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

 1 #_*_coding:utf-8_*_
 2 __author__ = 'Alex Li'
 3 
 4 import time
 5 
 6 
 7 # 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
 8 # print(time.altzone)  #返回与utc时间的时间差,以秒计算\
 9 # print(time.asctime()) #返回时间格式"Fri Aug 19 11:14:16 2016",
10 # print(time.localtime()) #返回本地时间 的struct time对象格式
11 # print(time.gmtime(time.time()-800000)) #返回utc时间的struc时间对象格式
12 
13 # print(time.asctime(time.localtime())) #返回时间格式"Fri Aug 19 11:14:16 2016",
14 #print(time.ctime()) #返回Fri Aug 19 12:38:29 2016 格式, 同上
15 
16 
17 
18 # 日期字符串 转成  时间戳
19 # 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
20 # print(string_2_struct)
21 # #
22 # struct_2_stamp = time.mktime(string_2_struct) #将struct时间对象转成时间戳
23 # print(struct_2_stamp)
24 
25 
26 
27 #将时间戳转为字符串格式
28 # print(time.gmtime(time.time()-86640)) #将utc时间戳转换成struct_time格式
29 # 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
30 
31 
32 
33 
34 
35 #时间加减
36 import datetime
37 
38 # print(datetime.datetime.now()) #返回 2016-08-19 12:47:03.941925
39 #print(datetime.date.fromtimestamp(time.time()) )  # 时间戳直接转成日期格式 2016-08-19
40 # print(datetime.datetime.now() )
41 # print(datetime.datetime.now() + datetime.timedelta(3)) #当前时间+3天
42 # print(datetime.datetime.now() + datetime.timedelta(-3)) #当前时间-3天
43 # print(datetime.datetime.now() + datetime.timedelta(hours=3)) #当前时间+3小时
44 # print(datetime.datetime.now() + datetime.timedelta(minutes=30)) #当前时间+30分
45 
46 
47 #
48 # c_time  = datetime.datetime.now()
49 # print(c_time.replace(minute=3,hour=2)) #时间替换
View Code

二、random模块

 随机数

1 import random
2 print random.random()
3 print random.randint(1,2)
4 print random.randrange(1,10)

生成随机验证码

 1 import random
 2 checkcode = ''
 3 for i in range(4):
 4     current = random.randrange(0,4)
 5     if current != i:
 6         temp = chr(random.randint(65,90))
 7     else:
 8         temp = random.randint(0,9)
 9     checkcode += str(temp)
10 print checkcode

三、OS模块

提供对操作系统进行调用的接口

 1 os.getcwd() 获取当前工作目录,即当前python脚本工作的目录路径
 2 os.chdir("dirname")  改变当前脚本工作目录;相当于shell下cd
 3 os.curdir  返回当前目录: ('.')
 4 os.pardir  获取当前目录的父目录字符串名:('..')
 5 os.makedirs('dirname1/dirname2')    可生成多层递归目录
 6 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
 7 os.mkdir('dirname')    生成单级目录;相当于shell中mkdir dirname
 8 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
 9 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
10 os.remove()  删除一个文件
11 os.rename("oldname","newname")  重命名文件/目录
12 os.stat('path/filename')  获取文件/目录信息
13 os.sep    输出操作系统特定的路径分隔符,win下为"\\",Linux下为"/"
14 os.linesep    输出当前平台使用的行终止符,win下为"\t\n",Linux下为"\n"
15 os.pathsep    输出用于分割文件路径的字符串
16 os.name    输出字符串指示当前使用平台。win->'nt'; Linux->'posix'
17 os.system("bash command")  运行shell命令,直接显示
18 os.environ  获取系统环境变量
19 os.path.abspath(path)  返回path规范化的绝对路径
20 os.path.split(path)  将path分割成目录和文件名二元组返回
21 os.path.dirname(path)  返回path的目录。其实就是os.path.split(path)的第一个元素
22 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
23 os.path.exists(path)  如果path存在,返回True;如果path不存在,返回False
24 os.path.isabs(path)  如果path是绝对路径,返回True
25 os.path.isfile(path)  如果path是一个存在的文件,返回True。否则返回False
26 os.path.isdir(path)  如果path是一个存在的目录,则返回True。否则返回False
27 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
28 os.path.getatime(path)  返回path所指向的文件或者目录的最后存取时间
29 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

