497 lines
15 KiB
Python
497 lines
15 KiB
Python
 
|
#!/usr/bin/env python3
|
||
|
|
"""
|
||
|
|
Lotto 6aus49 API Data Updater
|
||
|
|
|
||
|
|
Lädt Lotto-Ziehungen von verschiedenen APIs:
|
||
|
|
1. lottoAPI (https://lottoapi.herokuapp.com)
|
||
|
|
2. Lotto.de API
|
||
|
|
3. Fallback Quellen
|
||
|
|
|
||
|
|
Features:
|
||
|
|
- Automatisches Laden von APIs
|
||
|
|
- Fallback auf andere APIs wenn primäre fehlschlägt
|
||
|
|
- Duplikate-Vermeidung
|
||
|
|
- Automatisches Backup
|
||
|
|
"""
|
||
|
|
|
||
|
|
import requests
|
||
|
|
import pandas as pd
|
||
|
|
from datetime import datetime
|
||
|
|
import shutil
|
||
|
|
import os
|
||
|
|
from typing import List, Dict, Optional
|
||
|
|
import time
|
||
|
|
|
||
|
|
|
||
|
|
class LottoAPIUpdater:
|
||
|
|
"""Updater für Lotto 6aus49 über APIs."""
|
||
|
|
|
||
|
|
def __init__(self, data_file: str):
|
||
|
|
self.data_file = data_file
|
||
|
|
self.backup_file = None
|
||
|
|
self.df_existing = None
|
||
|
|
|
||
|
|
# API-Endpoints
|
||
|
|
self.apis = {
|
||
|
|
'github': {
|
||
|
|
'url': 'https://johannesfriedrich.github.io/LottoNumberArchive/Lottonumbers_tidy_complete.json',
|
||
|
|
'name': 'GitHub Lotto Archive',
|
||
|
|
'parser': self._parse_github_archive
|
||
|
|
},
|
||
|
|
'lottoapi': {
|
||
|
|
'url': 'https://lottoapi.herokuapp.com/lotto/6aus49/100',
|
||
|
|
'name': 'lottoAPI (Backup)',
|
||
|
|
'parser': self._parse_lottoapi
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
print("🔄 LOTTO 6AUS49 API UPDATER")
|
||
|
|
print("=" * 70)
|
||
|
|
print(f"📁 Datei: {os.path.basename(data_file)}")
|
||
|
|
print("=" * 70)
|
||
|
|
|
||
|
|
def load_existing_data(self) -> bool:
|
||
|
|
"""Lädt existierende Daten."""
|
||
|
|
print("\n📂 Lade existierende Daten...")
|
||
|
|
|
||
|
|
try:
|
||
|
|
if not os.path.exists(self.data_file):
|
||
|
|
print(f" ⚠️ Datei existiert nicht - erstelle neue")
|
||
|
|
self.df_existing = pd.DataFrame(
|
||
|
|
columns=['datum', 'Z1', 'Z2', 'Z3', 'Z4', 'Z5', 'Z6', 'SZ']
|
||
|
|
)
|
||
|
|
return True
|
||
|
|
|
||
|
|
self.df_existing = pd.read_csv(self.data_file, sep=';')
|
||
|
|
|
||
|
|
# Konvertiere Datum
|
||
|
|
if 'datum' in self.df_existing.columns:
|
||
|
|
self.df_existing['datum'] = pd.to_datetime(
|
||
|
|
self.df_existing['datum'],
|
||
|
|
format='%Y-%m-%d',
|
||
|
|
errors='coerce'
|
||
|
|
)
|
||
|
|
|
||
|
|
print(f" ✅ {len(self.df_existing)} Ziehungen geladen")
|
||
|
|
|
||
|
|
if len(self.df_existing) > 0:
|
||
|
|
latest = self.df_existing['datum'].max()
|
||
|
|
oldest = self.df_existing['datum'].min()
|
||
|
|
print(f" 📅 Zeitraum: {oldest.strftime('%Y-%m-%d')} bis {latest.strftime('%Y-%m-%d')}")
|
||
|
|
|
||
|
|
return True
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ❌ Fehler: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
def create_backup(self) -> bool:
|
||
|
|
"""Erstellt Backup."""
|
||
|
|
if not os.path.exists(self.data_file):
|
||
|
|
return True
|
||
|
|
|
||
|
|
try:
|
||
|
|
print("\n💾 Erstelle Backup...")
