Python学习笔记,day5
一、time & datetime模块
import本质为将要导入的模块,先解释一遍
#_*_coding:utf-8_*_
__author__ = 'Alex Li' import time # print(time.clock()) #返回处理器时间,3.3开始已废弃 , 改成了time.process_time()测量处理器运算时间,不包括sleep时间,不稳定,mac上测不出来
# print(time.altzone) #返回与utc时间的时间差,以秒计算\
# print(time.asctime()) #返回时间格式"Fri Aug 19 11:14:16 2016",
# print(time.localtime()) #返回本地时间 的struct time对象格式
# print(time.gmtime(time.time()-800000)) #返回utc时间的struc时间对象格式 # print(time.asctime(time.localtime())) #返回时间格式"Fri Aug 19 11:14:16 2016",
#print(time.ctime()) #返回Fri Aug 19 12:38:29 2016 格式, 同上 # 日期字符串 转成 时间戳
# string_2_struct = time.strptime("2016/05/22","%Y/%m/%d") #将 日期字符串 转成 struct时间对象格式
# print(string_2_struct)
# #
# struct_2_stamp = time.mktime(string_2_struct) #将struct时间对象转成时间戳
# print(struct_2_stamp) #将时间戳转为字符串格式
# print(time.gmtime(time.time()-86640)) #将utc时间戳转换成struct_time格式
# print(time.strftime("%Y-%m-%d %H:%M:%S",time.gmtime()) ) #将utc struct_time格式转成指定的字符串格式 #时间加减
import datetime # print(datetime.datetime.now()) #返回 2016-08-19 12:47:03.941925
#print(datetime.date.fromtimestamp(time.time()) ) # 时间戳直接转成日期格式 2016-08-19
# print(datetime.datetime.now() )
# print(datetime.datetime.now() + datetime.timedelta(3)) #当前时间+3天
# print(datetime.datetime.now() + datetime.timedelta(-3)) #当前时间-3天
# print(datetime.datetime.now() + datetime.timedelta(hours=3)) #当前时间+3小时
# print(datetime.datetime.now() + datetime.timedelta(minutes=30)) #当前时间+30分 #
# c_time = datetime.datetime.now()
# print(c_time.replace(minute=3,hour=2)) #时间替换
二、random模块
随机数
import random
print random.random()
print random.randint(1,2)
print random.randrange(1,10)
生成随机验证码
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
三、OS模块
提供对操作系统进行调用的接口
os.getcwd() 获取当前工作目录,即当前python脚本工作的目录路径
os.chdir("dirname") 改变当前脚本工作目录;相当于shell下cd
os.curdir 返回当前目录: ('.')
os.pardir 获取当前目录的父目录字符串名:('..')
os.makedirs('dirname1/dirname2') 可生成多层递归目录
os.removedirs('dirname1') 若目录为空,则删除,并递归到上一级目录,如若也为空,则删除,依此类推
os.mkdir('dirname') 生成单级目录;相当于shell中mkdir dirname
os.rmdir('dirname') 删除单级空目录,若目录不为空则无法删除,报错;相当于shell中rmdir dirname
os.listdir('dirname') 列出指定目录下的所有文件和子目录,包括隐藏文件,并以列表方式打印
os.remove() 删除一个文件
os.rename("oldname","newname") 重命名文件/目录
os.stat('path/filename') 获取文件/目录信息
os.sep 输出操作系统特定的路径分隔符,win下为"\\",Linux下为"/"
os.linesep 输出当前平台使用的行终止符,win下为"\t\n",Linux下为"\n"
os.pathsep 输出用于分割文件路径的字符串
os.name 输出字符串指示当前使用平台。win->'nt'; Linux->'posix'
os.system("bash command") 运行shell命令,直接显示
os.environ 获取系统环境变量
os.path.abspath(path) 返回path规范化的绝对路径
os.path.split(path) 将path分割成目录和文件名二元组返回
os.path.dirname(path) 返回path的目录。其实就是os.path.split(path)的第一个元素
os.path.basename(path) 返回path最后的文件名。如何path以/或\结尾,那么就会返回空值。即os.path.split(path)的第二个元素
os.path.exists(path) 如果path存在,返回True;如果path不存在,返回False
os.path.isabs(path) 如果path是绝对路径,返回True
os.path.isfile(path) 如果path是一个存在的文件,返回True。否则返回False
os.path.isdir(path) 如果path是一个存在的目录,则返回True。否则返回False
os.path.join(path1[, path2[, ...]]) 将多个路径组合后返回,第一个绝对路径之前的参数将被忽略
os.path.getatime(path) 返回path所指向的文件或者目录的最后存取时间
os.path.getmtime(path) 返回path所指向的文件或者目录的最后修改时间
