python 正则表达式

# -*- coding: utf-8 -*-
import re
line = "boooooooooooooobbbaaaaby123"
# ^ 以这个开始
# regex_str = "^b" 以b开始
# . 任何字符
# * 多次
regex_str = "^b.*"
# 正则匹配
if re.match(regex_str, line):
    print(‘yes‘)
# $ 结尾字符
regex_str = "^b.*3$"
if re.match(regex_str, line):
    print(‘yes‘)
# ? 非贪婪匹配
regex_str = ".*?(b.*?b).*"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# + 至少出现一次
regex_str = ".*(b.+b).*"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# {2}限定指定出现的次数 {2,}出现的次数2次以上 {2,5} 最少2次,最多5次
regex_str = ".*(b.{5,}b).*"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# | 或
line = "test123"
regex_str = "((test|test456)123)"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(2))
# [] 括号内的任意一个 [0-9] [a-z] [^1] 不等与1
line = "13822345789"
regex_str = "(1[3456789][^1]{9})"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# \s 空格 \S 不是空格都可以 \w 任意字符 \W 空格
line = "你 好"
regex_str = "(你\W好)"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# 提取汉字
line = "hello 你好世界"
regex_str = ".*?([\u4E00-\u9F45]+世界)"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# \d 数字
line = "hello 2019年"
regex_str = ".*?(\d+)年"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))
# 实例
line = "张三出生于2018年1月5日"
line = "张三出生于2018/1/5"
line = "张三出生于2018-1-5"
line = "张三出生于2018-01-05"
line = "张三出生于2018-01"
regex_str = ".*?出生于(\d{4}[年/-]\d{1,2}([月/-]\d{1,2}|[月/-]$|$))"
match_obj = re.match(regex_str, line)
if match_obj:
    print(match_obj.group(1))