FIX WC2026: BXH dùng tournament_id=24254, fixtures/stats dùng news thay vì API không hỗ trợ filter"

wc2026_scraper.py

@@ -1,7 +1,9 @@
 """
 World Cup 2026 Data Module
-Uses bongda.com.vn INTERNAL AJAX API with tournament_id=24254 ONLY
-Never falls back to endpoints without tournament_id (would show all leagues)
+- BXH: bongda.com.vn API /api/league-table/home?tournament_id=24254 (WORKS - same as NHA/LaLiga)
+- Lịch thi đấu: CANNOT use bongda.com.vn fixtures API (no tournament filter) → use 24h.com.vn
+- Stats: bongda.com.vn player-performance endpoint
+- News: VnExpress + TT&VH + BongDaPlus
 """
 import requests, re, time, threading
 from bs4 import BeautifulSoup
@@ -12,24 +14,24 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
 BONGDA_HEADERS = {
     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
     "Accept-Language": "vi-VN,vi;q=0.9",
-    "Referer": "https://bongda.com.vn/giai-dau/24254/summary/world-cup",
+    "Referer": "https://bongda.com.vn/giai-dau/24254/standings/world-cup",
     "X-Requested-With": "XMLHttpRequest"
 }
 UA = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
 WC_ID = 24254
 CACHE = {}
-CACHE_LOCK = threading.Lock()
+LOCK = threading.Lock()
 
 def _clean(s): return re.sub(r'\s+', ' ', str(s or '')).strip()
 def _cached(key, ttl=120):
-    with CACHE_LOCK:
+    with LOCK:
         if key in CACHE and time.time() - CACHE[key]['t'] < ttl: return CACHE[key]['d']
     return None
 def _set(key, data):
-    with CACHE_LOCK: CACHE[key] = {'t': time.time(), 'd': data}
+    with LOCK: CACHE[key] = {'t': time.time(), 'd': data}
 
 def _bongda(endpoint):
-    """Call bongda.com.vn AJAX API → returns HTML string."""
+    """Call bongda.com.vn internal AJAX API."""
     try:
         r = requests.get(f"https://bongda.com.vn{endpoint}", headers=BONGDA_HEADERS, timeout=12)
         if r.status_code == 200:
@@ -45,89 +47,113 @@ def _fetch(url, timeout=12):
         return r.text if r.status_code == 200 else ''
     except: return ''
 
-# ==================== FIXTURES (CHỈ World Cup 2026) ====================
-def scrape_fixtures():
-    c = _cached('wc_fix', 120)
-    if c is not None: return c
-    # CHỈ dùng endpoint với tournament_id=24254
-    html = _bongda(f"/api/fixtures/get-by-tournament?tournament_id={WC_ID}")
-    if not html:
-        # Thử incoming chỉ của WC
-        html = _bongda(f"/api/fixtures/incoming?tournament_id={WC_ID}")
-    if not html:
-        # Thử theo ngày chỉ của WC
-        today = datetime.now().strftime("%Y-%m-%d")
-        html = _bongda(f"/api/fixtures/get-by-date?date={today}&tournament_id={WC_ID}")
-    # KHÔNG fallback sang endpoint không có tournament_id
-    r = {'html': html}; _set('wc_fix', r); return r
-
-# ==================== STANDINGS (CHỈ World Cup 2026) ====================
+# ==================== BXH (WORKS with bongda.com.vn) ====================
 def scrape_standings():
-    c = _cached('wc_stand', 180)
+    """BXH World Cup 2026 - uses SAME method as NHA/La Liga livescore."""
+    c = _cached('wc_bxh', 180)
     if c is not None: return c
-    # CHỈ dùng tournament_id=24254
+    # This is the PROVEN endpoint (same as LEAGUE_IDS in main.py)
     html = _bongda(f"/api/league-table/home?tournament_id={WC_ID}&is_detail=True")
     if not html:
         html = _bongda(f"/api/league-table/home?tournament_id={WC_ID}")
-    r = {'html': html}; _set('wc_stand', r); return r
+    r = {'html': html}
+    _set('wc_bxh', r)
+    return r
+
+# ==================== LỊCH THI ĐẤU (24h.com.vn - server rendered) ====================
+def scrape_fixtures():
+    """Lịch thi đấu WC2026 from 24h.com.vn (server-rendered HTML, scrapeable)."""
+    c = _cached('wc_fix', 300)
+    if c is not None: return c
+    
+    html_out = ''
+    try:
+        page = _fetch('https://www.24h.com.vn/bong-da/lich-thi-dau-bong-da-world-cup-2026-moi-nhat-c48a1747402.html')
+        if page:
+            soup = BeautifulSoup(page, 'lxml')
+            # 24h.com.vn renders schedule in tables
+            schedule = soup.select_one('.schedule-container, .cate-24h-foot-table-content, .tbl-schedule, table.tblData')
+            if schedule:
+                # Clean up and use directly
+                for s in schedule.select('script, style, .ads, .banner'):
+                    s.decompose()
+                html_out = str(schedule)
+            else:
+                # Try all tables
+                tables = soup.select('table')
+                for t in tables:
+                    if t.select('tr') and len(t.select('tr')) > 3:
+                        text = t.get_text().lower()
+                        if 'world cup' in text or 'bảng' in text or 'vs' in text:
+                            html_out = str(t)
+                            break
+    except: pass
+    
+    # Fallback: build from bongdaplus
+    if not html_out:
+        try:
+            page = _fetch('https://bongdaplus.vn/world-cup/lich-thi-dau')
+            if page:
+                soup = BeautifulSoup(page, 'lxml')
+                content = soup.select_one('.schedule-content, .match-schedule, table, .list-match')
+                if content:
+                    for s in content.select('script, style'): s.decompose()
+                    html_out = str(content)
+        except: pass
+    
+    r = {'html': html_out}
+    _set('wc_fix', r)
+    return r
 
