[34288f42] Keine Zusammenfassung angegeben.

Keine Zusammenfassung angegeben.

fotograf-de-scraper/backend/siblings_logic.py

@@ -26,7 +26,7 @@ def generate_siblings_pdf_from_csv(csv_path: str, institution: str, calendly_eve
         except:
             raise Exception("CSV konnte nicht gelesen werden.")
 
-    df.columns = df.columns.str.strip().str.replace("\"", "")
+    df.columns = df.columns.str.strip().str.replace('"', "")
     
     # Identify Email Column
     email_col = next((c for c in df.columns if "email" in c.lower()), None)
@@ -56,8 +56,6 @@ def generate_siblings_pdf_from_csv(csv_path: str, institution: str, calendly_eve
             try:
                 start_dt = datetime.datetime.fromisoformat(event['start_time'].replace('Z', '+00:00'))
                 start_dt = start_dt.astimezone(ZoneInfo("Europe/Berlin"))
-                
-                # Allow all events for siblings logic, regardless of date, just to be sure we match them
                 calendly_map[event['invitee_email'].lower().strip()] = start_dt.strftime("%d.%m. %H:%M")
             except:
                 pass
@@ -123,3 +121,63 @@ def generate_siblings_pdf_from_csv(csv_path: str, institution: str, calendly_eve
     with open(output_path, "wb") as f:
         f.write(pdf)
     logger.info(f"Siblings PDF saved to {output_path}")
+
+def get_sibling_families_from_csv(csv_path: str, calendly_events: list = None) -> list:
+    df = None
+    for sep in [";", ","]:
+        try:
+            test_df = pd.read_csv(csv_path, sep=sep, encoding="utf-8-sig", nrows=5)
+            if len(test_df.columns) > 1:
+                df = pd.read_csv(csv_path, sep=sep, encoding="utf-8-sig")
+                break
+        except Exception as e:
+            continue
+            
+    if df is None:
+        try:
+            df = pd.read_csv(csv_path, sep=";", encoding="latin1")
+        except:
+            raise Exception("CSV konnte nicht gelesen werden.")
+
+    df.columns = df.columns.str.strip().str.replace('"', "")
+    
+    email_col = next((c for c in df.columns if "email" in c.lower()), None)
+    if not email_col:
+         email_col = next((c for c in df.columns if "e-mail" in c.lower()), None)
+         
+    if not email_col:
+        return []
+
+    lastname_col = next((c for c in df.columns if "nachname" in c.lower()), None)
+
+    # Build Calendly Email Set for filtering
+    booked_emails = set()
+    if calendly_events:
+        for event in calendly_events:
+            email = event.get('invitee_email', '').lower().strip()
+            if email:
+                booked_emails.add(email)
+
+    families_dict = defaultdict(list)
+    df = df.fillna("")
+    
+    for _, row in df.iterrows():
+        email = str(row[email_col]).strip().lower()
+        if email and "@" in email:
+            families_dict[email].append(row)
+
+    families = []
+    for email, rows in families_dict.items():
+        if len(rows) > 1: # SIBLINGS DETECTED
+            # FILTER OUT if they already have an appointment
+            if email in booked_emails:
+                logger.info(f"Family {email} already has Calendly appointment, skipping QR card.")
+                continue
+
+            family_last_name = str(rows[0][lastname_col]).strip() if lastname_col else "Unbekannt"
+            families.append({
+                "nachname": family_last_name
+            })
+    
+    families.sort(key=lambda x: x["nachname"])
+    return families