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

vorletzte Version war bisher die beste

Browse Source
This commit is contained in:
Floke
2025-07-08 15:58:36 +00:00
parent 8ec5ce77f7
commit 0daf868009
1 changed files with 12 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
dealfront_enrichment.py
View File

@@ -126,23 +126,27 @@ class DealfrontScraper:
rows_selector = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]")
self.wait.until(EC.presence_of_element_located(rows_selector))
time.sleep(3)
rows_selector = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]")
WebDriverWait(self.driver, 15).until(
EC.number_of_elements_to_be_more_than(rows_selector, 0)
)
rows = self.driver.find_elements(*rows_selector)
if not rows:
logger.warning("Keine Ergebniszeilen (tr[id]) gefunden.")
return []
logger.info(f"{len(rows)} Firmen-Datenzeilen zur Verarbeitung gefunden.")
for i, row in enumerate(rows, 1):
try:
# Name: erst title, dann Fallback auf Text
# 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: erst Link in td[2], sonst reiner Zellen-Text
# Website aus der zweiten Spalte: erst href, dann Text-Fallback
try:
website_elem = row.find_element(By.XPATH, ".//td[2]//a")
website = website_elem.text.strip()
website_elem = row.find_element(By.CSS_SELECTOR, "td:nth-of-type(2) a")
# HREF bereinigen (ohne https://)
website = website_elem.get_attribute("href").split("://")[-1].strip("/")
except NoSuchElementException:
website = row.find_element(By.XPATH, ".//td[2]").text.strip()
website = row.find_element(By.CSS_SELECTOR, "td:nth-of-type(2)").text.strip()
results.append({'name': company_name, 'website': website})
except NoSuchElementException: