python基础语法21 re模块补充 正则表达式

正则表达式

import re

print(re.findall('\w', 'hello 123_ */-='))
print(len(re.findall('\w', 'hello 123_ */-=')))

print(re.findall('\W', 'hello 123_ */-='))

print(re.findall('\s', 'hell\no 12\t3_ */-='))

print(re.findall('\S', 'hell\no 12\t3_ */-='))

print(re.findall('\d', 'hell\no 12\t3_ */-='))
print(re.findall('\D', 'hell\no 12\t3_ */-='))

print(re.findall('\n', 'hell\no 12\t3_ */-='))
print(re.findall('\t', 'hell\no 12\t3_ */-='))
print(re.findall('l', 'hell\no 12\t3_ */-='))

print(re.findall('tank', 'my name is tank, tank is handsome'))
print(re.findall('^tank', 'tank my name is tank, tank is handsome'))
print(re.findall('tank$', 'tank my name is tank,tank is handsome tank'))

重复匹配
.:匹配换行符以外的任意一个字符
['abc','a1c','aac','aac','a*c','a+c']
print(re.findall('a.c', 'abc a1c aac asd aaaaac a*c a+c abasd'))
a.c
print(re.findall('a.c', 'abc a1c aac a\nc asd aaaaac a*c a+c abasd', re.DOTALL))

[]: 匹配一个字符,该字符属于中括号内指定的字符
print(re.findall('a..c', 'abc a1 c aac asd aaaaac a *c a+c abasd ='))
print(re.findall('a.c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))
print(re.findall('a[a-z]c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))
print(re.findall('a[A-Z]c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))

[]内的+ * 不是量词
print(re.findall('a[-+*/]c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))
print(re.findall('a[a-z][a-z]c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))
^在[]内代表非
print(re.findall('a[^a-z]c', 'abc a1 c aac aAc aBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'))

*: 必须与其他字符连用，代表左侧的字符出现0次或者无穷次
ab* ---》 匹配0个或多个b字符, 并且是a开头的
print(re.findall('ab*', 'a ab abbb abbbb a1bbbb a-123'))
# ['a','ab','abbb','abbbb','a','a']
* == {0,}
print(re.findall('ab{0,}', 'a ab abbb abbbb a1bbbb a-123'))

?： 必须与其他字符连用,代表左侧的字符出现0次或者1次
print(re.findall('ab?', 'a ab abbb abbbb a1bbbb a-123'))
# ab?
# ['a','ab','ab','ab','a','a']
{0,1} == ?
print(re.findall('ab{0,1}', 'a ab abbb abbbb a1bbbb a-123'))

+： 必须与其他字符连用,代表左侧的字符出现1次或者无穷次
ab+
print(re.findall('ab+', 'a ab abbb abbbb a1bbbb a-123'))
# ['ab','abbb','abbbb']
{1,} == +
print(re.findall('ab{1,}', 'a ab abbb abbbb a1bbbb a-123'))

# {n,m}： 必须与其他字符连用
ab{1,3}  b字符出现1次——3次
print(re.findall('ab{1,3}', 'a ab abbb abb abbbb a1bbbb a-123'))
# ['ab', 'abbb', 'abb', 'abbb']


.*：贪婪匹配
a.*d ---> 匹配字符以最后的d作为结束标识
print(re.findall('a.*d', 'ab123adfc1134124123aasfc123123'))

# .*?:非贪婪匹配
a.*?c
print(re.findall('a.*?c', 'ab123adfc1134124123adasfc123123'))

():分组
expression=".*?"
print(re.findall('expression="(.*?)"', 'expression="1+2+3/4*5" tank="handsome"'))
print(re.findall('href="(.*?)"',
                 '<p>段落</p><a href="https://www.sb.com">点我啊</a><h1>标题</h1><a href="https://www.sb.com">点我啊</a>'))

a|b
print(re.findall('a|b', 'ab123abasdfaf'))

 companies  company
(?:)表示非捕获分组，和捕获分组唯一的区别在于，非捕获分组匹配的值不会保存起来
(?:)---> 将ies或者y保留与compan拼接
print(re.findall('compan(?:ies|y)',
                 'Too many companies have gone bankrupt, and the next one is my company'))

标识性字符(提取的内容)
print(re.findall('ale(x)', 'alex is SB,alex is bigSB'))
print(re.search('alex', 'alex is SB,alex is bigSB').group())
print(re.search('abcdefg', 'alex is SB,alex is bigSB'))

print(re.search('^alex', '123alex is SB,alex is bigSB'))
print(re.match('alex', '123alex is SB,alex is bigSB'))

l = 'tank:17:male'.split(':')
print(l)
 了解: 根据“ ” or “:” or “/” or “-” 来进行切分
l1 = re.split('[ :/-]', 'a-b/c tank:17:male xxx')
print(l1)

