常用模块：re ，shelve与xml模块

import xml.etree.ElementTree as ET
 
tree = ET.parse("xmltest.xml")
root = tree.getroot()
print(root.tag)
 
#遍历xml文档
for child in root:
    print(‘========>‘,child.tag,child.attrib,child.attrib[‘name‘])
    for i in child:
        print(i.tag,i.attrib,i.text)
 
#只遍历year 节点
for node in root.iter(‘year‘):
    print(node.tag,node.text)
#---------------------------------------

import xml.etree.ElementTree as ET
 
tree = ET.parse("xmltest.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‘)
    node.set(‘version‘,‘1.0‘)
tree.write(‘test.xml‘)
 
 
#删除node
for country in root.findall(‘country‘):
   rank = int(country.find(‘rank‘).text)
   if rank > 50:
     root.remove(country)
 
tree.write(‘output.xml‘)
复制代码
复制代码
#在country内添加（append）节点year2
import xml.etree.ElementTree as ET
tree = ET.parse("a.xml")
root=tree.getroot()
for country in root.findall(‘country‘):
    for year in country.findall(‘year‘):
        ifint(year.text) > 2000:
            year2=ET.Element(‘year2‘)
            year2.text=‘新年‘
            year2.attrib={‘update‘:‘yes‘}
            country.append(year2) #往country节点下添加子节点

