Update app.py

app.py

@@ -125,7 +125,7 @@ def fetch_basic_leads(start_date, end_date):
 def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=gr.Progress()):
     """ 
     Step 2: Go back and fetch the specific Visit URLs for each company.
-    CRITICAL FIX: Now accepts start_date and end_date.
+    FIX: Now specifically parses 'visit_route' to find the Exit Page.
     """
     if df.empty:
         return df
@@ -139,7 +139,6 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
         lead_id = row["lead_id"]
         
         try:
-            # FIX: Added start_date and end_date to params!
             visit_data = make_request(
                 f"{BASE_URL}/accounts/{ACCOUNT_ID}/leads/{lead_id}/visits",
                 params={
@@ -160,21 +159,37 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
                 visit = visits[0]
                 v_attrs = visit.get("attributes", {})
                 
-                # A. Direct Attributes
+                # --- STRATEGY 1: Direct Attributes ---
                 landing = v_attrs.get("landing_page_path") or v_attrs.get("landing_page_url")
-                exit_p = v_attrs.get("exit_page_path") or v_attrs.get("exit_page_url")
                 
-                # B. Page Views (Deep Link)
+                # --- STRATEGY 2: Parse 'visit_route' (The FIX for Exit Page) ---
+                # The visit_route is a list of all pages visited. 
+                # Last item in list = Exit Page.
+                visit_route = v_attrs.get("visit_route", [])
+                if visit_route and isinstance(visit_route, list):
+                    # Get Last Item for Exit Page
+                    last_step = visit_route[-1]
+                    if not exit_p:
+                        exit_p = last_step.get("page_path") or last_step.get("page_url")
+                    
+                    # Fallback for Landing Page (First Item)
+                    if not landing:
+                        first_step = visit_route[0]
+                        landing = first_step.get("page_path") or first_step.get("page_url")
+
+                # --- STRATEGY 3: Deep Link via 'included' Page Views (Backup) ---
                 if not landing or not exit_p:
                     pv_map = {p["id"]: p["attributes"] for p in included if p["type"] == "page_views"}
                     pv_ids = [r["id"] for r in visit.get("relationships", {}).get("page_views", {}).get("data", [])]
                     
                     if pv_ids:
-                        first_pv = pv_map.get(pv_ids[0])
-                        if first_pv: landing = first_pv.get("url") or first_pv.get("path")
-                            
-                        last_pv = pv_map.get(pv_ids[-1])
-                        if last_pv: exit_p = last_pv.get("url") or last_pv.get("path")
+                        if not landing:
+                            first_pv = pv_map.get(pv_ids[0])
+                            if first_pv: landing = first_pv.get("url") or first_pv.get("path")
+                        
+                        if not exit_p:    
+                            last_pv = pv_map.get(pv_ids[-1])
+                            if last_pv: exit_p = last_pv.get("url") or last_pv.get("path")
 
                 df.at[index, "landing_page_path"] = landing
                 df.at[index, "exit_page_path"] = exit_p
@@ -193,7 +208,6 @@ def enrich_leads_with_visits(df, start_date, end_date, max_rows=None, progress=g
 def inspect_raw_json(lead_id, start_date, end_date):
     if not lead_id: return "Please enter a Lead ID"
     try:
-        # FIX: Added dates to Debugger URL params
         url = f"{BASE_URL}/accounts/{ACCOUNT_ID}/leads/{lead_id}/visits"
         params = {
             "start_date": start_date, 
@@ -214,7 +228,6 @@ def load_preview(start, end):
     if df.empty:
         return df, pd.DataFrame(), "⚠️ No data found."
     
-    # Pass dates to enrichment!
     df_preview = df.copy()
     df_preview = enrich_leads_with_visits(df_preview, start, end, max_rows=10)
     
@@ -225,7 +238,6 @@ def download_full_excel(df, start, end):
     if df is None or df.empty: return None
     
     print("⏳ Starting full enrichment for Excel export...")
-    # Pass dates to enrichment!
     enriched_df = enrich_leads_with_visits(df.copy(), start, end) 
     
     path = "/tmp/leadfeeder_company_data_full.xlsx"
@@ -292,7 +304,6 @@ with gr.Blocks(title="Leadfeeder Pro Analytics") as demo:
             table = gr.Dataframe(label="Preview (Top 10 Enriched)", interactive=True)
             
             btn_load.click(load_preview, [start, end], [df_state, table, status])
-            # Updated to pass start/end inputs
             btn_dl.click(download_full_excel, [df_state, start, end], file_dl)
 
         # --- TAB 2: DASHBOARD ---
@@ -313,7 +324,6 @@ with gr.Blocks(title="Leadfeeder Pro Analytics") as demo:
             dbg_id = gr.Textbox(label="Lead ID (Copy from Data tab)")
             dbg_btn = gr.Button("Inspect Raw JSON")
             dbg_out = gr.Code(language="json")
-            # Updated to pass start/end inputs
             dbg_btn.click(inspect_raw_json, [dbg_id, start, end], dbg_out)
 
 if __name__ == "__main__":