def analyse(self,filename=None):
message = {}
# 调用mailAnalyse中的各个模块，进行分析和返回结果
mail = MailInfo()
mail.analyseMail(filename)
ip = mail.get_ip() # 使用ip进行联网判断
sender = mail.get_sender() # 使用sender进行黑白名单判断
c = mail.get_content() # 使用content进行机器学习的判断
# 判断是否存在于名单中，存在直接返回，否则进行下一步
try:
r = Rule()
judgeResult = r.find(sender)
if judgeResult:
r.content(c)
message['rule'] = r.getInfo()
if judgeResult is False:
return str(message),judgeResult
elif judgeResult is True:
return str(message),judgeResult
except:
message['rule'] = 'wrong'
# 判断是否被网站列为黑名单，正常则进行下一步，由于COOKIE问题，最容易出现问题
try:
judge = Judge()
judgeResult = judge.is_spam(ip)
message['ipInfo'] = judge.get_info()
if not judgeResult:
return str(message),judgeResult
except:
message['ipInfo'] = 'wrong'
# 通过机器学习进行内容的判断
try:
strAttribute = MailAttribute(c).get_attribute()
strAttribute = r.filter(strAttribute)
numAtrribute = AToD().transfer_array(strAttribute)
judgeResult = JudgeContent().judge(numAtrribute)
message['machineJudge'] = str(judgeResult)
except:
message['machineJudge'] = 'wrong'
# 组织信息，以便显示
if judgeResult :
info = 'rule: '+message['rule']+'\r\n'+\
'ipInfo: '+message['ipInfo']+'\r\n'+\
'machineJudge: normal'
else:
info = 'rule: ' + message['rule'] + '\r\n' + \
'ipInfo: ' + message['ipInfo'] + '\r\n' + \
'machineJudge: trash'
return info,judgeResult
def __parse(self, e, leave):
for item in e:
rule = Rule(leave)
for child in item:
if child.tag == 'from':
rule.from_address = child.text
if child.tag == 'to':
rule.to_address = child.text
if child.tag == 'cc':
rule.cc_address = child.text
if child.tag == 'subject':
rule.subject = child.text
if child.tag == 'content':
rule.content = child.text
if leave:
self.__leave.append(rule)
else:
self.__discard.append(rule)
Logger.info(str(rule))