revert: restore index.html + main.py to ed6aeb52 (stable version before comment bug)

main.py

@@ -15,18 +15,15 @@ BASE_24H = "https://www.24h.com.vn"
 SPACE_URL = "https://bep40-vnews.hf.space"
 _cache = {}
 _cache_ttl = 300
-
 def _cached(key, fn):
     now=time.time()
     if key in _cache and now-_cache[key]["t"]<_cache_ttl:return _cache[key]["d"]
     try:data=fn()
     except:data=_cache.get(key,{}).get("d",[])
     _cache[key]={"d":data,"t":now};return data
-
 def _get(url,headers=None):
     h=headers or HEADERS;r=requests.get(url,headers=h,timeout=15);r.encoding="utf-8"
     return BeautifulSoup(r.text,"lxml")
-
 def scrape_vne(cat_url):
     try:
         soup=_get(cat_url);arts=[]
@@ -43,7 +40,6 @@ def scrape_vne(cat_url):
             arts.append({"title":t,"link":lk,"img":img,"summary":(desc.get_text(strip=True)[:150] if desc else ""),"source":"vne"})
         return arts
     except:return[]
-
 def scrape_vne_article(url):
     try:
         soup=_get(url);h1=soup.select_one("h1.title-detail");desc=soup.select_one("p.description")
@@ -59,45 +55,6 @@ def scrape_vne_article(url):
                 elif ch.name in("h2","h3"):body.append({"type":"heading","text":ch.get_text(strip=True)})
         return{"title":h1.get_text(strip=True) if h1 else "","summary":desc.get_text(strip=True) if desc else "","og_image":og_img,"body":body,"source":"vne","url":url}
     except:return None
-
-def scrape_bdp_article(url):
-    try:
-        soup=_get(url);h1=soup.select_one(".lead-title h1") or soup.select_one("h1")
-        og=soup.find("meta",property="og:image");og_img=og.get("content","") if og else ""
-        se=soup.select_one("div.summary");body=[]
-        cd=soup.select_one("div.content#postContent") or soup.select_one("div.content")
-        if cd:
-            for ch in cd.children:
-                if not hasattr(ch,'name') or not ch.name:continue
-                if ch.name=="p":
-                    im=ch.find("img")
-                    if im:
-                        s=im.get("src") or im.get("data-src","")
-                        if s:body.append({"type":"img","src":s,"alt":""})
-                    t=ch.get_text(strip=True)
-                    if t:body.append({"type":"p","text":t})
-                elif ch.name in("h2","h3"):body.append({"type":"heading","text":ch.get_text(strip=True)})
-        return{"title":h1.get_text(strip=True) if h1 else "","summary":se.get_text(strip=True) if se else "","og_image":og_img,"body":body,"source":"bdp","url":url}
-    except:return None
-
-def scrape_24h_article(url):
-    try:
-        r=requests.get(url,headers=HEADERS,timeout=15);r.encoding="utf-8"
-        soup=BeautifulSoup(r.text,"lxml");h1=soup.select_one("h1")
-        og=soup.find("meta",property="og:image");og_img=og.get("content","") if og else ""
-        desc=soup.find("meta",property="og:description");summary=desc.get("content","")[:200] if desc else ""
-        body=[]
-        for sel in["div.the-article-body","div.nws-mainContent","div.nwsCt","div.detail-content"]:
-            cd=soup.select_one(sel)
-            if cd:
-                for ch in cd.children:
-                    if not hasattr(ch,'name') or not ch.name:continue
-                    if ch.name=="p":t=ch.get_text(strip=True);(body.append({"type":"p","text":t}) if t else None)
-                    elif ch.name in("h2","h3"):body.append({"type":"heading","text":ch.get_text(strip=True)})
-                break
-        return{"title":h1.get_text(strip=True) if h1 else "","summary":summary,"og_image":og_img,"body":body,"source":"24h","url":url}
-    except:return None