1 sys.argv           命令行参数List,第一个元素是程序本身路径
2 sys.exit(n)        退出程序,正常退出时exit(0)
3 sys.version        获取Python解释程序的版本信息
4 sys.maxint         最大的Int值
5 sys.path           返回模块的搜索路径,初始化时使用PYTHONPATH环境变量的值
6 sys.platform       返回操作系统平台名称
7 sys.stdout.write('please:')
8 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

1 def copyfileobj(fsrc, fdst, length=16*1024):
2     """copy data from file-like object fsrc to file-like object fdst"""
3     while 1:
4         buf = fsrc.read(length)
5         if not buf:
6             break
7         fdst.write(buf)
View Code

shutil.copyfile(src, dst)
拷贝文件

 1 def copyfile(src, dst):
 2     """Copy data from src to dst"""
 3     if _samefile(src, dst):
 4         raise Error("`%s` and `%s` are the same file" % (src, dst))
 5 
 6     for fn in [src, dst]:
 7         try:
 8             st = os.stat(fn)
 9         except OSError:
10             # File most likely does not exist
11             pass
12         else:
13             # XXX What about other special files? (sockets, devices...)
14             if stat.S_ISFIFO(st.st_mode):
15                 raise SpecialFileError("`%s` is a named pipe" % fn)
16 
17     with open(src, 'rb') as fsrc:
18         with open(dst, 'wb') as fdst:
19             copyfileobj(fsrc, fdst)
View Code

shutil.copymode(src, dst)
仅拷贝权限。内容、组、用户均不变

1 def copymode(src, dst):
2     """Copy mode bits from src to dst"""
3     if hasattr(os, 'chmod'):
4         st = os.stat(src)
5         mode = stat.S_IMODE(st.st_mode)
6         os.chmod(dst, mode)
View Code

shutil.copystat(src, dst)
拷贝状态的信息,包括:mode bits, atime, mtime, flags

 1 def copystat(src, dst):
 2     """Copy all stat info (mode bits, atime, mtime, flags) from src to dst"""
 3     st = os.stat(src)
 4     mode = stat.S_IMODE(st.st_mode)
 5     if hasattr(os, 'utime'):
 6         os.utime(dst, (st.st_atime, st.st_mtime))
 7     if hasattr(os, 'chmod'):
 8         os.chmod(dst, mode)
 9     if hasattr(os, 'chflags') and hasattr(st, 'st_flags'):
10         try:
11             os.chflags(dst, st.st_flags)
12         except OSError, why:
13             for err in 'EOPNOTSUPP', 'ENOTSUP':
14                 if hasattr(errno, err) and why.errno == getattr(errno, err):
15                     break
16             else:
17                 raise
View Code

shutil.copy(src, dst)
拷贝文件和权限

 1 def copy(src, dst):
 2     """Copy data and mode bits ("cp src dst").
 3 
 4     The destination may be a directory.
 5 
 6     """
 7     if os.path.isdir(dst):
 8         dst = os.path.join(dst, os.path.basename(src))
 9     copyfile(src, dst)
10     copymode(src, dst)
View Code

shutil.copy2(src, dst)
拷贝文件和状态信息

 1 def copy2(src, dst):
 2     """Copy data and all stat info ("cp -p src dst").
 3 
 4     The destination may be a directory.
 5 
 6     """
 7     if os.path.isdir(dst):
 8         dst = os.path.join(dst, os.path.basename(src))
 9     copyfile(src, dst)
10     copystat(src, dst)
View Code

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*'))

