v1.3.12: Neuer Modus 51 – Nur Verifizierung bis Spalte Y, Spalten um +1 verschoben
- Neuer Modus 51 implementiert, der ausschließlich die Wikipedia-Daten extrahiert und die Brancheneinordnung (bis Spalte Y) vornimmt. - FSM- und Servicetechniker-Bewertungen werden in diesem Modus übersprungen. - Alle Spalten wurden um +1 verschoben; Kurzform des Firmennamens ist nun in Spalte C. - Update-Aufrufe wurden entsprechend angepasst.
This commit is contained in:
@@ -14,7 +14,7 @@ import csv
|
|||||||
|
|
||||||
# ==================== KONFIGURATION ====================
|
# ==================== KONFIGURATION ====================
|
||||||
class Config:
|
class Config:
|
||||||
VERSION = "v1.3.11" # v1.3.11: Spalten um +1 verschoben, Kurzform in Spalte C; alle Referenzen angepasst.
|
VERSION = "v1.3.12" # v1.3.12: Neuer Modus 51 implementiert (nur Verifizierung bis Spalte Y)
|
||||||
LANG = "de"
|
LANG = "de"
|
||||||
CREDENTIALS_FILE = "service_account.json"
|
CREDENTIALS_FILE = "service_account.json"
|
||||||
SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
|
SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
|
||||||
@@ -199,6 +199,50 @@ def validate_article_with_chatgpt(crm_data, wiki_data):
|
|||||||
debug_print(f"Fehler beim Validierungs-API-Aufruf: {e}")
|
debug_print(f"Fehler beim Validierungs-API-Aufruf: {e}")
|
||||||
return "k.A."
|
return "k.A."
|
||||||
|
|
||||||
|
def evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kategorien):
|
||||||
|
# Dieser Prompt soll den Brancheneinordnungsprozess durchführen.
|
||||||
|
prompt_text = (
|
||||||
|
"Du bist ein Experte im Field Service Management. Analysiere die folgenden Branchenangaben und ordne das Unternehmen "
|
||||||
|
"einer der gültigen Branchen zu. Nutze ausschließlich die vorhandenen Informationen.\n\n"
|
||||||
|
f"CRM-Branche: {crm_branche}\n"
|
||||||
|
f"Beschreibung Branche extern: {beschreibung}\n"
|
||||||
|
f"Wikipedia-Branche: {wiki_branche}\n"
|
||||||
|
f"Wikipedia-Kategorien: {wiki_kategorien}\n\n"
|
||||||
|
"Ordne das Unternehmen exakt einer der gültigen Branchen zu und gib aus:\n"
|
||||||
|
"Branche: <vorgeschlagene Branche>\n"
|
||||||
|
"Übereinstimmung: <ok oder X>\n"
|
||||||
|
"Begründung: <kurze Begründung, falls abweichend, ansonsten leer>"
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
with open("api_key.txt", "r") as f:
|
||||||
|
api_key = f.read().strip()
|
||||||
|
except Exception as e:
|
||||||
|
debug_print(f"Fehler beim Lesen des API-Tokens (Branche): {e}")
|
||||||
|
return {"branch": "k.A.", "consistency": "k.A.", "justification": "k.A."}
|
||||||
|
openai.api_key = api_key
|
||||||
|
try:
|
||||||
|
response = openai.ChatCompletion.create(
|
||||||
|
model="gpt-3.5-turbo",
|
||||||
|
messages=[{"role": "system", "content": prompt_text}],
|
||||||
|
temperature=0.0
|
||||||
|
)
|
||||||
|
result = response.choices[0].message.content.strip()
|
||||||
|
debug_print(f"Branchenabgleich ChatGPT Antwort: '{result}'")
|
||||||
|
branch = "k.A."
|
||||||
|
consistency = "k.A."
|
||||||
|
justification = ""
|
||||||
|
for line in result.split("\n"):
|
||||||
|
if line.lower().startswith("branche:"):
|
||||||
|
branch = line.split(":", 1)[1].strip()
|
||||||
|
elif line.lower().startswith("übereinstimmung:"):
|
||||||
|
consistency = line.split(":", 1)[1].strip()
|
||||||
|
elif line.lower().startswith("begründung:"):
|
||||||
|
justification = line.split(":", 1)[1].strip()
|
||||||
|
return {"branch": branch, "consistency": consistency, "justification": justification}
|
||||||
|
except Exception as e:
|
||||||
|
debug_print(f"Fehler beim Aufruf der ChatGPT API für Branchenabgleich: {e}")
|
||||||
|
return {"branch": "k.A.", "consistency": "k.A.", "justification": "k.A."}
|
||||||
|
|
||||||
def evaluate_fsm_suitability(company_name, company_data):
|
def evaluate_fsm_suitability(company_name, company_data):
|
||||||
try:
|
try:
|
||||||
with open("api_key.txt", "r") as f:
|
with open("api_key.txt", "r") as f:
|
||||||
@@ -209,9 +253,7 @@ def evaluate_fsm_suitability(company_name, company_data):
|
|||||||
openai.api_key = api_key
|
openai.api_key = api_key
|
||||||
prompt = (
|
prompt = (
|
||||||
f"Bitte bewerte, ob das Unternehmen '{company_name}' für den Einsatz einer Field Service Management Lösung geeignet ist. "
|
f"Bitte bewerte, ob das Unternehmen '{company_name}' für den Einsatz einer Field Service Management Lösung geeignet ist. "
|
||||||
"Berücksichtige, dass ein Unternehmen mit einem technischen Außendienst, idealerweise mit über 50 Technikern und "
|
"Antworte ausschließlich mit 'Ja' oder 'Nein' und gib eine kurze Begründung."
