日志文件除重并生成新的文件

1、log文件格式：
======================
Thread T9 (GTest) created by T0 here:#0 0xb7237dcc in pthread_create (/usr/lib/i386-linux-gnu/libasan.so.2+0x2fdcc)#1 0xacaede0d  (libGTestServer.so+0x2ce0d)SUMMARY: AddressSanitizer: alloc-dealloc-mismatch ??:0 operator delete(void*)
==16061==HINT: if you don't care about these warnings you may set ASAN_OPTIONS=alloc_dealloc_mismatch=0
==16061==ABORTING
======================
2、脚本
#!/usr/bin/python
# -*- coding: UTF-8 -*-
# 文件名：ReplaceTXT.py
import os
import xlwt
#1.创建一个excell文件
workbook = xlwt.Workbook() #注意Workbook的开头W要大写
#2.创建一个sheet
sheet1 = workbook.add_sheet('sheet1',cell_overwrite_ok=True)
#文件名
file_x = open('D:\\worksoft\\ubuntu32_asan_asan_4.1.7.165\\nohup.out'.decode('utf-8').encode('cp936'))#file_y = open('E:\\model_output_log\\y\\_iter_36000_yhand_output.txt')
dir = 'C:\\work\\1220\\y\\'
# 临时变量，sheet的行
temp = 0
def solution( re_str,test_str ):# 如果两个字符串相等 就返回Trueif re_str == test_str :return True# 标记第一个字母r = re_str[0] if re_str != '' else ''t = test_str[0] if test_str !='' else ''# r 不是？ 也 不是* 的情况if r != '?' and r != '*' :if r != t :     # 如果不想相等就返回Falsereturn Falseelse :      # 相等 就 删掉第一个单词 递归re_str,test_str = re_str[1:],test_str[1:]return solution( re_str,test_str )# 如果r是? 相当于匹配一个字符 都删掉一个字符 然后 递归if r == '?' :re_str, test_str = re_str[1:], test_str[1:]return solution(re_str, test_str)# 如果r是*  re 是n个*  则返回Trueif r == '*' and re_str.strip('*') == '' :return True# 否则 就是包含* ，*匹配0个字符或多个字符，所以我们返回 递归 0个匹配 与 1个匹配 的逻辑或return solution(re_str[1:], test_str) or solution(re_str, test_str[1:])
def text_create(name, msg):desktop_path = 'D:\\log\\'full_path = desktop_path + name + '.txt'file = open(full_path, 'x')file.write(msg)file.close()print('Done')
#新建文件目录
#参数path：目录文件名
#成功返回1
#失败返回0
def createfile(path):# 去除首位空格path = path.strip()# 去除尾部 \ 符号path = path.rstrip("\\")# 判断路径是否存在# 存在     True# 不存在   FalseisExists = os.path.exists(path)# 判断结果if not isExists:# 如果不存在则创建目录# 创建目录操作函数os.makedirs(path)print path + ' 创建成功'return Trueelse:# 如果目录存在则不创建，并提示目录已存在print path + ' 目录已存在'return Falsetemp = 0
list1 = []
file_name = "bug_ubuntu_asan_"
file_num = 1
desktop_path = 'D:\\log\\'
for line in file_x.readlines():full_path = desktop_path + file_name + str(file_num) + '.txt'file = open(full_path, 'a')# line = line.strip('\n')re_str = "==============================*"res = solution(re_str, line)remark = Falseif res:remark = Trueif temp == 1:temp = 0file_num += 1# list1.append(line)temp += 1if remark:continuefile.write(line)re_str1 = "SUMMARY*"res1 = solution(re_str1, line)if res1:list1.append(line)
file.close()
list1 = list(set(list1))
print "list===", len(list1)
temp_list = []for i in list1:temp1 = 0for root, save_file, files in os.walk(desktop_path):for file in files:file_txt = open(root+file)for line in file_txt.readlines():if temp1 == 1:passelse:res = solution(i, line)if res:# import shutil# temp_file_txt = open(root+"temp"+"\\\\"+file)# shutil.copyfile(root+file, temp_file_txt)print "not same====", lineprint "file====", filetemp_list.append(file)temp1 += 1
import shutil
for i in range(len(temp_list)):file_name = desktop_path+"\\temp\\"+temp_list[i]createfile(desktop_path+"\\temp\\")shutil.copyfile(desktop_path + temp_list[i], file_name)file_txt = open(file_name,"r")lines = file_txt.readlines()file_txt.close()new_lines = [" "]new_lines[0] = "[UBUNTU_MONKEY_ASAN]" + list1[i] + "\n"for j in range(len(lines)):new_lines.append(lines[j])file_txt = open(file_name, "w")for j in new_lines:file_txt.write(j)file_txt.close()print "lines===", new_lines