1218 lines
57 KiB
Python
1218 lines
57 KiB
Python
import os
|
||
import time
|
||
import re
|
||
import gspread
|
||
import wikipedia
|
||
import requests
|
||
import openai
|
||
from bs4 import BeautifulSoup
|
||
from oauth2client.service_account import ServiceAccountCredentials
|
||
from datetime import datetime
|
||
from difflib import SequenceMatcher
|
||
import unicodedata
|
||
import csv
|
||
|
||
# Optional: tiktoken für Token-Zählung (Modus 8)
|
||
try:
|
||
import tiktoken
|
||
except ImportError:
|
||
tiktoken = None
|
||
|
||
# ==================== KONFIGURATION ====================
|
||
class Config:
|
||
VERSION = "v1.3.18" # v1.3.18: Neuer Modus 8 (Batch-Token-Zählung) & Modus 51 (nur Verifizierung)
|
||
LANG = "de"
|
||
CREDENTIALS_FILE = "service_account.json"
|
||
SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
|
||
MAX_RETRIES = 3
|
||
RETRY_DELAY = 5
|
||
LOG_CSV = "gpt_antworten_log.csv"
|
||
SIMILARITY_THRESHOLD = 0.65
|
||
DEBUG = True
|
||
WIKIPEDIA_SEARCH_RESULTS = 5
|
||
HTML_PARSER = "html.parser"
|
||
BATCH_SIZE = 10
|
||
TOKEN_MODEL = "gpt-3.5-turbo"
|
||
|
||
# ==================== RETRY-DECORATOR ====================
|
||
def retry_on_failure(func):
|
||
def wrapper(*args, **kwargs):
|
||
for attempt in range(Config.MAX_RETRIES):
|
||
try:
|
||
return func(*args, **kwargs)
|
||
except Exception as e:
|
||
print(f"⚠️ Fehler bei {func.__name__} (Versuch {attempt+1}): {str(e)[:100]}")
|
||
time.sleep(Config.RETRY_DELAY)
|
||
return None
|
||
return wrapper
|
||
|
||
# ==================== LOGGING & HELPER FUNCTIONS ====================
|
||
if not os.path.exists("Log"):
|
||
os.makedirs("Log")
|
||
LOG_FILE = os.path.join("Log", f"{datetime.now().strftime('%d-%m-%Y_%H-%M')}_{Config.VERSION.replace('.', '')}.txt")
|
||
|
||
def debug_print(message):
|
||
if Config.DEBUG:
|
||
print(f"[DEBUG] {message}")
|
||
try:
|
||
with open(LOG_FILE, "a", encoding="utf-8") as f:
|
||
f.write(f"[DEBUG] {message}\n")
|
||
except Exception as e:
|
||
print(f"[DEBUG] Log-Schreibfehler: {e}")
|
||
|
||
def clean_text(text):
|
||
if not text:
|
||
return "k.A."
|
||
text = unicodedata.normalize("NFKC", str(text))
|
||
text = re.sub(r'\[\d+\]', '', text)
|
||
text = re.sub(r'\s+', ' ', text).strip()
|
||
return text if text else "k.A."
|
||
|
||
def normalize_company_name(name):
|
||
if not name:
|
||
return ""
|
||
forms = [
|
||
r'gmbh', r'g\.m\.b\.h\.', r'ug', r'u\.g\.', r'ug \(haftungsbeschränkt\)',
|
||
r'u\.g\. \(haftungsbeschränkt\)', r'ag', r'a\.g\.', r'ohg', r'o\.h\.g\.',
|
||
r'kg', r'k\.g\.', r'gmbh & co\.?\s*kg', r'g\.m\.b\.h\. & co\.?\s*k\.g\.',
|
||
r'ag & co\.?\s*kg', r'a\.g\. & co\.?\s*k\.g\.', r'e\.k\.', r'e\.kfm\.',
|
||
r'e\.kfr\.', r'ltd\.', r'ltd & co\.?\s*kg', r's\.a r\.l\.', r'stiftung',
|
||
r'genossenschaft', r'ggmbh', r'gug', r'partg', r'partgmbb', r'kgaa', r'se',
|
||
r'og', r'o\.g\.', r'e\.u\.', r'ges\.n\.b\.r\.', r'genmbh', r'verein',
|
||
r'kollektivgesellschaft', r'kommanditgesellschaft', r'einzelfirma', r'sàrl',
|
||
r'sa', r'sagl', r'gmbh & co\.?\s*ohg', r'ag & co\.?\s*ohg', r'gmbh & co\.?\s*kgaa',
|
||
r'ag & co\.?\s*kgaa', r's\.a\.', r's\.p\.a\.', r'b\.v\.', r'n\.v\.'
