import hashlib
md5 = hashlib.md5()
md5.update(b'how to use md5 in ')
md5.update(b'python hashlib?')
print(md5.hexdigest())d03b3899d2d6ac723a4e70db7ca2b83f

for ii in i.xpath('div/div/img/@data-original'):img_url = ii[2:]wei = img_url[-4:]md5 = hashlib.md5(wei.encode("gb2312"))listss = md5.hexdigest()if listss in ['.jpg','.gif','.png']:make_files(img_name + '\\' + str(random.randint(1, 99999999999999)) + listss, img_url)else:print(img_url)

import hashlib
passwds=['alex3714','alex1313','alex94139413','alex123456','123456alex','a123lex',]
def make_passwd_dic(passwds):dic={}for passwd in passwds:m=hashlib.md5()m.update(passwd.encode('utf-8'))dic[passwd]=m.hexdigest()return dicdef break_code(cryptograph,passwd_dic):for k,v in passwd_dic.items():if v == cryptograph:print('密码是===>\033[46m%s\033[0m' %k)cryptograph='aee949757a2e698417463d47acac93df'
break_code(cryptograph,make_passwd_dic(passwds))

import hmac
h = hmac.new('alvin'.encode('utf8'))
h.update('hello'.encode('utf8'))
print (h.hexdigest())#320df9832eab4c038b6c1d7ed73a5940
要想保证hmac最终结果一致，必须保证：
1:hmac.new括号内指定的初始key一样
2:无论update多少次，校验的内容累加到一起是一样的内容import hmach1=hmac.new(b'egon')
h1.update(b'hello')
h1.update(b'world')
print(h1.hexdigest())h2=hmac.new(b'egon')
h2.update(b'helloworld')
print(h2.hexdigest())h3=hmac.new(b'egonhelloworld')
print(h3.hexdigest())'''
f1bf38d054691688f89dcd34ac3c27f2
f1bf38d054691688f89dcd34ac3c27f2
bcca84edd9eeb86f30539922b28f3981
'''

任何允许用户登录的网站都会存储用户登录的用户名和口令。如何存储用户名和口令呢？方法是存到数据库表中：name    | password
michael | 123456
bob     | abc999
alice   | alice2008
如果以明文保存用户口令，如果数据库泄露，所有用户的口令就落入黑客的手里。此外，网站运维人员是可以访问数据库的，也就是能获取到所有用户的口令。正确的保存口令的方式是不存储用户的明文口令，而是存储用户口令的摘要，比如MD5：username | password
michael  | e10adc3949ba59abbe56e057f20f883e
bob      | 878ef96e86145580c38c87f0410ad153
alice    | 99b1c2188db85afee403b1536010c2c9
考虑这么个情况，很多用户喜欢用123456，888888，password这些简单的口令，于是，黑客可以事先计算出这些常用口令的MD5值，得到一个反推表：'e10adc3949ba59abbe56e057f20f883e': '123456'
'21218cca77804d2ba1922c33e0151105': '888888'
'5f4dcc3b5aa765d61d8327deb882cf99': 'password'
这样，无需破解，只需要对比数据库的MD5，黑客就获得了使用常用口令的用户账号。
对于用户来讲，当然不要使用过于简单的口令。但是，我们能否在程序设计上对简单口令加强保护呢？由于常用口令的MD5值很容易被计算出来，所以，要确保存储的用户口令不是那些已经被计算出来的常用口令的MD5，这一方法通过对原始口令加一个复杂字符串来实现，俗称“加盐”：hashlib.md5("salt".encode("utf8"))
经过Salt处理的MD5口令，只要Salt不被黑客知道，即使用户输入简单口令，也很难通过MD5反推明文口令。但是如果有两个用户都使用了相同的简单口令比如123456，在数据库中，将存储两条相同的MD5值，这说明这两个用户的口令是一样的。有没有办法让使用相同口令的用户存储不同的MD5呢？如果假定用户无法修改登录名，就可以通过把登录名作为Salt的一部分来计算MD5，从而实现相同口令的用户也存储不同的MD5。摘要算法在很多地方都有广泛的应用。要注意摘要算法不是加密算法，不能用于加密（因为无法通过摘要反推明文），只能用于防篡改，但是它的单向计算特性决定了可以在不存储明文口令的情况下验证用户口令。

