From 82d138e87e68b1e198dfdc3b0d7f62d0de2e1ceb Mon Sep 17 00:00:00 2001
From: tpeng <pengtaoo@gmail.com>
Date: Mon, 1 Dec 2014 14:15:15 +0100
Subject: [PATCH] support namespace prefix in xmliter_lxml

---
 scrapy/contrib_exp/iterators.py |  6 +++---
 tests/test_utils_iterators.py   | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/scrapy/contrib_exp/iterators.py b/scrapy/contrib_exp/iterators.py
index 7cf9103fd..d96105fb9 100644
--- a/scrapy/contrib_exp/iterators.py
+++ b/scrapy/contrib_exp/iterators.py
@@ -2,18 +2,18 @@ from scrapy.http import Response
 from scrapy.selector import Selector
 
 
-def xmliter_lxml(obj, nodename, namespace=None):
+def xmliter_lxml(obj, nodename, namespace=None, prefix='x'):
     from lxml import etree
     reader = _StreamReader(obj)
     tag = '{%s}%s' % (namespace, nodename) if namespace else nodename
     iterable = etree.iterparse(reader, tag=tag, encoding=reader.encoding)
-    selxpath = '//' + ('x:%s' % nodename if namespace else nodename)
+    selxpath = '//' + ('%s:%s' % (prefix, nodename) if namespace else nodename)
     for _, node in iterable:
         nodetext = etree.tostring(node)
         node.clear()
         xs = Selector(text=nodetext, type='xml')
         if namespace:
-            xs.register_namespace('x', namespace)
+            xs.register_namespace(prefix, namespace)
         yield xs.xpath(selxpath)[0]
 
 
diff --git a/tests/test_utils_iterators.py b/tests/test_utils_iterators.py
index 840f4c596..d8faa810c 100644
--- a/tests/test_utils_iterators.py
+++ b/tests/test_utils_iterators.py
@@ -124,6 +124,38 @@ class LxmlXmliterTestCase(XmliterTestCase):
         node = next(namespace_iter)
         self.assertEqual(node.xpath('text()').extract(), ['http://www.mydummycompany.com/images/item2.jpg'])
 
+    def test_xmliter_namespaces_prefix(self):
+        body = """\
+        <?xml version="1.0" encoding="UTF-8"?>
+        <root>
+            <h:table xmlns:h="http://www.w3.org/TR/html4/">
+              <h:tr>
+                <h:td>Apples</h:td>
+                <h:td>Bananas</h:td>
+              </h:tr>
+            </h:table>
+
+            <f:table xmlns:f="http://www.w3schools.com/furniture">
+              <f:name>African Coffee Table</f:name>
+              <f:width>80</f:width>
+              <f:length>120</f:length>
+            </f:table>
+
+        </root>
+        """
+        response = XmlResponse(url='http://mydummycompany.com', body=body)
+        my_iter = self.xmliter(response, 'table', 'http://www.w3.org/TR/html4/', 'h')
+
+        node = next(my_iter)
+        self.assertEqual(len(node.xpath('h:tr/h:td').extract()), 2)
+        self.assertEqual(node.xpath('h:tr/h:td[1]/text()').extract(), ['Apples'])
+        self.assertEqual(node.xpath('h:tr/h:td[2]/text()').extract(), ['Bananas'])
+
+        my_iter = self.xmliter(response, 'table', 'http://www.w3schools.com/furniture', 'f')
+
+        node = next(my_iter)
+        self.assertEqual(node.xpath('f:name/text()').extract(), ['African Coffee Table'])
+
 
 class UtilsCsvTestCase(unittest.TestCase):
     sample_feeds_dir = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'sample_data', 'feeds')