v1.3.9: Modi 1-6 integriert, getrennte Timestamps und erweiterte Contact Research
- Regulärer Modus (1): Bearbeitet nur Zeilen ohne Wikipedia- (Spalte AM) bzw. ChatGPT-Timestamp (Spalte AN) - Re-Evaluierungsmodus (2): Verarbeitet nur Zeilen mit "x" in Spalte A - Alignment-Demo (3): Schreibt neuen Header in Haupt- und Contacts-Blatt - Modus 4: Nur Wikipedia-Suche, Modus 5: Nur ChatGPT-Bewertung - Modus 6: Contact Research via SerpAPI; Spalten AH-AK aktualisieren und AL als Timestamp setzen - Neue Header-Spalten: AH (Serviceleiter), AI (IT-Leiter), AJ (Management), AK (Disponent), AL (Contact Search Timestamp), AM (Wikipedia Timestamp), AN (ChatGPT Timestamp), AO (Version)
This commit is contained in:
@@ -14,7 +14,7 @@ import csv
|
||||
|
||||
# ==================== KONFIGURATION ====================
|
||||
class Config:
|
||||
VERSION = "v1.3.8" # v1.3.8: Neuer Modus 5 als Schreibtest für das Contacts-Sheet; restliche Funktionen unverändert.
|
||||
VERSION = "v1.3.9" # v1.3.9: Alle bisherigen Funktionen inkl. Reg. Modus, Re-Eval, Alignment, Wiki, ChatGPT, Contact Research.
|
||||
LANG = "de"
|
||||
CREDENTIALS_FILE = "service_account.json"
|
||||
SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
|
||||
@@ -327,7 +327,7 @@ def wait_for_sheet_update(sheet, cell, expected_value, timeout=5):
|
||||
time.sleep(0.5)
|
||||
return False
|
||||
|
||||
# ==================== NEUE FUNKTION: LINKEDIN-KONTAKT-SUCHE MIT SERPAPI ====================
|
||||
# ==================== NEUE FUNKTION: LINKEDIN-KONTAKT-SUCHE (Einzelkontakt) ====================
|
||||
def search_linkedin_contact(company_name, website, position_query):
|
||||
try:
|
||||
with open("serpApiKey.txt", "r") as f:
|
||||
@@ -378,128 +378,64 @@ def search_linkedin_contact(company_name, website, position_query):
|
||||
debug_print(f"Fehler bei der SerpAPI-Suche: {e}")
|
||||
return None
|
||||
|
||||
# ==================== 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)
|
||||
# ==================== NEUE FUNKTION: ZÄHLEN DER LINKEDIN-KONTAKTE (für Contact Research) ====================
|
||||
def count_linkedin_contacts(company_name, website, position_query):
|
||||
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.")
|
||||
|
||||
# ==================== 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)
|
||||
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:
|
||||
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.")
|
||||
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
|
||||
|
||||
# ==================== 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 5: CONTACTS-ALIGNMENT DEMO (Schreibtest Contacts) ====================
|
||||
def contacts_alignment_demo():
|
||||
debug_print("Starte Contacts-Alignment-Demo (Schreibtest)...")
|
||||
# ==================== NEUER MODUS 6: 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)
|
||||
try:
|
||||
contacts_sheet = sh.worksheet("Contacts")
|
||||
except gspread.exceptions.WorksheetNotFound:
|
||||
contacts_sheet = sh.add_worksheet(title="Contacts", rows="1000", cols="10")
|
||||
debug_print("Neues Blatt 'Contacts' erstellt.")
|
||||
# Schreibe Header falls noch nicht vorhanden
|
||||
if not contacts_sheet.get_all_values():
|
||||
header = ["Firmenname", "Website", "Vorname", "Nachname", "Position", "Anrede", "E-Mail"]
|
||||
contacts_sheet.update("A1:G1", [header])
|
||||
debug_print("Header in 'Contacts' geschrieben.")
|
||||
# Schreibe eine Testzeile
|
||||
test_row = ["TestFirma", "www.test.de", "Max", "Mustermann", "Testposition", "Herr", "max.mustermann@test.de"]
|
||||
contacts_sheet.update("A2:G2", [test_row])
|
||||
debug_print("Testzeile in 'Contacts' geschrieben.")