>> os.system('uname -a')
Darwin Alexs-MacBook-Pro.local 15.6.0 Darwin Kernel Version 15.6.0: Sun Jun  4 21:43:07 PDT 2017; root:xnu-3248.70.3~1/RELEASE_X86_64 x86_64
0

#执行命令，返回命令执行状态 ， 0 or 非0
>>> retcode = subprocess.call(["ls", "-l"])#执行命令，如果命令结果为0，就正常返回，否则抛异常
>>> subprocess.check_call(["ls", "-l"])
0#接收字符串格式命令，返回元组形式，第1个元素是执行状态，第2个是命令结果
>>> subprocess.getstatusoutput('ls /bin/ls')
(0, '/bin/ls')#接收字符串格式命令，并返回结果
>>> subprocess.getoutput('ls /bin/ls')
'/bin/ls'#执行命令，并返回结果，注意是返回结果，不是打印，下例结果返回给res
>>> res=subprocess.check_output(['ls','-l'])
>>> res
b'total 0\ndrwxr-xr-x 12 alex staff 408 Nov 2 11:05 OldBoyCRM\n'

args：shell命令，可以是字符串或者序列类型（如：list，元组）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。

poll()Check if child process has terminated. Returns returncode检查子进程是否已终止。返回returncodewait()Wait for child process to terminate. Returns returncode attribute.等待子进程终止。返回returncode属性terminate()终止所启动的进程   Terminate the process with SIGTERMkill()杀死所启动的进程    Kill the process with SIGKILLcommunicate()与启动的进程交互，发送数据到stdin,并从stdout接收输出，然后等待任务结束send_signal(signal.xxx)发送系统信号pid 拿到所启动进程的进程号

>>> a = subprocess.Popen('python3 guess_age.py',stdout=subprocess.PIPE,stderr=subprocess.PIPE,stdin=subprocess.PIPE,shell=True)>>> a.communicate(b'22')(b'your guess:try bigger\n', b'')

import logginglogging.debug('调试debug')
logging.info('消息info')
logging.warning('警告warn')
logging.error('错误error')
logging.critical('严重critical')'''
WARNING:root:警告warn
ERROR:root:错误error
CRITICAL:root:严重critical
'''

Logger也是第一个基于级别过滤消息的人——如果您将Logger设置为INFO，所有的处理程序都设置为DEBUG，您仍然不会在处理程序上接收调试消息——它们将被Logger自己拒绝。如果您将logger设置为DEBUG，但是所有的处理程序都设置为INFO，那么您也不会收到任何调试消息——因为当记录器说“ok，处理这个”时，处理程序会拒绝它(DEBUG < INFO)。#验证
import loggingform=logging.Formatter('%(asctime)s - %(name)s - %(levelname)s -%(module)s:  %(message)s',datefmt='%Y-%m-%d %H:%M:%S %p',)ch=logging.StreamHandler()ch.setFormatter(form)
# ch.setLevel(10)
ch.setLevel(20)l1=logging.getLogger('root')
# l1.setLevel(20)
l1.setLevel(10)
l1.addHandler(ch)l1.debug('l1 debug')