|
||
]
|
||
pattern = r'\b(' + '|'.join(forms) + r')\b'
|
||
normalized = re.sub(pattern, '', name, flags=re.IGNORECASE)
|
||
normalized = re.sub(r'[\-–]', ' ', normalized)
|
||
normalized = re.sub(r'\s+', ' ', normalized).strip()
|
||
return normalized.lower()
|
||
|
||
def extract_numeric_value(raw_value, is_umsatz=False):
|
||
raw_value = raw_value.strip()
|
||
if not raw_value:
|
||
return "k.A."
|
||
raw_value = re.sub(r'\b(ca\.?|circa|über)\b', '', raw_value, flags=re.IGNORECASE)
|
||
raw = raw_value.lower().replace("\xa0", " ")
|
||
match = re.search(r'([\d.,]+)', raw, flags=re.UNICODE)
|
||
if not match or not match.group(1).strip():
|
||
debug_print(f"Keine numerischen Zeichen gefunden im Rohtext: '{raw_value}'")
|
||
return "k.A."
|
||
num_str = match.group(1)
|
||
if ',' in num_str:
|
||
num_str = num_str.replace('.', '').replace(',', '.')
|
||
try:
|
||
num = float(num_str)
|
||
except Exception as e:
|
||
debug_print(f"Fehler bei der Umwandlung von '{num_str}' (Rohtext: '{raw_value}'): {e}")
|
||
return raw_value
|
||
else:
|
||
num_str = num_str.replace(' ', '').replace('.', '')
|
||
try:
|
||
num = float(num_str)
|
||
except Exception as e:
|
||
debug_print(f"Fehler bei der Umwandlung von '{num_str}' (Rohtext: '{raw_value}'): {e}")
|
||
return raw_value
|
||
if is_umsatz:
|
||
if "mrd" in raw or "milliarden" in raw:
|
||
num *= 1000
|
||
elif "mio" in raw or "millionen" in raw:
|
||
pass
|
||
else:
|
||
num /= 1e6
|
||
return str(int(round(num)))
|
||
else:
|
||
return str(int(round(num)))
|
||
|
||
def compare_umsatz_values(crm, wiki):
|
||
debug_print(f"Vergleich CRM Umsatz: '{crm}' mit Wikipedia Umsatz: '{wiki}'")
|
||
try:
|
||
crm_val = float(crm)
|
||
wiki_val = float(wiki)
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Umwandeln der Werte: CRM='{crm}', Wiki='{wiki}': {e}")
|
||
return "Daten unvollständig"
|
||
if crm_val == 0:
|
||
return "CRM Umsatz 0"
|
||
diff = abs(crm_val - wiki_val) / crm_val
|
||
if diff < 0.1:
|
||
return "OK"
|
||
else:
|
||
diff_mio = abs(crm_val - wiki_val)
|
||
return f"Abweichung: {int(round(diff_mio))} Mio €"
|
||
|
||
def evaluate_umsatz_chatgpt(company_name, wiki_umsatz):
|
||
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: {e}")
|
||
return "k.A."
|
||
openai.api_key = api_key
|
||
prompt = (
|
||
f"Bitte schätze den Umsatz in Mio. Euro für das Unternehmen '{company_name}'. "
|
||
f"Die Wikipedia-Daten zeigen: '{wiki_umsatz}'. "
|
||
"Antworte nur mit der Zahl."
|
||
)
|
||
try:
|
||
response = openai.ChatCompletion.create(
|
||
model="gpt-3.5-turbo",
|
||
messages=[{"role": "user", "content": prompt}],
|
||
temperature=0.0
|
||
)
|
||
result = response.choices[0].message.content.strip()
|
||
debug_print(f"ChatGPT Umsatzschätzung: '{result}'")
|
||
try:
|
||
value = float(result.replace(',', '.'))
|
||
return str(int(round(value)))
|
||
except Exception as conv_e:
|
||
debug_print(f"Fehler bei der Verarbeitung der Umsatzschätzung '{result}': {conv_e}")
|
||
return result
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Aufruf der ChatGPT API für Umsatzschätzung: {e}")
|
||
return "k.A."
|
||
|
||
def validate_article_with_chatgpt(crm_data, wiki_data):
|
||
crm_headers = "Firmenname;Website;Ort;Beschreibung;Aktuelle Branche;Beschreibung Branche extern;Anzahl Techniker;Umsatz (CRM);Anzahl Mitarbeiter (CRM)"
|
||
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 dabei, dass leichte Abweichungen in Firmennamen (z. B. unterschiedliche Schreibweisen, Mutter-Tochter-Beziehungen) "
|
||
"oder im Ort (z. B. 'Oberndorf' vs. 'Oberndorf/Neckar') tolerierbar sind. "
|
||
"Vergleiche insbesondere den Firmennamen, den Ort und die Branche. Unterschiede im Umsatz können bis zu 10% abweichen. "
|
||
"Wenn die Daten im Wesentlichen übereinstimmen, antworte ausschließlich mit 'OK'. "
|
||
"Falls nicht, nenne bitte den wichtigsten Grund und eine kurze Begründung, warum die Abweichung plausibel sein könnte.\n\n"
|
||
f"CRM-Daten:\n{crm_headers}\n{crm_data}\n\n"
|
||
f"Wikipedia-Daten:\n{wiki_headers}\n{wiki_data}\n\n"
|
||
"Antwort: "
|
||
)
|
||
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: {e}")
|
||
return "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"Validierungsantwort ChatGPT: '{result}'")
|
||
return result
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Validierungs-API-Aufruf: {e}")
|
||
return "k.A."
