工具函数

1.由域名获取IP地址

import urllibimport httplibimport reimport urlparseimport jsondef ip(host_addr,format="dot"):    '''    describe:        function try to find the ip addr of the given host addr    params:        host_addr:the format like www.baidu.com or http://www.baidu.com        format:the format of return value                dot=>ip string like 123.121.121.21,                num=>number format like 327382483    return :IP string list or number list when num specified    '''    query_url='http://ip.chinaz.com/?'    if host_addr.startswith("http"):        req_url=urlparse.urlsplit(host_addr).netloc    else:        req_url=host_addr    r=urllib.urlopen(query_url+"IP="+req_url)    ipRex=r':\s+([\d\.]*)\s'    try:        if r !=None:            context=r.read()            rst=re.findall(ipRex,context)                      if rst!=None:                if format=="num":                    rss=[]                    for rs in rst:                                            sum=0                        for  f in enumerate(rs.split('.')):                            sum+=int(f[1])<<((3-f[0])*8)                        rss.append(str(sum))                    del rst                    rst=rss                return rst        return None    except :        return Noneprint ip('www.baidu.com')print ip('www.baidu.com','num')

 

测试结果：

['220.181.111.147']['3702878099']参考：http://www.oschina.net/code/snippet_79695_16093

 

 

2. IP地址和整数之间的转换函数

 

import socketimport structdef str2uint(str1):         return socket.ntohl(struct.unpack("I",socket.inet_aton(str1))[0])      # 得到始终是正数    def str2int(str1):      uint = socket.ntohl(struct.unpack("I",socket.inet_aton(str1))[0])      return struct.unpack("i", struct.pack('I', uint))[0]  # 先得到负数，再转换一下    def num2str(ip):      if ip < 0:          ip = struct.unpack("I", struct.pack('i', ip))[0]      return socket.inet_ntoa(struct.pack('I',socket.htonl(ip)))  

测试结果：

print str2uint("10.7.11.213")print str2int("10.7.11.213")print num2str(168233941)

转自：http://blog.csdn.net/rainharder/article/details/6107154

3.判断文件编码并获取文件内容

__author__ = 'soso_fy'#codeing:utf-8# 写python脚本经常要用到的一些函数# 免得每次都重写蛋疼# require python 3.2 or laterimport osimport codecs# 读取文本文件函数，支持bom-utf-8，utf-8,utf-16,gbk,gb2312# 返回文件内容def ReadTextFile(filepath):    try:        file = open(filepath, 'rb')    except IOError as err:        print('读取文件出错 in ReadFile', err)    bytes = file.read()    file.close()    if bytes[:3] == codecs.BOM_UTF8:        content = bytes[3:].decode('utf-8')    else:        try:            content = bytes.decode('gb2312')        except UnicodeDecodeError as err:            try:                content = bytes.decode('utf-16')            except UnicodeDecodeError as err:                try:                    content = bytes.decode('utf-8')                except UnicodeDecodeError as err:                    try:                        content = bytes.decode('gbk')                    except UnicodeDecodeError as err:                        content = ''                        print('不支持此种类型的文本文件编码', err)    return content

测试结果：

print ReadTextFile('C://python2.7//myTest//kp.conf')运行结果

realserver 192.168.191.129 10447{ weight 3}realserver 192.168.191.130 80{ weight 3}

4.获取目录下的特定扩展名的文件名

__author__ = 'soso_fy'#codeing:utf-8# 获取指定路径下所有指定后缀的文件# dir 指定路径# ext 指定后缀，链表&不需要带点或者不指定。例子：['xml', 'java']def GetFileFromThisRootDir(dir,ext = None):    allfiles = []    needExtFilter = (ext != None)    if needExtFilter:        ext = list(map(lambda x:x.lower(), ext))    for root,dirs,files in os.walk(dir):        for filespath in files:            filepath = os.path.join(root, filespath).lower()            extension = os.path.splitext(filepath)[1][1:]            if needExtFilter and extension in ext:                allfiles.append(filepath)            elif not needExtFilter:                allfiles.append(filepath)    return allfiles测试结果：

print GetFileFromThisRootDir('C://python2.7//myTest',['txt,conf'])

 

运行结果

['c://python2.7//mytest\\1.txt', 'c://python2.7//mytest\\conf_1000.conf', 'c://python2.7//mytest\\kp.conf', 'c://python2.7//mytest\\rs.conf', 'c://python2.7//mytest\\test.conf']