 1 def ignore_patterns(*patterns):
 2     """Function that can be used as copytree() ignore parameter.
 3 
 4     Patterns is a sequence of glob-style patterns
 5     that are used to exclude files"""
 6     def _ignore_patterns(path, names):
 7         ignored_names = []
 8         for pattern in patterns:
 9             ignored_names.extend(fnmatch.filter(names, pattern))
10         return set(ignored_names)
11     return _ignore_patterns
12 
13 def copytree(src, dst, symlinks=False, ignore=None):
14     """Recursively copy a directory tree using copy2().
15 
16     The destination directory must not already exist.
17     If exception(s) occur, an Error is raised with a list of reasons.
18 
19     If the optional symlinks flag is true, symbolic links in the
20     source tree result in symbolic links in the destination tree; if
21     it is false, the contents of the files pointed to by symbolic
22     links are copied.
23 
24     The optional ignore argument is a callable. If given, it
25     is called with the `src` parameter, which is the directory
26     being visited by copytree(), and `names` which is the list of
27     `src` contents, as returned by os.listdir():
28 
29         callable(src, names) -> ignored_names
30 
31     Since copytree() is called recursively, the callable will be
32     called once for each directory that is copied. It returns a
33     list of names relative to the `src` directory that should
34     not be copied.
35 
36     XXX Consider this example code rather than the ultimate tool.
37 
38     """
39     names = os.listdir(src)
40     if ignore is not None:
41         ignored_names = ignore(src, names)
42     else:
43         ignored_names = set()
44 
45     os.makedirs(dst)
46     errors = []
47     for name in names:
48         if name in ignored_names:
49             continue
50         srcname = os.path.join(src, name)
51         dstname = os.path.join(dst, name)
52         try:
53             if symlinks and os.path.islink(srcname):
54                 linkto = os.readlink(srcname)
55                 os.symlink(linkto, dstname)
56             elif os.path.isdir(srcname):
57                 copytree(srcname, dstname, symlinks, ignore)
58             else:
59                 # Will raise a SpecialFileError for unsupported file types
60                 copy2(srcname, dstname)
61         # catch the Error from the recursive copytree so that we can
62         # continue with other files
63         except Error, err:
64             errors.extend(err.args[0])
65         except EnvironmentError, why:
66             errors.append((srcname, dstname, str(why)))
67     try:
68         copystat(src, dst)
69     except OSError, why:
70         if WindowsError is not None and isinstance(why, WindowsError):
71             # Copying file access times may fail on Windows
72             pass
73         else:
74             errors.append((src, dst, str(why)))
75     if errors:
76         raise Error, errors
View Code

shutil.rmtree(path[, ignore_errors[, onerror]])
递归的去删除文件

 1 def rmtree(path, ignore_errors=False, onerror=None):
 2     """Recursively delete a directory tree.
 3 
 4     If ignore_errors is set, errors are ignored; otherwise, if onerror
 5     is set, it is called to handle the error with arguments (func,
 6     path, exc_info) where func is os.listdir, os.remove, or os.rmdir;
 7     path is the argument to that function that caused it to fail; and
 8     exc_info is a tuple returned by sys.exc_info().  If ignore_errors
 9     is false and onerror is None, an exception is raised.
10 
11     """
12     if ignore_errors:
13         def onerror(*args):
14             pass
15     elif onerror is None:
16         def onerror(*args):
17             raise
18     try:
19         if os.path.islink(path):
20             # symlinks to directories are forbidden, see bug #1669
21             raise OSError("Cannot call rmtree on a symbolic link")
22     except OSError:
23         onerror(os.path.islink, path, sys.exc_info())
24         # can't continue even if onerror hook returns
25         return
26     names = []
27     try:
28         names = os.listdir(path)
29     except os.error, err:
30         onerror(os.listdir, path, sys.exc_info())
31     for name in names:
32         fullname = os.path.join(path, name)
33         try:
34             mode = os.lstat(fullname).st_mode
35         except os.error:
36             mode = 0
37         if stat.S_ISDIR(mode):
38             rmtree(fullname, ignore_errors, onerror)
39         else:
40             try:
41                 os.remove(fullname)
42             except os.error, err:
43                 onerror(os.remove, fullname, sys.exc_info())
44     try:
45         os.rmdir(path)
46     except os.error:
47         onerror(os.rmdir, path, sys.exc_info())
View Code