|
||
|
|
|
||
|
|
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
||
|
|
backup_dir = os.path.join(os.path.dirname(self.data_file), "data", "backups")
|
||
|
|
os.makedirs(backup_dir, exist_ok=True)
|
||
|
|
|
||
|
|
filename = os.path.basename(self.data_file)
|
||
|
|
self.backup_file = os.path.join(backup_dir, f"{filename}.backup_{timestamp}")
|
||
|
|
|
||
|
|
shutil.copy2(self.data_file, self.backup_file)
|
||
|
|
print(f" ✅ Backup: {os.path.basename(self.backup_file)}")
|
||
|
|
|
||
|
|
return True
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ⚠️ Backup-Fehler: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
def fetch_from_api(self, api_name: str) -> List[Dict]:
|
||
|
|
"""
|
||
|
|
Holt Daten von spezifischer API.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
api_name: Name der API ('lottoapi')
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
Liste von Ziehungen
|
||
|
|
"""
|
||
|
|
if api_name not in self.apis:
|
||
|
|
print(f" ❌ Unbekannte API: {api_name}")
|
||
|
|
return []
|
||
|
|
|
||
|
|
api = self.apis[api_name]
|
||
|
|
print(f"\n🌐 Versuche {api['name']}...")
|
||
|
|
print(f" URL: {api['url']}")
|
||
|
|
|
||
|
|
try:
|
||
|
|
headers = {
|
||
|
|
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36'
|
||
|
|
}
|
||
|
|
|
||
|
|
response = requests.get(api['url'], headers=headers, timeout=15)
|
||
|
|
response.raise_for_status()
|
||
|
|
|
||
|
|
print(f" ✅ Antwort erhalten ({len(response.content)} bytes)")
|
||
|
|
|
||
|
|
# Parse mit spezifischem Parser
|
||
|
|
draws = api['parser'](response.json())
|
||
|
|
|
||
|
|
if draws:
|
||
|
|
print(f" ✅ {len(draws)} Ziehungen extrahiert")
|
||
|
|
else:
|
||
|
|
print(f" ⚠️ Keine Ziehungen extrahiert")
|
||
|
|
|
||
|
|
return draws
|
||
|
|
|
||
|
|
except requests.RequestException as e:
|
||
|
|
print(f" ❌ Netzwerkfehler: {e}")
|
||
|
|
return []
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ❌ Fehler: {e}")
|
||
|
|
return []
|
||
|
|
|
||
|
|
def _parse_github_archive(self, data: List[Dict]) -> List[Dict]:
|
||
|
|
"""
|
||
|
|
Parst GitHub Lotto Archive Response.
|
||
|
|
|
||
|
|
Expected format:
|
||
|
|
[
|
||
|
|
{
|
||
|
|
"id": 4963,
|
||
|
|
"date": "26.11.2025",
|
||
|
|
"variable": "Lottozahl",
|
||
|
|
"value": 2
|
||
|
|
},
|
||
|
|
...
|
||
|
|
]
|
||
|
|
"""
|
||
|
|
draws = []
|
||
|
|
|
||
|
|
try:
|
||
|
|
# Gruppiere nach ID (jede ID = eine Ziehung)
|
||
|
|
draws_by_id = {}
|
||
|
|
|
||
|
|
for entry in data:
|
||
|
|
draw_id = entry.get('id')
|
||
|
|
if draw_id not in draws_by_id:
|
||
|
|
draws_by_id[draw_id] = {
|
||
|
|
'date': entry.get('date'),
|
||
|
|
'numbers': [],
|
||
|
|
'superzahl': None
|
||
|
|
}
|
||
|
|
|
||
|
|
variable = entry.get('variable')
|
||
|
|
value = entry.get('value')
|
||
|
|
|
||
|
|
if variable == 'Lottozahl':
|
||
|
|
draws_by_id[draw_id]['numbers'].append(value)
|
||
|
|
elif variable == 'Superzahl':
|
||
|
|
draws_by_id[draw_id]['superzahl'] = value
|
||
|
|
|
||
|
|
# Konvertiere zu unserem Format
|
||
|
|
for draw_id, draw_data in draws_by_id.items():
|
||
|
|
try:
|
||
|
|
# Parse Datum (Format: DD.MM.YYYY)
|
||
|
|
date_str = draw_data['date']
|
||
|
|
day, month, year = date_str.split('.')
