RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix `tail` issue when extracting nodes [lxml]

This commit is contained in:
Alexandru Cepoi 2012-05-07 17:23:27 +02:00
parent 43028876b5
commit 045ff8e5a7
2 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scrapy/selector/lxmlsel.py
View File

@ -59,7 +59,7 @@ class XPathSelector(object_ref):
def extract(self): def extract(self):
try: try:
return etree.tostring(self._root, method=self._tostring_method, \ return etree.tostring(self._root, method=self._tostring_method, \
encoding=unicode) encoding=unicode, with_tail=False)
except (AttributeError, TypeError): except (AttributeError, TypeError):
if self._root is True: if self._root is True:
return u'1' return u'1'

9
scrapy/tests/test_selector.py
View File

@ -43,6 +43,7 @@ class XPathSelectorTestCase(unittest.TestCase):
self.assertEqual([x.extract() for x in xpath.select("concat(//input[@name='a']/@value, //input[@name='b']/@value)")], self.assertEqual([x.extract() for x in xpath.select("concat(//input[@name='a']/@value, //input[@name='b']/@value)")],
[u'12']) [u'12'])
@libxml2debug
def test_selector_unicode_query(self): def test_selector_unicode_query(self):
body = u"<p><input name='\xa9' value='1'/></p>" body = u"<p><input name='\xa9' value='1'/></p>"
response = TextResponse(url="http://example.com", body=body, encoding='utf8') response = TextResponse(url="http://example.com", body=body, encoding='utf8')
@ -271,7 +272,6 @@ class XPathSelectorTestCase(unittest.TestCase):
@libxml2debug @libxml2debug
def test_select_on_text_nodes(self): def test_select_on_text_nodes(self):
# FIXME: can't get this to work with lxml backend
r = self.hxs_cls(text=u'<div><b>Options:</b>opt1</div><div><b>Other</b>opt2</div>') r = self.hxs_cls(text=u'<div><b>Options:</b>opt1</div><div><b>Other</b>opt2</div>')
x1 = r.select("//div/descendant::text()[preceding-sibling::b[contains(text(), 'Options')]]") x1 = r.select("//div/descendant::text()[preceding-sibling::b[contains(text(), 'Options')]]")
self.assertEquals(x1.extract(), [u'opt1']) self.assertEquals(x1.extract(), [u'opt1'])
@ -279,10 +279,15 @@ class XPathSelectorTestCase(unittest.TestCase):
x1 = r.select("//div/descendant::text()/preceding-sibling::b[contains(text(), 'Options')]") x1 = r.select("//div/descendant::text()/preceding-sibling::b[contains(text(), 'Options')]")
self.assertEquals(x1.extract(), [u'<b>Options:</b>']) self.assertEquals(x1.extract(), [u'<b>Options:</b>'])
@libxml2debug
def test_nested_select_on_text_nodes(self):
# FIXME: does not work with lxml backend [upstream]
r = self.hxs_cls(text=u'<div><b>Options:</b>opt1</div><div><b>Other</b>opt2</div>')
x1 = r.select("//div/descendant::text()") x1 = r.select("//div/descendant::text()")
x2 = x1.select("./preceding-sibling::b[contains(text(), 'Options')]") x2 = x1.select("./preceding-sibling::b[contains(text(), 'Options')]")
self.assertEquals(x2.extract(), [u'<b>Options:</b>']) self.assertEquals(x2.extract(), [u'<b>Options:</b>'])
test_select_on_text_nodes.skip = True test_nested_select_on_text_nodes.skip = True
@libxml2debug @libxml2debug
def test_weakref_slots(self): def test_weakref_slots(self):