【python】常用内建模块

【datetime】

No1：

获取当前时间

No2：

时区转换

>>> from datetime import datetime, timedelta, timezone
>>> tz_utc_8 = timezone(timedelta(hours=8)) # 创建时区UTC+8:00
>>> now = datetime.now()
>>> now
datetime.datetime(2015, 5, 18, 17, 2, 10, 871012)
>>> dt = now.replace(tzinfo=tz_utc_8) # 强制设置为UTC+8:00
>>> dt
datetime.datetime(2015, 5, 18, 17, 2, 10, 871012, tzinfo=datetime.timezone(datetime.timedelta(0, 28800)))

# 拿到UTC时间，并强制设置时区为UTC+0:00:
>>> utc_dt = datetime.utcnow().replace(tzinfo=timezone.utc)
>>> print(utc_dt)
2015-05-18 09:05:12.377316+00:00
# astimezone()将转换时区为北京时间:
>>> bj_dt = utc_dt.astimezone(timezone(timedelta(hours=8)))
>>> print(bj_dt)
2015-05-18 17:05:12.377316+08:00
# astimezone()将转换时区为东京时间:
>>> tokyo_dt = utc_dt.astimezone(timezone(timedelta(hours=9)))
>>> print(tokyo_dt)
2015-05-18 18:05:12.377316+09:00
# astimezone()将bj_dt转换时区为东京时间:
>>> tokyo_dt2 = bj_dt.astimezone(timezone(timedelta(hours=9)))
>>> print(tokyo_dt2)
2015-05-18 18:05:12.377316+09:00

【collections】

 No3：

No4：

deque方便插入和删除

OrderedDict有序

>>> 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
>>> list(od.keys()) # 按照插入的Key的顺序返回
['z', 'y', 'x']

FIFO（先进先出）的dict

from collections import OrderedDict

class LastUpdatedOrderedDict(OrderedDict):

    def __init__(self, capacity):
        super(LastUpdatedOrderedDict, self).__init__()
        self._capacity = capacity

    def __setitem__(self, key, value):
        containsKey = 1 if key in self else 0
        if len(self) - containsKey >= self._capacity:
            last = self.popitem(last=False)
            print('remove:', last)
        if containsKey:
            del self[key]
            print('set:', (key, value))
        else:
            print('add:', (key, value))
        OrderedDict.__setitem__(self, key, value)

Counter计数器

>>> from collections import Counter
>>> c = Counter()
>>> for ch in 'programming':
...     c[ch] = c[ch] + 1
...
>>> c
Counter({'g': 2, 'm': 2, 'r': 2, 'a': 1, 'i': 1, 'o': 1, 'n': 1, 'p': 1})

【base64】

No5：

Base64是一种用64个字符来表示任意二进制数据的方法。

>>> import base64
>>> base64.b64encode(b'binary\x00string')
b'YmluYXJ5AHN0cmluZw=='
>>> base64.b64decode(b'YmluYXJ5AHN0cmluZw==')
b'binary\x00string'

>>> base64.b64encode(b'i\xb7\x1d\xfb\xef\xff')
b'abcd++//'
>>> base64.urlsafe_b64encode(b'i\xb7\x1d\xfb\xef\xff')
b'abcd--__'
>>> base64.urlsafe_b64decode('abcd--__')
b'i\xb7\x1d\xfb\xef\xff'

No6：

【struct】

pack的第一个参数是处理指令，'>I'的意思是：

>表示字节顺序是big-endian，也就是网络序，I表示4字节无符号整数。

【摘要算法】

No7：

摘要算法又称哈希算法、散列算法。它通过一个函数，把任意长度的数据转换为一个长度固定的数据串（通常用16进制的字符串表示）

No8：

【hmac】

No9：

【itertools】迭代

count()

>>> import itertools
>>> natuals = itertools.count(1)
>>> for n in natuals:
...     print(n)
...

数字无限增长，差点没爆掉

cycle()

>>> import itertools
>>> cs = itertools.cycle('ABC') # 注意字符串也是序列的一种
>>> for c in cs:
...     print(c)
...

