From 56947296b57ae8114355ae20d546e153af201306 Mon Sep 17 00:00:00 2001
From: Peter Vacho <p_vacho@utb.cz>
Date: Sun, 24 Nov 2024 22:09:52 +0100
Subject: [PATCH] Handle parsing errors

---
 src/link_scraper.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/link_scraper.py b/src/link_scraper.py
index e6a8fb6..5b189b1 100644
--- a/src/link_scraper.py
+++ b/src/link_scraper.py
@@ -4,6 +4,7 @@ from urllib.parse import urljoin
 
 import httpx
 from bs4 import BeautifulSoup
+from bs4.builder import ParserRejectedMarkup
 from rich.console import Console
 from rich.style import StyleType
 from rich.text import Text
@@ -66,6 +67,9 @@ def standard_urlmap_exception_suppressor(exc: Exception, url: httpx.URL) -> bool
         print_exc("Got ", (exc.__class__.__qualname__, "red"), ", (", (str(exc), "orange"), ")")
         return True
 
+    if isinstance(exc, ParserRejectedMarkup):
+        print_exc("Parsing failure: ", ("Invalid HTML", "red"))
+
     return False