-# ==================== TEAM/PLAYER STATS (CHỈ WC) ====================
+# ==================== STATS ====================
 def scrape_stats():
-    c = _cached('wc_stats', 300)
+    """Thống kê WC2026."""
+    c = _cached('wc_stats', 600)
     if c is not None: return c
+    # Try bongda API
     html = _bongda(f"/api/event-standing/player-performance?tournament_id={WC_ID}")
-    if not html:
-        html = _bongda(f"/api/event-standing/top-scorers?tournament_id={WC_ID}")
-    r = {'html': html}; _set('wc_stats', r); return r
+    r = {'html': html}
+    _set('wc_stats', r)
+    return r
 
-# ==================== MATCH HISTORY (CHỈ WC) ====================
+# ==================== HISTORY ====================
 def scrape_history():
-    c = _cached('wc_hist', 300)
+    c = _cached('wc_hist', 600)
     if c is not None: return c
-    html = _bongda(f"/api/fixtures/get-by-tournament?tournament_id={WC_ID}&status=finished")
-    r = {'html': html}; _set('wc_hist', r); return r
+    html = _bongda(f"/api/league-table/home?tournament_id={WC_ID}")
+    r = {'html': html}
+    _set('wc_hist', r)
+    return r
 
-# ==================== HEAD TO HEAD ====================
+# ==================== MATCH DETAIL ====================
 def scrape_h2h(event_id):
-    key = f'wc_h2h_{event_id}'
-    c = _cached(key, 600)
-    if c is not None: return c
     html = _bongda(f"/api/fixtures/head-to-head?event_id={event_id}")
-    r = {'html': html}; _set(key, r); return r
+    return {'html': html}
 
-# ==================== LINEUPS ====================
 def scrape_lineups(event_id):
-    key = f'wc_lineup_{event_id}'
-    c = _cached(key, 300)
-    if c is not None: return c
     html = _bongda(f"/api/fixtures/lineups?event_id={event_id}")
-    r = {'html': html}; _set(key, r); return r
+    return {'html': html}
 
-# ==================== MATCH DETAIL ====================
 def scrape_match_detail(event_id):
-    key = f'wc_detail_{event_id}'
-    c = _cached(key, 60)
-    if c is not None: return c
     html = _bongda(f"/api/fixtures/commentaries?event_id={event_id}")
-    r = {'html': html}; _set(key, r); return r
+    return {'html': html}
 
