黑马程序员---正则表达式---记忆

深藏阁楼爱情的钟 2022-11-29 00:57 181阅读 0赞

一：re模块：正则表达式进行字符串匹配的时候需要调用的包。  
1:导包：import re  
2:检测：result = re.match(正则表达式，需要匹配的字符串),成功返回成功的部分字符串，不成功返回null。  
3：取出匹配的内容：result.group()

import re
    
    if __name__ == '__main__':
        result = re.match("0\d{3}-\d{8}","0755-81234567")
        if result:
            print("匹配成功")
            print(result.group())
    
        else :
            print("匹配失败")

4：match和search的区别：match会从头开始匹配，如果有不一样的，就失败。search 里面有就可以匹配成功。search与findall的区别：search只能匹配到第一个，findall可以匹配到所有字符串。并且findall获取到的直接用print打印就可以。不需要使用group获取。

import re
    
    result = re.search("itcast","www.itcast.cn")
    
    if result :
        print("匹配成功",result.group())
    else:
        print("匹配失败")
    
    
    result = re.match("itcast","www.itcast.cn")
    
    if result :
        print("匹配成功",result.group())
    else:
        print("匹配失败")

二：匹配单个字符：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center]  
1：点

import  re
    
    # 匹配任意一个除了换行的字符
    ret = re.match(".","M")
    print(ret.group())
    
    try:
        ret = re.match(".","\n")
        print(ret.group())
    except Exception as e:
        print("匹配失败，不允许是换行")
    
    ret = re.match("t.o","too")
    print(ret.group())

运行结果：

M
    匹配失败，不允许是换行
    too

2：方框：

import re
    
    # 1:匹配开头大小H写都可以
    ret = re.match("[hH]","hello python")
    print(ret.group())
    ret = re.match("[hH]","Hello python")
    print(ret.group())
    ret = re.match("[hH]ello python","Hello python")
    print(ret.group())
    # 运行结果：
    # h
    # H
    # Hello python
    
    # 2：匹配0-9的任何一个
    ret = re.match("[0-9]hello","1hello")
    print(ret.group())
    ret = re.match("[0-9]hello","2hello")
    print(ret.group())
    ret = re.match("[0-9]hello","9hello")
    print(ret.group())
    # 运行结果：
    # 1hello
    # 2hello
    # 9hello
    
    
    
    #3:匹配0-3  5-9中的任何一个
    
    ret = re.match("[0-35-9]hello","1hello")
    print(ret.group())
    
    try:
        ret = re.match("[0-35-9]hello", "4hello")
        print(ret.group())
    except Exception as e:
        print("匹配失败")
    
    # 运行结果：
    # 1hello
    # 匹配失败

3：\\d 与\\D:

import  re
    
    # /d  可以匹配任意一个数字：
    ret = re.match("python\d","python1")
    print(ret.group())
    ret = re.match("python\d","python9")
    print(ret.group())
    
    # /D ：匹配任意一个非数字
    ret = re.match("python\D","python_")
    print(ret.group())
    ret = re.match("python\D","python\n")
    print(ret.group())
    ret = re.match("python\D","python&")
    print(ret.group())
    ret = re.match("python\D","python.")
    print(ret.group())
    
    # 运行结果：
    # python1
    # python9
    # python_
    # python
    # 
    # python&
    # python.

4:\\s与\\S:

import re
    
    # 1：匹配空字符
    res = re.match("hello\sworld","hello world")
    print(res.group())
    res = re.match("hello\sworld","hello\nworld")
    print(res.group())
    res = re.match("hello\sworld","hello\tworld")
    print(res.group())
    
    # 运行结果：
    # hello world
    # hello
    # world
    # hello	world
    
    
    # 2：匹配非空字符
    res = re.match("hello\S","hello*")
    print(res.group())
    res = re.match("hello\S","hello-")
    print(res.group())
    try:
        res = re.match("hello\S", "hello ")
        print(res.group())
    except:
        print("匹配失败")
        
    # 运行结果：
    # hello*
    # hello-
    # 匹配失败

5:\\w 和\\W

import re
    
    #/w匹配非特殊字符，即a-z、A-Z、0-9、_、汉字
    res = re.match("hello\w","helloa")
    print(res.group())
    res = re.match("hello\w","helloA")
    print(res.group())
    res = re.match("hello\w","hello0")
    print(res.group())
    res = re.match("hello\w","hello_")
    print(res.group())
    res = re.match("hello\w","hello任")
    print(res.group())
    try:
        res = re.match("hello\w", "hello$")
        print(res.group())
    except Exception as e:
        print("匹配失败")
    