|
||||||
"Disponenten, die mit der Planung mobiler Ressourcen beschäftigt sind, als geeignet gilt. Nutze dabei verifizierte "
|
|
||||||
"Wikipedia-Daten und deine eigene Einschätzung. Antworte ausschließlich mit 'Ja' oder 'Nein' und gib eine kurze Begründung."
|
|
||||||
)
|
)
|
||||||
try:
|
try:
|
||||||
response = openai.ChatCompletion.create(
|
response = openai.ChatCompletion.create(
|
||||||
@@ -258,9 +300,7 @@ def evaluate_servicetechnicians_estimate(company_name, company_data):
|
|||||||
return "k.A."
|
return "k.A."
|
||||||
openai.api_key = api_key
|
openai.api_key = api_key
|
||||||
prompt = (
|
prompt = (
|
||||||
f"Bitte schätze auf Basis öffentlich zugänglicher Informationen (vor allem verifizierte Wikipedia-Daten) "
|
f"Bitte schätze die Anzahl der Servicetechniker des Unternehmens '{company_name}' in einer der folgenden Kategorien: "
|
||||||
f"die Anzahl der Servicetechniker des Unternehmens '{company_name}' ein. "
|
|
||||||
"Gib die Antwort ausschließlich in einer der folgenden Kategorien aus: "
|
|
||||||
"'<50 Techniker', '>100 Techniker', '>200 Techniker', '>500 Techniker'."
|
"'<50 Techniker', '>100 Techniker', '>200 Techniker', '>500 Techniker'."
|
||||||
)
|
)
|
||||||
try:
|
try:
|
||||||
@@ -285,8 +325,7 @@ def evaluate_servicetechnicians_explanation(company_name, st_estimate, company_d
|
|||||||
return "k.A."
|
return "k.A."
|
||||||
openai.api_key = api_key
|
openai.api_key = api_key
|
||||||
prompt = (
|
prompt = (
|
||||||
f"Bitte erkläre, warum du für das Unternehmen '{company_name}' die Anzahl der Servicetechniker als '{st_estimate}' geschätzt hast. "
|
f"Bitte erkläre, warum du für das Unternehmen '{company_name}' die Anzahl der Servicetechniker als '{st_estimate}' geschätzt hast."
|
||||||
"Berücksichtige dabei öffentlich zugängliche Informationen wie Branche, Umsatz, Mitarbeiterzahl und andere relevante Daten."
|
|
||||||
)
|
)
|
||||||
try:
|
try:
|
||||||
response = openai.ChatCompletion.create(
|
response = openai.ChatCompletion.create(
|
||||||
@@ -335,10 +374,7 @@ def search_linkedin_contact(company_name, website, position_query):
|
|||||||
except Exception as e:
|
except Exception as e:
|
||||||
debug_print("Fehler beim Lesen des SerpAPI-Schlüssels: " + str(e))
|
debug_print("Fehler beim Lesen des SerpAPI-Schlüssels: " + str(e))
|
||||||
return None
|
return None
|
||||||
# Nutze hier die Kurzform, falls vorhanden (Spalte C, Index 2); ansonsten Firmenname (Index 1)
|
search_name = company_name # Hier kannst du auch die Kurzform verwenden, falls vorhanden.
|
||||||
search_name = company_name
|
|
||||||
if company_name == "" and website != "":
|
|
||||||
search_name = website
|
|
||||||
query = f'site:linkedin.com/in "{position_query}" "{search_name}"'
|
query = f'site:linkedin.com/in "{position_query}" "{search_name}"'
|
||||||
debug_print(f"Erstelle LinkedIn-Query: {query}")
|
debug_print(f"Erstelle LinkedIn-Query: {query}")
|
||||||
params = {
|
params = {
|
||||||
@@ -382,7 +418,6 @@ def search_linkedin_contact(company_name, website, position_query):
|
|||||||
debug_print(f"Fehler bei der SerpAPI-Suche: {e}")
|
debug_print(f"Fehler bei der SerpAPI-Suche: {e}")
|
||||||
return None
|
return None
|
||||||
|
|
||||||
# ==================== NEUE FUNKTION: ZÄHLEN DER LINKEDIN-KONTAKTE ====================
|
|
||||||
def count_linkedin_contacts(company_name, website, position_query):
|
def count_linkedin_contacts(company_name, website, position_query):
|
||||||
try:
|
try:
|
||||||
with open("serpApiKey.txt", "r") as f:
|
with open("serpApiKey.txt", "r") as f:
|
||||||
@@ -412,35 +447,83 @@ def count_linkedin_contacts(company_name, website, position_query):
|
|||||||
debug_print(f"Fehler bei der SerpAPI-Suche (Count): {e}")
|
debug_print(f"Fehler bei der SerpAPI-Suche (Count): {e}")
|
||||||
return 0
|
return 0
|
||||||
|
|
||||||
# ==================== NEUER MODUS 6: CONTACT RESEARCH (via SerpAPI) ====================
|
# ==================== NEUER MODUS 51: VERIFIZIERUNG (Nur Wikipedia + Brancheneinordnung) ====================
|
||||||
def process_contact_research():
|
def process_verification_only():
|
||||||
debug_print("Starte Contact Research (Modus 6)...")
