re(正则)模块

re(正则)模块

re.findall

import re

s = "meet_宝元_meet"
print(re.findall("meet",s))
# ['meet', 'meet']
# 从字符串中全部查找内容,返回一个列表

s = "meet_宝元_meet123"
print(re.findall("w",s))
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', 'm', 'e', 'e', 't', '1', '2', '3']
# 查找数字,字母(中文),下划线

s = "meet_宝元_meet123!@#"
print(re.findall("W",s))
# ['!', '@', '#']
# 查找非数字,字母(中文),下划线

s = "meet_  宝元_  me  et	 
"
print(re.findall("s",s))
# [' ', ' ', ' ', ' ', ' ', ' ', '	', ' ', '
']
# 查找任意空格,换行符,制表符

s = "meet_  宝元_  me et	 
"
print(re.findall("S",s))
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', 'm', 'e', 'e', 't']
# 查找非任意空格,换行符,制表符

s = "meet_ 宝元_123me  et	 
"
print(re.findall("d",s))
# ['1', '2', '3']
# 查找数字

s = "meet_ 宝元_123me  et	 
"
print(re.findall("D",s))
# ['m', 'e', 'e', 't', '_', ' ', '宝', '元', '_', 'm', 'e', ' ', ' ', 'e', 't', '	', ' ', '
']
# 查找非数字

s = "meet宝元_123meet	 
"
print(re.findall("Ameet",s))
# ['meet']
# 查找是否以什么开头

s = "meet宝元_123meet"
print(re.findall("meet",s))
# ['meet']
# 查找是否以什么结尾

s = "meet宝元_123meet 
 	 
"
print(re.findall("
",s))
# ['
', '
']
# 查找换行符

s = "meet宝元_123meet 
 	 
"
print(re.findall("	",s))
# ['	']
# 查找制表符

s = "mtet宝元_123maet 
 	"
print(re.findall("m.e",s))
# ['mte', 'mae']
# .只能匹配任意一个内容(非换行符)

s = "m
et宝元_123maet 
 	 "
print(re.findall("m.e",s,re.DOTALL))
# ['m
e', 'mae']
# .只能匹配任意一个内容

s = "meet宝元_1A-23maet"
print(re.findall("[a-z]",s))
# ['m', 'e', 'e', 't', 'm', 'a', 'e', 't']
# 小写的a到z

print(re.findall("[A-Z]",s))
# ['A']
# 大写的A到Z

print(re.findall("[A-Za-z]",s))
# ['m', 'e', 'e', 't', 'A', 'm', 'a', 'e', 't']
# 大写和小写的A到Z,a到z

print(re.findall("[a-z0-9]",s))
# ['m', 'e', 'e', 't', '1', '2', '3', 'm', 'a', 'e', 't']
# 小写的a到z和数字0到9

s = "meet宝元_1A-23maet"
print(re.findall("[^0-9]",s))
# ['m', 'e', 'e', 't', '宝', '元', '_', 'A', '-', 'm', 'a', 'e', 't']
# [^0-9] 查找非0-9的内容

s = "mmmmmm"
print(re.findall("m*",s))
# ['mmmmmm', '']
# 匹配 * 前元素0个或多个 [贪婪匹配] 

s = "meet_asdf_meees_mmns_aaam_meeeee"
print(re.findall("me+",s))
# ['mee', 'meee', 'meeeee']
# 匹配 + 前元素一个或多个 

s = "meet_asdf_m"
print(re.findall("m?",s))
# ['m', '', '', '', '', '', '', '', '', '', 'm', '']
# 匹配 ? 前元素0个或一个[非贪婪匹配]

s = "meet_asdf_msss_mmns_aaam"
print(re.findall("s{3}",s))
# ['sss']
# 匹配 s{3} s重复3次 == sss 

s = "meet_assdf_msss_mmns_aaam"
print(re.findall("s{1,3}",s))
# ['ss', 'sss', 's']
# 指定元素最少重复多少次,最多重复多少次

