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

bugfix

Browse Source
This commit is contained in:
Floke
2025-04-18 06:30:48 +00:00
parent 45441ae4d7
commit d422260fff
1 changed files with 25 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
brancheneinstufung.py
View File

@@ -3367,15 +3367,33 @@ class DataProcessor:
debug_print(f" -> Nutze vorhandene URL aus Spalte M: {url_to_parse}") debug_print(f" -> Nutze vorhandene URL aus Spalte M: {url_to_parse}")
new_wiki_data_extracted = self.wiki_scraper.extract_company_data(url_to_parse) new_wiki_data_extracted = self.wiki_scraper.extract_company_data(url_to_parse)
else: else:
# --- Nur wenn M leer/ungültig ist, starte die Suche ---
debug_print(f" -> Spalte M ('{url_to_parse}') ungültig/leer. Starte Wiki-Suche...") debug_print(f" -> Spalte M ('{url_to_parse}') ungültig/leer. Starte Wiki-Suche...")
# ... (Suchlogik wie zuvor, nutzt crm_wiki_url als Fallback) ...
valid_crm_wiki_url = crm_wiki_url if crm_wiki_url and crm_wiki_url.strip() not in ["", "k.A."] else None valid_crm_wiki_url = crm_wiki_url if crm_wiki_url and crm_wiki_url.strip() not in ["", "k.A."] else None
article_page = None; current_website = website_url if website_url and website_url != 'k.A.' else original_website article_page = None # Initialisiere article_page
if valid_crm_wiki_url: # ... (Prüfe CRM Vorschlag) ... current_website_for_validation = website_url if website_url and website_url != 'k.A.' else original_website
else: article_page = self.wiki_scraper.search_company_article(company_name, current_website)
if article_page: new_wiki_data_extracted = self.wiki_scraper.extract_company_data(article_page.url) # --- KORREKTE EINRÜCKUNG HIER ---
else: new_wiki_data_extracted = {'url': 'Kein Artikel gefunden', 'first_paragraph': 'k.A.', 'branche': 'k.A.', 'umsatz': 'k.A.', 'mitarbeiter': 'k.A.', 'categories': 'k.A.'} if valid_crm_wiki_url:
debug_print(f" -> Prüfe CRM Vorschlag L: {valid_crm_wiki_url}")
page = self.wiki_scraper._fetch_page_content(valid_crm_wiki_url.split('/')[-1])
if page and self.wiki_scraper._validate_article(page, company_name, current_website_for_validation):
article_page = page
else:
debug_print(f" -> CRM Vorschlag L nicht validiert. Starte Suche...")
# Wenn CRM-Vorschlag nicht validiert, Suche trotzdem starten
article_page = self.wiki_scraper.search_company_article(company_name, current_website_for_validation)
else:
# --- DIESE ZEILE IST JETZT KORREKT EINGERÜCKT UNTER DEM ELSE ---
debug_print(f" -> Kein CRM Vorschlag L. Starte Suche...")
article_page = self.wiki_scraper.search_company_article(company_name, current_website_for_validation)
# --- ENDE KORREKTE EINRÜCKUNG ---
if article_page:
debug_print(f" -> Artikel gefunden durch Suche: {article_page.url}")
new_wiki_data_extracted = self.wiki_scraper.extract_company_data(article_page.url)
else:
debug_print(f" -> Kein passender Wikipedia Artikel durch Suche gefunden.")
new_wiki_data_extracted = {'url': 'Kein Artikel gefunden', 'first_paragraph': 'k.A.', 'branche': 'k.A.', 'umsatz': 'k.A.', 'mitarbeiter': 'k.A.', 'categories': 'k.A.'}
# --- WICHTIG: Überschreibe wiki_data mit den NEUEN Ergebnissen --- # --- WICHTIG: Überschreibe wiki_data mit den NEUEN Ergebnissen ---
if new_wiki_data_extracted: if new_wiki_data_extracted: