From 9cbcf7724df7de9a449659fbf68bc5d532c33499 Mon Sep 17 00:00:00 2001
From: Samuel Bartlett <sam.bartlett858@gmail.com>
Date: Fri, 31 Mar 2023 08:07:43 +0000
Subject: [PATCH] Add test to make sure spider doesn't crash on bad

---
 tests/test_linkextractors.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tests/test_linkextractors.py b/tests/test_linkextractors.py
index f663013ba..d992a5eae 100644
--- a/tests/test_linkextractors.py
+++ b/tests/test_linkextractors.py
@@ -815,3 +815,26 @@ class LxmlLinkExtractorTestCase(Base.LinkExtractorTestCase):
 
     def test_restrict_xpaths_with_html_entities(self):
         super().test_restrict_xpaths_with_html_entities()
+
+    def test_skip_bad_links(self):
+        html = b"""
+        <a href="http://example.org/ignore_links : http://example.com/like_this">Why would you do this?</a>
+        <a href="http://example.org/item2.html">Good Link</a>
+        <a href="http://example.org/item3.html">Good Link 2</a>
+        """
+        response = HtmlResponse("http://example.org/index.html", body=html)
+        self.assertEqual(
+            [link for link in lx.extract_links(response)],
+            [
+                Link(
+                    url="http://example.org/item2.html",
+                    text="Good Link",
+                    nofollow=False,
+                ),
+                Link(
+                    url="http://example.org/item3.html",
+                    text="Good Link 2",
+                    nofollow=False,
+                ),
+            ],
+        )