正则表达式模块re

import re
s = 'erqwejklfkj13i903i9ioj1423847283jr'  # 待匹配字符串 
p = re.compile('e.{0,6}')  # 创建正则对象
m = p.search(s)  # 使用正则匹配待匹配字符串 获得匹配结果

a = re.search('6e\w','sfa6ef234')
print(f"匹配结果的内容为{a.group(0)},匹配结果的位置区间为{a.span()},起点位置为{a.start()},终点位置为{a.end()}")

# macth()
re.match('6e\w','6ef234')

# search（）
re.search('6e\w','sfa6ef234')

# findall
import random
import string
r_list = string.ascii_letters + string.digits
s = ''.join([random.choice(r_list) for x in range(10000)])
p = re.compile('6e\w')
res = p.findall(s)
for a in res:
    print(f"匹配结果的内容为{a}")

# finditer
import random
import string
r_list = string.ascii_letters + string.digits
s = ''.join([random.choice(r_list) for x in range(10000)])
p = re.compile('6e\w')
res = p.finditer(s)
for a in res:
    print(f"匹配结果的内容为{a.group(0)},匹配结果的位置区间为{a.span()},起点位置为{a.start()},终点位置为{a.end()}")

# 字符串替换字符串
re.sub(r'def\s+([a-zA-Z_][a-zA-Z_0-9]*)\s*\(\s*\):',
       r'static PyObject*\npy_\1(void)\n{',
       'def myfunc():   123sdad')

# 函数替换字符串
def f(x):
    print("输入参数内容为",x.group(0))
    print("输入参数分组1为",x.group(1))
    return '替换'

re.subn(r'def\s+([a-zA-Z_][a-zA-Z_0-9]*)\s*\(\s*\):',
       f,
       'def myfunc():  def myfunc():def myfunc():  def myfunc():   123sdad')

# 限制替换次数
re.sub(r'def\s+([a-zA-Z_][a-zA-Z_0-9]*)\s*\(\s*\):',
       f,
       'def myfunc():  def myfunc():def myfunc():  def myfunc():   123sdad',count=2)

# 普通拆分
s = 'Words, words, words.'
re.split(r'\W+', s)

# 分组拆分
s = 'Words, words, words.'
re.split(r'(\W+)', s)

# 限制拆分
s = 'Words, words, words.'
re.split(r'(\W+)', s,1)

# 如果分隔符里有捕获组合，并且匹配到字符串的开始，那么结果将会以一个空字符串开始。对于结尾也是一样
re.split(r'(\W+)', '...words, words...')

# 样式的空匹配仅在与前一个空匹配不相邻时才会拆分字符串
re.split(r'\b', 'Words, words, words.')

# 开头
a = re.search('^6','6h432h4io23h4io2')
print(a.group())

# 结尾
a = re.search('2$','6h432h4io23h4io2')
print(a.group())

import random
import string
r_list = string.ascii_letters + string.digits
s = ''.join([random.choice(r_list) for x in range(10000)])

# 元素可有可无
p = re.compile('e\d*L')
res = p.findall(s)
res[:5]

# 元素至少出现一次
p = re.compile('e\d+L')
res = p.findall(s)
res[:5]

# 元素最多出现一次
p = re.compile('e\d?L')
res = p.findall(s)
res[:5]

# 元素出现n次
p = re.compile('e.{3}\d')
res = p.findall(s)
res[:5]

# 元素出现n-m次
p = re.compile('e.{1,6}\d')
res = p.findall(s)
res[:5]

# 元素出现n-m次失败案例
p = re.compile('e.{1,6}')
res = p.findall(s)
res[:10]

# 任意字符（除\n）
a = re.findall('.','\t\n\w12dfs!@%$')
print(a)

# 特定字符
a = re.findall('[1]','\t\n\w12dfs!@%$')
print(a)
a = re.findall('[1-9]','\t\n\w12dfs!@%$')
print(a)
a = re.findall('[a-z1!]','\t\n\w12dfs!@%$')
print(a)