shutil.move(src, dst)
递归的去移动文件

 1 def move(src, dst):
 2     """Recursively move a file or directory to another location. This is
 3     similar to the Unix "mv" command.
 4 
 5     If the destination is a directory or a symlink to a directory, the source
 6     is moved inside the directory. The destination path must not already
 7     exist.
 8 
 9     If the destination already exists but is not a directory, it may be
10     overwritten depending on os.rename() semantics.
11 
12     If the destination is on our current filesystem, then rename() is used.
13     Otherwise, src is copied to the destination and then removed.
14     A lot more could be done here...  A look at a mv.c shows a lot of
15     the issues this implementation glosses over.
16 
17     """
18     real_dst = dst
19     if os.path.isdir(dst):
20         if _samefile(src, dst):
21             # We might be on a case insensitive filesystem,
22             # perform the rename anyway.
23             os.rename(src, dst)
24             return
25 
26         real_dst = os.path.join(dst, _basename(src))
27         if os.path.exists(real_dst):
28             raise Error, "Destination path '%s' already exists" % real_dst
29     try:
30         os.rename(src, real_dst)
31     except OSError:
32         if os.path.isdir(src):
33             if _destinsrc(src, dst):
34                 raise Error, "Cannot move a directory '%s' into itself '%s'." % (src, dst)
35             copytree(src, real_dst, symlinks=True)
36             rmtree(src)
37         else:
38             copy2(src, real_dst)
39             os.unlink(src)
View Code

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
1 #将 /Users/wupeiqi/Downloads/test 下的文件打包放置当前程序目录
2  
3 import shutil
4 ret = shutil.make_archive("wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test')
5  
6  
7 #将 /Users/wupeiqi/Downloads/test 下的文件打包放置 /Users/wupeiqi/目录
8 import shutil
9 ret = shutil.make_archive("/Users/wupeiqi/wwwwwwwwww", 'gztar', root_dir='/Users/wupeiqi/Downloads/test')
 1 def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
 2                  dry_run=0, owner=None, group=None, logger=None):
 3     """Create an archive file (eg. zip or tar).
 4 
 5     'base_name' is the name of the file to create, minus any format-specific
 6     extension; 'format' is the archive format: one of "zip", "tar", "bztar"
 7     or "gztar".
 8 
 9     'root_dir' is a directory that will be the root directory of the
10     archive; ie. we typically chdir into 'root_dir' before creating the
11     archive.  'base_dir' is the directory where we start archiving from;
12     ie. 'base_dir' will be the common prefix of all files and
13     directories in the archive.  'root_dir' and 'base_dir' both default
14     to the current directory.  Returns the name of the archive file.
15 
16     'owner' and 'group' are used when creating a tar archive. By default,
17     uses the current owner and group.
18     """
19     save_cwd = os.getcwd()
20     if root_dir is not None:
21         if logger is not None:
22             logger.debug("changing into '%s'", root_dir)
23         base_name = os.path.abspath(base_name)
24         if not dry_run:
25             os.chdir(root_dir)
26 
27     if base_dir is None:
28         base_dir = os.curdir
29 
30     kwargs = {'dry_run': dry_run, 'logger': logger}
31 
32     try:
33         format_info = _ARCHIVE_FORMATS[format]
34     except KeyError:
35         raise ValueError, "unknown archive format '%s'" % format
36 
37     func = format_info[0]
38     for arg, val in format_info[1]:
39         kwargs[arg] = val
40 
41     if format != 'zip':
42         kwargs['owner'] = owner
43         kwargs['group'] = group
44 
45     try:
46         filename = func(base_name, base_dir, **kwargs)
47     finally:
48         if root_dir is not None:
49             if logger is not None:
50                 logger.debug("changing back to '%s'", save_cwd)
51             os.chdir(save_cwd)
52 
53     return filename
View Code

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

 1 import shelve
 2  
 3 d = shelve.open('shelve_test') #打开一个文件
 4  
 5 class Test(object):
 6     def __init__(self,n):
 7         self.n = n
 8  
 9  
10 t = Test(123) 
11 t2 = Test(123334)
12  
13 name = ["alex","rain","test"]
14 d["test"] = name #持久化列表
15 d["t1"] = t      #持久化类
16 d["t2"] = t2
17  
18 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:

