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

gemini nochmal

Browse Source
This commit is contained in:
Floke
2025-07-11 07:22:31 +00:00
parent 87c7c6d272
commit 858553ea78
1 changed files with 48 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

122
dealfront_enrichment.py
View File

@@ -10,40 +10,32 @@ from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException from selenium.common.exceptions import TimeoutException, NoSuchElementException
# Temporäre Konfiguration, um Unabhängigkeit zu gewährleisten # --- Konfiguration ---
class TempConfig: class TempConfig:
DEALFRONT_LOGIN_URL = "https://app.dealfront.com/login" DEALFRONT_LOGIN_URL = "https://app.dealfront.com/login"
TARGET_SEARCH_NAME = "Facility Management" # Passen Sie dies bei Bedarf an DEALFRONT_TARGET_URL = "https://app.dealfront.com/t/prospector/companies"
TARGET_SEARCH_NAME = "Facility Management" # BITTE AN IHRE SUCHE ANPASSEN
DEALFRONT_CREDENTIALS_FILE = "/app/dealfront_credentials.json" DEALFRONT_CREDENTIALS_FILE = "/app/dealfront_credentials.json"
DEALFRONT_TARGET_URL = "https://app.dealfront.com/t?products=target%2Cconnect%2Cpromote%2Cdatacare"
# Logging-Konfiguration # --- Logging Setup ---
OUTPUT_DIR = "/app/output" OUTPUT_DIR = "/app/output"
LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s' LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s'
logging.basicConfig(level=logging.INFO, format=LOG_FORMAT, force=True) logging.basicConfig(level=logging.INFO, format=LOG_FORMAT, force=True)
logging.getLogger("selenium").setLevel(logging.WARNING) logging.getLogger("selenium").setLevel(logging.INFO) # Selenium-Logs auf INFO reduzieren
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
# Log-Datei einrichten
log_filename = f"dealfront_run_{time.strftime('%Y%m%d-%H%M%S')}.txt"
log_filepath = os.path.join(OUTPUT_DIR, log_filename)
try:
os.makedirs(OUTPUT_DIR, exist_ok=True) os.makedirs(OUTPUT_DIR, exist_ok=True)
log_filepath = os.path.join(OUTPUT_DIR, f"dealfront_run_{time.strftime('%Y%m%d-%H%M%S')}.log")
file_handler = logging.FileHandler(log_filepath, mode='w', encoding='utf-8') file_handler = logging.FileHandler(log_filepath, mode='w', encoding='utf-8')
file_handler.setLevel(logging.DEBUG)
file_handler.setFormatter(logging.Formatter(LOG_FORMAT)) file_handler.setFormatter(logging.Formatter(LOG_FORMAT))
logging.getLogger().addHandler(file_handler) logging.getLogger().addHandler(file_handler)
logger.info(f"Logging konfiguriert. Log-Datei: {log_filepath}")
except Exception as e:
logger.error(f"Konnte Log-Datei nicht erstellen: {e}")
class DealfrontScraper: class DealfrontScraper:
def __init__(self): def __init__(self):
logger.info("Initialisiere den DealfrontScraper...") logger.info("Initialisiere WebDriver...")
chrome_options = ChromeOptions() chrome_options = ChromeOptions()
prefs = {"profile.managed_default_content_settings.images": 2} chrome_options.add_experimental_option("prefs", {"profile.managed_default_content_settings.images": 2})
chrome_options.add_experimental_option("prefs", prefs) chrome_options.add_argument("--headless=new")
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")
chrome_options.add_argument("--window-size=1920,1080") chrome_options.add_argument("--window-size=1920,1080")
@@ -51,31 +43,29 @@ class DealfrontScraper:
try: try:
self.driver = webdriver.Chrome(options=chrome_options) self.driver = webdriver.Chrome(options=chrome_options)
except Exception as e: except Exception as e:
logger.critical(f"WebDriver konnte nicht initialisiert werden.", exc_info=True) logger.critical("WebDriver konnte nicht initialisiert werden.", exc_info=True)
raise raise
self.wait = WebDriverWait(self.driver, 45) # Erhöhter Timeout für mehr Stabilität self.wait = WebDriverWait(self.driver, 30)
self.username, self.password = self._load_credentials() self.username, self.password = self._load_credentials()
logger.info("WebDriver erfolgreich initialisiert.") logger.info("WebDriver erfolgreich initialisiert.")