|
debug_print("Starte Verifizierungs-Modus (Modus 51)...")
|
||||||
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
processor = DataProcessor()
|
||||||
Config.CREDENTIALS_FILE, ["https://www.googleapis.com/auth/spreadsheets"]))
|
# Wir nutzen als Kriterium, dass in Spalte Y (Begründung Abweichung Branche) noch kein Wert steht.
|
||||||
sh = gc.open_by_url(Config.SHEET_URL)
|
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||||
main_sheet = sh.sheet1
|
if len(row) <= 24 or row[24].strip() == "": # Spalte Y ist Index 24 (0-basiert)
|
||||||
data = main_sheet.get_all_values()
|
processor._process_verification_row(i, row)
|
||||||
# Website ist nun in Spalte D (Index 3), Firmenname in Spalte B (Index 1)
|
debug_print("Verifizierungs-Modus abgeschlossen.")
|
||||||
for i, row in enumerate(data[1:], start=2):
|
|
||||||
company_name = row[1] if len(row) > 1 else ""
|
def _process_verification_row(self, row_num, row_data):
|
||||||
# Verwende die Kurzform (Spalte C, Index 2) für die Suche, wenn vorhanden, ansonsten Firmenname
|
# In diesem Modus verarbeiten wir nur bis Spalte Y (Begründung Abweichung Branche)
|
||||||
search_name = row[2].strip() if len(row) > 2 and row[2].strip() not in ["", "k.A."] else company_name
|
# Spalte B: Firmenname, Spalte C: Kurzform, Spalte D: Website, Spalte E: Ort, Spalte F: Beschreibung,
|
||||||
website = row[3] if len(row) > 3 else ""
|
# Spalte G: Aktuelle Branche, Spalte H: Beschreibung Branche extern,
|
||||||
if not company_name or not website:
|
# Spalte I: Anzahl Techniker CRM, J: Umsatz CRM, K: Anzahl Mitarbeiter CRM,
|
||||||
continue
|
# Spalte L: Vorschlag Wiki URL, M: Wikipedia URL, N: Wikipedia Absatz, O: Wikipedia Branche,
|
||||||
count_service = count_linkedin_contacts(search_name, website, "Serviceleiter")
|
# P: Wikipedia Umsatz, Q: Wikipedia Mitarbeiter, R: Wikipedia Kategorien,
|
||||||
count_it = count_linkedin_contacts(search_name, website, "IT-Leiter")
|
# S: Konsistenzprüfung, T: Begründung bei Inkonsistenz, U: Vorschlag Wiki Artikel ChatGPT,
|
||||||
count_management = count_linkedin_contacts(search_name, website, "Geschäftsführer")
|
# V: Begründung bei Abweichung, W: Vorschlag neue Branche, X: Konsistenzprüfung Branche,
|
||||||
count_disponent = count_linkedin_contacts(search_name, website, "Disponent")
|
# Y: Begründung Abweichung Branche.
|
||||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
company_name = row_data[1] if len(row_data) > 1 else ""
|
||||||
main_sheet.update(values=[[str(count_service)]], range_name=f"AH{i}")
|
website = row_data[3] if len(row_data) > 3 else ""
|
||||||
main_sheet.update(values=[[str(count_it)]], range_name=f"AI{i}")
|
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
main_sheet.update(values=[[str(count_management)]], range_name=f"AJ{i}")
|
# Wikipedia-Teil: Spalte L bis R
|
||||||
main_sheet.update(values=[[str(count_disponent)]], range_name=f"AK{i}")
|
if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."]:
|
||||||
main_sheet.update(values=[[current_dt]], range_name=f"AL{i}")
|
wiki_url = row_data[11].strip()
|
||||||
debug_print(f"Zeile {i}: Serviceleiter {count_service}, IT-Leiter {count_it}, Management {count_management}, Disponent {count_disponent} – Contact Search Timestamp gesetzt.")
|
try:
|
||||||
time.sleep(Config.RETRY_DELAY * 1.5)
|
wiki_data = self.wiki_scraper.extract_company_data(wiki_url)
|
||||||
debug_print("Contact Research abgeschlossen.")
