def setUp(self):
test_dir = os.path.abspath(os.path.join(__file__, ".."))
sample = os.path.join(test_dir, "query_result.html")
with file(sample, "r") as _fp:
self.contents = _fp.read().decode("utf-8")
self.parser = FJUDHTMLParser()
class HTMLParserTest(unittest.TestCase):
def setUp(self):
test_dir = os.path.abspath(os.path.join(__file__, ".."))
sample = os.path.join(test_dir, "query_result.html")
with file(sample, "r") as _fp:
self.contents = _fp.read().decode("utf-8")
self.parser = FJUDHTMLParser()
def test_parse_sn_and_url(self):
self.parser.feed(self.contents)
urls = self.parser.get_url_dict()
self.assertEqual(20, len(urls))
self.assertTrue(u"104,台抗,661" in urls)
self.assertTrue(u"104,台上,2308" in urls)
def test_next_page_bad_input(self):
self.parser.feed('<img src="python-logo.png" alt="The Python logo">')
self.assertFalse(self.parser.has_next_page())
self.assertEqual("", self.parser.get_next_page_url())
def test_next_page_trivial(self):
self.parser.feed(ur'<a href="http://foo">下一頁</a>')
self.assertTrue(self.parser.has_next_page())
self.assertEqual("http://foo", self.parser.get_next_page_url())
def test_next_page_standard(self):
self.parser.feed(self.contents)
self.assertTrue(self.parser.has_next_page())
self.assertNotEqual("", self.parser.get_next_page_url())