四、sys模块
sys.argv 命令行参数List,第一个元素是程序本身路径
sys.exit(n) 退出程序,正常退出时exit(0)
sys.version 获取Python解释程序的版本信息
sys.maxint 最大的Int值
sys.path 返回模块的搜索路径,初始化时使用PYTHONPATH环境变量的值
sys.platform 返回操作系统平台名称
sys.stdout.write('please:')
val = sys.stdin.readline()[:-1]
五、shutil模块
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_patterns def 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
shutil.rmtree(path[, ignore_errors[, onerror]])
递归的去删除文件
def rmtree(path, ignore_errors=False, onerror=None):
"""Recursively delete a directory tree. If ignore_errors is set, errors are ignored; otherwise, if onerror
is set, it is called to handle the error with arguments (func,
path, exc_info) where func is os.listdir, os.remove, or os.rmdir;
path is the argument to that function that caused it to fail; and
exc_info is a tuple returned by sys.exc_info(). If ignore_errors
is false and onerror is None, an exception is raised. """
if ignore_errors:
def onerror(*args):
pass
elif onerror is None:
def onerror(*args):
raise
try:
if os.path.islink(path):
# symlinks to directories are forbidden, see bug #1669
raise OSError("Cannot call rmtree on a symbolic link")
except OSError:
onerror(os.path.islink, path, sys.exc_info())
# can't continue even if onerror hook returns
return
names = []
try:
names = os.listdir(path)
except os.error, err:
onerror(os.listdir, path, sys.exc_info())
for name in names:
fullname = os.path.join(path, name)
try:
mode = os.lstat(fullname).st_mode
except os.error:
mode = 0
if stat.S_ISDIR(mode):
rmtree(fullname, ignore_errors, onerror)
else:
try:
os.remove(fullname)
except os.error, err:
onerror(os.remove, fullname, sys.exc_info())
try:
os.rmdir(path)
except os.error:
onerror(os.rmdir, path, sys.exc_info())
shutil.move(src, dst)
递归的去移动文件
def move(src, dst):
"""Recursively move a file or directory to another location. This is
similar to the Unix "mv" command. If the destination is a directory or a symlink to a directory, the source
is moved inside the directory. The destination path must not already
exist. If the destination already exists but is not a directory, it may be
overwritten depending on os.rename() semantics. If the destination is on our current filesystem, then rename() is used.
Otherwise, src is copied to the destination and then removed.
A lot more could be done here... A look at a mv.c shows a lot of
the issues this implementation glosses over. """
real_dst = dst
if os.path.isdir(dst):
if _samefile(src, dst):
# We might be on a case insensitive filesystem,
# perform the rename anyway.
os.rename(src, dst)
return real_dst = os.path.join(dst, _basename(src))
if os.path.exists(real_dst):
raise Error, "Destination path '%s' already exists" % real_dst
try:
os.rename(src, real_dst)
except OSError:
if os.path.isdir(src):
if _destinsrc(src, dst):
raise Error, "Cannot move a directory '%s' into itself '%s'." % (src, dst)
copytree(src, real_dst, symlinks=True)
rmtree(src)
else:
copy2(src, real_dst)
os.unlink(src)
shutil.make_archive(base_name, format,...)
