我已经通读了类似的主题,但我仍然不确定自己做错了什么。我收到错误,未定义全局名称"parseLog"。此外,我一直在摸索如何在这里正确地格式化代码,但在我的编辑器中,所有内容都正确地缩进了,只是对在这里这样做感到恼火。
import urllib2
import re
import json
class parseLog:
def __init__(self):
''' Get access log location and pattern(Common Log Format)'''
self.apacheLog = 'https://raw.githubusercontent.com/access.log'
self.data = urllib2.urlopen(self.apacheLog)
self.parts = [
r'(?P<host>S+)',
r'S+',
r'(?P<user>S+)',
r'[(?P<time>.+)]',
r'"(?P<request>.+)"',
r'(?P<status>[0-9]+)',
r'(?P<size>S+)',
r'"(?P<referer>.*)"',
r'"(?P<agent>.*)"',
]
self.pat = re.compile(r's+'.join(self.parts)+r's*Z')
def rescheck(result):
'''Check for absent refer page'''
if result["referer"] == "-":
result["referer"] = None
return
def getIPinfo(IP,result):
'''Get lat,long,org,and ISP using IP address from log record'''
apiURL = 'http://ip-api.com/json/'+IP
getResp = urllib2.urlopen(apiURL)
jsonResp = json.load(getResp)
result["lat"] = jsonResp['lat']
result["long"] = jsonResp['lon']
result["org"] = jsonResp['org']
result["ISPname"] = jsonResp['isp']
finalKeys = ["time","request","referer","host","org","lat","long","ISPname"]
finalDict = {x: result[x] for x in finalKeys if x in result}
print finalDict
return finalDict
def main():
with open('C:UsersBrandonDownloadsLogCopy1.txt','a') as f:
for line in parseLog.data:
match = parseLog.pat.match(line)
result = match.groupdict()
theIP = result["host"]
print theIP
parseLog.rescheck(result)
dictToWrite = parseLog.getIPinfo(theIP,result)
f.write(str(dictToWrite))
#print str(dictToWrite)
main()
parseLog是一个类。为了访问python中类的数据成员或方法(除非是静态的),您首先需要创建该类的实例:
pl = parseLog()
然后更新您的代码:
def main():
pl = parseLog()
with open('C:UsersBrandonDownloadsLogCopy1.txt','a') as f:
for line in pl.data:
match = pl.pat.match(line)
result = match.groupdict()
theIP = result["host"]
print theIP
rescheck(result)
dictToWrite = getIPinfo(theIP,result)
f.write(str(dictToWrite))