|
||
|
|
date_obj = datetime(int(year), int(month), int(day))
|
||
|
|
|
||
|
|
# Sortiere Zahlen
|
||
|
|
numbers = sorted(draw_data['numbers'])
|
||
|
|
|
||
|
|
# Validierung
|
||
|
|
if len(numbers) != 6:
|
||
|
|
continue
|
||
|
|
|
||
|
|
superzahl = draw_data['superzahl']
|
||
|
|
if superzahl is None:
|
||
|
|
continue
|
||
|
|
|
||
|
|
draw = {
|
||
|
|
'datum': date_obj,
|
||
|
|
'Z1': numbers[0],
|
||
|
|
'Z2': numbers[1],
|
||
|
|
'Z3': numbers[2],
|
||
|
|
'Z4': numbers[3],
|
||
|
|
'Z5': numbers[4],
|
||
|
|
'Z6': numbers[5],
|
||
|
|
'SZ': superzahl
|
||
|
|
}
|
||
|
|
|
||
|
|
if self._validate_draw(draw):
|
||
|
|
draws.append(draw)
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
continue
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ⚠️ Parse-Fehler: {e}")
|
||
|
|
|
||
|
|
return draws
|
||
|
|
|
||
|
|
def _parse_lottoapi(self, data: List[Dict]) -> List[Dict]:
|
||
|
|
"""
|
||
|
|
Parst lottoAPI Response.
|
||
|
|
|
||
|
|
Expected format:
|
||
|
|
[
|
||
|
|
{
|
||
|
|
"date": "2025-01-22",
|
||
|
|
"numbers": [3, 9, 12, 24, 39, 45],
|
||
|
|
"superzahl": 7
|
||
|
|
},
|
||
|
|
...
|
||
|
|
]
|
||
|
|
"""
|
||
|
|
draws = []
|
||
|
|
|
||
|
|
try:
|
||
|
|
for item in data:
|
||
|
|
# Datum
|
||
|
|
date_str = item.get('date')
|
||
|
|
if not date_str:
|
||
|
|
continue
|
||
|
|
|
||
|
|
date_obj = datetime.strptime(date_str, '%Y-%m-%d')
|
||
|
|
|
||
|
|
# Hauptzahlen (6 Zahlen)
|
||
|
|
numbers = sorted(item.get('numbers', []))
|
||
|
|
if len(numbers) != 6:
|
||
|
|
continue
|
||
|
|
|
||
|
|
# Superzahl
|
||
|
|
superzahl = item.get('superzahl')
|
||
|
|
if superzahl is None:
|
||
|
|
continue
|
||
|
|
|
||
|
|
draw = {
|
||
|
|
'datum': date_obj,
|
||
|
|
'Z1': numbers[0],
|
||
|
|
'Z2': numbers[1],
|
||
|
|
'Z3': numbers[2],
|
||
|
|
'Z4': numbers[3],
|
||
|
|
'Z5': numbers[4],
|
||
|
|
'Z6': numbers[5],
|
||
|
|
'SZ': superzahl
|
||
|
|
}
|
||
|
|
|
||
|
|
if self._validate_draw(draw):
|
||
|
|
draws.append(draw)
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ⚠️ Parse-Fehler: {e}")
|
||
|
|
|
||
|
|
return draws
|
||
|
|
|
||
|
|
def _validate_draw(self, draw: Dict) -> bool:
|
||
|
|
"""Validiert eine Ziehung."""
|
||
|
|
try:
|
||
|
|
required_fields = ['datum', 'Z1', 'Z2', 'Z3', 'Z4', 'Z5', 'Z6', 'SZ']
|
||
|
|
if not all(field in draw for field in required_fields):
|
||
|
|
return False
|
||
|
|
|
||
|
|
# Hauptzahlen (1-49)
|
||
|
|
main_numbers = [draw[f'Z{i}'] for i in range(1, 7)]
|
||
|
|
if not all(isinstance(n, int) and 1 <= n <= 49 for n in main_numbers):
|
||
|
|
return False
|
||
|
|
|
||
|
|
if len(set(main_numbers)) != 6:
|
||
|
|
return False
|
||
|
|
|
||
|
|
# Superzahl (0-9)
|
||
|
|
if not isinstance(draw['SZ'], int) or not 0 <= draw['SZ'] <= 9:
|
||
|
|
return False
|
||
|
|
|
||
|
|
if not isinstance(draw['datum'], datetime):
|
||
|
|
return False
|
||
|
|
|
||
|
|
return True
|
||
|
|
|
||
|
|
except Exception:
|
||
|
|
return False
|
||
|
|
|
||
|
|
def fetch_from_all_apis(self) -> List[Dict]:
|
||
|
|
"""
|
||
|
|
Versucht alle APIs nacheinander.
