python正则表达式的分组

(...)分组

import re

# (...)分组
string_01 = 'apple567WRAP899WRAP223funny2356'
pattern_01 = '([A-Z]{4})[0-9]+'
res_01 = re.search(pattern_01, string_01)
print(res_01, res_01.group(), res_01.group(1))

# 打印结果: <re.Match object; span=(8, 15), match='WRAP899'> WRAP899 WRAP

(?P<name>)给分组起别名

import re

# (?P<name>)给分组起别名
string_02 = 'apple567WRAP899WRAP223funny2356'
pattern_02 = '(?P<name_01>[A-Z]{4})(?P<name_02>[0-9]+).'
res_02 = re.search(pattern_02, string_02)
print(res_02, res_02.groupdict())
print(res_02.group(), res_02.group(1), res_02.group(2))  # 按分组索引获取
print(res_02.group('name_01'), res_02.group('name_02'))  # 按分组别名获取

# 打印结果:
# <re.Match object; span=(8, 16), match='WRAP899W'> {'name_01': 'WRAP', 'name_02': '899'}
# WRAP899W WRAP 899
# WRAP 899

(?P=name)引用分组

import re

# (?P=name)引用分组
# 引用分组匹配到的内容需要和被引用分组匹配到的内容一模一样
string_03 = 'apple567WRAP899WRAP223funny2356'
pattern_03 = '(?P<name_01>[A-Z]{4}).*(?P=name_01)'
res_03 = re.search(pattern_03, string_03)
print(res_03, res_03.groupdict())
print(res_03.group(), res_03.group(1))  # 引用分组无法被捕获,res_03.group(2)会报IndexError: no such group错
print(res_03.group('name_01'))

# 打印结果:
# <re.Match object; span=(8, 19), match='WRAP899WRAP'> {'name_01': 'WRAP'}
# WRAP899WRAP WRAP
# WRAP

(?#...) 正则中写注释括号里的内容会被忽略掉

import re

string_04 = 'apple567WRAP899WRAP223funny2356'
pattern_04 = '(?#这是注释)([A-Z]{4})[0-9]+'
res_04 = re.search(pattern_04, string_04)
print(res_04, res_04.group(), res_04.group(1))  # 注释分组无法被捕获

# 打印结果: <re.Match object; span=(8, 15), match='WRAP899'> WRAP899 WRAP

(?:...) 表示这个分组不会被捕获: 所以下面例子group(1)捕获到的是第二个分组

import re

string_05 = 'apple567WRAP899WRAP223funny2356'
pattern_05 = '(?:[A-Z]{4})([0-9]+)'
res_05 = re.search(pattern_05, string_05)
print(res_05, res_05.group(1))

# 打印结果: <re.Match object; span=(8, 15), match='WRAP899'> 899

（?=...) 后向界定 括号内的内容不会被匹配

import re

# 括号中的 ... 代表你希望匹配的字符串后面应该出现的字符串
string_06 = 'apple567WRAP899WRAP223funny2356'
pattern_06 = '[A-Z]{4}d{2}(?=3)'
res_06 = re.search(pattern_06, string_06)
print(res_06)

# 打印结果: <re.Match object; span=(15, 21), match='WRAP22'>

（?!...) 后向非界定 和上面的后向界定相反,就相当于 not

import re

string_07 = 'apple567WRAP899WRAP223funny2356'
pattern_07 = '[A-Z]{4}d{2}(?!9)'
res_07 = re.search(pattern_07, string_07)
print(res_07)

# 打印结果: <re.Match object; span=(15, 21), match='WRAP22'>

(?<=...)  前向界定 括号内的内容不会被匹配

import re

# 括号中 ...  代表你希望匹配的字符串的前面应该出现的字符串
string_08 = 'apple567WRAP899WRAP223funny2356'
pattern_08 = '(?<=99)[A-Z]{4}d'
res_08 = re.search(pattern_08, string_08)
print(res_08)

# 打印结果: <re.Match object; span=(15, 20), match='WRAP2'>

(?<!...) 前向非界定 与上面前向界定相反

import re

# 当希望的字符串前面不是 ... 的内容时才匹配
string_09 = 'apple567WRAP899WRAP223funny2356'
pattern_09 = '(?<!567)[A-Z]{4}d'
res_09 = re.search(pattern_09, string_09)
print(res_09)

# 打印结果: <re.Match object; span=(15, 20), match='WRAP2'>