|
except Exception as e:
|
||||||
|
debug_print(f"Fehler beim Laden des vorgeschlagenen Wikipedia-Artikels: {e}")
|
||||||
|
article = self.wiki_scraper.search_company_article(company_name, website)
|
||||||
|
wiki_data = self.wiki_scraper.extract_company_data(article.url) if article else {
|
||||||
|
'url': 'k.A.', 'first_paragraph': 'k.A.', 'branche': 'k.A.',
|
||||||
|
'umsatz': 'k.A.', 'mitarbeiter': 'k.A.', 'categories': 'k.A.',
|
||||||
|
'full_infobox': 'k.A.'
|
||||||
|
}
|
||||||
|
else:
|
||||||
|
article = self.wiki_scraper.search_company_article(company_name, website)
|
||||||
|
wiki_data = self.wiki_scraper.extract_company_data(article.url) if article else {
|
||||||
|
'url': 'k.A.', 'first_paragraph': 'k.A.', 'branche': 'k.A.',
|
||||||
|
'umsatz': 'k.A.', 'mitarbeiter': 'k.A.', 'categories': 'k.A.',
|
||||||
|
'full_infobox': 'k.A.'
|
||||||
|
}
|
||||||
|
wiki_values = [
|
||||||
|
row_data[11] if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."] else "k.A.",
|
||||||
|
wiki_data.get('url', 'k.A.'),
|
||||||
|
wiki_data.get('first_paragraph', 'k.A.'),
|
||||||
|
wiki_data.get('branche', 'k.A.'),
|
||||||
|
wiki_data.get('umsatz', 'k.A.'),
|
||||||
|
wiki_data.get('mitarbeiter', 'k.A.'),
|
||||||
|
wiki_data.get('categories', 'k.A.')
|
||||||
|
]
|
||||||
|
# Update Wikipedia-Spalten (L bis R)
|
||||||
|
self.sheet_handler.sheet.update(values=[wiki_values], range_name=f"L{row_num}:R{row_num}")
|
||||||
|
# Brancheneinordnung: Verwende CRM-Branche (Spalte G) und Beschreibung Branche extern (Spalte H)
|
||||||
|
crm_branche = row_data[6] if len(row_data) > 6 else "k.A."
|
||||||
|
beschreibung = row_data[7] if len(row_data) > 7 else "k.A."
|
||||||
|
wiki_branche = wiki_data.get('branche', 'k.A.')
|
||||||
|
wiki_kategorien = wiki_data.get('categories', 'k.A.')
|
||||||
|
branche_result = evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kategorien)
|
||||||
|
# Update Brancheneinordnung in Spalten V, W, X (Beispielsweise)
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["branch"]]], range_name=f"V{row_num}")
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["consistency"]]], range_name=f"W{row_num}")
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["justification"]]], range_name=f"X{row_num}")
|
||||||
|
# Verifizierungsstatus: Wir nutzen validate_article_with_chatgpt, um eine finale Aussage zu erhalten, in Spalte Y
|
||||||
|
crm_data = ";".join(row_data[1:11])
|
||||||
|
wiki_data_str = ";".join(row_data[11:18])
|
||||||
|
valid_result = validate_article_with_chatgpt(crm_data, wiki_data_str)
|
||||||
|
self.sheet_handler.sheet.update(values=[[valid_result]], range_name=f"Y{row_num}")
|
||||||
|
# Aktualisiere Timestamp und Version (z. B. in Spalte Z und AA)
|
||||||
|
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"Z{row_num}")
|
||||||
|
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"AA{row_num}")
|
||||||
|
debug_print(f"Zeile {row_num} verifiziert: URL: {wiki_data.get('url', 'k.A.')}, Branche: {wiki_data.get('branche', 'k.A.')}")
|
||||||
|
time.sleep(Config.RETRY_DELAY)
|
||||||
|
|
||||||
|
# Füge _process_verification_row als Methode in DataProcessor hinzu
|
||||||
|
DataProcessor._process_verification_row = _process_verification_row
|
||||||
|
|
||||||
# ==================== NEUER MODUS: ALIGNMENT DEMO (für Hauptblatt und Contacts) ====================
|
# ==================== NEUER MODUS: ALIGNMENT DEMO (für Hauptblatt und Contacts) ====================
|
||||||
def alignment_demo_full():
|
def alignment_demo_full():
|
||||||
@@ -486,25 +569,10 @@ def alignment_demo(sheet):
|
|||||||
"Spalte W (Vorschlag neue Branche)",
|
"Spalte W (Vorschlag neue Branche)",
|