上面2个转自：http://www.oschina.net/code/snippet_272860_16194

5. unicode编码转换成utf8编码

def h2b(x):"""十六进制转二进制"""result = []if x==0:return ['0']while x != 1:result.append(str(x%2))x /= 2result.append('1')result.reverse()if len(result) % 4 != 0:for i in range(0,(4 - len(result) % 4)):result.insert(0,'0')return "".join(result)def c2u(x):"""unicode 转 utf8"""result = ''if 0x0 <= x and x <= 0x7F:result =  h2b(x)elif 0x80 <= x and x <= 0x7FF:if len(h2b(x)) == 8:tmp = '000' + h2b(x)else:tmp = h2b(x)[1:]result = '110'+ tmp[0:5] + '10' + tmp[5:]elif 0x800 <= x and x <= 0xFFFF:if len(h2b(x)) == 12:tmp = '0000' + h2b(x)else:tmp = h2b(x)result = '1110'+ tmp[0:4] + '10' + tmp[4:10] + '10' + tmp[10:]return b2h(result)def b2h(x):"""二进制转十六进制"""hex = ['0', '1', '2', '3', '4', '5', '6', '7', '8', '9' , 'A' , 'B' , 'C' , 'D' , 'E' , 'F']result = []def getValue(bin):value = 0for i in range(4):value += int(bin[i]) * 2**(3-i)return valuefor i in range(len(x)/4):result.append(hex[getValue(x[i*4:(i+1)*4])])return result

转自：http://www.oschina.net/code/snippet_223232_15787

6.统计日志中IP出现的次数

#-*- coding:utf-8 -*-import re,timedef mail_log(file_path):    global count    log=open(file_path,'r')    C=r'\.'.join([r'\d{1,3}']*4)    find=re.compile(C)    count={}    for i in log:        for ip in find.findall(i):            count[ip]=count.get(ip,1)+1if __name__ == '__main__':    print time.clock()    num=0    mail_log(r'e:\MDaemon-20110329-all.log')    R=count.items()    for i in R:        if i[1]>0: #提取出现次数大于0的IP            print i            num+=1    print '符合要求数量：%s耗时(%s)'%(num,time.clock())             

 

测试结果：（这脚本可用于多种日志类型,本人测试MDaemon的all日志文件大小1.23G左右,分析用时2~3分钟
代码很简单,很适合运维人员,有不足的地方请大家指出哦）

('206.220.200.250', 8)('66.40.52.37', 10)('66.40.52.36', 5)('207.115.11.41', 4)('96.47.193.25', 9)('96.47.193.24', 5)('96.47.193.23', 17)('72.32.181.92', 5)

http://www.oschina.net/code/snippet_591089_12662

 

 

 5.subprocess函数的使用测试

import subprocessdef disk_report():    p = subprocess.Popen("df -h ",shell=True,stdout=subprocess.PIPE)    return p.stdout.readlines()print disk_report()

 结果：

['Filesystem            Size  Used Avail Use% Mounted on\n', '/dev/sda2              19G  9.9G  8.2G  55% /\n', '/dev/sda5             414G  6.4G  386G   2% /var\n', '/dev/sda1              99M   11M   83M  12% /boot\n', 'tmpfs                 4.0G     0  4.0G   0% /dev/shm\n']

 

 6.复制文件夹

def CopyFolderOs(sFolder,tFolder):    sourcePath = sFolder    destPath = tFolder    for root, dirs, files in os.walk(sourcePath):        #figure out where we're going        dest = destPath + root.replace(sourcePath, '')        #if we're in a directory that doesn't exist in the destination folder        #then create a new folder        if not os.path.isdir(dest):            os.mkdir(dest)            print 'Directory created at: ' + dest        #loop through all files in the directory        for f in files:            #compute current (old) & new file locations            oldLoc = root + '\\' + f            newLoc = dest + '\\' + f            if not os.path.isfile(newLoc):                try:                    shutil.copy2(oldLoc, newLoc)                    print 'File ' + f + ' copied.'                except IOError:                    print 'file "' + f + '" already exists'

测试结果：

CopyFolderOs("C://python2.7//myTest","C://python2.7//myTestbak")

 

Directory created at: C://python2.7//myTestbakFile Conf_1000.conf copied.File ip.log copied.File kp.conf copied.File RS.conf copied.File test.conf copied.

