#-*- coding:utf-8 -*- # # Copyright (C) 2008 - Olivier Lauzanne # # Distributed under the BSD license, see LICENSE.txt import os import sys sys.path.insert(0, os.path.dirname(os.path.dirname(__file__))) from lxml import etree from pyquery.pyquery import PyQuery as pq from pyquery.ajax import PyQuery as pqa from webtest import http from webtest.debugapp import debug_app from .apps import application from .apps import secure_application from .compat import PY3k from .compat import u from .compat import b from .compat import text_type from .compat import TestCase def not_py3k(func): if not PY3k: return func try: import requests # NOQA HAS_REQUEST = True except ImportError: HAS_REQUEST = False dirname = os.path.dirname(os.path.abspath(__file__)) docs = os.path.join(os.path.dirname(dirname), 'docs') path_to_html_file = os.path.join(dirname, 'test.html') path_to_invalid_file = os.path.join(dirname, 'invalid.xml') class TestUnicode(TestCase): def test_unicode(self): xml = pq(u("

", 'utf-8')) self.assertEqual(type(xml.html()), text_type) if PY3k: self.assertEqual(str(xml), '

') self.assertEqual(str(xml('p:contains("é")')), '

') else: self.assertEqual(unicode(xml), u("

", 'utf-8')) self.assertEqual(str(xml), '

') self.assertEqual(str(xml(u('p:contains("é")', 'utf8'))), '

') self.assertEqual(unicode(xml(u('p:contains("é")', 'utf8'))), u('

', 'utf8')) class TestAttributeCase(TestCase): def test_xml_upper_element_name(self): xml = pq('foo', parser='xml') self.assertEqual(len(xml('X')), 1) self.assertEqual(len(xml('x')), 0) def test_html_upper_element_name(self): xml = pq('foo', parser='html') self.assertEqual(len(xml('X')), 1) self.assertEqual(len(xml('x')), 1) class TestSelector(TestCase): klass = pq html = """

node1

node2

node3

""" html2 = """

node1

""" html3 = """

node1

node2

node3

""" html4 = """ """ html5 = """

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5

Heading 6

""" def test_get_root(self): doc = pq(b('

')) self.assertEqual(isinstance(doc.root, etree._ElementTree), True) self.assertEqual(doc.encoding, 'UTF-8') def test_selector_from_doc(self): doc = etree.fromstring(self.html) assert len(self.klass(doc)) == 1 assert len(self.klass('div', doc)) == 3 assert len(self.klass('div#node2', doc)) == 1 def test_selector_from_html(self): assert len(self.klass(self.html)) == 1 assert len(self.klass('div', self.html)) == 3 assert len(self.klass('div#node2', self.html)) == 1 def test_selector_from_obj(self): e = self.klass(self.html) assert len(e('div')) == 3 assert len(e('div#node2')) == 1 def test_selector_from_html_from_obj(self): e = self.klass(self.html) assert len(e('div', self.html2)) == 1 assert len(e('div#node2', self.html2)) == 0 def test_class(self): e = self.klass(self.html) assert isinstance(e, self.klass) n = e('div', self.html2) assert isinstance(n, self.klass) assert n._parent is e def test_pseudo_classes(self): e = self.klass(self.html) self.assertEqual(e('div:first').text(), 'node1') self.assertEqual(e('div:last').text(), 'node3') self.assertEqual(e('div:even').text(), 'node1 node3') self.assertEqual(e('div div:even').text(), '') self.assertEqual(e('body div:even').text(), 'node1 node3') self.assertEqual(e('div:gt(0)').text(), 'node2 node3') self.assertEqual(e('div:lt(1)').text(), 'node1') self.assertEqual(e('div:eq(2)').text(), 'node3') #test on the form e = self.klass(self.html4) assert len(e(':disabled')) == 1 assert len(e('input:enabled')) == 9 assert len(e(':selected')) == 1 assert len(e(':checked')) == 2 assert len(e(':file')) == 1 assert len(e(':input')) == 12 assert len(e(':button')) == 2 assert len(e(':radio')) == 3 assert len(e(':checkbox')) == 3 #test on other elements e = self.klass(self.html5) assert len(e(":header")) == 6 assert len(e(":parent")) == 2 assert len(e(":empty")) == 6 assert len(e(":contains('Heading')")) == 6 def test_on_the_fly_dom_creation(self): e = self.klass(self.html) assert e('

