1.json/pickle 略。

2.shelve模块

import shelve

# shelve 以key value的形式序列化，value为对象

class Foo(object):

    def __init__(self, n):

        self.n = n

s = shelve.open("shelve_test")

name = ["alex", "rain", "test"]

s["test"] = name

s["a"] = Foo(1)

s["b"] = Foo(2)

# 反序列化，提取对象

print(s.items())        # 提取所有

print(s.get("test"))    # 提取单个

s.close()

3.xml的处理

xml文件：country.xml

<?xml version="1.0"?>

<data>

    <country name="Liechtenstein">

        <rank updated="yes">2</rank>

        <year>2008</year>

        <gdppc>141100</gdppc>

        <neighbor name="Austria" direction="E"/>

        <neighbor name="Switzerland" direction="W"/>

    </country>

    <country name="Singapore">

        <rank updated="yes">5</rank>

        <year>2011</year>

        <gdppc>59900</gdppc>

        <neighbor name="Malaysia" direction="N"/>

    </country>

    <country name="Panama">

        <rank updated="yes">69</rank>

        <year>2011</year>

        <gdppc>13600</gdppc>

        <neighbor name="Costa Rica" direction="W"/>

        <neighbor name="Colombia" direction="E"/>

    </country>

</data>

遍历等处理：

import xml.etree.ElementTree as ET

tree = ET.parse("country.xml")

root = tree.getroot()　　 # data 根节点

'''

一般的节点<tag attrib="value"> text <tag/>

自结束标签<tag attrib="value"/>

'''

# 遍历xml文档

for child in root:

    print(child.tag, child.attrib)

    for i in child:

        print(i.tag, i.text)

# 只遍历year 节点

for node in root.iter('year'):

    print(node.tag, node.text)

修改和删除：

import xml.etree.ElementTree as ET

tree = ET.parse("country.xml")

root = tree.getroot()

# 修改

for node in root.iter('year'):

    new_year = int(node.text) + 1

    node.text = str(new_year)

    node.set("updated", "yes")

tree.write("country.xml")

# 删除node

for country in root.findall('country'):  # 或者root.iter('country')

    rank = int(country.find('rank').text)

    if rank > 50:

        root.remove(country)

tree.write('country.xml')

生成xml文件：

import xml.etree.ElementTree as ET

new_xml = ET.Element("infolist")

info = ET.SubElement(new_xml, "info", attrib={"enrolled": "yes"})

name = ET.SubElement(info, "name")

name.text = 'akira'

age = ET.SubElement(info, "age", attrib={"checked": "no"})

age.text = ''

sex = ET.SubElement(info, "sex")

sex.text = 'F'

info1 = ET.SubElement(new_xml, "info", attrib={"enrolled": "yes"})

name1 = ET.SubElement(info1, "name")

name1.text = 'alen'

age1 = ET.SubElement(info1, "age", attrib={"checked": "no"})

age1.text = ''

sex1 = ET.SubElement(info1, "sex")

sex1.text = 'M'

et = ET.ElementTree(new_xml)  # 生成文档对象

et.write("test.xml", encoding="utf-8", xml_declaration=True)

                                    # <?xml version='1.0' encoding='utf-8'?>

ET.dump(new_xml)  # 打印生成的格

生成的xml内容：

<?xml version='1.0' encoding='utf-8'?>

<infolist>

    <info enrolled="yes">

        <name>akira</name>

        <age checked="no">33</age>

        <sex>F</sex>

    </info>

    <info enrolled="yes">

        <name>alen</name>

        <age checked="no">22</age>

        <sex>M</sex>

    </info>

</infolist>

4.YAML

Python也可以很容易的处理ymal文档格式，只不过需要安装一个模块，参考文档：http://pyyaml.org/wiki/PyYAMLDocumentation

例如下面的格式

/etc/http/conf/http.conf:

  file.managed:

    - source: salt://apache/http.conf

    - user: root

    - group: root

    - mode: 644

    - template: jinja

    - defaults:

        custom_var: "default value"

        other_var: 123

5.configparser

修改配置文件的，格式：

[DEFAULT]

