Floke/Brancheneinstufung2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
Floke
2025-07-08 09:31:51 +00:00
parent 22d7e2a611
commit b06d050ac9
1 changed files with 14 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
dealfront_enrichment.py
View File

@@ -38,13 +38,16 @@ OUTPUT_DIR = "/app/output"
class DealfrontScraper: class DealfrontScraper:
def __init__(self): def __init__(self):
logger.info("Initialisiere DealfrontScraper und Chrome WebDriver.") """
Initialisiert den WebDriver und den WebDriverWait.
Verwendet explizit den im Dockerfile installierten chromedriver.
"""
logger.info("Initialisiere den DealfrontScraper und den Chrome WebDriver.")
chrome_options = ChromeOptions() chrome_options = ChromeOptions()
# NEU: Lade-Optimierungen # Lade-Optimierungen und Headless-Argumente
prefs = {"profile.managed_default_content_settings.images": 2} prefs = {"profile.managed_default_content_settings.images": 2}
chrome_options.add_experimental_option("prefs", prefs) chrome_options.add_experimental_option("prefs", prefs)
chrome_options.add_argument("--headless") chrome_options.add_argument("--headless")
chrome_options.add_argument("--no-sandbox") chrome_options.add_argument("--no-sandbox")
chrome_options.add_argument("--disable-dev-shm-usage") chrome_options.add_argument("--disable-dev-shm-usage")
@@ -53,8 +56,14 @@ class DealfrontScraper:
chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"]) chrome_options.add_experimental_option("excludeSwitches", ["enable-automation"])
chrome_options.add_experimental_option('useAutomationExtension', False) chrome_options.add_experimental_option('useAutomationExtension', False)
# --- ENTSCHEIDENDE ÄNDERUNG ---
# Wir geben den Pfad zum funktionierenden, system-installierten Treiber explizit an.
# Dies umgeht den fehlerhaften webdriver-manager vollständig.
from selenium.webdriver.chrome.service import Service
service = Service(executable_path='/usr/bin/chromedriver')
try: try:
self.driver = webdriver.Chrome(options=chrome_options) self.driver = webdriver.Chrome(service=service, options=chrome_options)
self.driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})") self.driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
except Exception as e: except Exception as e:
logger.critical(f"WebDriver konnte nicht initialisiert werden. Fehler: {e}", exc_info=True) logger.critical(f"WebDriver konnte nicht initialisiert werden. Fehler: {e}", exc_info=True)
@@ -62,7 +71,7 @@ class DealfrontScraper:
raise raise
self.wait = WebDriverWait(self.driver, 30) self.wait = WebDriverWait(self.driver, 30)
logger.info("WebDriver erfolgreich initialisiert (Bild-Laden deaktiviert).") logger.info("WebDriver erfolgreich initialisiert.")```
def _load_credentials(self): def _load_credentials(self):
# (Diese Methode bleibt unverändert) # (Diese Methode bleibt unverändert)