创建压缩包并返回文件路径,例如:zip、tar
- base_name: 压缩包的文件名,也可以是压缩包的路径。只是文件名时,则保存至当前目录,否则保存至指定路径,
如:www =>保存至当前路径
如:/Users/wupeiqi/www =>保存至/Users/wupeiqi/ - format: 压缩包种类,“zip”, “tar”, “bztar”,“gztar”
- root_dir: 要压缩的文件夹路径(默认当前目录)
- owner: 用户,默认当前用户
- group: 组,默认当前组
- logger: 用于记录日志,通常是logging.Logger对象
#将 /Users/wupeiqi/Downloads/test 下的文件打包放置当前程序目录 import shutil
ret = shutil.make_archive("wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test') #将 /Users/wupeiqi/Downloads/test 下的文件打包放置 /Users/wupeiqi/目录
import shutil
ret = shutil.make_archive("/Users/wupeiqi/wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test')
def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
dry_run=0, owner=None, group=None, logger=None):
"""Create an archive file (eg. zip or tar). 'base_name' is the name of the file to create, minus any format-specific
extension; 'format' is the archive format: one of "zip", "tar", "bztar"
or "gztar". 'root_dir' is a directory that will be the root directory of the
archive; ie. we typically chdir into 'root_dir' before creating the
archive. 'base_dir' is the directory where we start archiving from;
ie. 'base_dir' will be the common prefix of all files and
directories in the archive. 'root_dir' and 'base_dir' both default
to the current directory. Returns the name of the archive file. 'owner' and 'group' are used when creating a tar archive. By default,
uses the current owner and group.
"""
save_cwd = os.getcwd()
if root_dir is not None:
if logger is not None:
logger.debug("changing into '%s'", root_dir)
base_name = os.path.abspath(base_name)
if not dry_run:
os.chdir(root_dir) if base_dir is None:
base_dir = os.curdir kwargs = {'dry_run': dry_run, 'logger': logger} try:
format_info = _ARCHIVE_FORMATS[format]
except KeyError:
raise ValueError, "unknown archive format '%s'" % format func = format_info[0]
for arg, val in format_info[1]:
kwargs[arg] = val if format != 'zip':
kwargs['owner'] = owner
kwargs['group'] = group try:
filename = func(base_name, base_dir, **kwargs)
finally:
if root_dir is not None:
if logger is not None:
logger.debug("changing back to '%s'", save_cwd)
os.chdir(save_cwd) return filename
六、shelve模块
shelve模块是一个简单的k,v将内存数据通过文件持久化的模块,可以持久化任何pickle可支持的python数据格式
import shelve d = shelve.open('shelve_test') #打开一个文件 class Test(object):
def __init__(self,n):
self.n = n t = Test(123)
t2 = Test(123334) name = ["alex","rain","test"]
d["test"] = name #持久化列表
d["t1"] = t #持久化类
d["t2"] = t2 d.close()
七、XML模块
xml是实现不同语言或程序之间进行数据交换的协议,跟json差不多,但json使用起来更简单,不过,古时候,在json还没诞生的黑暗年代,大家只能选择用xml呀,至今很多传统公司如金融行业的很多系统的接口还主要是xml。
xml的格式如下,就是通过<>节点来区别数据结构的:
<?xml version="1.0"?>
<data>
<country name="Liechtenstein">
<rank updated="yes">2</rank>
<year>2008</year>
<gdppc>141100</gdppc>
<neighbor name="Austria" direction="E"/>
<neighbor name="Switzerland" direction="W"/>
</country>
<country name="Singapore">
<rank updated="yes">5</rank>
<year>2011</year>
<gdppc>59900</gdppc>
<neighbor name="Malaysia" direction="N"/>
</country>
<country name="Panama">
<rank updated="yes">69</rank>
<year>2011</year>
<gdppc>13600</gdppc>
<neighbor name="Costa Rica" direction="W"/>
<neighbor name="Colombia" direction="E"/>
</country>
</data>
xml协议在各个语言里的都 是支持的,在python中可以用以下模块操作xml
import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml")
root = tree.getroot()
print(root.tag) #遍历xml文档
for child in root:
print(child.tag, child.attrib)
for i in child:
print(i.tag,i.text) #只遍历year 节点
for node in root.iter('year'):
print(node.tag,node.text)
修改和删除xml文档内容
import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml")
root = tree.getroot() #修改
for node in root.iter('year'):
new_year = int(node.text) + 1
node.text = str(new_year)
node.set("updated","yes") tree.write("xmltest.xml") #删除node
for country in root.findall('country'):
rank = int(country.find('rank').text)
if rank > 50:
root.remove(country) tree.write('output.xml')
自己创建xml文档
import xml.etree.ElementTree as ET new_xml = ET.Element("namelist")
name = ET.SubElement(new_xml,"name",attrib={"enrolled":"yes"})
age = ET.SubElement(name,"age",attrib={"checked":"no"})
sex = ET.SubElement(name,"sex")
sex.text = ''
name2 = ET.SubElement(new_xml,"name",attrib={"enrolled":"no"})
age = ET.SubElement(name2,"age")
age.text = '' et = ET.ElementTree(new_xml) #生成文档对象
et.write("test.xml", encoding="utf-8",xml_declaration=True) ET.dump(new_xml) #打印生成的格式
八、ConfigParser模块
用于生成和修改常见配置文档,当前模块的名称在 python 3.x 版本中变更为 configparser。
来看一个好多软件的常见文档格式如下
[DEFAULT]
ServerAliveInterval = 45
Compression = yes
CompressionLevel = 9
ForwardX11 = yes [bitbucket.org]
User = hg [topsecret.server.com]
Port = 50022
ForwardX11 = no
如果想用python生成一个这样的文档怎么做呢?