 1 <?xml version="1.0"?>
 2 <data>
 3     <country name="Liechtenstein">
 4         <rank updated="yes">2</rank>
 5         <year>2008</year>
 6         <gdppc>141100</gdppc>
 7         <neighbor name="Austria" direction="E"/>
 8         <neighbor name="Switzerland" direction="W"/>
 9     </country>
10     <country name="Singapore">
11         <rank updated="yes">5</rank>
12         <year>2011</year>
13         <gdppc>59900</gdppc>
14         <neighbor name="Malaysia" direction="N"/>
15     </country>
16     <country name="Panama">
17         <rank updated="yes">69</rank>
18         <year>2011</year>
19         <gdppc>13600</gdppc>
20         <neighbor name="Costa Rica" direction="W"/>
21         <neighbor name="Colombia" direction="E"/>
22     </country>
23 </data>
View Code

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

 1 import xml.etree.ElementTree as ET
 2  
 3 tree = ET.parse("xmltest.xml")
 4 root = tree.getroot()
 5 print(root.tag)
 6  
 7 #遍历xml文档
 8 for child in root:
 9     print(child.tag, child.attrib)
10     for i in child:
11         print(i.tag,i.text)
12  
13 #只遍历year 节点
14 for node in root.iter('year'):
15     print(node.tag,node.text)

修改和删除xml文档内容

 1 import xml.etree.ElementTree as ET
 2  
 3 tree = ET.parse("xmltest.xml")
 4 root = tree.getroot()
 5  
 6 #修改
 7 for node in root.iter('year'):
 8     new_year = int(node.text) + 1
 9     node.text = str(new_year)
10     node.set("updated","yes")
11  
12 tree.write("xmltest.xml")
13  
14  
15 #删除node
16 for country in root.findall('country'):
17    rank = int(country.find('rank').text)
18    if rank > 50:
19      root.remove(country)
20  
21 tree.write('output.xml')
View Code

自己创建xml文档

 1 import xml.etree.ElementTree as ET
 2  
 3  
 4 new_xml = ET.Element("namelist")
 5 name = ET.SubElement(new_xml,"name",attrib={"enrolled":"yes"})
 6 age = ET.SubElement(name,"age",attrib={"checked":"no"})
 7 sex = ET.SubElement(name,"sex")
 8 sex.text = '33'
 9 name2 = ET.SubElement(new_xml,"name",attrib={"enrolled":"no"})
10 age = ET.SubElement(name2,"age")
11 age.text = '19'
12  
13 et = ET.ElementTree(new_xml) #生成文档对象
14 et.write("test.xml", encoding="utf-8",xml_declaration=True)
15  
16 ET.dump(new_xml) #打印生成的格式
View Code

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

 1 [DEFAULT]
 2 ServerAliveInterval = 45
 3 Compression = yes
 4 CompressionLevel = 9
 5 ForwardX11 = yes
 6  
 7 [bitbucket.org]
 8 User = hg
 9  
10 [topsecret.server.com]
11 Port = 50022
12 ForwardX11 = no

如果想用python生成一个这样的文档怎么做呢?

 1 import configparser
 2  
 3 config = configparser.ConfigParser()
 4 config["DEFAULT"] = {'ServerAliveInterval': '45',
 5                       'Compression': 'yes',
 6                      'CompressionLevel': '9'}
 7  
 8 config['bitbucket.org'] = {}
 9 config['bitbucket.org']['User'] = 'hg'
10 config['topsecret.server.com'] = {}
11 topsecret = config['topsecret.server.com']
12 topsecret['Host Port'] = '50022'     # mutates the parser
13 topsecret['ForwardX11'] = 'no'  # same here
14 config['DEFAULT']['ForwardX11'] = 'yes'
15 with open('example.ini', 'w') as configfile:
16    config.write(configfile)

