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
2025-04-09 09:19:40 +00:00
parent 55666b0603
commit 6919f3454c
1 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
brancheneinstufung.py
View File

@@ -1160,7 +1160,7 @@ def _process_single_row(self, row_num, row_data, process_wiki=True, process_chat
# Hole den Firmennamen aus Spalte B (Index 1) # Hole den Firmennamen aus Spalte B (Index 1)
company_name = row_data[1] if len(row_data) > 1 else "" company_name = row_data[1] if len(row_data) > 1 else ""
# Hole die CRM-Website (Spalte D, Index 3). Falls keine Website vorhanden ist, führe den SERP-API Lookup durch. # Hole die CRM-Website aus Spalte D (Index 3). Falls keine Website vorhanden ist, führe SERP-API Lookup durch.
website_url = row_data[3] if len(row_data) > 3 else "" website_url = row_data[3] if len(row_data) > 3 else ""
if website_url.strip() == "" or website_url.strip().lower() == "k.a.": if website_url.strip() == "" or website_url.strip().lower() == "k.a.":
new_website = serp_website_lookup(company_name) new_website = serp_website_lookup(company_name)
@@ -1174,10 +1174,11 @@ def _process_single_row(self, row_num, row_data, process_wiki=True, process_chat
else: else:
debug_print(f"Zeile {row_num}: Keine Website gefunden für {company_name}.") debug_print(f"Zeile {row_num}: Keine Website gefunden für {company_name}.")
# Website-Scraping: Für jeden Account soll die Website gescrapt werden. # Website-Scraping:
# Das Ergebnis (Title, Description, H1, H2, H3) wird in Spalte AQ ausgegeben. # Hier soll die Website gescrapt werden – *unabhängig* von jeglichen Flaggen in Spalte A.
website_details = "k.A." website_details = "k.A."
if website_url.strip() != "" and website_url.strip().lower() != "k.a.": if website_url.strip() != "" and website_url.strip().lower() != "k.a.":
# Rufe scrape_website_details auf, um Title, Description, H1, H2, H3 zu extrahieren.
website_details = scrape_website_details(website_url) website_details = scrape_website_details(website_url)
debug_print(f"Zeile {row_num}: Gescrappte Website-Details (erste 100 Zeichen): {website_details[:100]}") debug_print(f"Zeile {row_num}: Gescrappte Website-Details (erste 100 Zeichen): {website_details[:100]}")
try: try:
@@ -1279,6 +1280,7 @@ def _process_single_row(self, row_num, row_data, process_wiki=True, process_chat
time.sleep(Config.RETRY_DELAY) time.sleep(Config.RETRY_DELAY)
# ==================== ALIGNMENT DEMO FÜR HAUPTBLATT UND CONTACTS ==================== # ==================== ALIGNMENT DEMO FÜR HAUPTBLATT UND CONTACTS ====================
def alignment_demo_full(): def alignment_demo_full():
alignment_demo(GoogleSheetHandler().sheet) alignment_demo(GoogleSheetHandler().sheet)