Add highlights by league (Premier League, FA Cup, Bundesliga, Serie A, La Liga, Champions League, Europa League, World Cup 2026 Qualifiers)

main.py

@@ -20,6 +20,19 @@ _cache_ttl_live = 60
 _cache_ttl_yt = 1800
 PRIORITY_LEAGUES = ["Ngoại Hạng Anh","FA Cup","Champions League","LaLiga","Copa del Rey","Serie A","Bundesliga","Ligue 1","V-League"]
 LEAGUE_IDS = {"nha":27110,"laliga":27233,"seriea":27044,"bundesliga":26891,"ligue1":27212}
+
+# ===== HIGHLIGHT LEAGUE CONFIG =====
+HL_LEAGUES = {
+    "premier-league": {"path": "anh/premier-league", "name": "Premier League", "emoji": "🏴󠁧󠁢󠁥󠁮󠁧󠁿"},
+    "fa-cup": {"path": "anh/fa-cup", "name": "FA Cup", "emoji": "🏆"},
+    "bundesliga": {"path": "duc/bundesliga", "name": "Bundesliga", "emoji": "🇩🇪"},
+    "serie-a": {"path": "italy/serie-a", "name": "Serie A", "emoji": "🇮🇹"},
+    "la-liga": {"path": "tay-ban-nha/la-liga", "name": "La Liga", "emoji": "🇪🇸"},
+    "champions-league": {"path": "cup-chau-au/uefa-champions-league", "name": "Champions League", "emoji": "⭐"},
+    "europa-league": {"path": "cup-chau-au/uefa-europa-league", "name": "Europa League", "emoji": "🟠"},
+    "world-cup": {"path": "the-gioi/world-cup-qualifiers", "name": "World Cup 2026", "emoji": "🌍"},
+}
+
 def _cached(key, fn, ttl=None):
     now=time.time();t=ttl or _cache_ttl
     if key in _cache and now-_cache[key]["t"]<t:return _cache[key]["d"]
@@ -81,7 +94,6 @@ def proxy_m3u8(url: str = Query(...)):
 def proxy_video(url: str = Query(...), request: Request = None):
     """Proxy MP4/video for sources that block cross-origin (BDP). Supports range requests."""
     try:
-        # Pass through range header for seeking
         req_headers = dict(HEADERS)
         if request and request.headers.get("range"):
             req_headers["Range"] = request.headers["range"]
@@ -104,10 +116,11 @@ def proxy_video(url: str = Query(...), request: Request = None):
         return Response(status_code=502, content="proxy error")
 
 # ===== XEMLAIBONGDA HIGHLIGHTS =====
-def scrape_xemlaibongda():
-    """Get highlight videos from xemlaibongda.top - returns HLS m3u8 streams."""
+def _scrape_xemlaibongda_page(page_path):
+    """Scrape highlights from a specific xemlaibongda page (league or homepage)."""
     try:
-        r=requests.get("https://xemlaibongda.top/",headers=HEADERS,timeout=15)
+        url = f"https://xemlaibongda.top/{page_path}" if page_path else "https://xemlaibongda.top/"
+        r=requests.get(url,headers=HEADERS,timeout=15)
         if r.status_code!=200:return[]
         r.encoding="utf-8"
         soup=BeautifulSoup(r.text,"lxml")
@@ -118,23 +131,45 @@ def scrape_xemlaibongda():
             if not href.startswith("http"):href="https://xemlaibongda.top"+href
             if href in seen:continue
             seen.add(href)
-            # Title from URL slug
             slug=href.split("/video/")[-1].rstrip("/")
             title=slug.replace("-"," ").title()
             title=re.sub(r'\d{4}\s*\d{2}\s*\d{2}$','',title).strip()
             title=re.sub(r'\s+V\s+',' vs ',title)
             title=re.sub(r'\s+Vs\s+',' vs ',title)
-            # Image
             img=a.find("img") or (a.parent.find("img") if a.parent else None)
             img_src=""
             if img:img_src=img.get("data-src","") or img.get("src","") or img.get("data-lazy","")
             if not img_src:
                 img_src=f"https://img.refooty.com/thumbnail/{slug}.webp"
             videos.append({"title":title,"link":href,"img":img_src,"source":"xemlaibongda"})
-            if len(videos)>=20:break
+            if len(videos)>=12:break
         return videos
     except:return[]
 