s = "meet_assdf_msss_mmns_aaam"
print(re.findall("m|s",s))
# ['m', 's', 's', 'm', 's', 's', 's', 'm', 'm', 's', 'm']
# m|s,m或者s 

s = "meet_meet_assdf_mssst_(.)mmns_aaamt"
print(re.findall("m(.+)t",s))
# ['eet_meet_assdf_mssst_(.)mmns_aaam']
# m()t,取m与t中间的所有元素 [贪婪匹配]

s = "meet_assdf_mssst_(.)mmns_aaamaaat"
print(re.findall("m(?:..?)t",s))
# ["meet"]
# ?: 会匹配到括号两边的元素

扩展练习:

扩展练习:
import re
s = "alex_sb ale123_sb wu12sir_sb wusir_sb ritian_sb 的 alex wusir "
print(re.findall("w+_sb",s))
print(re.findall("[a-z]+_sb",s))
# ['alex_sb', 'ale123_sb', 'wu12sir_sb', 'wusir_sb', 'ritian_sb']
# ['alex_sb', 'sir_sb', 'wusir_sb', 'ritian_sb']

print(re.findall("常(.*)娃","常鑫垃圾_井盖_烧饼吃娃娃_自行车_葫芦爷爷救娃娃"))
print(re.findall("常(.*?)娃","常鑫垃圾_井盖_烧饼吃娃娃_自行车_葫芦爷爷救娃娃"))
# ['鑫垃圾_井盖_烧饼吃']
# ['鑫垃圾_井盖_烧饼吃娃娃_自行车_葫芦爷爷救娃']

re.search

import re
s = "_sb alex 123_sb wu12sir_sb wusir_sb ritian_sb 的 x wusir "
print(re.search("ale",s).group())
# "ale"
# 找到一个元素后就停止查找,从字符串中进行查找,找到后返回的是一个元素,查看元素加.group()
# 如果字符串中没有该元素,报错

re.match

import re
s = 'alex_sb alex 123_sb wu12sir_sb wusir_sb ritian_sb 的 x wusir '
print(re.match("ale",s).group())
# "ale"
# match 找到1个后就停止查找了,只从字符串的开头查找.找到后返回的是一个对象,查看元素.group()
# 如果字符串开头没有则报错

re.split

import re
s = "_sb alex,123:sb;wu12sir#sb*wusir!sb ritian_sb 的 x wusir "
print(re.split("[#,:!*]",s))
# ['_sb alex', '123', 'sb;wu12sir', 'sb', 'wusir', 'sb ritian_sb 的 x wusir ']
# 分割

re.sub

import re
print(re.sub("barry","太亮","barry是最好的讲师,barry就是一个普通老师,请不要将barry当男神对待"))
# 太亮是最好的讲师,太亮就是一个普通老师,请不要将太亮当男神对待
# 替换

compile

obj = re.compile("w")
print(obj.findall("meet_宝元_常鑫垃圾"))
# ['m', 'e', 'e', 't', '_', '宝', '元', '_', '常', '鑫', '垃', '圾']
# 自定义匹配规则

finditer

g = re.finditer("w","常鑫垃圾")
for i in g:
    print(i.group())
# 常 鑫 垃 圾
# 返回的是一个迭代器的地址,查看元素加 .group()

给分组起名字

import re
ret = re.search("<(?P<tag_name>w+)>w+</w+>","<h1>hello</h1>")
print(ret.group("tag_name"))
print(ret.group())
# h1
# <h1>hello</h1>

import re
ret = re.search(r"<(w+)>w+</1>","<h1>hello</h1>")
print(ret.group(1))
print(ret.group())
# h1
# <h1>hello</h1>

import re
ret = re.search("(?P<aaa>w+)dfa","asbsadfasdfa")
print(ret.group())
print(ret.group("aaa"))
# asbsadfasdfa
# asbsadfas