import loggingformatter=logging.Formatter('%(asctime)s - %(name)s - %(levelname)s -%(module)s:  %(message)s',datefmt='%Y-%m-%d %H:%M:%S %p',)ch=logging.StreamHandler()
ch.setFormatter(formatter)logger1=logging.getLogger('root')
logger2=logging.getLogger('root.child1')
logger3=logging.getLogger('root.child1.child2')logger1.addHandler(ch)
logger2.addHandler(ch)
logger3.addHandler(ch)
logger1.setLevel(10)
logger2.setLevel(10)
logger3.setLevel(10)logger1.debug('log1 debug')
logger2.debug('log2 debug')
logger3.debug('log3 debug')
'''
2017-07-28 22:22:05 PM - root - DEBUG -test:  log1 debug
2017-07-28 22:22:05 PM - root.child1 - DEBUG -test:  log2 debug
2017-07-28 22:22:05 PM - root.child1 - DEBUG -test:  log2 debug
2017-07-28 22:22:05 PM - root.child1.child2 - DEBUG -test:  log3 debug
2017-07-28 22:22:05 PM - root.child1.child2 - DEBUG -test:  log3 debug
2017-07-28 22:22:05 PM - root.child1.child2 - DEBUG -test:  log3 debug

"""
logging配置
"""import os
import logging.config# 定义三种日志输出格式 开始

standard_format = '[%(asctime)s][%(threadName)s:%(thread)d][task_id:%(name)s][%(filename)s:%(lineno)d]' \'[%(levelname)s][%(message)s]' #其中name为getlogger指定的名字

simple_format = '[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d]%(message)s'id_simple_format = '[%(levelname)s][%(asctime)s] %(message)s'# 定义日志输出格式 结束

logfile_dir = os.path.dirname(os.path.abspath(__file__))  # log文件的目录

logfile_name = 'all2.log'  # log文件名# 如果不存在定义的日志目录就创建一个
if not os.path.isdir(logfile_dir):os.mkdir(logfile_dir)# log文件的全路径
logfile_path = os.path.join(logfile_dir, logfile_name)# log配置字典
LOGGING_DIC = {'version': 1,'disable_existing_loggers': False,'formatters': {'standard': {'format': standard_format},'simple': {'format': simple_format},},'filters': {},'handlers': {#打印到终端的日志'console': {'level': 'DEBUG','class': 'logging.StreamHandler',  # 打印到屏幕'formatter': 'simple'},#打印到文件的日志,收集info及以上的日志'default': {'level': 'DEBUG','class': 'logging.handlers.RotatingFileHandler',  # 保存到文件'formatter': 'standard','filename': logfile_path,  # 日志文件'maxBytes': 1024*1024*5,  # 日志大小 5M'backupCount': 5,'encoding': 'utf-8',  # 日志文件的编码，再也不用担心中文log乱码了
        },},'loggers': {#logging.getLogger(__name__)拿到的logger配置'': {'handlers': ['default', 'console'],  # 这里把上面定义的两个handler都加上，即log数据既写入文件又打印到屏幕'level': 'DEBUG','propagate': True,  # 向上（更高level的logger）传递
        },},
}def load_my_logging_cfg():logging.config.dictConfig(LOGGING_DIC)  # 导入上面定义的logging配置logger = logging.getLogger(__name__)  # 生成一个log实例logger.info('It works!')  # 记录该文件的运行状态if __name__ == '__main__':load_my_logging_cfg()

