Day-6
JSON序列化
用于序列化的两个模块
json，用于字符串 和 python数据类型间进行转换
pickle，用于python特有的类型 和 python的数据类型间进行转换
Json模块提供了四个功能：dumps、dump、loads、load
pickle模块提供了四个功能：dumps、dump、loads、load
执行系统命令
可以执行shell命令的相关模块和函数有：
os.system
os.spawn*
os.popen* --废弃
popen2.* --废弃
commands.* --废弃，3.x中被移除
import commands
result = commands.getoutput('cmd')
result = commands.getstatus('cmd')
result = commands.getstatusoutput('cmd')
以上执行shell命令的相关的模块和函数的功能均在 subprocess 模块中实现，并提供了更丰富的功能。
call
执行命令，返回状态码
|
1
2
|
ret
=
subprocess.call([
"ls"
,
"-l"
], shell
=
False
)
ret
=
subprocess.call(
"ls -l"
, shell
=
True
)
|
shell = True ，允许 shell 命令是字符串形式
check_call
执行命令，如果执行状态码是 0 ，则返回0，否则抛异常
|
1
2
|
subprocess.check_call([
"ls"
,
"-l"
])
subprocess.check_call(
"exit 1"
, shell
=
True
)
|
check_output
执行命令，如果状态码是 0 ，则返回执行结果，否则抛异常
|
1
2
|
subprocess.check_output([
"echo"
,
"Hello World!"
])
subprocess.check_output(
"exit 1"
, shell
=
True
)
|
subprocess.Popen(...)
用于执行复杂的系统命令
参数：
args：shell命令，可以是字符串或者序列类型（如：list，元组）
bufsize：指定缓冲。0 无缓冲,1 行缓冲,其他 缓冲区大小,负值 系统缓冲
stdin, stdout, stderr：分别表示程序的标准输入、输出、错误句柄
preexec_fn：只在Unix平台下有效，用于指定一个可执行对象（callable object），它将在子进程运行之前被调用
close_sfs：在windows平台下，如果close_fds被设置为True，则新创建的子进程将不会继承父进程的输入、输出、错误管道。
所以不能将close_fds设置为True同时重定向子进程的标准输入、输出与错误(stdin, stdout, stderr)。shell：同上
cwd：用于设置子进程的当前目录
env：用于指定子进程的环境变量。如果env = None，子进程的环境变量将从父进程中继承。
universal_newlines：不同系统的换行符不同，True -> 同意使用 \n
startupinfo与createionflags只在windows下有效
将被传递给底层的CreateProcess()函数，用于设置子进程的一些属性，如：主窗口的外观，进程的优先级等等
import subprocess
ret1 = subprocess.Popen(["mkdir","t1"])
ret2 = subprocess.Popen("mkdir t2", shell=True)
终端输入的命令分为两种：
输入即可得到输出，如：ifconfig
输入进行某环境，依赖再输入，如：python
import subprocess
obj = subprocess.Popen("mkdir t3", shell=True, cwd='/home/dev',)
import subprocess
obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
obj.stdin.write('print 1 \n ')
obj.stdin.write('print 2 \n ')
obj.stdin.write('print 3 \n ')
obj.stdin.write('print 4 \n ')
obj.stdin.close()
cmd_out = obj.stdout.read()
obj.stdout.close()
cmd_error = obj.stderr.read()
obj.stderr.close()print cmd_outprint cmd_error
import subprocess
obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
obj.stdin.write('print 1 \n ')
obj.stdin.write('print 2 \n ')
obj.stdin.write('print 3 \n ')
obj.stdin.write('print 4 \n ')
out_error_list = obj.communicate()print out_error_list
import subprocess
obj = subprocess.Popen(["python"], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out_error_list = obj.communicate('print "hello"')print out_error_list
shutil
高级的 文件、文件夹、压缩包 处理模块
shutil.copyfileobj(fsrc, fdst[, length])
将文件内容拷贝到另一个文件中，可以部分内容
def copyfileobj(fsrc, fdst, length=16*1024): """copy data from file-like object fsrc to file-like object fdst""" while 1: buf = fsrc.read(length) if not buf: break fdst.write(buf)
shutil.copyfile(src, dst)
拷贝文件
def copyfile(src, dst): """Copy data from src to dst"""
if _samefile(src, dst): raise Error("`%s` and `%s` are the same file" % (src, dst)) for fn in [src, dst]: try:
st = os.stat(fn) except OSError: # File most likely does not exist
pass
else: # XXX What about other special files? (sockets, devices...)
