Skip to content

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

Add a test to cover searching for a missing node name

Adrián Chaves2f28cee3ce48
diff --git a/tests/test_utils_iterators.py b/tests/test_utils_iterators.py
index ae64e36cf..2adccebb8 100644
--- a/tests/test_utils_iterators.py
+++ b/tests/test_utils_iterators.py
@@ -175,6 +175,30 @@ class XmliterTestCase(unittest.TestCase):
node.register_namespace('g', 'http://base.google.com/ns/1.0')
self.assertEqual(node.xpath('text()').extract(), ['http://www.mydummycompany.com/images/item1.jpg'])
+ def test_xmliter_namespaced_nodename_missing(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:link_image')
+ with self.assertRaises(StopIteration):
+ next(my_iter)
+
def test_xmliter_exception(self):
body = (
'<?xml version="1.0" encoding="UTF-8"?>'