||||||
"Spalte X (Konsistenzprüfung Branche)",
|
"Spalte X (Konsistenzprüfung Branche)",
|
||||||
"Spalte Y (Begründung Abweichung Branche)",
|
"Spalte Y (Begründung Abweichung Branche)",
|
||||||
"Spalte Z (FSM Relevanz Ja / Nein)",
|
"Spalte Z (Timestamp Verifizierung)",
|
||||||
"Spalte AA (Begründung für FSM Relevanz)",
|
"Spalte AA (Version)"
|
||||||
"Spalte AB (Schätzung Anzahl Mitarbeiter)",
|
|
||||||
"Spalte AC (Konsistenzprüfung Mitarbeiterzahl)",
|
|
||||||
"Spalte AD (Begründung für Abweichung Mitarbeiterzahl)",
|
|
||||||
"Spalte AE (Einschätzung Anzahl Servicetechniker)",
|
|
||||||
"Spalte AF (Begründung bei Abweichung Anzahl Servicetechniker)",
|
|
||||||
"Spalte AG (Schätzung Umsatz ChatGPT)",
|
|
||||||
"Spalte AH (Begründung für Abweichung Umsatz)",
|
|
||||||
"Spalte AI (Serviceleiter gefunden)",
|
|
||||||
"Spalte AJ (IT-Leiter gefunden)",
|
|
||||||
"Spalte AK (Management gefunden)",
|
|
||||||
"Spalte AL (Disponent gefunden)",
|
|
||||||
"Spalte AM (Contact Search Timestamp)",
|
|
||||||
"Spalte AN (Wikipedia Timestamp)",
|
|
||||||
"Spalte AO (ChatGPT Timestamp)",
|
|
||||||
"Spalte AP (Version)"
|
|
||||||
]
|
]
|
||||||
header_range = "A11200:AP11200"
|
header_range = "A11200:AA11200"
|
||||||
sheet.update(values=[new_headers], range_name=header_range)
|
sheet.update(values=[new_headers], range_name=header_range)
|
||||||
print("Alignment-Demo abgeschlossen: Neue Spaltenüberschriften in Zeile 11200 geschrieben.")
|
print("Alignment-Demo abgeschlossen: Neue Spaltenüberschriften in Zeile 11200 geschrieben.")
|
||||||
|
|
||||||
@@ -702,7 +770,7 @@ class GoogleSheetHandler:
|
|||||||
self.sheet = gspread.authorize(creds).open_by_url(Config.SHEET_URL).sheet1
|
self.sheet = gspread.authorize(creds).open_by_url(Config.SHEET_URL).sheet1
|
||||||
self.sheet_values = self.sheet.get_all_values()
|
self.sheet_values = self.sheet.get_all_values()
|
||||||
def get_start_index(self):
|
def get_start_index(self):
|
||||||
# Wikipedia Timestamp ist jetzt in Spalte AN (Index 39)
|
# Wir verwenden Spalte AN (Index 39) als Wikipedia-Timestamp im regulären Modus
|
||||||
filled_n = [row[39] if len(row) > 39 else '' for row in self.sheet_values[1:]]
|
filled_n = [row[39] if len(row) > 39 else '' for row in self.sheet_values[1:]]
|
||||||
return next((i + 1 for i, v in enumerate(filled_n, start=1) if not str(v).strip()), len(filled_n) + 1)
|
return next((i + 1 for i, v in enumerate(filled_n, start=1) if not str(v).strip()), len(filled_n) + 1)
|
||||||
|
|
||||||
@@ -723,15 +791,20 @@ class DataProcessor:
|
|||||||
elif MODE == "4":
|
elif MODE == "4":
|
||||||
processor = DataProcessor()
|
processor = DataProcessor()
|
||||||
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||||
# Nur Zeilen ohne Wikipedia-Timestamp (Spalte AN, Index 39)
|
|
||||||
if len(row) <= 39 or row[39].strip() == "":
|
if len(row) <= 39 or row[39].strip() == "":
|
||||||
processor._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
|
processor._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
|
||||||
elif MODE == "5":
|
elif MODE == "5":
|
||||||
processor = DataProcessor()
|
processor = DataProcessor()
|
||||||
# Nur Zeilen ohne ChatGPT-Timestamp (Spalte AO, Index 40)
|
|
||||||
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||||
if len(row) <= 40 or row[40].strip() == "":
|
if len(row) <= 40 or row[40].strip() == "":
|
||||||
processor._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
|
processor._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
|
||||||
|
elif MODE == "51":
|
||||||
|
# Neuer Modus 51: Nur Verifizierung (Wikipedia + Brancheneinordnung) – bis Spalte Y bearbeiten.
|
||||||
|
processor = DataProcessor()