ServerAliveInterval = 45

Compression = yes

CompressionLevel = 9

ForwardX11 = yes

[bitbucket.org]

User = hg

[topsecret.server.com]

Port = 50022

ForwardX11 = no

解析：（读取配置文件，并查询条目）

import configparser

conf = configparser.ConfigParser()

conf.read("example.conf")

print(conf.defaults())  # DEFAULT下的条目：

                        # ["ServerAliveInterval":45,"Compression","yes"...]

print(conf.sections())  # 所有选项除DEFAULT:["bitbucket.org","topsecret.server.com"]

print(conf["DEFAULT"]["ForwardX11"])  # DEFAULT选项中的"ForwardX11"的值

print(conf["bitbucket.org"]["User"])

print(conf["topsecret.server.com"]["Port"])

for key in conf["DEFAULT"]:   # 遍历DEFAULT条目

    print(key, conf["DEFAULT"][key])

写入：

import configparser

conf = configparser.ConfigParser()  # 创建配置文件对象

conf.read("example.conf")           # 读取配置文件

conf.write(open("filename.conf", "w"))  # 配置文件对象写入文件

用Python生成这个文档：

import configparser

config = configparser.ConfigParser()

config["DEFAULT"] = {'ServerAliveInterval': '',

                      'Compression': 'yes',

                     'CompressionLevel': ''}

config['bitbucket.org'] = {}

config['bitbucket.org']['User'] = 'hg'

config['topsecret.server.com'] = {}

topsecret = config['topsecret.server.com']

topsecret['Host Port'] = ''     # mutates the parser

topsecret['ForwardX11'] = 'no'  # same here

config['DEFAULT']['ForwardX11'] = 'yes'

with open('example.ini', 'w') as configfile:

   config.write(configfile)

“增，删，改”：

import ConfigParser

config = ConfigParser.ConfigParser()

config.read('i.cfg')

# ########## 读 ##########

#secs = config.sections()

#print secs

#options = config.options('group2')

#print options

#item_list = config.items('group2')

#print item_list

#val = config.get('group1','key')

#val = config.getint('group1','key')

# ########## 改写 ##########

#sec = config.remove_section('group1')

#config.write(open('i.cfg', "w"))

#sec = config.has_section('wupeiqi')

#sec = config.add_section('wupeiqi')

#config.write(open('i.cfg', "w"))

#config.set('group2','k1',11111)

#config.write(open('i.cfg', "w"))

#config.remove_option('group2','age')

#config.write(open('i.cfg', "w"))

6、hashlib

加密相关操作，3.x里代替了md5和sha模块，提供 SHA1 , 224，256，384，512，MD5算法，MD5算法是hash散列表的一种实现，也是应用最广泛的一种

hashlib，hash字符串转数字，字典就是用hash做的，字符串排序，存取速度快，

网站防篡改报警功能，定时wget网站首页，如果文件没有变更，MD5值不变

SHA1----MD5 越来越复杂，越来越安全，都是基于hash的

hmac消息加密速度比较快

中文需要 ("中文".encode(encoding="utf8")) MD5的加密，其他SHA..一样的用法

import hashlib

#  先加hello， 再加world

m = hashlib.md5()

m.update("hello".encode("utf8"))

print(type("hello".encode("utf8")))  # <class 'bytes'>

m.update("world".encode("utf8"))

print(m.digest())       # MD5 二进制表示b'\xfc^\x03\x8d8\xa5p2\x08TA\xe7\xfep\x10\xb0'

print(m.hexdigest())    # 十六进制表示fc5e038d38a57032085441e7fe7010b0

# 直接helloworld

m1 = hashlib.md5()

m1.update("helloworld".encode("utf8"))

print(m.digest())       # b'\xfc^\x03\x8d8\xa5p2\x08TA\xe7\xfep\x10\xb0'

print(m.hexdigest())    # fc5e038d38a57032085441e7fe7010b0

还不够吊？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。

import hmac

h = hmac.new('天王盖地虎'.encode("utf8"), '宝塔镇河妖'.encode("utf8"))

print (h.hexdigest())

巴特西

Python学习第二阶段Day2（json/pickle）、 shelve、xml、PyYAML、configparser、hashlib模块