写完了还可以再读出来哈。

 1 >>> import configparser
 2 >>> config = configparser.ConfigParser()
 3 >>> config.sections()
 4 []
 5 >>> config.read('example.ini')
 6 ['example.ini']
 7 >>> config.sections()
 8 ['bitbucket.org', 'topsecret.server.com']
 9 >>> 'bitbucket.org' in config
10 True
11 >>> 'bytebong.com' in config
12 False
13 >>> config['bitbucket.org']['User']
14 'hg'
15 >>> config['DEFAULT']['Compression']
16 'yes'
17 >>> topsecret = config['topsecret.server.com']
18 >>> topsecret['ForwardX11']
19 'no'
20 >>> topsecret['Port']
21 '50022'
22 >>> for key in config['bitbucket.org']: print(key)
23 ...
24 user
25 compressionlevel
26 serveraliveinterval
27 compression
28 forwardx11
29 >>> config['bitbucket.org']['ForwardX11']
30 'yes'
View Code

configparser增删改查语法

 1 [section1]
 2 k1 = v1
 3 k2:v2
 4   
 5 [section2]
 6 k1 = v1
 7  
 8 import ConfigParser
 9   
10 config = ConfigParser.ConfigParser()
11 config.read('i.cfg')
12   
13 # ########## 读 ##########
14 #secs = config.sections()
15 #print secs
16 #options = config.options('group2')
17 #print options
18   
19 #item_list = config.items('group2')
20 #print item_list
21   
22 #val = config.get('group1','key')
23 #val = config.getint('group1','key')
24   
25 # ########## 改写 ##########
26 #sec = config.remove_section('group1')
27 #config.write(open('i.cfg', "w"))
28   
29 #sec = config.has_section('wupeiqi')
30 #sec = config.add_section('wupeiqi')
31 #config.write(open('i.cfg', "w"))
32   
33   
34 #config.set('group2','k1',11111)
35 #config.write(open('i.cfg', "w"))
36   
37 #config.remove_option('group2','age')
38 #config.write(open('i.cfg', "w"))
View Code

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

 1 import hashlib
 2  
 3 m = hashlib.md5()
 4 m.update(b"Hello")
 5 m.update(b"It's me")
 6 print(m.digest())
 7 m.update(b"It's been a long time since last time we ...")
 8  
 9 print(m.digest()) #2进制格式hash
10 print(len(m.hexdigest())) #16进制格式hash
11 '''
12 def digest(self, *args, **kwargs): # real signature unknown
13     """ Return the digest value as a string of binary data. """
14     pass
15  
16 def hexdigest(self, *args, **kwargs): # real signature unknown
17     """ Return the digest value as a string of hexadecimal digits. """
18     pass
19  
20 '''
21 import hashlib
22  
23 # ######## md5 ########
24  
25 hash = hashlib.md5()
26 hash.update('admin')
27 print(hash.hexdigest())
28  
29 # ######## sha1 ########
30  
31 hash = hashlib.sha1()
32 hash.update('admin')
33 print(hash.hexdigest())
34  
35 # ######## sha256 ########
36  
37 hash = hashlib.sha256()
38 hash.update('admin')
39 print(hash.hexdigest())
40  
41  
42 # ######## sha384 ########
43  
44 hash = hashlib.sha384()
45 hash.update('admin')
46 print(hash.hexdigest())
47  
48 # ######## sha512 ########
49  
50 hash = hashlib.sha512()
51 hash.update('admin')
52 print(hash.hexdigest())
View Code

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。

1 import hmac
2 h = hmac.new(b'天王盖地虎', b'宝塔镇河妖')
3 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

1 import logging
2  
3 logging.warning("user [alex] attempted wrong password more than 3 times")
4 logging.critical("server is down")
5  
6 #输出
7 WARNING:root:user [alex] attempted wrong password more than 3 times
8 CRITICAL:root:server is down

看一下这几个日志级别分别代表什么意思

LevelWhen 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

1 import logging
2  
3 logging.basicConfig(filename='example.log',level=logging.INFO)
4 logging.debug('This message should go to the log file')
5 logging.info('So should this')
6 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!

