BackTrackZ/scrapy
BackTrackZ/scrapy
1
0
Fork 0
mirror of https://github.com/scrapy/scrapy.git synced 2025-02-24 00:23:52 +00:00
Code Releases Wiki Activity

Add testcase to check is default Selector doesnt return smart strings

Browse Source
This commit is contained in:
Paul Tremberth 2014-01-17 00:04:20 +01:00
parent 5eb336215c
commit 001cf39ff4
1 changed files with 43 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
scrapy/tests/test_selector.py
View File

@ -297,6 +297,49 @@ class SelectorTestCase(unittest.TestCase):
sel.remove_namespaces()
self.assertEqual(len(sel.xpath("//link/@type")), 2)
def test_smart_strings(self):
"""Lxml smart strings return values"""
class SmartStringsSelector(Selector):
_lxml_smart_strings = True
body = """<body>
<div class='one'>
<ul>
<li>one</li><li>two</li>
</ul>
</div>
<div class='two'>
<ul>
<li>four</li><li>five</li><li>six</li>
</ul>
</div>
</body>"""
response = HtmlResponse(url="http://example.com", body=body)
# .getparent() is available for text nodes and attributes
# only when smart_strings are on
x = self.sscls(response)
li_text = x.xpath('//li/text()')
self.assertIs(
any(map(lambda e: hasattr(e._root, 'getparent'), li_text)),
False)
div_class = x.xpath('//div/@class')
self.assertIs(
any(map(lambda e: hasattr(e._root, 'getparent'), div_class)),
False)
x = SmartStringsSelector(response)
li_text = x.xpath('//li/text()')
self.assertIs(
all(map(lambda e: hasattr(e._root, 'getparent'), li_text)),
True)
div_class = x.xpath('//div/@class')
self.assertIs(
all(map(lambda e: hasattr(e._root, 'getparent'), div_class)),
True)
class DeprecatedXpathSelectorTest(unittest.TestCase):