正则表达式使用

import re

#  匹配- match从头匹配 (第一个参数就是正则表达式， 数据) 如果开始不能匹配就匹配失败
# 正则表达式都是以r字符开始的 -- 墙裂建议
# 返回值就是匹配结果的对象 如果需要获取对象中的结果就需要.group()
res = re.match(r'ello','ello meizi hello')

# 如果成功匹配 则返回对象 如果没有匹配结果则返回值为空
if res:
    print(res.group())
else:
    print("没有匹配结果")

# 搜索 查找 --- 如果开始不能匹配 则继续往后搜索 尝试看能否匹配
res = re.search(r'hello','ello meizi hello')

# 如果成功匹配 则返回对象 如果没有匹配结果则返回值为空
if res:
    print(res.group())
else:
    print("没有匹配结果")
    """match函数和search函数的功能 区别和联系"""

In [1]: import re
In [2]: re.match(r"hello","hello").group()
# ----------1. .匹配一个任意字符(除去
)-----------------------------------------
In [3]: re.match(r".ello","hello").group()
In [4]: re.match(r".ello","Hello").group()
In [5]: re.match(r".ello","1ello").group()
In [6]: re.match(r".ello","&ello").group()
In [7]: re.match(r".ello","
ello").group()  # 出错
In [14]: re.match(r".ello",".ello").group()
In [15]: re.match(r".ello",".ello").group()

------------2. []匹配集合中任意一个字符----------------------------------------
In [8]: re.match(r"[Hh]ello","Hello").group()
In [9]: re.match(r"[Hh]ello","hello").group()
In [10]: re.match(r"[Hh]ello","1ello").group() # 出错

In [11]: re.match(r"[0123456789]ello","1ello").group()
In [12]: re.match(r"[0123456789]ello","9ello").group()
In [13]: re.match(r"[0123456789]ello","Hello").group()  # 出错

In [16]: re.match(r"[0123456789]ello","Hello").group()  # 出错
In [17]: re.match(r"[0123456789]ello","1ello").group()

------------3. [-]匹配范围内部的任意一个字符-----------------
In [18]: re.match(r"[0-9]ello","1ello").group()
In [19]: re.match(r"[0-35-9]ello","1ello").group()
In [20]: re.match(r"[0-35-9]ello","9ello").group()
In [21]: re.match(r"[0-35-9]ello","4ello").group()  #  出错
In [22]: re.match(r"[0-9a-zA-Z]ello","4ello").group()
In [23]: re.match(r"[0-9a-zA-Z]ello","aello").group()
In [24]: re.match(r"[0-9a-zA-Z]ello","Hello").group()
In [25]: re.match(r"[0-35-9]ello","9ello").group()
In [26]: re.match(r"[0-35-9]ello","4ello").group()  # 出错

------------4. [^] 禁止匹配 范围内部的任意一个字符-----------------

In [27]: re.match(r"[^4]ello","4ello").group()
In [28]: re.match(r"[^4]ello","0ello").group()
In [29]: re.match(r"[^4]ello","9ello").group()

------------5. 'd'匹配一个任意数字字符  'D'匹配任意个非数字字符 -----------------

In [30]: re.match(r"dello","9ello").group()
In [31]: re.match(r"dello","0ello").group()
In [32]: re.match(r"dello","@ello").group()

In [33]: re.match(r"Dello","0ello").group()
In [34]: re.match(r"Dello","@ello").group()
In [35]: re.match(r"Dello","?ello").group()

------------6. 's'匹配一个任意空白字符  'S'匹配一个任意 非空白字符串-------------------------------
In [36]: re.match(r"Dello"," ello").group()

In [37]: re.match(r"[	
vf ]ello"," ello").group()
In [38]: re.match(r"sello"," ello").group()
In [39]: re.match(r"Sello"," ello").group()
In [40]: re.match(r"Sello","1ello").group()

-----------7. 'w'匹配一个任意单词字符 'W'匹配一个任务 非单词字符-----------------------------
In [41]: re.match(r"wello","1ello").group()
In [42]: re.match(r"wello","hello").group()
In [43]: re.match(r"wello","Hello").group()
In [44]: re.match(r"wello","_ello").group()
In [45]: re.match(r"Wello","_ello").group()
In [46]: re.match(r"Wello","?ello").group()

