Add debug logging to match_detail.py to trace scraping issues

match_detail.py

@@ -127,7 +127,7 @@ def _get_h2h(soup):
                     m['date'] = _cl(cells[0].get_text())
                     m['home'] = _cl(cells[1].get_text())
                     m['score'] = _cl(cells[2].get_text())
-                if m.get('home') and m.get('away' if len(cells) > 3 else 'home'):
+                if m.get('home'):
                     if len(cells) > 3: m['away'] = _cl(cells[3].get_text())
                     h2h['matches'].append(m)
             if h2h['matches']: break
@@ -159,14 +159,17 @@ def _get_info(soup):
     return info
 
 def _scrape(url):
+    print(f"[DEBUG] _scrape: {url[:80]}", flush=True)
     try:
         r = requests.get(url, headers=HH, timeout=15, allow_redirects=True)
+        print(f"[DEBUG] HTTP={r.status_code}", flush=True)
         if r.status_code != 200:
             return False, {}
         sp = _sp(r.text)
         d = {}
         
         teams = _get_teams(sp)
+        print(f"[DEBUG] teams={teams}", flush=True)
         if teams: d['info'] = teams
         
         mi = _get_info(sp)
@@ -195,8 +198,12 @@ def _scrape(url):
             if fm.get('home'): d['home_form'] = fm['home']
             if fm.get('away'): d['away_form'] = fm['away']
         
+        print(f"[DEBUG] success keys={list(d.keys())}", flush=True)
         return True, d
     except Exception as e:
+        import traceback
+        print(f"[DEBUG] error: {e}", flush=True)
+        traceback.print_exc()
         return False, {}
 
 def fetch_match_detail_by_url(url):
@@ -204,37 +211,33 @@ def fetch_match_detail_by_url(url):
     if not m: return {"error": "Could not extract event_id", "found": False}
     event_id = int(m.group(1))
     res = {"event_id": event_id, "found": False, "sections": []}
-    
-    # API
     _fetch_api(event_id, res)
-    # HTML
     ok, d = _scrape(url)
+    print(f"[DEBUG] by_url: ok={ok} d_keys={list(d.keys())}", flush=True)
     if ok: _merge(res, d)
     return res
 
 def fetch_match_detail(event_id):
+    print(f"[DEBUG] fetch_match_detail({event_id})", flush=True)
     res = {"event_id": event_id, "found": False, "sections": []}
-    
-    # API first
     _fetch_api(event_id, res)
     
-    # Then HTML (centre first, then preview)
     for pt in ["centre", "preview"]:
         url = f"https://bongda.com.vn/tran-dau/{event_id}/{pt}/"
         ok, d = _scrape(url)
+        print(f"[DEBUG] {pt}: ok={ok}", flush=True)
         if ok:
             _merge(res, d)
             if res.get("found"): break
     
+    print(f"[DEBUG] final: found={res['found']} sections={res['sections']}", flush=True)
     return res
 
 def _fetch_api(eid, res):
-    # pre-match
     pm = _api("/api/event-standing/pre-match", {"event_id": eid})
     res["pre_match"] = pm
     res["pre_match_html"] = pm.get("html","") if pm and pm.get("status")=="success" and len(pm.get("html","").strip())>10 else ""
     
-    # h2h matches
     hm = _api("/api/fixtures/h2h-match", {"event_id": eid})
     res["h2h_match"] = hm
     if hm and hm.get("status")=="success":
@@ -244,7 +247,6 @@ def _fetch_api(eid, res):
             res["sections"].append("h2h")
     else: res["h2h_html"] = ""
     
-    # h2h stats
     hs = _api("/api/fixtures/h2h-stats", {"event_id": eid})
     res["h2h_stats"] = hs
     if hs and hs.get("status")=="success":
@@ -252,7 +254,6 @@ def _fetch_api(eid, res):
         if len(h.strip())>10:
             res["h2h_stats_html"] = h
             res["sections"].append("h2h_stats")
-            # Parse stats
             try:
                 sp = _sp(h)
                 stats = {}
@@ -265,7 +266,6 @@ def _fetch_api(eid, res):
             except: pass
     else: res["h2h_stats_html"] = ""
     
-    # performance
     pf = _api("/api/event-standing/player-performance", {"event_id": eid})
     res["performance"] = pf
     if pf and pf.get("status")=="success" and len(pf.get("html","").strip())>10:
@@ -273,7 +273,6 @@ def _fetch_api(eid, res):
         res["sections"].append("stats")
     else: res["stats_html"] = ""
     
-    # commentaries
     cm = _api("/api/fixtures/commentaries", {"event_id": eid})
     if cm and cm.get("status")=="success" and len(cm.get("html","").strip())>10:
         res["commentaries_html"] = cm["html"]