第十章 Python常用标准库使用（必会）

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
print sys.argv[0]
print sys.argv[1]
print sys.argv[2]
print sys.argv[3]
print sys.argv
print len(sys.argv)
# python test.py
test.py
a
b
c
c
['test.py', 'a', 'b', 'c']
4 

>>> sys.path
['', '/usr/local/lib/python2.7/dist-packages/tornado-3.1-py2.7.egg', '/usr/lib/python2.7', '/usr/lib/python2.7/plat-x86_64-linux-gnu', '/usr/lib/python2.7/lib-tk', '/usr/lib/python2.7/lib-old', '/usr/lib/python2.7/lib-dynload', '/usr/local/lib/python2.7/dist-packages', '/usr/lib/python2.7/dist-packages']

>>> sys.path.append('/opt/scripts')
>>> sys.path
['', '/usr/local/lib/python2.7/dist-packages/tornado-3.1-py2.7.egg', '/usr/lib/python2.7', '/usr/lib/python2.7/plat-x86_64-linux-gnu', '/usr/lib/python2.7/lib-tk', '/usr/lib/python2.7/lib-old', '/usr/lib/python2.7/lib-dynload', '/usr/local/lib/python2.7/dist-packages', '/usr/lib/python2.7/dist-packages', '/opt/scripts']

>>> sys.subversion
('CPython', '', '') 

>>> sys.version
'2.7.6 (default, Jun 22 2015, 17:58:13) \n[GCC 4.8.2]' 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
print "Hello world!"
sys.exit()
print "Hello world!"
# python test.py
Hello world! 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
name = raw_input("Please input your name: ")
print name
# python test.py
Please input your name: xiaoming
xiaoming 

import sys
print "Please enter your name: "
name = sys.stdin.readline()
print name
# python b.py
Please enter your name:
xiaoming
xiaoming 

# cat a.py
import sys
sys.stdout.write("123456\n")
sys.stdout.flush()
# cat b.py
import sys
print sys.stdin.readlines()
# python a.py | python b.py
['123456\n'] 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import sys
print "Hello world!"
# python test.py
Hello world! 

import sys
import time
for i in range(5):
    print i,
    # sys.stdout.flush()
    time.sleep(1)
# python test.py
0 1 2 3 4 

>>> raise Exception, "raise..."
Traceback (most recent call last):File "<stdin>", line 1, in <module>
Exception: raise... 

# 查找目录中所有以.sh为后缀的文件
>>> glob.glob('/home/user/*.sh')
['/home/user/1.sh', '/home/user/b.sh', '/home/user/a.sh', '/home/user/sum.sh']
# 查找目录中出现单个字符并以.sh为后缀的文件
>>> glob.glob('/home/user/?.sh')
['/home/user/1.sh', '/home/user/b.sh', '/home/user/a.sh']
# 查找目录中出现a.sh或b.sh的文件
>>> glob.glob('/home/user/[a|b].sh')
['/home/user/b.sh', '/home/user/a.sh'] 

>>> import pickle
>>> dict = {'a':1, 'b':2, 'c':3}
>>> output = open('data.pkl', 'wb')  # 二进制模式打开文件
>>> pickle.dump(dict, output)   # 执行完导入操作，当前目录会生成data.pkl文件
>>> output.close()  # 写入数据并关闭 

# cat data.pkl
(dp0
S'a'
p1
I1
sS'c'
p2
I3
sS'b'
p3
I2
s. 

>>> f = open('data.pkl')
>>> data = pickle.load(f)
>>> print data
{'a': 1, 'c': 3, 'b': 2} 

>>> s = 'abc'
>>> pickle.dumps(s) 
"S'abc'\np0\n."
>>> pkl = pickle.dumps(s)
>>> pkl
"S'abc'\np0\n."
>>> pickle.loads(pkl)
'abc' 