#logging_config.py
LOGGING = {'version': 1,'disable_existing_loggers': False,'formatters': {'standard': {'format': '[%(asctime)s][%(threadName)s:%(thread)d][task_id:%(name)s][%(filename)s:%(lineno)d]''[%(levelname)s][%(message)s]'},'simple': {'format': '[%(levelname)s][%(asctime)s][%(filename)s:%(lineno)d]%(message)s'},'collect': {'format': '%(message)s'}},'filters': {'require_debug_true': {'()': 'django.utils.log.RequireDebugTrue',},},'handlers': {#打印到终端的日志'console': {'level': 'DEBUG','filters': ['require_debug_true'],'class': 'logging.StreamHandler','formatter': 'simple'},#打印到文件的日志,收集info及以上的日志'default': {'level': 'INFO','class': 'logging.handlers.RotatingFileHandler',  # 保存到文件，自动切'filename': os.path.join(BASE_LOG_DIR, "xxx_info.log"),  # 日志文件'maxBytes': 1024 * 1024 * 5,  # 日志大小 5M'backupCount': 3,'formatter': 'standard','encoding': 'utf-8',},#打印到文件的日志:收集错误及以上的日志'error': {'level': 'ERROR','class': 'logging.handlers.RotatingFileHandler',  # 保存到文件，自动切'filename': os.path.join(BASE_LOG_DIR, "xxx_err.log"),  # 日志文件'maxBytes': 1024 * 1024 * 5,  # 日志大小 5M'backupCount': 5,'formatter': 'standard','encoding': 'utf-8',},#打印到文件的日志'collect': {'level': 'INFO','class': 'logging.handlers.RotatingFileHandler',  # 保存到文件，自动切'filename': os.path.join(BASE_LOG_DIR, "xxx_collect.log"),'maxBytes': 1024 * 1024 * 5,  # 日志大小 5M'backupCount': 5,'formatter': 'collect','encoding': "utf-8"}},'loggers': {#logging.getLogger(__name__)拿到的logger配置'': {'handlers': ['default', 'console', 'error'],'level': 'DEBUG','propagate': True,},#logging.getLogger('collect')拿到的logger配置'collect': {'handlers': ['console', 'collect'],'level': 'INFO',}},
}# -----------
# 用法:拿到俩个logger

logger = logging.getLogger(__name__) #线上正常的日志
collect_logger = logging.getLogger("collect") #领导说,需要为领导们单独定制领导们看的日志

r"""Support for regular expressions (RE).This module provides regular expression matching operations similar to
those found in Perl.  It supports both 8-bit and Unicode strings; both
the pattern and the strings being processed can contain null bytes and
characters outside the US ASCII range.Regular expressions can contain both special and ordinary characters.
Most ordinary characters, like "A", "a", or "0", are the simplest
regular expressions; they simply match themselves.  You can
concatenate ordinary characters, so last matches the string 'last'.The special characters are:"."      Matches any character except a newline."^"      Matches the start of the string."$"      Matches the end of the string or just before the newline atthe end of the string."*"      Matches 0 or more (greedy) repetitions of the preceding RE.Greedy means that it will match as many repetitions as possible."+"      Matches 1 or more (greedy) repetitions of the preceding RE."?"      Matches 0 or 1 (greedy) of the preceding RE.*?,+?,?? Non-greedy versions of the previous three special characters.{m,n}    Matches from m to n repetitions of the preceding RE.{m,n}?   Non-greedy version of the above."\\"     Either escapes special characters or signals a special sequence.[]       Indicates a set of characters.A "^" as the first character indicates a complementing set."|"      A|B, creates an RE that will match either A or B.(...)    Matches the RE inside the parentheses.The contents can be retrieved or matched later in the string.(?aiLmsux) Set the A, I, L, M, S, U, or X flag for the RE (see below).(?:...)  Non-grouping version of regular parentheses.(?P<name>...) The substring matched by the group is accessible by name.(?P=name)     Matches the text matched earlier by the group named name.(?#...)  A comment; ignored.(?=...)  Matches if ... matches next, but doesn't consume the string.(?!...)  Matches if ... doesn't match next.(?<=...) Matches if preceded by ... (must be fixed length).(?<!...) Matches if not preceded by ... (must be fixed length).(?(id/name)yes|no) Matches yes pattern if the group with id/name matched,the (optional) no pattern otherwise.The special sequences consist of "\\" and a character from the list