-
 def scrape_bdp(url):
     try:
         soup=_get(url);arts=[];seen=set()
@@ -113,7 +70,6 @@ def scrape_bdp(url):
                 seen.add(lk);arts.append({"title":t,"link":lk,"img":img,"source":"bdp","summary":""})
         return arts[:15]
     except:return[]
-
 def scrape_bdp_videos():
     try:
         soup=_get(f"{BASE_BDP}/video");arts=[];seen=set()
@@ -129,7 +85,6 @@ def scrape_bdp_videos():
             seen.add(href);arts.append({"title":title,"link":href,"img":img,"source":"bdp"})
         return arts[:20]
     except:return[]
-
 def scrape_24h_highlights():
     try:
         soup=_get(f"{BASE_24H}/video-highlight-c953.html");arts=[];seen=set()
@@ -152,7 +107,6 @@ def scrape_24h_highlights():
             with ThreadPoolExecutor(5) as ex:list(ex.map(_og,need))
         return arts[:30]
     except:return[]
-
 def scrape_24h_shorts():
     try:
         r=requests.get(f"{BASE_24H}/video/video-tin-tuc-cvd769.html",headers=HEADERS,timeout=15);r.encoding="utf-8"
@@ -184,7 +138,6 @@ def scrape_24h_shorts():
                 seen.add(href);arts.append({"title":title,"link":href,"img":img_src,"source":"24h-shorts"})
         return arts[:20]
     except:return[]
-
 def scrape_bbc_vietnamese():
     try:
         bbc_h={"User-Agent":"Mozilla/5.0","Accept-Language":"en-GB,en;q=0.9"}
@@ -208,7 +161,6 @@ def scrape_bbc_vietnamese():
             if len(arts)>=15:break
         return arts
     except:return[]
-
 def scrape_bbc_article(url):
     try:
         r=requests.get(url,headers={"User-Agent":"Mozilla/5.0","Accept-Language":"en-GB"},timeout=15);r.encoding="utf-8"
@@ -223,7 +175,6 @@ def scrape_bbc_article(url):
             if src and("ichef" in src or"bbci" in src):body.append({"type":"img","src":src,"alt":img.get("alt","")})
         return{"title":h1.get_text(strip=True) if h1 else "","summary":"","og_image":og_img,"body":body,"source":"bbc","url":url}
     except:return None
-
 def extract_video_url(article_url):
     try:
         r=requests.get(article_url,headers={**HEADERS,"Referer":"https://www.24h.com.vn/"},timeout=10);r.encoding="utf-8"
@@ -233,8 +184,7 @@ def extract_video_url(article_url):
         primary=full or p720
         if not primary:return None
         soup=BeautifulSoup(r.text,"lxml");og=soup.find("meta",property="og:image");poster=og.get("content","") if og else ""
-        base_url=primary[0];parts=[base_url]
-        is_720p='_720p.m3u8' in base_url;name=base_url.replace('_720p.m3u8','').replace('.m3u8','')
+        base_url=primary[0];parts=[base_url];is_720p='_720p.m3u8' in base_url;name=base_url.replace('_720p.m3u8','').replace('.m3u8','')
         m=re.search(r'(\D)(\d{1,2})$',name)
         if m:
             cur=int(m.group(2));w=len(m.group(2));bn=name[:m.start(2)]
@@ -260,7 +210,6 @@ def extract_video_url(article_url):
         if len(parts)>1:return{"src":parts[0],"poster":poster,"all_parts":parts}
         return{"src":primary[0],"poster":poster}
     except:return None
-
 def extract_bdp_video(url):
     try:
         m=re.search(r'-(\d{6,})\.html',url)
@@ -271,11 +220,8 @@ def extract_bdp_video(url):
         source=video.find("source")
         return{"src":source.get("src","") if source else "","poster":video.get("poster","")}
     except:return None
-
-# API
 VNE_CATS={"thoi-su":("https://vnexpress.net/thoi-su","Thời Sự"),"the-gioi":("https://vnexpress.net/the-gioi","Thế Giới"),"kinh-doanh":("https://vnexpress.net/kinh-doanh","Kinh Doanh"),"cong-nghe":("https://vnexpress.net/so-hoa","Công Nghệ"),"the-thao":("https://vnexpress.net/the-thao","Thể Thao"),"giai-tri":("https://vnexpress.net/giai-tri","Giải Trí"),"suc-khoe":("https://vnexpress.net/suc-khoe","Sức Khỏe")}
