v1.3.6: LinkedIn-Contacts via SerpApi, Bugfix Zeilenlimit & Startindex

Neuer Modus (4) zur Suche von LinkedIn-Kontakten via SerpApi, Ausgabe im Tabellenblatt "Contacts" mit den Spalten Firmenname, Website, Vorname, Nachname, Position.

Bugfix: Im regulären Modus (1) wird jetzt ab dem letzten Timestamp in Spalte AH nur noch die angegebene Anzahl an Zeilen verarbeitet.

Bugfix: Bestehende Datensätze (mit Timestamp in AH) werden nicht überschrieben, es wird ab der ersten leeren Zeile gestartet.

Weitere Anpassungen bei den bisherigen Funktionen (FSM, Servicetechniker-Schätzung) bleiben erhalten.

brancheneinstufung.py

@@ -14,7 +14,7 @@ import csv
 
 # ==================== KONFIGURATION ====================
 class Config:
-    VERSION = "v1.3.5"  # v1.3.5: FSM-Eignungsprüfung & Servicetechniker-Explanation, Sheet-Update-Check, automatische Log-Datei.
+    VERSION = "v1.3.6"  # v1.3.6: LinkedIn-Contacts über SerpApi integriert, Bugfixes zu Zeilenbegrenzung und Startindex.
     LANG = "de"
     CREDENTIALS_FILE = "service_account.json"
     SHEET_URL = "https://docs.google.com/spreadsheets/d/1u_gHr9JUfmV1-iviRzbSe3575QEp7KLhK5jFV_gJcgo"
@@ -185,9 +185,7 @@ def validate_article_with_chatgpt(crm_data, wiki_data):
     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",
@@ -201,8 +199,6 @@ def validate_article_with_chatgpt(crm_data, wiki_data):
         debug_print(f"Fehler beim Validierungs-API-Aufruf: {e}")
         return "k.A."
 
-
-# ==================== NEUE FUNKTION: FSM-EIGNUNGSPRÜFUNG ====================
 def evaluate_fsm_suitability(company_name, company_data):
     try:
         with open("api_key.txt", "r") as f:
@@ -247,8 +243,14 @@ def evaluate_fsm_suitability(company_name, company_data):
         debug_print(f"Fehler beim Aufruf der ChatGPT API für FSM-Eignungsprüfung: {e}")
         return {"suitability": "k.A.", "justification": "k.A."}
 
-# ==================== NEUE FUNKTION: SCHÄTZUNG DER ANZAHL SERVICETECHNIKER ====================
 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."
+    # Wir nutzen SerpApi hier nicht, sondern die ChatGPT-Funktion
     try:
         with open("api_key.txt", "r") as f:
             api_key = f.read().strip()
@@ -314,7 +316,6 @@ def map_internal_technicians(value):
     else:
         return ">500 Techniker"
 
-# ==================== WARTEN BIS ZELLE AKTUALISIERT IST ====================
 def wait_for_sheet_update(sheet, cell, expected_value, timeout=5):
     start_time = time.time()
     while time.time() - start_time < timeout:
@@ -327,6 +328,82 @@ def wait_for_sheet_update(sheet, cell, expected_value, timeout=5):
         time.sleep(0.5)
     return False
 
+# ==================== NEUE FUNKTION: LINKEDIN-KONTAKT-SUCHE MIT SERPAPI ====================
+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 process_contacts():
+    # Öffne das Spreadsheet und erhalte das Arbeitsblatt "Contacts" (erstelle es, falls nicht vorhanden)
+    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])
+    main_sheet = sh.sheet1
+    data = main_sheet.get_all_values()
+    positions = ["Serviceleiter", "IT-Leiter", "Leiter After Sales", "Leiter Einsatzplanung"]
+    new_rows = []
+    for row in data[1:]:
+        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
+        for pos in positions:
+            contact = search_linkedin_contact(company_name, website, pos)
+            if contact:
+                new_rows.append([contact["Firmenname"], contact["Website"], contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
+    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.")
+
 # ==================== BRANCHENABGLEICH PER CHATGPT ====================
 def load_target_branches():
     try:
@@ -668,20 +745,23 @@ class DataProcessor:
     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)
-            return
         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 MODE == "2":
+                if i < start_index:
-                if row[0].strip().lower() == "x":
+                    continue
-                    self._process_single_row(i, row)
+                if num_rows is not None and rows_processed >= num_rows:
-            else:
+                    break
-                if i >= self.sheet_handler.get_start_index():
                 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 ""
@@ -693,7 +773,6 @@ class DataProcessor:
         ver_range = f"AI{row_num}"
         print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
         