|
||
|
||
def evaluate_branche_chatgpt(crm_branche, beschreibung, wiki_branche, wiki_kategorien):
|
||
# Lade das Ziel-Branchenschema aus der CSV
|
||
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]
|
||
return branches
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Laden des Ziel-Branchenschemas: {e}")
|
||
return []
|
||
target_branches = load_target_branches()
|
||
target_branches_str = "\n".join(target_branches)
|
||
focus_branches = [
|
||
"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"
|
||
]
|
||
focus_branches_str = "\n".join(focus_branches)
|
||
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
|
||
additional_instruction = ""
|
||
if wiki_branche.strip() == "k.A.":
|
||
additional_instruction = (
|
||
"Da keine Wikipedia-Branche vorliegt, berücksichtige bitte die Wikipedia-Kategorien mit erhöhter Gewichtung, "
|
||
"insbesondere wenn Hinweise auf Personentransport oder öffentliche Verkehrsdienstleistungen vorliegen. "
|
||
)
|
||
system_prompt = (
|
||
"Du bist ein Experte im Field Service Management. Deine Aufgabe ist es, ein Unternehmen basierend auf folgenden Angaben einer Branche zuzuordnen.\n\n"
|
||
f"CRM-Branche (Spalte F): {crm_branche}\n"
|
||
f"Branchenbeschreibung (Spalte G): {beschreibung}\n"
|
||
f"Wikipedia-Branche (Spalte N): {wiki_branche}\n"
|
||
f"Wikipedia-Kategorien (Spalte Q): {wiki_kategorien}\n\n"
|
||
+ additional_instruction +
|
||
"Das Ziel-Branchenschema umfasst ALLE gültigen Branchen, also sowohl Fokusbranchen als auch weitere, z. B. 'Housing > Sozialbau Unternehmen'.\n"
|
||
"Das vollständige Ziel-Branchenschema lautet:\n"
|
||
f"{target_branches_str}\n\n"
|
||
"Falls das Unternehmen mehreren Branchen zugeordnet werden könnte, wähle bitte bevorzugt eine Branche aus der folgenden Fokusliste, sofern zutreffend:\n"
|
||
f"{focus_branches_str}\n\n"
|
||
"Gewichtung der Angaben:\n"
|
||
"1. Wikipedia-Branche (Spalte N) zusammen mit Wikipedia-Kategorien (Spalte Q) (höchste Priorität, wenn verifiziert, ansonsten erhöhte Gewichtung der Kategorien)\n"
|
||
"2. Branchenbeschreibung (Spalte G)\n"
|
||
"3. CRM-Branche (Spalte F)\n\n"
|
||
"Ordne das Unternehmen exakt einer der oben genannten Branchen zu (es dürfen keine zusätzlichen Branchen erfunden werden). "
|
||
"Bitte antworte in folgendem Format (ohne zusätzliche Informationen):\n"
|
||
"Branche: <vorgeschlagene Branche>\n"
|
||
"Übereinstimmung: <ok oder X>\n"
|
||
"Begründung: <kurze Begründung, falls abweichend, ansonsten leer>"
|
||
)
|
||
try:
|
||
response = openai.ChatCompletion.create(
|
||
model="gpt-3.5-turbo",
|
||
messages=[{"role": "system", "content": system_prompt}],
|
||
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):
|
||
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):
|
||
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 auf Basis öffentlich zugänglicher Informationen (vor allem verifizierte Wikipedia-Daten) "
|
||
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'."
|
||
)
|
||
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):
|
||
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. "
|
||
"Berücksichtige dabei öffentlich zugängliche Informationen wie Branche, Umsatz, Mitarbeiterzahl und andere relevante Daten."
|
||
)
|
||
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:
|
||
num = int(value)
|
||
except Exception:
|
||
return "k.A."
