Update app_v2_entry.py

app_v2_entry.py

@@ -17,7 +17,12 @@ import re, html as html_lib, json, threading, time
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from urllib.parse import quote
 
-HL_LEAGUES['friendly'] = {"path": "giai-khac/friendly", "name": "Giao hữu", "emoji": "🤝"}
+# Update world-cup path to the actual xemlaibongda page (not qualifiers)
+HL_LEAGUES['world-cup'] = {"path": "the-gioi/world-cup", "name": "World Cup", "emoji": "🌍"}
+
+# Add friendly back
+if 'friendly' not in HL_LEAGUES:
+    HL_LEAGUES['friendly'] = {"path": "giai-khac/friendly", "name": "Giao hữu", "emoji": "🤝"}
 
 STATIC_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'static')
 app.router.routes=[r for r in app.router.routes if not(getattr(r,'path',None)=='/' and hasattr(r,'methods') and 'GET' in getattr(r,'methods',set()))]
@@ -26,27 +31,55 @@ app.router.routes=[r for r in app.router.routes if not isinstance(r, Mount)]
 
 def _clean(s): return re.sub(r"\s+"," ",html_lib.unescape(str(s or""))).strip()
 
-# Cache for match details (5 min TTL)
 _match_cache = {}
+_vtvnambo_cache = {'t': 0, 'd': []}
+_VTVNAMBO_CACHE_TTL = 1800  # 30 min
+
+def _yt_channel_shorts_fast(channel, count=15):
+    """Fast scrape YouTube shorts without yt-dlp."""
+    try:
+        url=f"https://www.youtube.com/@{channel}/shorts"
+        r=req.get(url,headers={**HEADERS,"Accept-Language":"vi,en;q=0.8"},timeout=15)
+        if r.status_code!=200:return[]
+        html=r.text
+        ids=[];items=[]
+        for m in re.finditer(r'"videoId":"([A-Za-z0-9_-]{11})"',html):
+            vid=m.group(1)
+            if vid in ids:continue
+            ids.append(vid)
+            snip=html[max(0,m.start()-900):m.start()+1600]
+            title=""
+            mt=re.search(r'"title":\{"runs":\[\{"text":"([^"]+)"',snip)
+            if mt:title=html_lib.unescape(mt.group(1)).replace('\n',' ').strip()
+            if not title:title="YouTube Short"
+            items.append({"title":title,"link":f"https://www.youtube.com/watch?v={vid}","img":f"https://i.ytimg.com/vi/{vid}/hqdefault.jpg","source":"yt","id":vid,"channel":channel})
+            if len(items)>=count:break
+        return items
+    except:return[]
+
+def _get_vtvnambo_shorts():
+    """Cached VTVNamBo shorts."""
+    now = time.time()
+    if _vtvnambo_cache['d'] and now - _vtvnambo_cache['t'] < _VTVNAMBO_CACHE_TTL:
+        return _vtvnambo_cache['d']
+    items = _yt_channel_shorts_fast("vtvnambo", 24)
+    _vtvnambo_cache['t'] = now
+    _vtvnambo_cache['d'] = items
+    return items
 