Hello world

').text() == 'Hello world' assert e('').text() == '' class TestTraversal(TestCase): klass = pq html = """

node1

node2 booyah

""" def test_filter(self): assert len(self.klass('div', self.html).filter('.node3')) == 1 assert len(self.klass('div', self.html).filter('#node2')) == 1 assert len(self.klass('div', self.html).filter(lambda i: i == 0)) == 1 d = pq('

Hello warming world

') self.assertEqual(d('strong').filter(lambda el: True), []) def test_not(self): assert len(self.klass('div', self.html).not_('.node3')) == 1 def test_is(self): assert self.klass('div', self.html).is_('.node3') assert not self.klass('div', self.html).is_('.foobazbar') def test_find(self): assert len(self.klass('#node1', self.html).find('span')) == 1 assert len(self.klass('#node2', self.html).find('span')) == 2 assert len(self.klass('div', self.html).find('span')) == 3 def test_each(self): doc = self.klass(self.html) doc('span').each(lambda: doc(this).wrap("")) # NOQA assert len(doc('em')) == 3 def test_map(self): def ids_minus_one(i, elem): return int(self.klass(elem).attr('id')[-1]) - 1 assert self.klass('div', self.html).map(ids_minus_one) == [0, 1] d = pq('

Hello warming world

') self.assertEqual(d('strong').map(lambda i, el: pq(this).text()), []) # NOQA def test_end(self): assert len(self.klass('div', self.html).find('span').end()) == 2 assert len(self.klass('#node2', self.html).find('span').end()) == 1 def test_closest(self): assert len(self.klass('#node1 span', self.html).closest('body')) == 1 assert self.klass('#node2', self.html).closest('.node3').attr('id') == 'node2' assert self.klass('.node3', self.html).closest('form') == [] class TestOpener(TestCase): def test_open_filename(self): doc = pq(filename=path_to_html_file) self.assertEqual(len(doc('p#test').text()), 14) def test_invalid_filename(self): doc = pq(filename=path_to_invalid_file) self.assertEqual(len(doc('p#test').text()), 14) def test_custom_opener(self): def opener(url): return '

' doc = pq(url='http://example.com', opener=opener) assert len(doc('.node')) == 1, doc class TestComment(TestCase): def test_comment(self): doc = pq('

bar

') self.assertEqual(doc.text(), 'bar') class TestCallback(TestCase): html = """

Coffee
Tea
Milk

""" def test_S_this_inside_callback(self): S = pq(self.html) self.assertEqual(S('li').map(lambda i, el: S(this).html()), # NOQA ['Coffee', 'Tea', 'Milk']) def test_parameterless_callback(self): S = pq(self.html) self.assertEqual(S('li').map(lambda: S(this).html()), # NOQA ['Coffee', 'Tea', 'Milk']) class TestHook(TestCase): html = """

Coffee
Tea
Milk

""" def test_fn(self): "Example from `PyQuery.Fn` docs." fn = lambda: this.map(lambda i, el: pq(this).outerHtml()) pq.fn.listOuterHtml = fn S = pq(self.html) self.assertEqual(S('li').listOuterHtml(), ['

Coffee

', '

Tea

', '

Milk

']) def test_fn_with_kwargs(self): "fn() with keyword arguments." pq.fn.test = lambda p=1: pq(this).eq(p) S = pq(self.html) self.assertEqual(S('li').test(0).text(), 'Coffee') self.assertEqual(S('li').test().text(), 'Tea') self.assertEqual(S('li').test(p=2).text(), 'Milk') class TestAjaxSelector(TestSelector): klass = pqa def setUp(self): self.s = http.StopableWSGIServer.create(application) @not_py3k def test_proxy(self): self.s.wait() application_url = self.s.application_url e = self.klass([]) val = e.get(application_url) assert len(val('pre')) == 1, (str(val.response), val) def test_get(self): e = self.klass(app=application) val = e.get('/') assert len(val('pre')) == 1, val def test_secure_get(self): e = self.klass(app=secure_application) val = e.get('/', environ=dict(REMOTE_USER='gawii')) assert len(val('pre')) == 1, val val = e.get('/', REMOTE_USER='gawii') assert len(val('pre')) == 1, val def test_secure_get_not_authorized(self): e = self.klass(app=secure_application) val = e.get('/') assert len(val('pre')) == 0, val def test_post(self): e = self.klass(app=application) val = e.post('/') assert len(val('a')) == 1, val def test_subquery(self): e = self.klass(app=application) n = e('div') val = n.post('/') assert len(val('a')) == 1, val def tearDown(self): self.s.shutdown() class TestManipulating(TestCase): html = '''

