Upload app.py

app.py

@@ -0,0 +1,279 @@
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+from datetime import datetime
+import time
+
+# ── Constants ──────────────────────────────────────────────────────────────────
+HEADERS = {
+    "User-Agent": (
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+        "AppleWebKit/537.36 (KHTML, like Gecko) "
+        "Chrome/120.0.0.0 Safari/537.36"
+    ),
+    "Accept-Language": "vi-VN,vi;q=0.9,en;q=0.8",
+}
+
+CATEGORIES = {
+    "🏠 Tin Mới Nhất": "https://bongdaplus.vn/tin-moi",
+    "🏴󠁧󠁢󠁥󠁮󠁧󠁿 Ngoại Hạng Anh": "https://bongdaplus.vn/ngoai-hang-anh",
+    "🇪🇸 La Liga": "https://bongdaplus.vn/la-liga",
+    "🇮🇹 Serie A": "https://bongdaplus.vn/serie-a",
+    "🇩🇪 Bundesliga": "https://bongdaplus.vn/bundesliga",
+    "🇫🇷 Ligue 1": "https://bongdaplus.vn/ligue-1",
+    "🏆 Champions League": "https://bongdaplus.vn/champions-league-cup-c1",
+    "🏆 Europa League": "https://bongdaplus.vn/europa-league",
+    "🇻🇳 Bóng Đá Việt Nam": "https://bongdaplus.vn/bong-da-viet-nam",
+    "🇻🇳 V-League": "https://bongdaplus.vn/v-league",
+    "⚽ Chuyển Nhượng": "https://bongdaplus.vn/tin-chuyen-nhuong",
+    "🌍 Bóng Đá Thế Giới": "https://bongdaplus.vn/bong-da-the-gioi",
+}
+
+BASE_URL = "https://bongdaplus.vn"
+REFRESH_SECONDS = 300  # 5 minutes
+
+
+# ── Scraper ────────────────────────────────────────────────────────────────────
+def scrape_news(url: str) -> list[dict]:
+    """Scrape news articles from bongdaplus.vn pages."""
+    try:
+        r = requests.get(url, headers=HEADERS, timeout=15)
+        r.encoding = "utf-8"
+        soup = BeautifulSoup(r.text, "lxml")
+        articles = []
+        seen_links = set()
+
+        # ─── Strategy 1: Featured news (div.news.fst) ───
+        for item in soup.select("div.news.fst"):
+            art = _parse_news_item(item)
+            if art and art["link"] not in seen_links:
+                art["featured"] = True
+                articles.append(art)
+                seen_links.add(art["link"])
+
+        # ─── Strategy 2: Slider items (div.sld-itm.news) ───
+        for item in soup.select("div.sld-itm.news"):
+            art = _parse_news_item(item)
+            if art and art["link"] not in seen_links:
+                art["featured"] = True
+                articles.append(art)
+                seen_links.add(art["link"])
+
+        # ─── Strategy 3: List items (li.news) — the main content ───
+        for item in soup.select("li.news"):
+            art = _parse_news_item(item)
+            if art and art["link"] not in seen_links:
+                art["featured"] = False
+                articles.append(art)
+                seen_links.add(art["link"])
+
+        return articles
+
+    except Exception as e:
+        return [{"title": f"⚠️ Lỗi tải tin: {e}", "link": "#", "img": None,
+                 "summary": "", "time": "", "featured": False}]
+
+
+def _parse_news_item(item) -> dict | None:
+    """Extract title, link, image, summary, time from a news item element."""
+    # Title
+    title_tag = item.find("a", class_="title")
+    if not title_tag:
+        title_tag = item.find("a", href=True)
+    if not title_tag:
+        return None
+
+    title = title_tag.get_text(strip=True)
+    if not title or len(title) < 5:
+        return None
+
+    # Link
+    link = title_tag.get("href", "")
+    if link and not link.startswith("http"):
+        link = BASE_URL + link
+
+    # Image
+    img_tag = item.find("img")
+    img = None
+    if img_tag:
+        img = img_tag.get("data-src") or img_tag.get("src")
+
+    # Summary
+    summ_tag = item.find("p", class_="summ")
+    summary = summ_tag.get_text(strip=True) if summ_tag else ""
+
+    # Time
+    time_tag = item.find("div", class_="in-time")
+    time_text = time_tag.get_text(strip=True) if time_tag else ""
+
+    return {
+        "title": title,
+        "link": link,
+        "img": img,
+        "summary": summary,
+        "time": time_text,
+        "featured": False,
+    }
+
+
+# ── HTML Renderer ──────────────────────────────────────────────────────────────
+def render_html(articles: list[dict]) -> str:
+    """Render articles as HTML cards."""
+    if not articles:
+        return "<p style='text-align:center;color:#888;padding:40px;'>Không tìm thấy tin tức.</p>"
+
+    now = datetime.now().strftime("%H:%M:%S %d/%m/%Y")
+
+    # Featured articles (big cards)
+    featured = [a for a in articles if a.get("featured")]
+    regular = [a for a in articles if not a.get("featured")]
+
+    html_parts = []
+
+    # Header
+    html_parts.append(f"""
+    <div style="font-family:'Segoe UI',Tahoma,Geneva,Verdana,sans-serif;max-width:1200px;margin:0 auto;">
+        <div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:16px;">
+            <span style="color:#666;font-size:12px;">⏱ Cập nhật lúc: {now}</span>
+            <span style="color:#666;font-size:12px;">📰 {len(articles)} tin</span>
+        </div>
+    """)
+
+    # Featured section
+    if featured:
+        html_parts.append('<div style="margin-bottom:24px;">')
+        html_parts.append('<div style="display:grid;grid-template-columns:repeat(auto-fill,minmax(320px,1fr));gap:16px;">')
+        for art in featured[:6]:
+            html_parts.append(_card_html(art, big=True))
+        html_parts.append('</div></div>')
+
+    # Regular news
+    if regular:
+        html_parts.append('<div style="display:grid;grid-template-columns:repeat(auto-fill,minmax(280px,1fr));gap:14px;">')
+        for art in regular[:30]:
+            html_parts.append(_card_html(art, big=False))
+        html_parts.append('</div>')
+
+    html_parts.append('</div>')
+    return '\n'.join(html_parts)
+
+
+def _card_html(art: dict, big: bool = False) -> str:
+    """Render a single article card."""
