re模块

Posted 2022-01-05 wjlv

# encoding:utf8
import re

# findall方法，查找全部匹配到的结果
s = ‘abcabbca3c‘
print(re.findall(‘ab‘, s))  # 结果为：[‘ab‘, ‘ab‘]

# . 单个字符
s = ‘abcabbca3c‘
print(re.findall(‘a.c‘, s))  # 结果为：[‘abc‘, ‘a3c‘]

# ?前面一个字符匹配0或1次
s = ‘2acbabcabbacc‘
print(re.findall(‘ab?‘, s))  # 结果为：[‘a‘, ‘ab‘, ‘ab‘, ‘a‘]

# + 前面一个字符匹配1~+∞次
s = ‘2acbabcabbacc‘
print(re.findall(‘ab+‘, s))  # 结果为：[‘ab‘, ‘abb‘]

# * 前面一个字符匹配0~+∞次
s = ‘2acbabcabbacc‘
print(re.findall(‘ab*‘, s))  # 结果为：[‘a‘, ‘ab‘, ‘abb‘, ‘a‘]

# ^ 以^后面的字符串开头,精准匹配
s = ‘acbabcacbbacc‘
print(re.findall(‘^acb‘, s))  # 结果为：[‘acb‘]
print(re.findall(‘^abc‘, s))  # 结果为：[]

# $ 以$前面的字符串开头,精准匹配
s = ‘acbabcacbbacc‘
print(re.findall(‘acc$‘, s))  # 结果为：[‘acc‘]
print(re.findall(‘abc$‘, s))  # 结果为：[]

#  指定匹配次数。3前面的字符匹配3次；1,同+,前面的字符匹配1~+∞次；1,3前面的字符匹配1-3次
s = ‘2aabcabbacabbbc‘
print(re.findall(‘ab2‘, s))  # 结果为：[‘abb‘, ‘abb‘]
print(re.findall(‘ab1,‘, s))  # 结果为：[‘ab‘, ‘abb‘, ‘abbb‘]
print(re.findall(‘ab2,3‘, s))  # 结果为：[‘abb‘, ‘abbb‘]

# () 吧()内的字符串作为整体。优先完全匹配；可通过?:来全部匹配
s = ‘2aabcabbacabbbc‘
print(re.findall(‘(ab)*‘, s))  # 匹配0到多次，结果为：[‘‘, ‘‘, ‘ab‘, ‘‘, ‘ab‘, ‘‘, ‘‘, ‘‘, ‘ab‘, ‘‘, ‘‘, ‘‘, ‘‘]
print(re.findall(‘(ab)+‘, s))  # 匹配1到多次，结果为：[‘ab‘, ‘ab‘, ‘ab‘]
s = ‘abcababcababab‘
print(re.findall(‘(ab)‘, s))  # 整体匹配，结果为：[‘ab‘, ‘ab‘, ‘ab‘, ‘ab‘, ‘ab‘, ‘ab‘]
print(re.findall(‘(?:ab)+‘, s))  # 整体全部匹配，结果为：[‘ab‘, ‘abab‘, ‘ababab‘]
print(re.findall(‘(?:ab)+‘, ‘abababab‘))  # 整体全部匹配， 结果为：[‘abababab‘]
print(re.findall(‘(ab)+‘, ‘abababab‘))  # 整体完全匹配，结果为：[‘ab‘]

# | 吧|左右的字符串作为整体匹配，若匹配成功左侧，则不再匹配右侧
s = ‘abcdacd‘
print(re.findall(‘abc|cd‘, s))  # 优先匹配左侧，结果为[‘abc‘, ‘cd‘]
print(re.findall(‘ab|cd‘, s))  # 结果为[‘ab‘, ‘cd‘]
print(re.findall(‘abc|abcd‘, ‘abcdabc‘))  # 优先匹配左侧，结果是[‘abc‘,‘abc‘]

# [] 吧[]内的字符集单独匹配,[]内的字符均当做普通字符处理；^表示不含
s = ‘abcdabdacdbad‘
print(re.findall(‘a[bc]d‘, s))  # 结果是[‘abd‘, ‘acd‘]
print(re.findall(‘a[b*]d‘, ‘abcabdacca*da‘))  # 结果是[‘abd‘, ‘a*d‘]

# 在[]内写^表示不包含字符
print(re.findall(‘a[^cb]d‘, ‘aedacdahdabdasd‘))  # 结果是[‘aed‘, ‘ahd‘, ‘asd‘]
print(re.findall(‘a[^a-z]c‘, ‘asa2a3c4c‘))  # 结果是[‘a3c‘]
print(re.findall(‘\([^()]+\)‘, ‘1+7-(3*(6-2)-4)‘))  # 提取最里面的括号和内容，结果是[‘(6-2)‘]

# 查找特殊字符例如*+().等，需要转义，使用\或者r‘待查找字符串‘
print(re.findall(‘www.baidu‘, ‘www.163www.baidu.comwwwabaidu‘))  # 结果是[‘www.baidu‘, ‘wwwabaidu‘],会默认.为一个字符
print(re.findall(‘www\.baidu‘, ‘www.163www.baidu.com‘))  # 结果是[‘www.baidu‘]
print(re.findall(r‘www.baidu‘, ‘www.163www.baidu.com‘))  # 结果是[‘www.baidu‘]

# 在[]内写范围，比如0-9，比如a-z
print(re.findall(‘a[1-3]c‘, ‘abca1caesa3cas‘))  # 结果是[‘a1c‘, ‘a3c‘]
print(re.findall(‘a[1-3a-zA-Z]c‘, ‘abca1caDsascaFc‘))  # 结果是[‘abc‘, ‘a1c‘, ‘asc‘, ‘aFc‘]

# 特殊字符 \d 表示[0-9]，\D表示除去前面的范围剩下的
print(re.findall(‘\d‘, ‘ab123c.d32a+"3452d‘))  # 结果是[‘1‘, ‘2‘, ‘3‘, ‘3‘, ‘2‘, ‘3‘, ‘4‘, ‘5‘, ‘2‘]
print(re.findall(‘\d+‘, ‘ab123c.d32a+"3452d‘))  # 结果是[‘123‘, ‘32‘, ‘3452‘]
print(re.findall(‘\D‘, ‘ab123c.d32a+"3452d‘))  # 结果是[‘a‘, ‘b‘, ‘c‘, ‘.‘, ‘d‘, ‘a‘, ‘+‘, ‘"‘, ‘d‘]
print(re.findall(‘\D+‘, ‘ab123c.d32a+"3452d‘))  # 结果是[‘ab‘, ‘c.d‘, ‘a+"‘, ‘d‘]

# 特殊字符 \w表示[0-9a-zA-Z_]以及中文，\W表示除去前面范围剩下的
print(re.findall(‘\w+‘, ‘ab12我3_c.d3是2a+"34_52d‘))  # 结果是[‘ab12我3_c‘, ‘d3是2a‘, ‘34_52d‘]
print(re.findall(‘\W+‘, ‘ab12我3_c.d3是2a+"34_52d‘))  # 结果是[‘.‘, ‘+"‘]