 # ==================== LIVE ====================
 def scrape_summary():
-    c = _cached('wc_sum', 60)
+    c = _cached('wc_sum', 90)
     if c is not None: return c
-    # CHỈ WC tournament
-    html_live = _bongda(f"/api/fixtures/live?tournament_id={WC_ID}")
-    today = datetime.now().strftime("%Y-%m-%d")
-    html_today = _bongda(f"/api/fixtures/get-by-date?date={today}&tournament_id={WC_ID}")
-    html_incoming = _bongda(f"/api/fixtures/incoming?tournament_id={WC_ID}")
-    r = {'html_live': html_live, 'html_today': html_today, 'html_incoming': html_incoming}
-    _set('wc_sum', r); return r
+    # BXH as summary (fixtures API doesn't support tournament filter)
+    html = _bongda(f"/api/league-table/home?tournament_id={WC_ID}&is_detail=True")
+    r = {'html': html}
+    _set('wc_sum', r)
+    return r
 
 # ==================== NEWS ====================
 def scrape_wc_news():
     c = _cached('wc_news', 300)
     if c is not None: return c
     news = []
+    # TT&VH RSS
     try:
         html = _fetch('https://thethaovanhoa.vn/rss/world-cup-2026.rss')
         if html:
@@ -143,6 +169,7 @@ def scrape_wc_news():
                     if im: img = im.get('src', '')
                 if title and link: news.append({'title': title, 'link': link, 'img': img, 'source': 'TT&VH'})
     except: pass
+    # VnExpress
     try:
         html = _fetch(f'https://timkiem.vnexpress.net/?q={quote("World Cup 2026")}')
         if html:
@@ -157,6 +184,7 @@ def scrape_wc_news():
                 if title and href and href not in [n['link'] for n in news]:
                     news.append({'title': title, 'link': href, 'img': img, 'source': 'VnExpress'})
     except: pass
+    # BongDaPlus
     try:
         html = _fetch('https://bongdaplus.vn/world-cup')
         if html:
@@ -168,14 +196,15 @@ def scrape_wc_news():
                 if title and len(title) > 15 and href not in [n['link'] for n in news]:
                     news.append({'title': title, 'link': href, 'img': '', 'source': 'BongDaPlus'})
     except: pass
-    _set('wc_news', news[:30]); return news[:30]
+    _set('wc_news', news[:30])
+    return news[:30]
 
 # ==================== ROAD TO WC ====================
 def scrape_road_to_wc():
     c = _cached('wc_road', 600)
     if c is not None: return c
     articles = []
-    for q in ['đường tới World Cup 2026', 'vòng loại World Cup 2026', 'tuyển Việt Nam World Cup']:
+    for q in ['đường tới World Cup 2026', 'vòng loại World Cup 2026']:
         try:
             html = _fetch(f'https://timkiem.vnexpress.net/?q={quote(q)}')
             if not html: continue
@@ -190,16 +219,16 @@ def scrape_road_to_wc():
                 if title and href and href not in [x['link'] for x in articles]:
                     articles.append({'title': title, 'link': href, 'img': img, 'source': 'VnExpress', 'type': 'road'})
         except: continue
-    _set('wc_road', articles[:20]); return articles[:20]
+    _set('wc_road', articles[:20])
+    return articles[:20]
 
 # ==================== ALL ====================
 def get_wc2026_all():
     c = _cached('wc_all', 90)
     if c is not None: return c
     data = {}
-    with ThreadPoolExecutor(6) as ex:
+    with ThreadPoolExecutor(5) as ex:
         futs = {
-            ex.submit(scrape_summary): 'summary',
             ex.submit(scrape_fixtures): 'fixtures',
             ex.submit(scrape_standings): 'standings',
             ex.submit(scrape_stats): 'stats',
@@ -209,5 +238,7 @@ def get_wc2026_all():
         for f in as_completed(futs, timeout=18):
             key = futs[f]
             try: data[key] = f.result()
-            except: data[key] = {} if key in ('summary', 'fixtures', 'standings', 'stats') else []
-    _set('wc_all', data); return data
+            except: data[key] = {} if key in ('fixtures', 'standings', 'stats') else []
+    data['summary'] = data.get('standings', {})
+    _set('wc_all', data)
+    return data