below.  If the ordinary character is not on the list, then the
resulting RE will match the second character.\number  Matches the contents of the group of the same number.\A       Matches only at the start of the string.\Z       Matches only at the end of the string.\b       Matches the empty string, but only at the start or end of a word.\B       Matches the empty string, but not at the start or end of a word.\d       Matches any decimal digit; equivalent to the set [0-9] inbytes patterns or string patterns with the ASCII flag.In string patterns without the ASCII flag, it will match the wholerange of Unicode digits.\D       Matches any non-digit character; equivalent to [^\d].\s       Matches any whitespace character; equivalent to [ \t\n\r\f\v] inbytes patterns or string patterns with the ASCII flag.In string patterns without the ASCII flag, it will match the wholerange of Unicode whitespace characters.\S       Matches any non-whitespace character; equivalent to [^\s].\w       Matches any alphanumeric character; equivalent to [a-zA-Z0-9_]in bytes patterns or string patterns with the ASCII flag.In string patterns without the ASCII flag, it will match therange of Unicode alphanumeric characters (letters plus digitsplus underscore).With LOCALE, it will match the set [0-9_] plus characters definedas letters for the current locale.\W       Matches the complement of \w.\\       Matches a literal backslash.This module exports the following functions:match     Match a regular expression pattern to the beginning of a string.fullmatch Match a regular expression pattern to all of a string.search    Search a string for the presence of a pattern.sub       Substitute occurrences of a pattern found in a string.subn      Same as sub, but also return the number of substitutions made.split     Split a string by the occurrences of a pattern.findall   Find all occurrences of a pattern in a string.finditer  Return an iterator yielding a match object for each match.compile   Compile a pattern into a RegexObject.purge     Clear the regular expression cache.escape    Backslash all non-alphanumerics in a string.Some of the functions in this module takes flags as optional parameters:A  ASCII       For string patterns, make \w, \W, \b, \B, \d, \Dmatch the corresponding ASCII character categories(rather than the whole Unicode categories, which is thedefault).For bytes patterns, this flag is the only availablebehaviour and needn't be specified.I  IGNORECASE  Perform case-insensitive matching.L  LOCALE      Make \w, \W, \b, \B, dependent on the current locale.M  MULTILINE   "^" matches the beginning of lines (after a newline)as well as the string."$" matches the end of lines (before a newline) as wellas the end of the string.S  DOTALL      "." matches any character at all, including the newline.X  VERBOSE     Ignore whitespace and comments for nicer looking RE's.U  UNICODE     For compatibility only. Ignored for string patterns (itis the default), and forbidden for bytes patterns.This module also defines an exception 'error'."""

