Initial commit: existing turf_saas codebase

Co-Authored-By: Paperclip <noreply@paperclip.ing>

multi_scraper.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python3
+"""
+Multi-site turf scraper
+Sources: Equidia, ZETurf, Canalturf, Boturfers
+"""
+import requests
+from bs4 import BeautifulSoup
+import json
+from datetime import datetime
+import re
+
+HEADERS = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
+}
+
+def scrape_equidia():
+    """Scrape Equidia - résultats détaillés"""
+    url = "https://www.equidia.fr/courses"
+    try:
+        r = requests.get(url, headers=HEADERS, timeout=10)
+        soup = BeautifulSoup(r.text, 'html.parser')
+        courses = []
+        for link in soup.select('a[href*="/courses/2026-"]'):
+            href = link.get('href', '')
+            if 'R1C' in href:
+                courses.append(f"https://www.equidia.fr{href}")
+        return list(set(courses))[:5]
+    except Exception as e:
+        print(f"Equidia error: {e}")
+        return []
+
+def scrape_zeturf():
+    """Scrape ZETurf - cotes"""
+    url = "https://www.zeturf.fr/fr/courses-du-jour"
+    try:
+        r = requests.get(url, headers=HEADERS, timeout=10)
+        soup = BeautifulSoup(r.text, 'html.parser')
+        courses = []
+        for link in soup.select('a[href*="/course-du-jour/"]'):
+            href = link.get('href', '')
+            courses.append(f"https://www.zeturf.fr{href}")
+        return list(set(courses))[:5]
+    except Exception as e:
+        print(f"ZETurf error: {e}")
+        return []
+
+def scrape_canalturf():
+    """Scrape Canalturf - pronostics"""
+    url = "https://www.canalturf.com/courses_chevaux_jour.php"
+    try:
+        r = requests.get(url, headers=HEADERS, timeout=10)
+        soup = BeautifulSoup(r.text, 'html.parser')
+        links = []
+        for link in soup.select('a'):
+            href = link.get('href', '')
+            if 'quinte' in href.lower():
+                links.append(f"https://www.canalturf.com{href}")
+        return list(set(links))[:5]
+    except Exception as e:
+        print(f"Canalturf error: {e}")
+        return []
+
+def scrape_boturfers():
+    """Scrape Boturfers - pronostics + stats"""
+    url = "https://www.boturfers.fr"
+    try:
+        r = requests.get(url, headers=HEADERS, timeout=10)
+        soup = BeautifulSoup(r.text, 'html.parser')
+        courses = []
+        for link in soup.select('a[href*="/quinte"]'):
+            href = link.get('href', '')
+            courses.append(f"https://www.boturfers.fr{href}")
+        return list(set(courses))[:5]
+    except Exception as e:
+        print(f"Boturfers error: {e}")
+        return []
+
+def main():
+    print(f"=== Turf Multi-Scraper {datetime.now().strftime('%Y-%m-%d %H:%M')} ===")
+    
+    print("\n[1/4] Scraping Equidia...")
+    equidia_courses = scrape_equidia()
+    print(f"   Found {len(equidia_courses)} courses")
+    
+    print("\n[2/4] Scraping ZETurf...")
+    zeturf_courses = scrape_zeturf()
+    print(f"   Found {len(zeturf_courses)} courses")
+    
+    print("\n[3/4] Scraping Canalturf...")
+    canalturf_courses = scrape_canalturf()
+    print(f"   Found {len(canalturf_courses)} courses")
+    
+    print("\n[4/4] Scraping Boturfers...")
+    boturfers_courses = scrape_boturfers()
+    print(f"   Found {len(boturfers_courses)} courses")
+    
+    data = {
+        'timestamp': datetime.now().isoformat(),
+        'equidia': equidia_courses,
+        'zeturf': zeturf_courses,
+        'canalturf': canalturf_courses,
+        'boturfers': boturfers_courses
+    }
+    
+    output_file = f"/home/h3r7/turf_scraper/courses_{datetime.now().strftime('%Y%m%d_%H%M')}.json"
+    with open(output_file, 'w') as f:
+        json.dump(data, f, indent=2)
+    
+    print(f"\n✅ Saved to {output_file}")
+    return data
+
+if __name__ == "__main__":
+    main()