ABC无限重复，又差点没爆掉

repeat()--限定重复次数

chain()--可以把一组迭代对象串联起来，形成一个更大的迭代器：

groupby()--把迭代器中相邻的重复元素挑出来放在一起：

No10:

try:
    f = open('/path/to/file', 'r')
    f.read()
finally:
    if f:
        f.close()

可简化为

with open('/path/to/file', 'r') as f:
    f.read()

No11：

class Query(object):

    def __init__(self, name):
        self.name = name

    def __enter__(self):
        print('Begin')
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        if exc_type:
            print('Error')
        else:
            print('End')

    def query(self):
        print('Query info about %s...' % self.name)

使用

with Query('Bob') as q:
    q.query()

》》》》类可简化为

from contextlib import contextmanager

class Query(object):

    def __init__(self, name):
        self.name = name

    def query(self):
        print('Query info about %s...' % self.name)

@contextmanager
def create_query(name):
    print('Begin')
    q = Query(name)
    yield q
    print('End')

使用

with create_query('Bob') as q:
    q.query()

No12：

No13：

from contextlib import closing
from urllib.request import urlopen

with closing(urlopen('https://www.python.org')) as page:
    for line in page:
        print(line)

结果居然打印出整个html界面的代码

【GET】

No14：

from urllib import request

req = request.Request('http://www.douban.com/')
req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25')
with request.urlopen(req) as f:
    print('Status:', f.status, f.reason)
    for k, v in f.getheaders():
        print('%s: %s' % (k, v))
    print('Data:', f.read().decode('utf-8'))

结果会返回豆瓣网的移动端页面

No15：

【POST】

模拟微博登陆

from urllib import request, parse

print('Login to weibo.cn...')
email = input('Email: ')
passwd = input('Password: ')
login_data = parse.urlencode([
    ('username', email),
    ('password', passwd),
    ('entry', 'mweibo'),
    ('client_id', ''),
    ('savestate', ''),
    ('ec', ''),
    ('pagerefer', 'https://passport.weibo.cn/signin/welcome?entry=mweibo&r=http%3A%2F%2Fm.weibo.cn%2F')
])

req = request.Request('https://passport.weibo.cn/sso/login')
req.add_header('Origin', 'https://passport.weibo.cn')
req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25')
req.add_header('Referer', 'https://passport.weibo.cn/signin/login?entry=mweibo&res=wel&wm=3349&r=http%3A%2F%2Fm.weibo.cn%2F')

with request.urlopen(req, data=login_data.encode('utf-8')) as f:
    print('Status:', f.status, f.reason)
    for k, v in f.getheaders():
        print('%s: %s' % (k, v))
    print('Data:', f.read().decode('utf-8'))

No16：

【Handler】

proxy_handler = urllib.request.ProxyHandler({'http': 'http://www.example.com:3128/'})
proxy_auth_handler = urllib.request.ProxyBasicAuthHandler()
proxy_auth_handler.add_password('realm', 'host', 'username', 'password')
opener = urllib.request.build_opener(proxy_handler, proxy_auth_handler)
with opener.open('http://www.example.com/login.html') as f:
    pass

No17:

【XML】

操作XML有两种方法：DOM和SAX。DOM会把整个XML读入内存，解析为树，因此占用内存大，解析慢，优点是可以任意遍历树的节点。SAX是流模式，边读边解析，占用内存小，解析快，缺点是我们需要自己处理事件。

正常情况下，优先考虑SAX，因为DOM实在太占内存。

from xml.parsers.expat import ParserCreate

class DefaultSaxHandler(object):
    def start_element(self, name, attrs):
        print('sax:start_element: %s, attrs: %s' % (name, str(attrs)))

    def end_element(self, name):
        print('sax:end_element: %s' % name)

    def char_data(self, text):
        print('sax:char_data: %s' % text)

xml = r'''<?xml version="1.0"?>
<ol>
    <li><a href="/python">Python</a></li>
    <li><a href="/ruby">Ruby</a></li>
</ol>
'''

handler = DefaultSaxHandler()
parser = ParserCreate()
parser.StartElementHandler = handler.start_element
parser.EndElementHandler = handler.end_element
parser.CharacterDataHandler = handler.char_data
parser.Parse(xml)

L = []
L.append(r'<?xml version="1.0"?>')
L.append(r'<root>')
L.append(encode('some & data'))
L.append(r'</root>')
return ''.join(L)

No18：

【HTMLParser】

from html.parser import HTMLParser
from html.entities import name2codepoint

class MyHTMLParser(HTMLParser):

    def handle_starttag(self, tag, attrs):
        print('<%s>' % tag)

    def handle_endtag(self, tag):
        print('</%s>' % tag)

    def handle_startendtag(self, tag, attrs):
        print('<%s/>' % tag)

    def handle_data(self, data):
        print(data)

    def handle_comment(self, data):
        print('<!--', data, '-->')

    def handle_entityref(self, name):
        print('&%s;' % name)

    def handle_charref(self, name):
        print('&#%s;' % name)

parser = MyHTMLParser()
parser.feed('''<html>
<head></head>
<body>
<!-- test html parser -->
    <p>Some <a href=\"#\">html</a> HTML&nbsp;tutorial...<br>END</p>
</body></html>''')