def test_extract_link(self):
html = decode_url('http://www.zhihu.com')
links = extract_link(html)
self.assertEqual(links, [])
html = decode_url('http://www.zhihu.com/topic/19554298')
links = extract_link(html)
self.assertTrue(len(links) > 5)
def test_rank_page(self):
hot_page = decode_url('http://www.zhihu.com/question/28676107')
cold_page = decode_url('http://www.zhihu.com/question/19555512')
self.assertTrue(rank_page(hot_page) > rank_page(cold_page))
def test_extract_title(self):
html = decode_url('http://www.zhihu.com')
title = extract_title(html)
self.assertEqual(title, '知乎')
def test_decode_url(self):
html = decode_url('http://www.zhihu.com')
self.assertTrue('知乎' in html[:1000])
# Unit test with Chinese characteristics
with self.assertRaises(urllib.error.URLError):
decode_url('https://www.google.com')