 # === FAST BONGDA PROXY ENDPOINT ===
 def _get_match_detail(event_id, slug=None):
-    """Internal function to scrape match detail from bongda.com.vn"""
     headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36", "Accept": "text/html", "Referer": "https://bongda.com.vn/"}
-    
     if slug:
         url = f"https://bongda.com.vn/tran-dau/{event_id}/centre/{slug}"
     else:
         url = f"https://bongda.com.vn/tran-dau/{event_id}"
-    
     resp = req.get(url, headers=headers, timeout=15, allow_redirects=True)
     if resp.status_code != 200:
         return None
-    
     soup = BeautifulSoup(resp.text, 'html.parser')
     result = {"event_id": event_id, "found": False, "sections": []}
     info = {}
-    
     tel = soup.select_one('.teams')
     if tel:
         he = tel.select_one('.team.home')
@@ -68,27 +101,22 @@ def _get_match_detail(event_id, slug=None):
             if len(parts) >= 2: info['score'] = f"{parts[0]} - {parts[1]}"
             lb = sc.select_one('.label')
             if lb: info['status_label'] = _clean(lb.get_text())
-    
     if info.get('home_team') and info.get('away_team'):
         result['info'] = info
         result['found'] = True
         result['sections'].append('info')
-    
     events = []
     for ev in soup.select('.events .period .event'):
         ev_cls = ' '.join(ev.get('class', []))
         ev_data = {'team': 'home' if 'home' in ev_cls else 'away', 'period': '', 'type': 'unknown', 'time': '', 'players': ''}
-        
         parent = ev.parent
         if parent:
             h2 = parent.find('h2')
             if h2: ev_data['period'] = _clean(h2.get_text())
-        
         if ev.select_one('[class*="goal"]'): ev_data['type'] = 'goal'
         elif ev.select_one('[class*="redcard"]'): ev_data['type'] = 'redcard'
         elif ev.select_one('[class*="yellowcard"]'): ev_data['type'] = 'yellowcard'
         elif ev.select_one('[class*="substitution"]'): ev_data['type'] = 'substitution'
-        
         players_el = ev.select_one('.players')
         if players_el:
             pl_text = _clean(players_el.get_text(' ', strip=True))
@@ -99,11 +127,9 @@ def _get_match_detail(event_id, slug=None):
             else:
                 ev_data['players'] = pl_text
         events.append(ev_data)
-    
     if events:
         result['events'] = events
         result['sections'].append('events')
-    
     pred = soup.select_one('.prediction-card')
     if pred:
         team_info = pred.select_one('.team-info')
@@ -118,7 +144,6 @@ def _get_match_detail(event_id, slug=None):
                 vc = pred.select_one('.vote-count')
                 if vc: pred_data['vote_count'] = _clean(vc.get_text())
             result['prediction'] = pred_data
-    
     recent = []
     ml = soup.select_one('.matches-list')
     if ml:
@@ -133,7 +158,6 @@ def _get_match_detail(event_id, slug=None):
     if recent:
         result['recent_matches'] = recent
         result['sections'].append('recent')
-    
     try:
         api_h = {"User-Agent": "Mozilla/5.0", "Accept": "application/json", "X-Requested-With": "XMLHttpRequest", "Referer": "https://bongda.com.vn/"}
         ar = req.get(f"https://bongda.com.vn/api/fixtures/h2h-stats?event_id={event_id}", headers=api_h, timeout=10)
@@ -151,20 +175,17 @@ def _get_match_detail(event_id, slug=None):
                     result['h2h_stats_parsed'] = ast
                     result['sections'].append('h2h_stats')
     except: pass
-    
     return result
 
 @app.get('/api/proxy/bongda')
 def proxy_bongda(event_id: int = Query(default=None), slug: str = Query(default=None)):
     if event_id is None:
         return JSONResponse({'error': 'event_id required'}, status_code=400)
-    
     cache_key = f"{event_id}_{slug}"
     now = time.time()
     cached = _match_cache.get(cache_key)
     if cached and now - cached.get('_ts', 0) < 300:
         return JSONResponse(cached)
-    
     try:
         result = _get_match_detail(event_id, slug)
         if result:
@@ -175,26 +196,21 @@ def proxy_bongda(event_id: int = Query(default=None), slug: str = Query(default=
         err = {"event_id": event_id, "found": False, "error": str(e), "_ts": now}
         _match_cache[cache_key] = err
         return JSONResponse(err)
-    
     return JSONResponse({"event_id": event_id, "found": False})
 
 @app.get('/api/match/{event_id}/detail')
 def api_match_detail(event_id: int, url: str = Query(default=None)):
-    # Try to extract slug from url if provided
     slug = None
     if url:
         m = re.match(r'.+/tran-dau/\d+/(?:centre|preview)/(.+)', url)
         if m:
             slug = m.group(1)
-    
     cache_key = f"{event_id}_{slug or ''}"
     now = time.time()
     cached = _match_cache.get(cache_key)
     if cached and now - cached.get('_ts', 0) < 300:
         return JSONResponse(cached)
-    
     try:
-        # If no slug, try to find it from homepage
         if not slug:
             try:
                 home_r = req.get("https://bongda.com.vn/", headers={"User-Agent": "Mozilla/5.0"}, timeout=10)
@@ -208,7 +224,6 @@ def api_match_detail(event_id: int, url: str = Query(default=None)):
                             cache_key = f"{event_id}_{slug}"
                             break
             except: pass
-        
         result = _get_match_detail(event_id, slug)
         if result:
             result['_ts'] = now
@@ -218,10 +233,13 @@ def api_match_detail(event_id: int, url: str = Query(default=None)):
         err = {"event_id": event_id, "found": False, "error": str(e), "_ts": now}
         _match_cache[cache_key] = err
         return JSONResponse(err)
-    
     return JSONResponse({"event_id": event_id, "found": False})
 
-# === Rest of endpoints (existing) ===
+# === VTVNamBo Shorts API ===
+@app.get('/api/shorts/vtvnambo')
+def api_shorts_vtvnambo():
+    return JSONResponse(_get_vtvnambo_shorts())
+
 _STOP=set('và của các những một được trong với cho tại sau trước khi không người việt nam hôm nay mới nhất nóng tin tức cập nhật theo từ đến là có thì này đã để'.split())
 
 def _has_kw(topic,title):
@@ -498,4 +516,4 @@ def _bg():
         time.sleep(90)
 threading.Thread(target=_bg,daemon=True).start()
 
-app.mount('/static',StaticFiles(directory=STATIC_DIR),name='vnews_static')
+app.mount('/static',StaticFiles(directory=STATIC_DIR),name='vnews_static')