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 17:52:35 +00:00
parent fdc5d75944
commit a2b60e2137
1 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
dealfront_enrichment.py
View File

@@ -113,7 +113,7 @@ class DealfrontScraper:
return False
def extract_current_page_results(self):
# 1) Warte auf erste Ergebniszeile (bis zu 20 Sek.)
# 1) Warten bis mindestens eine Ergebnis-Zeile sichtbar ist
rows_locator = (By.CSS_SELECTOR, "table#t-result-table tbody tr[id]")
WebDriverWait(self.driver, 20).until(
EC.visibility_of_element_located(rows_locator)
@@ -124,24 +124,24 @@ class DealfrontScraper:
results = []
for i, row in enumerate(rows, 1):
# 2) Name: erstes Profil-Link (<a href="/h/company/...">)
name_links = row.find_elements(
By.XPATH,
".//td[contains(@class,'sticky-column')]//a[contains(@href,'/h/company/')]"
# Name: <div class="t-highlight-text t-highlight-text-product" title="...">
name_divs = row.find_elements(
By.CSS_SELECTOR,
"div.t-highlight-text.t-highlight-text-product"
)
if not name_links:
logger.warning(f"Zeile {i}: Kein Name-Link gefunden. Überspringe.")
if not name_divs:
logger.warning(f"Zeile {i}: Kein Name-Element gefunden. Überspringe.")
continue
name_elem = name_links[0]
company_name = (name_elem.get_attribute("title") or name_elem.text).strip()
name_elem = name_divs[0]
company_name = (name_elem.get_attribute("title") or name_elem.text).strip() # :contentReference[oaicite:0]{index=0}
# 3) Website: erster externer Link (target="_blank")
ext_links = row.find_elements(By.XPATH, ".//a[@target='_blank']")
# Website: externer Link (target="_blank") in der dritten Spalte
ext_links = row.find_elements(By.CSS_SELECTOR, "td:nth-of-type(3) a[target='_blank']")
if ext_links:
href = ext_links[0].get_attribute("href")
website = href.replace("https://", "").replace("http://", "").rstrip("/")
else:
# Fallback: Text der 3. <td>
# Fallback: reiner Text in td[3]
cells = row.find_elements(By.TAG_NAME, "td")
website = cells[2].text.strip() if len(cells) >= 3 else ""