def test_match_keyword(self, mock_goodie):
fake = Faker()
mocked_keyword = fake.domain_word()
# Mock Goodies response
mock_goodie.return_value = [{'good_keyword': mocked_keyword}]
info("Created mock Goodie with keyword: {}".format(mocked_keyword))
domain = "{}x.com".format(mocked_keyword)
info("Requested domain - {}".format(domain))
l = match_keyword(domain)
assert_type(l, tuple, "Check if proper tuple is returned")
assert_true(l[0], "Check if keyword matches domain")
assert_equal(l[1], mocked_keyword,
"Check if returned keyword is equal to mocked one")
def test_not_match_keyword(self, mock_goodie):
fake = Faker()
mocked_keyword = fake.domain_word()
# Mock Goodies response
mock_goodie.return_value = [{'good_keyword': mocked_keyword}]
info("Created mock Goodie with keyword: {}".format(mocked_keyword))
while 1:
mocked_domain = fake.domain_name()
if mocked_keyword in mocked_domain:
continue
else:
break
info("Requested domain - {}".format(mocked_domain))
l = match_keyword(mocked_domain)
assert_type(l, tuple, "Check if proper tuple is returned")
assert_false(l[0], "Check if keyword does not match domain")
assert_none(l[1], "Check if returned keyword is equal to None")
def get_keyword_details(url_body):
try:
jsonschema.validate(url_body, details_url_schema)
except jsonschema.exceptions.ValidationError as exc:
raise BadRequest(exc.message)
domain = url_to_domain(url_body.get('url'))
_, keyword = keywords.match_keyword(domain)
if not keyword:
return _no_data_response()
response_text = {
"details": {
"matched_keyword": keyword
}
}
return Response(json.dumps(
response_text,
default=_default_json_model
), 200, mimetype="application/json")
def create_baddie(domain):
_, ip_id = add_ip(domain)
_, crt_id = add_cert(domain)
good_keywords = [k['good_keyword'] for k in Goodies.get_all_goodies()]
domain_phrases = domain.split('.')
_, _, lev_matched_keyword = lev.levenstein_check(good_keywords,
domain_phrases)
min_lev_distance = 0
lev_distance = 0
if lev_matched_keyword:
for phrase in domain_phrases:
lev_distance = lev.calculate_levenstein(lev_matched_keyword,
phrase)
if 3 > min_lev_distance > lev_distance:
min_lev_distance = lev_distance
if not lev_matched_keyword:
lev_matched_keyword = ''
_, contained_matched_keyword = match_keyword(domain)
if not contained_matched_keyword:
contained_matched_keyword = ''
entropy = ent.get_entropy(domain)
return add_baddie(domain, ip_id[1], crt_id[1], lev_distance,
lev_matched_keyword, contained_matched_keyword, entropy)
def verify_keyword_match(domain):
verdict, _ = match_keyword(domain)
return verdict