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

dealfront_enrichment.py aktualisiert

Browse Source
This commit is contained in:
Floke
2025-07-11 07:26:27 +00:00
parent 858553ea78
commit 2d9a630878
1 changed files with 68 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

144
dealfront_enrichment.py
View File

@@ -11,21 +11,21 @@ from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, NoSuchElementException from selenium.common.exceptions import TimeoutException, NoSuchElementException
# --- Konfiguration --- # --- Konfiguration ---
class TempConfig: class Config:
DEALFRONT_LOGIN_URL = "https://app.dealfront.com/login" LOGIN_URL = "https://app.dealfront.com/login"
DEALFRONT_TARGET_URL = "https://app.dealfront.com/t/prospector/companies" TARGET_URL = "https://app.dealfront.com/t/prospector/companies"
TARGET_SEARCH_NAME = "Facility Management" # BITTE AN IHRE SUCHE ANPASSEN SEARCH_NAME = "Facility Management" # <-- PASSEN SIE DIES AN IHRE GESPEICHERTE SUCHE AN
DEALFRONT_CREDENTIALS_FILE = "/app/dealfront_credentials.json" CREDENTIALS_FILE = "/app/dealfront_credentials.json"
OUTPUT_DIR = "/app/output"
# --- Logging Setup --- # --- Logging Setup ---
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.INFO) # Selenium-Logs auf INFO reduzieren logging.getLogger("selenium.webdriver.remote").setLevel(logging.WARNING) # Reduziert Selenium-Spam
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
os.makedirs(OUTPUT_DIR, exist_ok=True) os.makedirs(Config.OUTPUT_DIR, exist_ok=True)
log_filepath = os.path.join(OUTPUT_DIR, f"dealfront_run_{time.strftime('%Y%m%d-%H%M%S')}.log") log_filepath = os.path.join(Config.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.setFormatter(logging.Formatter(LOG_FORMAT)) file_handler.setFormatter(logging.Formatter(LOG_FORMAT))
logging.getLogger().addHandler(file_handler) logging.getLogger().addHandler(file_handler)
@@ -45,101 +45,93 @@ class DealfrontScraper:
except Exception as e: except Exception as e:
logger.critical("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, 30) self.wait = WebDriverWait(self.driver, 30)
self.username, self.password = self._load_credentials() self.username, self.password = self._load_credentials()
# FAIL-FAST: Sofortiger Abbruch, wenn Credentials fehlen
if not self.username or not self.password:
raise ValueError("Benutzername oder Passwort konnten nicht aus der Credentials-Datei geladen werden. Breche ab.")
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(Config.CREDENTIALS_FILE, 'r', encoding='utf-8') as f:
return json.load(f).get("username"), json.load(f).get("password") creds = json.load(f)
except Exception: return creds.get("username"), creds.get("password")
logger.error(f"Credentials-Datei {TempConfig.DEALFRONT_CREDENTIALS_FILE} nicht gefunden oder fehlerhaft.") except Exception as e:
logger.error(f"Credentials-Datei {Config.CREDENTIALS_FILE} 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_path = os.path.join(OUTPUT_DIR, f"error_{timestamp}.png") screenshot_path = os.path.join(Config.OUTPUT_DIR, f"error_{timestamp}.png")
html_path = os.path.join(OUTPUT_DIR, f"error_{timestamp}.html") html_path = os.path.join(Config.OUTPUT_DIR, f"error_{timestamp}.html")
self.driver.save_screenshot(screenshot_path) self.driver.save_screenshot(screenshot_path)
logger.error(f"Debug-Screenshot gespeichert: {screenshot_path}")
with open(html_path, "w", encoding="utf-8") as f: with open(html_path, "w", encoding="utf-8") as f:
f.write(self.driver.page_source) f.write(self.driver.page_source)
logger.error(f"Debug-Artefakte gespeichert: {screenshot_path}, {html_path}") logger.error(f"Debug-HTML-Quellcode gespeichert: {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}")
def login(self): def run(self):
try: # 1. LOGIN
logger.info(f"Navigiere zur Login-Seite: {TempConfig.DEALFRONT_LOGIN_URL}") logger.info(f"Navigiere zur Login-Seite: {Config.LOGIN_URL}")
self.driver.get(TempConfig.DEALFRONT_LOGIN_URL) self.driver.get(Config.LOGIN_URL)