if stat.S_ISFIFO(st.st_mode): raise SpecialFileError("`%s` is a named pipe" % fn)
with open(src, 'rb') as fsrc:
with open(dst, 'wb') as fdst:
copyfileobj(fsrc, fdst)
shutil.copymode(src, dst)
仅拷贝权限。内容、组、用户均不变
def copymode(src, dst): """Copy mode bits from src to dst""" if hasattr(os, 'chmod'): st = os.stat(src) mode = stat.S_IMODE(st.st_mode) os.chmod(dst, mode)
shutil.copystat(src, dst)
拷贝状态的信息，包括：mode bits, atime, mtime, flags
def copystat(src, dst): """Copy all stat info (mode bits, atime, mtime, flags) from src to dst""" st = os.stat(src) mode = stat.S_IMODE(st.st_mode) if hasattr(os, 'utime'): os.utime(dst, (st.st_atime, st.st_mtime)) if hasattr(os, 'chmod'): os.chmod(dst, mode) if hasattr(os, 'chflags') and hasattr(st, 'st_flags'): try: os.chflags(dst, st.st_flags) except OSError, why: for err in 'EOPNOTSUPP', 'ENOTSUP': if hasattr(errno, err) and why.errno == getattr(errno, err): break else: raise
shutil.copy(src, dst)
拷贝文件和权限
def copy(src, dst): """Copy data and mode bits ("cp src dst").
The destination may be a directory. """
if os.path.isdir(dst):
dst = os.path.join(dst, os.path.basename(src))
copyfile(src, dst)
copymode(src, dst)
shutil.copy2(src, dst)
拷贝文件和状态信息
def copy2(src, dst): """Copy data and all stat info ("cp -p src dst").
The destination may be a directory. """
if os.path.isdir(dst):
dst = os.path.join(dst, os.path.basename(src))
copyfile(src, dst)
copystat(src, dst)
shutil.ignore_patterns(*patterns)
shutil.copytree(src, dst, symlinks=False, ignore=None)
递归的去拷贝文件
例如：copytree(source, destination, ignore=ignore_patterns('*.pyc', 'tmp*'))
def ignore_patterns(*patterns): """Function that can be used as copytree() ignore parameter. Patterns is a sequence of glob-style patterns that are used to exclude files""" def _ignore_patterns(path, names): ignored_names = [] for pattern in patterns: ignored_names.extend(fnmatch.filter(names, pattern)) return set(ignored_names) return _ignore_patternsdef copytree(src, dst, symlinks=False, ignore=None): """Recursively copy a directory tree using copy2(). The destination directory must not already exist. If exception(s) occur, an Error is raised with a list of reasons. If the optional symlinks flag is true, symbolic links in the source tree result in symbolic links in the destination tree; if it is false, the contents of the files pointed to by symbolic links are copied. The optional ignore argument is a callable. If given, it is called with the `src` parameter, which is the directory being visited by copytree(), and `names` which is the list of `src` contents, as returned by os.listdir(): callable(src, names) -> ignored_names Since copytree() is called recursively, the callable will be called once for each directory that is copied. It returns a list of names relative to the `src` directory that should not be copied. XXX Consider this example code rather than the ultimate tool. """ names = os.listdir(src) if ignore is not None: ignored_names = ignore(src, names) else: ignored_names = set() os.makedirs(dst) errors = [] for name in names: if name in ignored_names: continue srcname = os.path.join(src, name) dstname = os.path.join(dst, name) try: if symlinks and os.path.islink(srcname): linkto = os.readlink(srcname) os.symlink(linkto, dstname) elif os.path.isdir(srcname): copytree(srcname, dstname, symlinks, ignore) else: # Will raise a SpecialFileError for unsupported file types copy2(srcname, dstname) # catch the Error from the recursive copytree so that we can # continue with other files except Error, err: errors.extend(err.args[0]) except EnvironmentError, why: errors.append((srcname, dstname, str(why))) try: copystat(src, dst) except OSError, why: if WindowsError is not None and isinstance(why, WindowsError): # Copying file access times may fail on Windows pass else: errors.append((src, dst, str(why))) if errors: raise Error, errors
Re正则表达式
re模块用于对python的正则表达式的操作。
字符：
. 匹配除换行符以外的任意字符
\w 匹配字母或数字或下划线或汉字
\s 匹配任意的空白符
\d 匹配数字
\b 匹配单词的开始或结束
^ 匹配字符串的开始
$ 匹配字符串的结束
次数：
* 重复零次或更多次
+ 重复一次或更多次
? 重复零次或一次
{n} 重复n次
{n,} 重复n次或更多次
{n,m} 重复n到m次
IP：^(25[0-5]|2[0-4]\d|[0-1]?\d?\d)(\.(25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}$
手机号：^1[3|4|5|8][0-9]\d{8}$
1、match(pattern, string, flags=0)
从起始位置开始根据模型去字符串中匹配指定内容，匹配单个
正则表达式
要匹配的字符串
标志位，用于控制正则表达式的匹配方式
import re
obj = re.match('\d+', '123uuasf')if obj: print obj.group()
flags
2、search(pattern, string, flags=0)
根据模型去字符串中匹配指定内容，匹配单个
import re
obj = re.search('\d+', 'u123uu888asf')if obj: print obj.group()
3、group和groups
a = "123abc456"print re.search("([0-9]*)([a-z]*)([0-9]*)", a).group()print re.search("([0-9]*)([a-z]*)([0-9]*)", a).group(0)print re.search("([0-9]*)([a-z]*)([0-9]*)", a).group(1)print re.search("([0-9]*)([a-z]*)([0-9]*)", a).group(2)print re.search("([0-9]*)([a-z]*)([0-9]*)", a).groups()
4、findall(pattern, string, flags=0)
上述两中方式均用于匹配单值，即：只能匹配字符串中的一个，如果想要匹配到字符串中所有符合条件的元素，则需要使用 findall。
import re
obj = re.findall('\d+', 'fa123uu888asf')print obj
5、sub(pattern, repl, string, count=0, flags=0)
用于替换匹配的字符串
content = "123abc456"new_content = re.sub('\d+', 'sb', content)# new_content = re.sub('\d+', 'sb', content, 1)print new_content
相比于str.replace功能更加强大
6、split(pattern, string, maxsplit=0, flags=0)
根据指定匹配进行分组
content = "'1 - 2 * ((60-30+1*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2) )'"new_content = re.split('\*', content)# new_content = re.split('\*', content, 1)print new_content
content = "'1 - 2 * ((60-30+1*(9-2*5/3+7/3*99/4*2998+10*568/14))-(-4*3)/(16-3*2) )'"new_content = re.split('[\+\-\*\/]+', content)# new_content = re.split('\*', content, 1)print new_content
inpp = '1-2*((60-30 +(-40-5)*(9-2*5/3 + 7 /3*99/4*2998 +10 * 568/14 )) - (-4*3)/ (16-3*2))'inpp = re.sub('\s*','',inpp)
new_content = re.split('\(([\+\-\*\/]?\d+[\+\-\*\/]?\d+){1}\)', inpp, 1)print new_content
相比于str.split更加强大
实例：计算器源码
十一、random
随机数
|
1
2
3
4
|
mport random
print
random.random()
print
random.randint(
1
,
2
)
print
random.randrange(
1
,
10
)
|
随机验证码实例：
|
1
2
3
4
5
6
7
8
9
10
|
import
random
checkcode
=
''
for
i
in
range
(
4
):
current
=
random.randrange(
0
,
4
)
if
current !
=
i:
temp
=
chr
(random.randint(
65
,
90
))
else
:
temp
=
random.randint(
0
,
9
)
checkcode
+
=
str
(temp)
print
checkcode
|