fix: shorts_carousel.py - filter only real article URLs (c{N}a{N} pattern)

shorts_carousel.py

@@ -1,18 +1,18 @@
-"""Self-contained 24h Shorts Carousel renderer.
-Import and call render_shorts_carousel_html(shorts_list) from app.py.
-"""
+"""Self-contained 24h Shorts Carousel - scrapes video-tin-tuc page for actual video articles."""
+import re
 import requests
 from bs4 import BeautifulSoup
 
 HEADERS = {
-    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+    "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",
 }
 BASE_24H = "https://www.24h.com.vn"
 
 
 def scrape_24h_news_shorts():
-    """Scrape https://www.24h.com.vn/video/video-tin-tuc-cvd769.html"""
+    """Scrape https://www.24h.com.vn/video/video-tin-tuc-cvd769.html
+    Returns only ACTUAL article links (pattern: -c{N}a{N}.html), not category pages."""
     try:
         url = f"{BASE_24H}/video/video-tin-tuc-cvd769.html"
         r = requests.get(url, headers=HEADERS, timeout=15)
@@ -21,26 +21,40 @@ def scrape_24h_news_shorts():
         articles, seen = [], set()
         for a in soup.find_all("a", href=True):
             href = a.get("href", "")
-            title = a.get("title", "") or a.get_text(strip=True)
-            if not title or len(title) < 10:
-                continue
-            if "javascript:" in href:
+            # Only match real article URLs: ends with -c{digits}a{digits}.html
+            if not re.search(r'-c\d+a\d+\.html$', href):
                 continue
             if not href.startswith("http"):
                 href = BASE_24H + href
             if href in seen:
                 continue
             seen.add(href)
+            # Get title
+            title = a.get("title", "") or ""
             img = a.find("img")
+            if img and not title:
+                title = img.get("alt", "")
+            if not title:
+                title = a.get_text(strip=True)
+            if not title or len(title) < 10:
+                continue
+            # Get image - priority: data-original > data-src > src
             img_src = None
             if img:
-                for attr in ["data-original", "data-src", "src"]:
-                    v = img.get(attr, "")
-                    if v and "base64" not in v and len(v) > 20:
-                        img_src = v
-                        break
+                img_src = img.get("data-original") or img.get("data-src") or img.get("src") or ""
+                if "base64" in img_src or len(img_src) < 20:
+                    img_src = None
+            # Try parent element for image if not found in link
+            if not img_src:
+                parent = a.parent
+                if parent:
+                    parent_img = parent.find("img")
+                    if parent_img:
+                        img_src = parent_img.get("data-original") or parent_img.get("data-src") or parent_img.get("src") or ""
+                        if "base64" in img_src or len(img_src) < 20:
+                            img_src = None
             if not img_src:
-                continue  # Skip items without image for the visual carousel
+                continue  # Skip items without thumbnail for visual carousel
             articles.append({
                 "title": title, "link": href, "img": img_src,
                 "source": "24h", "is_video": True
@@ -50,7 +64,7 @@ def scrape_24h_news_shorts():
         return []
 
 
-# CSS to be injected (add to your main CSS string)
+# CSS for the 9:16 shorts slider
 SHORTS_CSS = """
 /* Shorts 9:16 Slider */
 .vslide-shorts-item{flex:0 0 110px;scroll-snap-align:start;cursor:pointer;transition:transform .15s}