python re正则及os命令使用的一个小例子

http://www.cnblogs.com/huxi/archive/2010/07/04/1771073.html
这篇文章写得很好啊。

另外字符类的正则使用

du -sh .[a-zA-Z]* ~/
ls | grep "^[0-9].*"

##cmd_eg : phthon change.py /home/log


import os
import re
import sys

log_dir=sys.argv[1]#'/home/wren/script/python/test1'
search_argu=[['check_logfiles.log.bz2'],['sf_tc.store','check_logfiles.log'],['<result>FAILED','<item>check_logs failed'],['ipdb_common_sync_glitch_chk']]

change_search_argu=['<result>PASSED','<item>""']                        #search_argu[0] is the two search search_arguments in file1                                                                       #search_argu[1] is the two search search_arguments in file2

reObj = re.compile('#.*') 
#re 编译为pattern
def detect():#ergodic the files in path log_dir                            #search_argu[1] is the two search search_arguments in file2
    i=0

    cd_folder= 'cd '+log_dir+' && touch module_log_merge.txt'
 #   print os.getcwd()
 #   print ('cd_folder_and_touch')
 #   os.system(cd_folder)
    os.system(cd_folder)
    print os.getcwd()
    global script_dir
    script_dir =   os.getcwd()
  #  f = open('module_log_merge.txt', 'w')
  #  f.close()


    global check_file1
    global check_file2
    for rt,dirs,files in os.walk(log_dir):#ergodic the files in path log_dir
        for file in files:

            #detect zip file
            print(rt)
            path=rt+'/'
            pathlist=os.listdir(path)
            for filename in pathlist:
                if filename.endswith(str(search_argu[0][0])):
                    print("*******need to bunzip********")
                    order1='cd '+path+' && bunzip2 '+filename
                    os.system(order1)
                    #利用OS.system执行命令
                else:
                    pass
            if (pathlist.count(search_argu[1][0])==0) or (pathlist.count(search_argu[1][1])==0):
                i+=1
                print('file not found')
                print(i)
                break
            try:
                check_file1=path+search_argu[1][0]
                check_file2=path+search_argu[1][1]
            except FileNotFoundError:
                print('can not find files')
                sys.exit()
            merge_log(check_file2)
            print ("##################################################")
            break
def check1(file):#check file st_tc.store has [<result>FAILED] [<item>check_logs failed] or not
    a=0
    b=0
    #print('check1')
    open_file1=open(file)
    #print(open_file1)
    for line in open_file1:
        if(re.search(search_argu[2][0],line)):
            a=1
            break
    for line in open_file1:
        if (re.search(search_argu[2][1],line)):
            b=1
            break
    open_file1.close()
    if(a+b==2):
        print('check1 succeed')
        return(1)
    else:
        print('check1 failed')
        return(0)

def merge_log(file):#check file check_logfiles.log
    num=0
    should_detect=[]
    remain_file=[]
    open_file2=open(file)
  #  script_dir =   os.getcwd()
    if(check1(check_file1)==1):
        os.chdir(log_dir)
        with open('module_log_merge.txt','r+') as add2txt:
            for line in open_file2:
                if line.lstrip()[0].isdigit():
                    filter_num_line = reObj.search(line)
                    #利用编译的对象，进行search
                    add2txt.write(filter_num_line.group(0)+'\n')
                else:
                    pass
    else:   
        print('this case is pass') 
    os.chdir(script_dir)


if __name__=='__main__':
    detect()

这个脚本实现的是
1，在目标文件夹中创建一个文本A
2，将目标文件夹中所有的子文件夹中，每个check_logfiles.log的，以#来头的行搜集起来，写到这个创建的文本A中