|
||||||
|
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||||
|
# Hier prüfen wir, ob in Spalte Y (Index 24) noch kein Wert steht.
|
||||||
|
if len(row) <= 25 or row[24].strip() == "":
|
||||||
|
processor._process_verification_row(i, row)
|
||||||
else:
|
else:
|
||||||
start_index = self.sheet_handler.get_start_index()
|
start_index = self.sheet_handler.get_start_index()
|
||||||
print(f"Starte bei Zeile {start_index+1}")
|
print(f"Starte bei Zeile {start_index+1}")
|
||||||
@@ -744,17 +817,15 @@ class DataProcessor:
|
|||||||
self._process_single_row(i, row)
|
self._process_single_row(i, row)
|
||||||
rows_processed += 1
|
rows_processed += 1
|
||||||
def _process_single_row(self, row_num, row_data, force_all=False, process_wiki=True, process_chatgpt=True):
|
def _process_single_row(self, row_num, row_data, force_all=False, process_wiki=True, process_chatgpt=True):
|
||||||
# Spalte B: Firmenname, Spalte C: Kurzform, Spalte D: Website
|
# Dies ist die vollständige Verarbeitung (wie in v1.3.11)
|
||||||
company_name = row_data[1] if len(row_data) > 1 else ""
|
company_name = row_data[1] if len(row_data) > 1 else ""
|
||||||
website = row_data[3] if len(row_data) > 3 else ""
|
website = row_data[3] if len(row_data) > 3 else ""
|
||||||
wiki_update_range = f"L{row_num}:R{row_num}" # Vorschlag Wiki URL bis Wikipedia Kategorien (Spalte L bis R)
|
wiki_update_range = f"L{row_num}:R{row_num}"
|
||||||
dt_wiki_range = f"AN{row_num}" # Wikipedia Timestamp (Spalte AN)
|
dt_wiki_range = f"AN{row_num}"
|
||||||
dt_chat_range = f"AO{row_num}" # ChatGPT Timestamp (Spalte AO)
|
dt_chat_range = f"AO{row_num}"
|
||||||
ver_range = f"AP{row_num}" # Version (Spalte AP)
|
ver_range = f"AP{row_num}"
|
||||||
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
|
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")
|
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
|
|
||||||
# Wikipedia-Teil
|
|
||||||
if force_all or process_wiki:
|
if force_all or process_wiki:
|
||||||
if len(row_data) <= 39 or row_data[39].strip() == "":
|
if len(row_data) <= 39 or row_data[39].strip() == "":
|
||||||
if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."]:
|
if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."]:
|
||||||
@@ -789,17 +860,12 @@ class DataProcessor:
|
|||||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_wiki_range)
|
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_wiki_range)
|
||||||
else:
|
else:
|
||||||
debug_print(f"Zeile {row_num}: Wikipedia-Timestamp bereits gesetzt – überspringe Wiki-Auswertung.")
|
debug_print(f"Zeile {row_num}: Wikipedia-Timestamp bereits gesetzt – überspringe Wiki-Auswertung.")
|
||||||
|
|
||||||
# ChatGPT-Teil
|
|
||||||
if force_all or process_chatgpt:
|
if force_all or process_chatgpt:
|
||||||
if len(row_data) <= 40 or row_data[40].strip() == "":
|
if len(row_data) <= 40 or row_data[40].strip() == "":
|
||||||
# Umsatz CRM ist nun in Spalte J (Index 9), Anzahl Mitarbeiter in Spalte K (Index 10)
|
|
||||||
crm_umsatz = row_data[9] if len(row_data) > 9 else "k.A."
|
crm_umsatz = row_data[9] if len(row_data) > 9 else "k.A."
|
||||||
abgleich_result = compare_umsatz_values(crm_umsatz, wiki_data.get('umsatz', 'k.A.') if 'wiki_data' in locals() 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}")
|
self.sheet_handler.sheet.update(values=[[abgleich_result]], range_name=f"AG{row_num}")
|
||||||
# CRM-Daten: von Spalte B bis K (Indices 1 bis 10)
|
|
||||||
crm_data = ";".join(row_data[1:11])
|
crm_data = ";".join(row_data[1:11])
|
||||||
# Wiki-Daten: von Spalte L bis R (Indices 11 bis 18)
|
|
||||||
wiki_data_str = ";".join(row_data[11:18])
|
wiki_data_str = ";".join(row_data[11:18])
|
||||||
valid_result = validate_article_with_chatgpt(crm_data, wiki_data_str)
|
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}")
|
self.sheet_handler.sheet.update(values=[[valid_result]], range_name=f"R{row_num}")
|
||||||
@@ -808,7 +874,7 @@ class DataProcessor:
|
|||||||
self.sheet_handler.sheet.update(values=[[fsm_result["justification"]]], range_name=f"Z{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' in locals() 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"AE{row_num}")
|
self.sheet_handler.sheet.update(values=[[st_estimate]], range_name=f"AE{row_num}")
|
||||||
internal_value = row_data[8] if len(row_data) > 8 else "k.A." # Anzahl Techniker CRM in Spalte I (Index 8)
|
internal_value = row_data[8] if len(row_data) > 8 else "k.A."