|
||
if num < 50:
|
||
return "<50 Techniker"
|
||
elif num < 100:
|
||
return ">100 Techniker"
|
||
elif num < 200:
|
||
return ">200 Techniker"
|
||
else:
|
||
return ">500 Techniker"
|
||
|
||
def wait_for_sheet_update(sheet, cell, expected_value, timeout=5):
|
||
start_time = time.time()
|
||
while time.time() - start_time < timeout:
|
||
try:
|
||
current_value = sheet.acell(cell).value
|
||
if current_value == expected_value:
|
||
return True
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Lesen von Zelle {cell}: {e}")
|
||
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
|
||
query = f'site:linkedin.com/in "{position_query}" "{company_name}"'
|
||
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 and len(data["organic_results"]) > 0:
|
||
result = data["organic_results"][0]
|
||
title = result.get("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 = ""
|
||
return {"Firmenname": company_name, "Website": website, "Vorname": firstname, "Nachname": lastname, "Position": pos}
|
||
else:
|
||
return {"Firmenname": company_name, "Website": website, "Vorname": "", "Nachname": "", "Position": title}
|
||
else:
|
||
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}"'
|
||
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(self, row_num, row_data):
|
||
# Verarbeitung: Extrahiere relevante Daten für die Verifizierung
|
||
company_name = row_data[1] if len(row_data) > 1 else ""
|
||
website = row_data[3] if len(row_data) > 3 else ""
|
||
crm_description = row_data[7] if len(row_data) > 7 else ""
|
||
wiki_url = row_data[11] if len(row_data) > 11 and row_data[11].strip() not in ["", "k.A."] else "k.A."
|
||
wiki_absatz = row_data[12] if len(row_data) > 12 else "k.A."
|
||
wiki_categories = row_data[16] if len(row_data) > 16 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
|
||
|
||
def process_verification_only():
|
||
debug_print("Starte Verifizierungsmodus (Modus 51) im Batch-Prozess...")
|
||
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_size = Config.BATCH_SIZE
|
||
batch_entries = []
|
||
row_indices = []
|
||
for i, row in enumerate(data[1:], start=2):
|
||
if len(row) <= 19 or row[18].strip() == "":
|
||
entry_text = _process_verification_row(None, i, row)
|
||
batch_entries.append(entry_text)
|
||
row_indices.append(i)
|
||
if len(batch_entries) == 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. "
|
||
"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")
|
||
aggregated_prompt += "\n".join(batch_entries)
|
||
debug_print("Aggregierter Prompt für Verifizierungs-Batch erstellt.")
|
||
token_count = "n.v."
|
||
if tiktoken:
|
||
try:
|
||
enc = tiktoken.encoding_for_model(Config.TOKEN_MODEL)
|
||
token_count = len(enc.encode(aggregated_prompt))
|
||
debug_print(f"Token-Zahl für Batch: {token_count}")
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Token-Counting: {e}")
|
||
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 (Verifizierung): {e}")
|
||
return
|
||
openai.api_key = api_key
|
||
try:
|
||
response = openai.ChatCompletion.create(
|
||
model=Config.TOKEN_MODEL,
|
||
messages=[{"role": "system", "content": aggregated_prompt}],
|
||
temperature=0.0
|
||
)
|
||
result = response.choices[0].message.content.strip()
|
||
debug_print(f"Antwort ChatGPT Verifizierung Batch: {result}")
|
||
except Exception as e:
|
||
debug_print(f"Fehler bei der ChatGPT Anfrage für Verifizierung: {e}")
|
||
return
|
||
answers = result.split("\n")
|
||
for idx, row_num in enumerate(row_indices):
|
||
answer = "k.A."
|
||
for line in answers:
|
||
if line.strip().startswith(f"Eintrag {row_num}:"):
|
||
answer = line.split(":", 1)[1].strip()
|
||
break
|
||
if answer.upper() == "OK":
|
||
wiki_confirm = "OK"
|
||
alt_article = ""
|
||
wiki_explanation = ""
|
||
elif answer.upper() == "KEIN WIKIPEDIA-EINTRAG VORHANDEN.":
|
||
wiki_confirm = ""
|
||
alt_article = "Kein Wikipedia-Eintrag vorhanden."
|
||
wiki_explanation = ""
|
||
elif answer.startswith("Alternativer Wikipedia-Artikel vorgeschlagen:"):
|
||
parts = answer.split(":", 1)[1].split("|")
|
||
alt_article = parts[0].strip() if len(parts) > 0 else "k.A."
|
||
wiki_explanation = parts[2].strip() if len(parts) > 2 else ""
|
||
wiki_confirm = "X"
|
||
else:
|
||
wiki_confirm = ""
|
||
alt_article = answer
|
||
wiki_explanation = answer
|
||
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."
|
||
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.")