------------'w'语义拓展
In [2]: re.match(r"wBC","ABC")
In [3]: re.match(r"wBC","ABC").group()
In [4]: re.match(r"wBC","呵BC").group()
In [5]: re.match(r"wBC","呵BC",re.ASCII).group()
In [6]: re.match(r"wBC","呵BC",re.UNICODE).group()
In [7]: re.match(r"wBC","呵BC").group()


-----------二 量词  匹配多个字符---------------------------
In [47]: re.match(r"嫦娥号d升空了","嫦娥1号升空了").group()
In [48]: re.match(r"嫦娥d号升空了","嫦娥1号升空了").group()
In [49]: re.match(r"嫦娥d号升空了","嫦娥9号升空了").group()
In [50]: re.match(r"嫦娥d号升空了","嫦娥10号升空了").group()
In [51]: re.match(r"嫦娥dd号升空了","嫦娥10号升空了").group()
In [52]: re.match(r"嫦娥dd号升空了","嫦娥99号升空了").group()
In [53]: re.match(r"嫦娥dd号升空了","嫦娥100号升空了").group()
In [54]: re.match(r"嫦娥ddd号升空了","嫦娥100号升空了").group()
In [55]: re.match(r"嫦娥ddddd号升空了","嫦娥10000号升空了").group()

In [56]: re.match(r"嫦娥d{5}号升空了","嫦娥10000号升空了").group()
In [57]: re.match(r"嫦娥d{3}号升空了","嫦娥10000号升空了").group()
In [58]: re.match(r"嫦娥d{3}号升空了","嫦娥100号升空了").group()

In [59]: re.match(r"嫦娥d{1,3}号升空了","嫦娥100号升空了").group()
In [60]: re.match(r"嫦娥d{1,3}号升空了","嫦娥1号升空了").group()
In [61]: re.match(r"嫦娥d{1,3}号升空了","嫦娥10号升空了").group()
In [62]: re.match(r"嫦娥d{1,1}号升空了","嫦娥10号升空了").group()
In [64]: re.match(r"嫦娥d{0,3}号升空了","嫦娥号升空了").group()

In [65]: re.match(r"嫦娥d{0,}号升空了","嫦娥号升空了").group()
In [66]: re.match(r"嫦娥d*号升空了","嫦娥号升空了").group()

In [67]: re.match(r"嫦娥d{1,}号升空了","嫦娥1号升空了").group()
In [68]: re.match(r"嫦娥d{1,}号升空了","嫦娥号升空了").group()
In [69]: re.match(r"嫦娥d{1,}号升空了","嫦娥1000号升空了").group()
In [70]: re.match(r"嫦娥d+号升空了","嫦娥1000号升空了").group()

In [8]: re.match(r"w?BC","ABC").group()
In [9]: re.match(r"w?BC","BC").group()


---------------三 匹配开始^ 和结束位置$--------------------------

In [71]: re.match(r"w{4,20}@163.com","hello@163.com").group()
In [72]: re.match(r"w{4,20}@163.com","hello@163Acom").group()
In [73]: re.match(r"w{4,20}@163.com","hello@163Acom").group()
In [74]: re.match(r"w{4,20}@163.com","hello@163.com").group()
In [75]: re.match(r"w{4,20}@163.com","hello@163.com.cn").group()
In [76]: re.match(r"w{4,20}@163.com","cc.hello@163.com").group()
In [77]: re.search(r"w{4,20}@163.com","cc.hello@163.com").group()
In [78]: re.search(r"w{4,20}@163.com","cc.hello@163.com.cn").group()

In [79]: re.search(r"^w{4,20}@163.com","cc.hello@163.com.cn").group()
In [80]: re.search(r"^w{4,20}@163.com","hello@163.com.cn").group()

In [81]: re.search(r"^w{4,20}@163.com$","hello@163.com.cn").group()
In [82]: re.search(r"^w{4,20}@163.com$","hello@163.com").group()
In [83]: re.match(r"^w{4,20}@163.com","hello@163.com.cn").group()
In [84]: re.match(r"^w{4,20}@163.com$","hello@163.com.cn").group()
In [85]: re.match(r"^w{4,20}@163.com$","hello@163.com").group()


