python 超大文件分析map_async seek

2019-04-17 14:53:34 浏览数 (1)

代码语言:javascript复制
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @Time    : 2018/9/16 上午2:00
# @Author  : BrownWang
# @Email   : 277215243@qq.com
# @File    : Analysis.py
# @Software: PyCharm
import re
import heapq
import threading
from multiprocessing import Pool


dic={}
fdic={}
def readconfig():
    with open('./ipdb_cn.txt',mode='r') as f:
        for i in f:
            nn=i.split()
            tn= nn[2].decode('utf-8')
            if dic.has_key(tn):
                dic[tn].add('.'.join(nn[0].split('.')[0:3]))
            else:
                dic[tn]=set()
                dic[tn].add('.'.join(nn[0].split('.')[0:3]))
                fdic[tn]=0


t=threading.Thread(target=readconfig)
t.start()

tf=open('./flowdata.log','r')
tf.seek(0,2)
total=tf.tell()

def run(arg):
    start=arg[0]
    end=arg[1]

    with open('./flowdata.log','r') as f:
        sets=set()
        f.seek(start,0)
        for i in f:
            if f.tell() > end:
                return sets
            if '_ip' in i:
                sets.add(re.findall(r'_ip:s*(d .d .d ).d ',i)[0])
        return sets
p=Pool(8)
runl=[]
for i in range(8):
    runl.append((total*i/8,total*(i 1)/8))
result=p.map_async(run,runl)
p.close()
p.join()
fil=[]
results=result.get()
for i in results:
    fil =i

filset=set(fil)
sumfil=len(filset)
t.join()
for k in dic:
    for i in filset:
        if i in dic[k]:
            fdic[k] =1
ret=[{'n':k,'v':fdic[k]/float(sumfil)*100} for k in fdic]
sortl=heapq.nlargest(len(ret),ret,key=lambda s:s['v'])
for i in sortl:
    print i['n']   '   '   str(round(i['v'],2)) '%'

0 人点赞