v1.3.7: Vollständige Version mit allen Funktionen, Modus 4: Nur Wikipedia-Suche
- Beibehaltung aller Funktionen aus früheren Versionen (Modi 1-3, LinkedIn Contacts) - Neuer Modus 4 implementiert, der ausschließlich Wikipedia-Suchen ausführt und keine ChatGPT-Anfragen stellt - Debug-Ausgaben wurden verbessert, um den Ablauf und die Ergebnisse besser nachvollziehen zu können - Startindex wird anhand des letzten Timestamps in Spalte AH korrekt ermittelt, sodass bestehende Datensätze nicht überschrieben werden
This commit is contained in:
@@ -14,7 +14,7 @@ import csv
|
|||||||
|
|
||||||
# ==================== KONFIGURATION ====================
|
# ==================== KONFIGURATION ====================
|
||||||
class Config:
|
class Config:
|
||||||
VERSION = "v1.3.7" # v1.3.7: Alle bisherigen Funktionen beibehalten, neuer Modus 4: Nur Wikipedia-Suche.
|
VERSION = "v1.3.7" # v1.3.7: Alle bisherigen Funktionen bleiben erhalten; neuer Modus 4: Nur Wikipedia-Suche.
|
||||||
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"
|
||||||
@@ -417,7 +417,7 @@ def process_contacts():
|
|||||||
else:
|
else:
|
||||||
debug_print("Keine Kontakte gefunden in der Haupttabelle.")
|
debug_print("Keine Kontakte gefunden in der Haupttabelle.")
|
||||||
|
|
||||||
# ==================== NEUE FUNKTION: NUR WIKIPEDIA-SUCHE (MODUS 4) ====================
|
# ==================== NEUER MODUS 4: NUR WIKIPEDIA-SUCHE ====================
|
||||||
def process_wikipedia_only():
|
def process_wikipedia_only():
|
||||||
debug_print("Starte ausschließlich Wikipedia-Suche (Modus 4)...")
|
debug_print("Starte ausschließlich Wikipedia-Suche (Modus 4)...")
|
||||||
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
gc = gspread.authorize(ServiceAccountCredentials.from_json_keyfile_name(
|
||||||
@@ -522,6 +522,508 @@ def alignment_demo(sheet):
|
|||||||
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.")
|
||||||
|
|
||||||
|
# ==================== 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
|
||||||
|
|
||||||
|
# ==================== 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 (Modus 3) ====================
|
||||||
|
def alignment_demo(sheet):
|
||||||
|
new_headers = [
|
||||||
|
"Spalte A (ReEval Flag)",
|
||||||
|
"Spalte B (Firmenname)",
|
||||||
|
"Spalte C (Website)",
|
||||||
|
"Spalte D (Ort)",
|
||||||
|
"Spalte E (Beschreibung)",
|
||||||
|
"Spalte F (Aktuelle Branche)",
|
||||||
|
"Spalte G (Beschreibung Branche extern)",
|
||||||
|
"Spalte H (Anzahl Techniker CRM)",
|
||||||
|
"Spalte I (Umsatz CRM)",
|
||||||
|
"Spalte J (Anzahl Mitarbeiter CRM)",
|
||||||
|
"Spalte K (Vorschlag Wiki URL)",
|
||||||
|
"Spalte L (Wikipedia URL)",
|
||||||
|
"Spalte M (Wikipedia Absatz)",
|
||||||
|
"Spalte N (Wikipedia Branche)",
|
||||||
|
"Spalte O (Wikipedia Umsatz)",
|
||||||
|
"Spalte P (Wikipedia Mitarbeiter)",
|
||||||
|
"Spalte Q (Wikipedia Kategorien)",
|
||||||
|
"Spalte R (Konsistenzprüfung)",
|
||||||
|
"Spalte S (Begründung bei Inkonsistenz)",
|
||||||
|
"Spalte T (Vorschlag Wiki Artikel ChatGPT)",
|
||||||
|
"Spalte U (Begründung bei Abweichung)",
|
||||||
|
"Spalte V (Vorschlag neue Branche)",
|
||||||
|
"Spalte W (Konsistenzprüfung Branche)",
|
||||||
|
"Spalte X (Begründung Abweichung Branche)",
|
||||||
|
"Spalte Y (FSM Relevanz Ja / Nein)",
|
||||||
|
"Spalte Z (Begründung für FSM Relevanz)",
|
||||||
|
"Spalte AA (Schätzung Anzahl Mitarbeiter)",
|
||||||
|
"Spalte AB (Konsistenzprüfung Mitarbeiterzahl)",
|
||||||
|
"Spalte AC (Begründung für Abweichung Mitarbeiterzahl)",
|
||||||
|
"Spalte AD (Einschätzung Anzahl Servicetechniker)",
|
||||||
|
"Spalte AE (Begründung bei Abweichung Anzahl Servicetechniker)",
|
||||||
|
"Spalte AF (Schätzung Umsatz ChatGPT)",
|
||||||
|
"Spalte AG (Begründung für Abweichung Umsatz)",
|
||||||
|
"Spalte AH (Timestamp letzte Prüfung)",
|
||||||
|
"Spalte AI (Version)"
|
||||||
|
]
|
||||||
|
header_range = "A11200:AI11200"
|
||||||
|
sheet.update(values=[new_headers], range_name=header_range)
|
||||||
|
print("Alignment-Demo abgeschlossen: Neue Spaltenüberschriften in Zeile 11200 geschrieben.")