+def scrape_xemlaibongda():
+    """Get all highlight videos from homepage."""
+    return _scrape_xemlaibongda_page("")
+
+def scrape_highlights_by_league(league_key):
+    """Get highlights for a specific league."""
+    if league_key not in HL_LEAGUES:return[]
+    return _scrape_xemlaibongda_page(HL_LEAGUES[league_key]["path"])
+
+def scrape_all_league_highlights():
+    """Fetch highlights for all leagues in parallel."""
+    results = {}
+    def _fetch(key):
+        return key, scrape_highlights_by_league(key)
+    with ThreadPoolExecutor(8) as ex:
+        futs = [ex.submit(_fetch, k) for k in HL_LEAGUES]
+        for f in as_completed(futs):
+            try:
+                key, vids = f.result()
+                if vids:
+                    results[key] = vids[:6]
+            except:pass
+    return results
+
 def extract_xemlaibongda_video(url):
     """Extract HLS m3u8 URL from xemlaibongda article page."""
     try:
@@ -151,7 +186,6 @@ def extract_xemlaibongda_video(url):
                 if source:src=source.get("src","")
             if src:
                 return{"src":src,"poster":poster,"type":"hls" if".m3u8" in src else"video"}
-        # Fallback: search for m3u8 in page
         m3u8s=re.findall(r'(https?://[^\s"\'<>]+\.m3u8)',r.text)
         if m3u8s:
             og=soup.find("meta",property="og:image")
@@ -246,23 +280,33 @@ def api_shorts():
 @app.get("/api/highlights")
 def api_highlights():
     return JSONResponse(_cached("xemlaibongda_hl",scrape_xemlaibongda,ttl=_cache_ttl))
+@app.get("/api/highlights/leagues")
+def api_highlights_leagues():
+    """Get highlights grouped by league for homepage display."""
+    return JSONResponse(_cached("hl_leagues",scrape_all_league_highlights,ttl=_cache_ttl))
+@app.get("/api/highlights/{league}")
+def api_highlights_league(league:str):
+    """Get highlights for a specific league."""
+    if league not in HL_LEAGUES:
+        return JSONResponse({"error":"league not found"})
+    return JSONResponse(_cached(f"hl_{league}",lambda:scrape_highlights_by_league(league),ttl=_cache_ttl))
+@app.get("/api/highlights_config")
+def api_highlights_config():
+    """Return league config for frontend."""
+    return JSONResponse(HL_LEAGUES)
 @app.get("/api/video_url")
 def api_video_url(url:str=Query(...)):
-    # YouTube
     if "youtube.com" in url or "youtu.be" in url:
         m=re.search(r'(?:v=|shorts/|youtu\.be/)([a-zA-Z0-9_-]{11})',url)
         if m:
             vid=m.group(1)
             return JSONResponse({"src":f"https://www.youtube.com/embed/{vid}?autoplay=1&rel=0&enablejsapi=1","poster":f"https://i.ytimg.com/vi/{vid}/hqdefault.jpg","type":"youtube"})
-    # xemlaibongda - return proxied m3u8 URL
     if "xemlaibongda.top" in url:
         v=extract_xemlaibongda_video(url)
         if v:
             if v["type"]=="hls":
-                # Proxy the m3u8 through our server to fix CORS
                 v["src"] = "/api/proxy/m3u8?url=" + quote(v["src"], safe="")
             return JSONResponse(v)
-    # BDP - return proxied video URL
     if "bongdaplus.vn" in url:
         try:
             m=re.search(r'-(\d{6,})\.html',url)
@@ -274,7 +318,6 @@ def api_video_url(url:str=Query(...)):
                     src=source.get("src","") if source else ""
                     poster=video.get("poster","")
                     if src:
-                        # Proxy through our server to fix CORS
                         proxied_src = "/api/proxy/video?url=" + quote(src, safe="")
                         return JSONResponse({"src":proxied_src,"poster":poster,"type":"video"})
         except:pass