async def test_before_request_reject_request_to_path_not_matching_filter_in_whitelist(
self):
filter = FilterRequestFromURL(allowed_urls="/allowed")
with self.assertRaises(RejectRequest):
await filter.before_request(
Entry.create("http://example.com/test/index.html"))
async def test_before_request_reject_request_to_host_not_matching_filter_in_whitelist(
self):
filter = FilterRequestFromURL(allowed_urls="example.com")
with self.assertRaises(RejectRequest):
await filter.before_request(Entry.create("http://www.example.com/")
)
async def test_before_request_reject_request_to_path_and_host_matching_filter_in_blacklist(
self):
filter = FilterRequestFromURL(forbidden_urls="example.com/forbidden")
with self.assertRaises(RejectRequest):
await filter.before_request(
Entry.create("http://example.com/forbidden/index.html"))
async def test_before_request_allow_request_to_path_or_host_not_matching_filter_in_blacklist(
self):
filter = FilterRequestFromURL(forbidden_urls="example.com/forbidden")
await filter.before_request(
Entry.create("http://example.ca/forbidden/index.html"))
await filter.before_request(
Entry.create("http://example.com/test/index.html"))
def setup_hammertime_heuristics(hammertime,
*,
user_agent=default_user_agent,
vhost=None):
# TODO Make sure rejecting 404 does not conflict with tomcat fake 404 detection.
global heuristics_with_child
dead_host_detection = DeadHostDetection(threshold=200)
detect_soft_404 = DetectSoft404(distance_threshold=6)
follow_redirects = FollowRedirects()
heuristics_with_child = [
RejectCatchAllRedirect(), follow_redirects,
RejectIgnoredQuery()
]
hosts = (vhost,
conf.target_host) if vhost is not None else conf.target_host
global_heuristics = [
RejectStatusCode({404, 406, 502, 503}),
DynamicTimeout(1.0, 5),
RedirectLimiter(),
FilterRequestFromURL(allowed_urls=hosts),
IgnoreLargeBody(initial_limit=initial_limit)
]
heuristics = [
StripTag('input'),
StripTag('script'), detect_soft_404,
RejectSoft404(),
MatchString(),
DetectBehaviorChange(buffer_size=100),
LogBehaviorChange()
]
# Dead host detection must be first to make sure there is no skipped after_headers
hammertime.heuristics.add(dead_host_detection)
hammertime.heuristics.add_multiple(global_heuristics)
# Make sure follow redirect comes in before soft404
hammertime.heuristics.add_multiple(heuristics_with_child)
hammertime.heuristics.add_multiple(heuristics)
for heuristic in heuristics_with_child:
heuristic.child_heuristics.add_multiple(global_heuristics)
detect_soft_404.child_heuristics.add(StripTag('input'))
detect_soft_404.child_heuristics.add(StripTag('script'))
detect_soft_404.child_heuristics.add(dead_host_detection)
detect_soft_404.child_heuristics.add(follow_redirects)
add_http_header(hammertime, "User-Agent", user_agent)
add_http_header(hammertime, "Host",
vhost if vhost is not None else conf.target_host)
async def test_before_request_accept_list_of_url_for_whitelist(self):
filter = FilterRequestFromURL(allowed_urls=[
"example.com", "www.example.com", "test.example.com"
])
good_urls = [
"http://example.com/", "https://www.example.com/index.php",
"http://test.example.com/index.html"
]
bad_urls = [
"http://abc.example.com/", "https://example.ca/",
"http://www.example.com.net/"
]
for url in bad_urls:
with self.assertRaises(RejectRequest):
await filter.before_request(Entry.create(url))
for url in good_urls:
await filter.before_request(Entry.create(url))
async def test_before_request_allow_request_to_path_and_host_matching_filter_in_whitelist(
self):
filter = FilterRequestFromURL(allowed_urls="example.com/allowed")
await filter.before_request(
Entry.create("http://example.com/allowed/index.html"))
def test_constructor_raise_value_error_if_both_domain_list_are_set(self):
with self.assertRaises(ValueError):
FilterRequestFromURL(allowed_urls="example.com",
forbidden_urls="test.com")
def test_constructor_raise_value_error_if_both_domain_list_are_none(self):
with self.assertRaises(ValueError):
FilterRequestFromURL(allowed_urls=None, forbidden_urls=None)
async def test_path_matching_only_apply_to_full_directory_name(self):
filter = FilterRequestFromURL(allowed_urls="example.com/allowed")
with self.assertRaises(RejectRequest):
await filter.before_request(
Entry.create("http://example.com/allowed-test"))
def setup_hammertime_heuristics(hammertime,
*,
user_agent=default_user_agent,
vhost=None,
confirmation_factor=1,
har_output_dir=None):
global heuristics_with_child
dead_host_detection = DeadHostDetection(threshold=200)
detect_soft_404 = DetectSoft404(distance_threshold=6,
confirmation_factor=confirmation_factor)
follow_redirects = FollowRedirects()
heuristics_with_child = [
RejectCatchAllRedirect(), follow_redirects,
RejectIgnoredQuery()
]
hosts = (vhost,
conf.target_host) if vhost is not None else conf.target_host
init_heuristics = [
SetHeader("User-Agent", user_agent),
SetHeader("Host", vhost if vhost is not None else conf.target_host),
ContentHashSampling(),
ContentSampling(),
ContentSimhashSampling(), dead_host_detection,
RejectStatusCode({503, 508}, exception_class=StopRequest),
StripTag('input'),
StripTag('script')
]
global_heuristics = [
RejectStatusCode({404, 406, 502}),
RejectWebApplicationFirewall(),
DynamicTimeout(1.0, 5),
RedirectLimiter(),
FilterRequestFromURL(allowed_urls=hosts),
IgnoreLargeBody(initial_limit=initial_limit)
]
# Dead host detection must be first to make sure there is no skipped after_headers
hammertime.heuristics.add_multiple(init_heuristics)
# General
hammertime.heuristics.add_multiple(global_heuristics)
hammertime.heuristics.add_multiple(heuristics_with_child)
hammertime.heuristics.add_multiple([
detect_soft_404,
MatchString(),
ValidateEntry(),
DetectBehaviorChange(buffer_size=100),
LogBehaviorChange(),
ValidateEntry(),
])
detect_soft_404.child_heuristics.add_multiple(init_heuristics)
detect_soft_404.child_heuristics.add_multiple(heuristics_with_child)
for heuristic in heuristics_with_child:
heuristic.child_heuristics.add_multiple(init_heuristics)
heuristic.child_heuristics.add_multiple(global_heuristics)
if har_output_dir is not None:
from tachyon.har import StoreHAR, FileWriter
hammertime.heuristics.add(StoreHAR(writer=FileWriter(har_output_dir)))