1 import logging
2 logging.basicConfig(format='%(asctime)s %(message)s', datefmt='%m/%d/%Y %I:%M:%S %p')
3 logging.warning('is when this event was logged.')
4  
5 #输出
6 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

 1 import logging
 2  
 3 #create logger
 4 logger = logging.getLogger('TEST-LOG')
 5 logger.setLevel(logging.DEBUG)
 6  
 7  
 8 # create console handler and set level to debug
 9 ch = logging.StreamHandler()
10 ch.setLevel(logging.DEBUG)
11  
12 # create file handler and set level to warning
13 fh = logging.FileHandler("access.log")
14 fh.setLevel(logging.WARNING)
15 # create formatter
16 formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
17  
18 # add formatter to ch and fh
19 ch.setFormatter(formatter)
20 fh.setFormatter(formatter)
21  
22 # add ch and fh to logger
23 logger.addHandler(ch)
24 logger.addHandler(fh)
25  
26 # 'application' code
27 logger.debug('debug message')
28 logger.info('info message')
29 logger.warn('warn message')
30 logger.error('error message')
31 logger.critical('critical message')
View Code

文件自动截断例子

 1 import logging
 2 
 3 from logging import handlers
 4 
 5 logger = logging.getLogger(__name__)
 6 
 7 log_file = "timelog.log"
 8 #fh = handlers.RotatingFileHandler(filename=log_file,maxBytes=10,backupCount=3)
 9 fh = handlers.TimedRotatingFileHandler(filename=log_file,when="S",interval=5,backupCount=3)
10 
11 
12 formatter = logging.Formatter('%(asctime)s %(module)s:%(lineno)d %(message)s')
13 
14 fh.setFormatter(formatter)
15 
16 logger.addHandler(fh)
17 
18 
19 logger.warning("test1")
20 logger.warning("test12")
21 logger.warning("test13")
22 logger.warning("test14")
View Code

十一、re模块

常用正则表达式符号

 1 '.'     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
 2 '^'     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)
 3 '$'     匹配字符结尾,或e.search("foo$","bfoo\nsdfsf",flags=re.MULTILINE).group()也可以
 4 '*'     匹配*号前的字符0次或多次,re.findall("ab*","cabb3abcbbac")  结果为['abb', 'ab', 'a']
 5 '+'     匹配前一个字符1次或多次,re.findall("ab+","ab+cd+abb+bba") 结果['ab', 'abb']
 6 '?'     匹配前一个字符1次或0次
 7 '{m}'   匹配前一个字符m次
 8 '{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']
 9 '|'     匹配|左或|右的字符,re.search("abc|ABC","ABCBabcCD").group() 结果'ABC'
10 '(...)' 分组匹配,re.search("(abc){2}a(123|456)c", "abcabca456c").group() 结果 abcabca456c
11  
12  
13 '\A'    只从字符开头匹配,re.search("\Aabc","alexabc") 是匹配不到的
14 '\Z'    匹配字符结尾,同$
15 '\d'    匹配数字0-9
16 '\D'    匹配非数字
17 '\w'    匹配[A-Za-z0-9]
18 '\W'    匹配非[A-Za-z0-9]
19 's'     匹配空白字符、\t、\n、\r , re.search("\s+","ab\tc1\n3").group() 结果 '\t'
20  
21 '(?P<name>...)' 分组匹配 re.search("(?P<province>[0-9]{4})(?P<city>[0-9]{2})(?P<birthday>[0-9]{4})","371481199306143242").groupdict("city") 结果{'province': '3714', 'city': '81', 'birthday': '1993'}

最常用的匹配语法

1 re.match 从头开始匹配
2 re.search 匹配包含
3 re.findall 把所有匹配到的字符放到以列表中的元素返回
4 re.split 以匹配到的字符当做列表分隔符
5 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

1 re.I(re.IGNORECASE): 忽略大小写(括号内是完整写法,下同)
2 M(MULTILINE): 多行模式,改变'^''$'的行为(参见上图)
3 S(DOTALL): 点任意匹配模式,改变'.'的行为