|
||||
main_sheet = sh.sheet1
|
||||
data = main_sheet.get_all_values()
|
||||
# Neue Spalten: AH (Serviceleiter), AI (IT-Leiter), AJ (Management), AK (Disponent), AL (Contact Search Timestamp)
|
||||
for i, row in enumerate(data[1:], start=2):
|
||||
company_name = row[1] if len(row) > 1 else ""
|
||||
website = row[2] if len(row) > 2 else ""
|
||||
if not company_name or not website:
|
||||
continue
|
||||
count_service = count_linkedin_contacts(company_name, website, "Serviceleiter")
|
||||
count_it = count_linkedin_contacts(company_name, website, "IT-Leiter")
|
||||
count_management = count_linkedin_contacts(company_name, website, "Geschäftsführer")
|
||||
count_disponent = count_linkedin_contacts(company_name, website, "Disponent")
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
# Update die Spalten: AH, AI, AJ, AK, AL (entsprechend: Spalte AH=Index33, AI=34, AJ=35, AK=36, AL=37)
|
||||
main_sheet.update(f"AH{i}", [[str(count_service)]])
|
||||
main_sheet.update(f"AI{i}", [[str(count_it)]])
|
||||
main_sheet.update(f"AJ{i}", [[str(count_management)]])
|
||||
main_sheet.update(f"AK{i}", [[str(count_disponent)]])
|
||||
main_sheet.update(f"AL{i}", [[current_dt]])
|
||||
debug_print(f"Zeile {i}: Serviceleiter {count_service}, IT-Leiter {count_it}, Management {count_management}, Disponent {count_disponent} – Timestamp gesetzt.")
|
||||
time.sleep(Config.RETRY_DELAY * 1.5) # etwas langsamer
|
||||
debug_print("Contact Research abgeschlossen.")
|
||||
|
||||
# ==================== ALIGNMENT DEMO (Modus 3) ====================
|
||||
def alignment_demo(sheet):
|
||||
@@ -537,17 +473,385 @@ def alignment_demo(sheet):
|
||||
"Spalte AE (Begründung bei Abweichung Anzahl Servicetechniker)",
|
||||
"Spalte AF (Schätzung Umsatz ChatGPT)",
|
||||
"Spalte AG (Begründung für Abweichung Umsatz)",
|
||||
"Spalte AH (Timestamp Wiki Update)",
|
||||
"Spalte AI (Timestamp ChatGPT Bewertung)",
|
||||
"Spalte AJ (Version)"
|
||||
"Spalte AH (Serviceleiter gefunden)",
|
||||
"Spalte AI (IT-Leiter gefunden)",
|
||||
"Spalte AJ (Management gefunden)",
|
||||
"Spalte AK (Disponent gefunden)",
|
||||
"Spalte AL (Contact Search Timestamp)",
|
||||
"Spalte AM (Wikipedia Timestamp)",
|
||||
"Spalte AN (ChatGPT Timestamp)",
|
||||
"Spalte AO (Version)"
|
||||
]
|
||||
header_range = "A11200:AJ11200"
|
||||
header_range = "A11200:AO11200"
|
||||
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
|
||||
|
||||
# ==================== 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[38] if len(row) > 38 else '' for row in self.sheet_values[1:]] # Spalte AM = Wikipedia Timestamp
|
||||
return next((i + 1 for i, v in enumerate(filled_n, start=1) if not str(v).strip()), len(filled_n) + 1)
|
||||
|
||||
# ==================== DATA PROCESSOR ====================
|
||||
class DataProcessor:
|
||||
def __init__(self):
|
||||
self.sheet_handler = GoogleSheetHandler()
|
||||
self.wiki_scraper = WikipediaScraper()
|
||||
def process_rows(self, num_rows=None):
|
||||
# MODE 1: Regulärer Modus – nur Zeilen ohne entsprechende Timestamps werden bearbeitet
|
||||
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: Schreibe neue Spaltenüberschriften in Zeile 11200.")