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 5 Sekunden, damit die Session etabliert wird.") logger.info("Login-Befehl gesendet. Kurze Pause für die Weiterleitung.")
time.sleep(5) time.sleep(5)
return True
except Exception as e:
logger.critical("Login-Prozess fehlgeschlagen.", exc_info=True)
self._save_debug_artifacts()
return False
def navigate_and_load_search(self, search_name): # 2. NAVIGATION & SUCHE LADEN
try: logger.info(f"Navigiere direkt zur Target-Seite und lade die Suche: '{Config.SEARCH_NAME}'")
logger.info(f"Navigiere direkt zur Target-URL und lade die Suche...") self.driver.get(Config.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()='{Config.SEARCH_NAME}']")
self.wait.until(EC.element_to_be_clickable(search_item_selector)).click()
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()
logger.info("Suche geladen. Warte auf die Ergebnistabelle.") # 3. ERGEBNISSE EXTRAHIEREN
self.wait.until(EC.visibility_of_element_located((By.CSS_SELECTOR, "table#t-result-table tbody tr"))) logger.info("Suche geladen. Extrahiere Ergebnisse der ersten Seite.")
return True results_table_selector = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]")
except Exception as e: self.wait.until(EC.presence_of_element_located(results_table_selector))
logger.critical("Navigation oder Laden der Suche fehlgeschlagen.", exc_info=True)
self._save_debug_artifacts() data_rows = self.driver.find_elements(By.XPATH, "//tr[.//a[contains(@class, 't-highlight-text')]]")
return False logger.info(f"{len(data_rows)} gültige Datenzeilen gefunden.")
def extract_results_from_page(self): companies = []
try: for row in data_rows:
logger.info("Extrahiere Daten von der aktuellen Seite...") try:
results = [] name = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text").get_attribute("title").strip()
rows_selector = (By.XPATH, "//table[@id='t-result-table']/tbody/tr[.//a[contains(@class, 't-highlight-text')]]") website = row.find_element(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text").text.strip()
data_rows = self.wait.until(EC.presence_of_all_elements_located(rows_selector)) companies.append({'name': name, 'website': website})
logger.info(f"{len(data_rows)} gültige Firmen-Datenzeilen gefunden.") except NoSuchElementException:
continue
for row in data_rows:
try: return companies
name = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text").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:
logger.warning("Einzelne Zeile konnte nicht verarbeitet werden, überspringe.")
continue
return results
except Exception as e:
logger.error("Fehler bei der Extraktion.", exc_info=True)
self._save_debug_artifacts()
return []
def close(self): def close(self):
if self.driver: if self.driver:
logger.info("Schließe den WebDriver.")
self.driver.quit() self.driver.quit()
logger.info("WebDriver geschlossen.")
if __name__ == "__main__": if __name__ == "__main__":
logger.info("Starte Dealfront Automatisierung - Finaler, robuster Workflow")
scraper = None scraper = None
try: try:
scraper = DealfrontScraper() scraper = DealfrontScraper()
if not scraper.login(): raise Exception("Login-Phase fehlgeschlagen") company_list = scraper.run()
if not scraper.navigate_and_load_search(TempConfig.TARGET_SEARCH_NAME): raise Exception("Navigations-Phase fehlgeschlagen")
companies = scraper.extract_results_from_page() if company_list:
if companies: df = pd.DataFrame(company_list)
df = pd.DataFrame(companies) pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 120)
pd.set_option('display.max_colwidth', None)
print("\n" + "="*80) print("\n" + "="*80)
print(" EXTRAHIERTE FIRMEN (ERSTE SEITE) ".center(80, "=")) print(" EXTRAHIERTE FIRMEN (ERSTE SEITE) ".center(80, "="))
print("="*80) print("="*80)
@@ -147,10 +139,10 @@ 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("Workflow erfolgreich abgeschlossen.")
except Exception as e: except Exception as e:
logger.critical(f"Ein kritischer Fehler ist im Hauptprozess aufgetreten: {e}") logger.critical(f"Ein kritischer Fehler ist im Hauptprozess aufgetreten: {e}", exc_info=False)
finally: finally:
if scraper: if scraper:
scraper.close() scraper.close()