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
2025-04-08 19:37:22 +00:00
parent 4b374192b1
commit 1d11ed3ef0
1 changed files with 68 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

78
brancheneinstufung.py
View File

@@ -1272,12 +1272,77 @@ def count_linkedin_contacts(company_name, website, position_query):
debug_print(f"Fehler bei der SerpAPI-Suche (Count): {e}")
return 0
# ==================== MAIN-FUNKTION ====================
# ----------------- DataProcessor-Klasse inklusive neuer SERP-API Website Lookup-Methode -----------------
class DataProcessor:
def __init__(self):
self.sheet_handler = GoogleSheetHandler()
self.wiki_scraper = WikipediaScraper()
def process_serp_website_lookup(self):
debug_print("Starte SERP-API Website Lookup für alle Zeilen ohne CRM-Website (Spalte D).")
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
# Prüfe, ob in Spalte D (Index 3) bereits ein Website-Wert vorhanden ist
current_website = row[3] if len(row) > 3 else ""
if current_website.strip() == "":
company_name = row[1] if len(row) > 1 else ""
new_website = serp_website_lookup(company_name)
if new_website != "k.A.":
self.sheet_handler.sheet.update(values=[[new_website]], range_name=f"D{i}")
debug_print(f"Zeile {i}: Neue Website gefunden und in Spalte D eingetragen: {new_website}")
else:
debug_print(f"Zeile {i}: Keine Website gefunden für {company_name}.")
time.sleep(Config.RETRY_DELAY)
else:
debug_print(f"Zeile {i}: CRM-Website bereits vorhanden, überspringe.")
def process_rows(self, num_rows=None):
global MODE
if MODE == "1":
self.process_rows_complete() # Vollständige Verarbeitung (sofern implementiert)
elif MODE == "11":
# Re-Evaluation markierter Zeilen (nur "x" in Spalte A)
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
if row[0].strip().lower() == "x":
self._process_single_row(i, row)
elif MODE == "21":
# Website-Scraping Testmodus: Nur Website-Rohtext & Zusammenfassung extrahieren
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
self._process_single_row(i, row, process_wiki=False, process_chatgpt=False)
elif MODE == "22":
# SERP-API Website Lookup: Füllt Spalte D, wenn leer, mit dem SERP-Ergebnis
self.process_serp_website_lookup()
elif MODE == "31":
# Nur ChatGPT-Auswertung: Alle ChatGPT-Routinen werden ausgeführt (ohne Wiki und Website)
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
self._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
elif MODE == "41":
# Nur Wikipedia-Scraping
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
self._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
elif MODE == "51":
process_verification_only()
elif MODE == "6":
process_contact_research()
elif MODE == "8":
process_batch_token_count()
else:
start_index = self.sheet_handler.get_start_index()
print(f"Starte bei Zeile {start_index+1}")
rows_processed = 0
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
if i < start_index:
continue
if num_rows is not None and rows_processed >= num_rows:
break
self._process_single_row(i, row)
rows_processed += 1
# ----------------- Main-Funktion -----------------
def main():
global MODE, LOG_FILE
print("Bitte wählen Sie den Betriebsmodus:")
print("1: Vollständige Verarbeitung (alle Funktionen)")
print("11: Re-Evaluation markierter Zeilen (nur 'x' in Spalte A)")
print("11: Re-Evaluation markierter Zeilen (nur 'x' in Spalte A)")
print("21: Website-Scraping Testmodus (nur Website-Rohtext & Zusammenfassung)")
print("22: SERP-API Website Lookup (nur Website-Daten ermitteln)")
print("31: Nur ChatGPT-Auswertung (alle ChatGPT-Routinen)")
@@ -1301,30 +1366,23 @@ def main():
if MODE == "1":
dp.process_rows() # Vollständige Verarbeitung
elif MODE == "11":
# Re-Evaluation markierter Zeilen (nur "x" in Spalte A)
for i, row in enumerate(dp.sheet_handler.sheet_values[1:], start=2):
if row[0].strip().lower() == "x":
dp._process_single_row(i, row)
elif MODE == "21":
# Website-Scraping Testmodus: Nur Website-Rohtext & Zusammenfassung extrahieren
for i, row in enumerate(dp.sheet_handler.sheet_values[1:], start=2):
dp._process_single_row(i, row, process_wiki=False, process_chatgpt=False)
elif MODE == "22":
# SERP-API Website Lookup: Überprüft jede Zeile, ob in Spalte D keine Website vorhanden ist,
# und sucht dann via SERP-API nach einer Website, die in Spalte D eingetragen wird.
dp.process_serp_website_lookup()
elif MODE == "31":
# Nur ChatGPT-Auswertung: Alle ChatGPT-Routinen (ohne Wikipedia und Website) werden ausgeführt.
for i, row in enumerate(dp.sheet_handler.sheet_values[1:], start=2):
dp._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
elif MODE == "41":
# Nur Wikipedia-Scraping
for i, row in enumerate(dp.sheet_handler.sheet_values[1:], start=2):
dp._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
elif MODE == "51":
process_verification_only()
elif MODE == "6":
# Contact Research (LinkedIn)
process_contact_research()
elif MODE == "8":
process_batch_token_count()
@@ -1335,7 +1393,7 @@ def main():
for i, row in enumerate(dp.sheet_handler.sheet_values[1:], start=2):
if i < start_index:
continue
if rows_processed >= 1: # Hier kann die Anzahl angepasst werden.
if rows_processed >= 1:
break
dp._process_single_row(i, row)
rows_processed += 1