-        # Prüfen: Wikipedia-Vorschlag in Spalte K?
         if len(row_data) > 10 and row_data[10].strip() not in ["", "k.A."]:
             wiki_url = row_data[10].strip()
             try:
@@ -727,21 +806,17 @@ class DataProcessor:
         wait_for_sheet_update(self.sheet_handler.sheet, f"K{row_num}", wiki_values[0])
         time.sleep(3)
         
-        # Umsatz-Schätzung: Spalte AF soll "XX" erhalten
         self.sheet_handler.sheet.update(values=[["XX"]], range_name=chatgpt_range)
         
-        # Umsatz-Abgleich (Spalte AG)
         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)
         
-        # Validierung
         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)
         
-        # Branchenabgleich
         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.')
@@ -754,12 +829,10 @@ class DataProcessor:
         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-Eignungsprüfung (Spalte Y/Z)
         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}")
         
-        # Servicetechniker-Schätzung (Spalte AD) und Vergleich (Spalte AE)
         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."
@@ -771,11 +844,9 @@ class DataProcessor:
             discrepancy = "ok"
         self.sheet_handler.sheet.update(values=[[discrepancy]], range_name=f"AE{row_num}")
         
-        # Spalten AF und AG: "XX"
         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))
         
-        # Timestamp und Version
         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)
@@ -786,12 +857,62 @@ class DataProcessor:
                     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)
+
+# ==================== NEUER MODUS: CONTACTS ====================
+def process_contacts():
+    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])
+    main_sheet = sh.sheet1
+    data = main_sheet.get_all_values()
+    positions = ["Serviceleiter", "IT-Leiter", "Leiter After Sales", "Leiter Einsatzplanung"]
+    new_rows = []
+    for row in data[1:]:
+        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
+        for pos in positions:
+            contact = search_linkedin_contact(company_name, website, pos)
+            if contact:
+                new_rows.append([contact["Firmenname"], contact["Website"], contact["Vorname"], contact["Nachname"], contact["Position"], "", ""])
+    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.")
+
+# ==================== MAIN PROGRAMM ====================
 if __name__ == "__main__":
-    mode_input = input("Wählen Sie den Modus: 1 für normalen Modus, 2 für Re-Evaluierungsmodus, 3 für Alignment-Demo: ").strip()
+    print("Modi: 1 = regulärer Modus, 2 = Re-Evaluierungsmodus, 3 = Alignment-Demo, 4 = LinkedIn Contacts")
+    mode_input = input("Wählen Sie den Modus: ").strip()
     if mode_input == "2":
         MODE = "2"
     elif mode_input == "3":
         MODE = "3"
+    elif mode_input == "4":
+        MODE = "4"
     else:
         MODE = "1"
     if MODE == "1":
@@ -800,8 +921,11 @@ if __name__ == "__main__":
         except Exception as e:
             print("Ungültige Eingabe. Bitte eine Zahl eingeben.")
             exit(1)
-    else:
-        num_rows = None
         processor = DataProcessor()
         processor.process_rows(num_rows)
+    elif MODE in ["2", "3"]:
+        processor = DataProcessor()
+        processor.process_rows()
+    elif MODE == "4":
+        process_contacts()
     print(f"\n✅ Wikipedia-Auswertung abgeschlossen ({Config.VERSION})")