Test

My link text

My link text 2

''' def test_remove(self): d = pq(self.html) d('img').remove() val = d('a:first').html() assert val == 'Test My link text', repr(val) val = d('a:last').html() assert val == ' My link text 2', repr(val) def test_class(self): d = pq('

') d.removeClass('xx') assert 'class' not in str(d), str(d) class TestMakeLinks(TestCase): html = '''

with href without href

''' def test_make_link(self): d = pq(self.html, parser='xml') d.make_links_absolute(base_url='http://example.com') self.assertTrue(len(d('a[href]')), 1) self.assertEqual(d('a[href]').attr('href'), 'http://example.com/path_info') class TestHTMLParser(TestCase): xml = "

I'm valid XML

" html = '''

TestimageMy link text imageMy link text 2 Behind you, a three-headed HTML‐Entity!

''' def test_parser_persistance(self): d = pq(self.xml, parser='xml') self.assertRaises(etree.XMLSyntaxError, lambda: d.after(self.html)) d = pq(self.xml, parser='html') d.after(self.html) # this should not fail @not_py3k def test_soup_parser(self): d = pq('Hello</head><body onload=crash()>Hi all<p>', parser='soup') self.assertEqual(str(d), ( '<html><meta/><head><title>Hello' 'Hi all

')) def test_replaceWith(self): expected = '''

TestimageMy link text imageMy link text 2 Behind you, a three-headed HTML&dash;Entity!

''' d = pq(self.html) d('img').replace_with('image') val = d.__html__() assert val == expected, (repr(val), repr(expected)) def test_replaceWith_with_function(self): expected = '''

TestimageMy link text imageMy link text 2 Behind you, a three-headed HTML&dash;Entity!

''' d = pq(self.html) d('a').replace_with(lambda i, e: pq(e).html()) val = d.__html__() assert val == expected, (repr(val), repr(expected)) class TestXMLNamespace(TestCase): xml = ''' What 123 ''' xhtml = '''

What

''' def test_selector(self): expected = 'What' d = pq(b(self.xml), parser='xml') val = d('bar|blah', namespaces={'bar': 'http://example.com/bar'}).text() self.assertEqual(repr(val), repr(expected)) def test_selector_with_xml(self): expected = 'What' d = pq('bar|blah', b(self.xml), parser='xml', namespaces={'bar': 'http://example.com/bar'}) val = d.text() self.assertEqual(repr(val), repr(expected)) def test_selector_html(self): expected = 'What' d = pq('blah', self.xml.split('?>', 1)[1], parser='html') val = d.text() self.assertEqual(repr(val), repr(expected)) def test_xhtml_namespace(self): expected = 'What' d = pq(b(self.xhtml), parser='xml') d.xhtml_to_html() val = d('div').text() self.assertEqual(repr(val), repr(expected)) def test_xhtml_namespace_html_parser(self): expected = 'What' d = pq(self.xhtml, parser='html') d.xhtml_to_html() val = d('div').text() self.assertEqual(repr(val), repr(expected)) def test_remove_namespaces(self): expected = 'What' d = pq(b(self.xml), parser='xml').remove_namespaces() val = d('blah').text() self.assertEqual(repr(val), repr(expected)) class TestWebScrapping(TestCase): def setUp(self): self.s = http.StopableWSGIServer.create(debug_app) self.s.wait() self.application_url = self.s.application_url.rstrip('/') def test_get(self): d = pq(self.application_url, {'q': 'foo'}, method='get') print(d) self.assertIn('REQUEST_METHOD: GET', d('p').text()) self.assertIn('q=foo', d('p').text()) def test_post(self): d = pq(self.application_url, {'q': 'foo'}, method='post') self.assertIn('REQUEST_METHOD: POST', d('p').text()) self.assertIn('q=foo', d('p').text()) def tearDown(self): self.s.shutdown() class TestWebScrappingEncoding(TestCase): def test_get(self): if not HAS_REQUEST: return d = pq(u('http://ru.wikipedia.org/wiki/Заглавная_страница', 'utf8'), method='get') print(d) self.assertEqual(d('#n-mainpage a').text(), u('Заглавная страница', 'utf8'))