Python3实时操作处理日志文件的实现

import re
import codecs
import subprocess
 
def pg_data_to_elk():
    p = subprocess.Popen('tail -F /data/mongodb/shard1/log/pg.csv', shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE,)    #起一个进程，执行shell命令
    while True:
        line = p.stdout.readline()   #实时获取行
        if line:                     #如果行存在的话
            xxxxxxxxxxxx
            your operation

class subprocess.Popen(args, bufsize=-1, executable=None, stdin=None, stdout=None, stderr=None, 
    preexec_fn=None, close_fds=True, shell=False, cwd=None, env=None, universal_newlines=False,
    startup_info=None, creationflags=0, restore_signals=True, start_new_session=False, pass_fds=())

import re
import os
import time
import codecs
import subprocess
from datetime import datetime
 
path = '/home/liao/python/csv'
time_now_day = datetime.now.strftime('%Y-%m-%d')
 
def get_file_size(new_file):
    fsize = os.path.getsize(new_file)
    fsize = fsize/float(1024*1024)
    return fsize
 
def get_the_new_file():
    files = os.listdir(path)
    files_list = list(filter(lambda x:x[-4:]=='.csv' and x[11:21]==time_now_day, files))
    files_list.sort(key=lambda fn:os.path.getmtime(path + '/' + fn) if not os.path.isdir(path + '/' + fn) else 0)
    new_file = os.path.join(path, files_list[-1])
    return new_file
 
def pg_data_to_elk():
    while True:
        new_file = get_the_new_file()
        p = subprocess.Popen('tail -F {0}'.format(new_file), shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE,)    #起一个进程，执行shell命令
        while True:
            line = p.stdout.readline()   #实时获取行
            if line:                     #如果行存在的话
                if get_file_size(new_file) > 20:    #如果大于20M，则跳出循环
                    break
                xxxxxxxxxxxx
                your operation
        time.sleep(3)