duplicate_checker.py aktualisiert

duplicate_checker.py

@@ -2,60 +2,69 @@ import os
 import sys
 import logging
 import pandas as pd
+import tldextract
 from datetime import datetime
 from thefuzz import fuzz
 from helpers import normalize_company_name, simple_normalize_url
 from google_sheet_handler import GoogleSheetHandler
 
-# duplicate_checker.py v2.3 (Rückkehr zum v2.0-Scoring, erweitert mit Logging)
+# duplicate_checker.py v2.4 (root-domain match via tldextract)
-# Version: 2025-08-06_16-00
+# Version: 2025-08-06_16-30
 # --- Konfiguration ---
 CRM_SHEET_NAME      = "CRM_Accounts"
 MATCHING_SHEET_NAME = "Matching_Accounts"
-SCORE_THRESHOLD     = 80   # v2.0 Schwelle (0–190 Skala)
+SCORE_THRESHOLD     = 80   # Schwelle für automatisches Match
 LOG_DIR             = "Log"
 
 # --- Logging Setup mit Datum im Dateinamen ---
 if not os.path.exists(LOG_DIR):
     os.makedirs(LOG_DIR, exist_ok=True)
 now = datetime.now().strftime('%Y-%m-%d_%H-%M')
-log_path = os.path.join(LOG_DIR, f"{now}_Duplicate_v2.3.log")
+log_path = os.path.join(LOG_DIR, f"{now}_Duplicate_v2.4.log")
+
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
-# Console Handler (INFO+)
+
+# Console-Handler (INFO+)
 ch = logging.StreamHandler()
 ch.setLevel(logging.INFO)
 ch.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(message)s"))
 logger.addHandler(ch)
-# File Handler (DEBUG+)
+
+# File-Handler (DEBUG+)
 fh = logging.FileHandler(log_path, mode='a', encoding='utf-8')
 fh.setLevel(logging.DEBUG)
 fh.setFormatter(logging.Formatter("%(asctime)s - %(levelname)-8s - %(name)s - %(message)s"))
 logger.addHandler(fh)
+
 logger.info(f"Logging in Datei: {log_path}")
-logger.info("Version: duplicate_checker.py v2.3 (v2.0-Scoring mit Logging) | Build: 2025-08-06_16-00")
+logger.info("Version: duplicate_checker.py v2.4 (root-domain match via tldextract) | Build: 2025-08-06_16-30")
 
 
 def calculate_similarity(record1, record2):
-    """Berechnet den v2.0-Score: Domain=100, Name*0.7, Ort+Land=20."""
+    """Berechnet v2.0-Score mit root-domain match."""
     total_score = 0
-    # Domain(exakt)
+    # Domain root only
-    if record1.get('normalized_domain') and record1['normalized_domain'] == record2.get('normalized_domain'):
+    url1 = record1.get('CRM Website', '')
+    url2 = record2.get('CRM Website', '')
+    dom1 = tldextract.extract(url1).domain
+    dom2 = tldextract.extract(url2).domain
+    if dom1 and dom1 == dom2:
         total_score += 100
     # Name fuzzy
-    name1 = record1.get('normalized_name','')
+    name1 = record1.get('normalized_name', '')
-    name2 = record2.get('normalized_name','')
+    name2 = record2.get('normalized_name', '')
     if name1 and name2:
         sim = fuzz.token_set_ratio(name1, name2)
         total_score += sim * 0.7
-    # Ort+Land exakt
+    # Ort+Land exact
     if record1.get('CRM Ort') == record2.get('CRM Ort') and record1.get('CRM Land') == record2.get('CRM Land'):
         total_score += 20
     return round(total_score)
 
 
 def main():
-    logger.info("Starte Duplikats-Check v2.3 (v2.0-Scoring mit Logging)")
+    logger.info("Starte Duplikats-Check v2.4 (root-domain match)")
     try:
         sheet = GoogleSheetHandler()
         logger.info("GoogleSheetHandler initialisiert")
@@ -72,15 +81,15 @@ def main():
     logger.info(f"{len(crm_df)} CRM- und {len(match_df)} Matching-Zeilen geladen")
 