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
Liste von Ziehungen
|
||
|
|
"""
|
||
|
|
print("\n🔍 SUCHE NACH DATEN VON APIs")
|
||
|
|
print("=" * 70)
|
||
|
|
|
||
|
|
all_draws = []
|
||
|
|
|
||
|
|
# Versuche alle APIs (GitHub zuerst, da zuverlässig)
|
||
|
|
for api_name in ['github', 'lottoapi']:
|
||
|
|
draws = self.fetch_from_api(api_name)
|
||
|
|
|
||
|
|
if draws:
|
||
|
|
all_draws.extend(draws)
|
||
|
|
print(f" ✅ {len(draws)} Ziehungen von {self.apis[api_name]['name']}")
|
||
|
|
break # Erste erfolgreiche API nutzen
|
||
|
|
else:
|
||
|
|
print(f" ⏭️ Weiter zur nächsten API...")
|
||
|
|
|
||
|
|
time.sleep(1) # Pause zwischen APIs
|
||
|
|
|
||
|
|
if not all_draws:
|
||
|
|
print("\n ❌ Keine Daten von APIs erhalten")
|
||
|
|
print(" 💡 Tipp: Verwende simple_update.py für manuelle Eingabe")
|
||
|
|
|
||
|
|
return all_draws
|
||
|
|
|
||
|
|
def merge_with_existing(self, new_draws: List[Dict]) -> pd.DataFrame:
|
||
|
|
"""Merged neue Ziehungen mit existierenden Daten."""
|
||
|
|
print(f"\n🔀 Merge mit existierenden Daten...")
|
||
|
|
|
||
|
|
if not new_draws:
|
||
|
|
print(" ⚠️ Keine neuen Ziehungen zum Mergen")
|
||
|
|
return self.df_existing
|
||
|
|
|
||
|
|
df_new = pd.DataFrame(new_draws)
|
||
|
|
|
||
|
|
if self.df_existing is None or len(self.df_existing) == 0:
|
||
|
|
df_combined = df_new
|
||
|
|
print(f" ✅ Neue Datei erstellt mit {len(df_combined)} Ziehungen")
|
||
|
|
else:
|
||
|
|
df_combined = pd.concat([self.df_existing, df_new], ignore_index=True)
|
||
|
|
|
||
|
|
before_dedup = len(df_combined)
|
||
|
|
df_combined = df_combined.drop_duplicates(subset=['datum'], keep='first')
|
||
|
|
after_dedup = len(df_combined)
|
||
|
|
|
||
|
|
duplicates = before_dedup - after_dedup
|
||
|
|
if duplicates > 0:
|
||
|
|
print(f" 🗑️ {duplicates} Duplikat(e) entfernt")
|
||
|
|
|
||
|
|
df_combined = df_combined.sort_values('datum', ascending=True)
|
||
|
|
df_combined = df_combined.reset_index(drop=True)
|
||
|
|
|
||
|
|
new_entries = len(df_combined) - (len(self.df_existing) if self.df_existing is not None else 0)
|
||
|
|
|
||
|
|
print(f" ✅ Merge abgeschlossen:")
|
||
|
|
print(f" Vorher: {len(self.df_existing) if self.df_existing is not None else 0} Ziehungen")
|
||
|
|
print(f" Neue: {new_entries} Ziehungen")
|
||
|
|
print(f" Gesamt: {len(df_combined)} Ziehungen")
|
||
|
|
|
||
|
|
return df_combined
|
||
|
|
|
||
|
|
def save_data(self, df: pd.DataFrame) -> bool:
|
||
|
|
"""Speichert Daten."""
|
||
|
|
try:
|
||
|
|
print(f"\n💾 Speichere Daten...")
