CIRCL
/
lookyloo
mirror of https://github.com/CIRCL/lookyloo
2
0
Fork 0
Code Issues Releases Wiki Activity

chg: Make mypy happy

pull/906/head
Raphaël Vinot 2024-04-08 20:41:23 +02:00
parent e8492cc96f
commit f680c0a11b
1 changed files with 18 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
lookyloo/modules/uwhois.py
View File

@ -40,12 +40,12 @@ class UniversalWhois(AbstractModule):
# old format
_all_ips = hostnode.resolved_ips
for ip in _all_ips:
self.whois(ip)
self.whois(ip, contact_email_only=False)
if hasattr(hostnode, 'cnames'):
cname: str
for cname in hostnode.cnames:
self.whois(cname)
self.whois(hostnode.name)
self.whois(cname, contact_email_only=False)
self.whois(hostnode.name, contact_email_only=False)
def capture_default_trigger(self, crawled_tree: CrawledTree, /, *, force: bool=False, auto_trigger: bool=False) -> None:
'''Run the module on all the nodes up to the final redirect'''
@ -72,11 +72,11 @@ class UniversalWhois(AbstractModule):
...
@overload
def whois(self, query: str, contact_email_only: bool=False) -> str | list[str]:
def whois(self, query: str, contact_email_only: bool) -> str | list[str]:
...
def whois(self, query: str, contact_email_only: bool=False) -> str | list[str]:
EMAIL_REGEX = rb'(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)'
if not self.available:
@ -91,17 +91,22 @@ class UniversalWhois(AbstractModule):
break
bytes_whois += data
#if an abuse-c-Object is found in the whois entry, it will take precedence
# if an abuse-c-Object is found in the whois entry, it will take precedence
abuse_c = re.search(rb'abuse-c:\s+(.*)\s', bytes_whois)
if abuse_c:
abuse_c_query = self.whois(abuse_c.group(1).decode(), contact_email_only)
if contact_email_only:
if abuse_c and abuse_c.lastindex and abuse_c.lastindex > 0: # make sure we have a match and avoid exception on None or missing group 1
# The whois entry has an abuse-c object
_obj_name: str = abuse_c.group(1).decode()
abuse_c_query = self.whois(_obj_name, contact_email_only)
# The object exists
if abuse_c_query and contact_email_only:
# The object exists and we only want the email(s), the response is a list of emails
return abuse_c_query
else:
return bytes_whois.decode() + abuse_c_query
elif abuse_c_query:
# The object exists and we want the full whois entry, contatenate with a new line.
# contact_email_only is False, so the response is a string, ignore the typing warning accordingy
return '\n'.join([bytes_whois.decode(), abuse_c_query]) # type: ignore[list-item]
# We either dont have an abuse-c object or it does not exist
if not contact_email_only:
return bytes_whois.decode()
emails = list(set(re.findall(EMAIL_REGEX, bytes_whois)))
return [e.decode() for e in sorted(emails)]