def test_extract_csspath(self):
from mobilize.components import CssPath
testdata = [
{'datafile' : 'a.xml',
'components' : [CssPath('div#happy', classvalue='some-class')],
'extracted' : ['<div class="some-class" id="some-id"><div id="happy">lucky</div></div>'],
},
{'datafile' : 'b.xml',
'components' : [CssPath('div#joyful', classvalue='some-class')],
'extracted' : ['<div class="some-class" id="some-id"><div id="joyful">fun</div></div>'],
},
{'datafile' : 'c.xml',
'components' : [CssPath('p.graceful', classvalue='some-class')],
'extracted' : ['<div class="some-class" id="some-id"><p class="graceful">laughing</p></div>'],
},
{'datafile' : 'd.xml',
'components' : [CssPath('p.graceful', classvalue='some-class')],
'extracted' : ['<div class="some-class" id="some-id"><p class="skipping graceful enthusiastic">laughing</p></div>'],
},
{'datafile' : 'e.xml',
'components' : [CssPath('p.graceful', classvalue='some-class')],
'extracted' : ['<div class="some-class" id="some-id"><p class="skipping graceful enthusiastic">laughing</p><p class="graceful">enthusiastic</p></div>'],
},
]
for ii, td in enumerate(testdata):
doc = html.fromstring(open(data_file_path('extract_celems', td['datafile'])).read())
for sel in td['components']:
sel.extract(doc)
sel.process('some-id')
expected = list(map(normxml, td['extracted']))
actual = [normxml(sel.html()) for sel in td['components']]
msg = 'e: %s, a: %s [%d %s]' % (expected, actual, ii, td['datafile'])
self.assertEqual(expected, actual, msg)
def test_GoogleAnalytics_none(self):
# Check negative case where we expect to not find GA tracking codes
from mobilize.components import GoogleAnalytics
doc_str = open(data_file_path('whole-html', 'cnn.html')).read()
doc = html.fromstring(doc_str)
noga = GoogleAnalytics()
noga.extract(doc)
noga.process()
actual = normxml(noga.html())
expected = normxml('''<div class="mwu-elem" id="mwu-elem-ga"></div>''')
self.assertSequenceEqual(expected, actual)
def test_GoogleAnalytics_v1(self):
from mobilize.components import GoogleAnalytics
# Check positive case, where we expect to find the GA tracking code (older version)
doc_str = open(data_file_path('whole-html', 'luxwny.html')).read()
doc = html.fromstring(doc_str)
ga = GoogleAnalytics()
ga.extract(doc)
ga.process()
extracted_str = ga.html()
extracted = html.fromstring(extracted_str)
extracted_script_tags = extracted.cssselect('script')
self.assertEqual(len(extracted_script_tags), 2)
ga_script1_text = extracted_script_tags[0].text
self.assertTrue('var gaJsHost' in ga_script1_text)
ga_script2_text = extracted_script_tags[1].text
self.assertTrue('UA-12345678-1' in ga_script2_text)
def test_GoogleAnalytics_v2(self):
# Check positive case, where we expect to find the GA tracking codes
from mobilize.components import GoogleAnalytics
testdatafiles = [
'msia.org.html', # variant 1
'msia.org.2.html', # variant 2
]
for testdatafile in testdatafiles:
doc_str = open(data_file_path('whole-html', testdatafile)).read()
doc = html.fromstring(doc_str)
ga = GoogleAnalytics()
ga.extract(doc)
ga.process()
extracted_str = ga.html()
extracted = html.fromstring(extracted_str)
extracted_script_tags = extracted.cssselect('script')
self.assertEqual(len(extracted_script_tags), 1, testdatafile)
ga_script_text = extracted_script_tags[0].text
self.assertTrue('UA-12345678-1' in ga_script_text, testdatafile)