|
||||||
internal_category = map_internal_technicians(internal_value) if internal_value != "k.A." 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:
|
if internal_category != "k.A." and st_estimate != internal_category:
|
||||||
explanation = evaluate_servicetechnicians_explanation(company_name, st_estimate, wiki_data if 'wiki_data' in locals() else {})
|
explanation = evaluate_servicetechnicians_explanation(company_name, st_estimate, wiki_data if 'wiki_data' in locals() else {})
|
||||||
@@ -819,10 +885,8 @@ class DataProcessor:
|
|||||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_chat_range)
|
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_chat_range)
|
||||||
else:
|
else:
|
||||||
debug_print(f"Zeile {row_num}: ChatGPT-Timestamp bereits gesetzt – überspringe ChatGPT-Auswertung.")
|
debug_print(f"Zeile {row_num}: ChatGPT-Timestamp bereits gesetzt – überspringe ChatGPT-Auswertung.")
|
||||||
|
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=ver_range)
|
||||||
# Aktualisiere letzten Timestamp und Version (Spalte AP)
|
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=ver_range)
|
||||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AP{row_num}")
|
|
||||||
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"AP{row_num}")
|
|
||||||
debug_print(f"✅ Aktualisiert: URL: {(wiki_data.get('url', 'k.A.') if 'wiki_data' in locals() else 'k.A.')}, "
|
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"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"Umsatz-Abgleich: {abgleich_result if 'abgleich_result' in locals() else 'k.A.'}, "
|
||||||
@@ -830,7 +894,7 @@ class DataProcessor:
|
|||||||
f"FSM: {fsm_result['suitability'] if 'fsm_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.'}")
|
f"Servicetechniker-Schätzung: {st_estimate if 'st_estimate' in locals() else 'k.A.'}")
|
||||||
time.sleep(Config.RETRY_DELAY)
|
time.sleep(Config.RETRY_DELAY)
|
||||||
|
|
||||||
# ==================== NEUER MODUS 6: CONTACT RESEARCH (via SerpAPI) ====================
|
# ==================== NEUER MODUS 6: CONTACT RESEARCH (via SerpAPI) ====================
|
||||||
def process_contact_research():
|
def process_contact_research():
|
||||||
debug_print("Starte Contact Research (Modus 6)...")
|
debug_print("Starte Contact Research (Modus 6)...")
|
||||||
@@ -839,10 +903,8 @@ def process_contact_research():
|
|||||||
sh = gc.open_by_url(Config.SHEET_URL)
|
sh = gc.open_by_url(Config.SHEET_URL)
|
||||||
main_sheet = sh.sheet1
|
main_sheet = sh.sheet1
|
||||||
data = main_sheet.get_all_values()
|
data = main_sheet.get_all_values()
|
||||||
# Website ist nun in Spalte D (Index 3); Firmenname in Spalte B; Kurzform in Spalte C
|
|
||||||
for i, row in enumerate(data[1:], start=2):
|
for i, row in enumerate(data[1:], start=2):
|
||||||
company_name = row[1] if len(row) > 1 else ""
|
company_name = row[1] if len(row) > 1 else ""
|
||||||
# Verwende Kurzform (Spalte C, Index 2) falls vorhanden, sonst Firmenname
|
|
||||||
search_name = row[2].strip() if len(row) > 2 and row[2].strip() not in ["", "k.A."] else company_name
|
search_name = row[2].strip() if len(row) > 2 and row[2].strip() not in ["", "k.A."] else company_name
|
||||||
website = row[3] if len(row) > 3 else ""
|
website = row[3] if len(row) > 3 else ""
|
||||||
if not company_name or not website:
|
if not company_name or not website:
|
||||||
@@ -852,31 +914,15 @@ def process_contact_research():
|
|||||||
count_management = count_linkedin_contacts(search_name, website, "Geschäftsführer")
|
count_management = count_linkedin_contacts(search_name, website, "Geschäftsführer")
|
||||||
count_disponent = count_linkedin_contacts(search_name, website, "Disponent")
|
count_disponent = count_linkedin_contacts(search_name, website, "Disponent")
|
||||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
main_sheet.update(values=[[str(count_service)]], range_name=f"AI{i}") # Neu: Spalte AI (Serviceleiter gefunden) – vorher AH -> jetzt AI
|
main_sheet.update(values=[[str(count_service)]], range_name=f"AI{i}")
|
||||||
main_sheet.update(values=[[str(count_it)]], range_name=f"AJ{i}") # IT-Leiter gefunden in Spalte AJ
|
main_sheet.update(values=[[str(count_it)]], range_name=f"AJ{i}")
|
||||||
main_sheet.update(values=[[str(count_management)]], range_name=f"AK{i}") # Management gefunden in Spalte AK
|
main_sheet.update(values=[[str(count_management)]], range_name=f"AK{i}")
|
||||||
main_sheet.update(values=[[str(count_disponent)]], range_name=f"AL{i}") # Disponent gefunden in Spalte AL
|
main_sheet.update(values=[[str(count_disponent)]], range_name=f"AL{i}")
|
||||||
main_sheet.update(values=[[current_dt]], range_name=f"AM{i}") # Contact Search Timestamp in Spalte AM
|
main_sheet.update(values=[[current_dt]], range_name=f"AM{i}")
|
||||||
debug_print(f"Zeile {i}: Serviceleiter {count_service}, IT-Leiter {count_it}, Management {count_management}, Disponent {count_disponent} – Contact Search Timestamp gesetzt.")
