Merge pull request #144 from SkywaveTM/main

fix(fetch): properly handles robots.txt

src/fetch/src/mcp_server_fetch/server.py

@@ -74,7 +74,9 @@ async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
     async with AsyncClient() as client:
         try:
             response = await client.get(
-                robot_txt_url, headers={"User-Agent": user_agent}
+                robot_txt_url,
+                follow_redirects=True,
+                headers={"User-Agent": user_agent},
             )
         except HTTPError:
             raise McpError(
@@ -93,7 +95,7 @@ async def check_may_autonomously_fetch_url(url: str, user_agent: str) -> None:
         line for line in robot_txt.splitlines() if not line.strip().startswith("#")
     )
     robot_parser = Protego.parse(processed_robot_txt)
-    if not robot_parser.can_fetch(url, user_agent):
+    if not robot_parser.can_fetch(str(url), user_agent):
         raise McpError(
             INTERNAL_ERROR,
             f"The sites robots.txt ({robot_txt_url}), specifies that autonomous fetching of this page is not allowed, "