-------------四 匹配分组 ()将感兴趣的数据进行提取------
In [86]: re.match(r"嫦娥(d+)号升空了","嫦娥1000号升空了").group()
In [87]: re.match(r"嫦娥(d+)号升空了","嫦娥1000号升空了").group(0)
In [88]: re.match(r"嫦娥(d+)号升空了","嫦娥1000号升空了").group(1)
In [89]: re.match(r"^(w{4,20})@(163).com$","hello@163.com").group()
In [90]: re.match(r"^(w{4,20})@(163).com$","hello@163.com").group(1)
In [91]: re.match(r"^(w{4,20})@(163).com$","hello@163.com").group(2)

-------(|)匹配其中任何一个表达式并且放入分组中----

In [92]: re.match(r"^(w{4,20})@(163|qq).com$","hello@263.com").group(2)
In [93]: re.match(r"^(w{4,20})@(163|qq).com$","hello@qq.com").group(2)
In [94]: re.match(r"^(w*)hello(w*)$","hellohello@qq.com").group(1)


---------------------'分组编号' 使用某个分组的数据在后面某个位置继续匹配 ----

In [11]: re.match(r"^w{4,20}@163.com$|^w{4,20}@qq.com$","hello@163.com").group()
In [12]: re.match(r"^w{4,20}@163.com$|^w{4,20}@qq.com$","hello@qq.com").group()
In [13]: re.match(r"^w{4,20}@(163|qq).com$","hello@qq.com").group()
In [14]: re.match(r"^w{4,20}@(163|qq).com$","hello@163.com").group()

In [15]: re.match(r"(d{3,4})-(d{6,8})","0755-12345678").group()
In [16]: re.match(r"(d{3,4})-(d{6,8})","0755-12345678").group(1)
In [17]: re.match(r"(d{3,4})-(d{6,8})","0755-12345678").group(2)

In [18]: re.match(r"(d{3,4})-(d{6,8}) 1-2","0755-12345678 0755-1234567").group(2)
In [19]: re.match(r"(d{3,4})-(d{6,8}) 1-2","0755-12345678 0755-12345678").group()
In [20]: re.match(r"(d{3,4})-(d{6,8}) 1-2","0755-12345678 0755-1234567").group()
In [21]: re.match(r"<(w+)>","<html>aaa</html>").group(1)
In [22]: re.match(r"<(w+)>(.*)</1>","<html>aaa</html>").group(1)
In [23]: re.match(r"<(w+)>(.*)</1>","<html>aaa</html2>").group(1)

匹配多个标签中的数据 
<html><body>hello</body></html>
"""思考问题  如何创建有名分组  如何引用有名分组"""

In [24]: re.match(r"<(w+)><(w+)>(.+)</2></1>","<html><body>hello</body></html>").group()
In [25]: re.match(r"<(w+)><(w+)>(.+)</2></1>","<html><body>hello</body></html>").group(1)
In [26]: re.match(r"<(w+)><(w+)>(.+)</2></1>","<html><body>hello</body></html>").group(2)
In [27]: re.match(r"<(w+)><(w+)>(.+)</2></1>","<html><body>hello</body></html1>").group(2)
In [28]: re.match(r"<(w+)><(w+)>(.+)</2></1>","<html><body>hello</body></html1>").group()

In [29]: re.match(r"((d{3,4})-(d{6,8}))","0755-12345678").group()
In [30]: re.match(r"((d{3,4})-(d{6,8}))","0755-12345678").group(1)
In [31]: re.match(r"((d{3,4})-(d{6,8}))","0755-12345678").group(2)
In [32]: re.match(r"((d{3,4})-(d{6,8}))","0755-12345678").group(3)

In [34]: re.match(r"((d{3,4})-(d{6,8})) 2-3","0755-12345678 0755-12345678").group()

In [35]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8})","0755-12345678").group()
In [36]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8})","0755-12345678").group(1)
In [37]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8})","0755-12345678").group(2)
In [38]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8})","0755-12345678").group('quhao')
In [39]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8})","0755-12345678").group('zuoji')
In [40]: re.match(r"(?P<quhao>d{3,4})-(?P<zuoji>d{6,8}) (?P=quhao)-(?P=zuoji)","0755-12345678 07
    ...: 55-12345678").group()