def _load_credentials(self): def _load_credentials(self):
try: try:
with open(TempConfig.DEALFRONT_CREDENTIALS_FILE, 'r') as f: with open(TempConfig.DEALFRONT_CREDENTIALS_FILE, 'r') as f:
creds = json.load(f) return json.load(f).get("username"), json.load(f).get("password")
return creds.get("username"), creds.get("password") except Exception:
except Exception as e: logger.error(f"Credentials-Datei {TempConfig.DEALFRONT_CREDENTIALS_FILE} nicht gefunden oder fehlerhaft.")
logger.error(f"Credentials-Datei konnte nicht geladen werden: {e}")
return None, None return None, None
def _save_debug_artifacts(self): def _save_debug_artifacts(self):
try: try:
timestamp = time.strftime("%Y%m%d-%H%M%S") timestamp = time.strftime("%Y%m%d-%H%M%S")
screenshot_filepath = os.path.join(OUTPUT_DIR, f"error_{timestamp}.png") screenshot_path = os.path.join(OUTPUT_DIR, f"error_{timestamp}.png")
html_filepath = os.path.join(OUTPUT_DIR, f"error_{timestamp}.html") html_path = os.path.join(OUTPUT_DIR, f"error_{timestamp}.html")
self.driver.save_screenshot(screenshot_filepath) self.driver.save_screenshot(screenshot_path)
logger.error(f"Screenshot '{screenshot_filepath}' wurde gespeichert.") with open(html_path, "w", encoding="utf-8") as f:
with open(html_filepath, "w", encoding="utf-8") as f:
f.write(self.driver.page_source) f.write(self.driver.page_source)
logger.error(f"HTML-Quellcode '{html_filepath}' wurde gespeichert.") logger.error(f"Debug-Artefakte gespeichert: {screenshot_path}, {html_path}")
except Exception as e: except Exception as e:
logger.error(f"Konnte Debug-Artefakte nicht speichern: {e}") logger.error(f"Konnte Debug-Artefakte nicht speichern: {e}")
@@ -86,65 +76,51 @@ class DealfrontScraper:
self.wait.until(EC.visibility_of_element_located((By.NAME, "email"))).send_keys(self.username) self.wait.until(EC.visibility_of_element_located((By.NAME, "email"))).send_keys(self.username)
self.driver.find_element(By.CSS_SELECTOR, "input[type='password']").send_keys(self.password) self.driver.find_element(By.CSS_SELECTOR, "input[type='password']").send_keys(self.password)
self.driver.find_element(By.XPATH, "//button[normalize-space()='Log in']").click() self.driver.find_element(By.XPATH, "//button[normalize-space()='Log in']").click()
logger.info("Login-Befehl gesendet. Warte auf Weiterleitung...") logger.info("Login-Befehl gesendet. Warte 5 Sekunden, damit die Session etabliert wird.")
# Warten auf ein Element, das nach dem Login sicher da ist (z.B. Dashboard-Link) time.sleep(5)
self.wait.until(EC.visibility_of_element_located((By.XPATH, "//a[contains(@href, '/dashboard')]")))
logger.info("Login erfolgreich und Dashboard erreicht.")
return True return True
except Exception as e: except Exception as e:
logger.critical(f"Login-Prozess fehlgeschlagen.", exc_info=True) logger.critical("Login-Prozess fehlgeschlagen.", exc_info=True)
self._save_debug_artifacts() self._save_debug_artifacts()
return False return False
def navigate_and_load_search(self, search_name): def navigate_and_load_search(self, search_name):
try: try:
logger.info(f"Navigiere direkt zur Target-Seite und lade Suche '{search_name}'...") logger.info(f"Navigiere direkt zur Target-URL und lade die Suche...")
self.driver.get(TempConfig.DEALFRONT_TARGET_URL) self.driver.get(TempConfig.DEALFRONT_TARGET_URL)
self.wait.until(EC.url_contains("/t/prospector/")) self.wait.until(EC.url_contains("/t/prospector/"))
logger.info("Target-Seite erreicht. Klicke auf die Suche: '{}'".format(search_name))
search_item_selector = (By.XPATH, f"//div[contains(@class, 'truncate') and normalize-space()='{search_name}']") search_item_selector = (By.XPATH, f"//div[contains(@class, 'truncate') and normalize-space()='{search_name}']")
self.wait.until(EC.element_to_be_clickable(search_item_selector)).click() self.wait.until(EC.element_to_be_clickable(search_item_selector)).click()
logger.info(f"Suche '{search_name}' geladen. Warte auf das Rendern der Ergebnisse.") logger.info("Suche geladen. Warte auf die Ergebnistabelle.")
first_row_locator = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]") self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "table#t-result-table tbody tr")))
self.wait.until(EC.visibility_of_element_located(first_row_locator))
logger.info("Ergebnisseite erfolgreich geladen.")
