[31388f42] Fix NameError in reply generator and implement free-mail quality detection

lead-engine/trading_twins_ingest.py

@@ -70,6 +70,18 @@ def fetch_tradingtwins_emails(token, limit=200):
     filtered = [m for m in all_msgs if "Neue Anfrage zum Thema Roboter" in (m.get('subject') or '')]
     return filtered
 
+def is_free_mail(email_addr):
+    """Checks if an email belongs to a known free-mail provider."""
+    if not email_addr: return False
+    free_domains = {
+        'gmail.com', 'googlemail.com', 'outlook.com', 'hotmail.com', 'live.com', 
+        'msn.com', 'icloud.com', 'me.com', 'mac.com', 'yahoo.com', 'ymail.com', 
+        'rocketmail.com', 'gmx.de', 'gmx.net', 'web.de', 't-online.de', 
+        'freenet.de', 'mail.com', 'protonmail.com', 'proton.me', 'online.de'
+    }
+    domain = email_addr.split('@')[-1].lower()
+    return domain in free_domains
+
 def parse_tradingtwins_html(html_body):
     """
     Extracts data from the Tradingtwins HTML table structure.
@@ -80,15 +92,15 @@ def parse_tradingtwins_html(html_body):
     # Map label names in HTML to our keys
     field_map = {
         'Firma': 'company',
-        'Vorname': 'contact_first', # Key fixed to match ingest.py logic
-        'Nachname': 'contact_last', # Key fixed to match ingest.py logic
+        'Vorname': 'contact_first', 
+        'Nachname': 'contact_last', 
         'E-Mail': 'email',
         'Rufnummer': 'phone',
-        'Einsatzzweck': 'purpose', # Specific field
-        'Reinigungs-Fläche': 'area', # Specific field
+        'Einsatzzweck': 'purpose', 
+        'Reinigungs-Fläche': 'area', 
         'PLZ': 'zip',
         'Stadt': 'city',
-        'Lead-ID': 'source_id' # Mapped to DB column source_id
+        'Lead-ID': 'source_id' 
     }
     
     for label, key in field_map.items():
@@ -103,6 +115,13 @@ def parse_tradingtwins_html(html_body):
     if data.get('contact_first') and data.get('contact_last'):
         data['contact'] = f"{data['contact_first']} {data['contact_last']}"
     
+    # Quality Check: Free mail or missing company
+    email = data.get('email', '')
+    company = data.get('company', '-')
+    
+    data['is_free_mail'] = is_free_mail(email)
+    data['is_low_quality'] = data['is_free_mail'] or company == '-' or not company
+    
     # Ensure source_id is present and map to 'id' for db.py compatibility
     if not data.get('source_id'):
          data['source_id'] = f"tt_unknown_{int(datetime.now().timestamp())}"
@@ -111,7 +130,7 @@ def parse_tradingtwins_html(html_body):
 
     return data
 
-def process_leads(auto_sync=True):
+def process_leads(auto_sync=False):
     init_db()
     new_count = 0
     try: