Modus 51: Zielgerichtete Branchen & FSM-Bewertung; AO/AP/AQ werden aktualisiert
This commit is contained in:
@@ -18,7 +18,7 @@ except ImportError:
|
||||
|
||||
# ==================== KONFIGURATION ====================
|
||||
class Config:
|
||||
VERSION = "v1.3.16" # v1.3.16: Modus 51 implementiert mit separaten Spalten für Wiki-Confirm, alternative Wiki URL, Branchenvorschlag etc.
|
||||
VERSION = "v1.3.16" # v1.3.16: Neuer Modus 51 für gezielte Verifizierung (Branche & FSM)
|
||||
LANG = "de"
|
||||
CREDENTIALS_FILE = "service_account.json"
|
||||
SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
|
||||
@@ -176,7 +176,7 @@ def validate_article_with_chatgpt(crm_data, wiki_data):
|
||||
wiki_headers = "Wikipedia URL;Wikipedia Absatz;Wikipedia Branche;Wikipedia Umsatz;Wikipedia Mitarbeiter;Wikipedia Kategorien"
|
||||
prompt_text = (
|
||||
"Bitte überprüfe, ob die folgenden beiden Datensätze grundsätzlich zum gleichen Unternehmen gehören. "
|
||||
"Berücksichtige leichte Abweichungen in Firmennamen und Ort. Wenn sie im Wesentlichen übereinstimmen, antworte mit 'OK'. "
|
||||
"Berücksichtige dabei leichte Abweichungen in Firmennamen und Ort. Wenn sie im Wesentlichen übereinstimmen, antworte mit 'OK'. "
|
||||
"Andernfalls nenne den wichtigsten Grund und eine kurze Begründung.\n\n"
|
||||
f"CRM-Daten:\n{crm_headers}\n{crm_data}\n\n"
|
||||
f"Wikipedia-Daten:\n{wiki_headers}\n{wiki_data}\n\n"
|
||||
@@ -202,48 +202,18 @@ def validate_article_with_chatgpt(crm_data, wiki_data):
|
||||
debug_print(f"Fehler beim Validierungs-API-Aufruf: {e}")
|
||||
return "k.A."
|
||||
|
||||
def load_target_branches():
|
||||
try:
|
||||
with open("ziel_Branchenschema.csv", "r", encoding="utf-8") as csvfile:
|
||||
reader = csv.reader(csvfile)
|
||||
branches = [row[0] for row in reader if row and row[0].strip() != ""]
|
||||
return branches
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Laden des Ziel-Branchenschemas: {e}")
|
||||
return [
|
||||
"Gutachter / Versicherungen > Baugutachter",
|
||||
"Gutachter / Versicherungen > Technische Gutachten",
|
||||
"Gutachter / Versicherungen > Versicherungsgutachten",
|
||||
"Gutachter / Versicherungen > Medizinische Gutachten",
|
||||
"Hersteller / Produzenten > Anlagenbau",
|
||||
"Hersteller / Produzenten > Automaten (Vending, Slot)",
|
||||
"Hersteller / Produzenten > Gebäudetechnik Allgemein",
|
||||
"Hersteller / Produzenten > Gebäudetechnik Heizung, Lüftung, Klima",
|
||||
"Hersteller / Produzenten > Maschinenbau",
|
||||
"Hersteller / Produzenten > Medizintechnik",
|
||||
"Service provider (Dienstleister) > Aufzüge und Rolltreppen",
|
||||
"Service provider (Dienstleister) > Feuer- und Sicherheitssysteme",
|
||||
"Service provider (Dienstleister) > Servicedienstleister / Reparatur ohne Produktion",
|
||||
"Service provider (Dienstleister) > Facility Management",
|
||||
"Versorger > Telekommunikation"
|
||||
]
|
||||
|
||||
def evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kategorien):
|
||||
target_branches = load_target_branches()
|
||||
target_branches_str = "\n".join(target_branches)
|
||||
prompt_text = (
|
||||
"Du bist ein Experte im Field Service Management. Hier ist das gültige Ziel-Branchenschema:\n"
|
||||
f"{target_branches_str}\n\n"
|
||||
"Ordne anhand der folgenden Informationen das Unternehmen genau einer der oben genannten Branchen zu. "
|
||||
"Wenn keine der Informationen passt, antworte mit 'k.A.'. Verwende dabei exakt die Schreibweise aus dem Ziel-Branchenschema.\n\n"
|
||||
"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"
|
||||
"Gib aus im exakten Format (ohne zusätzliche Erklärungen):\n"
|
||||
"Ordne das Unternehmen exakt einer der gültigen Branchen zu und gib aus:\n"
|
||||
"Branche: <vorgeschlagene Branche>\n"
|
||||
"Konsistenz: <OK oder X>\n"
|
||||
"Begründung: <Begründung bei Abweichung (leer, wenn OK)>"
|
||||
"Übereinstimmung: <OK oder X>\n"
|
||||
"Begründung: <kurze Begründung, falls abweichend, ansonsten leer>"
|
||||
)
|
||||
try:
|
||||
with open("api_key.txt", "r") as f:
|
||||
@@ -266,24 +236,7 @@ def evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kateg
|
||||
for line in result.split("\n"):
|
||||
if line.lower().startswith("branche:"):
|
||||
branch = line.split(":", 1)[1].strip()
|
||||
elif line.lower().startswith("konsistenz:"):
|
||||
consistency = line.split(":", 1)[1].strip()
|
||||
elif line.lower().startswith("begründung:"):
|
||||
justification = line.split(":", 1)[1].strip()
|
||||
if branch not in target_branches:
|
||||
debug_print(f"Vorgeschlagene Branche '{branch}' nicht im Ziel-Branchenschema enthalten.")
|
||||
branch = "k.A."
|
||||
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."}
|
||||
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("konsistenz:"):
|
||||
elif line.lower().startswith("übereinstimmung:"):
|
||||
consistency = line.split(":", 1)[1].strip()
|
||||
elif line.lower().startswith("begründung:"):
|
||||
justification = line.split(":", 1)[1].strip()
|
||||
@@ -293,16 +246,101 @@ def evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kateg
|
||||
return {"branch": "k.A.", "consistency": "k.A.", "justification": "k.A."}
|
||||
|
||||
def evaluate_fsm_suitability(company_name, company_data):
|
||||
# Vorläufig nicht genutzt – Rückgabe "n.v."
|
||||
return {"suitability": "n.v.", "justification": ""}
|
||||
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 (FSM): {e}")
|
||||
return {"suitability": "k.A.", "justification": "k.A."}
|
||||
openai.api_key = api_key
|
||||
prompt = (
|
||||
f"Bitte bewerte, ob das Unternehmen '{company_name}' für den Einsatz einer Field Service Management Lösung geeignet ist. "
|
||||
"Antworte ausschließlich mit 'Ja' oder 'Nein' und gib eine kurze Begründung."
|
||||
)
|
||||
try:
|
||||
response = openai.ChatCompletion.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages=[{"role": "system", "content": prompt}],
|
||||
temperature=0.0
|
||||
)
|
||||
result = response.choices[0].message.content.strip()
|
||||
debug_print(f"FSM-Eignungsantwort ChatGPT: '{result}'")
|
||||
suitability = "k.A."
|
||||
justification = ""
|
||||
lines = result.split("\n")
|
||||
if len(lines) == 1:
|
||||
parts = result.split(" ", 1)
|
||||
suitability = parts[0].strip()
|
||||
justification = parts[1].strip() if len(parts) > 1 else ""
|
||||
else:
|
||||
for line in lines:
|
||||
if line.lower().startswith("eignung:"):
|
||||
suitability = line.split(":", 1)[1].strip()
|
||||
elif line.lower().startswith("begründung:"):
|
||||
justification = line.split(":", 1)[1].strip()
|
||||
if suitability not in ["Ja", "Nein"]:
|
||||
parts = result.split(" ", 1)
|
||||
suitability = parts[0].strip()
|
||||
justification = " ".join(result.split()[1:]).strip()
|
||||
return {"suitability": suitability, "justification": justification}
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Aufruf der ChatGPT API für FSM-Eignungsprüfung: {e}")
|
||||
return {"suitability": "k.A.", "justification": "k.A."}
|
||||
|
||||
def evaluate_servicetechnicians_estimate(company_name, company_data):
|
||||
# Vorläufig nicht genutzt – Rückgabe "n.v."
|
||||
return "n.v."
|
||||
try:
|
||||
with open("serpApiKey.txt", "r") as f:
|
||||
serp_key = f.read().strip()
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Lesen des SerpAPI-Schlüssels (Servicetechniker): {e}")
|
||||
return "k.A."
|
||||
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 (Servicetechniker): {e}")
|
||||
return "k.A."
|
||||
openai.api_key = api_key
|
||||
prompt = (
|
||||
f"Bitte schätze die Anzahl der Servicetechniker des Unternehmens '{company_name}' in einer der folgenden Kategorien: "
|
||||
"'<50 Techniker', '>100 Techniker', '>200 Techniker', '>500 Techniker'."
