From 22283854d49de2a4b01fd114880b486f45c5e3f0 Mon Sep 17 00:00:00 2001
From: Pablo Hoffman <pablo@pablohoffman.com>
Date: Wed, 27 Oct 2010 21:39:28 -0200
Subject: [PATCH] avoid stripping trailing spaces on lxml-based selectors.
 closes #270

---
 scrapy/selector/lxmlsel.py    |  5 ++---
 scrapy/tests/test_selector.py | 12 +++++++++---
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/scrapy/selector/lxmlsel.py b/scrapy/selector/lxmlsel.py
index 55d1a48e6..cc32a81f4 100644
--- a/scrapy/selector/lxmlsel.py
+++ b/scrapy/selector/lxmlsel.py
@@ -4,7 +4,6 @@ XPath selectors based on lxml
 
 from lxml import etree
 
-from scrapy.utils.python import flatten
 from scrapy.utils.misc import extract_regex
 from scrapy.utils.trackref import object_ref
 from scrapy.utils.python import unicode_to_str
@@ -65,9 +64,9 @@ class XPathSelector(object_ref):
     def extract(self):
         try:
             return etree.tostring(self.root, method=self._tostring_method, \
-                encoding=unicode).strip()
+                encoding=unicode)
         except (AttributeError, TypeError):
-            return unicode(self.root).strip()
+            return unicode(self.root)
 
     def register_namespace(self, prefix, uri):
         if self.namespaces is None:
diff --git a/scrapy/tests/test_selector.py b/scrapy/tests/test_selector.py
index 375ef3464..5ee0c6625 100644
--- a/scrapy/tests/test_selector.py
+++ b/scrapy/tests/test_selector.py
@@ -97,15 +97,21 @@ class XPathSelectorTestCase(unittest.TestCase):
         x = self.hxs_cls(response)
 
         divtwo = x.select('//div[@class="two"]')
-        self.assertEqual(divtwo.select("//li").extract(),
+        self.assertEqual(map(unicode.strip, divtwo.select("//li").extract()),
                          ["<li>one</li>", "<li>two</li>", "<li>four</li>", "<li>five</li>", "<li>six</li>"])
-        self.assertEqual(divtwo.select("./ul/li").extract(),
+        self.assertEqual(map(unicode.strip, divtwo.select("./ul/li").extract()),
                          ["<li>four</li>", "<li>five</li>", "<li>six</li>"])
-        self.assertEqual(divtwo.select(".//li").extract(),
+        self.assertEqual(map(unicode.strip, divtwo.select(".//li").extract()),
                          ["<li>four</li>", "<li>five</li>", "<li>six</li>"])
         self.assertEqual(divtwo.select("./li").extract(),
                          [])
 
+    @libxml2debug
+    def test_dont_strip(self):
+        hxs = self.hxs_cls(text='<div>fff: <a href="#">zzz</a></div>')
+        self.assertEqual(hxs.select("//text()").extract(),
+            [u'fff: ', u'zzz'])
+
     @libxml2debug
     def test_selector_namespaces_simple(self):
         body = """