mirror of https://github.com/scrapy/scrapy.git
moved all similar selector tests to common selector tests, to reuse them among all backends
This commit is contained in:
Pablo Hoffman
parent
d1f63237ad
commit
e625a8d56e
|
|
@ -52,6 +52,18 @@ class XPathSelectorTestCase(unittest.TestCase):
|
|||
assert isinstance(self.hxs_cls(text=text).select("//p")[0],
|
||||
self.hxs_cls)
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_boolean_result(self):
|
||||
body = "<p><input name='a'value='1'/><input name='b'value='2'/></p>"
|
||||
response = TextResponse(url="http://example.com", body=body)
|
||||
xs = self.hxs_cls(response)
|
||||
true = xs.select("//input[@name='a']/@name='a'").extract()[0]
|
||||
false = xs.select("//input[@name='a']/@name='n'").extract()[0]
|
||||
|
||||
# the actual result depends on the backend used
|
||||
assert true in [u'1', u'True'], true
|
||||
assert false in [u'0', u'False'], false
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_xml_html(self):
|
||||
"""Test that XML and HTML XPathSelector's behave differently"""
|
||||
|
|
@ -94,6 +106,46 @@ class XPathSelectorTestCase(unittest.TestCase):
|
|||
self.assertEqual(divtwo.select("./li").extract(),
|
||||
[])
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_simple(self):
|
||||
body = """
|
||||
<test xmlns:somens="http://scrapy.org">
|
||||
<somens:a id="foo">take this</a>
|
||||
<a id="bar">found</a>
|
||||
</test>
|
||||
"""
|
||||
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = self.xxs_cls(response)
|
||||
|
||||
x.register_namespace("somens", "http://scrapy.org")
|
||||
self.assertEqual(x.select("//somens:a/text()").extract(),
|
||||
[u'take this'])
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_multiple(self):
|
||||
body = """<?xml version="1.0" encoding="UTF-8"?>
|
||||
<BrowseNode xmlns="http://webservices.amazon.com/AWSECommerceService/2005-10-05"
|
||||
xmlns:b="http://somens.com"
|
||||
xmlns:p="http://www.scrapy.org/product" >
|
||||
<b:Operation>hello</b:Operation>
|
||||
<TestTag b:att="value"><Other>value</Other></TestTag>
|
||||
<p:SecondTestTag><material>iron</material><price>90</price><p:name>Dried Rose</p:name></p:SecondTestTag>
|
||||
</BrowseNode>
|
||||
"""
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = self.xxs_cls(response)
|
||||
|
||||
x.register_namespace("xmlns", "http://webservices.amazon.com/AWSECommerceService/2005-10-05")
|
||||
x.register_namespace("p", "http://www.scrapy.org/product")
|
||||
x.register_namespace("b", "http://somens.com")
|
||||
self.assertEqual(len(x.select("//xmlns:TestTag")), 1)
|
||||
self.assertEqual(x.select("//b:Operation/text()").extract()[0], 'hello')
|
||||
self.assertEqual(x.select("//xmlns:TestTag/@b:att").extract()[0], 'value')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:price/text()").extract()[0], '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag").select("./xmlns:price/text()")[0].extract(), '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:material/text()").extract()[0], 'iron')
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_re(self):
|
||||
body = """<div>Name: Mary
|
||||
|
|
|
|||
|
|
@ -9,55 +9,14 @@ from scrapy.selector.libxml2sel import XmlXPathSelector, HtmlXPathSelector, \
|
|||
XPathSelector
|
||||
from scrapy.selector.document import Libxml2Document
|
||||
from scrapy.utils.test import libxml2debug
|
||||
from scrapy.tests.test_selector import XPathSelectorTestCase
|
||||
from scrapy.tests import test_selector
|
||||
|
||||
class XPathSelectorTestCase(XPathSelectorTestCase):
|
||||
class Libxml2XPathSelectorTestCase(test_selector.XPathSelectorTestCase):
|
||||
|
||||
xs_cls = XPathSelector
|
||||
hxs_cls = HtmlXPathSelector
|
||||
xxs_cls = XmlXPathSelector
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_simple(self):
|
||||
body = """
|
||||
<test xmlns:somens="http://scrapy.org">
|
||||
<somens:a id="foo"/>
|
||||
<a id="bar">found</a>
|
||||
</test>
|
||||
"""
|
||||
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = XmlXPathSelector(response)
|
||||
|
||||
x.register_namespace("somens", "http://scrapy.org")
|
||||
self.assertEqual(x.select("//somens:a").extract(),
|
||||
['<somens:a id="foo"/>'])
|
||||
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_multiple(self):
|
||||
body = """<?xml version="1.0" encoding="UTF-8"?>
|
||||
<BrowseNode xmlns="http://webservices.amazon.com/AWSECommerceService/2005-10-05"
|
||||
