Update helpers.py

helpers.py

@@ -34,21 +34,25 @@ from tqdm.asyncio import tqdm
 async def _fetch_urls(base_url):
     """Extract all links from a JavaScript-rendered webpage."""
     async with async_playwright() as p:
-        browser = await p.chromium.launch(headless=True)
-        page = await browser.new_page()
-        await page.goto(base_url)
-        await page.wait_for_load_state("networkidle")
-
-        urls = set()
-        links = await page.locator("a").all()
-        for link in links:
-            href = await link.get_attribute("href")
-            if href and "#" not in href:
-                full_url = urljoin(base_url, href)
-                if full_url.startswith(base_url):
-                    urls.add(full_url)
-
-        await browser.close()
+        try:
+            browser = await p.chromium.launch(headless=True)
+            page = await browser.new_page()
+            await page.goto(base_url)
+            await page.wait_for_load_state("networkidle")
+    
+            urls = set()
+            links = await page.locator("a").all()
+            for link in links:
+                href = await link.get_attribute("href")
+                if href and "#" not in href:
+                    full_url = urljoin(base_url, href)
+                    if full_url.startswith(base_url):
+                        urls.add(full_url)
+    
+            await browser.close()
+        except Exception as e:
+            print(f"⚠️ Không thể truy cập {base_url}: {e}")
+        return []  # Trả về danh sách rỗng nếu gặp lỗi
     return list(urls)
 
 async def _fetch_web_content(urls):