正则表达式

 

/*
一: 基本操作
二: 匹配: 字符
三: 匹配: 数量
四: 开头结尾
五: 匹配分组
*/

 

一: 基本操作

import re
if __name__ == '__main__':
    # 匹配操作: match()
    result = re.match(正则表达式, 要匹配的字符串)
    # 提取数据: group()
    result.group()
    
 
import re
if __name__ == '__main__':
    result = re.match("cnblogs.","cnblogs.com")
    info = result.group()   # cnblogs.
    print(info)

 

二: 匹配: 字符

 

import re

# . : 任意1个字符
if __name__ == '__main__':
    ret = re.match(".", "M")
    print(ret.group())  # M

    ret = re.match("t.o", "too")
    print(ret.group())  # too

    ret = re.match("t.o", "two")
    print(ret.group())  # two
    
    
# [] : 多中取1 
if __name__ == '__main__':
    # 匹配字母
    result = re.match("h","hello")
    print(result.group())   # h 

    result = re.match("H","Hello")
    print(result.group())   # H
    
    result = re.match("[Hh]","hello")
    print(result.group())   # h
    
    # 匹配数字
    result = re.match("[0123456789]","6hello")
    print(result.group())   # 6
        
    result = re.match("[0-9]","6hello")
    print(result.group())   # 6


# \d : 数字
if __name__ == '__main__':
    result = re.match("嫦娥\d号","嫦娥6号")
    print(result.group())   # 嫦娥6号


# \D : 非数字
if __name__ == '__main__':
    result = re.match("\D","嫦娥66号")
    print(result.group())   # 嫦
   
   
# \s : 空白 
if __name__ == '__main__':
    match_obj = re.match("hello\sworld", "hello world")
    if match_obj:
        result = match_obj.group()
        print(result)       # hello world
    else:
        print("匹配失败")   
        
        
# \S : 非空白   
if __name__ == '__main__':
    match_obj = re.match("hello\Sworld", "hello0world")
    result = match_obj.group()
    print(result)   # hello0world    
    
    
# \w : 非特殊字符
if __name__ == '__main__':
    match_obj = re.match("\w", "ab")
    result = match_obj.group()        
    print(result)   # a 
    
    
# \W : 特殊字符   
if __name__ == '__main__':
    match_obj = re.match("\W", "#")
    result = match_obj.group()
    print(result)   # #

 

三: 匹配: 数量

import re

# * : 匹配前一个字符出现0次或者无限次
if __name__ == '__main__':
    ret = re.match("[A-Z][a-z]*", "M")
    print(ret.group())  # M
   
if __name__ == '__main__':
    ret = re.match("[A-Z][a-z]*", "MmmM")
    print(ret.group())  # Mmm
    
if __name__ == '__main__':
    ret = re.match("[A-Z][a-z]*", "MmmMnn")
    print(ret.group())  # Mmm
    
# + : 匹配前一个字符出现1次或者无限次
if __name__ == '__main__':
    match_obj = re.match("t.+o", "two")
    print(match_obj.group())    # two
    
    
# ? : 匹配前一个字符出现1次或者0次
if __name__ == '__main__':
    match_obj = re.match("https?", "http")
    print(match_obj.group())    # http
    
    
# {m} : 匹配前一个字符出现m次
# {m, n} : 匹配前一个字符出现从m到n次
if __name__ == '__main__':
    ret = re.match("[a-zA-Z0-9]{6}", "12a3g45678")
    print(ret.group())  # 12a3g4

if __name__ == '__main__':
    ret = re.match("[a-zA-Z0-9]{10,12}", "1ad12f23s34455ff66")
    print(ret.group())  # 1ad12f23s344

 

四: 开头结尾

 

# ^ : 匹配字符串开头
# $ : 匹配字符串结尾
if __name__ == '__main__':
    ret = re.match("^\d.*", "3hello")
    print(ret.group())  # 3hello

if __name__ == '__main__':
    ret = re.match(".*\d$", "3hello6")
    print(ret.group())  # 3hello6
    

    # 匹配以数字开头中间内容不管以数字结尾
if __name__ == '__main__':
    ret = re.match("^\d.*\d$", "6hello6")
    print(ret.group())  # 6hello6
    
    # [^指定字符]: 表示除了指定字符都匹配
if __name__ == '__main__':
    ret = re.match("[^abcef]", "dello6")
    print(ret.group())  # d

 

五: 匹配分组

 

# | : 匹配左右任意一个表达式
if __name__ == '__main__':
    fruit_list = ["apple", "banana", "orange", "pear"]

    for value in fruit_list:
        match_obj = re.match("apple|pear", value)
        if match_obj:
            print("%s 是我想要的" %match_obj.group())
        else:
            print("%s 不是我想要的" %value)
      
    
# (ab) : 括号中字符作为一个分组
if __name__ == '__main__':
    # 需求: 匹配qq:10567这样的数据，提取出来qq文字和qq号码 
    match_obj = re.match("(qq):([1-9]\d{4,10})", "qq:10567")

    if match_obj:
        print(match_obj.group())    # qq:10567
        print(match_obj.group(1))   # qq
        print(match_obj.group(2))   # 10567
    else:
        print("匹配失败")  
    
    
# \num : 引用分组num匹配到的字符串  

    match_obj = re.match("<[a-zA-Z1-6]+>.*</[a-zA-Z1-6]+>", "<html>hh123</div>")
    print(match_obj.group())    # <html>hh123</div>

    match_obj = re.match("<([a-zA-Z1-6]+)>.*</\\1>", "<html>h789h</html>")
    print(match_obj.group())    # <html>h789h</html> 

    match_obj = re.match("<([a-zA-Z1-6]+)><([a-zA-Z1-6]+)>.*</\\2></\\1>", "<html><h1>www.cnblogs.cn</h1></html>")
    print(match_obj.group())    # <html><h1>www.cnblogs.cn</h1></html>
    
    
# (?P<name>) (?P=name) : 分组起别名 引用别名  
    match_obj = re.match("<(?P<name1>[a-zA-Z1-6]+)><(?P<name2>[a-zA-Z1-6]+)>.*</(?P=name2)></(?P=name1)>", "<html><h1>www.cnblogs.cn</h1></html>")
    print(match_obj)    # <re.Match object; span=(0, 36), match='<html><h1>www.cnblogs.cn</h1></html>'>