|
||||
alignment_demo(self.sheet_handler.sheet)
|
||||
elif MODE == "4":
|
||||
# Nur Wikipedia-Suche: nur Zeilen ohne Wikipedia-Timestamp (Spalte AM, Index 38)
|
||||
for i, row in enumerate(self.sheet_handler.sheet_values[1:], start=2):
|
||||
if len(row) <= 38 or row[38].strip() == "":
|
||||
self._process_single_row(i, row, process_wiki=True, process_chatgpt=False)
|
||||
elif MODE == "5":
|
||||
# Nur ChatGPT Bewertung: nur Zeilen ohne ChatGPT-Timestamp (Spalte AN, Index 39)
|
||||
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=False, process_chatgpt=True)
|
||||
else:
|
||||
# Regulärer Modus: Bearbeite nur Zeilen, die noch nicht vollständig bewertet wurden
|
||||
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[2] if len(row_data) > 2 else ""
|
||||
wiki_update_range = f"K{row_num}:Q{row_num}"
|
||||
dt_wiki_range = f"AM{row_num}" # Wikipedia Timestamp
|
||||
dt_chat_range = f"AN{row_num}" # ChatGPT Timestamp
|
||||
dt_last_range = f"AN{row_num}" # Falls benötigt, hier können Sie noch "Timestamp letzte Prüfung" anpassen
|
||||
ver_range = f"AO{row_num}" # Version
|
||||
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
|
||||
# Wikipedia-Teil (Spalte AM) – nur ausführen, wenn kein Wiki-Timestamp vorhanden oder force_all True oder explizit process_wiki=True
|
||||
wiki_data = None
|
||||
if force_all or process_wiki or (len(row_data) <= 38 or row_data[38].strip() == ""):
|
||||
if len(row_data) > 11 and row_data[10].strip() not in ["", "k.A."]:
|
||||
wiki_url = row_data[10].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[10] if len(row_data) > 10 and row_data[10].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=wiki_update_range)
|
||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_wiki_range)
|
||||
# ChatGPT-Bewertung (Spalte AN) – nur ausführen, wenn kein ChatGPT-Timestamp vorhanden oder force_all/ process_chatgpt True
|
||||
if force_all or process_chatgpt or (len(row_data) <= 39 or row_data[39].strip() == ""):
|
||||
crm_umsatz = row_data[8] if len(row_data) > 8 else "k.A."
|
||||
abgleich_result = compare_umsatz_values(crm_umsatz, wiki_data.get('umsatz', 'k.A.') if wiki_data else "k.A.")
|
||||
self.sheet_handler.sheet.update(values=[[abgleich_result]], range_name=f"AG{row_num}")
|
||||
crm_data = ";".join(row_data[1:10])
|
||||
wiki_data_str = ";".join(row_data[11:17])
|
||||
valid_result = validate_article_with_chatgpt(crm_data, wiki_data_str)
|
||||
self.sheet_handler.sheet.update(values=[[valid_result]], range_name=f"R{row_num}")
|
||||
fsm_result = evaluate_fsm_suitability(company_name, wiki_data if wiki_data else {})
|
||||
self.sheet_handler.sheet.update(values=[[fsm_result["suitability"]]], range_name=f"Y{row_num}")
|
||||
self.sheet_handler.sheet.update(values=[[fsm_result["justification"]]], range_name=f"Z{row_num}")
|
||||
st_estimate = evaluate_servicetechnicians_estimate(company_name, wiki_data if wiki_data else {})
|
||||
self.sheet_handler.sheet.update(values=[[st_estimate]], range_name=f"AD{row_num}")
|
||||
internal_value = row_data[7] if len(row_data) > 7 else "k.A."
|
||||
internal_category = map_internal_technicians(internal_value) if internal_value != "k.A." else "k.A."