|
||||
)
|
||||
try:
|
||||
response = openai.ChatCompletion.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages=[{"role": "system", "content": prompt}],
|
||||
temperature=0.0
|
||||
)
|
||||
result = response.choices[0].message.content.strip()
|
||||
debug_print(f"Schätzung Servicetechniker ChatGPT: '{result}'")
|
||||
return result
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Aufruf der ChatGPT API für Servicetechniker-Schätzung: {e}")
|
||||
return "k.A."
|
||||
|
||||
def evaluate_servicetechnicians_explanation(company_name, st_estimate, company_data):
|
||||
# Vorläufig nicht genutzt – Rückgabe "n.v."
|
||||
return "n.v."
|
||||
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 (ST-Erklärung): {e}")
|
||||
return "k.A."
|
||||
openai.api_key = api_key
|
||||
prompt = (
|
||||
f"Bitte erkläre, warum du für das Unternehmen '{company_name}' die Anzahl der Servicetechniker als '{st_estimate}' geschätzt hast."
|
||||
)
|
||||
try:
|
||||
response = openai.ChatCompletion.create(
|
||||
model="gpt-3.5-turbo",
|
||||
messages=[{"role": "system", "content": prompt}],
|
||||
temperature=0.0
|
||||
)
|
||||
result = response.choices[0].message.content.strip()
|
||||
debug_print(f"Servicetechniker-Erklärung ChatGPT: '{result}'")
|
||||
return result
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Aufruf der ChatGPT API für Servicetechniker-Erklärung: {e}")
|
||||
return "k.A."
|
||||
|
||||
def map_internal_technicians(value):
|
||||
try:
|
||||
@@ -330,111 +368,60 @@ def wait_for_sheet_update(sheet, cell, expected_value, timeout=5):
|
||||
time.sleep(0.5)
|
||||
return False
|
||||
|
||||
# ==================== NEUE FUNKTION: LINKEDIN-KONTAKT-SUCHE (Einzelkontakt) ====================
|
||||
def search_linkedin_contact(company_name, website, position_query):
|
||||
try:
|
||||
with open("serpApiKey.txt", "r") as f:
|
||||
serp_key = f.read().strip()
|
||||
except Exception as e:
|
||||
debug_print("Fehler beim Lesen des SerpAPI-Schlüssels: " + str(e))
|
||||
return None
|
||||
# Falls vorhanden, könnte hier auch die Kurzform (Spalte C) verwendet werden
|
||||
search_name = company_name
|
||||
query = f'site:linkedin.com/in "{position_query}" "{search_name}"'
|
||||
debug_print(f"Erstelle LinkedIn-Query: {query}")
|
||||
params = {
|
||||
"engine": "google",
|
||||
"q": query,
|
||||
"api_key": serp_key,
|
||||
"hl": "de"
|
||||
}
|
||||
try:
|
||||
response = requests.get("https://serpapi.com/search", params=params)
|
||||
data = response.json()
|
||||
debug_print(f"SerpAPI-Response für Query '{query}': {data.get('organic_results', [])[:1]}")
|
||||
if "organic_results" in data and len(data["organic_results"]) > 0:
|
||||
result = data["organic_results"][0]
|
||||
title = result.get("title", "")
|
||||
debug_print(f"LinkedIn-Suchergebnis-Titel: {title}")
|
||||
if "–" in title:
|
||||
parts = title.split("–")
|
||||
elif "-" in title:
|
||||
parts = title.split("-")
|
||||
else:
|
||||
parts = [title]
|
||||
if len(parts) >= 2:
|
||||
name_part = parts[0].strip()
|
||||
pos = parts[1].split("|")[0].strip()
|
||||
name_parts = name_part.split(" ", 1)
|
||||
if len(name_parts) == 2:
|
||||
firstname, lastname = name_parts
|
||||
else:
|
||||
firstname = name_part
|
||||
lastname = ""
|
||||
debug_print(f"Kontakt gefunden: {firstname} {lastname}, Position: {pos}")
|
||||
return {"Firmenname": company_name, "Website": website, "Vorname": firstname, "Nachname": lastname, "Position": pos}
|
||||
else:
|
||||
debug_print(f"Kontakt gefunden, aber unvollständige Informationen: {title}")
|
||||
return {"Firmenname": company_name, "Website": website, "Vorname": "", "Nachname": "", "Position": title}
|
||||
else:
|
||||
debug_print(f"Keine LinkedIn-Ergebnisse für Query: {query}")
|
||||
return None
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler bei der SerpAPI-Suche: {e}")
|
||||
return None
|
||||
|
||||
def count_linkedin_contacts(company_name, website, position_query):
|
||||
try:
|
||||
