def test_html(self):
shutil.copy('./tests/data/dirty.html', './tests/data/clean.html')
p = web.HTMLParser('./tests/data/clean.html')
meta = p.get_meta()
self.assertEqual(meta['author'], 'jvoisin')
ret = p.remove_all()
self.assertTrue(ret)
p = web.HTMLParser('./tests/data/clean.cleaned.html')
self.assertEqual(p.get_meta(), {})
self.assertTrue(p.remove_all())
os.remove('./tests/data/clean.html')
os.remove('./tests/data/clean.cleaned.html')
os.remove('./tests/data/clean.cleaned.cleaned.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('<title><title><pouet/><meta/></title></title><test/>')
p = web.HTMLParser('./tests/data/clean.html')
self.assertTrue(p.remove_all())
with open('./tests/data/clean.cleaned.html', 'r') as f:
self.assertEqual(f.read(), '<title></title><test/>')
os.remove('./tests/data/clean.html')
os.remove('./tests/data/clean.cleaned.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('<test><title>Some<b>metadata</b><br/></title></test>')
p = web.HTMLParser('./tests/data/clean.html')
self.assertTrue(p.remove_all())
with open('./tests/data/clean.cleaned.html', 'r') as f:
self.assertEqual(f.read(), '<test><title></title></test>')
os.remove('./tests/data/clean.html')
os.remove('./tests/data/clean.cleaned.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('<meta><meta/><!----><!-- test--></meta>')
p = web.HTMLParser('./tests/data/clean.html')
self.assertTrue(p.remove_all())
with open('./tests/data/clean.cleaned.html', 'r') as f:
self.assertEqual(f.read(), '')
os.remove('./tests/data/clean.html')
os.remove('./tests/data/clean.cleaned.html')
def test_html(self):
shutil.copy('./tests/data/dirty.html', './tests/data/clean.html')
with open('./tests/data/clean.html', 'a') as f:
f.write('<open>but not</closed>')
with self.assertRaises(ValueError):
web.HTMLParser('./tests/data/clean.html')
os.remove('./tests/data/clean.html')
# Yes, we're able to deal with malformed html :/
shutil.copy('./tests/data/dirty.html', './tests/data/clean.html')
with open('./tests/data/clean.html', 'a') as f:
f.write('<meta name=\'this" is="weird"/>')
p = web.HTMLParser('./tests/data/clean.html')
self.assertTrue(p.remove_all())
p = web.HTMLParser('./tests/data/clean.cleaned.html')
self.assertEqual(p.get_meta(), {})
os.remove('./tests/data/clean.html')
os.remove('./tests/data/clean.cleaned.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('</meta>')
with self.assertRaises(ValueError):
web.HTMLParser('./tests/data/clean.html')
os.remove('./tests/data/clean.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('<meta><a>test</a><set/></meta><title></title><meta>')
p = web.HTMLParser('./tests/data/clean.html')
with self.assertRaises(ValueError):
p.get_meta()
p = web.HTMLParser('./tests/data/clean.html')
with self.assertRaises(ValueError):
p.remove_all()
os.remove('./tests/data/clean.html')
with open('./tests/data/clean.html', 'w') as f:
f.write('<doctitle><br/></doctitle><br/><notclosed>')
p = web.HTMLParser('./tests/data/clean.html')
with self.assertRaises(ValueError):
p.get_meta()
p = web.HTMLParser('./tests/data/clean.html')
with self.assertRaises(ValueError):
p.remove_all()
os.remove('./tests/data/clean.html')
