Brancheneinstufung2/brancheneinstufung.py

import os
import time
import re
import gspread
import wikipedia
import requests
from bs4 import BeautifulSoup
from oauth2client.service_account import ServiceAccountCredentials
from datetime import datetime
from difflib import SequenceMatcher
import csv

# ==================== KONFIGURATION ====================
class Config:
    VERSION = "1.1.0"
    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 = 0.6
    DEBUG = True
    WIKIPEDIA_SEARCH_RESULTS = 8
    HTML_PARSER = "html.parser"

# ==================== HELPER FUNCTIONS ====================
def retry_on_failure(func):
    """Decorator für Wiederholungsversuche bei Fehlern"""
    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

def debug_print(message):
    """Debug-Ausgabe, wenn Config.DEBUG=True"""
    if Config.DEBUG:
        print(f"[DEBUG] {message}")

def clean_text(text):
    """Bereinigt Text von HTML-Entitäten und überflüssigen Whitespaces"""
    if not text:
        return "k.A."
    
    # Konvertierung und Säuberung
    text = str(text)
    text = re.sub(r'\[.*?\]', '', text)  # Entferne eckige Klammern mit Inhalt
    text = re.sub(r'\(.*?\)', '', text)  # Entferne runde Klammern mit Inhalt
    text = re.sub(r'<.*?>', '', text)    # Entferne HTML-Tags
    text = re.sub(r'\s+', ' ', text).strip()
    return text if text else "k.A."

# ==================== GOOGLE SHEET HANDLER ====================
class GoogleSheetHandler:
    """Klasse zur Handhabung der Google Sheets Interaktion"""
    
    def __init__(self):
        self.sheet = None
        self.sheet_values = []
        self._connect()
        
    def _connect(self):
        """Stellt Verbindung zum Google Sheet her"""
        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):
        """Ermittelt die erste leere Zeile in Spalte N (Index 13)"""
        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
        )
    
    def update_row(self, row_num, values):
        """Aktualisiert eine Zeile im Sheet"""
        self.sheet.update(
            range_name=f"G{row_num}:Q{row_num}",
            values=[values]
        )

# ==================== WIKIPEDIA SCRAPER ====================
class WikipediaScraper:
    """Klasse zur Handhabung der Wikipedia-Suche und Datenextraktion"""
    
    def __init__(self):
        wikipedia.set_lang(Config.LANG)
        
    def _generate_search_terms(self, company_name, website_hint=""):
        """Generiert Suchbegriffe aus Firmenname und Website"""
        search_terms = [company_name.strip()]
        
        # Zusatzbegriffe aus Firmennamen
        name_parts = company_name.split()
        if len(name_parts) > 1:
            search_terms.append(" ".join(name_parts[:2]))
        
        # Bereinigung von Rechtsformen
        clean_name = re.sub(r'\s+(?:GmbH|AG|KG|OHG|e\.V\.|mbH).*$', '', company_name)
        if clean_name != company_name:
            search_terms.append(clean_name)
            
        # Extraktion aus Website
        if website_hint:
            domain_parts = website_hint.replace("https://", "").replace("http://", "").replace("www.", "").split(".")
            if len(domain_parts) > 1 and domain_parts[0] not in ["de", "com", "org"]:
                search_terms.append(domain_parts[0])
                
        debug_print(f"Generierte Suchbegriffe: {search_terms}")
        return search_terms
    
    def _validate_article(self, page, company_name, domain_hint=""):
        """Überprüft ob der Artikel zum Unternehmen passt"""
        # Ähnlichkeitsprüfung des Titels
        title_similarity = SequenceMatcher(
            None, 
            page.title.lower(), 
            company_name.lower()
        ).ratio()
        
        # Zusätzliche Domain-Prüfung
        if domain_hint:
            html_content = requests.get(page.url).text
            if domain_hint.lower() not in html_content.lower():
                return False
                
        return title_similarity >= Config.SIMILARITY_THRESHOLD
    
    @retry_on_failure
    def search_company_article(self, company_name, website_hint=""):
        """Hauptfunktion zur Artikelsuche"""
        search_terms = self._generate_search_terms(company_name, website_hint)
        domain_hint = self._extract_domain_hint(website_hint)
        