import configparser config = configparser.ConfigParser()
config["DEFAULT"] = {'ServerAliveInterval': '',
'Compression': 'yes',
'CompressionLevel': ''} config['bitbucket.org'] = {}
config['bitbucket.org']['User'] = 'hg'
config['topsecret.server.com'] = {}
topsecret = config['topsecret.server.com']
topsecret['Host Port'] = '' # mutates the parser
topsecret['ForwardX11'] = 'no' # same here
config['DEFAULT']['ForwardX11'] = 'yes'
with open('example.ini', 'w') as configfile:
config.write(configfile)
写完了还可以再读出来哈。
>>> import configparser
>>> config = configparser.ConfigParser()
>>> config.sections()
[]
>>> config.read('example.ini')
['example.ini']
>>> config.sections()
['bitbucket.org', 'topsecret.server.com']
>>> 'bitbucket.org' in config
True
>>> 'bytebong.com' in config
False
>>> config['bitbucket.org']['User']
'hg'
>>> config['DEFAULT']['Compression']
'yes'
>>> topsecret = config['topsecret.server.com']
>>> topsecret['ForwardX11']
'no'
>>> topsecret['Port']
''
>>> for key in config['bitbucket.org']: print(key)
...
user
compressionlevel
serveraliveinterval
compression
forwardx11
>>> config['bitbucket.org']['ForwardX11']
'yes'
configparser增删改查语法
[section1]
k1 = v1
k2:v2 [section2]
k1 = v1 import ConfigParser config = ConfigParser.ConfigParser()
config.read('i.cfg') # ########## 读 ##########
#secs = config.sections()
#print secs
#options = config.options('group2')
#print options #item_list = config.items('group2')
#print item_list #val = config.get('group1','key')
#val = config.getint('group1','key') # ########## 改写 ##########
#sec = config.remove_section('group1')
#config.write(open('i.cfg', "w")) #sec = config.has_section('wupeiqi')
#sec = config.add_section('wupeiqi')
#config.write(open('i.cfg', "w")) #config.set('group2','k1',11111)
#config.write(open('i.cfg', "w")) #config.remove_option('group2','age')
#config.write(open('i.cfg', "w"))
九、hashlib模块
用于加密相关的操作,3.x里代替了md5模块和sha模块,主要提供 SHA1, SHA224, SHA256, SHA384, SHA512 ,MD5 算法
import hashlib m = hashlib.md5()
m.update(b"Hello")
m.update(b"It's me")
print(m.digest())
m.update(b"It's been a long time since last time we ...") print(m.digest()) #2进制格式hash
print(len(m.hexdigest())) #16进制格式hash
'''
def digest(self, *args, **kwargs): # real signature unknown
""" Return the digest value as a string of binary data. """
pass def hexdigest(self, *args, **kwargs): # real signature unknown
""" Return the digest value as a string of hexadecimal digits. """