>>> import subprocess 
>>> retcode = subprocess.call(["ls", "-l"])
total 504
-rw-r--r-- 1 root root      54 Nov  2 06:15 data.pkl
>>> retcode
0
>>> retcode = subprocess.call(["ls", "a"]) 
ls: cannot access a: No such file or directory
>>> retcode
2
# 也可以这样写
>>> subprocess.call('ls -l', shell=True)
subprocess.check_call()：运行命令与参数。如果退出状态码非0，引发CalledProcessError异常，包含状态码。
>>> subprocess.check_call("ls a", shell=True)
ls: cannot access a: No such file or directory
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/lib/python2.7/subprocess.py", line 540, in check_call
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command 'ls a' returned non-zero exit status 2 

>>> p = subprocess.Popen('dmesg |grep eth0', stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
>>> p.communicate() 
......  # 元组形式返回结果
>>> p.pid
57039
>>> p.wait()
0
>>> p.returncode
0 

>>> from Queue import Queue
>>> q = Queue()
>>> q.put('test')
>>> q.qsize()
1
>>> q.get()
'test'
>>> q.qsize()
0
>>> q.full()
False
>>> q.empty()
True 

>>> f = StringIO()
>>> f.write('hello')
>>> f.getvalue()
'hello' 

>>> f = StringIO('hello\nworld!')
>>> f.read()
'hello\nworld!'
>>> s = StringIO('hello world!')
>>> s.seek(5)            # 指针移动到第五个字符，开始写入      
>>> s.write('-')               
>>> s.getvalue()
'hello-world!' 

#!/usr/bin/python
# -*- coding: utf-8 -*-
#--------------------------------------------------
# 日志格式
#--------------------------------------------------
# %(asctime)s       年-月-日 时-分-秒,毫秒 2013-04-26 20:10:43,745
# %(filename)s      文件名，不含目录
# %(pathname)s      目录名，完整路径
# %(funcName)s      函数名
# %(levelname)s     级别名
# %(lineno)d        行号
# %(module)s        模块名
# %(message)s       消息体
# %(name)s          日志模块名
# %(process)d       进程id
# %(processName)s   进程名
# %(thread)d        线程id
# %(threadName)s    线程名
import logging
format = logging.Formatter('%(asctime)s - %(levelname)s %(filename)s [line:%(lineno)d] %(message)s')
# 创建日志记录器
info_logger = logging.getLogger('info')
# 设置日志级别,小于INFO的日志忽略
info_logger.setLevel(logging.INFO)
# 日志记录到磁盘文件
info_file = logging.FileHandler("info.log")
# info_file.setLevel(logging.INFO)
# 设置日志格式
info_file.setFormatter(format)
info_logger.addHandler(info_file)
error_logger = logging.getLogger('error')
error_logger.setLevel(logging.ERROR)
error_file = logging.FileHandler("error.log")
error_file.setFormatter(format)
error_logger.addHandler(error_file)
# 输出控制台（stdout）
console = logging.StreamHandler()
console.setLevel(logging.DEBUG)
console.setFormatter(format)
info_logger.addHandler(console)
error_logger.addHandler(console)
if __name__ == "__main__":
    # 写日志
    info_logger.warning("info message.")
    error_logger.error("error message!") 

# python test.py
2016-07-02 06:52:25,624 - WARNING test.py [line:49] info message.
2016-07-02 06:52:25,631 - ERROR test.py [line:50] error message!
# cat info.log
2016-07-02 06:52:25,624 - WARNING test.py [line:49] info message.
# cat error.log
2016-07-02 06:52:25,631 - ERROR test.py [line:50] error message! 

