日志分析

import re
import datetime



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)"'''


pattern = '''(?P<remote>[\d\.]{7,}) - - \[(?P<datetime>[^\[\]]+)\] "(?P<request>[^"]+)" (?P<status>\d+) (?P<size>\d+) "([^"]+)" "(?P<useragent>[^"]+)'''
regex = re.compile(pattern)
ops = {
    'datetime':lambda timestr:datetime.datetime.strptime(timestr,'%d/%b/%Y:%H:%M:%S %z'),
    'status': int,
    'size': int,
    'request':lambda request: dict(zip(('method', 'url', 'protocol'), request.split()))
    }
d = {}
#for k , v in extract(logline).items():
#d[k] = ops[k].get(k, lambda x:x)(v)
#{k:ops[k].get(k, lambda x:x)(v) for k , v in matcher.groupdict().items() }

def extract(line):
    matcher = regex.match(line)
    info ={k:ops.get(k, lambda x:x)(v) for k , v in matcher.groupdict().items()}
    return info