m = hashlib.md5()
 myFile = open(full_path, 'rb')
 for line in myFile.readlines(): #以行為單位不斷更新哈希值，避免文件過大導(dǎo)致一次產(chǎn)生大量開銷
  m.update(line) #最后可以得到整個文件的哈希值

class myListener(threading.Thread):

 thread1 = myListener(mydir, json_list_include, json_list_exclude) #生成線程

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author: JYRoooy
import collections
import json
import toml
if __name__ == '__main__':
 myOrderDict = collections.OrderedDict
 myOrderDict = {'dict':[{'path':'E:/testing', 'include':['log_'], 'exclude': ['.swp', '.swx', 'tmp']},{'path':'E:/tmp', 'include':['.record'], 'exclude': ['.tmp']}]}
 myToml = toml.dump(myOrderDict, open('E:/python/code/PythonProject/tomlConfig.txt','w+'))

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author: JYRoooy
import toml
import hashlib
import os
import sys
import time
import importlib
import threading
importlib.reload(sys)

class myListener(threading.Thread):
 '''
 監(jiān)聽類
 '''
 def __init__(self, input_dir, filt_in, filt_ex): #文件夾路徑，必須包含的字符，必須過濾的字符
 threading.Thread.__init__(self)
 self.input_dir = input_dir
 self.filt_in = filt_in
 self.filt_ex = filt_ex
 self.dict = {} #用來存儲文件名和對應(yīng)的哈希值
 self.file_list = [] #存儲每一次掃描時的文件的文件名
 self.pop_list = [] #存儲需要刪除的文件名

 def run(self):
 while (1): #保證文件夾一直處于被監(jiān)聽的狀態(tài)
  for cur_dir, dirs, files in os.walk(self.input_dir):
  if files != []:
   self.file_list = []
   for each_file_1 in files:
   each_file = each_file_1
   if self.filt_in: #判斷文件名中是否有必須存在的字段
    flagone = 0
    for i in range(len(self.filt_in)):
    if self.filt_in[i] in each_file:
     flagone += 1
    if flagone == 0:
    continue

   if self.filt_ex: #判斷文件名中是否有必須過濾掉的字段
    flagtwo = 0
    for i in range(len(self.filt_ex)):
    if self.filt_ex[i] in each_file:
     flagtwo = 1
    if flagtwo==1:
    continue

   self.file_list.append(each_file)
   full_path = os.path.join(cur_dir, each_file)
   m = hashlib.md5() #實例化md5算法

   myFile = open(full_path, 'rb')

   for line in myFile.readlines():
    m.update(line)
   if each_file not in self.dict.keys(): #如果當(dāng)前的dict中沒有這個文件，那么就添加進(jìn)去
    self.dict[each_file] = m.hexdigest() #生成哈希值
    print('文件夾:' +cur_dir+ "中的文件名為：" + each_file + "的文件為新文件" + time.strftime('%Y-%m-%d %H:%M:%S',
           time.localtime(time.time())))
   if each_file in self.dict.keys() and self.dict[each_file] != m.hexdigest(): #如果當(dāng)前dict中有這個文件，但是哈希值不同，說明文件被修改過，則需要對字典進(jìn)行更新
    print('文件夾:' +cur_dir+ "中的文件名為：" + each_file + "的文件被修改于" + time.strftime('%Y-%m-%d %H:%M:%S',
           time.localtime(time.time())))
    self.dict[each_file] = m.hexdigest()
   myFile.close()
  pop_list = []
  for i in self.dict.keys():
   if i not in self.file_list: #當(dāng)字典中有不在當(dāng)前文件名列表中時，說明文件已經(jīng)被刪除
   print('文件夾:' +cur_dir+ '中的文件名為:' + i + "的文件已被刪除!!!" + time.strftime('%Y-%m-%d %H:%M:%S',
          time.localtime(time.time())))
   pop_list.append(i)
  for i in pop_list:
   self.dict.pop(i)

  time.sleep(2)

if __name__ == '__main__':
 threads = [] #用來存儲線程的線程池
 with open('E:/python/code/PythonProject/tomlConfig.txt','r+') as f: #讀取toml格式的文件，并分解格式
 mytoml = toml.load(f)
 myList = mytoml['dict']
 for i in range(len(myList)): #因為可能同時需要監(jiān)聽多個文件夾，所以利用線程池處理多線程
  json_list_include = []
  json_list_exclude = []
  mydir = myList[i]['path']
  for sublist in range(len(myList[i]['include'])):
  json_list_include.append(myList[i]['include'][sublist])
  for sublist in range(len(myList[i]['exclude'])):
  json_list_exclude.append(myList[i]['exclude'][sublist])
  thread1 = myListener(mydir, json_list_include, json_list_exclude) #生成線程
  threads.append(thread1)

 for t in threads: #開啟所有線程
  t.start();