update website

src/crawl/huggingface_daily.py

@@ -18,10 +18,10 @@ class HuggingFaceDailyPapers:
         """Extract arXiv ID from a URL"""
         if not url:
             return None
-        # Matches /abs/2508.05629, /pdf/2508.05629.pdf
-        m = re.search(r"arxiv\.org/(abs|pdf)/([0-9]{4}\.\d{4,5})(?:\.pdf)?", url)
+        # matches https://huggingface.co/papers/2508.10711
+        m = re.search(r"huggingface\.co/papers/(\d{4,5}\.\d+)(v\d+)?", url)
         if m:
-            return m.group(2)
+            return m.group(1)
         return None
 
     def extract_json_data(self, html: str) -> Dict[str, Any]: