python实现日志的查询、统计代码,Python代码库,德仔网

代码语言

代码分类

【Python】 python实现日志的查询、统计

作者:水熊宝宝 / 发布于2013/8/5/ 642

简单的日志统计是不需要使用重量级的Hadoop，我用python实现了日志的统计。原理是用fabric登录到远程linux，组合使用grep、uniq、sort、awk对日志进行操作，可以根据正则表达式指定规则抽取符合规则的日志，做查询，计数，分类统计。注意：要安装fabric库


	#encoding=utf-8

	from fabric.api import run,env,local,cd
	from fabric.tasks import execute,abort
	from fabric.contrib.console import confirm
	import logging

	logging.basicConfig(format='[%(levelname)s]: %(message)s', level=logging.DEBUG)
	logger = logging.getLogger(__name__)
	logging.getLogger('paramiko.transport').setLevel(logging.ERROR)
	logger.setLevel(logging.DEBUG)

	EXECUTE_RESULT = {}

	def hosts(hostarr):
	 '''
	 set hosts
	 hostarr:[(hostname,password),(hostname,password)...]
	 '''
	 env.hosts = [x[0] for x in hostarr]
	 env.passwords = dict(x for x in hostarr)

	def query(expression,hostname,logfile,unique=True,sort=None,output=None,pattern=None,path=None):
	 '''
	 expression: regex rule
	 hostname: hostname as specified hosts()
	 logfile: log file name, wildcard supported, eg:*.log
	 unique: whether result is unique
	 sort: 1(ASC) or -1(DESC) ,default None
	 output:None or file name, default None imply print stream
	 pattern: group pattern , default None imply '1'
	 path: cd to path before execution
	 '''

	 if not path:
	 path = r'.'
	 cmd_str = generate_cmd(expression,logfile,unique,sort,output,pattern)
	 execute(executor,hostname,cmd_str,path,host=hostname)
	 result = EXECUTE_RESULT[hostname]
	 return result

	def aggregate(expression,hostname,logfile,output=None,pattern=None,path=None):
	 '''
	 expression: regex rule
	 hostname: hostname as specified hosts()
	 logfile: log file name, wildcard supported, eg:*.log
	 output:None or file name, default None imply print stream
	 pattern: group pattern , default None imply '1'
	 path: cd to path before execution
	 '''
	 if not path:
	 path = r'.'
	 cmd_str = generate_cmd(expression,logfile,False,None,output,pattern,True,True)
	 execute(executor,hostname,cmd_str,path,host=hostname)
	 result = EXECUTE_RESULT[hostname]
	 return result

	def count(expression,hostname,logfile,unique=True,sort=None,output=None,pattern=None,path=None):
	 '''
	 expression: regex rule
	 hostname: hostname as specified hosts()
	 logfile: log file name, wildcard supported, eg:*.log
	 unique: whether result is unique
	 sort: 1(ASC) or -1(DESC) ,default None
	 output:None or file name, default None imply print stream
	 pattern: group pattern , default None imply '1'
	 path: cd to path before execution
	 '''

	 if not path:
	 path = r'.'
	 cmd_str = generate_cmd(expression,logfile,unique,sort,output,pattern,True)
	 execute(executor,hostname,cmd_str,path,host=hostname)
	 result = EXECUTE_RESULT[hostname]
	 if result:
	 result = int(result[0])
	 return result


	def executor(hostname,cmd_str,path=None):
	 '''
	 executor , called by execute
	 '''
	 if not path:
	 path = r'.'
	 with cd(path):
	 res = run(cmd_str,quiet=True)
	 logger.debug('Command: %s:%s > %s'%(hostname,path,cmd_str))
	 logger.debug('Command Execute Successful:%s, Failure:%s'%(res.succeeded,res.failed))
	 EXECUTE_RESULT[hostname] = res.splitlines()

	def generate_cmd(expression,logfile,unique=True,sort=None,output=None,pattern=None,count=False,aggregate=False):
	 '''
	 generate command
	 '''
	 if not pattern:
	 pattern = r'\1'

	 if aggregate:
	 aggregate = '''| awk '{a[$1]++}END{for (j in a) print j","a[j]}' '''
	 unique = False
	 sort = False
	 count = False
	 else:
	 aggregate = ''

	 if not unique:
	 unique = ''
	 else:
	 unique = '| uniq'

	 if sort:
	 if sort==1:
	 sort = '| sort'
	 elif sort==-1:
	 sort = '| sort -r'
	 else:
	 sort = ''
	 else:
	 sort = ''

	 if count:
	 count = '| wc -l'
	 else:
	 count = ''

	 if output:
	 output = '>%s'%output
	 else:
	 output = ''

	 cmd_str = '''cat %s | grep "%s" | sed 's/%s/%s/gp' %s %s %s %s %s'''%(logfile,expression,expression,pattern,unique,sort,count,output,aggregate)
	 return cmd_str

评论列表

本站所提供的代码，版权归原作者所有，若有侵犯作者版权，请与我们联系，我们将立即删除或修改。谢谢!
本站所有代码发布及提供者。

试试其它关键字

　日志的查询　

同语言下

可能有用的

水熊宝宝贡献的其它代码(2)