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

Erste funktionierende Version!

Browse Source
This commit is contained in:
Floke
2025-07-08 15:48:44 +00:00
parent 9481297b33
commit 8ec5ce77f7
1 changed files with 11 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
dealfront_enrichment.py
View File

@@ -133,8 +133,17 @@ class DealfrontScraper:
logger.info(f"{len(rows)} Firmen-Datenzeilen zur Verarbeitung gefunden.") logger.info(f"{len(rows)} Firmen-Datenzeilen zur Verarbeitung gefunden.")
for i, row in enumerate(rows, 1): for i, row in enumerate(rows, 1):
try: try:
company_name = row.find_element(By.CSS_SELECTOR, ".sticky-column a.t-highlight-text").get_attribute("title").strip() # Name: erst title, dann Fallback auf Text
website = row.find_element(By.CSS_SELECTOR, "a.text-gray-400.t-highlight-text").text.strip() 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
try:
website_elem = row.find_element(By.XPATH, ".//td[2]//a")
website = website_elem.text.strip()
except NoSuchElementException:
website = row.find_element(By.XPATH, ".//td[2]").text.strip()
results.append({'name': company_name, 'website': website}) results.append({'name': company_name, 'website': website})
except NoSuchElementException: except NoSuchElementException:
logger.warning(f"Zeile {i}: Name oder Webseite nicht extrahierbar. Überspringe.") logger.warning(f"Zeile {i}: Name oder Webseite nicht extrahierbar. Überspringe.")