     # Normalisierung & Blocking-Key
-    for df, label in [(crm_df,'CRM'), (match_df,'Matching')]:
+    for df, label in [(crm_df, 'CRM'), (match_df, 'Matching')]:
-        df['normalized_name']   = df['CRM Name'].astype(str).apply(normalize_company_name)
+        df['normalized_name'] = df['CRM Name'].astype(str).apply(normalize_company_name)
         df['normalized_domain'] = df['CRM Website'].astype(str).apply(simple_normalize_url)
-        df['CRM Ort']           = df['CRM Ort'].astype(str).str.lower().str.strip()
+        df['CRM Ort'] = df['CRM Ort'].astype(str).str.lower().str.strip()
-        df['CRM Land']          = df['CRM Land'].astype(str).str.lower().str.strip()
+        df['CRM Land'] = df['CRM Land'].astype(str).str.lower().str.strip()
-        df['block_key']         = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
+        df['block_key'] = df['normalized_name'].apply(lambda x: x.split()[0] if x else None)
         logger.debug(f"{label}-Sample: {df.iloc[0][['normalized_name','normalized_domain','block_key']].to_dict()}")
 
-    # Build Blocking-Index
+    # Blocking-Index bauen
     crm_index = {}
     for idx, row in crm_df.iterrows():
         key = row['block_key']
@@ -88,32 +97,31 @@ def main():
             crm_index.setdefault(key, []).append(row)
     logger.info(f"Blocking-Index mit {len(crm_index)} Keys erstellt")
 
-    # Matching mit relevanten Kandidaten im Log
+    # Matching mit Top-3-Log
     results = []
     total = len(match_df)
     for i, mrow in match_df.iterrows():
         key = mrow['block_key']
-        candidates = crm_index.get(key, [])
+        cands = crm_index.get(key, [])
-        logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(candidates)} Kandidaten")
+        logger.info(f"Prüfe {i+1}/{total}: '{mrow['CRM Name']}' (Key='{key}') -> {len(cands)} Kandidaten")
-        if not candidates:
+        if not cands:
-            results.append({'Potenzieller Treffer im CRM':'','Ähnlichkeits-Score':0})
+            results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': 0})
             continue
-        # Score for each candidate
+        # Score für Kandidaten
-        scored = [(crow['CRM Name'], calculate_similarity(mrow,crow)) for crow in candidates]
+        scored = [(crow['CRM Name'], calculate_similarity(mrow, crow)) for crow in cands]
-        # Top 3 candidates logged
         top3 = sorted(scored, key=lambda x: x[1], reverse=True)[:3]
         logger.debug(f" Top3 Kandidaten: {top3}")
         best_name, best_score = max(scored, key=lambda x: x[1])
         if best_score >= SCORE_THRESHOLD:
-            results.append({'Potenzieller Treffer im CRM':best_name,'Ähnlichkeits-Score':best_score})
+            results.append({'Potenzieller Treffer im CRM': best_name, 'Ähnlichkeits-Score': best_score})
             logger.info(f" --> Match: '{best_name}' mit Score {best_score}")
         else:
-            results.append({'Potenzieller Treffer im CRM':'','Ähnlichkeits-Score':best_score})
+            results.append({'Potenzieller Treffer im CRM': '', 'Ähnlichkeits-Score': best_score})
             logger.info(f" --> Kein Match (höchster Score {best_score})")
 
-    # Write results back
+    # Ergebnisse zurückschreiben
-    out = pd.DataFrame(results)
+    out_df = pd.DataFrame(results)
-    output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out], axis=1)
+    output = pd.concat([match_df[['CRM Name','CRM Website','CRM Ort','CRM Land']].reset_index(drop=True), out_df], axis=1)
     data = [output.columns.tolist()] + output.values.tolist()
     ok = sheet.clear_and_write_data(MATCHING_SHEET_NAME, data)
     if ok:
@@ -121,5 +129,5 @@ def main():
     else:
         logger.error("Fehler beim Schreiben ins Google Sheet")
 
-if __name__=='__main__':
+if __name__ == '__main__':
     main()