def test_apply(self):
rule = PathRule(['.*', {}, [u'td', {u'colspan': u'2',
u'class': u'small-text'}, 1],
[u'span', {u'class': u'small-text'}, 5]
])
result = rule.apply(self.example01.content)
self.failUnless(result[0] == u' Volume 70 , Issue 16-18 (October '
'2007)')
def test_apply(self):
rule = PathRule([
'.*', {}, [u'td', {
u'colspan': u'2',
u'class': u'small-text'
}, 1], [u'span', {
u'class': u'small-text'
}, 5]
])
result = rule.apply(self.example01.content)
self.failUnless(result[0] == u' Volume 70 , Issue 16-18 (October '
'2007)')
class TestPathRule(unittest.TestCase):
def setUp(self):
self.rule = PathRule()
def test_apply_standard_path(self):
html = get_soup('acm01.html')
path = ['.*', {},
[u'td', {u'colspan': u'2', u'class': u'small-text'}, 1],
[u'span', {u'class': u'small-text'}, 5]]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Volume 70'))
def test_apply_wildcard_path(self):
html = get_soup('acm01.html')
path = ['.*', {},
[u'td', {u'colspan': u'2', u'class': u'small-text'}, 1],
[u'span', {u'class': u'small-text'}, -1]]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Volume 70'))
def test_middle_wildcard_path(self):
html = get_soup('acm01.html')
path = ['.*', {},
[u'div', {u'class':'authors'}, -1],
[u'table', {u'cellpadding':u'0', u'cellspacing':u'0'}, 0],
[u'tbody', {}, 0],
[u'tr', {}, -1],
[u'td', {u'class': u'small-text'}, 1],
[u'small', {}, 0]]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
def test_regex_guided_wildcard(self):
html = get_soup('acm01.html')
path = ['.*Year of Publication.*', {},
[u'td', {u'colspan': u'2', u'class': u'small-text'}, 1],
[u'div', {u'class':u'small-text'}, -1]]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Year of'))
def test_apply_no_sibling(self):
html = BeautifulSoup('<html><body><div id="01" class="div01"><span>'
'Some text</span><p>Paragraph</p></div>'
'</body></html>')
path = ['.*', {}, (u'div', {u'class': u'div01'}, 1),
(u'p', {}, -1)]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0] == "Paragraph")
def test_choose_element(self):
html = get_soup('springer01.html')
path = ['.*', {u"Journal":1},
["table", {"cellpadding": "0", "cellspacing": "0", "class": "MPReader_Profiles_SpringerLink_Content_PrimitiveHeadingControl"}, 0],
["tbody", {}, -1],
["tr", {"valign": "top"}, 0],
["td", {}, 1],
["table", {"cellpadding": "0", "cellspacing": "0"}, 1],
["tbody", {}, -1],
["tr", {}, 1],
["td", {"class": "labelValue"}, 1]]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0] == u'Catalysis Letters')
class TestPathRule(unittest.TestCase):
def setUp(self):
self.rule = PathRule()
def test_apply_standard_path(self):
html = get_soup('acm01.html')
path = [
'.*', {}, [u'td', {
u'colspan': u'2',
u'class': u'small-text'
}, 1], [u'span', {
u'class': u'small-text'
}, 5]
]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Volume 70'))
def test_apply_wildcard_path(self):
html = get_soup('acm01.html')
path = [
'.*', {}, [u'td', {
u'colspan': u'2',
u'class': u'small-text'
}, 1], [u'span', {
u'class': u'small-text'
}, -1]
]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Volume 70'))
def test_middle_wildcard_path(self):
html = get_soup('acm01.html')
path = [
'.*', {}, [u'div', {
u'class': 'authors'
}, -1],
[u'table', {
u'cellpadding': u'0',
u'cellspacing': u'0'
}, 0], [u'tbody', {}, 0], [u'tr', {}, -1],
[u'td', {
u'class': u'small-text'
}, 1], [u'small', {}, 0]
]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
def test_regex_guided_wildcard(self):
html = get_soup('acm01.html')
path = [
'.*Year of Publication.*', {},
[u'td', {
u'colspan': u'2',
u'class': u'small-text'
}, 1], [u'div', {
u'class': u'small-text'
}, -1]
]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0].startswith(' Year of'))
def test_apply_no_sibling(self):
html = BeautifulSoup('<html><body><div id="01" class="div01"><span>'
'Some text</span><p>Paragraph</p></div>'
'</body></html>')
path = ['.*', {}, (u'div', {u'class': u'div01'}, 1), (u'p', {}, -1)]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0] == "Paragraph")
def test_choose_element(self):
html = get_soup('springer01.html')
path = [
'.*', {
u"Journal": 1
},
[
"table", {
"cellpadding":
"0",
"cellspacing":
"0",
"class":
"MPReader_Profiles_SpringerLink_Content_PrimitiveHeadingControl"
}, 0
], ["tbody", {}, -1], ["tr", {
"valign": "top"
}, 0], ["td", {}, 1],
["table", {
"cellpadding": "0",
"cellspacing": "0"
}, 1], ["tbody", {}, -1], ["tr", {}, 1],
["td", {
"class": "labelValue"
}, 1]
]
self.rule.pattern = path
result = self.rule.apply(html)
self.failIf(not result)
self.failUnless(result[0] == u'Catalysis Letters')