def test_get_parser_allowed(self):
self.parser = resources.get_parser_for_html(VALID_PAGE_URL)
content = self.parser.get_content()
self.assertIn("Cogito ergo sum", content)
with self.assertRaises(resources.URLNotParseableException):
self.parser = resources.get_parser_for_html(BANNED_PAGE_URL)
content = self.parser.get_content()
self.assertNotIn("accessed", content)
def test_get_parser_allowed(self):
self.parser = resources.get_parser_for_html(VALID_PAGE_URL)
content = self.parser.get_content()
self.assertIn('Cogito ergo sum', content)
with self.assertRaises(resources.URLNotParseableException):
self.parser = resources.get_parser_for_html(BANNED_PAGE_URL)
content = self.parser.get_content()
self.assertNotIn('accessed', content)
def test_unicode_page(self):
self.parser = resources.get_parser_for_html(UNICODE_PAGE_URL)
content = self.parser.get_content()
self.assertIn("Paradox", content)
title = self.parser.get_title()
self.assertIn("Quoted string", title)
def test_bad_urls(self):
for url in ['http://', 'invalid.null', '//invalid.null', '//',
'invalid', '?test=1', 'invalid?test=1']:
with self.assertRaises(resources.URLNotParseableException):
self.parser = resources.get_parser_for_html(url)
content = self.parser.get_content()
self.assertNotIn('impsum', content)
def test_unicode_page(self):
self.parser = resources.get_parser_for_html(UNICODE_PAGE_URL)
content = self.parser.get_content()
self.assertIn('Paradox', content)
title = self.parser.get_title()
self.assertIn('Quoted string', title)
def test_bad_urls(self):
for url in [
'http://', 'invalid.null', '//invalid.null', '//', 'invalid',
'?test=1', 'invalid?test=1'
]:
with self.assertRaises(resources.URLNotParseableException):
self.parser = resources.get_parser_for_html(url)
content = self.parser.get_content()
self.assertNotIn('impsum', content)
def test_bad_urls(self):
for url in ["http://", "invalid.null", "//invalid.null", "//", "invalid", "?test=1", "invalid?test=1"]:
with self.assertRaises(resources.URLNotParseableException):
self.parser = resources.get_parser_for_html(url)
content = self.parser.get_content()
self.assertNotIn("impsum", content)