diff --git a/scrapy/contrib/linkextractors/sgml.py b/scrapy/contrib/linkextractors/sgml.py
index d8f6ae4ec..9a63fcd53 100644
--- a/scrapy/contrib/linkextractors/sgml.py
+++ b/scrapy/contrib/linkextractors/sgml.py
@@ -121,7 +121,7 @@ class SgmlLinkExtractor(BaseSgmlLinkExtractor):
body = u''.join(f
for x in self.restrict_xpaths
for f in sel.xpath(x).extract()
- ).encode(response.encoding)
+ ).encode(response.encoding, errors='xmlcharrefreplace')
else:
body = response.body
diff --git a/scrapy/tests/test_contrib_linkextractors.py b/scrapy/tests/test_contrib_linkextractors.py
index 4135b086c..19d122a89 100644
--- a/scrapy/tests/test_contrib_linkextractors.py
+++ b/scrapy/tests/test_contrib_linkextractors.py
@@ -236,6 +236,13 @@ class SgmlLinkExtractorTestCase(unittest.TestCase):
self.assertEqual(lx.extract_links(response),
[Link(url='http://example.org/about.html', text=u'About us\xa3')])
+ def test_restrict_xpaths_with_html_entities(self):
+ html = 'text
'
+ response = HtmlResponse("http://example.org/somepage/index.html", body=html, encoding='iso8859-15')
+ links = SgmlLinkExtractor(restrict_xpaths='//p').extract_links(response)
+ self.assertEqual(links,
+ [Link(url='http://example.org/%E2%99%A5/you?c=%E2%82%AC', text=u'text')])
+
def test_restrict_xpaths_concat_in_handle_data(self):
"""html entities cause SGMLParser to call handle_data hook twice"""
body = """