with open("serpApiKey.txt", "r") as f:
|
||||
serp_key = f.read().strip()
|
||||
except Exception as e:
|
||||
debug_print("Fehler beim Lesen des SerpAPI-Schlüssels: " + str(e))
|
||||
return 0
|
||||
query = f'site:linkedin.com/in "{position_query}" "{company_name}"'
|
||||
debug_print(f"Erstelle LinkedIn-Query (Count): {query}")
|
||||
params = {
|
||||
"engine": "google",
|
||||
"q": query,
|
||||
"api_key": serp_key,
|
||||
"hl": "de"
|
||||
}
|
||||
try:
|
||||
response = requests.get("https://serpapi.com/search", params=params)
|
||||
data = response.json()
|
||||
if "organic_results" in data:
|
||||
count = len(data["organic_results"])
|
||||
debug_print(f"Anzahl Kontakte für Query '{query}': {count}")
|
||||
return count
|
||||
else:
|
||||
debug_print(f"Keine Ergebnisse für Query: {query}")
|
||||
return 0
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler bei der SerpAPI-Suche (Count): {e}")
|
||||
return 0
|
||||
|
||||
# ==================== VERIFIZIERUNGS-MODUS (Modus 51) ====================
|
||||
def _process_verification_row(row_num, row_data):
|
||||
"""
|
||||
Aggregiert relevante Informationen für die Verifizierung:
|
||||
- Firmenname (Spalte B)
|
||||
- CRM-Beschreibung (Spalte G)
|
||||
- Wikipedia-URL (Spalte M)
|
||||
- Wikipedia-Absatz (Spalte N)
|
||||
- Wikipedia-Kategorien (Spalte R)
|
||||
"""
|
||||
company_name = row_data[1] if len(row_data) > 1 else ""
|
||||
crm_description = row_data[6] if len(row_data) > 6 else ""
|
||||
wiki_url = row_data[12] if len(row_data) > 12 else "k.A."
|
||||
wiki_absatz = row_data[13] if len(row_data) > 13 else "k.A."
|
||||
wiki_categories = row_data[17] if len(row_data) > 17 else "k.A."
|
||||
entry_text = (f"Eintrag {row_num}:\n"
|
||||
f"Firmenname: {company_name}\n"
|
||||
f"CRM-Beschreibung: {crm_description}\n"
|
||||
f"Wikipedia-URL: {wiki_url}\n"
|
||||
f"Wikipedia-Absatz: {wiki_absatz}\n"
|
||||
f"Wikipedia-Kategorien: {wiki_categories}\n"
|
||||
"-----\n")
|
||||
return entry_text
|
||||
website = row_data[3] if len(row_data) > 3 else ""
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."]:
|
||||
wiki_url = row_data[11].strip()
|
||||
try:
|
||||
wiki_data = WikipediaScraper().extract_company_data(wiki_url)
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Laden des vorgeschlagenen Wikipedia-Artikels: {e}")
|
||||
article = WikipediaScraper().search_company_article(company_name, website)
|
||||
wiki_data = WikipediaScraper().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 = WikipediaScraper().search_company_article(company_name, website)
|
||||
wiki_data = WikipediaScraper().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.')
|
||||
]
|
||||
gh = GoogleSheetHandler()
|
||||
gh.sheet.update(values=[wiki_values], range_name=f"L{row_num}:R{row_num}")
|
||||
# Branchenbewertung:
|
||||
crm_branch = row_data[6] if len(row_data) > 6 else "k.A."
|
||||
ext_branch = row_data[7] if len(row_data) > 7 else "k.A."
|
||||
wiki_branch = wiki_data.get('branche', 'k.A.')
|
||||
wiki_cats = wiki_data.get('categories', 'k.A.')
|
||||
branch_result = evaluate_branche_chatgpt(crm_branch, ext_branch, wiki_branch, wiki_cats)
|
||||
gh.sheet.update(values=[[branch_result["branch"]]], range_name=f"W{row_num}")
|
||||
gh.sheet.update(values=[[branch_result["consistency"]]], range_name=f"Y{row_num}")
|
||||
# Validierung mit ChatGPT:
|
||||
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)
|
||||
gh.sheet.update(values=[[valid_result]], range_name=f"R{row_num}")
|
||||
# Schreibe Timestamp, Version und Token Count:
|
||||
gh.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
|
||||
gh.sheet.update(values=[[Config.VERSION]], range_name=f"AP{row_num}")
|
||||
# Für Batch-Token-Zählung wird später Spalte AQ aktualisiert.
|
||||
debug_print(f"Zeile {row_num} verifiziert: Antwort: {valid_result}")
|
||||
time.sleep(Config.RETRY_DELAY)
|
||||
|
||||
def process_verification_only():
|
||||
debug_print("Starte Verifizierungsmodus (Modus 51) im Batch-Prozess...")
