# ### 正则表达式
# findall 匹配字符串中相应内容, 返回列表
import re
'''
lst = re.findall(正则表达式,要匹配的字符串)
'''
'''
\d 匹配数字
\D 匹配非数字
'''
lst = re.findall("\d","sadfsdfsa 98&*^&^&92sdf3sdf839 sdf_as 神秘男孩 89")
print(lst)
lst = re.findall("\D","sadfsdfsa 98&*^&^&92sdf3sdf839 sdf_as 神秘卫星 89")
print(lst)
"""
\w 字母,数字,下划线,包含中文(正则函数当中支持中文的匹配)
\W 匹配非字母或数字或下划线
"""
lst = re.findall("\w","09090sdf909sdf_+()()&*&*%^%^你好sd")
print(lst)
lst = re.findall("\W","09090sdf909sdf_+()()&*&*%^%^你好sd")
print(lst)
"""
\s 匹配任意空白符
\S 匹配任意非空白符
"""
strvar = """
"""
lst = re.findall("\s"," ")
print(lst)
lst = re.findall("\s",strvar)
print(lst)
lst = re.findall("\S"," lklkl sdfsdf sdfsdf")
print(lst)
"""
\n 匹配换行
\t 匹配一个制表符
"""
strvar = """
今天 拉 肚 子
"""
lst = re.findall(r"\n",strvar)
print(lst)
lst = re.findall(r"\t",strvar)
print(lst)
# ###字符组练习 必须从字符组选一个,如果一个都没有则匹配不成功
lst = re.findall("[123]","s3dafsf2s1")
print(lst)
print(re.findall('a[abc]b','aab abb acb adb'))
print(re.findall('a[0123456789]b','a1b a2b a3b acb ayb a9090909009b'))
# 优化版:0123456789 => 0-9 等价
print(re.findall('a[0-9]b','a1b a2b a3b acb ayb a9090909009b'))
print(re.findall('a[abcdefg]b','a1b a2b a3b acb ayb adb aabababbababb')) #['acb', 'adb']
# 优化版:a b c d .... z => a-z
print(re.findall('a[a-g]b','a1b a2b a3b acb ayb adb aabababbababb'))
print(re.findall('a[a-z]b','a1b a2b a3b acb ayb adb aabababbababb'))
print(re.findall('a[ABCDEFG]b','a1b a2b a3b aAb aDb aYb'))
# 优化版: A B C ... Z => A-Z
print(re.findall('a[A-G]b','a1b a2b a3b aAb aDb aYb'))
print(re.findall('a[A-Z]b','a1b a2b a3b aAb aDb aYb'))
print(re.findall('a[0-9a-zA-Z]b','a-b aab aAb aWb aqba1b'))
# 优化版: a-zA-Z => A-z 可以匹配所有大小写,但是有缺陷,一些特殊符号也匹配到了
print(re.findall('[A-z]','('))
print(re.findall('[0-z]','9')) # 语法上允许,但是别这么用,没意义
print(re.findall('a[0-9][*#/]b','a1/b a2b a29b a56b a456bab'))
# ^ 字符组中的^ 代表除了的意思
print(re.findall('a[^-+*/]b',"a%b ccaa*bda&bd"))
# 单独匹配一个特殊字符,用\让他的意思失效 转义字符
print(re.findall('a[\^]b',"a^b"))
来源：https://www.cnblogs.com/huangjiangyong/p/10924350.html