Merge pull request #229 from MrNeRF/arxiv-pdf

Parse arxiv PDF links
MrNeRF · Jan 3, 2025 · 08f8e6c · 08f8e6c
2 parents d2373e5 + c036c95
commit 08f8e6c
Showing 1 changed file with 4 additions and 1 deletion.
diff --git a/arxiv_integration.py b/arxiv_integration.py
@@ -26,8 +26,11 @@ def extract_arxiv_id(self, url_or_id: str) -> str:
 
         # Extract ID from path
         path = parsed.path
-        if 'abs' in path:
+        if 'abs' in path or 'pdf' in path:
             arxiv_id = path.split('/')[-1]
+            # Remove .pdf extension if present
+            if arxiv_id.endswith('.pdf'):
+                arxiv_id = arxiv_id[:-4]
         else:
             # If it's already an ID format (YYMM.NNNNN)
             arxiv_id = path.strip('/')