Update brancheneinstufung.py

brancheneinstufung.py

@@ -1,4 +1,4 @@
-# Neue Version mit Wikipedia-Validierung, GPT-Schutz und Antwortlogging
+# Neue Version mit Wikipedia-Validierung, GPT-Schutz und Antwortlogging inkl. Retry
 
 import os
 import time
@@ -12,6 +12,7 @@ from bs4 import BeautifulSoup
 import requests
 from oauth2client.service_account import ServiceAccountCredentials
 from datetime import datetime
+from openai.error import OpenAIError
 
 # === KONFIGURATION ===
 EXCEL = "Bestandsfirmen.xlsx"
@@ -98,7 +99,6 @@ system_prompt = {
     )
 }
 
-# === WIKIPEDIA FUNKTION ===
 WHITELIST_KATEGORIEN = ["Unternehmen", "Hersteller", "Produktion", "Industrie", "Maschinenbau", "Technik", "Dienstleistungsunternehmen"]
 
 def get_wikipedia_data(name, website_hint=""):
@@ -156,27 +156,38 @@ def get_wikipedia_data(name, website_hint=""):
                 continue
     return "", "k.A.", "k.A."
 
-# === GPT BEWERTUNG ===
 def classify_company(row, wikipedia_url=""):
     user_prompt = {
         "role": "user",
         "content": f"{row[0]};{row[1]};{row[2]};{row[4]};{row[5]}\nWikipedia-Link: {wikipedia_url}"
     }
+    for attempt in range(3):
+        try:
             response = openai.chat.completions.create(
                 model="gpt-3.5-turbo",
                 messages=[system_prompt, user_prompt],
                 temperature=0
             )
             full_text = response.choices[0].message.content.strip()
+            break
+        except OpenAIError as e:
+            print(f"⚠️ GPT-Fehler bei Versuch {attempt+1}: {e}")
+            time.sleep(10)
+    else:
+        print("❌ GPT 3x fehlgeschlagen – setze alles auf 'k.A.'")
+        full_text = "k.A.;k.A.;k.A.;k.A.;k.A.;k.A.;k.A.;k.A."
+
     lines = full_text.splitlines()
     csv_line = next((l for l in lines if ";" in l and not l.lower().startswith("wikipedia-branche")), "")
-    parts = [v.strip().strip('"') for v in csv_line.split(";")] if csv_line else []
+    parts = [v.strip().strip('"') for v in csv_line.split(";")] if csv_line else ["k.A."] * 8
+
     if len(parts) != 8:
-        print("⚠️  Antwort unvollständig → Setze alles auf 'k.A.'")
         parts = ["k.A."] * 8
+
     with open(LOG_CSV, "a", newline="", encoding="utf-8") as log:
         writer = csv.writer(log, delimiter=";")
         writer.writerow([datetime.now().strftime("%Y-%m-%d %H:%M:%S"), row[0], *parts, full_text])
+
     return parts
 
 # === VERARBEITUNG ===