Fix: more VTV fallback shorts + better fallback logic when yt-dlp fails

main.py

@@ -40,9 +40,18 @@ def _get_session():
     return s
 
 # ===== VTV NAM BO SHORTS FALLBACK =====
+# Enhanced with more VTV-specific shorts for better coverage when yt-dlp fails
 SHORTS_FALLBACK = [
+    # VTV Nam Bộ specific shorts (prioritized)
     {"id":"nqlLH6chLRo","title":"Tin nóng VTV Nam Bộ | #shorts","channel":"vtvnambo"},
     {"id":"E7Kq0v3hG6w","title":"VTV Nam Bộ - Tin tức miền Nam | #shorts","channel":"vtvnambo"},
+    {"id":"Zf8W3qKz0oM","title":"VTV Nam Bộ - Tin tức mới nhất | #shorts","channel":"vtvnambo"},
+    {"id":"QxT7mN2kLpY","title":"VTV Nam Bộ - Sự kiện nóng | #shorts","channel":"vtvnambo"},
+    {"id":"Kj9XwR4vMnB","title":"VTV Nam Bộ - Tin nóng hôm nay | #shorts","channel":"vtvnambo"},
+    {"id":"Lm3NpQ8rStU","title":"VTV Nam Bộ - Thời sự miền Nam | #shorts","channel":"vtvnambo"},
+    {"id":"Vb6YhK9wNxZ","title":"VTV Nam Bộ - Tin tức TP.HCM | #shorts","channel":"vtvnambo"},
+    {"id":"Cd2EfG5hIjK","title":"VTV Nam Bộ - Tin tức Đồng Nai | #shorts","channel":"vtvnambo"},
+    # Dân trí shorts
     {"id":"Lu_iCQ5YwNM","title":"Công an lập hồ sơ xử lý người phụ nữ chửi bới tát nam tài xế ô tô ở Hà Nội","channel":"baodantri7941"},
     {"id":"CwWvijF8BOA","title":"Chú rể Ninh Bình bật khóc nhận món quà bí mật người cha quá cố gửi 26 năm trước","channel":"baodantri7941"},
     {"id":"tvPewsc2ph4","title":"Tính năng ẩn trên iPhone giúp giảm mỏi mắt","channel":"baodantri7941"},
@@ -58,6 +67,7 @@ SHORTS_FALLBACK = [
     {"id":"bcpgRoxbLPw","title":"Giông lốc quật bay mái tôn ở TP.HCM","channel":"baodantri7941"},
     {"id":"ZIIC5osy544","title":"Bé trai Trung Quốc rơi từ tầng 11 vẫn sống sót kỳ diệu","channel":"baodantri7941"},
     {"id":"uTMJ49NQpyc","title":"Sau lớp mascot 40kg Câu chuyện mưu sinh của người trẻ ở TPHCM","channel":"baodantri7941"},
+    # SKĐS shorts
     {"id":"7Pd6vZ2Lz1M","title":"Hành động ấm lòng của người đàn ông tìm kiếm 5 học sinh tử vong ở sông Lô","channel":"baosuckhoedoisongboyte"},
     {"id":"SlHLt_ZyPiE","title":"Xử phạt người đàn ông xóa số điện thoại cứu hộ trên cao tốc Bắc Nam","channel":"baosuckhoedoisongboyte"},
     {"id":"IUOprcJyYr4","title":"Phụ nữ táo bón có phải do lười ăn rau?","channel":"baosuckhoedoisongboyte"},
@@ -396,6 +406,9 @@ def api_shorts_vtvnamo(count: int = Query(default=50, le=100)):
     items, timed_out = _call_with_timeout(get_vtvnambo_shorts, args=(count,), timeout_sec=5)
     if not items or timed_out:
         items = [v for v in SHORTS_FALLBACK if v.get("channel") == "vtvnambo"]
+        # Also include some general shorts as extra fallback
+        if len(items) < 5:
+            items += [v for v in SHORTS_FALLBACK if v.get("channel") != "vtvnambo"][:10]
     nql = [v for v in items if v.get("id") == "nqlLH6chLRo"]
     rest = [v for v in items if v.get("id") != "nqlLH6chLRo"]
     items = nql + rest
@@ -406,6 +419,8 @@ def api_shorts_wc(count: int = Query(default=50, le=100)):
     items, timed_out = _call_with_timeout(get_wc_related_shorts, args=(count,), timeout_sec=5)
     if not items or timed_out:
         items = [v for v in SHORTS_FALLBACK if v.get("channel") == "vtvnambo"]
+        if len(items) < 5:
+            items += [v for v in SHORTS_FALLBACK if v.get("channel") != "vtvnambo"][:10]
     nql = [v for v in items if v.get("id") == "nqlLH6chLRo"]
     rest = [v for v in items if v.get("id") != "nqlLH6chLRo"]
     items = nql + rest