    # 运行结果：
    # helloa
    # helloA
    # hello0
    # hello_
    # hello任
    # 匹配失败
    
    # 2:匹配特殊字符：
    res = re.match("hello\W","hello#")
    print(res.group())
    res = re.match("hello\W","hello*")
    print(res.group())
    res = re.match("hello\W","hello ")
    print(res.group())
    res = re.match("hello\W","hello%")
    print(res.group())
    res = re.match("hello\W","hello/")
    print(res.group())
    
    # 运行结果：
    # hello#
    # hello*
    # hello 
    # hello%
    # hello/

三：匹配多个字符：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center 1]

import  re
    
    res = re.match("python*","pytho")
    print(res.group())
    res = re.match("python*","pythonn")
    print(res.group())
    res = re.match("python*","pythonnnnnnnnn")
    print(res.group())
    # 运行结果：
    # pytho
    # pythonn
    # pythonnnnnnnnn
    
    try:
        res = re.match("python+","pytho")
        print(res.group())
    except:
        print("匹配失败")
    
    res = re.match("python+","python")
    print(res.group())
    res = re.match("python+","pythonn")
    print(res.group())
    res = re.match("python+","pythonnnnnn")
    print(res.group())
    
    # 运行结果：
    # 匹配失败
    # python
    # pythonn
    # pythonnnnnn
    print("--------------------------")
    res = re.match("python?","pytho")
    print(res.group())
    res = re.match("python?","python")
    print(res.group())
    try:
        res = re.match("python?","pythonn")
        print(res.group())
    except:
        print("匹配失败，只能匹配一个或没有")
    
    # pytho
    # python
    # python
    # 注意：最后这个不报错，因为匹配完成了，不再向下验证
    
    print("-----------------------------------")
    
    res = re.match("python{2}","pythonn")
    print(res.group())
    try:
        res = re.match("python{2}","python")
        print(res.group())
    except Exception as e:
        print("少一个也不行")
    
    res = re.match("python{2}","pythonnn")
    print(res.group())
    # 注意：多一个可以，后面的仍然不匹配。
    # 运行结果：
    # pythonn
    # 少一个也不行
    # pythonn
    
    print("------------------------------------")
    
    res = re.match("python{2,4}","pythonn")
    print(res.group())
    res = re.match("python{2,4}","pythonnn")
    print(res.group())
    res = re.match("python{2,4}","pythonnnn")
    print(res.group())
    res = re.match("python{2,4}","pythonnnnn")
    print(res.group())
    
    # 注意多一个没事，但匹配结果仍然显示前面的
    try:
        res = re.match("python{2,4}","python")
        print(res.group())
    except Exception as e:
        print("少一个也不行")
        
    # 运行结果：
    # pythonn
    # pythonnn
    # pythonnnn
    # pythonnnn
    # 少一个也不行

四：匹配开头和结尾：  
![在这里插入图片描述][20200818211719757.png_pic_center]

import re
    
    # 一：匹配以数字开头
    # ^ 以后面的开头
    # \d  匹配0-9的数字
    # . 任意一个除换行字符
    # * 前面的有任意多个
    
    mach_obj = re.match("^\d.*","4acajks")
    print(mach_obj.group())
    
    
    try:
        mach_obj = re.match("^\d.*","hello")
        print(mach_obj.group())
    except Exception as e:
        print("匹配失败")
    
    # 4acajks
    # 匹配失败
    
    
    # 匹配以数字结尾：
    mach_obj = re.match(".*\d$","hello333")
    print(mach_obj.group())
    try:
        mach_obj = re.match(".*\d$","helloaaa")
        print(mach_obj.group())
    except Exception as e:
        print("匹配失败")
    
    # hello333
    # 匹配失败
    
    
    # 匹配以数字开头中间内容不管以数字结尾
    mach_obj = re.match("^\d.*\d$","111hello333")
    print(mach_obj.group())
    try:
        mach_obj = re.match("^\d.*\d$", "hello333")
        print(mach_obj.group())
    except Exception as e:
        print("匹配失败")
    
    try:
        mach_obj = re.match("^\d.*\d$", "hello")
        print(mach_obj.group())
    except Exception as e:
        print("匹配失败")
    
