思路
使用正则表达式处理: 使用正则提取对应内容 每段数据转换为对应格式 精简代码,异常处理,代码效率检查
import datetime
import re
logline = '''183.60.212.153 - - [19/Feb/2013:10:23:29 +0800] \
"GET /o2o/media.html?menu=3 HTTP/1.1" 200 16691 "-" \
"Mozilla/5.0 (compatible; EasouSpider; +http://www.easou.com/search/spider.html)"'''
# 使用正则表达式的命名分组,可以直接根据分组名和对应匹配字段
# 进行对应生成新字典
def log_clean(line:str):
pattern = '''(?P<remote>([\d\.]{7,})) - - \[(?P<time>[^\[\]]+)\] \"(?P<request>[^"]+)\" (?P<status>\d{3}) (?P<size>\d+) \"-\" \"(?P<useragent>[^"]+)\"\s?'''
regex = re.compile(pattern)
matcher = regex.fullmatch(line)
if matcher: # None时,异常处理
return { k:operations.get(k,lambda x:x)(v) for k,v in matcher.groupdict().items()}
operations = {
'time':lambda time: datetime.datetime.strptime(time, '%d/%b/%Y:%H:%M:%S %z'),
'request': lambda request: dict(zip(('method','url','protocol'),request.split())),
'status': int,
'size': int
}
print(log_clean(logline))