# cat config.ini
[host1]   
host = 192.168.1.1
port = 22
user = zhangsan
pass = 123
[host2]
host = 192.168.1.2
port = 22
user = lisi
pass = 456
[host3]
host = 192.168.1.3
port = 22
user = wangwu
pass = 789 

#!/usr/bin/python
# -*- coding: utf-8 -*-
from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
section = conf.sections()[0]  # 获取随机的第一个部分标识
options = conf.options(section) # 获取部分中的所有键
key = options[2]
value = conf.get(section, options[2]) # 获取部分中键的值
print key, value
print type(value)
# python test.py
port 22
<type 'str'> 

#!/usr/bin/python
# -*- coding: utf-8 -*-
from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
sections = conf.sections()  # 获取部分名称 ['host3', 'host2', 'host1']
for section in sections:
    options = conf.options(section) # 获取部分名称中的键 ['user', 'host', 'port', 'pass']
    for option in options:
         value = conf.get(section, option) # 获取部分中的键值
         print option + ": " + value  
    print "-------------"
    
# python test.py
user: wangwu
host: 192.168.1.3
port: 22
pass: 789
-------------
user: lisi
host: 192.168.1.2
port: 22
pass: 456
-------------
user: zhangsan
host: 192.168.1.1
port: 22
pass: 123
------------- 

from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
print conf.items('host1')
# python test.py
[('user', 'zhangsan'), ('host', '192.168.1.1'), ('port', '22'), ('pass', '123')]

from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
fp = open("config.ini", "w")   # 写模式打开文件，供后面提交写的内容
conf.set("host1", "port", "2222")  # 有这个选项就更新，否则添加
conf.write(fp)  # 写入的操作必须执行这个方法 

from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
fp = open("config.ini", "w")
conf.add_section("host4")   # 添加[host4]
conf.set("host4", "host", "192.168.1.4")
conf.set("host4", "port", "22")
conf.set("host4", "user", "zhaoliu")
conf.set("host4", "pass", "123")
conf.write(fp) 

from ConfigParser import ConfigParser
conf = ConfigParser()
conf.read("config.ini")
fp = open("config.ini", "w")
conf.remove_section('host4')  # 删除[host4]
conf.remove_option('host3', 'pass')  # 删除[host3]的pass选项
conf.write(fp) 

>>> import urllib, urllib2
>>> response = urllib.urlopen("http://www.baidu.com")   # 获取的网站页面源码
>>> response.readline()
'<!DOCTYPE html>\n'
>>> response.getcode()
200
>>> response.geturl()
'http://www.baidu.com' 

>>> user_agent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36"
>>> header = {"User-Agent": user_agent}
>>> request = urllib2.Request("http://www.baidu.com", headers=header) # 也可以通过request.add_header('User-Agent', 'Mozilla...')方式添加    
>>> response = urllib2.urlopen(request)
>>> response.geturl()
'https://www.baidu.com/'
>>> print respose.info()  # 查看服务器返回的header信息
Server: bfe/1.0.8.18
Date: Sat, 12 Nov 2016 06:34:54 GMT
Content-Type: text/html; charset=utf-8
Transfer-Encoding: chunked
Connection: close
Vary: Accept-Encoding
Set-Cookie: BAIDUID=5979A74F742651531360C08F3BE06754:FG=1; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
Set-Cookie: BIDUPSID=5979A74F742651531360C08F3BE06754; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
Set-Cookie: PSTM=1478932494; expires=Thu, 31-Dec-37 23:55:55 GMT; max-age=2147483647; path=/; domain=.baidu.com
Set-Cookie: BDSVRTM=0; path=/
Set-Cookie: BD_HOME=0; path=/
Set-Cookie: H_PS_PSSID=1426_18240_17945_21118_17001_21454_21408_21394_21377_21525_21192; path=/; domain=.baidu.com
P3P: CP=" OTI DSP COR IVA OUR IND COM "
Cache-Control: private
Cxy_all: baidu+a24af77d41154f5fc0d314a73fd4c48f
Expires: Sat, 12 Nov 2016 06:34:17 GMT
X-Powered-By: HPHP
X-UA-Compatible: IE=Edge,chrome=1
Strict-Transport-Security: max-age=604800
BDPAGETYPE: 1
BDQID: 0xf51e0c970000d938
BDUSERID: 0
Set-Cookie: __bsi=12824513216883597638_00_24_N_N_3_0303_C02F_N_N_N_0; expires=Sat, 12-Nov-16 06:34:59 GMT; domain=www.baidu.com; path=/