xmlns:b="http://somens.com"
|
||||
xmlns:p="http://www.scrapy.org/product" >
|
||||
<b:Operation>hello</b:Operation>
|
||||
<TestTag b:att="value"><Other>value</Other></TestTag>
|
||||
<p:SecondTestTag><material/><price>90</price><p:name>Dried Rose</p:name></p:SecondTestTag>
|
||||
</BrowseNode>
|
||||
"""
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = XmlXPathSelector(response)
|
||||
|
||||
x.register_namespace("xmlns", "http://webservices.amazon.com/AWSECommerceService/2005-10-05")
|
||||
x.register_namespace("p", "http://www.scrapy.org/product")
|
||||
x.register_namespace("b", "http://somens.com")
|
||||
self.assertEqual(len(x.select("//xmlns:TestTag")), 1)
|
||||
self.assertEqual(x.select("//b:Operation/text()").extract()[0], 'hello')
|
||||
self.assertEqual(x.select("//xmlns:TestTag/@b:att").extract()[0], 'value')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:price/text()").extract()[0], '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag").select("./xmlns:price/text()")[0].extract(), '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:material").extract()[0], '<material/>')
|
||||
|
||||
@libxml2debug
|
||||
def test_null_bytes(self):
|
||||
hxs = HtmlXPathSelector(text='<root>la\x00la</root>')
|
||||
|
|
|
|||
|
|
@ -10,9 +10,9 @@ try:
|
|||
except ImportError:
|
||||
has_lxml = False
|
||||
from scrapy.utils.test import libxml2debug
|
||||
from scrapy.tests.test_selector import XPathSelectorTestCase
|
||||
from scrapy.tests import test_selector
|
||||
|
||||
class XPathSelectorTestCase(XPathSelectorTestCase):
|
||||
class LxmlXPathSelectorTestCase(test_selector.XPathSelectorTestCase):
|
||||
|
||||
if has_lxml:
|
||||
xs_cls = XPathSelector
|
||||
|
|
@ -21,55 +21,6 @@ class XPathSelectorTestCase(XPathSelectorTestCase):
|
|||
else:
|
||||
skip = "lxml not available"
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_boolean_result(self):
|
||||
body = "<p><input name='a'value='1'/><input name='b'value='2'/></p>"
|
||||
response = TextResponse(url="http://example.com", body=body)
|
||||
xs = HtmlXPathSelector(response)
|
||||
self.assertEqual(xs.select("//input[@name='a']/@name='a'").extract(), [u'True'])
|
||||
self.assertEqual(xs.select("//input[@name='a']/@name='n'").extract(), [u'False'])
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_simple(self):
|
||||
body = """
|
||||
<test xmlns:somens="http://scrapy.org">
|
||||
<somens:a id="foo">take this</a>
|
||||
<a id="bar">found</a>
|
||||
</test>
|
||||
"""
|
||||
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = XmlXPathSelector(response)
|
||||
|
||||
x.register_namespace("somens", "http://scrapy.org")
|
||||
self.assertEqual(x.select("//somens:a/text()").extract(),
|
||||
[u'take this'])
|
||||
|
||||
|
||||
@libxml2debug
|
||||
def test_selector_namespaces_multiple(self):
|
||||
body = """<?xml version="1.0" encoding="UTF-8"?>
|
||||
<BrowseNode xmlns="http://webservices.amazon.com/AWSECommerceService/2005-10-05"
|
||||
xmlns:b="http://somens.com"
|
||||
xmlns:p="http://www.scrapy.org/product" >
|
||||
<b:Operation>hello</b:Operation>
|
||||
<TestTag b:att="value"><Other>value</Other></TestTag>
|
||||
<p:SecondTestTag><material>iron</material><price>90</price><p:name>Dried Rose</p:name></p:SecondTestTag>
|
||||
</BrowseNode>
|
||||
"""
|
||||
response = XmlResponse(url="http://example.com", body=body)
|
||||
x = XmlXPathSelector(response)
|
||||
|
||||
x.register_namespace("xmlns", "http://webservices.amazon.com/AWSECommerceService/2005-10-05")
|
||||
x.register_namespace("p", "http://www.scrapy.org/product")
|
||||
x.register_namespace("b", "http://somens.com")
|
||||
self.assertEqual(len(x.select("//xmlns:TestTag")), 1)
|
||||
self.assertEqual(x.select("//b:Operation/text()").extract()[0], 'hello')
|
||||
self.assertEqual(x.select("//xmlns:TestTag/@b:att").extract()[0], 'value')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:price/text()").extract()[0], '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag").select("./xmlns:price/text()")[0].extract(), '90')
|
||||
self.assertEqual(x.select("//p:SecondTestTag/xmlns:material/text()").extract()[0], 'iron')
|
||||
|
||||
# XXX: this test was disabled because lxml behaves inconsistently when
|
||||
# handling null bytes between different 2.2.x versions, but it may be due
|
||||
# to differences in libxml2 too. it's also unclear what should be the
|
||||
|
|
|
|||
Loading…
Reference in New Issue