 BDP_CATS={"ngoai-hang-anh":("https://bongdaplus.vn/ngoai-hang-anh","Ngoại Hạng Anh"),"la-liga":("https://bongdaplus.vn/la-liga","La Liga"),"champions-league":("https://bongdaplus.vn/champions-league-cup-c1","Champions League"),"bong-da-vn":("https://bongdaplus.vn/bong-da-viet-nam","Bóng Đá VN")}
-
 @app.get("/api/homepage")
 def api_homepage():
     def _f():
@@ -292,7 +238,6 @@ def api_homepage():
         except:pass
         return articles
     return JSONResponse(_cached("homepage",_f))
-
 @app.get("/api/category/{cat_id}")
 def api_category(cat_id:str):
     def _f():
@@ -301,43 +246,35 @@ def api_category(cat_id:str):
         if cat_id in BDP_CATS:arts=scrape_bdp(BDP_CATS[cat_id][0]);[a.update({"group":BDP_CATS[cat_id][1]}) for a in arts];return arts
         return[]
     return JSONResponse(_cached(f"cat_{cat_id}",_f))
-
 @app.get("/api/categories")
 def api_categories():
     cats=[{"id":"bbc","name":"BBC Tiếng Việt","source":"bbc"}]
     for k,(u,n) in VNE_CATS.items():cats.append({"id":k,"name":n,"source":"vne"})
     for k,(u,n) in BDP_CATS.items():cats.append({"id":k,"name":n,"source":"bdp"})
     return JSONResponse(cats)
-
 @app.get("/api/highlights")
 def api_highlights():return JSONResponse(_cached("highlights",scrape_24h_highlights))
 @app.get("/api/shorts")
 def api_shorts():return JSONResponse(_cached("shorts",scrape_24h_shorts))
 @app.get("/api/bdp_videos")
 def api_bdp_videos():return JSONResponse(_cached("bdp_videos",scrape_bdp_videos))
-
 @app.get("/api/video_url")
 def api_video_url(url:str=Query(...)):
     if"24h.com.vn" in url:v=extract_video_url(url)
     elif"bongdaplus.vn" in url:v=extract_bdp_video(url)
     else:v=None
     return JSONResponse(v if v else{"error":"not found"})
-
-# ★ FIX: supports ALL sources now
 @app.get("/api/article")
 def api_article(url:str=Query(...)):
-    data=None
     if"vnexpress.net" in url:data=scrape_vne_article(url)
     elif"bbc.com" in url:data=scrape_bbc_article(url)
-    elif"bongdaplus.vn" in url:data=scrape_bdp_article(url)
-    elif"24h.com.vn" in url:data=scrape_24h_article(url)
+    else:data=None
     return JSONResponse(data if data else{"error":"not supported"})
-
 @app.get("/s")
 async def share_redirect(url:str=Query(default=""),title:str=Query(default="VNEWS"),img:str=Query(default="")):
     og_image=unquote(img) if img else "https://s1.vnecdn.net/vnexpress/restruct/i/v9505/logo_default.jpg"
     decoded_url=unquote(url)
-    redirect_target=f"{SPACE_URL}/?open={quote(decoded_url,'')}" if decoded_url else SPACE_URL
+    redirect_script=f'<script>localStorage.setItem("pending_article","{decoded_url}");location.href="{SPACE_URL}";</script>' if decoded_url else f'<script>location.href="{SPACE_URL}";</script>'
     return HTMLResponse(f'''<!DOCTYPE html><html><head>
 <meta charset="utf-8"><title>{unquote(title)}</title>
 <meta property="og:title" content="{unquote(title)}">
@@ -349,10 +286,8 @@ async def share_redirect(url:str=Query(default=""),title:str=Query(default="VNEW
 <meta name="twitter:card" content="summary_large_image">
 <meta name="twitter:title" content="{unquote(title)}">
 <meta name="twitter:image" content="{og_image}">
-</head><body><script>window.location.replace("{redirect_target}");</script></body></html>''')
-
+</head><body>{redirect_script}</body></html>''')
 @app.get("/")
 async def index():
     with open("/app/static/index.html","r",encoding="utf-8") as f:return HTMLResponse(content=f.read())
-
 app.mount("/static",StaticFiles(directory="/app/static"),name="static")