMKA"
+
+async def process_excel_task(file_path, selected_pt, task_id):
     # Retrieve the task record from the database
     scraper = cloudscraper.create_scraper() # This replaces requests.get
     task = ProcessingTask.objects.get(task_id=task_id)
@@ -405,10 +437,11 @@ def process_excel_task(file_path, selected_pt, task_id):
             df['New_Generated_Title'] = ""
 
         headers = {"User-Agent": "Mozilla/5.0"}
+        dynamic_token = await get_fresh_token(scraper)
         # Specific Headers for the Item# API
         api_headers = {
             "accept": "application/json, text/plain, */*",
-            "authorization": "Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJERVYifQ.uOFB7h7_Aw6jbA1HSqVJ44tKMO7E1ljz1kV_JddeKL64YCOH57-l1ZX2Lly-Jnhdnxk3xMAeW5FawAgymEaMKA",
+            "authorization": f"Bearer {dynamic_token}",#"Bearer eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJERVYifQ.uOFB7h7_Aw6jbA1HSqVJ44tKMO7E1ljz1kV_JddeKL64YCOH57-l1ZX2Lly-Jnhdnxk3xMAeW5FawAgymEaMKA",
             "client_id": "GEC",
             "referer": "https://www.globalindustrial.com/"
         }