tree.write(‘a.xml.swap‘)
复制代码

 =================================匹配模式=================================
#一对一的匹配
# ‘hello‘.replace(old,new)
# ‘hello‘.find(‘pattern‘)#正则匹配import re
#\w与\Wprint(re.findall(‘\w‘,‘hello egon 123‘)) #[‘h‘, ‘e‘, ‘l‘, ‘l‘, ‘o‘, ‘e‘, ‘g‘, ‘o‘, ‘n‘, ‘1‘, ‘2‘, ‘3‘]print(re.findall(‘\W‘,‘hello egon 123‘)) #[‘ ‘, ‘ ‘]#\s与\Sprint(re.findall(‘\s‘,‘hello  egon  123‘)) #[‘ ‘, ‘ ‘, ‘ ‘, ‘ ‘]print(re.findall(‘\S‘,‘hello  egon  123‘)) #[‘h‘, ‘e‘, ‘l‘, ‘l‘, ‘o‘, ‘e‘, ‘g‘, ‘o‘, ‘n‘, ‘1‘, ‘2‘, ‘3‘]#\n \t都是空,都可以被\s匹配print(re.findall(‘\s‘,‘hello \n egon \t 123‘)) #[‘ ‘, ‘\n‘, ‘ ‘, ‘ ‘, ‘\t‘, ‘ ‘]#\n与\tprint(re.findall(r‘\n‘,‘hello egon \n123‘)) #[‘\n‘]print(re.findall(r‘\t‘,‘hello egon\t123‘)) #[‘\n‘]#\d与\Dprint(re.findall(‘\d‘,‘hello egon 123‘)) #[‘1‘, ‘2‘, ‘3‘]print(re.findall(‘\D‘,‘hello egon 123‘)) #[‘h‘, ‘e‘, ‘l‘, ‘l‘, ‘o‘, ‘ ‘, ‘e‘, ‘g‘, ‘o‘, ‘n‘, ‘ ‘]#\A与\Zprint(re.findall(‘\Ahe‘,‘hello egon 123‘)) #[‘he‘],\A==>^print(re.findall(‘123\Z‘,‘hello egon 123‘)) #[‘he‘],\Z==>$#^与$print(re.findall(‘^h‘,‘hello egon 123‘)) #[‘h‘]print(re.findall(‘3$‘,‘hello egon 123‘)) #[‘3‘]# 重复匹配：| . | * | ? | .* | .*? | + | {n,m} |
#.print(re.findall(‘a.b‘,‘a1b‘)) #[‘a1b‘]print(re.findall(‘a.b‘,‘a1b a*b a b aaab‘)) #[‘a1b‘, ‘a*b‘, ‘a b‘, ‘aab‘]print(re.findall(‘a.b‘,‘a\nb‘)) #[]print(re.findall(‘a.b‘,‘a\nb‘,re.S)) #[‘a\nb‘]print(re.findall(‘a.b‘,‘a\nb‘,re.DOTALL)) #[‘a\nb‘]同上一条意思一样#*print(re.findall(‘ab*‘,‘bbbbbbb‘)) #[]print(re.findall(‘ab*‘,‘a‘)) #[‘a‘]print(re.findall(‘ab*‘,‘abbbb‘)) #[‘abbbb‘]#?print(re.findall(‘ab?‘,‘a‘)) #[‘a‘]print(re.findall(‘ab?‘,‘abbb‘)) #[‘ab‘]
#匹配所有包含小数在内的数字print(re.findall(‘\d+\.?\d*‘,"asdfasdf123as1.13dfa12adsf1asdf3")) #[‘123‘, ‘1.13‘, ‘12‘, ‘1‘, ‘3‘]#.*默认为贪婪匹配print(re.findall(‘a.*b‘,‘a1b22222222b‘)) #[‘a1b22222222b‘]#.*?为非贪婪匹配：推荐使用print(re.findall(‘a.*?b‘,‘a1b22222222b‘)) #[‘a1b‘]#+print(re.findall(‘ab+‘,‘a‘)) #[]print(re.findall(‘ab+‘,‘abbb‘)) #[‘abbb‘]#{n,m}print(re.findall(‘ab{2}‘,‘abbb‘)) #[‘abb‘]print(re.findall(‘ab{2,4}‘,‘abbb‘)) #[‘abb‘]print(re.findall(‘ab{1,}‘,‘abbb‘)) #‘ab{1,}‘ ===> ‘ab+‘print(re.findall(‘ab{0,}‘,‘abbb‘)) #‘ab{0,}‘ ===> ‘ab*‘#[]print(re.findall(‘a[1*-]b‘,‘a1b a*b a-b‘)) #[]内的都为普通字符了，且如果-没有被转意的话，应该放到[]的开头或结尾print(re.findall(‘a[^1*-]b‘,‘a1b a*b a-b a=b‘)) #[]内的^代表的意思是取反，所以结果为[‘a=b‘]print(re.findall(‘a[0-9]b‘,‘a1b a*b a-b a=b‘)) #[]内的^代表的意思是取反，所以结果为[‘a=b‘]print(re.findall(‘a[a-z]b‘,‘a1b a*b a-b a=b aeb‘)) #[]内的^代表的意思是取反，所以结果为[‘a=b‘]print(re.findall(‘a[a-zA-Z]b‘,‘a1b a*b a-b a=b aeb aEb‘)) #[]内的^代表的意思是取反，所以结果为[‘a=b‘]#\# print(re.findall(‘a\\c‘,‘a\c‘)) #对于正则来说a\\c确实可以匹配到a\c,但是在python解释器读取a\\c时，会发生转义，然后交给re去执行，所以抛出异常print(re.findall(r‘a\\c‘,‘a\c‘)) #r代表告诉解释器使用rawstring，即原生字符串，把我们正则内的所有符号都当普通字符处理，不要转义print(re.findall(‘a\\\\c‘,‘a\c‘)) #同上面的意思一样，和上面的结果一样都是[‘a\\c‘]#():分组print(re.findall(‘ab+‘,‘ababab123‘)) #[‘ab‘, ‘ab‘, ‘ab‘]print(re.findall(‘(ab)+123‘,‘ababab123‘)) #[‘ab‘]，匹配到末尾的ab123中的abprint(re.findall(‘(?:ab)+123‘,‘ababab123‘)) #findall的结果不是匹配的全部内容，而是组内的内容,?:可以让结果为匹配的全部内容print(re.findall(‘href="(.*?)"‘,‘<a href="http://www.baidu.com">点击</a>‘))#[‘http://www.baidu.com‘]print(re.findall(‘href="(?:.*?)"‘,‘<a href="http://www.baidu.com">点击</a>‘))#[‘href="http://www.baidu.com"‘]#|print(re.findall(‘compan(?:y|ies)‘,‘Too many companies have gone bankrupt, and the next one is my company‘))
复制代码