shelve模块比pickle模块简单,只有一个open函数,返回类似字典的对象,
可读可写;key必须为字符串,而值可以是python所支持的数据类型
import shelve
info1={'age':18,'height':180,'weight':80}
info2={'age':73,'height':150,'weight':80}
f=shelve.open(r'123.txt')
f['egon']=info1
f['alex']=info2
f.close
d=shelve.open(r'123.txt')
print(d['egon'])
print(d['alex'])
d.close
xml模块
八 xml模块
xml是实现不同语言或程序之间进行数据交换的协议,跟json差不多,但json使用起来更简单,
不过,古时候,在json还没诞生的黑暗年代,大家只能选择用xml呀,
至今很多传统公司如金融行业的很多系统的接口还主要是xml。
xml的格式如下,就是通过<>节点来区别数据结构的:
xml数据:
<?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>
xml协议在各个语言里的都 是支持的,在python中可以用以下模块操作xml:
print(root.iter('year')) #全文搜索
print(root.find('country')) #在root的子节点找,只找一个
print(root.findall('country')) #在root的子节点找,找所有
re模块
正则就是用一些具有特殊含义的符号组合到一起(称为正则表达式)来描述字符或者字符串的方法。
常用匹配模式(元字符)
# 重复匹配:
#. ? * + {m,n} .* .*?
#1、.:代表除了换行符外的任意一个字符
# print(re.findall('a.c','abc a1c aAc aaaaaca
c'))
# a.c
# print(re.findall('a.c','abc a1c aAc aaaaaca
c',re.DOTALL))
#2、?:代表左边那一个字符重复0次或1次
# print(re.findall('ab?','a ab abb abbb abbbb abbbb'))
# ab?
#3、*:代表左边那一个字符出现0次或无穷次
# print(re.findall('ab*','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# ab*
#4、+ :代表左边那一个字符出现1次或无穷次
# print(re.findall('ab+','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# ab+
#5、{m,n}:代表左边那一个字符出现m次到n次
# print(re.findall('ab?','a ab abb abbb abbbb abbbb'))
# print(re.findall('ab{0,1}','a ab abb abbb abbbb abbbb'))
# print(re.findall('ab*','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# print(re.findall('ab{0,}','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# print(re.findall('ab+','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# print(re.findall('ab{1,}','a ab abb abbb abbbb abbbb a1bbbbbbb'))
# print(re.findall('ab{1,3}','a ab abb abbb abbbb abbbb a1bbbbbbb'))
#6、.*:匹配任意长度,任意的字符=====》贪婪匹配
# print(re.findall('a.*c','ac a123c aaaac a *123)()c asdfasfdsadf'))
# a.*c
#7、.*?:非贪婪匹配
# print(re.findall('a.*?c','a123c456c'))
# ():分组
# print(re.findall('(alex)_sb','alex_sb asdfsafdafdaalex_sb'))
# (alex)_sb
# print(re.findall(
# 'href="(.*?)"',
# '<li><a id="blog_nav_sitehome" class="menu" href="http://www.cnblogs.com/">博客园</a></li>')
# )
# <li><a id="blog_nav_sitehome" class="menu" href="http://www.cnblogs.com/">博客园</a></li>
# href=".*?"
# []:匹配一个指定范围内的字符(这一个字符来自于括号内定义的)
# print(re.findall('a[0-9][0-9]c','a1c a+c a2c a9c a11c a-c acc aAc'))
#当-需要被当中普通符号匹配时,只能放到[]的最左边或最 右边
# print(re.findall('a[-+*]c','a1c a+c a2c a9c a*c a11c a-c acc aAc'))
# print(re.findall('a[a-zA-Z]c','a1c a+c a2c a9c a*c a11c a-c acc aAc'))
# []内的^代表取反的意思
# print(re.findall('a[^a-zA-Z]c','a c a1c a+c a2c a9c a*c a11c a-c acc aAc'))
# print(re.findall('a[^0-9]c','a c a1c a+c a2c a9c a*c a11c a-c acc aAc'))
# print(re.findall('([a-z]+)_sb','egon alex_sb123123wxxxxxxxxxxxxx_sb,lxx_sb'))
# [a-z]+_sb
# | :或者
# print(re.findall('compan(ies|y)','Too many companies have gone bankrupt, and the next one is my company'))
# (?:):代表取匹配成功的所有内容,而不仅仅只是括号内的内容
# print(re.findall('compan(?:ies|y)','Too many companies have gone bankrupt, and the next one is my company'))
# print(re.findall('alex|sb','alex sb sadfsadfasdfegon alex sb egon'))
# re模块的其他方法:
# print(re.findall('alex|sb','123123 alex sb sadfsadfasdfegon alex sb egon'))
# print(re.search('alex|sb','123213 alex sb sadfsadfasdfegon alex sb egon').group())
# print(re.search('^alex','123213 alex sb sadfsadfasdfegon alex sb egon'))
# print(re.search('^alex','alex sb sadfsadfasdfegon alex sb egon').group())
# print(re.match('alex','alex sb sadfsadfasdfegon alex sb egon').group())
# print(re.match('alex','123213 alex sb sadfsadfasdfegon alex sb egon'))
# info='a:b:c:d'
# print(info.split(':'))
# print(re.split(':',info))
# info=r'get :a.txt3333/rwx'
# print(re.split('[ :\/]',info))
# print('egon is beutifull egon'.replace('egon','EGON',1))
# print(re.sub('(.*?)(egon)(.*?)(egon)(.*?)',r'123EGON5','123 egon is beutifull egon 123'))
# (123 )(egon)( is beutifull )(egon)( 123)
#123EGON5
# print(re.sub('(lqz)(.*?)(SB)',r'321',r'lqz is SB'))
# print(re.sub('([a-zA-Z]+)([^a-zA-Z]+)([a-zA-Z]+)([^a-zA-Z]+)([a-zA-Z]+)',r'52341',r'lqzzzz123+ is SB'))
#(lqzzzz)(123+ )(is)( )(SB)
pattern=re.compile('alex')
print(pattern.findall('alex is alex alex'))
print(pattern.findall('alexasdfsadfsadfasdfasdfasfd is alex alex'))