+    img_height = "200px" if big else "160px"
+    title_size = "16px" if big else "14px"
+
+    img_html = ""
+    if art.get("img"):
+        img_html = f"""
+        <div style="width:100%;height:{img_height};overflow:hidden;background:#f0f0f0;">
+            <img src="{art['img']}" alt=""
+                 style="width:100%;height:100%;object-fit:cover;transition:transform 0.3s;"
+                 onerror="this.style.display='none'">
+        </div>"""
+
+    time_html = ""
+    if art.get("time"):
+        time_html = f'<span style="color:#999;font-size:11px;">🕐 {art["time"]}</span>'
+
+    summ_html = ""
+    if art.get("summary"):
+        summ_html = f'<p style="font-size:12px;color:#666;margin:6px 0 0 0;line-height:1.4;">{art["summary"][:150]}{"..." if len(art["summary"]) > 150 else ""}</p>'
+
+    return f"""
+    <div style="border:1px solid #e8e8e8;border-radius:10px;overflow:hidden;
+                background:#fff;box-shadow:0 2px 8px rgba(0,0,0,0.06);
+                transition:box-shadow 0.2s,transform 0.2s;"
+         onmouseover="this.style.boxShadow='0 4px 16px rgba(0,0,0,0.12)';this.style.transform='translateY(-2px)'"
+         onmouseout="this.style.boxShadow='0 2px 8px rgba(0,0,0,0.06)';this.style.transform='translateY(0)'">
+        <a href="{art['link']}" target="_blank" rel="noopener"
+           style="text-decoration:none;color:inherit;display:block;">
+            {img_html}
+            <div style="padding:12px 14px;">
+                <h3 style="font-size:{title_size};font-weight:600;color:#1a1a1a;
+                           margin:0;line-height:1.45;">
+                    {art['title']}
+                </h3>
+                {summ_html}
+                <div style="margin-top:8px;">{time_html}</div>
+            </div>
+        </a>
+    </div>"""
+
+
+# ── Main fetch function ───────────────────────────────────────────────────────
+def fetch_news(category: str) -> str:
+    """Fetch and render news for a given category."""
+    url = CATEGORIES.get(category, CATEGORIES["🏠 Tin Mới Nhất"])
+    articles = scrape_news(url)
+    return render_html(articles)
+
+
+# ── Gradio App ─────────────────────────────────────────────────────────────────
+CUSTOM_CSS = """
+.gradio-container {
+    max-width: 1280px !important;
+    background: #fafafa !important;
+}
+.header-banner {
+    background: linear-gradient(135deg, #1a472a 0%, #2d8659 50%, #d4af37 100%);
+    padding: 24px 32px;
+    border-radius: 12px;
+    margin-bottom: 16px;
+    text-align: center;
+}
+.header-banner h1 {
+    color: #fff !important;
+    font-size: 28px !important;
+    margin: 0 !important;
+    text-shadow: 0 2px 4px rgba(0,0,0,0.2);
+}
+.header-banner p {
+    color: rgba(255,255,255,0.85) !important;
+    font-size: 14px !important;
+    margin: 4px 0 0 0 !important;
+}
+footer { display: none !important; }
+"""
+
+with gr.Blocks(
+    title="⚽ BongDaPlus - Tin Tức Bóng Đá",
+) as demo:
+
+    gr.HTML("""
+    <div class="header-banner">
+        <h1>⚽ BongDaPlus — Tin Tức Bóng Đá</h1>
+        <p>Tự động cập nhật tin tức từ bongdaplus.vn mỗi 5 phút</p>
+    </div>
+    """)
+
+    with gr.Row():
+        cat_dropdown = gr.Dropdown(
+            choices=list(CATEGORIES.keys()),
+            value="🏠 Tin Mới Nhất",
+            label="📂 Chuyên mục",
+            scale=4,
+            interactive=True,
+        )
+        refresh_btn = gr.Button(
+            "🔄 Làm mới",
+            variant="primary",
+            scale=1,
+        )
+
+    news_display = gr.HTML(label="Tin tức")
+
+    # Auto-refresh every 5 minutes
+    timer = gr.Timer(value=REFRESH_SECONDS, active=True)
+    timer.tick(fn=fetch_news, inputs=cat_dropdown, outputs=news_display)
+
+    # Manual interactions
+    refresh_btn.click(fn=fetch_news, inputs=cat_dropdown, outputs=news_display)
+    cat_dropdown.change(fn=fetch_news, inputs=cat_dropdown, outputs=news_display)
+
+    # Load on startup
+    demo.load(fn=fetch_news, inputs=cat_dropdown, outputs=news_display)
+
+
+if __name__ == "__main__":
+    demo.launch(css=CUSTOM_CSS, theme=gr.themes.Soft())