Skip to content

Scrapy, a fast high-level web crawling & scraping framework for Python.

Mark the new test as xfail for xmliter_lxml

Adrián Chavese90be0d8a5e3
diff --git a/tests/test_utils_iterators.py b/tests/test_utils_iterators.py
index bbdc88dd1..ae64e36cf 100644
--- a/tests/test_utils_iterators.py
+++ b/tests/test_utils_iterators.py
@@ -1,5 +1,6 @@
import os
+from pytest import mark
from twisted.trial import unittest
from scrapy.utils.iterators import csviter, xmliter, _body_or_str, xmliter_lxml
@@ -149,6 +150,26 @@ class XmliterTestCase(unittest.TestCase):
self.assertEqual(node.xpath('id/text()').getall(), [])
self.assertEqual(node.xpath('price/text()').getall(), [])
+ def test_xmliter_namespaced_nodename(self):
+ body = b"""
+ <?xml version="1.0" encoding="UTF-8"?>
+ <rss version="2.0" xmlns:g="http://base.google.com/ns/1.0">
+ <channel>
+ <title>My Dummy Company</title>
+ <link>http://www.mydummycompany.com</link>
+ <description>This is a dummy company. We do nothing.</description>
+ <item>
+ <title>Item 1</title>
+ <description>This is item 1</description>
+ <link>http://www.mydummycompany.com/items/1</link>
+ <g:image_link>http://www.mydummycompany.com/images/item1.jpg</g:image_link>
+ <g:id>ITEM_1</g:id>
+ <g:price>400</g:price>
+ </item>
+ </channel>
+ </rss>
+ """
+ response = XmlResponse(url='http://mydummycompany.com', body=body)
my_iter = self.xmliter(response, 'g:image_link')
node = next(my_iter)
node.register_namespace('g', 'http://base.google.com/ns/1.0')
@@ -187,6 +208,10 @@ class XmliterTestCase(unittest.TestCase):
class LxmlXmliterTestCase(XmliterTestCase):
xmliter = staticmethod(xmliter_lxml)
+ @mark.xfail(reason='known bug of the current implementation')
+ def test_xmliter_namespaced_nodename(self):
+ super().test_xmliter_namespaced_nodename()
+
def test_xmliter_iterate_namespace(self):
body = b"""
<?xml version="1.0" encoding="UTF-8"?>