duplicate_checker.py aktualisiert

This commit is contained in:
2025-08-08 06:07:04 +00:00
parent ec56daa9ea
commit f420b84aee

View File

@@ -2,6 +2,7 @@ import os
import sys import sys
import logging import logging
import pandas as pd import pandas as pd
from datetime import datetime
from thefuzz import fuzz from thefuzz import fuzz
from helpers import normalize_company_name, simple_normalize_url, serp_website_lookup from helpers import normalize_company_name, simple_normalize_url, serp_website_lookup
from config import Config from config import Config
@@ -15,7 +16,8 @@ CRM_SHEET_NAME = "CRM_Accounts"
MATCHING_SHEET_NAME = "Matching_Accounts" MATCHING_SHEET_NAME = "Matching_Accounts"
SCORE_THRESHOLD = 80 # Score-Schwelle SCORE_THRESHOLD = 80 # Score-Schwelle
LOG_DIR = "Log" LOG_DIR = "Log"
LOG_FILE = "duplicate_check_v2.12.txt" now = datetime.now().strftime('%Y-%m-%d_%H-%M')
LOG_FILE = f"{now}_duplicate_check_v2.12.txt"
# --- Logging Setup --- # --- Logging Setup ---
if not os.path.exists(LOG_DIR): if not os.path.exists(LOG_DIR):
@@ -36,7 +38,7 @@ fh.setFormatter(formatter)
root.addHandler(fh) root.addHandler(fh)
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
logger.info(f"Logging to console and file: {log_path}") logger.info(f"Logging to console and file: {log_path}")
logger.info("Starting duplicate_checker.py v2.12 | Version: 2025-08-08_10-20") logger.info(f"Starting duplicate_checker.py v2.12 | Version: {now}")
# --- SerpAPI Key laden --- # --- SerpAPI Key laden ---
try: try: