下面为大家分享一篇python 日志增量抓取实现方法，具有很好的参考价值，希望对大家有所帮助。一起过来看看吧
实例如下所示：
import timeimport pickleimport osimport reclass 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'] = <b style="color:transparent">本文来源gao@!dai!ma.com搞$$代^@码!网!</b>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)
相关推荐：
浅谈python日志的配置文件路径问题
详解python日志打印和写入并发实现代码
以上就是python 日志增量抓取实现方法的详细内容，更多请关注搞代码gaodaima其它相关文章！
搞代码网（gaodaima.com）提供的所有资源部分来自互联网，如果有侵犯您的版权或其他权益，请说明详细缘由并提供版权或权益证明然后发送到邮箱[email protected]，我们会在看到邮件的第一时间内为您处理，或直接联系QQ：872152909。本网站采用BY-NC-SA协议进行授权
转载请注明原文链接：python 日志增量抓取实现方法
转载请注明原文链接：python 日志增量抓取实现方法
