Floke
5a94a3d4c5
Flag-Spalte A: Nur Zeilen mit einem "x" in Spalte A werden verarbeitet. Verschiebung der Spaltenzuordnungen: Firmenname in Spalte B, Website in Spalte C. Ausgabe erfolgt in den Spalten H bis L (H: Wikipedia URL, I: erster Absatz, J: Branche, K: Umsatz in Mio €, L: Mitarbeiterzahl). Datum und Uhrzeit in Spalte O, Version in Spalte R. Umsatz-Extraktion: Erweiterte Regex-Logik zur Erkennung von Tausendertrennzeichen und zur Umrechnung in Mio €. Mitarbeiterextraktion: Umstellung auf re.findall, um robust das erste Zahlenfragment zu erfassen. Weitere Anpassungen: Deprecation-Warnings bei den Update-Aufrufen wurden behoben (mittels benannter Argumente).
317 lines
16 KiB
Python
317 lines
16 KiB
Python
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 = "1.1.6" # Neue Version
|
||
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"
|
||
|
||
# ==================== HELPER FUNCTIONS ====================
|
||
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
|
||
|
||
def debug_print(message):
|
||
if Config.DEBUG:
|
||
print(f"[DEBUG] {message}")
|
||
|
||
def clean_text(text):
|
||
if not text:
|
||
return "k.A."
|
||
text = 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()
|
||
|
||
# ==================== 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)
|
||
# Update-Aufrufe erfolgen separat.
|
||
|
||
# ==================== 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_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']
|
||
}
|
||
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':
|
||
raw = raw_value.lower()
|
||
match = re.search(r'(\d{1,3}(?:[.,]\d{3})*|\d+)', raw)
|
||
if match:
|
||
num_str = match.group(1)
|
||
if ',' in num_str:
|
||
num_str = num_str.replace('.', '').replace(',', '.')
|
||
else:
|
||
num_str = num_str.replace('.', '')
|
||
try:
|
||
num = float(num_str)
|
||
except Exception as e:
|
||
debug_print(f"Umsatz-Umwandlungsfehler: {e} für {num_str}")
|
||
return raw_value.strip()
|
||
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)))
|
||
return raw_value.strip()
|
||
if target == 'mitarbeiter':
|
||
raw = raw_value.lower()
|
||
numbers = re.findall(r'\d+', raw)
|
||
if numbers:
|
||
return numbers[0]
|
||
return raw_value.strip()
|
||
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 token.lower() == field.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.'}
|
||
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'])
|
||
branche_val = extracted_fields.get('Branche', self._extract_infobox_value(soup, 'branche'))
|
||
umsatz_val = extracted_fields.get('Umsatz', self._extract_infobox_value(soup, 'umsatz'))
|
||
mitarbeiter_val = extracted_fields.get('Mitarbeiter', self._extract_infobox_value(soup, 'mitarbeiter'))
|
||
first_paragraph = self.extract_first_paragraph(page_url)
|
||
return {
|
||
'url': page_url,
|
||
'first_paragraph': first_paragraph,
|
||
'branche': branche_val,
|
||
'umsatz': umsatz_val,
|
||
'mitarbeiter': mitarbeiter_val
|
||
}
|
||
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.'}
|
||
@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):
|
||
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):
|
||
# Nur verarbeiten, wenn in Spalte A ein "x" steht
|
||
if not row_data[0].strip().lower() == "x":
|
||
print(f"[{datetime.now().strftime('%H:%M:%S')}] Überspringe Zeile {row_num}, kein 'x' in Spalte A.")
|
||
return
|
||
# Firmenname in Spalte B und Website in Spalte C
|
||
company_name = row_data[1] if len(row_data) > 1 else ""
|
||
website = row_data[2] if len(row_data) > 2 else ""
|
||
print(f"\n[{datetime.now().strftime('%H:%M:%S')}] Verarbeite Zeile {row_num}: {company_name}")
|
||
article = self.wiki_scraper.search_company_article(company_name, website)
|
||
if article:
|
||
company_data = self.wiki_scraper.extract_company_data(article.url)
|
||
else:
|
||
company_data = {'url': 'k.A.', 'first_paragraph': 'k.A.', 'branche': 'k.A.', 'umsatz': 'k.A.', 'mitarbeiter': 'k.A.'}
|
||
# Update der Spalten: Da Flag-Spalte A vorhanden ist, verschieben sich alle Ausgabespalten um eine Spalte nach rechts.
|
||
# Spalte H: URL, I: Erster Absatz, J: Branche, K: Umsatz, L: Mitarbeiter
|
||
self.sheet_handler.sheet.update(values=[[
|
||
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.')
|
||
]], range_name=f"H{row_num}:L{row_num}")
|
||
# Spalte O: Datum und aktuelle Zeit
|
||
current_dt = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
|
||
self.sheet_handler.sheet.update(values=[[current_dt]], range_name=f"O{row_num}")
|
||
# Spalte R: Version
|
||
self.sheet_handler.sheet.update(values=[[Config.VERSION]], range_name=f"R{row_num}")
|
||
print(f"✅ Aktualisiert: URL: {company_data.get('url', 'k.A.')}, Erster Absatz: {company_data.get('first_paragraph', 'k.A.')[:30]}..., Branche: {company_data.get('branche', 'k.A.')}, Umsatz: {company_data.get('umsatz', 'k.A.')}, Mitarbeiter: {company_data.get('mitarbeiter', 'k.A.')}")
|
||
time.sleep(Config.RETRY_DELAY)
|
||
|
||
# ==================== MAIN ====================
|
||
if __name__ == "__main__":
|
||
try:
|
||
num_rows = 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)
|
||
print("\n✅ Wikipedia-Auswertung abgeschlossen")
|