from datetime import datetimehtml
>>> now = datetime.now() >>> print(now) 2019-01-13 14:19:38.181000
>>> dt = datetime(2019,1,10,15,0) >>> print(dt) 2019-01-10 15:00:00
from datetime import datetime now = datetime.now() print(now.timestamp())
注意:
Python的timestamp是一個浮點數。若是有小數位,小數位表示毫秒數。python
#本地時區時間 datetime.fromtimestamp(1547360695.313724) #UTC標準時區的時間 print(datetime.utcfromtimestamp(1547360695.313724))
datetime.strptime('2015-6-1 18:19:59', '%Y-%m-%d %H:%M:%S')
now = datetime.now() print(now.strftime('%a, %b %d %H:%M'))
from datetime import datetime, timedelta now = datetime.now() new_time = now + timedelta(hours=10) print(new_time)
from datetime import datetime, timedelta, timezone tz_utc_8 = timezone(timedelta(hours=8)) now = datetime.now() dt = now.replace(tzinfo=tz_utc_8) print(dt)
from datetime import datetime, timedelta, timezone # 強制設置時區爲UTC+0:00: utc_dt = datetime.utcnow().replace(tzinfo=timezone.utc) print(utc_dt) # 利用astimezone()將轉換時區爲北京時間: bj_dt = utc_dt.astimezone(timezone(timedelta(hours=8))) print(bj_dt)
注意:
若是要存儲datetime,最佳方法是將其轉換爲timestamp再存儲,由於timestamp的值與時區徹底無關算法
from collections import namedtuple Point = namedtuple('Point', ['x', 'y', 'z']) p = Point(1,3,9) print(p.x, p.y, p.z)
使用list存儲數據時,按索引訪問元素很快,可是插入和刪除元素就很慢了,由於list是線性存儲,數據量大的時候,插入和刪除效率很低。
deque是爲了高效實現插入和刪除操做的雙向列表,適合用於隊列和棧:安全
from collections import deque q = deque([2,3,5]) q.appendleft(6) q.popleft() print(q)
使用dict時,若是引用的Key不存在,就會拋出KeyError。若是但願key不存在時,返回一個默認值,就能夠用defaultdictruby
from collections import defaultdict d = defaultdict(lambda : 'N/A') d['l'] = 100 print(d['l']) print(d['m'])
使用dict時,Key是無序的。OrderedDict的Key會按照插入的順序排列,能夠實現FIFO網絡
from collections import OrderedDict d1 = OrderedDict() d1['a'] = 1 d1['b'] = 2 d1['c'] = 3 print(d1)
輸出:
OrderedDict([('a', 1), ('b', 2), ('c', 3)])app
ChainMap能夠把一組dict串起來並組成一個邏輯上的dict。ChainMap自己也是一個dict,可是查找的時候,會按照順序在內部的dict依次查找函數
from collections import ChainMap import os default_dict = {'platform': os.name} user_select = {'platform': 'posix'} d = ChainMap(user_select, default_dict) print(d['platform'])
若是user_select存在platform就是用該值,不然就使用默認的post
Counter是一個簡單的計數器編碼
from collections import Counter c = Counter() for ch in 'helloworld': c[ch] += 1 print(c)
輸出:
Counter({'l': 3, 'o': 2, 'h': 1, 'e': 1, 'w': 1, 'r': 1, 'd': 1})
Base64是一種用64個字符來表示任意二進制數據的方法,Base64編碼會把3字節的二進制數據編碼爲4字節的文本數據,長度增長33%,好處是編碼後的文本數據能夠在郵件正文、網頁等直接顯示。
若是要編碼的二進制數據不是3的倍數,最後會剩下1個或2個字節怎麼辦?Base64用\x00字節在末尾補足後,再在編碼的末尾加上1個或2個=號,表示補了多少字節,解碼的時候,會自動去掉。
示例代碼:
import base64 # base64編碼 base64_encode = base64.b64encode(b'52222') # base64安全編碼,會將可能出現的字符字符+和/替換爲-和_ base64_safe_encode = base64.urlsafe_b64encode(b'52222') print(base64_encode) print(base64_safe_encode) # 解碼 print(base64.b64decode(base64_encode)) print(base64.urlsafe_b64decode(base64_safe_encode))
輸出:
b'NTIyMjI='
b'NTIyMjI='
b'52222'
b'52222'
Python提供了一個struct模塊來解決bytes和其餘二進制數據類型的轉換
import struct # 變成字節,>表示字節順序是big-endian,也就是網絡序,I表示4字節無符號整數 print(struct.pack('>I', 10240099)) # 字節變成相應的數據類型,根據>IH的說明,後面的bytes依次變爲I:4字節無符號整數和H:2字節無符號整數。 print(struct.unpack('>IH', b'\xf0\xf0\xf0\xf0\x80\x80'))
md5/SHA1解密加密
import hashlib #加密 md5 = hashlib.md5() md5.update('hello'.encode('utf-8')) print(md5.hexdigest())
import hashlib sha1 = hashlib.sha1() sha1.update('hello'.encode('utf-8')) print(sha1.hexdigest())
它經過一個標準算法,在計算哈希的過程當中,把key混入計算過程當中
import hmac hmac_encode = hmac.new(b'salt', b'message', 'MD5') print(hmac_encode.hexdigest())
import itertools for i in itertools.count(1): print(i)
import itertools for i in itertools.cycle('abc'): print(i)
import itertools natuals = itertools.count(1) ns = itertools.takewhile(lambda x: x <= 10, natuals) print(list(ns))
import itertools for i in itertools.chain('abc', 'def'): print(i)
輸出:
a
b
c
d
e
f
import itertools for key, group in itertools.groupby('AAABBBCCAAA'): print(key, group)
輸出:
A <itertools._grouper object at 0x000001C32D2A3550>
B <itertools._grouper object at 0x000001C32D2DCDA0>
C <itertools._grouper object at 0x000001C32D2A3550>
A <itertools._grouper object at 0x000001C32D2DCD68>
任何對象,只要正確實現了上下文管理,就能夠用於with語句.要使用with實現上下文管理是經過__enter__和__exit__這兩個方法實現的
class Query: def __enter__(self): print('enter') return self def query(self, params): print(params) return 100 def __exit__(self, exc_type, exc_val, exc_tb): if exc_type: print('error') else: print('exit') with Query() as query: query.query('rorshach')
from contextlib import contextmanager class Query: def query(self, params): print(params) return 100 @contextmanager def make_context_query(): q = Query() yield q with make_context_query() as query: query.query('rorshach')
不少時候,咱們但願在某段代碼執行先後自動執行特定代碼,也能夠用@contextmanager實現:
from contextlib import contextmanager @contextmanager def tag(): print('<h1>') yield print('</h1>') #yield沒有生成值,with語句中就不須要寫as子句了 with tag() as tag: print('hello')
輸出:
<h1>
hello
</h1>
若是出錯,關閉對象示例:
from contextlib import contextmanager from urllib.request import urlopen @contextmanager def closing(thing): try: yield thing finally: thing.close() with closing(urlopen('http://www.baidu.com')) as page: for line in page: print(line)
from urllib import request req = request.Request('http://www.baidu.com/') # 設置ua 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'))
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', '1'), ('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'))
DOM會把整個XML讀入內存,解析爲樹,所以佔用內存大,解析慢,優勢是能夠任意遍歷樹的節點
示例代碼:
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)
from html.parser import HTMLParser 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 tutorial...<br>END</p> </body></html>''')