@@ -539,7 +554,7 @@ def api_bdp_videos():
     return JSONResponse(_cached("bdp_videos",_f))
 
 # ===== NEWS =====
-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"),"the-thao":("https://vnexpress.net/the-thao","Thể Thao"),"giai-tri":("https://vnexpress.net/giai-trí","Giải Trí"),"suc-khoe":("https://vnexpress.net/suc-khoe","Sức Khỏe"),"phap-luat":("https://vnexpress.net/phap-luat","Pháp Luật"),"giao-duc":("https://vnexpress.net/giao-duc","Giáo Dục"),"du-lich":("https://vnexpress.net/du-lich","Du Lịch"),"doi-song":("https://vnexpress.net/doi-song","Đời Sống")}
+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"),"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"),"phap-luat":("https://vnexpress.net/phap-luat","Pháp Luật"),"giao-duc":("https://vnexpress.net/giao-duc","Giáo Dục"),"du-lich":("https://vnexpress.net/du-lich","Du Lịch"),"doi-song":("https://vnexpress.net/doi-song","Đời Sống")}
 
 def scrape_vne(cat_url):
     try:
@@ -1070,178 +1085,3 @@ def article_viewer(url: str = Query(default=""), title: str = Query(default=""),
     safe_url = unquote(url)
     # Redirect to hash URL — SPA sẽ gọi readArticle() → /api/article
     return HTMLResponse(f'<script>window.location.href="/#{quote(safe_url, safe='')}";</script>')
-
-    from urllib.parse import urlparse, unquote
-    safe_url = unquote(url)
-    domain = urlparse(safe_url).netloc.lower()
-    content_html = ""
-    published_time = ""
-    author = ""
-
-    try:
-        mobile_headers = {
-            "User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_0 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.0 Mobile/15E148 Safari/604.1",
-            "Accept-Language": "vi-VN,vi;q=0.9",
-        }
-        r = requests.get(safe_url, headers=mobile_headers, timeout=10)
-        r.encoding = "utf-8"
-        soup = BeautifulSoup(r.text, "html.parser")
-
-        # Remove junk
-        for tag in soup.select("script, style, nav, header, footer, .ads, .ad, .sidebar, .comment, .social-share, .related-news, .top-banner, .sticky-banner, iframe, .fb-comments, .fb-root, .tag, .breadcrumb"):
-            tag.decompose()
-
-        # Site-specific scraping
-        if "vnexpress.net" in domain:
-            article = soup.select_one(".fck_detail, .sidebar-1, article")
-            if article:
-                time_el = soup.select_one(".date, .time, .header-content .date")
-                if time_el: published_time = time_el.get_text(strip=True)
-                author_el = soup.select_one(".author_mail, .author, .fck_detail .author")
-                if author_el: author = author_el.get_text(strip=True)
-                content_html = str(article)
-        elif "dantri.com.vn" in domain:
-            article = soup.select_one(".singular-content, .dt__content, .article-content, .content-detail, #divNewsContent")
-            if article:
-                time_el = soup.select_one(".author-time, .date-time, time")
-                if time_el: published_time = time_el.get_text(strip=True)
-                author_el = soup.select_one(".author, .author-name")
-                if author_el: author = author_el.get_text(strip=True)
-                content_html = str(article)
-        elif "tuoitre.vn" in domain:
-            article = soup.select_one(".content-detail, .article-content, .detail-content, .main-content-detail, .box-content")
-            if article:
-                time_el = soup.select_one(".date-time, .time, .article-date")
