\"[^\"]*\""""
#以"开始, 除双引号以外的任意字符 防止匹配上下个""项目(也可以使用非贪婪匹配*?),以"结束
#"Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"'
userAgentP = r"""?P\"[^\"]*\""""
#以(开始, 除双引号以外的任意字符 防止匹配上下个()项目(也可以使用非贪婪匹配*?),以"结束
#(compatible; Googlebot/2.1; +http://www.google.com/bot.html)"'
userSystems = re.compile(r'\([^\(\)]*\)')
#以"开始,除双引号以外的任意字符防止匹配上下个""项目(也可以使用非贪婪匹配*?),以"结束
userlius = re.compile(r'[^\)]*\"')
#原理:主要通过空格和-来区分各不同项目,各项目内部写各自的匹配表达式
nginxLogPattern = re.compile(r"(%s)\ -\ -\ (%s)\ (%s)\ (%s)\ (%s)\ (%s)\ (%s)" %(ipP, timeP, requestP, statusP, bodyBytesSentP, referP, userAgentP), re.VERBOSE)
#数据库连接信息
conn=MySQLdb.connect(host='192.168.1.22',user='test',passwd='pass',port=3306,db='python')
cur=conn.cursor()
sql = "INSERT INTO python.test VALUES(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
while True:
line = logfile.readline()
if not line:break
matchs = nginxLogPattern.match(line)
if matchs != None:
allGroup = matchs.groups()
ip = allGroup[0]
time = allGroup[1]
request = allGroup[2]
status = allGroup[3]
bodyBytesSent = allGroup[4]
refer = allGroup[5]
userAgent = allGroup[6]
Time = time.replace('T',' ')[1:-7]
if len(userAgent) > 20:
userinfo = userAgent.split(' ')
userkel = userinfo[0]
try:
usersystem = userSystems.findall(userAgent)
usersystem = usersystem[0]
print usersystem
userliu = userlius.findall(userAgent)
value = [ip,Time,request,status,bodyBytesSent,refer,userkel,usersystem,userliu[1]]
conn.commit()
print value
except IndexError:
userinfo = userAgent
value = [ip,Time,request,status,bodyBytesSent,refer,userinfo,"",""]
else:
useraa = userAgent
value = [ip,Time,request,status,bodyBytesSent,refer,useraa,"",""]
try:
result = cur.execute(sql,value)
#conn.commit()
print result
except MySQLdb.Error,e:
print "Mysql Error %d: %s" % (e.args[0], e.args[1])
conn.commit()
conn.close()
四、存入数据库后数据是如下图:
本条技术文章来源于互联网,如果无意侵犯您的权益请点击此处反馈版权投诉