 

 7.复制文件夹里面的文件

 

def RemoveFolderOs(sourceDir,localAppDataPath):    for root, dirs, files in os.walk(sourceDir):        for f in files:            os.unlink(os.path.join(root, f))        for d in dirs:            shutil.rmtree(os.path.join(root, d))

测试结果：

RemoveFolderOs("C://python2.7//myTestbak")

myTestbak文件夹还存在

 

 转自 http://www.oschina.net/code/snippet_72895_1576

 

8.创建守护进程

def createDaemon():    ”’Funzione che crea un demone per eseguire un determinato programma…”’       import os       # create - fork 1    try:        if os.fork() > 0: os._exit(0) # exit father…    except OSError, error:        print ‘fork #1 failed: %d (%s)’ % (error.errno, error.strerror)        os._exit(1)    # it separates the son from the father    os.chdir(’/')    os.setsid()    os.umask(0)    # create - fork 2    try:        pid = os.fork()        if pid > 0:            print ‘Daemon PID %d’ % pid            os._exit(0)    except OSError, error:        print ‘fork #2 failed: %d (%s)’ % (error.errno, error.strerror)        os._exit(1)    funzioneDemo() # function demo   def funzioneDemo():    import time    fd = open('/tmp/demone.log', 'w')    while True:        fd.write(time.ctime()+'\n')        fd.flush()        time.sleep(2)    fd.close()   if __name__ == '__main__':    createDaemon()

转自：http://www.oschina.net/code/snippet_16840_1896

9.执行外部命令

通常我们调用os.system(cmd) 只能获得命令是否能执行成功。即结果为0或者非0标识是否执行成功。

而有时我们希望即获取到是否成功，同时也获取命令的执行结果。

这时就可以使用commands了，通过它可以同时获取命令的执行结果输出和结果。

这样ret就反馈是否执行成功，比如为0(成功) 或者非0(不成功)

output 用来获取ls命令的执行结果。

 

import commands  ret, output = commands.getstatusoutput('ls')print ret    print output

转自：http://www.cnblogs.com/lovemdx/archive/2013/03/08/2950301.html

10.文件内容的查找和替换

查找

import remyfile = file("C://python2.7//myTest//file.txt", "r+")count = 0for s in myfile.readlines():          li = re.findall("hello", s)       if len([li]) > 0:                             count =  count + li.count("hello")print "find:" + str(count) + "times hello"  myfile.close()

文件内容的查找：从hello.txt中查找字符串“hello”， 并统计“hello”出现的次数。
结果：find:10times hello

替换：文件内容的替换：把hello.txt中的hello全部换为”hi“，并把结果保存到myhello.txt中。

f1 = file("C://python2.7//myTest//file.txt", "r")f2 = file("C://python2.7//myTest//myhello.txt", "w")for s in f1.readlines():    f2.write(s.replace("hello","hi"))                                                                                f1.close()f2.close()

 11.目录的遍历

方法1：递归

import osdef VisitDir(path) :    li = os.listdir(path)     for p in li:        pathname = os.path.join(path, p)        if not os.path.isfile(pathname) :            VisitDir(pathname)        else:            print pathnameif __name__ == "__main__":    path = r"C://python2.7//myTest"    VisitDir(path)

2.walk()函数
os.walk()的执行效率最高，且不需要回调函数，容易使用。os.walk（）的声明如下：
walk(top, topdown=ture, onerron= none)
(1)top表示需要遍历的目录树的路径。
(2)参数topdown的默认值为ture，表示先返回目录树下的文件，然后再遍历目录树的子目录，topdow为          false表示先遍历目录树下的子目录，然后返回根目录树的文件
(3)onerror为none表示忽略文件遍历时产生的错误。
(4)该函数返回一个元组，该元组有三个元素，分别是：每次遍历的路径名，目录列表和文件列表

def VisitDirWalk(path) :        for root, dirs, files in os.walk(path):        print 'root:',root        print 'dirs:',dirs        print 'files:',files        for filepath in files:            print os.path.join(root, filepath)

测试结果：

path = r"C://python2.7//myTest"   VisitDirWalk(path)

root: C://python2.7//myTestdirs: ['test']files: ['Conf_1000.conf', 'file.txt', 'ip.log', 'kp.conf', 'myhello.txt', 'RS.conf', 'test.conf']C://python2.7//myTest\Conf_1000.confC://python2.7//myTest\file.txtC://python2.7//myTest\ip.logC://python2.7//myTest\kp.confC://python2.7//myTest\myhello.txtC://python2.7//myTest\RS.confC://python2.7//myTest\test.confroot: C://python2.7//myTest\testdirs: []files: ['Conf_1000.conf']C://python2.7//myTest\test\Conf_1000.conf

12.删除py中的注释

f = open('file1.py', 'r+')line = f.readlines()f.seek(0)for l in line:    for i in range(len(l)):        if l[i]=='#':            l=l[:i]+' '*(len(l)-i-1)+'\n'            break    f.write(l)f.close()