From 2784f9117584464c104bb175f0a26bd8d43dac11 Mon Sep 17 00:00:00 2001 From: Floke Date: Thu, 8 May 2025 10:56:07 +0000 Subject: [PATCH] bugfix --- brancheneinstufung.py | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/brancheneinstufung.py b/brancheneinstufung.py index 4df994fb..3aa1da92 100644 --- a/brancheneinstufung.py +++ b/brancheneinstufung.py @@ -192,6 +192,21 @@ BRANCH_MAPPING = {} TARGET_SCHEMA_STRING = "Ziel-Branchenschema nicht verfuegbar." ALLOWED_TARGET_BRANCHES = [] +# Liste gängiger User-Agents für Rotation +USER_AGENTS = [ + 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36', + 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36', + 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36', + 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36', + 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36', + 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15', + 'Mozilla/5.0 (Macintosh; Intel Mac OS X 13_1) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.1 Safari/605.1.15', + 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/109.0', + 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:108.0) Gecko/20100101 Firefox/108.0', + 'Mozilla/5.0 (X11; Linux i686; rv:108.0) Gecko/20100101 Firefox/108.0', + 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:108.0) Gecko/20100101 Firefox/108.0', +] + # ============================================================================== # Ende Basis-Setup Block # ============================================================================== @@ -2093,8 +2108,7 @@ def get_website_raw(url, max_length=20000, verify_cert=True): # verify_cert Defa url = "https://" + url headers = { - "User-Agent": getattr(Config, 'USER_AGENT', 'Mozilla/5.0 (compatible; UnternehmenSkript/1.0; +https://www.example.com/bot)') - # TODO (Optional): User-Agent Rotation hier implementieren + "User-Agent": random.choice(USER_AGENTS) # Wählt zufälligen User-Agent aus der Liste } # --- ANPASSUNG START: SSL Fallback & Spezifische Fehler --- response = None