|
||
|
||
# ==================== GOOGLE SHEET HANDLER ====================
|
||
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[13] if len(row) > 13 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)
|
||
|
||
# ==================== ALIGNMENT DEMO (Hauptblatt) ====================
|
||
def alignment_demo(sheet):
|
||
new_headers = [
|
||
[
|
||
"ReEval Flag", # A
|
||
"CRM Name", # B
|
||
"CRM Kurzform", # C
|
||
"CRM Website", # D
|
||
"CRM Ort", # E
|
||
"CRM Beschreibung", # F
|
||
"CRM Branche", # G
|
||
"CRM Beschreibung Branche extern", # H
|
||
"CRM Anzahl Techniker", # I
|
||
"CRM Umsatz", # J
|
||
"CRM Anzahl Mitarbeiter", # K
|
||
"CRM Vorschlag Wiki URL", # L
|
||
"Wiki URL", # M
|
||
"Wiki Absatz", # N
|
||
"Wiki Branche", # O
|
||
"Wiki Umsatz", # P
|
||
"Wiki Mitarbeiter", # Q
|
||
"Wiki Kategorien", # R
|
||
"Chat Wiki Konsistenzprüfung", # S
|
||
"Chat Begründung Wiki Inkonsistenz", # T
|
||
"Chat Vorschlag Wiki Artikel", # U
|
||
"Begründung bei Abweichung", # V
|
||
"Chat Vorschlag Branche", # W
|
||
"Chat Konsistenz Branche", # X
|
||
"Chat Begründung Abweichung Branche", # Y
|
||
"Chat Prüfung FSM Relevanz", # Z
|
||
"Chat Begründung für FSM Relevanz", # AA
|
||
"Chat Schätzung Anzahl Mitarbeiter", # AB
|
||
"Chat Konsistenzprüfung Mitarbeiterzahl", # AC
|
||
"Chat Begründung Abweichung Mitarbeiterzahl", # AD
|
||
"Chat Einschätzung Anzahl Servicetechniker", # AE
|
||
"Chat Begründung Abweichung Anzahl Servicetechniker", # AF
|
||
"Chat Schätzung Umsatz", # AG
|
||
"Chat Begründung Abweichung Umsatz", # AH
|
||
"Linked Serviceleiter gefunden", # AI
|
||
"Linked It-Leiter gefunden", # AJ
|
||
"Linked Management gefunden", # AK
|
||
"Linked Disponent gefunden", # AL
|
||
"Contact Search Timestamp", # AM
|
||
"Wikipedia Timestamp", # AN
|
||
"Timestamp letzte Prüfung", # AO
|
||
"Version", # AP
|
||
"Tokens" # AQ
|
||
],
|
||
[ # <- Hier das fehlende Komma eingefügt
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"CRM",
|
||
"Wikipediascraper",
|
||
"Wikipediascraper",
|
||
"Wikipediascraper",
|
||
"Wikipediascraper",
|
||
"Wikipediascraper",
|
||
"Wikipediascraper",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"Chat GPT API",
|
||
"LinkedIn (via SerpApi)",
|
||
"LinkedIn (via SerpApi)",
|
||
"LinkedIn (via SerpApi)",
|
||
"LinkedIn (via SerpApi)",
|
||
"System",
|
||
"System",
|
||
"System",
|
||
"System",
|
||
"System"
|
||
]
|
||
]
|
||
header_range = "A1:AQ2"
|
||
sheet.update(values=[new_headers], range_name=header_range)
|
||
|
||
print("Alignment-Demo abgeschlossen: Neue Spaltenüberschriften in Zeile 11200 geschrieben.")
|
||
|
||
|
||
|
||
# ==================== WIKIPEDIA SCRAPER ====================
|
||
class WikipediaScraper:
|
||
def __init__(self):
|
||
wikipedia.set_lang(Config.LANG)
|
||
def _get_full_domain(self, website):
|
||
if not website:
|
||
return ""
|
||
website = website.lower().strip()
|
||
website = re.sub(r'^https?:\/\/', '', website)
|
||
website = re.sub(r'^www\.', '', website)
|
||
return website.split('/')[0]
|
||
def _generate_search_terms(self, company_name, website):
|
||
terms = []
|
||
full_domain = self._get_full_domain(website)
|
||
if full_domain:
|
||
terms.append(full_domain)
|
||
normalized_name = normalize_company_name(company_name)
|
||
candidate = " ".join(normalized_name.split()[:2]).strip()
|
||
if candidate and candidate not in terms:
|
||
terms.append(candidate)
|
||
if normalized_name and normalized_name not in terms:
|
||
terms.append(normalized_name)
|
||
debug_print(f"Generierte Suchbegriffe: {terms}")
|
||
return terms
|
||
def _validate_article(self, page, company_name, website):
|
||
full_domain = self._get_full_domain(website)
|
||
domain_found = False
|
||
if full_domain:
|
||
try:
|
||
html_raw = requests.get(page.url).text
|
||
soup = BeautifulSoup(html_raw, Config.HTML_PARSER)
|
||
