diff --git a/brancheneinstufung.py b/brancheneinstufung.py index 78191d12..e539b013 100644 --- a/brancheneinstufung.py +++ b/brancheneinstufung.py @@ -12,7 +12,7 @@ import csv # ==================== KONFIGURATION ==================== class Config: - VERSION = "1.1.2" + VERSION = "1.0.14" LANG = "de" CREDENTIALS_FILE = "service_account.json" SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo" @@ -255,4 +255,33 @@ class DataProcessor: print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}") article = self.wiki_scraper.search_company_article(company_name, website) if article: - company_data = self.w_ + company_data = self.wiki_scraper.extract_company_data(article.url) + else: + company_data = {'branche': 'k.A.', 'umsatz': 'k.A.', 'url': '', 'full_infobox': 'k.A.'} + + current_values = self.sheet_handler.sheet.row_values(row_num) + new_values = [ + company_data.get('full_infobox', 'k.A.'), # Spalte G: kompletter Infobox-Text + company_data['branche'] if company_data['branche'] != "k.A." else current_values[6] if len(current_values) > 6 else "k.A.", + "k.A.", + company_data['umsatz'] if company_data['umsatz'] != "k.A." else current_values[8] if len(current_values) > 8 else "k.A.", + "k.A.", "k.A.", "k.A.", + company_data['url'] if company_data['url'] else current_values[12] if len(current_values) > 12 else "", + datetime.now().strftime("%Y-%m-%d %H:%M:%S"), + "k.A.", "k.A.", + Config.VERSION + ] + self.sheet_handler.update_row(row_num, new_values) + print(f"✅ Aktualisiert: Branche: {new_values[1]}, Umsatz: {new_values[3]}, URL: {new_values[7]}") + time.sleep(Config.RETRY_DELAY) + +# ==================== MAIN ==================== +if __name__ == "__main__": + try: + num_rows = int(input("Wieviele Zeilen sollen überprüft werden? ")) + except Exception as e: + print("Ungültige Eingabe. Bitte eine Zahl eingeben.") + exit(1) + processor = DataProcessor() + processor.process_rows(num_rows) + print("\n✅ Wikipedia-Auswertung abgeschlossen")