|
||||
@@ -443,28 +430,33 @@ def process_verification_only():
|
||||
sh = gc.open_by_url(Config.SHEET_URL)
|
||||
main_sheet = sh.sheet1
|
||||
data = main_sheet.get_all_values()
|
||||
batch_size = Config.BATCH_SIZE
|
||||
batch_entries = []
|
||||
row_indices = []
|
||||
# Prüfe Spalte AO (Index 40) für den Verifizierungstimestamp: nur leere Zeilen verarbeiten
|
||||
for i, row in enumerate(data[1:], start=2):
|
||||
if len(row) <= 41 or row[40].strip() == "":
|
||||
entry_text = _process_verification_row(i, row)
|
||||
if len(row) <= 25 or row[24].strip() == "":
|
||||
# Hier wird _process_verification_row genutzt
|
||||
entry_text = (f"Eintrag {i}:\n"
|
||||
f"Firmenname: {row[1] if len(row)>1 else 'k.A.'}\n"
|
||||
f"CRM-Beschreibung: {row[7] if len(row)>7 else 'k.A.'}\n"
|
||||
f"Wikipedia-URL: {row[11] if len(row)>11 else 'k.A.'}\n"
|
||||
f"Wikipedia-Absatz: {row[12] if len(row)>12 else 'k.A.'}\n"
|
||||
f"Wikipedia-Kategorien: {row[17] if len(row)>17 else 'k.A.'}\n"
|
||||
"-----")
|
||||
batch_entries.append(entry_text)
|
||||
row_indices.append(i)
|
||||
if len(batch_entries) == batch_size:
|
||||
if len(batch_entries) == Config.BATCH_SIZE:
|
||||
break
|
||||
if not batch_entries:
|
||||
debug_print("Keine Einträge für die Verifizierung gefunden.")
|
||||
return
|
||||
aggregated_prompt = ("Du bist ein Experte in der Verifizierung von Wikipedia-Artikeln für Unternehmen. "
|
||||
"Für jeden der folgenden Einträge prüfe, ob der vorhandene Wikipedia-Artikel (URL, Absatz, Kategorien) plausibel passt. "
|
||||
"Für jeden der folgenden Einträge prüfe, ob der vorhandene Wikipedia-Artikel plausibel passt. "
|
||||
"Gib für jeden Eintrag das Ergebnis im Format aus:\n"
|
||||
"Eintrag <Zeilennummer>: <Antwort>\n"
|
||||
"Dabei gilt:\n"
|
||||
"- Wenn der Artikel passt, antworte mit 'OK'.\n"
|
||||
"- Wenn der Artikel unpassend ist, antworte mit 'Alternativer Wikipedia-Artikel vorgeschlagen: <URL> | X | <Begründung>'.\n"
|
||||
"- Wenn kein Artikel gefunden wurde, antworte mit 'Kein Wikipedia-Eintrag vorhanden.'\n\n")
|
||||
"Antwortoptionen:\n"
|
||||
"- 'OK' wenn der Artikel passt\n"
|
||||
"- 'Kein Wikipedia-Eintrag vorhanden.'\n"
|
||||
"- 'Alternativer Wikipedia-Artikel vorgeschlagen: <URL> | X | <Begründung>'\n\n")
|
||||
aggregated_prompt += "\n".join(batch_entries)
|
||||
debug_print("Aggregierter Prompt für Verifizierungs-Batch erstellt.")
|
||||
token_count = "n.v."
|
||||
@@ -520,22 +512,21 @@ def process_verification_only():
|
||||
main_sheet.update(values=[[wiki_confirm]], range_name=f"S{row_num}")
|
||||
main_sheet.update(values=[[alt_article]], range_name=f"U{row_num}")
|
||||
main_sheet.update(values=[[wiki_explanation]], range_name=f"V{row_num}")
|
||||
crm_branch = data[row_num-1][6] if len(data[row_num-1]) > 6 else "k.A."
|
||||
ext_branch = data[row_num-1][7] if len(data[row_num-1]) > 7 else "k.A."
|
||||
crm_branch = data[row_num-1][7] if len(data[row_num-1]) > 7 else "k.A."
|
||||
ext_branch = data[row_num-1][8] if len(data[row_num-1]) > 8 else "k.A."
|
||||
wiki_branch = data[row_num-1][14] if len(data[row_num-1]) > 14 else "k.A."
|
||||
wiki_cats = data[row_num-1][17] if len(data[row_num-1]) > 17 else "k.A."
