Chat GPT Bugfixing Infobox ausgabe

brancheneinstufung.py

@@ -171,19 +171,22 @@ class WikipediaScraper:
     def extract_company_data(self, page_url):
         """Extrahiert Daten aus dem Wikipedia-Artikel"""
         if not page_url:
-            return {'branche': 'k.A.', 'umsatz': 'k.A.', 'url': ''}
+            return {
+                'full_infobox': self.extract_full_infobox(soup),'branche': 'k.A.', 'umsatz': 'k.A.', 'url': ''}
             
         try:
             response = requests.get(page_url)
             soup = BeautifulSoup(response.text, Config.HTML_PARSER)
             return {
+                'full_infobox': self.extract_full_infobox(soup),
                 'branche': self._extract_infobox_value(soup, 'branche'),
                 'umsatz': self._extract_infobox_value(soup, 'umsatz'),
                 'url': page_url
             }
         except Exception as e:
             debug_print(f"Extraktionsfehler: {str(e)}")
-            return {'branche': 'k.A.', 'umsatz': 'k.A.', 'url': page_url}
+            return {
+                'full_infobox': self.extract_full_infobox(soup),'branche': 'k.A.', 'umsatz': 'k.A.', 'url': page_url}
 
     def _extract_infobox_value(self, soup, target):
         """Extrahiert Werte aus der Infobox"""
@@ -238,6 +241,18 @@ class WikipediaScraper:
         
         return "k.A."
 
+
+    def extract_full_infobox(self, soup):
+        """Extrahiert die komplette Infobox als Text"""
+        infobox = soup.find('table', class_=lambda c: c and any(
+            kw in c.lower() for kw in ['infobox', 'vcard', 'unternehmen']
+        ))
+        
+        if not infobox:
+            return "k.A."
+        
+        return clean_text(infobox.get_text(separator=' | '))
+
 # ==================== DATA PROCESSOR ====================
 class DataProcessor:
     """Steuerung des Gesamtprozesses"""
@@ -266,10 +281,11 @@ class DataProcessor:
         if article:
             company_data = self.wiki_scraper.extract_company_data(article.url)
         else:
-            company_data = {'branche': 'k.A.', 'umsatz': 'k.A.', 'url': ''}
+            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.'),
             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.",