adulau/DomainClassifier
1
0
Fork 0
mirror of https://github.com/adulau/DomainClassifier.git synced 2024-11-07 11:56:25 +00:00
Code Issues Projects Releases Packages Wiki Activity

potentialdomain() is now called at the init

Browse source 
To avoid confusion the method name domain() has
been renamed to potentialdomain().
This commit is contained in:
Alexandre Dulaunoy 2014-08-22 08:29:59 +02:00
parent b32ff4a776
commit 80dc03f59c
2 changed files with 6 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
DomainClassifier/domainclassifier.py
View file

@ -30,6 +30,7 @@ class Extract:
self.presolver.lifetime = 1.0 self.presolver.lifetime = 1.0
self.bgprankingserver = 'pdns.circl.lu' self.bgprankingserver = 'pdns.circl.lu'
self.vdomain = [] self.vdomain = []
self.domain = self.potentialdomain()
"""__origin is a private function to the ASN lookup for an IP address via """__origin is a private function to the ASN lookup for an IP address via
the Team Cymru DNS interface. ipadd is a string contain the IP address in a the Team Cymru DNS interface. ipadd is a string contain the IP address in a
@ -65,7 +66,7 @@ class Extract:
s.close() s.close()
if len(r) > 0: if len(r) > 0:
try: rr = r.split("\n")[1].split(",") try: rr = r.split("\n")[1].split(",")
except IndexError: return None except IndexError: return None
if len(rr) > 1: if len(rr) > 1:
rank = rr[1] rank = rr[1]
return float(rank) return float(rank)
@ -74,12 +75,12 @@ class Extract:
else: else:
return None return None
"""domain method extracts potential domains matching any """potentialdomain method extracts potential domains matching any
string that is a serie of string with maximun 63 character separated by a string that is a serie of string with maximun 63 character separated by a
dot. The method used the rawtext defined at the instantiation of the class. dot. The method used the rawtext defined at the instantiation of the class.
This return a list of a potential domain.""" This return a list of a potential domain."""
def domain(self): def potentialdomain(self):
self.domain = [] self.domain = []
domain = re.compile(r'\b([a-zA-Z\d-]{,63}(\.[a-zA-Z\d-]{,63})+)\b') domain = re.compile(r'\b([a-zA-Z\d-]{,63}(\.[a-zA-Z\d-]{,63})+)\b')
for x in domain.findall(self.rawtext): for x in domain.findall(self.rawtext):

4
DomainClassifier/test.py
View file

@ -1,7 +1,7 @@
import domainclassifier import domainclassifier
c = domainclassifier.Extract( rawtext = "www.xxx.com this is a text with a domain called test@foo.lu another test abc.lu something a.b.c.d.e end of 1.2.3.4 foo.be www.belnet.be http://www.cert.be/ www.public.lu www.allo.lu quuxtest www.eurodns.com something-broken-www.google.com www.google.lu trailing test www.facebook.com www.nic.ru www.youporn.com 8.8.8.8 201.1.1.1") c = domainclassifier.Extract( rawtext = "www.xxx.com this is a text with a domain called test@foo.lu another test abc.lu something a.b.c.d.e end of 1.2.3.4 foo.be www.belnet.be http://www.cert.be/ www.public.lu www.allo.lu quuxtest www.eurodns.com something-broken-www.google.com www.google.lu trailing test www.facebook.com www.nic.ru www.youporn.com 8.8.8.8 201.1.1.1", nameservers = ['149.13.33.69'])
print c.domain() #print c.potentialdomain()
print c.validdomain(extended=True) print c.validdomain(extended=True)
print "US:" print "US:"
print c.localizedomain(cc='US') print c.localizedomain(cc='US')