    # 111hello333
    # 匹配失败
    # 匹配失败
    
    # 第一个字符除了aeiou的字符都匹配
    
    mach_obj = re.match("[^aeiou]", "hello333")
    print(mach_obj.group())
    
    #  注意这里只会匹配显示h，后面的不会管
    try:
        mach_obj = re.match("[^aeiou]", "aello333")
        print(mach_obj.group())
    except Exception as e:
        print("匹配失败")
        
    # 运行结果：
    # h
    # 匹配失败

五：匹配分组：  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center 2]

import re
    
    # 1：在列表中["apple", "banana", "orange", "pear"]，匹配apple和pear
    
    my_list = ["apple", "banana", "orange", "pear"]
    
    for i in my_list:
        res = re.match("apple|pear",i)
        if res:
            print("匹配成功")
        else:
            print("匹配失败")
    
    # 运行结果：
    # 匹配成功
    # 匹配失败
    # 匹配失败
    # 匹配成功
    print("--------------------------")
    
    
    
    # 2： 匹配出163、126、qq等邮箱
    # 以字母数字下划线组成的4到20位，中间是@ 后面163或者126或者...
    result = re.match("[a-zA-Z0-9_]{4,20}@(163|126|qq|sina|yahoo).com","hello@163.com")
    print(result.group())
    
    # 提取分组的内容：
    # 提取分组一的内容
    print("分组1的内容：" + result.group(1))
    
    # hello@163.com
    # 分组1的内容：163
    
    
    #3：匹配qq:10567这样的数据，提取出来qq文字和qq号码
    #前面一个分组是qq，后面是1-9之间任意一个字符，任意一个0-9数字，任意0-9数字有4位到10位
    match_obj = re.match("(qq):([1-9]\d{4,10})", "qq:10567")
    print(match_obj.group())
    print(match_obj.group(1))
    print(match_obj.group(2))
    
    # 运行结果：
    # qq:10567
    # qq
    # 10567
    
    
    # 4：引用分组匹配的内容：
    # 匹配出<html>hh</html>
    
    match_obj = re.match("<[a-zA-Z1-6]+>.*<[/a-zA-Z1-6]+>","<html>hh</div>")
    if match_obj:
        print(match_obj.group())
    else:
        print("匹配失败。。。。")
    # <html>hh</div>
    # 但是这个如果匹配<html></p>这不是一对标签也能匹配成功。怎么能让两边一样才能匹配呢？
    # 需要将左边的分组，然后右边取出左边的分组内容,1就是第一个分组
    match_obj = re.match("<([a-zA-Z1-6]+)>.*</\\1>","<html></html>")
    if match_obj:
        print(match_obj.group())
    else:
        print("匹配失败。。。。")
    
    
    # 5：匹配:<html><h1>www.itcast.cn</h1></html>
    # 注意：后面的括号数字要反着写
    match_obj = re.match("<([a-zA-Z1-6]+)><([a-zA-Z1-6]+)>.*</\\2></\\1>","<html><h1>www.itcast.cn</h1></html>")
    if match_obj:
        print(match_obj.group())
    else:
        print("匹配失败。。。。")
    
    # 运行结果
    # <html><h1>www.itcast.cn</h1></html>
    
    
    # 6：分组取别名，用别名引用。
    match_obj = re.match("<(?P<name1>[a-zA-Z1-6]+)><(?P<name2>[a-zA-Z1-6]+)>.*</(?P=name2)></(?P=name1)>","<html><h1>www.itcast.cn</h1></html>")
    if match_obj:
        print(match_obj.group())
    else:
        print("匹配失败。。。。")
    
    # <html><h1>www.itcast.cn</h1></html>

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center]: /images/20221124/9122d585f2c2435c8b308ce98e7e49b2.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221124/9ac796ec13b342f2b5ff80cf4ad6feda.png
[20200818211719757.png_pic_center]: /images/20221124/5006d8a331674b12a30188323517ad1e.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzQxNzU3_size_16_color_FFFFFF_t_70_pic_center 2]: /images/20221124/633d9e72f2b44d9f8799648051c2dd6b.png