|
||||
branch_result = evaluate_branche_chatgpt(crm_branch, ext_branch, wiki_branch, wiki_cats)
|
||||
main_sheet.update(values=[[branch_result["branch"]]], range_name=f"W{row_num}")
|
||||
main_sheet.update(values=[[branch_result["consistency"]]], range_name=f"Y{row_num}")
|
||||
main_sheet.update(values=[[str(token_count)]], range_name=f"AQ{row_num}")
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
main_sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
|
||||
main_sheet.update(values=[[Config.VERSION]], range_name=f"AP{row_num}")
|
||||
debug_print(f"Zeile {row_num} verifiziert: Antwort: {answer}")
|
||||
time.sleep(Config.RETRY_DELAY)
|
||||
debug_print("Verifizierungs-Batch abgeschlossen.")
|
||||
|
||||
# ==================== NEUER MODUS: CONTACT RESEARCH (via SerpAPI) ====================
|
||||
# ==================== CONTACT RESEARCH (Modus 6) ====================
|
||||
def process_contact_research():
|
||||
debug_print("Starte Contact Research (Modus 6)...")
|
||||
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
||||
@@ -563,7 +554,7 @@ def process_contact_research():
|
||||
time.sleep(Config.RETRY_DELAY * 1.5)
|
||||
debug_print("Contact Research abgeschlossen.")
|
||||
|
||||
# ==================== NEUER MODUS: CONTACTS (LinkedIn) ====================
|
||||
# ==================== CONTACTS (Modus 7) ====================
|
||||
def process_contacts():
|
||||
debug_print("Starte LinkedIn-Kontaktsuche (Modus 7)...")
|
||||
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
||||
@@ -582,98 +573,254 @@ def process_contacts():
|
||||
new_rows = []
|
||||
for idx, row in enumerate(data[1:], start=2):
|
||||
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
|
||||
website = row[3] if len(row) > 3 else ""
|
||||
debug_print(f"Verarbeite Firma: '{company_name}' (Zeile {idx}), Website: '{website}'")
|
||||
if not company_name or not website:
|
||||
debug_print("Überspringe, da Firmenname oder Website fehlt.")
|
||||
continue
|
||||
for pos in positions:
|
||||
debug_print(f"Suche nach Position: '{pos}' bei '{company_name}'")
|
||||
contact = search_linkedin_contact(company_name, website, pos)
|
||||
debug_print(f"Suche nach Position: '{pos}' bei '{search_name}'")
|
||||
contact = search_linkedin_contact(search_name, website, pos)
|
||||
if contact:
|
||||
debug_print(f"Kontakt gefunden: {contact}")
|
||||
new_rows.append([contact["Firmenname"], contact["Website"], "", contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
|
||||
new_rows.append([contact["Firmenname"], website, search_name, contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
|
||||
else:
|
||||
debug_print(f"Kein Kontakt für Position '{pos}' bei '{company_name}' gefunden.")
|
||||
debug_print(f"Kein Kontakt für Position '{pos}' bei '{search_name}' gefunden.")
|
||||
if new_rows:
|
||||
last_row = len(contacts_sheet.get_all_values()) + 1
|
||||
range_str = f"A{last_row}:H{last_row + len(new_rows) - 1}"
|
||||
contacts_sheet.update(range_str, new_rows)
|
||||
contacts_sheet.update(values=new_rows, range_name=range_str)
|
||||
debug_print(f"{len(new_rows)} Kontakte in 'Contacts' hinzugefügt.")
|
||||
else:
|
||||
debug_print("Keine Kontakte gefunden in der Haupttabelle.")
|
||||
|
||||
# ==================== BATCH-TOKEN-ZÄHLUNG (Modus 8) ====================
|
||||
def process_batch_token_count(batch_size=10):
|
||||
import tiktoken
|
||||
def count_tokens(text, model="gpt-3.5-turbo"):
|
||||
encoding = tiktoken.encoding_for_model(model)
|
||||
tokens = encoding.encode(text)
|
||||
return len(tokens)
|
||||
debug_print("Starte Batch-Token-Zählung (Modus 8)...")
|
||||
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)
|
||||
main_sheet = sh.sheet1
|
||||
data = main_sheet.get_all_values()
|
||||
for i in range(2, len(data)+1, batch_size):
|
||||
batch_rows = data[i-1:i-1+batch_size]
|
||||
aggregated_prompt = ""
|
||||
for row in batch_rows:
|
||||
info = []
|
||||
if len(row) > 1:
|
||||
info.append(row[1]) # Firmenname
|
||||
if len(row) > 2:
|
||||
info.append(row[2]) # Kurzform
|
||||
if len(row) > 3:
|
||||
info.append(row[3]) # Website
|
||||
if len(row) > 4:
|
||||
info.append(row[4]) # Ort
|
||||
if len(row) > 5:
|
||||
info.append(row[5]) # Beschreibung
|
||||
if len(row) > 6:
|
||||
info.append(row[6]) # Aktuelle Branche
|
||||
aggregated_prompt += "; ".join(info) + "\n"
|
||||
token_count = count_tokens(aggregated_prompt)
|
||||
debug_print(f"Batch beginnend in Zeile {i}: {token_count} Tokens")
|
||||
for j in range(i, min(i+batch_size, len(data)+1)):
|
||||
main_sheet.update(values=[[str(token_count)]], range_name=f"AQ{j}")
|
||||
time.sleep(Config.RETRY_DELAY)
|
||||
debug_print("Batch-Token-Zählung abgeschlossen.")
