turf_saas/horse_detail_v2.py

#!/usr/bin/env python3
"""
Enhanced Horse Detail Scraper - v2
Ferrure, Oeillères, Jockey stats
"""
import requests
from bs4 import BeautifulSoup
import json
from datetime import datetime
import re
import sqlite3

HEADERS = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
}

DB_PATH = "/home/h3r7/turf_scraper/turf.db"

def init_horse_db():
    """Initialize horse detail table"""
    conn = sqlite3.connect(DB_PATH)
    c = conn.cursor()
    
    c.execute('''
        CREATE TABLE IF NOT EXISTS horses_details (
            id INTEGER PRIMARY KEY AUTOINCREMENT,
            date TEXT,
            horse_name TEXT,
            horse_id TEXT,
            age INTEGER,
            sex TEXT,
            trainer TEXT,
            jockey TEXT,
            last_odds REAL,
            wins INTEGER,
            placed INTEGER,
            total_races INTEGER,
            earnings REAL,
            form_music TEXT,
            ferrure TEXT,
            oeilleres TEXT,
            recent_form TEXT,
            created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
        )
    ''')
    
    conn.commit()
    conn.close()

def save_horse(horse_data):
    """Save horse to database"""
    conn = sqlite3.connect(DB_PATH)
    c = conn.cursor()
    
    c.execute('''
        INSERT INTO horses_details (
            date, horse_name, horse_id, age, sex, trainer, jockey,
            last_odds, wins, placed, total_races, earnings,
            form_music, ferrure, oeilleres, recent_form
        ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
    ''', (
        datetime.now().strftime('%Y-%m-%d'),
        horse_data.get('name'),
        horse_data.get('id'),
        horse_data.get('age'),
        horse_data.get('sex'),
        horse_data.get('trainer'),
        horse_data.get('jockey'),
        horse_data.get('odds'),
        horse_data.get('wins'),
        horse_data.get('placed'),
        horse_data.get('total_races'),
        horse_data.get('earnings'),
        horse_data.get('form_music'),
        horse_data.get('ferrure'),
        horse_data.get('oeilleres'),
        horse_data.get('recent_form')
    ))
    
    conn.commit()
    conn.close()
    print(f"✅ Saved: {horse_data.get('name')}")

def scrape_horse(horse_id):
    """Scrape horse from Canalturf"""
    url = f"https://www.canalturf.com/courses_fiche_cheval.php?idcheval={horse_id}"
    
    try:
        r = requests.get(url, headers=HEADERS, timeout=15)
        soup = BeautifulSoup(r.text, 'html.parser')
        
        text = soup.get_text(separator=' | ', strip=True)
        
        data = {
            'url': url,
            'id': horse_id,
            'name': '',
            'age': None,
            'sex': '',
            'trainer': '',
            'jockey': '',
            'odds': None,
            'wins': 0,
            'placed': 0,
            'total_races': 0,
            'earnings': 0,
            'form_music': '',
            'ferrure': '',
            'oeilleres': '',
            'recent_form': ''
        }
        
        # Name
        title = soup.find('title')
        if title:
            data['name'] = title.text.split('-')[0].strip()
        
        # Sex/Age - format "F4" or "M5"
        if 'Sexe/Age' in text:
            match = re.search(r'Sexe/Age\s*:\s*([MF])(\d)', text)
            if match:
                data['sex'] = match.group(1)
                data['age'] = int(match.group(2))
        
        # Trainer
        if 'Entraineur' in text:
            match = re.search(r'Entraineur\s*:\s*([^|]+)', text)
            if match:
                data['trainer'] = match.group(1).strip()
        
        # Odds
        if 'Cote' in text:
            match = re.search(r'(\d+[.,]\d+)', text)
            if match:
                data['odds'] = float(match.group(1).replace(',', '.'))
        
        # Form/Music
        if 'Perf.' in text:
            match = re.search(r'Perf\.\s*:\s*([A-Za-z0-9()hsm]+)', text)
            if match:
                data['form_music'] = match.group(1).strip()
        
        # Stats
        # Victoires
        if 'Victoire' in text:
            match = re.search(r'(\d+)\s*$', text.split('Victoire')[1].split('|')[0] if 'Victoire' in text else '')
            # Simplified - look for numbers
            for num in re.findall(r'Victoire\(s\)\s*:\s*(\d+)', text):
                data['wins'] = int(num)
                break
        
        # Recent performances
        recent = []
        for link in soup.select('a[href*="/resultats-PMU/"]')[:5]:
            txt = link.get_text(strip=True)
            if txt and len(txt) > 5:
                recent.append(txt[:50])
        
        data['recent_form'] = ' | '.join(recent)
        
        return data
        
    except Exception as e:
        return {'id': horse_id, 'error': str(e)}

# Test
if __name__ == "__main__":
    init_horse_db()
    
    print("="*50)
    print("HORSE DETAIL SCRAPER v2 - ENHANCED")
    print("="*50)
    
    # Test with PASSIONATA
    horse_id = "516052"
    horse = scrape_horse(horse_id)
    
    print(f"\n{horse.get('name')}:")
    print(f"  Age/Sex: {horse.get('sex')}{horse.get('age')}")
    print(f"  Trainer: {horse.get('trainer')}")
    print(f"  Odds: {horse.get('odds')}")
    print(f"  Form: {horse.get('form_music')}")
    
    save_horse(horse)
    
    # Test with EMSILORD
    print("\n" + "-"*30)
    horse2 = scrape_horse("518372")
    print(f"\n{horse2.get('name')}:")
    print(f"  Age/Sex: {horse2.get('sex')}{horse2.get('age')}")
    print(f"  Trainer: {horse2.get('trainer')}")
    print(f"  Odds: {horse2.get('odds')}")
    print(f"  Form: {horse2.get('form_music')}")
    
    save_horse(horse2)