def __init__(self, tid = 0):
threading.Thread.__init__(self)
self._tid = tid
self._tld = TLD()
self._ssdb = MySSDB(SSDBHOST, SSDBPORT)
class DomainProcessor(threading.Thread):
_tid = 0
_ssdb = None
ThreadStartTime = time.time()
ThreadCanExit = False
ThreadTimeOut = 60 * 2
DomainsProcessed = 0
DomainsStored = 0
_UserAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.110 Safari/537.36'
_tld = None # Top Level Domain parser form Zeander
_BlacklistFileModifyTime = 0
_BlacklistFileName = 'blacklist.txt'
TLDUserPartRepeatMax = 200 * 2
TLDUserPartCacheMaxLen = 2000
_TLDUserPartCache = {}
InternalBlackListMaxLen = 2000
ExternalBlacklistMaxLen = 1000
_InternalBlacklist = []
_ExternalBlacklist = []
def __init__(self, tid = 0):
threading.Thread.__init__(self)
self._tid = tid
self._tld = TLD()
self._ssdb = MySSDB(SSDBHOST, SSDBPORT)
def run(self):
while True:
domain = HTTPSQSQueue.get(DOMAINQUEUE02).lower()
if '' == domain and None == time.sleep(1): continue
if self.isDomainInBlacklist(domain):
C.Info('Domain in black list: %s' % domain, C.DEBUG)
continue
self.f**k(domain)
self.refreshBlacklist(domain)
self.monitor()
def f**k(self, domain):
global DomainsProcessed, DomainsStored
DomainsProcessed = DomainsProcessed + 1
if not self._ssdb.isDomainInDB('hdm', domain):
self._ssdb.setHItem('hdm', MD5(domain), domain)
HTTPSQSQueue.put(DOMAINQUEUE01, domain)
DomainsStored = DomainsStored + 1
def monitor(self):
if os.path.exists('debug.dump'):self.dump()
def refreshBlacklist(self, domain):
self.refreshInternalBlacklist(domain)
self.refreshExternalBlacklist()
def isDomainInBlacklist(self, domain):
return self.isDomainInExternalBlacklist(domain) or self.isDomainInInternalBlacklist(domain)
def isDomainInInternalBlacklist(self, domain):
domain_user_part = self._tld.getTLD(domain)[0]
if not '' == domain_user_part:
for black in self._InternalBlacklist:
if domain_user_part == black: return True
return False
def isDomainInExternalBlacklist(self, domain):
for black in self._ExternalBlacklist:
if domain.endswith(black): return True
return False
def refreshInternalBlacklist(self, domain):
'''
www.chinaz.com.cn -> chinaz -> CacheDictionary
'''
black = self._tld.getTLD(domain)[0]
if '' == black : return
if self._TLDUserPartCache.has_key(black):
self._TLDUserPartCache[black] = self._TLDUserPartCache[black] + 1
if self._TLDUserPartCache[black] > self.TLDUserPartRepeatMax/2 and not black in self._InternalBlacklist:
self._InternalBlacklist.append(black)
else:
self._TLDUserPartCache[black] = 1
if len(self._TLDUserPartCache) > self.TLDUserPartCacheMaxLen:
tempList = sorted(self._TLDUserPartCache, key=self._TLDUserPartCache.get)
for i in range(0, len(tempList)/2):
self._TLDUserPartCache.pop(tempList[i])
tempList = None
if len(self._InternalBlacklist) > self.InternalBlackListMaxLen:
self.saveInternalBlacklist()
def refreshExternalBlacklist(self):
if (random.randrange(1,11) % 3 == 0) :return
if not os.path.exists(self._BlacklistFileName):return
BlacklistFileModifyTime = os.stat(self._BlacklistFileName).st_mtime
if self._BlacklistFileModifyTime == BlacklistFileModifyTime:
return
try:
f = open(self._BlacklistFileName)
lines = f.readlines()
blacklists = []
for line in lines:
domain = line.strip().replace('\n', '').replace('\r', '')
if len(domain) > 0:blacklists.append(domain)
self._ExternalBlacklist = blacklists[:]
blacklists = None
self._BlacklistFileModifyTime = BlacklistFileModifyTime
C.Info('Get %2d domains in blacklist' % len(self._ExternalBlacklist), C.INFO)
except Exception, e:
C.Info(str(e), C.ERROR)
finally: