chore: sync project files

fetch_backmarket.py

@@ -0,0 +1,68 @@
+#!/usr/bin/env python3
+"""Script pour tester le scraping Backmarket - HTTP vs Playwright."""
+
+from pricewatch.app.scraping.http_fetch import fetch_http
+from pricewatch.app.scraping.pw_fetch import fetch_playwright
+
+url = "https://www.backmarket.fr/fr-fr/p/iphone-15-pro"
+
+print("=" * 80)
+print("TEST BACKMARKET.FR - HTTP vs PLAYWRIGHT")
+print("=" * 80)
+
+# Test 1: HTTP
+print("\n1. Test avec HTTP")
+print("-" * 80)
+result_http = fetch_http(url, timeout=30)
+
+if result_http.success and result_http.html:
+    print(f"✓ HTTP fonctionne!")
+    print(f"  Taille: {len(result_http.html)} chars")
+    print(f"  Status: {result_http.status_code}")
+    print(f"  Durée: {result_http.duration_ms}ms")
+
+    # Sauvegarder
+    with open("scraped/backmarket_http.html", "w", encoding="utf-8") as f:
+        f.write(result_http.html)
+    print(f"  Sauvegardé: scraped/backmarket_http.html")
+
+    # Vérifier si c'est du vrai contenu
+    if "iphone" in result_http.html.lower() and "pro" in result_http.html.lower():
+        print(f"  ✓ Contenu valide détecté")
+    else:
+        print(f"  ⚠ Contenu suspect (pas de mention iPhone/Pro)")
+else:
+    print(f"✗ HTTP a échoué: {result_http.error}")
+
+# Test 2: Playwright
+print("\n2. Test avec Playwright")
+print("-" * 80)
+result_pw = fetch_playwright(url, headless=True, timeout_ms=60000)
+
+if result_pw.success and result_pw.html:
+    print(f"✓ Playwright fonctionne!")
+    print(f"  Taille: {len(result_pw.html)} chars")
+    print(f"  Durée: {result_pw.duration_ms}ms")
+
+    # Sauvegarder
+    with open("scraped/backmarket_pw.html", "w", encoding="utf-8") as f:
+        f.write(result_pw.html)
+    print(f"  Sauvegardé: scraped/backmarket_pw.html")
+else:
+    print(f"✗ Playwright a échoué: {result_pw.error}")
+
+# Comparaison
+print("\n3. Comparaison")
+print("-" * 80)
+if result_http.success and result_pw.success:
+    size_diff = len(result_pw.html) - len(result_http.html)
+    print(f"Différence de taille: {size_diff:,} chars ({size_diff/len(result_http.html)*100:.1f}%)")
+
+    if size_diff > 10000:
+        print("→ Playwright récupère beaucoup plus de contenu")
+        print("→ Recommandation: Utiliser Playwright")
+    else:
+        print("→ HTTP et Playwright donnent des résultats similaires")
+        print("→ Recommandation: HTTP (plus rapide)")
+
+print("\n" + "=" * 80)