>>> post_data = {"loginform-username":"test","loginform-password":"123456"}
>>> response = urllib2.urlopen("http://home.51cto.com/index", data=(urllib.urlencode(post_data)))
>>> response.read() # 登录后网页内容 

>>> urllib.urlencode(post_data)
'loginform-password=123456&loginform-username=test' 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib, urllib2
import cookielib
# 实例化CookieJar对象来保存cookie
cookie = cookielib.CookieJar()
# 创建cookie处理器
handler = urllib2.HTTPCookieProcessor(cookie)
# 通过handler构造opener
opener = urllib2.build_opener(handler)
response = opener.open("http://www.baidu.com")
for item in cookie:
    print item.name, item.value
    
# python test.py
BAIDUID EB4BF619C95630EFD619B99C596744B0:FG=1
BIDUPSID EB4BF619C95630EFD619B99C596744B0
H_PS_PSSID 1437_20795_21099_21455_21408_21395_21377_21526_21190_21306
PSTM 1478936429
BDSVRTM 0
BD_HOME 0 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib, urllib2
import cookielib
cookie_file = 'cookie.txt'
# 保存cookie到文件
cookie = cookielib.MozillaCookieJar(cookie_file)
# 创建cookie处理器
handler = urllib2.HTTPCookieProcessor(cookie)
# 通过handler构造opener
opener = urllib2.build_opener(handler)
response = opener.open("http://www.baidu.com")
# 保存
cookie.save(ignore_discard=True, ignore_expires=True)  # ignore_discard默认是false，不保存将被丢失的。ignore_expires默认flase，如果cookie存在，则不写入。
# python test.py
# cat cookie.txt
# Netscape HTTP Cookie File
# http://curl.haxx.se/rfc/cookie_spec.html
# This is a generated file!  Do not edit.
.baidu.com    TRUE    /    FALSE    3626420835    BAIDUID    687544519EA906BD0DE5AE02FB25A5B3:FG=1
.baidu.com    TRUE    /    FALSE    3626420835    BIDUPSID    687544519EA906BD0DE5AE02FB25A5B3
.baidu.com    TRUE    /    FALSE        H_PS_PSSID    1420_21450_21097_18560_21455_21408_21395_21377_21526_21192_20927
.baidu.com    TRUE    /    FALSE    3626420835    PSTM    1478937189
www.baidu.com    FALSE    /    FALSE        BDSVRTM    0
www.baidu.com    FALSE    /    FALSE        BD_HOME    0 

#!/usr/bin/python
# -*- coding: utf-8 -*-
import urllib2
import cookielib
# 实例化对象
cookie = cookielib.MozillaCookieJar()
# 从文件中读取cookie
cookie.load("cookie.txt", ignore_discard=True, ignore_expires=True)
# 创建cookie处理器
handler = urllib2.HTTPCookieProcessor(cookie)
# 通过handler构造opener
opener = urllib2.build_opener(handler)
# request = urllib2.Request("http://www.baidu.com")
response = opener.open("http://www.baidu.com") 

import urllib2
proxy_address = {"http": "http://218.17.252.34:3128"}
handler = urllib2.ProxyHandler(proxy_address)
opener = urllib2.build_opener(handler)
response = opener.open("http://www.baidu.com")
print response.read()

import urllib2
auth = urllib2.HTTPBasicAuthHandler()
# (realm, uri, user, passwd)
auth.add_password(None, 'http://www.example.com','user','123456')
opener = urllib2.build_opener(auth)
response = opener.open('http://www.example.com/test.html') 

# 获取昨天日期
>>> date.today() - timedelta(days=1)         
datetime.date(2016, 11, 11)
>>> date.isoformat(date.today() - timedelta(days=1))
'2016-11-11'
# 获取明天日期
>>> date.today() + timedelta(days=1)               
datetime.date(2016, 11, 13)
>>> date.isoformat(date.today() + timedelta(days=1))
'2016-11-13'