return True return True
except Exception as e: except Exception as e:
logger.critical(f"Navigation oder Laden der Suche fehlgeschlagen.", exc_info=True) logger.critical("Navigation oder Laden der Suche fehlgeschlagen.", exc_info=True)
self._save_debug_artifacts() self._save_debug_artifacts()
return False return False
def extract_current_page_results(self): def extract_results_from_page(self):
try: try:
logger.info("Extrahiere Ergebnisse zeilenweise...") logger.info("Extrahiere Daten von der aktuellen Seite...")
results = [] results = []
# Warte auf das Laden der Tabelle rows_selector = (By.XPATH, "//table[@id='t-result-table']/tbody/tr[.//a[contains(@class, 't-highlight-text')]]")
table_rows = self.driver.find_elements(By.CSS_SELECTOR, "table#t-result-table tbody tr[id]") data_rows = self.wait.until(EC.presence_of_all_elements_located(rows_selector))
logger.info(f"{len(table_rows)} Tabellenzeilen gefunden.") logger.info(f"{len(data_rows)} gültige Firmen-Datenzeilen gefunden.")
for row in table_rows: for row in data_rows:
# Firmenname extrahieren
try: try:
company_elem = row.find_element(By.CSS_SELECTOR, "td.sticky-column a.t-highlight-text") name = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text").get_attribute("title").strip()
company_name = company_elem.get_attribute("title").strip() website = row.find_element(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text").text.strip()
results.append({'name': name, 'website': website})
except NoSuchElementException: except NoSuchElementException:
company_name = "N/A" logger.warning("Einzelne Zeile konnte nicht verarbeitet werden, überspringe.")
continue
# Webseite extrahieren (kann fehlen)
try:
website_elem = row.find_element(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text")
website = website_elem.text.strip()
except NoSuchElementException:
website = "N/A"
results.append({'name': company_name, 'website': website})
logger.info(f"Extraktion abgeschlossen. {len(results)} Firmen verarbeitet.")
return results return results
except Exception as e: except Exception as e:
logger.error(f"Fehler bei der zeilenweisen Extraktion: {type(e).__name__}", exc_info=True) logger.error("Fehler bei der Extraktion.", exc_info=True)
self._save_debug_artifacts() self._save_debug_artifacts()
return [] return []
@@ -154,26 +130,16 @@ class DealfrontScraper:
self.driver.quit() self.driver.quit()
if __name__ == "__main__": if __name__ == "__main__":
logger.info("Starte Dealfront Automatisierung - Finaler Workflow") logger.info("Starte Dealfront Automatisierung - Finaler, robuster Workflow")
scraper = None scraper = None
try: try:
scraper = DealfrontScraper() scraper = DealfrontScraper()
if not scraper.driver: if not scraper.login(): raise Exception("Login-Phase fehlgeschlagen")
raise Exception("WebDriver konnte nicht initialisiert werden.") if not scraper.navigate_and_load_search(TempConfig.TARGET_SEARCH_NAME): raise Exception("Navigations-Phase fehlgeschlagen")
if not scraper.login(): companies = scraper.extract_results_from_page()
raise Exception("Login fehlgeschlagen.")
if not scraper.navigate_and_load_search(TempConfig.TARGET_SEARCH_NAME):
raise Exception("Navigation und Laden der Suche fehlgeschlagen.")
companies = scraper.extract_current_page_results()
if companies: if companies:
df = pd.DataFrame(companies) df = pd.DataFrame(companies)
pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 1000)
pd.set_option('display.max_colwidth', -1)
print("\n" + "="*80) print("\n" + "="*80)
print(" EXTRAHIERTE FIRMEN (ERSTE SEITE) ".center(80, "=")) print(" EXTRAHIERTE FIRMEN (ERSTE SEITE) ".center(80, "="))
print("="*80) print("="*80)
@@ -181,7 +147,6 @@ if __name__ == "__main__":
print("="*80 + "\n") print("="*80 + "\n")
else: else:
logger.warning("Keine Firmen konnten extrahiert werden.") logger.warning("Keine Firmen konnten extrahiert werden.")
logger.info("Test erfolgreich abgeschlossen.") logger.info("Test erfolgreich abgeschlossen.")
except Exception as e: except Exception as e:
@@ -189,5 +154,4 @@ if __name__ == "__main__":
finally: finally:
if scraper: if scraper:
scraper.close() scraper.close()
logger.info("Dealfront Automatisierung beendet.") logger.info("Dealfront Automatisierung beendet.")