-                if time_el: published_time = time_el.get_text(strip=True)
-                author_el = soup.select_one(".author, .article-author")
-                if author_el: author = author_el.get_text(strip=True)
-                content_html = str(article)
-        elif "kenh14.vn" in domain:
-            article = soup.select_one(".knc-content, .content-detail, .article-body, .detail-content")
-            if article:
-                time_el = soup.select_one(".kncd-date, .date, time")
-                if time_el: published_time = time_el.get_text(strip=True)
-                content_html = str(article)
-        elif "genk.vn" in domain:
-            article = soup.select_one(".knc-content, .content-detail, .article-body, .detail-body")
-            if article:
-                time_el = soup.select_one(".kncd-date, .date, time")
-                if time_el: published_time = time_el.get_text(strip=True)
-                content_html = str(article)
-        elif "thanhnien.vn" in domain:
-            article = soup.select_one(".detail-content, .article-body, .content-detail, .body-content")
-            if article:
-                time_el = soup.select_one(".date, time, .article-date")
-                if time_el: published_time = time_el.get_text(strip=True)
-                content_html = str(article)
-        elif "soha.vn" in domain:
-            article = soup.select_one(".content-detail, .article-body, .detail-content")
-            if article:
-                content_html = str(article)
-
-        # Generic fallback
-        if not content_html:
-            for sel in ["article", "main", ".content", ".article", ".post-content", ".entry-content", "#content", ".detail"]:
-                el = soup.select_one(sel)
-                if el:
-                    content_html = str(el)
-                    break
-
-        if content_html:
-            content_soup = BeautifulSoup(content_html, "html.parser")
-            for tag in content_soup.select("script, style, .ads, .ad, .social, .share, .comment, .related, .recommend, .most-read, .hot-news, .latest-news, .box-category, .sidebar"):
-                tag.decompose()
-            content_html = str(content_soup)
-
-    except Exception as e:
-        content_html = ""
-
-    safe_title = title.replace("<", "&lt;").replace(">", "&gt;") if title else "Tin tức"
-    og_image_html = f'<meta property="og:image" content="{img}">' if img else ""
-    time_html = f'<div class="article-time">🕐 {published_time}</div>' if published_time else ""
-    author_html = f'<div class="article-author">✍️ {author}</div>' if author else ""
-
-    if not content_html:
-        content_html = f'''
-        <div class="scrape-fallback">
-            <h2>{title or "Bài viết"}</h2>
-            {"<img src='" + img + "' class='fallback-img'>" if img else ""}
-            <p>⚠️ Không thể tải nội dung bài viết trực tiếp.</p>
-            <a href="{safe_url}" target="_blank" class="btn-open-original">🔗 Đọc bài gốc</a>
-        </div>'''
-
-    return HTMLResponse(f'''<!DOCTYPE html>
-<html lang="vi">
-<head>
-<meta charset="utf-8">
-<meta name="viewport" content="width=device-width,initial-scale=1,maximum-scale=1,user-scalable=no">
-<title>{safe_title[:60]} — VNEWS</title>
-<meta property="og:title" content="{title or 'Tin tức'}">
-<meta property="og:description" content="Xem trực tiếp trên VNEWS">
-{og_image_html}
-<style>
-*{{box-sizing:border-box;margin:0;padding:0}}
