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

Better error catching

Browse source 
- Timeout of DNS reduce to 1 sec
 - Socket exception catched
 - Ranking default value is now 1.0
This commit is contained in:
Alexandre Dulaunoy 2012-03-02 21:12:39 +01:00
parent 738060ab57
commit 0be08a31c6
1 changed files with 26 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
DomainClassifier/domainclassifier.py
View file

@ -27,6 +27,7 @@ class Extract:
self.rawtext = rawtext self.rawtext = rawtext
self.presolver = dns.resolver.Resolver() self.presolver = dns.resolver.Resolver()
self.presolver.nameservers = ['149.13.33.69'] self.presolver.nameservers = ['149.13.33.69']
self.presolver.lifetime = 1.0
self.bgprankingserver = 'pdns.circl.lu' self.bgprankingserver = 'pdns.circl.lu'
self.vdomain = [] self.vdomain = []
@ -38,7 +39,9 @@ class Extract:
if ipaddr: if ipaddr:
clook = IPy.IP(str(ipaddr)).reverseName().replace('.in-addr.arpa.','.origin.asn.cymru.com') clook = IPy.IP(str(ipaddr)).reverseName().replace('.in-addr.arpa.','.origin.asn.cymru.com')
a = self.presolver.query(clook, 'TXT') try: a = self.presolver.query(clook, 'TXT')
except dns.resolver.NXDOMAIN: return None
except dns.exception.Timeout: return None
if a: if a:
x = str(a[0]).split("|") x = str(a[0]).split("|")
# why so many spaces? # why so many spaces?
@ -61,10 +64,15 @@ class Extract:
break break
s.close() s.close()
if len(r) > 0: if len(r) > 0:
rank = r.split("\n")[1].split(",")[1] try: rr = r.split("\n")[1].split(",")
except IndexError: return None
if len(rr) > 1:
rank = rr[1]
return float(rank) return float(rank)
else: else:
return None return None
else:
return None
"""domain method extracts potential domains matching any """domain 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
@ -136,16 +144,21 @@ class Extract:
if self.validdomain: if self.validdomain:
for dom in self.validdomain: for dom in self.validdomain:
rank = None rank = None
asn = None
if dom[1] == 'A': if dom[1] == 'A':
ip = dom[2] ip = dom[2]
asn = self.__origin(ipaddr=dom[2])[0] o = self.__origin(ipaddr=dom[2])
if o:
asn = o[0]
rank = self.__bgpranking(asn) rank = self.__bgpranking(asn)
t = (rank, dom[0]) t = (rank, dom[0])
self.rankdom.append(t) self.rankdom.append(t)
elif dom[1] == 'CNAME': elif dom[1] == 'CNAME':
cname = str(dom[2]) cname = str(dom[2])
ip = socket.gethostbyname(cname) try: ip = socket.gethostbyname(cname)
asn = self.__origin(ipaddr=ip)[0] except: continue
try: asn = self.__origin(ipaddr=ip)[0]
except TypeError: continue
rank = self.__bgpranking(asn) rank = self.__bgpranking(asn)
t = (rank, dom[0]) t = (rank, dom[0])
self.rankdom.append(t) self.rankdom.append(t)