In [41]: re.match(r"((?P<quhao>d{3,4})-(?P<zuoji>d{6,8})) (?P=quhao)-(?P=zuoji)","0755-12345678 
    ...: 0755-12345678").group()


---------------------------re模块高级函数--------------------------
In [42]: ret = re.search(r"d+", "阅读次数为 9999").group()

In [43]: re.search(r"d+", "阅读次数为 9999").group()
Out[43]: '9999'

In [46]: re.findall(r"d+", "python = 9999, c = 7890, c++ = 12345")
Out[46]: ['9999', '7890', '12345']

In [47]: re.sub(r"d+","998","python=997")
Out[47]: 'python=998'

In [48]: re.sub(r"d+","998","python=997 c=988")
Out[48]: 'python=998 c=998'

In [49]: re.sub(r"d+","998","python=997 c=988",1)
Out[49]: 'python=998 c=988'

In [52]: def func(matchobj):
    ...:     data = matchobj.group()
    ...:     str_data = str( int(data) + 1)
    ...:     return str_data
    ...: 

In [53]: re.sub(r"d+",func, "age=17")
Out[53]: 'age=18'

In [54]: data = """
    ...: <div>
    ...:         <p>岗位职责：</p>
    ...: <p>完成推荐算法、数据统计、接口、后台等服务器端相关工作</p>
    ...: <p><br></p>
    ...: <p>必备要求：</p>
    ...: <p>良好的自我驱动力和职业素养，工作积极主动、结果导向</p>
    ...: <p>&nbsp;<br></p>
    ...: <p>技术要求：</p>
    ...: <p>1、一年以上 Python 开发经验，掌握面向对象分析和设计，了解设计模式</p>
    ...: <p>2、掌握HTTP协议，熟悉MVC、MVVM等概念以及相关WEB开发框架</p>
    ...: <p>3、掌握关系数据库开发设计，掌握 SQL，熟练使用 MySQL/PostgreSQL 中的一种<br></p>
    ...: <p>4、掌握NoSQL、MQ，熟练使用对应技术解决方案</p>
    ...: <p>5、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js</p>
    ...: <p>&nbsp;<br></p>
    ...: <p>加分项：</p>
    ...: <p>大数据，数理统计，机器学习，sklearn，高性能，大并发。</p>
    ...: 
    ...:         </div>"""

In [55]: re.sub(r"<.*>","",data)
Out[55]: '

        















        '

In [56]: re.sub(r"<w+>","",data)
Out[56]: '

        岗位职责：</p>
完成推荐算法、数据统计、接口、后台等服务器端相关工作</p>
</p>
必备要求：</p>
良好的自我驱动力和职业素养，工作积极主动、结果导向</p>
&nbsp;</p>
技术要求：</p>
1、一年以上 Python 开发经验，掌握面向对象分析和设计，了解设计模式</p>
2、掌握HTTP协议，熟悉MVC、MVVM等概念以及相关WEB开发框架</p>
3、掌握关系数据库开发设计，掌握 SQL，熟练使用 MySQL/PostgreSQL 中的一种</p>
4、掌握NoSQL、MQ，熟练使用对应技术解决方案</p>
5、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js</p>
&nbsp;</p>
加分项：</p>
大数据，数理统计，机器学习，sklearn，高性能，大并发。</p>

        </div>'

In [57]: re.sub(r"</?w+>","",data)
Out[57]: '

        岗位职责：
完成推荐算法、数据统计、接口、后台等服务器端相关工作

必备要求：
良好的自我驱动力和职业素养，工作积极主动、结果导向
&nbsp;
技术要求：
1、一年以上 Python 开发经验，掌握面向对象分析和设计，了解设计模式
2、掌握HTTP协议，熟悉MVC、MVVM等概念以及相关WEB开发框架
3、掌握关系数据库开发设计，掌握 SQL，熟练使用 MySQL/PostgreSQL 中的一种
4、掌握NoSQL、MQ，熟练使用对应技术解决方案
5、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js
&nbsp;
加分项：
大数据，数理统计，机器学习，sklearn，高性能，大并发。

        '

