From 90ce6589eee58e8aca9c368a71907b30250df68d Mon Sep 17 00:00:00 2001
From: Samuel Bartlett <sam.bartlett858@gmail.com>
Date: Thu, 30 Mar 2023 13:07:51 +0000
Subject: [PATCH] Add try/except to safe_url_string()

Added a try catch condition to the safe_url_string() processing
in the LxmlParserLinkExtractor class to avoid scrapers crashing
unneccessarily
---
 scrapy/linkextractors/lxmlhtml.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/scrapy/linkextractors/lxmlhtml.py b/scrapy/linkextractors/lxmlhtml.py
index dd8dcdf7c..1ee81427c 100644
--- a/scrapy/linkextractors/lxmlhtml.py
+++ b/scrapy/linkextractors/lxmlhtml.py
@@ -88,7 +88,11 @@ class LxmlParserLinkExtractor:
                 url = self.process_attr(attr_val)
                 if url is None:
                     continue
-            url = safe_url_string(url, encoding=response_encoding)
+            try:
+                url = safe_url_string(url, encoding=response_encoding)
+            except ValueError:
+                continue  # Disregard badly formatted urls
+
             # to fix relative links after process_value
             url = urljoin(response_url, url)
             link = Link(