pass '''
import hashlib # ######## md5 ######## hash = hashlib.md5()
hash.update('admin')
print(hash.hexdigest()) # ######## sha1 ######## hash = hashlib.sha1()
hash.update('admin')
print(hash.hexdigest()) # ######## sha256 ######## hash = hashlib.sha256()
hash.update('admin')
print(hash.hexdigest()) # ######## sha384 ######## hash = hashlib.sha384()
hash.update('admin')
print(hash.hexdigest()) # ######## sha512 ######## hash = hashlib.sha512()
hash.update('admin')
print(hash.hexdigest())
python 还有一个 hmac 模块,它内部对我们创建 key 和 内容 再进行处理然后再加密
散列消息鉴别码,简称HMAC,是一种基于消息鉴别码MAC(Message Authentication Code)的鉴别机制。使用HMAC时,消息通讯的双方,通过验证消息中加入的鉴别密钥K来鉴别消息的真伪;
一般用于网络通信中消息加密,前提是双方先要约定好key,就像接头暗号一样,然后消息发送把用key把消息加密,接收方用key + 消息明文再加密,拿加密后的值 跟 发送者的相对比是否相等,这样就能验证消息的真实性,及发送者的合法性了。
import hmac
h = hmac.new(b'天王盖地虎', b'宝塔镇河妖')
print h.hexdigest()
十、logging模块
很多程序都有记录日志的需求,并且日志中包含的信息即有正常的程序访问日志,还可能有错误、警告等信息输出,python的logging模块提供了标准的日志接口,你可以通过它存储各种格式的日志,logging的日志可以分为 debug()
, info()
, warning()
, error()
and critical() 5个级别,
下面我们看一下怎么用。
最简单用法
import logging logging.warning("user [alex] attempted wrong password more than 3 times")
logging.critical("server is down") #输出
WARNING:root:user [alex] attempted wrong password more than 3 times
CRITICAL:root:server is down
看一下这几个日志级别分别代表什么意思
Level | When it’s used |
---|---|
DEBUG |
Detailed information, typically of interest only when diagnosing problems. |
INFO |
Confirmation that things are working as expected. |
WARNING |
An indication that something unexpected happened, or indicative of some problem in the near future (e.g. ‘disk space low’). The software is still working as expected. |
ERROR |
Due to a more serious problem, the software has not been able to perform some function. |
CRITICAL |
A serious error, indicating that the program itself may be unable to continue running. |
如果想把日志写到文件里,也很简单
import logging logging.basicConfig(filename='example.log',level=logging.INFO)
logging.debug('This message should go to the log file')
logging.info('So should this')
logging.warning('And this, too')
其中下面这句中的level=loggin.INFO意思是,把日志纪录级别设置为INFO,也就是说,只有比日志是INFO或比INFO级别更高的日志才会被纪录到文件里,在这个例子, 第一条日志是不会被纪录的,如果希望纪录debug的日志,那把日志级别改成DEBUG就行了。
感觉上面的日志格式忘记加上时间啦,日志不知道时间怎么行呢,下面就来加上!
import logging
logging.basicConfig(format='%(asctime)s %(message)s', datefmt='%m/%d/%Y %I:%M:%S %p')
logging.warning('is when this event was logged.') #输出
12/12/2010 11:46:36 AM is when this event was logged.