|
||||
|
||||
# ==================== ALIGNMENT DEMO FÜR HAUPTBLATT & 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.")
|
||||
|
||||
# ==================== GOOGLE SHEET HANDLER (Hauptdaten) ====================
|
||||
class GoogleSheetHandler:
|
||||
def __init__(self):
|
||||
self.sheet = None
|
||||
self.sheet_values = []
|
||||
self._connect()
|
||||
def _connect(self):
|
||||
scope = ["https://www.googleapis.com/auth/spreadsheets"]
|
||||
creds = ServiceAccountCredentials.from_json_keyfile_name(Config.CREDENTIALS_FILE, scope)
|
||||
self.sheet = gspread.authorize(creds).open_by_url(Config.SHEET_URL).sheet1
|
||||
self.sheet_values = self.sheet.get_all_values()
|
||||
def get_start_index(self):
|
||||
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)
|
||||
|
||||
# ==================== DATA PROCESSOR (Regulärer Modus) ====================
|
||||
class DataProcessor:
|
||||
def __init__(self):
|
||||
self.sheet_handler = GoogleSheetHandler()
|
||||
self.wiki_scraper = WikipediaScraper()
|
||||
def process_rows(self, num_rows=None):
|
||||
if MODE == "2":
|
||||
print("Re-Evaluierungsmodus: Verarbeitung aller Zeilen mit '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, force_all=True)
|
||||
elif MODE == "3":
|
||||
print("Alignment-Demo-Modus: Hauptblatt und Contacts aktualisieren.")
|
||||
alignment_demo_full()
|
||||
elif MODE == "4":
|
||||
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
|
||||
if len(row) <= 39 or row[39].strip() == "":
|
||||
self._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
|
||||
elif MODE == "5":
|
||||
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
|
||||
if len(row) <= 40 or row[40].strip() == "":
|
||||
self._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
|
||||
elif MODE == "51":
|
||||
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
|
||||
# Hier: Nur Zeilen ohne Verifizierungstimestamp (Spalte Y, z.B.) werden verarbeitet
|
||||
if len(row) <= 25 or row[24].strip() == "":
|
||||
_process_verification_row(i, row)
|
||||
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
|
||||
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[3] if len(row_data) > 3 else ""
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
# Wiki-Auswertung (Spalten L bis R, Timestamp AO)
|
||||
if force_all or process_wiki:
|
||||
if len(row_data) <= 39 or row_data[39].strip() == "":
|
||||
if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."]:
|
||||
wiki_url = row_data[11].strip()
|
||||
try:
|
||||
wiki_data = self.wiki_scraper.extract_company_data(wiki_url)
|
||||
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.')
|
||||
]
|
||||
self.sheet_handler.sheet.update(values=[wiki_values], range_name=f"L{row_num}:R{row_num}")
|
||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
|
||||
else:
|
||||
debug_print(f"Zeile {row_num}: Wikipedia-Timestamp bereits gesetzt – überspringe Wiki-Auswertung.")
|
||||
# ChatGPT-Auswertung (Branche & FSM, etc. – Spalten R, AG, Y, Z, AE, AF; Timestamp in AO, Version in AP)
|
||||
if force_all or process_chatgpt:
|
||||
if len(row_data) <= 40 or row_data[40].strip() == "":
|
||||
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.")
|
||||
self.sheet_handler.sheet.update(values=[[abgleich_result]], range_name=f"AG{row_num}")
|
||||
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"R{row_num}")
|
||||
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' in locals() else {})
|
||||
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."
|
||||
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' in locals() else {})
|
||||
discrepancy = explanation
|
||||
else:
|
||||
discrepancy = "ok"
|
||||
self.sheet_handler.sheet.update(values=[[discrepancy]], range_name=f"AF{row_num}")
|
||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
|
||||
else:
|
||||
debug_print(f"Zeile {row_num}: ChatGPT-Timestamp bereits gesetzt – überspringe ChatGPT-Auswertung.")
