improved url source detection heuristic

emcf · Apr 16, 2024 · 11099c0 · 11099c0
1 parent 754143a
commit 11099c0
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/thepipe_api/extractor.py b/thepipe_api/extractor.py
@@ -89,7 +89,7 @@ def extract_from_file(file_path: str, source_type: str, verbose: bool = False, a
 def detect_type(source: str) -> Optional[SourceTypes]:
     if source.startswith("https://github.com"):
         return SourceTypes.GITHUB
-    elif source.startswith("http") or source.startswith("www.") or source.startswith("ftp."):
+    elif source.startswith("http") or source.startswith("ftp."):
         return SourceTypes.URL
     elif source.endswith(".zip"):
         return SourceTypes.ZIP