日志格式
%(name)s |
Logger的名字 |
%(levelno)s |
数字形式的日志级别 |
%(levelname)s |
文本形式的日志级别 |
%(pathname)s |
调用日志输出函数的模块的完整路径名,可能没有 |
%(filename)s |
调用日志输出函数的模块的文件名 |
%(module)s |
调用日志输出函数的模块名 |
%(funcName)s |
调用日志输出函数的函数名 |
%(lineno)d |
调用日志输出函数的语句所在的代码行 |
%(created)f |
当前时间,用UNIX标准的表示时间的浮 点数表示 |
%(relativeCreated)d |
输出日志信息时的,自Logger创建以 来的毫秒数 |
%(asctime)s |
字符串形式的当前时间。默认格式是 “2003-07-08 16:49:45,896”。逗号后面的是毫秒 |
%(thread)d |
线程ID。可能没有 |
%(threadName)s |
线程名。可能没有 |
%(process)d |
进程ID。可能没有 |
%(message)s |
用户输出的消息 |
如果想同时把log打印在屏幕和文件日志里,就需要了解一点复杂的知识 了
Python 使用logging模块记录日志涉及四个主要类,使用官方文档中的概括最为合适:
logger提供了应用程序可以直接使用的接口;
handler将(logger创建的)日志记录发送到合适的目的输出;
filter提供了细度设备来决定输出哪条日志记录;
formatter决定日志记录的最终输出格式。
logger
每个程序在输出信息之前都要获得一个Logger。Logger通常对应了程序的模块名,比如聊天工具的图形界面模块可以这样获得它的Logger:
LOG=logging.getLogger(”chat.gui”)
而核心模块可以这样:
LOG=logging.getLogger(”chat.kernel”)
Logger.setLevel(lel):指定最低的日志级别,低于lel的级别将被忽略。debug是最低的内置级别,critical为最高
Logger.addFilter(filt)、Logger.removeFilter(filt):添加或删除指定的filter
Logger.addHandler(hdlr)、Logger.removeHandler(hdlr):增加或删除指定的handler
Logger.debug()、Logger.info()、Logger.warning()、Logger.error()、Logger.critical():可以设置的日志级别
handler
handler对象负责发送相关的信息到指定目的地。Python的日志系统有多种Handler可以使用。有些Handler可以把信息输出到控制台,有些Logger可以把信息输出到文件,还有些 Handler可以把信息发送到网络上。如果觉得不够用,还可以编写自己的Handler。可以通过addHandler()方法添加多个多handler
Handler.setLevel(lel):指定被处理的信息级别,低于lel级别的信息将被忽略
Handler.setFormatter():给这个handler选择一个格式
Handler.addFilter(filt)、Handler.removeFilter(filt):新增或删除一个filter对象
每个Logger可以附加多个Handler。接下来我们就来介绍一些常用的Handler:
1) logging.StreamHandler
使用这个Handler可以向类似与sys.stdout或者sys.stderr的任何文件对象(file object)输出信息。它的构造函数是:
StreamHandler([strm])
其中strm参数是一个文件对象。默认是sys.stderr
2) logging.FileHandler
和StreamHandler类似,用于向一个文件输出日志信息。不过FileHandler会帮你打开这个文件。它的构造函数是:
FileHandler(filename[,mode])
filename是文件名,必须指定一个文件名。
mode是文件的打开方式。参见Python内置函数open()的用法。默认是’a',即添加到文件末尾。
3) logging.handlers.RotatingFileHandler
这个Handler类似于上面的FileHandler,但是它可以管理文件大小。当文件达到一定大小之后,它会自动将当前日志文件改名,然后创建 一个新的同名日志文件继续输出。比如日志文件是chat.log。当chat.log达到指定的大小之后,RotatingFileHandler自动把 文件改名为chat.log.1。不过,如果chat.log.1已经存在,会先把chat.log.1重命名为chat.log.2。。。最后重新创建 chat.log,继续输出日志信息。它的构造函数是:
RotatingFileHandler( filename[, mode[, maxBytes[, backupCount]]])
其中filename和mode两个参数和FileHandler一样。
maxBytes用于指定日志文件的最大文件大小。如果maxBytes为0,意味着日志文件可以无限大,这时上面描述的重命名过程就不会发生。
backupCount用于指定保留的备份文件的个数。比如,如果指定为2,当上面描述的重命名过程发生时,原有的chat.log.2并不会被更名,而是被删除。
4) logging.handlers.TimedRotatingFileHandler
这个Handler和RotatingFileHandler类似,不过,它没有通过判断文件大小来决定何时重新创建日志文件,而是间隔一定时间就 自动创建新的日志文件。重命名的过程与RotatingFileHandler类似,不过新的文件不是附加数字,而是当前时间。它的构造函数是:
TimedRotatingFileHandler( filename [,when [,interval [,backupCount]]])
其中filename参数和backupCount参数和RotatingFileHandler具有相同的意义。
interval是时间间隔。