#!/usr/bin/python env
#_*_coding:utf-8_*_

贪婪匹配：在满足匹配时，匹配尽可能长的字符串，默认情况下，采用贪婪匹配
正则                   待匹配字符                  匹配结果                说明
<.*>                   <script>...<script>         <script>...<script>     默认为贪婪匹配模式，会匹配尽量长的字符串
<.*?>                   r'\d'                       <script>/<script>      加上？为将贪婪匹配模式转为非贪婪匹配模式，会匹配尽量短的字符串几个常用的非贪婪匹配Pattern
*? 重复任意次，但尽可能少重复
+? 重复1次或更多次，但尽可能少重复
?? 重复0次或1次，但尽可能少重复
{n,m}? 重复n到m次，但尽可能少重复
{n,}? 重复n次以上，但尽可能少重复.*?的用法
. 是任意字符
* 是取 0 至 无限长度
? 是非贪婪模式。
何在一起就是 取尽量少的任意字符，一般不会这么单独写，他大多用在：
.*?x就是取前面任意长度的字符，直到一个x出现

 1 #!/usr/bin/python env2 #_*_coding:utf-8_*_3 4 #1、匹配标签5 import re6 ret = re.search("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>","<h1>hello</h1>")7 #还可以在分组中利用?<name>的形式给分组起名字8 #获取的匹配结果可以直接用group('名字')拿到对应的值9 print(ret.group('tag_name'))  #结果 ：h1
10 print(ret.group())  #结果 ：<h1>hello</h1>
11
12 ret = re.search(r"<(\w+)>\w+</\1>","<h1>hello</h1>")
13 #如果不给组起名字，也可以用\序号来找到对应的组，表示要找的内容和前面的组内容一致
14 #获取的匹配结果可以直接用group(序号)拿到对应的值
15 print(ret.group(1))
16 print(ret.group())  #结果 ：<h1>hello</h1>
17
18 #2、匹配整数
19 import re
20 ret=re.findall(r"\d+","1-2*(60+(-40.35/5)-(-4*3))")
21 print(ret) #['1', '2', '60', '40', '35', '5', '4', '3']
22 ret=re.findall(r"-?\d+\.\d*|(-?\d+)","1-2*(60+(-40.35/5)-(-4*3))")
23 print(ret) #['1', '-2', '60', '', '5', '-4', '3']
24 ret.remove("")
25 print(ret) #['1', '-2', '60', '5', '-4', '3']
26
27 #3、数字匹配
28 # 1、 匹配一段文本中的每行的邮箱
29 #       http://blog.csdn.net/make164492212/article/details/51656638
30 # 2、 匹配一段文本中的每行的时间字符串，比如：‘1990-07-12’；
31 #
32 #    分别取出1年的12个月（^(0?[1-9]|1[0-2])$）、
33 #    一个月的31天：^((0?[1-9])|((1|2)[0-9])|30|31)$
34 # 3、 匹配qq号。(腾讯QQ号从10000开始)  ［1,9］[0,9]{4,}
35 # 4、 匹配一个浮点数。       ^(-?\d+)(\.\d+)?$   或者  -?\d+\.?\d*
36 # 5、 匹配汉字。             ^[\u4e00-\u9fa5]{0,}$
37 # 6、 匹配出所有整数

 1 #!/usr/bin/python env2 #_*_coding:utf-8_*_3 import re4 import json5 import requests  #urlopen6 7 def getPage(url):8     response = requests.get(url)9     return response.text
10
11 def parsePage(s):
12     com = re.compile(
13         '<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?<span class="title">(?P<title>.*?)</span>'
14         '.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>(?P<comment_num>.*?)评价</span>', re.S)
15
16     ret = com.finditer(s)
17     for i in ret:
18         yield {
19             "id": i.group("id"),
20             "title": i.group("title"),
21             "rating_num": i.group("rating_num"),
22             "comment_num": i.group("comment_num"),
23         }
24
25 def main(num):
26     url = 'https://movie.douban.com/top250?start=%s&filter=' % num
27     response_html = getPage(url)
28     ret = parsePage(response_html)
29     print(ret)
30     f = open("move_info7", "a", encoding="utf8")
31
32     for obj in ret:  #循环生成器
33         print(obj)
34         data = json.dumps(obj, ensure_ascii=False)
35         f.write(data + "\n")
36
37 count = 0
38 for i in range(10):
39     main(count)
40     count += 25

namedtuple: 生成可以使用名字来访问元素内容的tupledeque: 双端队列，可以快速的从另外一侧追加和推出对象Counter: 计数器，主要用来计数OrderedDict: 有序字典defaultdict: 带有默认值的字典

>>> p = (1, 2)

>>> from collections import namedtuple
>>> Point = namedtuple('Point', ['x', 'y'])
>>> p = Point(1, 2)
>>> p.x
1
>>> p.y
2

#namedtuple('名称', [属性list]):
Circle = namedtuple('Circle', ['x', 'y', 'r'])

>>> from collections import deque
>>> q = deque(['a', 'b', 'c'])
>>> q.append('x')
>>> q.appendleft('y')
>>> q
deque(['y', 'a', 'b', 'c', 'x'])

>>> from collections import OrderedDict
>>> d = dict([('a', 1), ('b', 2), ('c', 3)])
>>> d # dict的Key是无序的
{'a': 1, 'c': 3, 'b': 2}
>>> od = OrderedDict([('a', 1), ('b', 2), ('c', 3)])
>>> od # OrderedDict的Key是有序的
OrderedDict([('a', 1), ('b', 2), ('c', 3)])