|
||||||
|
|
||||||
|
# ==================== NEUER MODUS 4: NUR WIKIPEDIA-SUCHE ====================
|
||||||
|
def process_wikipedia_only():
|
||||||
|
debug_print("Starte ausschließlich Wikipedia-Suche (Modus 4)...")
|
||||||
|
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()
|
||||||
|
start_index = GoogleSheetHandler().get_start_index()
|
||||||
|
debug_print(f"Starte bei Zeile {start_index+1}")
|
||||||
|
for i, row in enumerate(data[1:], start=2):
|
||||||
|
if i < start_index:
|
||||||
|
continue
|
||||||
|
company_name = row[1] if len(row) > 1 else ""
|
||||||
|
website = row[2] if len(row) > 2 else ""
|
||||||
|
debug_print(f"Verarbeite Zeile {i}: {company_name}")
|
||||||
|
article = WikipediaScraper().search_company_article(company_name, website)
|
||||||
|
if article:
|
||||||
|
company_data = WikipediaScraper().extract_company_data(article.url)
|
||||||
|
else:
|
||||||
|
company_data = {
|
||||||
|
'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[10] if len(row) > 10 and row[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.')
|
||||||
|
]
|
||||||
|
wiki_range = f"K{i}:Q{i}"
|
||||||
|
main_sheet.update(values=[wiki_values], range_name=wiki_range)
|
||||||
|
debug_print(f"Zeile {i} mit Wikipedia-Daten aktualisiert.")
|
||||||
|
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
|
main_sheet.update(values=[[current_dt]], range_name=f"AH{i}")
|
||||||
|
main_sheet.update(values=[[Config.VERSION]], range_name=f"AI{i}")
|
||||||
|
time.sleep(Config.RETRY_DELAY)
|
||||||
|
debug_print("Wikipedia-Suche abgeschlossen.")
|
||||||
|
|
||||||
|
# ==================== 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)
|
||||||
|
|
||||||
|
# ==================== 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", "Vorname", "Nachname", "Position", "Anrede", "E-Mail"]
|
||||||
|
contacts_sheet.update("A1:G1", [header])
|
||||||
|
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 ""
|
||||||
|
website = row[2] if len(row) > 2 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)
|
||||||
|
if contact:
|
||||||
|
debug_print(f"Kontakt gefunden: {contact}")
|
||||||
|
new_rows.append([contact["Firmenname"], contact["Website"], contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
|
||||||
|
else:
|
||||||
|
debug_print(f"Kein Kontakt für Position '{pos}' bei '{company_name}' gefunden.")
|
||||||
|
if new_rows:
|
||||||
|
last_row = len(contacts_sheet.get_all_values()) + 1
|
||||||
|
range_str = f"A{last_row}:G{last_row + len(new_rows) - 1}"
|
||||||
|
contacts_sheet.update(range_str, new_rows)
|
||||||
|
debug_print(f"{len(new_rows)} Kontakte in 'Contacts' hinzugefügt.")
|
||||||
|
else:
|
||||||
|
debug_print("Keine Kontakte gefunden in der Haupttabelle.")