|
debug_print(f"Zeile {i}: Serviceleiter {count_service}, IT-Leiter {count_it}, Management {count_management}, Disponent {count_disponent} – Contact Search Timestamp gesetzt.")
|
||||||
time.sleep(Config.RETRY_DELAY * 1.5)
|
time.sleep(Config.RETRY_DELAY * 1.5)
|
||||||
debug_print("Contact Research abgeschlossen.")
|
debug_print("Contact Research abgeschlossen.")
|
||||||
|
|
||||||
# ==================== NEUER MODUS: ALIGNMENT DEMO (für Hauptblatt und Contacts) ====================
|
|
||||||
def alignment_demo_full():
|
|
||||||
alignment_demo(GoogleSheetHandler().sheet)
|
|
||||||
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
|
||||||
Config.CREDENTIALS_FILE, ["https://www.googleapis.com/auth/spreadsheets"]))
|
|
||||||
sh = gc.open_by_url(Config.SHEET_URL)
|
|
||||||
try:
|
|
||||||
contacts_sheet = sh.worksheet("Contacts")
|
|
||||||
except gspread.exceptions.WorksheetNotFound:
|
|
||||||
contacts_sheet = sh.add_worksheet(title="Contacts", rows="1000", cols="10")
|
|
||||||
header = ["Firmenname", "Website", "Kurzform", "Vorname", "Nachname", "Position", "Anrede", "E-Mail"]
|
|
||||||
contacts_sheet.update(values=[header], range_name="A1:H1")
|
|
||||||
debug_print("Neues Blatt 'Contacts' erstellt und Header eingetragen.")
|
|
||||||
alignment_demo(contacts_sheet)
|
|
||||||
debug_print("Alignment-Demo für Hauptblatt und Contacts abgeschlossen.")
|
|
||||||
|
|
||||||
# ==================== NEUER MODUS: CONTACTS (LinkedIn) ====================
|
# ==================== NEUER MODUS: CONTACTS (LinkedIn) ====================
|
||||||
def process_contacts():
|
def process_contacts():
|
||||||
debug_print("Starte LinkedIn-Kontaktsuche...")
|
debug_print("Starte LinkedIn-Kontaktsuche...")
|
||||||
@@ -895,7 +941,6 @@ def process_contacts():
|
|||||||
positions = ["Serviceleiter", "IT-Leiter", "Leiter After Sales", "Leiter Einsatzplanung"]
|
positions = ["Serviceleiter", "IT-Leiter", "Leiter After Sales", "Leiter Einsatzplanung"]
|
||||||
new_rows = []
|
new_rows = []
|
||||||
for idx, row in enumerate(data[1:], start=2):
|
for idx, row in enumerate(data[1:], start=2):
|
||||||
# Firmenname in Spalte B (Index 1), Kurzform in Spalte C (Index 2), Website in Spalte D (Index 3)
|
|
||||||
company_name = row[1] if len(row) > 1 else ""
|
company_name = row[1] if len(row) > 1 else ""
|
||||||
search_name = row[2].strip() if len(row) > 2 and row[2].strip() not in ["", "k.A."] else company_name
|
search_name = row[2].strip() if len(row) > 2 and row[2].strip() not in ["", "k.A."] else company_name
|
||||||
website = row[3] if len(row) > 3 else ""
|
website = row[3] if len(row) > 3 else ""
|
||||||
@@ -923,7 +968,7 @@ def process_contacts():
|
|||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
import argparse
|
import argparse
|
||||||
parser = argparse.ArgumentParser()
|
parser = argparse.ArgumentParser()
|
||||||
parser.add_argument("--mode", type=str, default="1", help="Modus: 1, 2, 3, 4, 5, 6 oder 7")
|
parser.add_argument("--mode", type=str, default="1", help="Modus: 1, 2, 3, 4, 5, 6, 7 oder 51")
|
||||||
parser.add_argument("--num_rows", type=int, default=0, help="Anzahl der zu bearbeitenden Zeilen (nur für Modus 1)")
|
parser.add_argument("--num_rows", type=int, default=0, help="Anzahl der zu bearbeitenden Zeilen (nur für Modus 1)")
|
||||||
args = parser.parse_args()
|
args = parser.parse_args()
|
||||||
|
|
||||||
@@ -949,4 +994,6 @@ if __name__ == "__main__":
|
|||||||
process_contact_research()
|
process_contact_research()
|
||||||
elif MODE == "7":
|
elif MODE == "7":
|
||||||
process_contacts()
|
process_contacts()
|
||||||
print(f"\n✅ Auswertung abgeschlossen ({Config.VERSION})")
|
elif MODE == "51":
|
||||||
|
process_verification_only()
|
||||||
|
print(f"\n✅ Auswertung abgeschlossen ({Config.VERSION})")
|
||||||
|
|||||||
Reference in New Issue
Block a user