|
||||
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.')}, "
|
||||
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)
|
||||
|
||||
# ==================== MAIN PROGRAMM ====================
|
||||
if __name__ == "__main__":
|
||||
import argparse
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--mode", type=str, help="Modus: 1,2,3,4,5,6,7,8 oder 51")
|
||||
parser.add_argument("--mode", type=str, help="Modus: 1,2,3,4,5,6,7,51 oder 8")
|
||||
parser.add_argument("--num_rows", type=int, default=0, help="Anzahl der zu bearbeitenden Zeilen (nur für Modus 1)")
|
||||
args = parser.parse_args()
|
||||
if not args.mode:
|
||||
print("Modi:")
|
||||
print("1 = Regulärer Modus")
|
||||
print("2 = Re-Evaluierungsmodus (nur Zeilen mit 'x' in Spalte A)")
|
||||
print("3 = Alignment-Demo (Header in Hauptblatt und Contacts)")
|
||||
print("3 = Alignment-Demo (Hauptblatt & Contacts)")
|
||||
print("4 = Nur Wikipedia-Suche (Zeilen ohne Wikipedia-Timestamp)")
|
||||
print("5 = Nur ChatGPT-Bewertung (Zeilen ohne ChatGPT-Timestamp)")
|
||||
print("6 = Contact Research (via SerpAPI)")
|
||||
print("7 = Contacts (LinkedIn)")
|
||||
print("8 = Batch-Token-Zählung")
|
||||
print("51 = Nur Verifizierung (Wikipedia + Brancheneinordnung)")
|
||||
print("51 = Nur Verifizierung (gezielte Branchen- & FSM-Evaluierung)")
|
||||
args.mode = input("Wählen Sie den Modus: ").strip()
|
||||
MODE = args.mode
|
||||
if MODE == "1":
|
||||
try:
|
||||
num_rows = int(input("Wieviele Zeilen sollen überprüft werden? "))
|
||||
except Exception as e:
|
||||
print("Ungültige Eingabe. Bitte eine Zahl eingeben.")
|
||||
exit(1)
|
||||
num_rows = args.num_rows if args.num_rows > 0 else int(input("Wieviele Zeilen sollen überprüft werden? "))
|
||||
processor = DataProcessor()
|
||||
processor.process_rows(num_rows)
|
||||
elif MODE in ["2", "3"]:
|
||||
processor = DataProcessor()
|
||||
processor.process_rows()
|
||||
elif MODE == "4":
|
||||
gh = GoogleSheetHandler()
|
||||
start_index = gh.get_start_index(39) # Wiki-Timestamp in Spalte AN
|
||||
debug_print(f"Wiki-Modus: Starte bei Zeile {start_index+1}")
|
||||
processor = DataProcessor()
|
||||
processor.process_rows()
|
||||
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||
if len(row) <= 39 or row[39].strip() == "":
|
||||
processor._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
|
||||
elif MODE == "5":
|
||||
gh = GoogleSheetHandler()
|
||||
start_index = gh.get_start_index(40) # ChatGPT-Timestamp in Spalte AO
|
||||
debug_print(f"ChatGPT-Modus: Starte bei Zeile {start_index+1}")
|
||||
processor = DataProcessor()
|
||||
processor.process_rows()
|
||||
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||||
if len(row) <= 40 or row[40].strip() == "":
|
||||
processor._process_single_row(i, row, process_wiki=False, process_chatgpt=True)
|
||||
elif MODE == "51":
|
||||
process_verification_only()
|
||||
elif MODE == "6":
|
||||
process_contact_research()
|
||||
elif MODE == "7":
|
||||
process_contacts()
|
||||
elif MODE == "8":
|
||||
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)
|
||||
main_sheet = sh.sheet1
|
||||
data = main_sheet.get_all_values()
|
||||
batch_entries = []
|
||||
row_indices = []
|
||||
for i, row in enumerate(data[1:], start=2):
|
||||
batch_entries.append(" ".join(row))
|
||||
row_indices.append(i)
|
||||
if len(batch_entries) == Config.BATCH_SIZE:
|
||||
break
|
||||
aggregated_text = "\n".join(batch_entries)
|
||||
token_count = "n.v."
|
||||
if tiktoken:
|
||||
try:
|
||||
enc = tiktoken.encoding_for_model(Config.TOKEN_MODEL)
|
||||
token_count = len(enc.encode(aggregated_text))
|
||||
except Exception as e:
|
||||
debug_print(f"Fehler beim Token-Counting: {e}")
|
||||
for row_num in row_indices:
|
||||
main_sheet.update(values=[[str(token_count)]], range_name=f"AQ{row_num}")
|
||||
debug_print(f"Batch-Token-Zählung abgeschlossen. Token: {token_count}")
|
||||
elif MODE == "51":
|
||||
process_verification_only()
|
||||
process_batch_token_count()
|
||||
print(f"\n✅ Auswertung abgeschlossen ({Config.VERSION})")
|
||||
|
||||
Reference in New Issue
Block a user