def analyze_url(uri: str) -> List[str]:
"""
Analyze given URI and get page information by using webXray.
Arg:
uri(str): Any URI that is not analyzed yet.
Return:
dict {"uri": list[str]}: (key: given uri, value: listed domain name of cookies)
"""
parser = ParseURI()
pd = PhantomDriver("--ignore-ssl-errors=true --ssl-protocol=any", "wbxr_logger.js")
output = pd.execute(uri, 25)
if re.match("^FAIL.+", output):
# Probably this isn't needed
return []
else:
try:
parsed_data = json.loads(re.search("(\{.+\})", output).group(1))
except Exception as e:
print(e)
return []
orig_domain = parser.get_domain_pubsuffix_tld(uri)[0]
cookie_domains = map(lambda x: x["domain"], parsed_data["cookies"])
tpcookie_domains = filter(
lambda x: parser.get_domain_pubsuffix_tld(f"http://{x[1:]}")[0]
!= orig_domain,
cookie_domains,
)
tpcookie_domain_names = map(remove_dot, tpcookie_domains)
return list(tpcookie_domain_names)
def __init__(self, dbname):
self.uri_parser = ParseURI()
self.sql_driver = MySQLDriver(dbname)
def __init__(self):
self.uri_parser = ParseURI()
