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
2025-07-08 11:52:21 +00:00
parent 8d35722c0d
commit 25f6fc85a9
1 changed files with 33 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
dealfront_enrichment.py
View File

@@ -22,7 +22,10 @@ class TempConfig:
# ============================================================================== # ==============================================================================
OUTPUT_DIR = "/app/output" OUTPUT_DIR = "/app/output"
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s', force=True) # Logging-Konfiguration
LOG_LEVEL = logging.INFO
LOG_FORMAT = '%(asctime)s - %(levelname)-8s - %(name)-25s - %(message)s' # Diese Zeile hat gefehlt
logging.basicConfig(level=LOG_LEVEL, format=LOG_FORMAT, force=True, handlers=[logging.StreamHandler()])
logging.getLogger("selenium").setLevel(logging.WARNING) logging.getLogger("selenium").setLevel(logging.WARNING)
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@@ -111,28 +114,41 @@ class DealfrontScraper:
return False return False
def extract_current_page_results(self): def extract_current_page_results(self):
# ... (Diese Methode bleibt unverändert) ... """
Extrahiert Firmennamen und Webseiten direkt von der Seite
mithilfe der verifizierten CSS-Selektoren.
"""
try: try:
logger.info("Extrahiere Ergebnisse von der aktuellen Seite...") logger.info("Extrahiere Ergebnisse mit direkten CSS-Selektoren...")
results = [] results = []
rows_selector = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]")
self.wait.until(EC.presence_of_element_located(rows_selector)) # Warten, bis das erste Firmenelement vorhanden ist.
company_name_selector = ".sticky-column a.t-highlight-text"
logger.info(f"Warte auf das erste Firmenelement mit Selektor: '{company_name_selector}'")
self.wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, company_name_selector)))
time.sleep(3) time.sleep(3)
rows = self.driver.find_elements(*rows_selector)
if not rows: # Extraktion aller Elemente
logger.warning("Keine Ergebniszeilen (tr[id]) gefunden.") company_elements = self.driver.find_elements(By.CSS_SELECTOR, company_name_selector)
website_elements = self.driver.find_elements(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text")
logger.info(f"{len(company_elements)} Firmennamen und {len(website_elements)} Webseiten-Elemente gefunden.")
num_results = min(len(company_elements), len(website_elements))
if num_results == 0:
logger.warning("Keine Firmen oder Webseiten gefunden.")
self._save_debug_artifacts()
return [] return []
logger.info(f"{len(rows)} Firmen-Datenzeilen zur Verarbeitung gefunden.")
for i, row in enumerate(rows, 1): for i in range(num_results):
try: company_name = company_elements[i].get_attribute("title").strip()
company_name = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text").get_attribute("title").strip() website = website_elements[i].text.strip()
website = row.find_element(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text").text.strip() if company_name and website:
results.append({'name': company_name, 'website': website}) results.append({'name': company_name, 'website': website})
except NoSuchElementException:
logger.warning(f"Zeile {i}: Name oder Webseite nicht extrahierbar. Überspringe.") logger.info(f"Extraktion abgeschlossen. {len(results)} Firmen erfolgreich zugeordnet.")
continue
logger.info(f"Extraktion abgeschlossen. {len(results)} Firmen gefunden.")
return results return results
except Exception as e: except Exception as e:
logger.error(f"Schwerwiegender Fehler bei der Extraktion: {type(e).__name__}", exc_info=True) logger.error(f"Schwerwiegender Fehler bei der Extraktion: {type(e).__name__}", exc_info=True)
self._save_debug_artifacts() self._save_debug_artifacts()