#! /usr/bin/python
# -*- coding:UTF-8 -*-
 
import os
import os.path
import string

txt_path = 'D:/youxinProjections/trafic-youxin/MobileNet_v1/obtain_qq_json_new/Crop_Ocr_txt/'
des_txt_path = 'D:/youxinProjections/trafic-youxin/MobileNet_v1/obtain_qq_json_new/1000_simple_OCRtxts/'
 
txt_files = os.listdir(txt_path) #txt_files能得到该目录下的所有txt文件的文件名

def select_simples():
  for txtfile in txt_files:
    if not os.path.isdir(txtfile):
      in_file = open(txt_path + txtfile, 'r')
      out_file = open(des_txt_path + txtfile, 'a') # 此处自动新建一个文件夹和txtfile的文件名相同,'a'为自动换行写入
      lines = in_file.readlines()
      for line in lines:
        str_name = line.split(" ")[0] # 这里获取的是txt文件中每行内容以空格隔开的第一个元素，也就是我自己txt文件中的*.jpg那一块内容

str1 = '_9' # 这就是我要判断的子串
        str2 = '_10' # 这也是子串
 
        #if (string.find(str_name, str1)!=-1) or (string.find(str_name, str2)):
        if (str1 in str_name) or (str2 in str_name): # in 可以判断在str_name中是否包含有两个子串，
          out_file.write(line) # 若包含子串，则将该行内容全部重新写入新的txt文件
          print(str_name)
      out_file.close() 

#!/bin/env python
# coding:utf-8
#程序功能是为了完成判断文件中是否有重复句子
#并将重复句子打印出来

res_list = []
f = open('./downloadmd5.txt','r')
res_dup = []
index = 0
file_dul = open('./r_d.txt', 'w')
file_last = open('./r_nd.txt','w')
for line in f.readlines():
  index = index + 1
  if line in res_list:
    temp_str = ""
    #temp_str = temp_str + str(index) + ','  #要变为str才行
    temp_line = ''.join(line)
    temp_str = temp_str+temp_line
    #最终要变为str类型
    file_dul.write(temp_str);         #将重复的存入到文件中
  else:
    res_list.append(line)
    file_last.write(line)

#!/bin/env python
# coding:utf-8
import re

res_list = []
f = open('./md5.txt','r')
f2 = open('./virus.conf','r')

index = 0
#没重复的文件名
file_dul = open('./m_nd.txt', 'w')
#重复的文件名
file_ex = open('./m_d.txt', 'w')

virstr = f2.read();
for line in f.readlines():
  line=line.strip('\n')
  if(re.search(line, virstr)):
    line = line + '\n'
    file_ex.write(line);
    #调用删除rm -rf filename
  else:
    line = line+'\n'
    file_dul.write(line);