In [58]: re.sub(r"</?w+>|
","",data)
Out[58]: '        岗位职责：完成推荐算法、数据统计、接口、后台等服务器端相关工作必备要求：良好的自我驱动力和职业素养，工作积极主动、结果导向&nbsp;技术要求：1、一年以上 Python 开发经验，掌握面向对象分析和设计，了解设计模式2、掌握HTTP协议，熟悉MVC、MVVM等概念以及相关WEB开发框架3、掌握关系数据库开发设计，掌握 SQL，熟练使用 MySQL/PostgreSQL 中的一种4、掌握NoSQL、MQ，熟练使用对应技术解决方案5、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js&nbsp;加分项：大数据，数理统计，机器学习，sklearn，高性能，大并发。        '

In [59]: re.sub(r"</?w+>|
|&nbsp","",data)
Out[59]: '        岗位职责：完成推荐算法、数据统计、接口、后台等服务器端相关工作必备要求：良好的自我驱动力和职业素养，工作积极主动、结果导向;技术要求：1、一年以上 Python 开发经验，掌握面向对象分析和设计，了解设计模式2、掌握HTTP协议，熟悉MVC、MVVM等概念以及相关WEB开发框架3、掌握关系数据库开发设计，掌握 SQL，熟练使用 MySQL/PostgreSQL 中的一种4、掌握NoSQL、MQ，熟练使用对应技术解决方案5、熟悉 Javascript/CSS/HTML5，JQuery、React、Vue.js;加分项：大数据，数理统计，机器学习，sklearn，高性能，大并发。        '

In [60]: re.split(r" ","age=18 name=tom")
Out[60]: ['age=18', 'name=tom']

In [61]: re.split(r" |=","age=18 name=tom")
Out[61]: ['age', '18', 'name', 'tom']

----------------------?号将正则转化为非贪婪模式(懒惰模式)-------------------------------

In [62]: re.match(r"(d+)(d?)","12345678").group()
Out[62]: '12345678'

In [63]: re.match(r"(d+)(d?)","12345678").group(1)
Out[63]: '12345678'

In [64]: re.match(r"(d+)(d?)","12345678").group(2)
Out[64]: ''

In [65]: re.match(r"(d+?)(d?)","12345678").group(2)
Out[65]: '2'

In [66]: re.match(r"(d+?)(d+)","12345678").group(2)
Out[66]: '2345678'

In [67]: re.match(r"(d+?)(d+)","12345678").group(1)
Out[67]: '1'

In [68]: re.match(r"(d+)(d+)","12345678").group(1)
Out[68]: '1234567'

In [69]: re.match(r"(d+)(d+)","12345678").group(2)
Out[69]: '8'
In [70]: url = """<img alt="丁叮c的直播" data-original="https://rpic.douyucdn.cn/live-cover/appCov
    ...: ers/2017/12/27/462253_20171227014914_big.jpg" src="https://rpic.douyucdn.cn/live-cover/ap
    ...: pCovers/2017/12/27/462253_20171227014914_big.jpg" width="283" height="163" style="display
    ...: : block;">"""

In [72]: re.search(r"http.*jpg",url).group()
Out[72]: 'https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg" src="https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg'

In [73]: re.search(r"http.*?jpg",url).group()
Out[73]: 'https://rpic.douyucdn.cn/live-cover/appCovers/2017/12/27/462253_20171227014914_big.jpg'



----------------r原生字符串 可以自动将其中的反斜线 进行转义----------------------
In [74]: path = "c:\a\b"

In [75]: print(path)
c:a

In [76]: path = "c:a
"

In [77]: print(path)
c:


In [78]: re.match("c:\a","c:\a\b\c").group()
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-78-c8bbf045c2be> in <module>()
----> 1 re.match("c:\a","c:\a\b\c").group()

AttributeError: 'NoneType' object has no attribute 'group'

In [79]: re.match("c:\\a","c:\a\b\c").group()
Out[79]: 'c:\a'

In [80]: re.match("c:\\a\\b\\c","c:\a\b\c").group()
Out[80]: 'c:\a\b\c'

In [81]: re.match(r"c:\a\b\c","c:\a\b\c").group()
Out[81]: 'c:\a\b\c'

In [82]: r"c:\a\b\c"
Out[82]: 'c:\\a\\b\\c'