常用模块—re模块

Posted 2020-10-11

import re
#findall查找所有,从头找到尾，找到的结果取出来
‘‘‘
\w：字母，数字，下划线
\W：非字母，数字，下划线
\s:空白字符 ，等价于\n,\t
\S:非空白字符
\d:数字
\D:非数字
\A:从开头找
\Z:从结尾找
\n：换行符
\t：制表符
‘‘‘
# print(re.findall(‘\W‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘\S‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘\d\d‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘\D‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘^a‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘6$‘,‘alex say hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘\n‘,‘alex say\n hello alex sb 123_ 4%6*6‘))
# print(re.findall(‘\t‘,‘alex say\t hello alex sb 123_ 4%6*6‘))

‘‘‘
重复匹配
.:任意一个字符，什么都可以
*:左边字符出现0次或无穷次
?:左边字符出现0次或1次
+:左边字符出现1次或无穷次
{}:｛n,m}左边的字符出现n到m次

‘‘‘
# print(re.findall(‘a.e‘,‘alex a\ne hello alex sb 123_ 4%6*6‘,re.DOTALL))
# print(re.findall(‘ab?‘,‘ab a abbba abbb‘))
# print(re.findall(‘ab{0,1}‘,‘ab a abbba abbb‘))
# print(re.findall(‘ab*‘,‘ab a abbba abbb‘))
# print(re.findall(‘ab+‘,‘ab a abbba abbb‘))
# print(re.findall(‘ab{3,}‘,‘ab a abbba abbbb abbbbb‘))

‘‘‘
.*:所有字符，贪婪匹配
.*?:非贪婪匹配
‘‘‘
# print(re.findall(‘a.*?b‘,‘axde123.bbbbaabb‘))
# print(re.findall(‘a.*b‘,‘axde123.bbbbaabb‘))

#分组（）
# print(re.findall(‘<imag href="(.*)" />‘,
#                  ‘<h1>hello</h1><a href=""><imag href="http://www.baidu.com/a.jpg" />‘))
#l或者
#print(re.findall(‘compan(?:ies|y)‘,‘too many companies have gone bankrupt,and the next is my company‘))


# re.search()，从头找到尾，但匹配成功一次就结束
#print(re.search(‘alex‘,‘alex say hello alex sb 123_ 4%6*6‘).group())
# re.match()，从头匹配，头部找不到返回NONE
#print(re.match(‘alex‘,‘alex say hello alex sb 123_ 4%6*6‘).group())