infobox = soup.find('table', class_=lambda c: c and 'infobox' in c.lower())
|
||
if infobox:
|
||
links = infobox.find_all('a', href=True)
|
||
for link in links:
|
||
href = link.get('href').lower()
|
||
if href.startswith('/wiki/datei:'):
|
||
continue
|
||
if full_domain in href:
|
||
debug_print(f"Definitiver Link-Match in Infobox gefunden: {href}")
|
||
domain_found = True
|
||
break
|
||
if not domain_found and hasattr(page, 'externallinks'):
|
||
for ext_link in page.externallinks:
|
||
if full_domain in ext_link.lower():
|
||
debug_print(f"Definitiver Link-Match in externen Links gefunden: {ext_link}")
|
||
domain_found = True
|
||
break
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Extrahieren von Links: {str(e)}")
|
||
normalized_title = normalize_company_name(page.title)
|
||
normalized_company = normalize_company_name(company_name)
|
||
similarity = SequenceMatcher(None, normalized_title, normalized_company).ratio()
|
||
debug_print(f"Ähnlichkeit (normalisiert): {similarity:.2f} ({normalized_title} vs {normalized_company})")
|
||
threshold = 0.60 if domain_found else Config.SIMILARITY_THRESHOLD
|
||
return similarity >= threshold
|
||
def extract_first_paragraph(self, page_url):
|
||
try:
|
||
response = requests.get(page_url)
|
||
soup = BeautifulSoup(response.text, Config.HTML_PARSER)
|
||
paragraphs = soup.find_all('p')
|
||
for p in paragraphs:
|
||
text = clean_text(p.get_text())
|
||
if len(text) > 50:
|
||
return text
|
||
return "k.A."
|
||
except Exception as e:
|
||
debug_print(f"Fehler beim Extrahieren des ersten Absatzes: {e}")
|
||
return "k.A."
|
||
def extract_categories(self, soup):
|
||
cat_div = soup.find('div', id="mw-normal-catlinks")
|
||
if cat_div:
|
||
ul = cat_div.find('ul')
|
||
if ul:
|
||
cats = [clean_text(li.get_text()) for li in ul.find_all('li')]
|
||
return ", ".join(cats)
|
||
return "k.A."
|
||
def _extract_infobox_value(self, soup, target):
|
||
infobox = soup.find('table', class_=lambda c: c and any(kw in c.lower() for kw in ['infobox', 'vcard', 'unternehmen']))
|
||
if not infobox:
|
||
return "k.A."
|
||
keywords_map = {
|
||
'branche': ['branche', 'industrie', 'tätigkeit', 'geschäftsfeld', 'sektor', 'produkte', 'leistungen', 'aktivitäten', 'wirtschaftszweig'],
|
||
'umsatz': ['umsatz', 'jahresumsatz', 'konzernumsatz', 'gesamtumsatz', 'erlöse', 'umsatzerlöse', 'einnahmen', 'ergebnis', 'jahresergebnis'],
|
||
'mitarbeiter': ['mitarbeiter', 'beschäftigte', 'personal', 'mitarbeiterzahl', 'angestellte', 'belegschaft', 'personalstärke']
|
||
}
|
||
keywords = keywords_map.get(target, [])
|
||
for row in infobox.find_all('tr'):
|
||
header = row.find('th')
|
||
if header:
|
||
header_text = clean_text(header.get_text()).lower()
|
||
if any(kw in header_text for kw in keywords):
|
||
value = row.find('td')
|
||
if value:
|
||
raw_value = clean_text(value.get_text())
|
||
if target == 'branche':
|
||
clean_val = re.sub(r'\[.*?\]|\(.*?\)', '', raw_value)
|
||
return ' '.join(clean_val.split()).strip()
|
||
if target == 'umsatz':
|
||
return extract_numeric_value(raw_value, is_umsatz=True)
|
||
if target == 'mitarbeiter':
|
||
return extract_numeric_value(raw_value, is_umsatz=False)
|
||
return "k.A."
|
||
def extract_full_infobox(self, soup):
|
||
infobox = soup.find('table', class_=lambda c: c and any(kw in c.lower() for kw in ['infobox', 'vcard', 'unternehmen']))
|
||
if not infobox:
|
||
return "k.A."
|
||
return clean_text(infobox.get_text(separator=' | '))
|
||
def extract_fields_from_infobox_text(self, infobox_text, field_names):
|
||
result = {}
|
||
tokens = [token.strip() for token in infobox_text.split("|") if token.strip()]
|
||
for i, token in enumerate(tokens):
|
||
for field in field_names:
|
||
if field.lower() in token.lower():
|
||
j = i + 1
|
||
while j < len(tokens) and not tokens[j]:
|
||
j += 1
|
||
result[field] = tokens[j] if j < len(tokens) else "k.A."
