1 XML 模块
import xml.etree.ElementTree as ET
tree=ET.parse('a.xml')
root=tree.getroot()
三种查找节点的方式
res=root.iter('rank') # 会在整个树中进行查找，而且是查找到所有
for item in res:
# print(item)
print('='*50)
print(item.tag) # 标签名
print(item.attrib) #属性
print(item.text) #文本内容
res=root.find('country') # 只能在当前元素的下一级开始查找。并且只找到一个就结束
print(res.tag)
print(res.attrib)
print(res.text)
nh=res.find('neighbor')
print(nh.attrib)
cy=root.findall('country') # 只能在当前元素的下一级开始查找,
print([item.attrib for item in cy])
==========================================>改
import xml.etree.ElementTree as ET
tree=ET.parse('a.xml')
root=tree.getroot()
for year in root.iter('year'):
year.text=str(int(year.text) + 10)
year.attrib={'updated':'yes'}
# tree.write('b.xml')
tree.write('a.xml')
==========================================>增
import xml.etree.ElementTree as ET
tree=ET.parse('a.xml')
root=tree.getroot()
for country in root.iter('country'):
# print(country)
year=country.find('year')
# print(year)
if int(year.text) > 2020:
# print(country.attrib)
# ele=ET.Element('egon')
# ele.attrib={'nb':'yes'}
# ele.text='非常帅'
# country.append(ele)
country.remove(year)
tree.write('b.xml')
2 shelve 模块
import shelve
info1={'age':18,'height':180,'weight':80}
info2={'age':73,'height':150,'weight':80}
d=shelve.open('db.shv')
d['egon']=info1
d['alex']=info2
d.close()
d=shelve.open('db.shv')
# print(d['egon'])
# print(d['alex'])
d.close()
d=shelve.open('db.shv',writeback=True)
d['alex']['age']=10000
# print(d['alex'])
d.close()
d=shelve.open('db.shv',writeback=True)
print(d['alex'])
d.close()
import json
l={'a':1,'b':2,'c':3}
json.dump(l,open('a.json','wt',encoding='utf-8'))
3 re 模块
import re
print(re.findall('w','ab 12+- *&_'))
w
print(re.findall('W','ab 12+- *&_'))
print(re.findall('s','ab 1 2 +- *&_'))
print(re.findall('S','ab 1 2 +- *&_'))
print(re.findall('d','ab 1 2 +- *&_'))
d
print(re.findall('D','ab 1 2 +- *&_'))
print(re.findall('w_sb','egon alex_sb123123wxx_sb,lxx_sb'))
w_sb
print(re.findall('Aalex','abcalex is salexb'))
print(re.findall('Aalex','alex is salexb'))
print(re.findall('^alex','alex is salexb'))
print(re.findall('sb','alexsb is sbalexbsb'))
print(re.findall('sb$','alexsb is sbalexbsb'))
sb
print(re.findall('^ebn$','ebn1'))
ebn
print(re.findall('a c','a c a c a1c'))
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'))