[a-z]+xx
了解: sub: 替换  ---》 第二个参数 根据正则替换到第三参数中
print(re.sub('[a-z]+xx', 'yxp', 'lxx is good,sb is lllxx wxx is good cxx is good'))

了解: compile可以将字符转成字节
pattern = re.compile('alex')  # 返回一个对象
print(pattern)
print(pattern.findall('alex is SB,alex is bigSB'))
print(re.findall('alex', 'alex is SB,alex is bigSB'))

print(pattern.search('alex is SB,alex is bigSB').group())  # alex

import re

str1 = '1abc a1 c aac aAc\n \taBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'
print(re.findall('\w', str1))  # \w---匹配字母数字及下划线
print(re.findall('\W', str1))  # \w---匹配非字母数字及下划线 \n \t
print(re.findall('\s', str1))  # 匹配任意空白字符\n\t\r\f
print(re.findall('\S', str1))  # 匹配非空白字符
print(re.findall('\d', str1))  # 匹配数字等价0-9
print(re.findall('\D', str1))  # 匹配任意非数字0-9
print(re.findall('\Aac', str1))  # 匹配字母开始
print(re.findall('\\n\Z', str1))  # 匹配字母结束，只匹配到换行前的结束字符串
print(re.findall('\n', str1))  # 匹配换行符
print(re.findall('\t', str1))  # 匹配换行符
print(re.findall('^1abc', str1))  # 匹配以什么开头
print(re.findall('c$', str1))  # 匹配以什么结尾

str1 = '1abbb a1 a\nbc aac aAc\n \taBc asd aaaaac a-c a/c a *c a+c abasd = a1c a2c'
print(re.findall('a.b', str1))  # 匹配中间是任意字符除了换行符
print(re.findall('a.b', str1, re.S))  # 匹配中间是任意字符包含换行符
print(re.findall('a.b', str1, re.DOTALL))  # 匹配中间是任意字符包含换行符
print(re.findall('ab*', str1))  # 匹配0个或多个表达式
print(re.findall('ab+', str1))  # 匹配1个或多个表达式
print(re.findall('ab?', str1))  # 匹配0个或1个表达式
print(re.findall('ab?a', str1))  # 匹配0个或1个表达式指代找b
print(re.findall('ab{2}', 'abbb aabxbaa'))  # 表示1个a2个b
print(re.findall('a[1*-]b', 'a1b  a\nb a*b a-b'))  # ['a1b', 'a*b', 'a-b']
print(re.findall('a[^1*-]b', 'a1b a*b a-b a=b'))  # []内的^表示取反
print(re.findall('a[0-9]b', 'a1b a*b a-b a=b'))  # ['a1b']
print(re.findall('a[a-z]b', 'a1b a*b a-b a=b aeb'))  # ['aeb']
print(re.findall('a[a-zA-Z]b', 'a1b a*b a-b a=b aeb aEb'))  # ['aeb', 'aEb']
print(re.findall(r'a\\c', 'a\c'))
print(re.findall('(ab)+123', 'ababab123'))
print(re.findall('(?:ab)+123', 'xxxaab123'))  # ['ab123']
print(re.findall('(?:ab)+123', '12abab123'))  # ['abab123']如果有相同的ab连接在一起就一起显示
print(re.findall('compan(?:ies|y)', 'Too many companies have gone bankrupt, and the next one is my company'))
print(re.findall('href="(.*?)"',
                 '<p>段落</p><a href="https://www.sb.com">点我啊</a><h1>标题</h1><a href="https://www.sb.com">点我啊</a>'))
print(re.findall('a|b', 'ab123abasdfaf'))
print(re.split('ab', 'abcd'))  # ['', 'cd']
print(re.split('[ab]', 'abcd'))  # ['', '', 'cd'] #如果是列表按照索引取
print('===>', re.sub('a', 'A', 'alex make love'))  # ===> Alex mAke love，不指定n，默认替换所有
print('===>', re.sub('a', 'A', 'alex make love', 1))  # ===> Alex make love

obj = re.compile('\d{3}')  # 查找3个数字还要连续的
print(obj.search('abc123eee1e').group())  # 12
print(obj.findall('abc123eeee'))  # ['12'],重用了obj

print(re.findall('a,b|c', 'ac,a,b，accc'))
print(re.findall('ab?', 'a'))

import re

print(re.findall("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>", "<h1>hello</h1>"))  # ['h1']


import re

str1 = '<h1>www.oldboyedu.*+com<h1>'

# www.oldboyedu.
re.findall(
    # \. == '.'
    # . == 任意字符
    'www.*\.\*\+',
    str1
)