|
||
return result
|
||
def extract_company_data(self, page_url):
|
||
if not page_url:
|
||
return {
|
||
'url': 'k.A.',
|
||
'first_paragraph': 'k.A.',
|
||
'branche': 'k.A.',
|
||
'umsatz': 'k.A.',
|
||
'mitarbeiter': 'k.A.',
|
||
'categories': 'k.A.',
|
||
'full_infobox': 'k.A.'
|
||
}
|
||
try:
|
||
response = requests.get(page_url)
|
||
soup = BeautifulSoup(response.text, Config.HTML_PARSER)
|
||
full_infobox = self.extract_full_infobox(soup)
|
||
extracted_fields = self.extract_fields_from_infobox_text(full_infobox, ['Branche', 'Umsatz', 'Mitarbeiter'])
|
||
raw_branche = extracted_fields.get('Branche', self._extract_infobox_value(soup, 'branche'))
|
||
raw_umsatz = extracted_fields.get('Umsatz', self._extract_infobox_value(soup, 'umsatz'))
|
||
raw_mitarbeiter = extracted_fields.get('Mitarbeiter', self._extract_infobox_value(soup, 'mitarbeiter'))
|
||
umsatz_val = extract_numeric_value(raw_umsatz, is_umsatz=True)
|
||
mitarbeiter_val = extract_numeric_value(raw_mitarbeiter, is_umsatz=False)
|
||
categories_val = self.extract_categories(soup)
|
||
first_paragraph = self.extract_first_paragraph(page_url)
|
||
return {
|
||
'url': page_url,
|
||
'first_paragraph': first_paragraph,
|
||
'branche': raw_branche,
|
||
'umsatz': umsatz_val,
|
||
'mitarbeiter': mitarbeiter_val,
|
||
'categories': categories_val,
|
||
'full_infobox': full_infobox
|
||
}
|
||
except Exception as e:
|
||
debug_print(f"Extraktionsfehler: {str(e)}")
|
||
return {
|
||
'url': 'k.A.',
|
||
'first_paragraph': 'k.A.',
|
||
'branche': 'k.A.',
|
||
'umsatz': 'k.A.',
|
||
'mitarbeiter': 'k.A.',
|
||
'categories': 'k.A.',
|
||
'full_infobox': 'k.A.'
|
||
}
|
||
@retry_on_failure
|
||
def search_company_article(self, company_name, website):
|
||
search_terms = self._generate_search_terms(company_name, website)
|
||
for term in search_terms:
|
||
try:
|
||
results = wikipedia.search(term, results=Config.WIKIPEDIA_SEARCH_RESULTS)
|
||
debug_print(f"Suchergebnisse für '{term}': {results}")
|
||
for title in results:
|
||
try:
|
||
page = wikipedia.page(title, auto_suggest=False)
|
||
if self._validate_article(page, company_name, website):
|
||
return page
|
||
except (wikipedia.exceptions.DisambiguationError, wikipedia.exceptions.PageError) as e:
|
||
debug_print(f"Seitenfehler: {str(e)}")
|
||
continue
|
||
except Exception as e:
|
||
debug_print(f"Suchfehler: {str(e)}")
|
||
continue
|
||
return None
|
||
|
||
# ==================== DATA PROCESSOR ====================
|
||
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)
|
||
elif MODE == "3":
|
||
print("Alignment-Demo-Modus: Schreibe neue Spaltenüberschriften in Hauptblatt und Contacts.")
|
||
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):
|
||
if len(row) <= 25 or row[24].strip() == "":
|
||
self._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, 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"AN{row_num}"
|
||
dt_chat_range = f"AO{row_num}"
|
||
ver_range = f"AP{row_num}"
|
||
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")
|
||
if process_wiki:
|
||
if len(row_data) <= 39 or row_data[39].strip() == "":
|
||
if len(row_data) > 10 and row_data[10].strip() not in ["", "k.A."]:
|
||
wiki_url = row_data[10].strip()
|
||
try:
|
||
company_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)
|
||
company_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)
|
||
company_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[10] if len(row_data) > 10 and row_data[10].strip() not in ["", "k.A."] else "k.A.",
|
||
company_data.get('url', 'k.A.'),
|
||
company_data.get('first_paragraph', 'k.A.'),
|
||
company_data.get('branche', 'k.A.'),
|
||
company_data.get('umsatz', 'k.A.'),
|
||
company_data.get('mitarbeiter', 'k.A.'),
|
||
company_data.get('categories', 'k.A.')
|
||
]
|
||
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)
|
||
else:
|
||
debug_print(f"Zeile {row_num}: Wikipedia-Timestamp bereits gesetzt – überspringe Wiki-Auswertung.")
|
||
if process_chatgpt:
|
||
if len(row_data) <= 40 or row_data[40].strip() == "":
|
||
crm_umsatz = row_data[8] if len(row_data) > 8 else "k.A."
