feat: add 24h news shorts scraper module

shorts_scraper.py

@@ -0,0 +1,51 @@
+"""24h.com.vn News Shorts scraper for video-tin-tuc page."""
+import requests
+from bs4 import BeautifulSoup
+
+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",
+}
+BASE_24H = "https://www.24h.com.vn"
+
+def scrape_24h_news_shorts():
+    """Scrape 24h.com.vn video tin tuc (shorts/news clips) page.
+    Returns list of dicts with title, link, img, source='24h', is_video=True."""
+    try:
+        url = f"{BASE_24H}/video/video-tin-tuc-cvd769.html"
+        r = requests.get(url, headers=HEADERS, timeout=15); r.encoding = "utf-8"
+        soup = BeautifulSoup(r.text, "lxml")
+        articles, seen = [], set()
+        for art in soup.find_all("article"):
+            a = art.find("a", href=True)
+            if not a:
+                continue
+            href = a.get("href", "")
+            if not href.startswith("http"):
+                href = BASE_24H + href
+            if href in seen:
+                continue
+            img_tag = art.find("img")
+            title = ""
+            if img_tag:
+                title = img_tag.get("alt", "")
+            if not title:
+                title = a.get("title", "") or a.get_text(strip=True)
+            if not title or len(title) < 10:
+                continue
+            img_src = None
+            if img_tag:
+                for attr in ["data-original", "data-src", "src"]:
+                    v = img_tag.get(attr, "")
+                    if v and "base64" not in v and len(v) > 20:
+                        img_src = v
+                        break
+            seen.add(href)
+            articles.append({
+                "title": title, "link": href, "img": img_src,
+                "summary": "", "time": "", "featured": False,
+                "source": "24h", "group": "Shorts", "is_video": True
+            })
+        return articles[:20]
+    except:
+        return []