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
2025-04-03 14:44:22 +00:00
parent 80867d97cd
commit e2072bfb8b
1 changed files with 41 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
brancheneinstufung.py
View File

@@ -720,21 +720,22 @@ class DataProcessor:
break
self._process_single_row(i, row)
rows_processed += 1
def _process_single_row(self, row_num, row_data, force_all=False, process_wiki=True, process_chatgpt=True):
company_name = row_data[1] if len(row_data) > 1 else ""
website = row_data[2] if len(row_data) > 2 else ""
wiki_update_range = f"K{row_num}:Q{row_num}"
dt_wiki_range = f"AM{row_num}" # Wikipedia Timestamp
dt_chat_range = f"AN{row_num}" # ChatGPT Timestamp
dt_last_range = f"AN{row_num}" # Falls benötigt, hier können Sie noch "Timestamp letzte Prüfung" anpassen
ver_range = f"AO{row_num}" # Version
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# Wikipedia-Teil (Spalte AM) – nur ausführen, wenn kein Wiki-Timestamp vorhanden oder force_all True oder explizit process_wiki=True
wiki_data = None
if force_all or process_wiki or (len(row_data) <= 38 or row_data[38].strip() == ""):
if len(row_data) > 11 and row_data[10].strip() not in ["", "k.A."]:
def _process_single_row(self, row_num, row_data, force_all=False, process_wiki=True, process_chatgpt=True):
company_name = row_data[1] if len(row_data) > 1 else ""
website = row_data[2] if len(row_data) > 2 else ""
wiki_update_range = f"K{row_num}:Q{row_num}"
dt_wiki_range = f"AM{row_num}" # Wikipedia Timestamp
dt_chat_range = f"AN{row_num}" # ChatGPT Timestamp
ver_range = f"AO{row_num}" # Version
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
# Wikipedia-Teil: Wird ausgeführt, wenn process_wiki True ist oder force_all aktiv ist.
if force_all or process_wiki:
# Hier zuerst prüfen, ob wir bereits einen Wiki-Timestamp haben (Spalte AM)
if len(row_data) <= 38 or row_data[38].strip() == "":
# Führe die Wikipedia-Auswertung durch
if len(row_data) > 10 and row_data[10].strip() not in ["", "k.A."]:
wiki_url = row_data[10].strip()
try:
wiki_data = self.wiki_scraper.extract_company_data(wiki_url)
@@ -764,39 +765,47 @@ class DataProcessor:
]
self.sheet_handler.sheet.update(values=[wiki_values], range_name=wiki_update_range)
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_wiki_range)
# ChatGPT-Bewertung (Spalte AN) – nur ausführen, wenn kein ChatGPT-Timestamp vorhanden oder force_all/ process_chatgpt True
if force_all or process_chatgpt or (len(row_data) <= 39 or row_data[39].strip() == ""):
else:
debug_print(f"Zeile {row_num}: Wikipedia-Timestamp bereits gesetzt – überspringe Wiki-Auswertung.")
# ChatGPT-Teil: Wird nur ausgeführt, wenn process_chatgpt True ist oder force_all aktiv ist.
if force_all or process_chatgpt:
# Hier prüfen, ob bereits ein ChatGPT-Timestamp in Spalte AN vorliegt
if len(row_data) <= 39 or row_data[39].strip() == "":
crm_umsatz = row_data[8] if len(row_data) > 8 else "k.A."
abgleich_result = compare_umsatz_values(crm_umsatz, wiki_data.get('umsatz', 'k.A.') if wiki_data else "k.A.")
abgleich_result = compare_umsatz_values(crm_umsatz, wiki_data.get('umsatz', 'k.A.') if 'wiki_data' in locals() else "k.A.")
self.sheet_handler.sheet.update(values=[[abgleich_result]], range_name=f"AG{row_num}")
crm_data = ";".join(row_data[1:10])
wiki_data_str = ";".join(row_data[11:17])
valid_result = validate_article_with_chatgpt(crm_data, wiki_data_str)
self.sheet_handler.sheet.update(values=[[valid_result]], range_name=f"R{row_num}")
fsm_result = evaluate_fsm_suitability(company_name, wiki_data if wiki_data else {})
fsm_result = evaluate_fsm_suitability(company_name, wiki_data if 'wiki_data' in locals() else {})
self.sheet_handler.sheet.update(values=[[fsm_result["suitability"]]], range_name=f"Y{row_num}")
self.sheet_handler.sheet.update(values=[[fsm_result["justification"]]], range_name=f"Z{row_num}")
st_estimate = evaluate_servicetechnicians_estimate(company_name, wiki_data if wiki_data else {})
st_estimate = evaluate_servicetechnicians_estimate(company_name, wiki_data if 'wiki_data' in locals() else {})
self.sheet_handler.sheet.update(values=[[st_estimate]], range_name=f"AD{row_num}")
internal_value = row_data[7] if len(row_data) > 7 else "k.A."
internal_category = map_internal_technicians(internal_value) if internal_value != "k.A." else "k.A."
if internal_category != "k.A." and st_estimate != internal_category:
explanation = evaluate_servicetechnicians_explanation(company_name, st_estimate, wiki_data if wiki_data else {})
explanation = evaluate_servicetechnicians_explanation(company_name, st_estimate, wiki_data if 'wiki_data' in locals() else {})
discrepancy = explanation
else:
discrepancy = "ok"
self.sheet_handler.sheet.update(values=[[discrepancy]], range_name=f"AE{row_num}")
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_chat_range)
# Letzten Timestamp und Version aktualisieren (Spalte AO)
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"AO{row_num}")
debug_print(f"✅ Aktualisiert: URL: {(wiki_data.get('url', 'k.A.') if wiki_data else 'k.A.')}, "
f"Branche: {(wiki_data.get('branche', 'k.A.') if wiki_data else 'k.A.')}, "
f"Umsatz-Abgleich: {abgleich_result if 'abgleich_result' in locals() else 'k.A.'}, "
f"Validierung: {valid_result if 'valid_result' in locals() else 'k.A.'}, "
f"FSM: {fsm_result['suitability'] if 'fsm_result' in locals() else 'k.A.'}, "
f"Servicetechniker-Schätzung: {st_estimate if 'st_estimate' in locals() else 'k.A.'}")
time.sleep(Config.RETRY_DELAY)
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AN{row_num}")
else:
debug_print(f"Zeile {row_num}: ChatGPT-Timestamp bereits gesetzt – überspringe ChatGPT-Auswertung.")
# Aktualisiere letzten Timestamp und Version (Spalte AO)
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"AO{row_num}")
debug_print(f"✅ Aktualisiert: URL: {(wiki_data.get('url', 'k.A.') if 'wiki_data' in locals() else 'k.A.')}, "
f"Branche: {(wiki_data.get('branche', 'k.A.') if 'wiki_data' in locals() else 'k.A.')}, "
f"Umsatz-Abgleich: {abgleich_result if 'abgleich_result' in locals() else 'k.A.'}, "
f"Validierung: {valid_result if 'valid_result' in locals() else 'k.A.'}, "
f"FSM: {fsm_result['suitability'] if 'fsm_result' in locals() else 'k.A.'}, "
f"Servicetechniker-Schätzung: {st_estimate if 'st_estimate' in locals() else 'k.A.'}")
time.sleep(Config.RETRY_DELAY)
# ==================== NEUER MODUS 6: CONTACT RESEARCH (via SerpAPI) ====================
def process_contact_research():