From d806184bb6c13b0d0b121a8a5a29260508d4cd43 Mon Sep 17 00:00:00 2001
From: Paul Tremberth <paul.tremberth@gmail.com>
Date: Tue, 8 Oct 2013 00:01:44 +0200
Subject: [PATCH] .remove_namespaces(): remove namespaces on elements'
 attributes

---
 scrapy/selector/lxmlsel.py         |  4 ++++
 scrapy/tests/test_selector_lxml.py | 12 ++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/scrapy/selector/lxmlsel.py b/scrapy/selector/lxmlsel.py
index 8708144bd..5bf9fd1dc 100644
--- a/scrapy/selector/lxmlsel.py
+++ b/scrapy/selector/lxmlsel.py
@@ -77,6 +77,10 @@ class XPathSelector(object_ref):
         for el in self._root.iter('*'):
             if el.tag.startswith('{'):
                 el.tag = el.tag.split('}', 1)[1]
+            # loop on element attributes also
+            for an in el.attrib.keys():
+                if an.startswith('{'):
+                    el.attrib[an.split('}', 1)[1]] = el.attrib.pop(an)
 
     def __nonzero__(self):
         return bool(self.extract())
diff --git a/scrapy/tests/test_selector_lxml.py b/scrapy/tests/test_selector_lxml.py
index f9c9ec2ac..352861ae6 100644
--- a/scrapy/tests/test_selector_lxml.py
+++ b/scrapy/tests/test_selector_lxml.py
@@ -27,6 +27,18 @@ class LxmlXPathSelectorTestCase(test_selector.XPathSelectorTestCase):
         xxs.remove_namespaces()
         self.assertEqual(len(xxs.select("//link")), 2)
 
+    def test_remove_attributes_namespaces(self):
+        xml = """<?xml version="1.0" encoding="UTF-8"?>
+<feed xmlns:atom="http://www.w3.org/2005/Atom" xml:lang="en-US" xmlns:media="http://search.yahoo.com/mrss/">
+  <link atom:type="text/html">
+  <link atom:type="application/atom+xml">
+</feed>
+"""
+        xxs = XmlXPathSelector(XmlResponse("http://example.com/feed.atom", body=xml))
+        self.assertEqual(len(xxs.select("//link/@type")), 0)
+        xxs.remove_namespaces()
+        self.assertEqual(len(xxs.select("//link/@type")), 2)
+
 class Libxml2DocumentTest(unittest.TestCase):
 
     def test_caching(self):