|
||
|
|
|
||
|
|
df_export = df.copy()
|
||
|
|
df_export['datum'] = df_export['datum'].dt.strftime('%Y-%m-%d')
|
||
|
|
|
||
|
|
column_order = ['datum', 'Z1', 'Z2', 'Z3', 'Z4', 'Z5', 'Z6', 'SZ']
|
||
|
|
df_export = df_export[column_order]
|
||
|
|
|
||
|
|
df_export.to_csv(self.data_file, sep=';', index=False)
|
||
|
|
|
||
|
|
print(f" ✅ Gespeichert: {self.data_file}")
|
||
|
|
print(f" 📊 {len(df)} Ziehungen total")
|
||
|
|
|
||
|
|
if len(df) > 0:
|
||
|
|
latest = df['datum'].max()
|
||
|
|
oldest = df['datum'].min()
|
||
|
|
print(f" 📅 Zeitraum: {oldest.strftime('%Y-%m-%d')} bis {latest.strftime('%Y-%m-%d')}")
|
||
|
|
|
||
|
|
return True
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
print(f" ❌ Speicherfehler: {e}")
|
||
|
|
|
||
|
|
if self.backup_file and os.path.exists(self.backup_file):
|
||
|
|
print(" 🔄 Stelle Backup wieder her...")
|
||
|
|
shutil.copy2(self.backup_file, self.data_file)
|
||
|
|
print(" ✅ Backup wiederhergestellt")
|
||
|
|
|
||
|
|
return False
|
||
|
|
|
||
|
|
def update(self, api_name: str = 'all', create_backup: bool = True) -> bool:
|
||
|
|
"""
|
||
|
|
Führt komplettes Update durch.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
api_name: 'all' oder 'lottoapi'
|
||
|
|
create_backup: Backup erstellen
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
True bei Erfolg
|
||
|
|
"""
|
||
|
|
print("\n🚀 STARTE UPDATE")
|
||
|
|
print("=" * 70)
|
||
|
|
|
||
|
|
if not self.load_existing_data():
|
||
|
|
return False
|
||
|
|
|
||
|
|
if create_backup:
|
||
|
|
self.create_backup()
|
||
|
|
|
||
|
|
if api_name == 'all':
|
||
|
|
new_draws = self.fetch_from_all_apis()
|
||
|
|
else:
|
||
|
|
new_draws = self.fetch_from_api(api_name)
|
||
|
|
|
||
|
|
if not new_draws:
|
||
|
|
print("\n❌ Keine Daten von APIs geladen")
|
||
|
|
print("💡 Tipp: Verwende simple_update.py für manuelle Eingabe")
|
||
|
|
return False
|
||
|
|
|
||
|
|
df_updated = self.merge_with_existing(new_draws)
|
||
|
|
success = self.save_data(df_updated)
|
||
|
|
|
||
|
|
print("\n" + "=" * 70)
|
||
|
|
if success:
|
||
|
|
print("✅ UPDATE ERFOLGREICH ABGESCHLOSSEN")
|
||
|
|
else:
|
||
|
|
print("❌ UPDATE FEHLGESCHLAGEN")
|
||
|
|
print("=" * 70)
|
||
|
|
|
||
|
|
return success
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
"""Hauptfunktion."""
|
||
|
|
import sys
|
||
|
|
|
||
|
|
print()
|
||
|
|
print("=" * 70)
|
||
|
|
print(" LOTTO 6AUS49 API UPDATER")
|
||
|
|
print(" Unterstützt: GitHub Lotto Archive, lottoAPI")
|
||
|
|
print("=" * 70)
|
||
|
|
print()
|
||
|
|
|
||
|
|
default_file = "/Users/sebastianfrohlich/Library/Mobile Documents/com~apple~CloudDocs/Jupyter Notebooks/Lotto/data/AlleLottozahlen.csv"
|
||
|
|
|
||
|
|
if len(sys.argv) > 1:
|
||
|
|
data_file = sys.argv[1]
|
||
|
|
api_name = sys.argv[2] if len(sys.argv) > 2 else 'all'
|
||
|
|
else:
|
||
|
|
print(f"Standard-Datei: {default_file}")
|
||
|
|
use_default = input("\nStandard verwenden? (j/n): ").strip().lower()
|
||
|
|
|
||
|
|
if use_default in ['j', 'ja', 'y', 'yes', '']:
|
||
|
|
data_file = default_file
|
||
|
|
else:
|
||
|
|
data_file = input("Pfad zur Datei: ").strip()
|
||
|
|
|
||
|
|
api_name = 'all'
|
||
|
|
|
||
|
|
print()
|
||
|
|
|
||
|
|
updater = LottoAPIUpdater(data_file)
|
||
|
|
success = updater.update(api_name=api_name)
|
||
|
|
|
||
|
|
sys.exit(0 if success else 1)
|
||
|
|
|
||
|
|
|
||
|
|
if __name__ == "__main__":
|
||
|
|
main()
|