        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, domain_hint):
                            return page
                    except wikipedia.exceptions.DisambiguationError:
                        continue
            except Exception as e:
                debug_print(f"Fehler bei Suche nach {term}: {str(e)}")
                continue
        return None
    
    def extract_company_data(self, page_url):
        """Extrahiert Branche und Umsatz aus dem Wikipedia-Artikel"""
        response = requests.get(page_url)
        soup = BeautifulSoup(response.text, Config.HTML_PARSER)
        
        return {
            'branche': self._extract_infobox_value(soup, 'branche'),
            'umsatz': self._extract_infobox_value(soup, 'umsatz'),
            'url': page_url
        }
    
    def _extract_infobox_value(self, soup, target):
        """Extrahiert spezifischen Wert aus der Infobox"""
        infobox = soup.find('table', class_=lambda c: c and 'infobox' in c.lower())
        if not infobox:
            return "k.A."
            
        # Definiere Keywords für verschiedene Targets
        keywords = {
            'branche': ['branche', 'tätigkeitsfeld', 'geschäftsfeld', 'sektor'],
            'umsatz': ['umsatz', 'jahresumsatz', 'konzernumsatz', 'umsatzerlöse']
        }.get(target, [])
        
        # Durchsuche Infobox-Zeilen
        for row in infobox.find_all('tr'):
            header = row.find('th')
            if header and any(kw in clean_text(header).lower() for kw in keywords):
                value = row.find('td')
                return clean_text(value) if value else "k.A."
        
        return "k.A."

# ==================== DATA PROCESSOR ====================
class DataProcessor:
    """Klasse zur Steuerung des Gesamtprozesses"""
    
    def __init__(self):
        self.sheet_handler = GoogleSheetHandler()
        self.wiki_scraper = WikipediaScraper()
        
    def process_rows(self, num_rows):
        """Verarbeitet die angegebene Anzahl an Zeilen"""
        start_index = self.sheet_handler.get_start_index()
        print(f"Starte bei Zeile {start_index+1}")
        
        for i in range(start_index, min(start_index + num_rows, len(self.sheet_handler.sheet_values))):
            row = self.sheet_handler.sheet_values[i]
            self._process_single_row(i+1, row)
            
    def _process_single_row(self, row_num, row_data):
        """Verarbeitet eine einzelne Zeile"""
        company_name = row_data[0] if len(row_data) > 0 else ""
        website = row_data[1] if len(row_data) > 1 else ""
        print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
        
        # Schritt 1: Wikipedia-Artikel finden
        article = self.wiki_scraper.search_company_article(company_name, website)
        
        # Schritt 2: Daten extrahieren
        if article:
            company_data = self.wiki_scraper.extract_company_data(article.url)
        else:
            company_data = {'branche': 'k.A.', 'umsatz': 'k.A.', 'url': ''}
        
        # Aktualisiere Daten im Sheet
        self._update_sheet(row_num, company_data)
        time.sleep(Config.RETRY_DELAY)
        
    def _update_sheet(self, row_num, data):
        """Aktualisiert die Zeile mit den neuen Daten"""
        current_values = self.sheet_handler.sheet.row_values(row_num)
        new_values = [
            data['branche'] if data['branche'] != "k.A." else current_values[6] if len(current_values) > 6 else "k.A.",
            "k.A.",  # LinkedIn-Branche bleibt unverändert
            data['umsatz'] if data['umsatz'] != "k.A." else current_values[8] if len(current_values) > 8 else "k.A.",
            "k.A.", "k.A.", "k.A.",
            data['url'] if data['url'] else current_values[12] if len(current_values) > 12 else "",
            datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
            "k.A.", "k.A.",
            Config.VERSION
        ]
        self.sheet_handler.update_row(row_num, new_values)
        print(f"✅ Aktualisiert: Branche: {new_values[0]}, Umsatz: {new_values[2]}, URL: {new_values[6]}")

# ==================== MAIN EXECUTION ====================
if __name__ == "__main__":
    num_rows = int(input("Wieviele Zeilen sollen überprüft werden? "))
    processor = DataProcessor()
    processor.process_rows(num_rows)
    print("\n✅ Wikipedia-Auswertung abgeschlossen")