|
||||||
|
|
||||||
|
# ==================== 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 Zeile 11200.")
|
||||||
|
alignment_demo(self.sheet_handler.sheet)
|
||||||
|
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):
|
||||||
|
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}"
|
||||||
|
chatgpt_range = f"AF{row_num}"
|
||||||
|
abgleich_range = f"AG{row_num}"
|
||||||
|
valid_range = f"R{row_num}"
|
||||||
|
dt_range = f"AH{row_num}"
|
||||||
|
ver_range = f"AI{row_num}"
|
||||||
|
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
|
||||||
|
|
||||||
|
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)
|
||||||
|
wait_for_sheet_update(self.sheet_handler.sheet, f"K{row_num}", wiki_values[0])
|
||||||
|
time.sleep(3)
|
||||||
|
|
||||||
|
self.sheet_handler.sheet.update(values=[["XX"]], range_name=chatgpt_range)
|
||||||
|
|
||||||
|
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=abgleich_range)
|
||||||
|
|
||||||
|
crm_data = ";".join(row_data[1:10])
|
||||||
|
wiki_data = ";".join(row_data[11:17])
|
||||||
|
valid_result = validate_article_with_chatgpt(crm_data, wiki_data)
|
||||||
|
self.sheet_handler.sheet.update(values=[[valid_result]], range_name=valid_range)
|
||||||
|
|
||||||
|
crm_branche = row_data[5] if len(row_data) > 5 else "k.A."
|
||||||
|
beschreibung_branche = row_data[6] if len(row_data) > 6 else "k.A."
|
||||||
|
wiki_branche = company_data.get('branche', 'k.A.')
|
||||||
|
wiki_kategorien = company_data.get('categories', 'k.A.')
|
||||||
|
branche_result = evaluate_branche_chatgpt(crm_branche, beschreibung_branche, wiki_branche, wiki_kategorien)
|
||||||
|
branche_v_range = f"V{row_num}"
|
||||||
|
branche_w_range = f"W{row_num}"
|
||||||
|
branche_x_range = f"X{row_num}"
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["branch"]]], range_name=branche_v_range)
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["consistency"]]], range_name=branche_w_range)
|
||||||
|
self.sheet_handler.sheet.update(values=[[branche_result["justification"]]], range_name=branche_x_range)
|
||||||
|
|
||||||
|
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"AE{row_num}")
|
||||||
|
|
||||||
|
self.sheet_handler.sheet.update(values=[["XX"]], range_name="AF" + str(row_num))
|
||||||
|
self.sheet_handler.sheet.update(values=[["XX"]], range_name="AG" + str(row_num))
|
||||||
|
|
||||||
|
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||||
|
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_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}, Branchenvorschlag: {branche_result['branch']}, "
|
||||||
|
f"FSM: {fsm_result['suitability']}, Servicetechniker-Schätzung: {st_estimate}")
|
||||||
|
time.sleep(Config.RETRY_DELAY)
|
||||||
|
|
||||||
|
# ==================== 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", "Vorname", "Nachname", "Position", "Anrede", "E-Mail"]
|
||||||
|
contacts_sheet.update("A1:G1", [header])
|
||||||
|
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 ""
|
||||||
|
website = row[2] if len(row) > 2 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)
|
||||||
|
if contact:
|
||||||
|
debug_print(f"Kontakt gefunden: {contact}")
|
||||||
|
new_rows.append([contact["Firmenname"], contact["Website"], contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
|
||||||
|
else:
|
||||||
|
debug_print(f"Kein Kontakt für Position '{pos}' bei '{company_name}' gefunden.")
|
||||||
|
if new_rows:
|
||||||
|
last_row = len(contacts_sheet.get_all_values()) + 1
|
||||||
|
range_str = f"A{last_row}:G{last_row + len(new_rows) - 1}"
|
||||||
|
contacts_sheet.update(range_str, new_rows)
|
||||||
|
debug_print(f"{len(new_rows)} Kontakte in 'Contacts' hinzugefügt.")
|
||||||
|
else:
|
||||||
|
debug_print("Keine Kontakte gefunden in der Haupttabelle.")
|
||||||
|
|
||||||
# ==================== MAIN PROGRAMM ====================
|
# ==================== MAIN PROGRAMM ====================
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
print("Modi: 1 = regulärer Modus, 2 = Re-Evaluierungsmodus, 3 = Alignment-Demo, 4 = Nur Wikipedia-Suche, 5 = LinkedIn Contacts")
|
print("Modi: 1 = regulärer Modus, 2 = Re-Evaluierungsmodus, 3 = Alignment-Demo, 4 = Nur Wikipedia-Suche, 5 = LinkedIn Contacts")
|
||||||
|
|||||||
Reference in New Issue
Block a user