python日志解析

Python字典的setdefault()方法

setdefault(key[, default])

If key is in the dictionary, return its value. If not, insert key with a value of default and return default. default defaults to None.

如果键在字典中，返回这个键所对应的值。如果键不在字典中，向字典 中插入这个键，并且以default为这个键的值，并返回 default。default的默认值为None

 

>>> dict={}
>>> dict['key']='a'
>>> dict
{'key': 'a'}
>>> dict.setdefault('key', 'b')  # 键key存在，故返回简直a.
'a'
>>> dict
{'key': 'a'}
>>> dict.setdefault('key0', 'b') # 键key0不存在，故插入此键，并以b为键值.
'b'
>>> dict
{'key0': 'b', 'key': 'a'}

日志分析

利用字典分析apache访问日志的脚本，以提取IP地址，字节数和状态

 

#!/usr/bin/env python
"""
USAGE:
apache_log.py some_log_file

This script takes one command line argument:the name of a log file to parse.It then parses the lof file and generates a report which associates remote hosts with number of bytes transferred to them.
"""

import sys

def dictify_logline(line):
        split_line = line.split()
        return {'remote_host': split_line[0],'status':split_line[8],'bytes_sent':split_line[9]}

def generate_log_report(logfile):
        report_dict = {}
        for line in logfile:
                line_dict = dictify_logline(line)
                print line_dict
                try:
                        bytes_sent = int(line_dict['bytes_sent'])
                except ValueError:
                        continue
                report_dict.setdefault(line_dict['remote_host'],[]).append(bytes_sent)
        return report_dict

if __name__ == "__main__":
        if not len(sys.argv) > 1:
                print __doc__
                sys.exit(1)
        infile_name = sys.argv[1]
        try:
                infile = open(infile_name,'r')
        except ValueError:
                print "You must specify a valid file to parse"
                sys.exit(1)
        log_report = generate_log_report(infile)
        print log_report
        infile.close()