>>> od = OrderedDict()
>>> od['z'] = 1
>>> od['y'] = 2
>>> od['x'] = 3
>>> od.keys() # 按照插入的Key的顺序返回
['z', 'y', 'x']

values = [11, 22, 33,44,55,66,77,88,99,90]my_dict = {}for value in  values:if value>66:if my_dict.has_key('k1'):my_dict['k1'].append(value)else:my_dict['k1'] = [value]else:if my_dict.has_key('k2'):my_dict['k2'].append(value)else:my_dict['k2'] = [value]

from collections import defaultdictvalues = [11, 22, 33,44,55,66,77,88,99,90]my_dict = defaultdict(list)for value in  values:if value>66:my_dict['k1'].append(value)else:my_dict['k2'].append(value)

>>> from collections import defaultdict
>>> dd = defaultdict(lambda: 'N/A')
>>> dd['key1'] = 'abc'
>>> dd['key1'] # key1存在
'abc'
>>> dd['key2'] # key2不存在，返回默认值
'N/A'

>>> c = Counter()  # 创建一个空的Counter类
>>> c = Counter('gallahad')  # 从一个可iterable对象（list、tuple、dict、字符串等）创建
>>> c = Counter({'a': 4, 'b': 2})  # 从一个字典对象创建
>>> c = Counter(a=4, b=2)  # 从一组键值对创建

View Code

>>> c = Counter("abcdefgab")
>>> c["a"]
2
>>> c["c"]
1
>>> c["h"]
0

View Code

>>> c = Counter('which')
>>> c.update('witch')  # 使用另一个iterable对象更新
>>> c['h']
3
>>> d = Counter('watch')
>>> c.update(d)  # 使用另一个Counter对象更新
>>> c['h']
4

View Code

>>> c = Counter('which')
>>> c.subtract('witch')  # 使用另一个iterable对象更新
>>> c['h']
1
>>> d = Counter('watch')
>>> c.subtract(d)  # 使用另一个Counter对象更新
>>> c['a']
-1

View Code

>>> c = Counter("abcdcba")
>>> c
Counter({'a': 2, 'c': 2, 'b': 2, 'd': 1})
>>> c["b"] = 0
>>> c
Counter({'a': 2, 'c': 2, 'd': 1, 'b': 0})
>>> del c["a"]
>>> c
Counter({'c': 2, 'b': 2, 'd': 1})

View Code

>>> c = Counter(a=4, b=2, c=0, d=-2)
>>> list(c.elements())
['a', 'a', 'a', 'a', 'b', 'b']

View Code

>>> c = Counter('abracadabra')
>>> c.most_common()
[('a', 5), ('r', 2), ('b', 2), ('c', 1), ('d', 1)]
>>> c.most_common(3)
[('a', 5), ('r', 2), ('b', 2)]

View Code

>>> c = Counter(a=3, b=1)
>>> d = Counter(a=1, b=2)
>>> c + d  # c[x] + d[x]
Counter({'a': 4, 'b': 3})
>>> c - d  # subtract（只保留正数计数的元素）
Counter({'a': 2})
>>> c & d  # 交集:  min(c[x], d[x])
Counter({'a': 1, 'b': 1})
>>> c | d  # 并集:  max(c[x], d[x])
Counter({'a': 3, 'b': 2})

View Code

sum(c.values())  # 所有计数的总数
c.clear()  # 重置Counter对象，注意不是删除
list(c)  # 将c中的键转为列表
set(c)  # 将c中的键转为set
dict(c)  # 将c中的键值对转为字典
c.items()  # 转为(elem, cnt)格式的列表
Counter(dict(list_of_pairs))  # 从(elem, cnt)格式的列表转换为Counter类对象
c.most_common()[:-n:-1]  # 取出计数最少的n个元素
c += Counter()  # 移除0和负值

View Code