dealfront_enrichment.py aktualisiert

This commit is contained in:
2025-07-08 17:12:17 +00:00
parent cfea6cc293
commit 668bba36c2

View File

@@ -135,24 +135,26 @@ class DealfrontScraper:
self.driver.implicitly_wait(1)
for i, row in enumerate(rows, 1):
try:
# Firmennamen holen...
name_elem = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text")
company_name = (name_elem.get_attribute("title") or name_elem.text).strip()
# Website aus der dritten Spalte: erst href, dann Text-Fallback
elems = row.find_elements(By.CSS_SELECTOR, "td:nth-of-type(3) a")
if elems:
website = elems[0].get_attribute("href").split("://", 1)[1].rstrip("/")
else:
website = row.find_element(By.CSS_SELECTOR, "td:nth-of-type(3)").text.strip()
results.append({'name': company_name, 'website': website})
except NoSuchElementException:
logger.warning(f"Zeile {i}: Name oder Webseite nicht extrahierbar. Überspringe.")
# Name per find_elements (kein Exception-Overhead)
name_elems = row.find_elements(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text")
if not name_elems:
logger.warning(f"Zeile {i}: Kein Name-Element gefunden. Überspringe.")
continue
name_elem = name_elems[0]
company_name = (name_elem.get_attribute("title") or name_elem.text).strip()
# Implicit-Wait wiederherstellen (z. B. 10 Sekunden)
# Website per find_elements
web_elems = row.find_elements(By.CSS_SELECTOR, "td:nth-of-type(3) a")
if web_elems:
website = web_elems[0].get_attribute("href").split("://", 1)[1].rstrip("/")
else:
# no-link-Fallback: Text aus td
text_elems = row.find_elements(By.CSS_SELECTOR, "td:nth-of-type(3)")
website = text_elems[0].text.strip() if text_elems else ""
results.append({'name': company_name, 'website': website})
# Implicit-Wait wiederherstellen (empfehlenswert 10 s)
self.driver.implicitly_wait(10)
logger.info(f"Extraktion abgeschlossen. {len(results)} Firmen gefunden.")