|
||||
if internal_category != "k.A." and st_estimate != internal_category:
|
||||
explanation = evaluate_servicetechnicians_explanation(company_name, st_estimate, wiki_data if wiki_data else {})
|
||||
discrepancy = explanation
|
||||
else:
|
||||
discrepancy = "ok"
|
||||
self.sheet_handler.sheet.update(values=[[discrepancy]], range_name=f"AE{row_num}")
|
||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=dt_chat_range)
|
||||
# Letzten Timestamp und Version aktualisieren (Spalte AO)
|
||||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"AO{row_num}")
|
||||
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"AO{row_num}")
|
||||
debug_print(f"✅ Aktualisiert: URL: {(wiki_data.get('url', 'k.A.') if wiki_data else 'k.A.')}, "
|
||||
f"Branche: {(wiki_data.get('branche', 'k.A.') if wiki_data else 'k.A.')}, "
|
||||
f"Umsatz-Abgleich: {abgleich_result if 'abgleich_result' in locals() else 'k.A.'}, "
|
||||
f"Validierung: {valid_result if 'valid_result' in locals() else 'k.A.'}, "
|
||||
f"FSM: {fsm_result['suitability'] if 'fsm_result' in locals() else 'k.A.'}, "
|
||||
f"Servicetechniker-Schätzung: {st_estimate if 'st_estimate' in locals() else 'k.A.'}")
|
||||
time.sleep(Config.RETRY_DELAY)
|
||||
|
||||
# ==================== NEUER MODUS 6: 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()
|
||||
# Für jeden Datensatz werden für vier Kategorien die Trefferanzahl ermittelt:
|
||||
for i, row in enumerate(data[1:], start=2):
|
||||
company_name = row[1] if len(row) > 1 else ""
|
||||
website = row[2] if len(row) > 2 else ""
|
||||
if not company_name or not website:
|
||||
continue
|
||||
count_service = count_linkedin_contacts(company_name, website, "Serviceleiter")
|
||||
count_it = count_linkedin_contacts(company_name, website, "IT-Leiter")
|
||||
count_management = count_linkedin_contacts(company_name, website, "Geschäftsführer")
|
||||
count_disponent = count_linkedin_contacts(company_name, website, "Disponent")
|
||||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||||
main_sheet.update(f"AH{i}", [[str(count_service)]])
|
||||
main_sheet.update(f"AI{i}", [[str(count_it)]])
|
||||
main_sheet.update(f"AJ{i}", [[str(count_management)]])
|
||||
main_sheet.update(f"AK{i}", [[str(count_disponent)]])
|
||||
main_sheet.update(f"AL{i}", [[current_dt]])
|
||||
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: ALIGNMENT DEMO (für Hauptblatt und Contacts) ====================
|
||||
def alignment_demo_full():
|
||||
# Aktualisiere Hauptblatt
|
||||
alignment_demo(GoogleSheetHandler().sheet)
|
||||
# Aktualisiere auch das Contacts-Blatt
|
||||
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])
|
||||
alignment_demo(contacts_sheet)
|
||||
debug_print("Alignment-Demo für Hauptblatt und Contacts abgeschlossen.")
|
||||
|
||||
# ==================== MAIN PROGRAMM ====================
|
||||
if __name__ == "__main__":
|
||||
print("Modi: 1 = regulärer Modus, 2 = Re-Evaluierungsmodus, 3 = Alignment-Demo, 4 = Nur Wikipedia-Suche, 5 = Contacts-Alignment Demo (Schreibtest)")
|
||||
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)")
|
||||
mode_input = input("Wählen Sie den Modus: ").strip()
|
||||
if mode_input == "2":
|
||||
MODE = "2"
|
||||
@@ -557,6 +861,8 @@ if __name__ == "__main__":
|
||||
MODE = "4"
|
||||
elif mode_input == "5":
|
||||
MODE = "5"
|
||||
elif mode_input == "6":
|
||||
MODE = "6"
|
||||
else:
|
||||
MODE = "1"
|
||||
if MODE == "1":
|
||||
@@ -571,7 +877,14 @@ if __name__ == "__main__":
|
||||
processor = DataProcessor()
|
||||
processor.process_rows()
|
||||
elif MODE == "4":
|
||||
processor = DataProcessor()
|
||||
# Für Mode 4: Nur Wikipedia-Suche
|
||||
processor.process_rows(num_rows=0) # Unser _process_single_row prüft dann die Wiki-Timestamp-Bedingung
|
||||
process_wikipedia_only()
|
||||
elif MODE == "5":
|
||||
contacts_alignment_demo()
|
||||
processor = DataProcessor()
|
||||
# Für Mode 5: Nur ChatGPT-Bewertung
|
||||
processor.process_rows(num_rows=0)
|
||||
elif MODE == "6":
|
||||
process_contact_research()
|
||||
print(f"\n✅ Auswertung abgeschlossen ({Config.VERSION})")
|
||||
|
||||
Reference in New Issue
Block a user