|
||
abgleich_result = compare_umsatz_values(crm_umsatz, company_data.get('umsatz', '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[11:18])
|
||
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, company_data)
|
||
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, company_data)
|
||
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, company_data)
|
||
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=dt_chat_range)
|
||
else:
|
||
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)
|
||
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=ver_range)
|
||
debug_print(f"✅ Aktualisiert: URL: {company_data.get('url', 'k.A.')}, "
|
||
f"Branche: {company_data.get('branche', 'k.A.')}, Umsatz-Abgleich: {abgleich_result}, "
|
||
f"Validierung: {valid_result}, "
|
||
f"FSM: {fsm_result['suitability']}, Servicetechniker-Schätzung: {st_estimate}")
|
||
time.sleep(Config.RETRY_DELAY)
|
||
|
||
# ==================== GOOGLE SHEET HANDLER (für 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[13] if len(row) > 13 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)
|
||
|
||
# ==================== ALIGNMENT DEMO (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: CONTACT RESEARCH (via SerpAPI) ====================
|
||
def process_contact_research():
|
||
debug_print("Starte Contact Research (Modus 6)...")
|
||
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, 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 ""
|
||
if not company_name or not website:
|
||
continue
|
||
count_service = count_linkedin_contacts(search_name, website, "Serviceleiter")
|
||
count_it = count_linkedin_contacts(search_name, website, "IT-Leiter")
|
||
count_management = count_linkedin_contacts(search_name, website, "Geschäftsführer")
|
||
count_disponent = count_linkedin_contacts(search_name, website, "Disponent")
|
||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||
main_sheet.update(values=[[str(count_service)]], range_name=f"AI{i}")
|
||
main_sheet.update(values=[[str(count_it)]], range_name=f"AJ{i}")
|
||
main_sheet.update(values=[[str(count_management)]], range_name=f"AK{i}")
|
||
main_sheet.update(values=[[str(count_disponent)]], range_name=f"AL{i}")
|
||
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.")
|
||
time.sleep(Config.RETRY_DELAY * 1.5)
|
||
debug_print("Contact Research abgeschlossen.")
|
||
|
||
# ==================== NEUER MODUS: CONTACTS (LinkedIn) ====================
|
||
def process_contacts():
|
||
debug_print("Starte LinkedIn-Kontaktsuche...")
|
||
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.")
|
||
main_sheet = sh.sheet1
|
||
data = main_sheet.get_all_values()
|
||
positions = ["Serviceleiter", "IT-Leiter", "Leiter After Sales", "Leiter Einsatzplanung"]
|
||
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 ""
|
||
if not company_name or not website:
|
||
continue
|
||
for pos in positions:
|
||
debug_print(f"Suche nach Position: '{pos}' bei '{search_name}'")
|
||
contact = search_linkedin_contact(search_name, website, pos)
|
||
if contact:
|
||
new_rows.append([contact["Firmenname"], website, search_name, contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
|
||
else:
|
||
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(values=new_rows, range_name=range_str)
|
||
debug_print(f"{len(new_rows)} Kontakte in 'Contacts' hinzugefügt.")
|
||
else:
|
||
debug_print("Keine Kontakte gefunden.")
|
||
|
||
# ==================== NEUER MODUS: BATCH-PROZESSING MIT 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.")
|
||
|
||
# ==================== MAIN PROGRAMM ====================
|
||
if __name__ == "__main__":
|
||
import argparse
|
||
parser = argparse.ArgumentParser()
|
||
parser.add_argument("--mode", type=str, help="Modus: 1,2,3,4,5,6,7,51 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("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)")
|
||
args.mode = input("Wählen Sie den Modus: ").strip()
|
||
|
||
MODE = args.mode
|
||
if MODE == "1":
|
||
try:
|
||
num_rows = args.num_rows if args.num_rows > 0 else int(input("Wieviele Zeilen sollen überprüft werden? "))
|
||
except Exception as e:
|
||
print("Ungültige Eingabe. Bitte eine Zahl eingeben.")
|
||
exit(1)
|
||
processor = DataProcessor()
|
||
processor.process_rows(num_rows)
|
||
elif MODE in ["2", "3"]:
|
||
processor = DataProcessor()
|
||
processor.process_rows()
|
||
elif MODE == "4":
|
||
processor = DataProcessor()
|
||
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":
|
||
processor = DataProcessor()
|
||
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":
|
||
processor = DataProcessor()
|
||
for i, row in enumerate(processor.sheet_handler.sheet_values[1:], start=2):
|
||
if len(row) <= 25 or row[24].strip() == "":
|
||
processor._process_verification_row(i, row)
|
||
elif MODE == "6":
|
||
process_contact_research()
|
||
elif MODE == "7":
|
||
process_contacts()
|
||
elif MODE == "8":
|
||
process_batch_token_count()
|
||
print(f"\n✅ Auswertung abgeschlossen ({Config.VERSION})")
|