when参数是一个字符串。表示时间间隔的单位,不区分大小写。它有以下取值:
S 秒
M 分
H 小时
D 天
W 每星期(interval==0时代表星期一)
midnight 每天凌晨
import logging #create logger
logger = logging.getLogger('TEST-LOG')
logger.setLevel(logging.DEBUG) # create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG) # create file handler and set level to warning
fh = logging.FileHandler("access.log")
fh.setLevel(logging.WARNING)
# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') # add formatter to ch and fh
ch.setFormatter(formatter)
fh.setFormatter(formatter) # add ch and fh to logger
logger.addHandler(ch)
logger.addHandler(fh) # 'application' code
logger.debug('debug message')
logger.info('info message')
logger.warn('warn message')
logger.error('error message')
logger.critical('critical message')
文件自动截断例子
import logging from logging import handlers logger = logging.getLogger(__name__) log_file = "timelog.log"
#fh = handlers.RotatingFileHandler(filename=log_file,maxBytes=10,backupCount=3)
fh = handlers.TimedRotatingFileHandler(filename=log_file,when="S",interval=5,backupCount=3) formatter = logging.Formatter('%(asctime)s %(module)s:%(lineno)d %(message)s') fh.setFormatter(formatter) logger.addHandler(fh) logger.warning("test1")
logger.warning("test12")
logger.warning("test13")
logger.warning("test14")
十一、re模块
常用正则表达式符号
'.' 默认匹配除\n之外的任意一个字符,若指定flag DOTALL,则匹配任意字符,包括换行
'^' 匹配字符开头,若指定flags MULTILINE,这种也可以匹配上(r"^a","\nabc\neee",flags=re.MULTILINE)
'$' 匹配字符结尾,或e.search("foo$","bfoo\nsdfsf",flags=re.MULTILINE).group()也可以
'*' 匹配*号前的字符0次或多次,re.findall("ab*","cabb3abcbbac") 结果为['abb', 'ab', 'a']
'+' 匹配前一个字符1次或多次,re.findall("ab+","ab+cd+abb+bba") 结果['ab', 'abb']
'?' 匹配前一个字符1次或0次
'{m}' 匹配前一个字符m次
'{n,m}' 匹配前一个字符n到m次,re.findall("ab{1,3}","abb abc abbcbbb") 结果'abb', 'ab', 'abb']
'|' 匹配|左或|右的字符,re.search("abc|ABC","ABCBabcCD").group() 结果'ABC'
'(...)' 分组匹配,re.search("(abc){2}a(123|456)c", "abcabca456c").group() 结果 abcabca456c '\A' 只从字符开头匹配,re.search("\Aabc","alexabc") 是匹配不到的
'\Z' 匹配字符结尾,同$
'\d' 匹配数字0-9
'\D' 匹配非数字
'\w' 匹配[A-Za-z0-9]
'\W' 匹配非[A-Za-z0-9]
's' 匹配空白字符、\t、\n、\r , re.search("\s+","ab\tc1\n3").group() 结果 '\t' '(?P<name>...)' 分组匹配 re.search("(?P<province>[0-9]{4})(?P<city>[0-9]{2})(?P<birthday>[0-9]{4})","").groupdict("city") 结果{'province': '', 'city': '', 'birthday': ''}
最常用的匹配语法
re.match 从头开始匹配
re.search 匹配包含
re.findall 把所有匹配到的字符放到以列表中的元素返回
re.split 以匹配到的字符当做列表分隔符
re.sub 匹配字符并替换
反斜杠的困扰
与大多数编程语言相同,正则表达式里使用"\"作为转义字符,这就可能造成反斜杠困扰。假如你需要匹配文本中的字符"\",那么使用编程语言表示的正则表达式里将需要4个反斜杠"\\\\":前两个和后两个分别用于在编程语言里转义成反斜杠,转换成两个反斜杠后再在正则表达式里转义成一个反斜杠。Python里的原生字符串很好地解决了这个问题,这个例子中的正则表达式可以使用r"\\"表示。同样,匹配一个数字的"\\d"可以写成r"\d"。有了原生字符串,你再也不用担心是不是漏写了反斜杠,写出来的表达式也更直观。
仅需轻轻知道的几个匹配模式
re.I(re.IGNORECASE): 忽略大小写(括号内是完整写法,下同)
M(MULTILINE): 多行模式,改变'^'和'$'的行为(参见上图)
S(DOTALL): 点任意匹配模式,改变'.'的行为