catch_response_codes

README.md

@@ -26,7 +26,7 @@ File: tests/test_md_files/fail.md:13 • Link: a.md#fail • Error: Not found fr
 ```
 
 > [!NOTE]
-> Only error codes like **404 (Not Found)**, **410 (Gone)**, and **500 (Internal Server Error)**,
+> Error codes like **404 (Not Found)**, **408 (Timeout)**, **410 (Gone)**, and **500 (Internal Server Error)**,
 > and links that don't exist are considered "dead links". Other error codes typically indicate
 > temporary issues with the host server or unsupported links for the HEAD request type.
 
@@ -90,9 +90,11 @@ This tool seamlessly integrates with your project's `pyproject.toml` file for co
 To leverage a different file, invoke the `--config` option during execution.
 
 - timeout: Specifies the maximum time (in seconds) to wait for web link responses. Default: `5` seconds.
-- exclude_links: Accepts a list of links to exclude from checks. Default: `[]`.
-- exclude_files: Accepts a list of files to exclude from checks. Default: `[]`.
-- force_get_requests_for_links: Accepts a list of links for which the tool will use `GET` requests during checks. Default: `[]`.
+- catch_response_codes: List of HTTP response codes to consider as failures.
+If empty, all codes greater than 400 will be marked as failures. Default: `[404, 410, 500]`.
+- exclude_links: List of links to exclude from checks. Default: `[]`.
+- exclude_files: List of files to exclude from checks. Default: `[]`.
+- force_get_requests_for_links: List of links for which the tool will use `GET` requests during checks. Default: `[]`.
 - check_web_links: Toggle web link checks on or off. Default: `true`.
 - validate_ssl: Toggles whether to validate SSL certificates when checking web links. Default: `true`.
 

md_dead_link_check/config.py

@@ -7,10 +7,17 @@
 
 PROJECT_NAME = "md_dead_link_check"
 
+DEFAULT_CATCH_RESPONSE_CODES = [
+    404,  # Not found
+    410,  # Gone
+    500,  # Internal Server Error (for cannot connect to host under proxy)
+]
+
 
 @dataclass
 class Config:
     timeout: int = 5
+    catch_response_codes: List[int] = field(default_factory=lambda: DEFAULT_CATCH_RESPONSE_CODES)
     exclude_links: List[str] = field(default_factory=lambda: [])
     exclude_files: List[str] = field(default_factory=lambda: [])
     force_get_requests_for_links: List[str] = field(default_factory=lambda: [])

md_dead_link_check/link_checker.py

@@ -15,11 +15,7 @@
 from md_dead_link_check.preprocess import LinkInfo
 from md_dead_link_check.preprocess import MarkdownInfo
 
-CATCH_RESPONSE_STATUS = [
-    404,  # Not found
-    410,  # Gone
-    500,  # Internal Server Error (for cannot connect to host under proxy)
-]
+TIMEOUT_RESPONSE_CODE = 408
 
 
 @dataclass
@@ -53,15 +49,17 @@ async def process_link(link_info: LinkInfo, session: ClientSession, config: Conf
 
         response.raise_for_status()
     except ClientResponseError as e:
-        if e.status in CATCH_RESPONSE_STATUS:
+        if not config.catch_response_codes or e.status in config.catch_response_codes:
             return StatusInfo(link_info, f"{e.status}: {e.message}")
         return StatusInfo(link_info, warn_msg=f"{e.status}: {e.message}")
     except asyncio.CancelledError as e:
         return StatusInfo(link_info, str(e))
     except ClientConnectorError as e:
         return StatusInfo(link_info, str(e))
     except asyncio.TimeoutError:
-        return StatusInfo(link_info, warn_msg="TimeoutError")
+        if TIMEOUT_RESPONSE_CODE in config.catch_response_codes:
+            return StatusInfo(link_info, err_msg="408: Timeout")
+        return StatusInfo(link_info, warn_msg="408: Timeout")
 
     return StatusInfo(link_info)