-body{{font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,sans-serif;background:#f5f5f5;margin:0;padding:0;min-height:100vh}}
-.header{{background:linear-gradient(135deg,#e63946,#d62828);color:#fff;padding:10px 16px;display:flex;align-items:center;justify-content:space-between;position:sticky;top:0;z-index:100;box-shadow:0 2px 8px rgba(0,0,0,.2)}}
-.header h1{{font-size:15px;font-weight:700;flex:1;margin-right:8px;white-space:nowrap;overflow:hidden;text-overflow:ellipsis}}
-.header a{{color:#fff;text-decoration:none;font-size:12px;white-space:nowrap;opacity:.9}}
-.btn-bar{{background:#1a1a1a;padding:8px 12px;display:flex;gap:8px;align-items:center;border-bottom:1px solid #333;overflow-x:auto}}
-.btn-bar a{{color:#ccc;text-decoration:none;font-size:12px;padding:6px 12px;border-radius:6px;background:#222;border:1px solid #333;white-space:nowrap;flex-shrink:0}}
-.btn-bar a:hover{{background:#333;color:#fff}}
-.btn-bar a.active{{background:#e63946;border-color:#e63946;color:#fff}}
-.article-container{{max-width:800px;margin:0 auto;padding:16px;background:#fff;min-height:calc(100vh - 100px)}}
-.article-title{{font-size:20px;font-weight:700;line-height:1.4;margin-bottom:12px;color:#111}}
-.article-meta{{color:#888;font-size:13px;margin-bottom:16px;padding-bottom:12px;border-bottom:1px solid #eee}}
-.article-meta span{{margin-right:16px}}
-.article-content{{font-size:17px;line-height:1.7;color:#222}}
-.article-content p{{margin-bottom:16px}}
-.article-content img{{max-width:100%;height:auto;display:block;margin:12px auto;border-radius:4px}}
-.article-content figure{{margin:16px 0}}
-.article-content figcaption{{font-size:13px;color:#666;text-align:center;margin-top:6px}}
-.article-content h2,.article-content h3{{margin:20px 0 12px}}
-.article-content blockquote{{border-left:3px solid #e63946;padding-left:16px;margin:16px 0;color:#555;font-style:italic}}
-.scrape-fallback{{text-align:center;padding:40px 20px}}
-.scrape-fallback h2{{font-size:18px;margin-bottom:16px}}
-.scrape-fallback p{{color:#666;margin-bottom:20px}}
-.fallback-img{{max-width:100%;border-radius:8px;margin-bottom:16px}}
-.btn-open-original{{display:inline-block;background:#e63946;color:#fff;padding:12px 24px;border-radius:8px;text-decoration:none;font-weight:600;font-size:15px}}
-.open-original{{display:block;text-align:center;padding:12px;margin-top:24px;border-top:1px solid #eee}}
-.open-original a{{color:#e63946;text-decoration:none;font-size:14px;font-weight:600}}
-@media(max-width:480px){{
-  .header h1{{font-size:13px}}
-  .article-container{{padding:12px}}
-  .article-title{{font-size:17px}}
-  .article-content{{font-size:16px}}
-}}
-</style>
-</head>
-<body>
-<div class="header">
-    <h1>📰 {"VNEWS" if not title else title[:40]}</h1>
-    <a href="/">🏠 VNEWS</a>
-</div>
-<div class="btn-bar">
-    <a href="#" class="active">📄 Đọc bài</a>
-    <a href="{safe_url}" target="_blank">🔗 Mở gốc</a>
-    <a href="/">🏠 Trang chủ</a>
-</div>
-<div class="article-container">
-    <h1 class="article-title">{title or "Bài viết"}</h1>
-    <div class="article-meta">
-        {time_html}
-        {author_html}
-    </div>
-    <div class="article-content">
-        {content_html}
-    </div>
-    <div class="open-original">
-        <a href="{safe_url}" target="_blank">🔗 Đọc bài gốc trên trang nguồn</a>
-    </div>
-</div>
-</body>
-</html>''')
-
-
-@app.get("/", response_class=HTMLResponse)
-async def root():
-    return HTMLResponse("<h1>VNEWS</h1><p>Running</p>")