# 多种匹配成功条件
a = re.findall('[a-z]|[0-9]','\t\n\w12dfs!@%$')
print(a)

# 数字
s = '\t\n\w12dfs!@%$'
a = re.findall('[0-9]',s)
c = re.findall('\d',s)
b = re.findall('[^0-9]',s)
d = re.findall('\D',s)
print(a,c,b,d)

# 空白字符
s = ' \t\n\f 12dfs!@%$'
a = re.findall('[ \t\n\r\f\v]',s)
c = re.findall('\s',s)
b = re.findall('[^ \t\n\r\f\v]',s)
d = re.findall('\S',s)
print(a,c,b,d)

# 数字、字母、下划线字符
s = ' \t\nDS\f -__12dfs!@%$'
a = re.findall('[a-zA-Z0-9_]',s)
c = re.findall('\w',s)
b = re.findall('[^a-zA-Z0-9_]',s)
d = re.findall('\W',s)
print(a,c,b,d)

# 位置约束-\A\Z
s = ' \t\nDS\f -__12dfs!@%$'
a = re.findall('\A[ \S]',s)
c = re.findall('^[ \S]',s)
b = re.findall('[\S]\Z',s)
d = re.findall('[\S]$',s)
print(a,c,b,d)

# 位置约束-\b \B  通常用于\w限定边界
s = ' \t\nDS\f -__12dfs!@%$'
a = re.findall('[\b\w\b]',s)
c = re.findall(' ',s)
b = re.findall('[\S]\B',s)
d = re.findall('[\S]',s)
print(a,c,b,d)

# \1 引用组 组编号可以根据实际改动
s = '7fajoi2j31227'
p = re.compile(r'^.*(.).*\1')
print(p.findall(s))

#  忽略大小写
a = re.findall('a','AadfdfAjDaskhdsj',flags=re.I)
for x in a:
    print(x)

# 多行匹配
s = """This line is the first,
another line,
that line, it's the best"""
a = re.findall('^[tT]h[\w\s]*',s,flags=re.M)
for x in a:
    print(x)

# 匹配任意字符
s = """T
, 
t"""

a = re.findall('.',s,flags=re.S)
for x in a:
    print(f"匹配结果为：{x}")
    
# 匹配Unicode 
a = re.findall('\S','结果dfAj123!@$$',flags=re.U)
for x in a:
    print(f"匹配结果为：{x}")
    
# 匹配ASCII
a = re.findall('\w','结果dfAj123!@$$',flags=re.A)
for x in a:
    print(f"匹配结果为：{x}")

# 分组命名
p = re.compile('(?P<a>e.{1,6}d).{1,10}(?P<b>[\w]{1,3})')
print(p.search(s).group('a'),p.search(s).groupdict())

# 命名引用
s = ''.join([random.choice(r_list) for x in range(10000)])
p = re.compile('(?P<a>[\'"]).{1,10}(?P=a)')
print(p.search(s).group(),p.search(s).groupdict())

# 添加匹配标志
result = re.findall(r'(?im)(^th[\w\s]+) (l[\w]*)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 匹配但不捕获-?:
result = re.findall(r'(?im)(^th[\w\s]+)(?:l[\w]*)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 匹配但不捕获（从后方）-?=
result = re.findall(r'(?im)(^th[\w\s]+)(?=l[\w]*)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 匹配但不捕获（从前方）-?<=
result = re.findall(r'(?im)(?<=[ ,])(i[\w\s]+)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 不匹配但不捕获（从后方）-?!
result = re.findall(r'(?im)(^th[\w\s]+)(?![h-z,])', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 不匹配但不捕获（从前方）-?<!
result = re.findall(r'(?im)(?<![ ,])(i[\w\s]+)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)

# 注释
result = re.findall(r'(?im)(^th[\w\s]+) (?#注释)', '''
This Line Is The First,
another line,
that line, it's the best
''')
print(result)