实例如下所示：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
import time
import pickle
import os
import re
class LogIncScaner(object):
def __init__(self,log_file, reg_ex,seek_file='/tmp/log-inc-scan.seek.temp'):
self.log_file = log_file
self.reg_ex = reg_ex
self.seek_file = seek_file
def scan(self):
seek = self._get_seek()
file_mtime = os.path.getmtime(self.log_file)
if file_mtime <= seek['time']:
print 'file mtime not change since last scan'
seek['time'] = file_mtime
self._dump_seek(seek)
return []
file_size = os.path.getsize(self.log_file)
if file_size <= seek['position']:
print 'file size not change since last scan'
seek['position'] = file_size
self._dump_seek(seek)
return []
print 'file changed,start to scan'
matchs = []
with open(self.log_file, 'rb') as logfd:
logfd.seek(seek['position'],os.SEEK_SET)
for match in re.finditer(self.reg_ex, logfd.read()):
matchs.append(match)
seek = {'time':time.time(),'position': logfd.tell()}
print seek
self._dump_seek(seek)
return matchs
def _get_seek(self):
seek = {'time':time.time(),'position':0}
if os.path.exists(self.seek_file):
with open(self.seek_file,'rb') as seekfd:
try:
seek = pickle.load(seekfd)
except:
pass
print seek
return seek
def _dump_seek(self, seek):
with open(self.seek_file,'wb') as seekfd:
pickle.dump(seek,seekfd)
def reset_seek(self):
self._dump_seek({'time':time.time(),'position':0})
if __name__ == "__main__":
scaner = LogIncScaner('/var/log/messages',r'(\w+ \d+ \d+:\d+:\d+) .+?exception')
scaner.reset_seek()
while True:
matchs = scaner.scan()
for match in matchs:
print 'fond at:' + match.group(1) + ' content:' + match.group(0)
time.sleep(5)
|
以上这篇python 日志增量抓取实现方法就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/tiankai517/article/details/50549395